Returns 1 if the psl timebase register is synchronized
with the core timebase register, 0 otherwise.
Users: https://github.com/ibm-capi/libcxl
+
+What: /sys/class/cxl/<card>/tunneled_ops_supported
+Date: May 2018
+Contact: linuxppc-dev@lists.ozlabs.org
+Description: read only
+ Returns 1 if tunneled operations are supported in capi mode,
+ 0 otherwise.
+Users: https://github.com/ibm-capi/libcxl
In this mode ``intel_pstate`` registers utilization update callbacks with the
CPU scheduler in order to run a P-state selection algorithm, either
-``powersave`` or ``performance``, depending on the ``scaling_cur_freq`` policy
+``powersave`` or ``performance``, depending on the ``scaling_governor`` policy
setting in ``sysfs``. The current CPU frequency information to be made
available from the ``scaling_cur_freq`` policy attribute in ``sysfs`` is
periodically updated by those utilization update callbacks too.
==================================
Depending on its configuration and the capabilities of the platform it runs on,
-the Linux kernel can support up to four system sleep states, includig
+the Linux kernel can support up to four system sleep states, including
hibernation and up to three variants of system suspend. The sleep states that
can be supported by the kernel are listed below.
--- /dev/null
+=================
+BPF documentation
+=================
+
+This directory contains documentation for the BPF (Berkeley Packet
+Filter) facility, with a focus on the extended BPF version (eBPF).
+
+This kernel side documentation is still work in progress. The main
+textual documentation is (for historical reasons) described in
+`Documentation/networking/filter.txt`_, which describe both classical
+and extended BPF instruction-set.
+The Cilium project also maintains a `BPF and XDP Reference Guide`_
+that goes into great technical depth about the BPF Architecture.
+
+The primary info for the bpf syscall is available in the `man-pages`_
+for `bpf(2)`_.
+
+
+
+Frequently asked questions (FAQ)
+================================
+
+Two sets of Questions and Answers (Q&A) are maintained.
+
+* QA for common questions about BPF see: bpf_design_QA_
+
+* QA for developers interacting with BPF subsystem: bpf_devel_QA_
+
+
+.. Links:
+.. _bpf_design_QA: bpf_design_QA.rst
+.. _bpf_devel_QA: bpf_devel_QA.rst
+.. _Documentation/networking/filter.txt: ../networking/filter.txt
+.. _man-pages: https://www.kernel.org/doc/man-pages/
+.. _bpf(2): http://man7.org/linux/man-pages/man2/bpf.2.html
+.. _BPF and XDP Reference Guide: http://cilium.readthedocs.io/en/latest/bpf/
--- /dev/null
+==============
+BPF Design Q&A
+==============
+
+BPF extensibility and applicability to networking, tracing, security
+in the linux kernel and several user space implementations of BPF
+virtual machine led to a number of misunderstanding on what BPF actually is.
+This short QA is an attempt to address that and outline a direction
+of where BPF is heading long term.
+
+.. contents::
+ :local:
+ :depth: 3
+
+Questions and Answers
+=====================
+
+Q: Is BPF a generic instruction set similar to x64 and arm64?
+-------------------------------------------------------------
+A: NO.
+
+Q: Is BPF a generic virtual machine ?
+-------------------------------------
+A: NO.
+
+BPF is generic instruction set *with* C calling convention.
+-----------------------------------------------------------
+
+Q: Why C calling convention was chosen?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A: Because BPF programs are designed to run in the linux kernel
+which is written in C, hence BPF defines instruction set compatible
+with two most used architectures x64 and arm64 (and takes into
+consideration important quirks of other architectures) and
+defines calling convention that is compatible with C calling
+convention of the linux kernel on those architectures.
+
+Q: can multiple return values be supported in the future?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: NO. BPF allows only register R0 to be used as return value.
+
+Q: can more than 5 function arguments be supported in the future?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: NO. BPF calling convention only allows registers R1-R5 to be used
+as arguments. BPF is not a standalone instruction set.
+(unlike x64 ISA that allows msft, cdecl and other conventions)
+
+Q: can BPF programs access instruction pointer or return address?
+-----------------------------------------------------------------
+A: NO.
+
+Q: can BPF programs access stack pointer ?
+------------------------------------------
+A: NO.
+
+Only frame pointer (register R10) is accessible.
+From compiler point of view it's necessary to have stack pointer.
+For example LLVM defines register R11 as stack pointer in its
+BPF backend, but it makes sure that generated code never uses it.
+
+Q: Does C-calling convention diminishes possible use cases?
+-----------------------------------------------------------
+A: YES.
+
+BPF design forces addition of major functionality in the form
+of kernel helper functions and kernel objects like BPF maps with
+seamless interoperability between them. It lets kernel call into
+BPF programs and programs call kernel helpers with zero overhead.
+As all of them were native C code. That is particularly the case
+for JITed BPF programs that are indistinguishable from
+native kernel C code.
+
+Q: Does it mean that 'innovative' extensions to BPF code are disallowed?
+------------------------------------------------------------------------
+A: Soft yes.
+
+At least for now until BPF core has support for
+bpf-to-bpf calls, indirect calls, loops, global variables,
+jump tables, read only sections and all other normal constructs
+that C code can produce.
+
+Q: Can loops be supported in a safe way?
+----------------------------------------
+A: It's not clear yet.
+
+BPF developers are trying to find a way to
+support bounded loops where the verifier can guarantee that
+the program terminates in less than 4096 instructions.
+
+Instruction level questions
+---------------------------
+
+Q: LD_ABS and LD_IND instructions vs C code
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Q: How come LD_ABS and LD_IND instruction are present in BPF whereas
+C code cannot express them and has to use builtin intrinsics?
+
+A: This is artifact of compatibility with classic BPF. Modern
+networking code in BPF performs better without them.
+See 'direct packet access'.
+
+Q: BPF instructions mapping not one-to-one to native CPU
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Q: It seems not all BPF instructions are one-to-one to native CPU.
+For example why BPF_JNE and other compare and jumps are not cpu-like?
+
+A: This was necessary to avoid introducing flags into ISA which are
+impossible to make generic and efficient across CPU architectures.
+
+Q: why BPF_DIV instruction doesn't map to x64 div?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: Because if we picked one-to-one relationship to x64 it would have made
+it more complicated to support on arm64 and other archs. Also it
+needs div-by-zero runtime check.
+
+Q: why there is no BPF_SDIV for signed divide operation?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: Because it would be rarely used. llvm errors in such case and
+prints a suggestion to use unsigned divide instead
+
+Q: Why BPF has implicit prologue and epilogue?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: Because architectures like sparc have register windows and in general
+there are enough subtle differences between architectures, so naive
+store return address into stack won't work. Another reason is BPF has
+to be safe from division by zero (and legacy exception path
+of LD_ABS insn). Those instructions need to invoke epilogue and
+return implicitly.
+
+Q: Why BPF_JLT and BPF_JLE instructions were not introduced in the beginning?
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+A: Because classic BPF didn't have them and BPF authors felt that compiler
+workaround would be acceptable. Turned out that programs lose performance
+due to lack of these compare instructions and they were added.
+These two instructions is a perfect example what kind of new BPF
+instructions are acceptable and can be added in the future.
+These two already had equivalent instructions in native CPUs.
+New instructions that don't have one-to-one mapping to HW instructions
+will not be accepted.
+
+Q: BPF 32-bit subregister requirements
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Q: BPF 32-bit subregisters have a requirement to zero upper 32-bits of BPF
+registers which makes BPF inefficient virtual machine for 32-bit
+CPU architectures and 32-bit HW accelerators. Can true 32-bit registers
+be added to BPF in the future?
+
+A: NO. The first thing to improve performance on 32-bit archs is to teach
+LLVM to generate code that uses 32-bit subregisters. Then second step
+is to teach verifier to mark operations where zero-ing upper bits
+is unnecessary. Then JITs can take advantage of those markings and
+drastically reduce size of generated code and improve performance.
+
+Q: Does BPF have a stable ABI?
+------------------------------
+A: YES. BPF instructions, arguments to BPF programs, set of helper
+functions and their arguments, recognized return codes are all part
+of ABI. However when tracing programs are using bpf_probe_read() helper
+to walk kernel internal datastructures and compile with kernel
+internal headers these accesses can and will break with newer
+kernels. The union bpf_attr -> kern_version is checked at load time
+to prevent accidentally loading kprobe-based bpf programs written
+for a different kernel. Networking programs don't do kern_version check.
+
+Q: How much stack space a BPF program uses?
+-------------------------------------------
+A: Currently all program types are limited to 512 bytes of stack
+space, but the verifier computes the actual amount of stack used
+and both interpreter and most JITed code consume necessary amount.
+
+Q: Can BPF be offloaded to HW?
+------------------------------
+A: YES. BPF HW offload is supported by NFP driver.
+
+Q: Does classic BPF interpreter still exist?
+--------------------------------------------
+A: NO. Classic BPF programs are converted into extend BPF instructions.
+
+Q: Can BPF call arbitrary kernel functions?
+-------------------------------------------
+A: NO. BPF programs can only call a set of helper functions which
+is defined for every program type.
+
+Q: Can BPF overwrite arbitrary kernel memory?
+---------------------------------------------
+A: NO.
+
+Tracing bpf programs can *read* arbitrary memory with bpf_probe_read()
+and bpf_probe_read_str() helpers. Networking programs cannot read
+arbitrary memory, since they don't have access to these helpers.
+Programs can never read or write arbitrary memory directly.
+
+Q: Can BPF overwrite arbitrary user memory?
+-------------------------------------------
+A: Sort-of.
+
+Tracing BPF programs can overwrite the user memory
+of the current task with bpf_probe_write_user(). Every time such
+program is loaded the kernel will print warning message, so
+this helper is only useful for experiments and prototypes.
+Tracing BPF programs are root only.
+
+Q: bpf_trace_printk() helper warning
+------------------------------------
+Q: When bpf_trace_printk() helper is used the kernel prints nasty
+warning message. Why is that?
+
+A: This is done to nudge program authors into better interfaces when
+programs need to pass data to user space. Like bpf_perf_event_output()
+can be used to efficiently stream data via perf ring buffer.
+BPF maps can be used for asynchronous data sharing between kernel
+and user space. bpf_trace_printk() should only be used for debugging.
+
+Q: New functionality via kernel modules?
+----------------------------------------
+Q: Can BPF functionality such as new program or map types, new
+helpers, etc be added out of kernel module code?
+
+A: NO.
+++ /dev/null
-BPF extensibility and applicability to networking, tracing, security
-in the linux kernel and several user space implementations of BPF
-virtual machine led to a number of misunderstanding on what BPF actually is.
-This short QA is an attempt to address that and outline a direction
-of where BPF is heading long term.
-
-Q: Is BPF a generic instruction set similar to x64 and arm64?
-A: NO.
-
-Q: Is BPF a generic virtual machine ?
-A: NO.
-
-BPF is generic instruction set _with_ C calling convention.
-
-Q: Why C calling convention was chosen?
-A: Because BPF programs are designed to run in the linux kernel
- which is written in C, hence BPF defines instruction set compatible
- with two most used architectures x64 and arm64 (and takes into
- consideration important quirks of other architectures) and
- defines calling convention that is compatible with C calling
- convention of the linux kernel on those architectures.
-
-Q: can multiple return values be supported in the future?
-A: NO. BPF allows only register R0 to be used as return value.
-
-Q: can more than 5 function arguments be supported in the future?
-A: NO. BPF calling convention only allows registers R1-R5 to be used
- as arguments. BPF is not a standalone instruction set.
- (unlike x64 ISA that allows msft, cdecl and other conventions)
-
-Q: can BPF programs access instruction pointer or return address?
-A: NO.
-
-Q: can BPF programs access stack pointer ?
-A: NO. Only frame pointer (register R10) is accessible.
- From compiler point of view it's necessary to have stack pointer.
- For example LLVM defines register R11 as stack pointer in its
- BPF backend, but it makes sure that generated code never uses it.
-
-Q: Does C-calling convention diminishes possible use cases?
-A: YES. BPF design forces addition of major functionality in the form
- of kernel helper functions and kernel objects like BPF maps with
- seamless interoperability between them. It lets kernel call into
- BPF programs and programs call kernel helpers with zero overhead.
- As all of them were native C code. That is particularly the case
- for JITed BPF programs that are indistinguishable from
- native kernel C code.
-
-Q: Does it mean that 'innovative' extensions to BPF code are disallowed?
-A: Soft yes. At least for now until BPF core has support for
- bpf-to-bpf calls, indirect calls, loops, global variables,
- jump tables, read only sections and all other normal constructs
- that C code can produce.
-
-Q: Can loops be supported in a safe way?
-A: It's not clear yet. BPF developers are trying to find a way to
- support bounded loops where the verifier can guarantee that
- the program terminates in less than 4096 instructions.
-
-Q: How come LD_ABS and LD_IND instruction are present in BPF whereas
- C code cannot express them and has to use builtin intrinsics?
-A: This is artifact of compatibility with classic BPF. Modern
- networking code in BPF performs better without them.
- See 'direct packet access'.
-
-Q: It seems not all BPF instructions are one-to-one to native CPU.
- For example why BPF_JNE and other compare and jumps are not cpu-like?
-A: This was necessary to avoid introducing flags into ISA which are
- impossible to make generic and efficient across CPU architectures.
-
-Q: why BPF_DIV instruction doesn't map to x64 div?
-A: Because if we picked one-to-one relationship to x64 it would have made
- it more complicated to support on arm64 and other archs. Also it
- needs div-by-zero runtime check.
-
-Q: why there is no BPF_SDIV for signed divide operation?
-A: Because it would be rarely used. llvm errors in such case and
- prints a suggestion to use unsigned divide instead
-
-Q: Why BPF has implicit prologue and epilogue?
-A: Because architectures like sparc have register windows and in general
- there are enough subtle differences between architectures, so naive
- store return address into stack won't work. Another reason is BPF has
- to be safe from division by zero (and legacy exception path
- of LD_ABS insn). Those instructions need to invoke epilogue and
- return implicitly.
-
-Q: Why BPF_JLT and BPF_JLE instructions were not introduced in the beginning?
-A: Because classic BPF didn't have them and BPF authors felt that compiler
- workaround would be acceptable. Turned out that programs lose performance
- due to lack of these compare instructions and they were added.
- These two instructions is a perfect example what kind of new BPF
- instructions are acceptable and can be added in the future.
- These two already had equivalent instructions in native CPUs.
- New instructions that don't have one-to-one mapping to HW instructions
- will not be accepted.
-
-Q: BPF 32-bit subregisters have a requirement to zero upper 32-bits of BPF
- registers which makes BPF inefficient virtual machine for 32-bit
- CPU architectures and 32-bit HW accelerators. Can true 32-bit registers
- be added to BPF in the future?
-A: NO. The first thing to improve performance on 32-bit archs is to teach
- LLVM to generate code that uses 32-bit subregisters. Then second step
- is to teach verifier to mark operations where zero-ing upper bits
- is unnecessary. Then JITs can take advantage of those markings and
- drastically reduce size of generated code and improve performance.
-
-Q: Does BPF have a stable ABI?
-A: YES. BPF instructions, arguments to BPF programs, set of helper
- functions and their arguments, recognized return codes are all part
- of ABI. However when tracing programs are using bpf_probe_read() helper
- to walk kernel internal datastructures and compile with kernel
- internal headers these accesses can and will break with newer
- kernels. The union bpf_attr -> kern_version is checked at load time
- to prevent accidentally loading kprobe-based bpf programs written
- for a different kernel. Networking programs don't do kern_version check.
-
-Q: How much stack space a BPF program uses?
-A: Currently all program types are limited to 512 bytes of stack
- space, but the verifier computes the actual amount of stack used
- and both interpreter and most JITed code consume necessary amount.
-
-Q: Can BPF be offloaded to HW?
-A: YES. BPF HW offload is supported by NFP driver.
-
-Q: Does classic BPF interpreter still exist?
-A: NO. Classic BPF programs are converted into extend BPF instructions.
-
-Q: Can BPF call arbitrary kernel functions?
-A: NO. BPF programs can only call a set of helper functions which
- is defined for every program type.
-
-Q: Can BPF overwrite arbitrary kernel memory?
-A: NO. Tracing bpf programs can _read_ arbitrary memory with bpf_probe_read()
- and bpf_probe_read_str() helpers. Networking programs cannot read
- arbitrary memory, since they don't have access to these helpers.
- Programs can never read or write arbitrary memory directly.
-
-Q: Can BPF overwrite arbitrary user memory?
-A: Sort-of. Tracing BPF programs can overwrite the user memory
- of the current task with bpf_probe_write_user(). Every time such
- program is loaded the kernel will print warning message, so
- this helper is only useful for experiments and prototypes.
- Tracing BPF programs are root only.
-
-Q: When bpf_trace_printk() helper is used the kernel prints nasty
- warning message. Why is that?
-A: This is done to nudge program authors into better interfaces when
- programs need to pass data to user space. Like bpf_perf_event_output()
- can be used to efficiently stream data via perf ring buffer.
- BPF maps can be used for asynchronous data sharing between kernel
- and user space. bpf_trace_printk() should only be used for debugging.
-
-Q: Can BPF functionality such as new program or map types, new
- helpers, etc be added out of kernel module code?
-A: NO.
--- /dev/null
+=================================
+HOWTO interact with BPF subsystem
+=================================
+
+This document provides information for the BPF subsystem about various
+workflows related to reporting bugs, submitting patches, and queueing
+patches for stable kernels.
+
+For general information about submitting patches, please refer to
+`Documentation/process/`_. This document only describes additional specifics
+related to BPF.
+
+.. contents::
+ :local:
+ :depth: 2
+
+Reporting bugs
+==============
+
+Q: How do I report bugs for BPF kernel code?
+--------------------------------------------
+A: Since all BPF kernel development as well as bpftool and iproute2 BPF
+loader development happens through the netdev kernel mailing list,
+please report any found issues around BPF to the following mailing
+list:
+
+ netdev@vger.kernel.org
+
+This may also include issues related to XDP, BPF tracing, etc.
+
+Given netdev has a high volume of traffic, please also add the BPF
+maintainers to Cc (from kernel MAINTAINERS_ file):
+
+* Alexei Starovoitov <ast@kernel.org>
+* Daniel Borkmann <daniel@iogearbox.net>
+
+In case a buggy commit has already been identified, make sure to keep
+the actual commit authors in Cc as well for the report. They can
+typically be identified through the kernel's git tree.
+
+**Please do NOT report BPF issues to bugzilla.kernel.org since it
+is a guarantee that the reported issue will be overlooked.**
+
+Submitting patches
+==================
+
+Q: To which mailing list do I need to submit my BPF patches?
+------------------------------------------------------------
+A: Please submit your BPF patches to the netdev kernel mailing list:
+
+ netdev@vger.kernel.org
+
+Historically, BPF came out of networking and has always been maintained
+by the kernel networking community. Although these days BPF touches
+many other subsystems as well, the patches are still routed mainly
+through the networking community.
+
+In case your patch has changes in various different subsystems (e.g.
+tracing, security, etc), make sure to Cc the related kernel mailing
+lists and maintainers from there as well, so they are able to review
+the changes and provide their Acked-by's to the patches.
+
+Q: Where can I find patches currently under discussion for BPF subsystem?
+-------------------------------------------------------------------------
+A: All patches that are Cc'ed to netdev are queued for review under netdev
+patchwork project:
+
+ http://patchwork.ozlabs.org/project/netdev/list/
+
+Those patches which target BPF, are assigned to a 'bpf' delegate for
+further processing from BPF maintainers. The current queue with
+patches under review can be found at:
+
+ https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
+
+Once the patches have been reviewed by the BPF community as a whole
+and approved by the BPF maintainers, their status in patchwork will be
+changed to 'Accepted' and the submitter will be notified by mail. This
+means that the patches look good from a BPF perspective and have been
+applied to one of the two BPF kernel trees.
+
+In case feedback from the community requires a respin of the patches,
+their status in patchwork will be set to 'Changes Requested', and purged
+from the current review queue. Likewise for cases where patches would
+get rejected or are not applicable to the BPF trees (but assigned to
+the 'bpf' delegate).
+
+Q: How do the changes make their way into Linux?
+------------------------------------------------
+A: There are two BPF kernel trees (git repositories). Once patches have
+been accepted by the BPF maintainers, they will be applied to one
+of the two BPF trees:
+
+ * https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/
+ * https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/
+
+The bpf tree itself is for fixes only, whereas bpf-next for features,
+cleanups or other kind of improvements ("next-like" content). This is
+analogous to net and net-next trees for networking. Both bpf and
+bpf-next will only have a master branch in order to simplify against
+which branch patches should get rebased to.
+
+Accumulated BPF patches in the bpf tree will regularly get pulled
+into the net kernel tree. Likewise, accumulated BPF patches accepted
+into the bpf-next tree will make their way into net-next tree. net and
+net-next are both run by David S. Miller. From there, they will go
+into the kernel mainline tree run by Linus Torvalds. To read up on the
+process of net and net-next being merged into the mainline tree, see
+the `netdev FAQ`_ under:
+
+ `Documentation/networking/netdev-FAQ.txt`_
+
+Occasionally, to prevent merge conflicts, we might send pull requests
+to other trees (e.g. tracing) with a small subset of the patches, but
+net and net-next are always the main trees targeted for integration.
+
+The pull requests will contain a high-level summary of the accumulated
+patches and can be searched on netdev kernel mailing list through the
+following subject lines (``yyyy-mm-dd`` is the date of the pull
+request)::
+
+ pull-request: bpf yyyy-mm-dd
+ pull-request: bpf-next yyyy-mm-dd
+
+Q: How do I indicate which tree (bpf vs. bpf-next) my patch should be applied to?
+---------------------------------------------------------------------------------
+
+A: The process is the very same as described in the `netdev FAQ`_, so
+please read up on it. The subject line must indicate whether the
+patch is a fix or rather "next-like" content in order to let the
+maintainers know whether it is targeted at bpf or bpf-next.
+
+For fixes eventually landing in bpf -> net tree, the subject must
+look like::
+
+ git format-patch --subject-prefix='PATCH bpf' start..finish
+
+For features/improvements/etc that should eventually land in
+bpf-next -> net-next, the subject must look like::
+
+ git format-patch --subject-prefix='PATCH bpf-next' start..finish
+
+If unsure whether the patch or patch series should go into bpf
+or net directly, or bpf-next or net-next directly, it is not a
+problem either if the subject line says net or net-next as target.
+It is eventually up to the maintainers to do the delegation of
+the patches.
+
+If it is clear that patches should go into bpf or bpf-next tree,
+please make sure to rebase the patches against those trees in
+order to reduce potential conflicts.
+
+In case the patch or patch series has to be reworked and sent out
+again in a second or later revision, it is also required to add a
+version number (``v2``, ``v3``, ...) into the subject prefix::
+
+ git format-patch --subject-prefix='PATCH net-next v2' start..finish
+
+When changes have been requested to the patch series, always send the
+whole patch series again with the feedback incorporated (never send
+individual diffs on top of the old series).
+
+Q: What does it mean when a patch gets applied to bpf or bpf-next tree?
+-----------------------------------------------------------------------
+A: It means that the patch looks good for mainline inclusion from
+a BPF point of view.
+
+Be aware that this is not a final verdict that the patch will
+automatically get accepted into net or net-next trees eventually:
+
+On the netdev kernel mailing list reviews can come in at any point
+in time. If discussions around a patch conclude that they cannot
+get included as-is, we will either apply a follow-up fix or drop
+them from the trees entirely. Therefore, we also reserve to rebase
+the trees when deemed necessary. After all, the purpose of the tree
+is to:
+
+i) accumulate and stage BPF patches for integration into trees
+ like net and net-next, and
+
+ii) run extensive BPF test suite and
+ workloads on the patches before they make their way any further.
+
+Once the BPF pull request was accepted by David S. Miller, then
+the patches end up in net or net-next tree, respectively, and
+make their way from there further into mainline. Again, see the
+`netdev FAQ`_ for additional information e.g. on how often they are
+merged to mainline.
+
+Q: How long do I need to wait for feedback on my BPF patches?
+-------------------------------------------------------------
+A: We try to keep the latency low. The usual time to feedback will
+be around 2 or 3 business days. It may vary depending on the
+complexity of changes and current patch load.
+
+Q: How often do you send pull requests to major kernel trees like net or net-next?
+----------------------------------------------------------------------------------
+
+A: Pull requests will be sent out rather often in order to not
+accumulate too many patches in bpf or bpf-next.
+
+As a rule of thumb, expect pull requests for each tree regularly
+at the end of the week. In some cases pull requests could additionally
+come also in the middle of the week depending on the current patch
+load or urgency.
+
+Q: Are patches applied to bpf-next when the merge window is open?
+-----------------------------------------------------------------
+A: For the time when the merge window is open, bpf-next will not be
+processed. This is roughly analogous to net-next patch processing,
+so feel free to read up on the `netdev FAQ`_ about further details.
+
+During those two weeks of merge window, we might ask you to resend
+your patch series once bpf-next is open again. Once Linus released
+a ``v*-rc1`` after the merge window, we continue processing of bpf-next.
+
+For non-subscribers to kernel mailing lists, there is also a status
+page run by David S. Miller on net-next that provides guidance:
+
+ http://vger.kernel.org/~davem/net-next.html
+
+Q: Verifier changes and test cases
+----------------------------------
+Q: I made a BPF verifier change, do I need to add test cases for
+BPF kernel selftests_?
+
+A: If the patch has changes to the behavior of the verifier, then yes,
+it is absolutely necessary to add test cases to the BPF kernel
+selftests_ suite. If they are not present and we think they are
+needed, then we might ask for them before accepting any changes.
+
+In particular, test_verifier.c is tracking a high number of BPF test
+cases, including a lot of corner cases that LLVM BPF back end may
+generate out of the restricted C code. Thus, adding test cases is
+absolutely crucial to make sure future changes do not accidentally
+affect prior use-cases. Thus, treat those test cases as: verifier
+behavior that is not tracked in test_verifier.c could potentially
+be subject to change.
+
+Q: samples/bpf preference vs selftests?
+---------------------------------------
+Q: When should I add code to `samples/bpf/`_ and when to BPF kernel
+selftests_ ?
+
+A: In general, we prefer additions to BPF kernel selftests_ rather than
+`samples/bpf/`_. The rationale is very simple: kernel selftests are
+regularly run by various bots to test for kernel regressions.
+
+The more test cases we add to BPF selftests, the better the coverage
+and the less likely it is that those could accidentally break. It is
+not that BPF kernel selftests cannot demo how a specific feature can
+be used.
+
+That said, `samples/bpf/`_ may be a good place for people to get started,
+so it might be advisable that simple demos of features could go into
+`samples/bpf/`_, but advanced functional and corner-case testing rather
+into kernel selftests.
+
+If your sample looks like a test case, then go for BPF kernel selftests
+instead!
+
+Q: When should I add code to the bpftool?
+-----------------------------------------
+A: The main purpose of bpftool (under tools/bpf/bpftool/) is to provide
+a central user space tool for debugging and introspection of BPF programs
+and maps that are active in the kernel. If UAPI changes related to BPF
+enable for dumping additional information of programs or maps, then
+bpftool should be extended as well to support dumping them.
+
+Q: When should I add code to iproute2's BPF loader?
+---------------------------------------------------
+A: For UAPI changes related to the XDP or tc layer (e.g. ``cls_bpf``),
+the convention is that those control-path related changes are added to
+iproute2's BPF loader as well from user space side. This is not only
+useful to have UAPI changes properly designed to be usable, but also
+to make those changes available to a wider user base of major
+downstream distributions.
+
+Q: Do you accept patches as well for iproute2's BPF loader?
+-----------------------------------------------------------
+A: Patches for the iproute2's BPF loader have to be sent to:
+
+ netdev@vger.kernel.org
+
+While those patches are not processed by the BPF kernel maintainers,
+please keep them in Cc as well, so they can be reviewed.
+
+The official git repository for iproute2 is run by Stephen Hemminger
+and can be found at:
+
+ https://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git/
+
+The patches need to have a subject prefix of '``[PATCH iproute2
+master]``' or '``[PATCH iproute2 net-next]``'. '``master``' or
+'``net-next``' describes the target branch where the patch should be
+applied to. Meaning, if kernel changes went into the net-next kernel
+tree, then the related iproute2 changes need to go into the iproute2
+net-next branch, otherwise they can be targeted at master branch. The
+iproute2 net-next branch will get merged into the master branch after
+the current iproute2 version from master has been released.
+
+Like BPF, the patches end up in patchwork under the netdev project and
+are delegated to 'shemminger' for further processing:
+
+ http://patchwork.ozlabs.org/project/netdev/list/?delegate=389
+
+Q: What is the minimum requirement before I submit my BPF patches?
+------------------------------------------------------------------
+A: When submitting patches, always take the time and properly test your
+patches *prior* to submission. Never rush them! If maintainers find
+that your patches have not been properly tested, it is a good way to
+get them grumpy. Testing patch submissions is a hard requirement!
+
+Note, fixes that go to bpf tree *must* have a ``Fixes:`` tag included.
+The same applies to fixes that target bpf-next, where the affected
+commit is in net-next (or in some cases bpf-next). The ``Fixes:`` tag is
+crucial in order to identify follow-up commits and tremendously helps
+for people having to do backporting, so it is a must have!
+
+We also don't accept patches with an empty commit message. Take your
+time and properly write up a high quality commit message, it is
+essential!
+
+Think about it this way: other developers looking at your code a month
+from now need to understand *why* a certain change has been done that
+way, and whether there have been flaws in the analysis or assumptions
+that the original author did. Thus providing a proper rationale and
+describing the use-case for the changes is a must.
+
+Patch submissions with >1 patch must have a cover letter which includes
+a high level description of the series. This high level summary will
+then be placed into the merge commit by the BPF maintainers such that
+it is also accessible from the git log for future reference.
+
+Q: Features changing BPF JIT and/or LLVM
+----------------------------------------
+Q: What do I need to consider when adding a new instruction or feature
+that would require BPF JIT and/or LLVM integration as well?
+
+A: We try hard to keep all BPF JITs up to date such that the same user
+experience can be guaranteed when running BPF programs on different
+architectures without having the program punt to the less efficient
+interpreter in case the in-kernel BPF JIT is enabled.
+
+If you are unable to implement or test the required JIT changes for
+certain architectures, please work together with the related BPF JIT
+developers in order to get the feature implemented in a timely manner.
+Please refer to the git log (``arch/*/net/``) to locate the necessary
+people for helping out.
+
+Also always make sure to add BPF test cases (e.g. test_bpf.c and
+test_verifier.c) for new instructions, so that they can receive
+broad test coverage and help run-time testing the various BPF JITs.
+
+In case of new BPF instructions, once the changes have been accepted
+into the Linux kernel, please implement support into LLVM's BPF back
+end. See LLVM_ section below for further information.
+
+Stable submission
+=================
+
+Q: I need a specific BPF commit in stable kernels. What should I do?
+--------------------------------------------------------------------
+A: In case you need a specific fix in stable kernels, first check whether
+the commit has already been applied in the related ``linux-*.y`` branches:
+
+ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git/
+
+If not the case, then drop an email to the BPF maintainers with the
+netdev kernel mailing list in Cc and ask for the fix to be queued up:
+
+ netdev@vger.kernel.org
+
+The process in general is the same as on netdev itself, see also the
+`netdev FAQ`_ document.
+
+Q: Do you also backport to kernels not currently maintained as stable?
+----------------------------------------------------------------------
+A: No. If you need a specific BPF commit in kernels that are currently not
+maintained by the stable maintainers, then you are on your own.
+
+The current stable and longterm stable kernels are all listed here:
+
+ https://www.kernel.org/
+
+Q: The BPF patch I am about to submit needs to go to stable as well
+-------------------------------------------------------------------
+What should I do?
+
+A: The same rules apply as with netdev patch submissions in general, see
+`netdev FAQ`_ under:
+
+ `Documentation/networking/netdev-FAQ.txt`_
+
+Never add "``Cc: stable@vger.kernel.org``" to the patch description, but
+ask the BPF maintainers to queue the patches instead. This can be done
+with a note, for example, under the ``---`` part of the patch which does
+not go into the git log. Alternatively, this can be done as a simple
+request by mail instead.
+
+Q: Queue stable patches
+-----------------------
+Q: Where do I find currently queued BPF patches that will be submitted
+to stable?
+
+A: Once patches that fix critical bugs got applied into the bpf tree, they
+are queued up for stable submission under:
+
+ http://patchwork.ozlabs.org/bundle/bpf/stable/?state=*
+
+They will be on hold there at minimum until the related commit made its
+way into the mainline kernel tree.
+
+After having been under broader exposure, the queued patches will be
+submitted by the BPF maintainers to the stable maintainers.
+
+Testing patches
+===============
+
+Q: How to run BPF selftests
+---------------------------
+A: After you have booted into the newly compiled kernel, navigate to
+the BPF selftests_ suite in order to test BPF functionality (current
+working directory points to the root of the cloned git tree)::
+
+ $ cd tools/testing/selftests/bpf/
+ $ make
+
+To run the verifier tests::
+
+ $ sudo ./test_verifier
+
+The verifier tests print out all the current checks being
+performed. The summary at the end of running all tests will dump
+information of test successes and failures::
+
+ Summary: 418 PASSED, 0 FAILED
+
+In order to run through all BPF selftests, the following command is
+needed::
+
+ $ sudo make run_tests
+
+See the kernels selftest `Documentation/dev-tools/kselftest.rst`_
+document for further documentation.
+
+Q: Which BPF kernel selftests version should I run my kernel against?
+---------------------------------------------------------------------
+A: If you run a kernel ``xyz``, then always run the BPF kernel selftests
+from that kernel ``xyz`` as well. Do not expect that the BPF selftest
+from the latest mainline tree will pass all the time.
+
+In particular, test_bpf.c and test_verifier.c have a large number of
+test cases and are constantly updated with new BPF test sequences, or
+existing ones are adapted to verifier changes e.g. due to verifier
+becoming smarter and being able to better track certain things.
+
+LLVM
+====
+
+Q: Where do I find LLVM with BPF support?
+-----------------------------------------
+A: The BPF back end for LLVM is upstream in LLVM since version 3.7.1.
+
+All major distributions these days ship LLVM with BPF back end enabled,
+so for the majority of use-cases it is not required to compile LLVM by
+hand anymore, just install the distribution provided package.
+
+LLVM's static compiler lists the supported targets through
+``llc --version``, make sure BPF targets are listed. Example::
+
+ $ llc --version
+ LLVM (http://llvm.org/):
+ LLVM version 6.0.0svn
+ Optimized build.
+ Default target: x86_64-unknown-linux-gnu
+ Host CPU: skylake
+
+ Registered Targets:
+ bpf - BPF (host endian)
+ bpfeb - BPF (big endian)
+ bpfel - BPF (little endian)
+ x86 - 32-bit X86: Pentium-Pro and above
+ x86-64 - 64-bit X86: EM64T and AMD64
+
+For developers in order to utilize the latest features added to LLVM's
+BPF back end, it is advisable to run the latest LLVM releases. Support
+for new BPF kernel features such as additions to the BPF instruction
+set are often developed together.
+
+All LLVM releases can be found at: http://releases.llvm.org/
+
+Q: Got it, so how do I build LLVM manually anyway?
+--------------------------------------------------
+A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have
+that set up, proceed with building the latest LLVM and clang version
+from the git repositories::
+
+ $ git clone http://llvm.org/git/llvm.git
+ $ cd llvm/tools
+ $ git clone --depth 1 http://llvm.org/git/clang.git
+ $ cd ..; mkdir build; cd build
+ $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
+ -DBUILD_SHARED_LIBS=OFF \
+ -DCMAKE_BUILD_TYPE=Release \
+ -DLLVM_BUILD_RUNTIME=OFF
+ $ make -j $(getconf _NPROCESSORS_ONLN)
+
+The built binaries can then be found in the build/bin/ directory, where
+you can point the PATH variable to.
+
+Q: Reporting LLVM BPF issues
+----------------------------
+Q: Should I notify BPF kernel maintainers about issues in LLVM's BPF code
+generation back end or about LLVM generated code that the verifier
+refuses to accept?
+
+A: Yes, please do!
+
+LLVM's BPF back end is a key piece of the whole BPF
+infrastructure and it ties deeply into verification of programs from the
+kernel side. Therefore, any issues on either side need to be investigated
+and fixed whenever necessary.
+
+Therefore, please make sure to bring them up at netdev kernel mailing
+list and Cc BPF maintainers for LLVM and kernel bits:
+
+* Yonghong Song <yhs@fb.com>
+* Alexei Starovoitov <ast@kernel.org>
+* Daniel Borkmann <daniel@iogearbox.net>
+
+LLVM also has an issue tracker where BPF related bugs can be found:
+
+ https://bugs.llvm.org/buglist.cgi?quicksearch=bpf
+
+However, it is better to reach out through mailing lists with having
+maintainers in Cc.
+
+Q: New BPF instruction for kernel and LLVM
+------------------------------------------
+Q: I have added a new BPF instruction to the kernel, how can I integrate
+it into LLVM?
+
+A: LLVM has a ``-mcpu`` selector for the BPF back end in order to allow
+the selection of BPF instruction set extensions. By default the
+``generic`` processor target is used, which is the base instruction set
+(v1) of BPF.
+
+LLVM has an option to select ``-mcpu=probe`` where it will probe the host
+kernel for supported BPF instruction set extensions and selects the
+optimal set automatically.
+
+For cross-compilation, a specific version can be select manually as well ::
+
+ $ llc -march bpf -mcpu=help
+ Available CPUs for this target:
+
+ generic - Select the generic processor.
+ probe - Select the probe processor.
+ v1 - Select the v1 processor.
+ v2 - Select the v2 processor.
+ [...]
+
+Newly added BPF instructions to the Linux kernel need to follow the same
+scheme, bump the instruction set version and implement probing for the
+extensions such that ``-mcpu=probe`` users can benefit from the
+optimization transparently when upgrading their kernels.
+
+If you are unable to implement support for the newly added BPF instruction
+please reach out to BPF developers for help.
+
+By the way, the BPF kernel selftests run with ``-mcpu=probe`` for better
+test coverage.
+
+Q: clang flag for target bpf?
+-----------------------------
+Q: In some cases clang flag ``-target bpf`` is used but in other cases the
+default clang target, which matches the underlying architecture, is used.
+What is the difference and when I should use which?
+
+A: Although LLVM IR generation and optimization try to stay architecture
+independent, ``-target <arch>`` still has some impact on generated code:
+
+- BPF program may recursively include header file(s) with file scope
+ inline assembly codes. The default target can handle this well,
+ while ``bpf`` target may fail if bpf backend assembler does not
+ understand these assembly codes, which is true in most cases.
+
+- When compiled without ``-g``, additional elf sections, e.g.,
+ .eh_frame and .rela.eh_frame, may be present in the object file
+ with default target, but not with ``bpf`` target.
+
+- The default target may turn a C switch statement into a switch table
+ lookup and jump operation. Since the switch table is placed
+ in the global readonly section, the bpf program will fail to load.
+ The bpf target does not support switch table optimization.
+ The clang option ``-fno-jump-tables`` can be used to disable
+ switch table generation.
+
+- For clang ``-target bpf``, it is guaranteed that pointer or long /
+ unsigned long types will always have a width of 64 bit, no matter
+ whether underlying clang binary or default target (or kernel) is
+ 32 bit. However, when native clang target is used, then it will
+ compile these types based on the underlying architecture's conventions,
+ meaning in case of 32 bit architecture, pointer or long / unsigned
+ long types e.g. in BPF context structure will have width of 32 bit
+ while the BPF LLVM back end still operates in 64 bit. The native
+ target is mostly needed in tracing for the case of walking ``pt_regs``
+ or other kernel structures where CPU's register width matters.
+ Otherwise, ``clang -target bpf`` is generally recommended.
+
+You should use default target when:
+
+- Your program includes a header file, e.g., ptrace.h, which eventually
+ pulls in some header files containing file scope host assembly codes.
+
+- You can add ``-fno-jump-tables`` to work around the switch table issue.
+
+Otherwise, you can use ``bpf`` target. Additionally, you *must* use bpf target
+when:
+
+- Your program uses data structures with pointer or long / unsigned long
+ types that interface with BPF helpers or context data structures. Access
+ into these structures is verified by the BPF verifier and may result
+ in verification failures if the native architecture is not aligned with
+ the BPF architecture, e.g. 64-bit. An example of this is
+ BPF_PROG_TYPE_SK_MSG require ``-target bpf``
+
+
+.. Links
+.. _Documentation/process/: https://www.kernel.org/doc/html/latest/process/
+.. _MAINTAINERS: ../../MAINTAINERS
+.. _Documentation/networking/netdev-FAQ.txt: ../networking/netdev-FAQ.txt
+.. _netdev FAQ: ../networking/netdev-FAQ.txt
+.. _samples/bpf/: ../../samples/bpf/
+.. _selftests: ../../tools/testing/selftests/bpf/
+.. _Documentation/dev-tools/kselftest.rst:
+ https://www.kernel.org/doc/html/latest/dev-tools/kselftest.html
+
+Happy BPF hacking!
+++ /dev/null
-This document provides information for the BPF subsystem about various
-workflows related to reporting bugs, submitting patches, and queueing
-patches for stable kernels.
-
-For general information about submitting patches, please refer to
-Documentation/process/. This document only describes additional specifics
-related to BPF.
-
-Reporting bugs:
----------------
-
-Q: How do I report bugs for BPF kernel code?
-
-A: Since all BPF kernel development as well as bpftool and iproute2 BPF
- loader development happens through the netdev kernel mailing list,
- please report any found issues around BPF to the following mailing
- list:
-
- netdev@vger.kernel.org
-
- This may also include issues related to XDP, BPF tracing, etc.
-
- Given netdev has a high volume of traffic, please also add the BPF
- maintainers to Cc (from kernel MAINTAINERS file):
-
- Alexei Starovoitov <ast@kernel.org>
- Daniel Borkmann <daniel@iogearbox.net>
-
- In case a buggy commit has already been identified, make sure to keep
- the actual commit authors in Cc as well for the report. They can
- typically be identified through the kernel's git tree.
-
- Please do *not* report BPF issues to bugzilla.kernel.org since it
- is a guarantee that the reported issue will be overlooked.
-
-Submitting patches:
--------------------
-
-Q: To which mailing list do I need to submit my BPF patches?
-
-A: Please submit your BPF patches to the netdev kernel mailing list:
-
- netdev@vger.kernel.org
-
- Historically, BPF came out of networking and has always been maintained
- by the kernel networking community. Although these days BPF touches
- many other subsystems as well, the patches are still routed mainly
- through the networking community.
-
- In case your patch has changes in various different subsystems (e.g.
- tracing, security, etc), make sure to Cc the related kernel mailing
- lists and maintainers from there as well, so they are able to review
- the changes and provide their Acked-by's to the patches.
-
-Q: Where can I find patches currently under discussion for BPF subsystem?
-
-A: All patches that are Cc'ed to netdev are queued for review under netdev
- patchwork project:
-
- http://patchwork.ozlabs.org/project/netdev/list/
-
- Those patches which target BPF, are assigned to a 'bpf' delegate for
- further processing from BPF maintainers. The current queue with
- patches under review can be found at:
-
- https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
-
- Once the patches have been reviewed by the BPF community as a whole
- and approved by the BPF maintainers, their status in patchwork will be
- changed to 'Accepted' and the submitter will be notified by mail. This
- means that the patches look good from a BPF perspective and have been
- applied to one of the two BPF kernel trees.
-
- In case feedback from the community requires a respin of the patches,
- their status in patchwork will be set to 'Changes Requested', and purged
- from the current review queue. Likewise for cases where patches would
- get rejected or are not applicable to the BPF trees (but assigned to
- the 'bpf' delegate).
-
-Q: How do the changes make their way into Linux?
-
-A: There are two BPF kernel trees (git repositories). Once patches have
- been accepted by the BPF maintainers, they will be applied to one
- of the two BPF trees:
-
- https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/
- https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/
-
- The bpf tree itself is for fixes only, whereas bpf-next for features,
- cleanups or other kind of improvements ("next-like" content). This is
- analogous to net and net-next trees for networking. Both bpf and
- bpf-next will only have a master branch in order to simplify against
- which branch patches should get rebased to.
-
- Accumulated BPF patches in the bpf tree will regularly get pulled
- into the net kernel tree. Likewise, accumulated BPF patches accepted
- into the bpf-next tree will make their way into net-next tree. net and
- net-next are both run by David S. Miller. From there, they will go
- into the kernel mainline tree run by Linus Torvalds. To read up on the
- process of net and net-next being merged into the mainline tree, see
- the netdev FAQ under:
-
- Documentation/networking/netdev-FAQ.txt
-
- Occasionally, to prevent merge conflicts, we might send pull requests
- to other trees (e.g. tracing) with a small subset of the patches, but
- net and net-next are always the main trees targeted for integration.
-
- The pull requests will contain a high-level summary of the accumulated
- patches and can be searched on netdev kernel mailing list through the
- following subject lines (yyyy-mm-dd is the date of the pull request):
-
- pull-request: bpf yyyy-mm-dd
- pull-request: bpf-next yyyy-mm-dd
-
-Q: How do I indicate which tree (bpf vs. bpf-next) my patch should be
- applied to?
-
-A: The process is the very same as described in the netdev FAQ, so
- please read up on it. The subject line must indicate whether the
- patch is a fix or rather "next-like" content in order to let the
- maintainers know whether it is targeted at bpf or bpf-next.
-
- For fixes eventually landing in bpf -> net tree, the subject must
- look like:
-
- git format-patch --subject-prefix='PATCH bpf' start..finish
-
- For features/improvements/etc that should eventually land in
- bpf-next -> net-next, the subject must look like:
-
- git format-patch --subject-prefix='PATCH bpf-next' start..finish
-
- If unsure whether the patch or patch series should go into bpf
- or net directly, or bpf-next or net-next directly, it is not a
- problem either if the subject line says net or net-next as target.
- It is eventually up to the maintainers to do the delegation of
- the patches.
-
- If it is clear that patches should go into bpf or bpf-next tree,
- please make sure to rebase the patches against those trees in
- order to reduce potential conflicts.
-
- In case the patch or patch series has to be reworked and sent out
- again in a second or later revision, it is also required to add a
- version number (v2, v3, ...) into the subject prefix:
-
- git format-patch --subject-prefix='PATCH net-next v2' start..finish
-
- When changes have been requested to the patch series, always send the
- whole patch series again with the feedback incorporated (never send
- individual diffs on top of the old series).
-
-Q: What does it mean when a patch gets applied to bpf or bpf-next tree?
-
-A: It means that the patch looks good for mainline inclusion from
- a BPF point of view.
-
- Be aware that this is not a final verdict that the patch will
- automatically get accepted into net or net-next trees eventually:
-
- On the netdev kernel mailing list reviews can come in at any point
- in time. If discussions around a patch conclude that they cannot
- get included as-is, we will either apply a follow-up fix or drop
- them from the trees entirely. Therefore, we also reserve to rebase
- the trees when deemed necessary. After all, the purpose of the tree
- is to i) accumulate and stage BPF patches for integration into trees
- like net and net-next, and ii) run extensive BPF test suite and
- workloads on the patches before they make their way any further.
-
- Once the BPF pull request was accepted by David S. Miller, then
- the patches end up in net or net-next tree, respectively, and
- make their way from there further into mainline. Again, see the
- netdev FAQ for additional information e.g. on how often they are
- merged to mainline.
-
-Q: How long do I need to wait for feedback on my BPF patches?
-
-A: We try to keep the latency low. The usual time to feedback will
- be around 2 or 3 business days. It may vary depending on the
- complexity of changes and current patch load.
-
-Q: How often do you send pull requests to major kernel trees like
- net or net-next?
-
-A: Pull requests will be sent out rather often in order to not
- accumulate too many patches in bpf or bpf-next.
-
- As a rule of thumb, expect pull requests for each tree regularly
- at the end of the week. In some cases pull requests could additionally
- come also in the middle of the week depending on the current patch
- load or urgency.
-
-Q: Are patches applied to bpf-next when the merge window is open?
-
-A: For the time when the merge window is open, bpf-next will not be
- processed. This is roughly analogous to net-next patch processing,
- so feel free to read up on the netdev FAQ about further details.
-
- During those two weeks of merge window, we might ask you to resend
- your patch series once bpf-next is open again. Once Linus released
- a v*-rc1 after the merge window, we continue processing of bpf-next.
-
- For non-subscribers to kernel mailing lists, there is also a status
- page run by David S. Miller on net-next that provides guidance:
-
- http://vger.kernel.org/~davem/net-next.html
-
-Q: I made a BPF verifier change, do I need to add test cases for
- BPF kernel selftests?
-
-A: If the patch has changes to the behavior of the verifier, then yes,
- it is absolutely necessary to add test cases to the BPF kernel
- selftests suite. If they are not present and we think they are
- needed, then we might ask for them before accepting any changes.
-
- In particular, test_verifier.c is tracking a high number of BPF test
- cases, including a lot of corner cases that LLVM BPF back end may
- generate out of the restricted C code. Thus, adding test cases is
- absolutely crucial to make sure future changes do not accidentally
- affect prior use-cases. Thus, treat those test cases as: verifier
- behavior that is not tracked in test_verifier.c could potentially
- be subject to change.
-
-Q: When should I add code to samples/bpf/ and when to BPF kernel
- selftests?
-
-A: In general, we prefer additions to BPF kernel selftests rather than
- samples/bpf/. The rationale is very simple: kernel selftests are
- regularly run by various bots to test for kernel regressions.
-
- The more test cases we add to BPF selftests, the better the coverage
- and the less likely it is that those could accidentally break. It is
- not that BPF kernel selftests cannot demo how a specific feature can
- be used.
-
- That said, samples/bpf/ may be a good place for people to get started,
- so it might be advisable that simple demos of features could go into
- samples/bpf/, but advanced functional and corner-case testing rather
- into kernel selftests.
-
- If your sample looks like a test case, then go for BPF kernel selftests
- instead!
-
-Q: When should I add code to the bpftool?
-
-A: The main purpose of bpftool (under tools/bpf/bpftool/) is to provide
- a central user space tool for debugging and introspection of BPF programs
- and maps that are active in the kernel. If UAPI changes related to BPF
- enable for dumping additional information of programs or maps, then
- bpftool should be extended as well to support dumping them.
-
-Q: When should I add code to iproute2's BPF loader?
-
-A: For UAPI changes related to the XDP or tc layer (e.g. cls_bpf), the
- convention is that those control-path related changes are added to
- iproute2's BPF loader as well from user space side. This is not only
- useful to have UAPI changes properly designed to be usable, but also
- to make those changes available to a wider user base of major
- downstream distributions.
-
-Q: Do you accept patches as well for iproute2's BPF loader?
-
-A: Patches for the iproute2's BPF loader have to be sent to:
-
- netdev@vger.kernel.org
-
- While those patches are not processed by the BPF kernel maintainers,
- please keep them in Cc as well, so they can be reviewed.
-
- The official git repository for iproute2 is run by Stephen Hemminger
- and can be found at:
-
- https://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git/
-
- The patches need to have a subject prefix of '[PATCH iproute2 master]'
- or '[PATCH iproute2 net-next]'. 'master' or 'net-next' describes the
- target branch where the patch should be applied to. Meaning, if kernel
- changes went into the net-next kernel tree, then the related iproute2
- changes need to go into the iproute2 net-next branch, otherwise they
- can be targeted at master branch. The iproute2 net-next branch will get
- merged into the master branch after the current iproute2 version from
- master has been released.
-
- Like BPF, the patches end up in patchwork under the netdev project and
- are delegated to 'shemminger' for further processing:
-
- http://patchwork.ozlabs.org/project/netdev/list/?delegate=389
-
-Q: What is the minimum requirement before I submit my BPF patches?
-
-A: When submitting patches, always take the time and properly test your
- patches *prior* to submission. Never rush them! If maintainers find
- that your patches have not been properly tested, it is a good way to
- get them grumpy. Testing patch submissions is a hard requirement!
-
- Note, fixes that go to bpf tree *must* have a Fixes: tag included. The
- same applies to fixes that target bpf-next, where the affected commit
- is in net-next (or in some cases bpf-next). The Fixes: tag is crucial
- in order to identify follow-up commits and tremendously helps for people
- having to do backporting, so it is a must have!
-
- We also don't accept patches with an empty commit message. Take your
- time and properly write up a high quality commit message, it is
- essential!
-
- Think about it this way: other developers looking at your code a month
- from now need to understand *why* a certain change has been done that
- way, and whether there have been flaws in the analysis or assumptions
- that the original author did. Thus providing a proper rationale and
- describing the use-case for the changes is a must.
-
- Patch submissions with >1 patch must have a cover letter which includes
- a high level description of the series. This high level summary will
- then be placed into the merge commit by the BPF maintainers such that
- it is also accessible from the git log for future reference.
-
-Q: What do I need to consider when adding a new instruction or feature
- that would require BPF JIT and/or LLVM integration as well?
-
-A: We try hard to keep all BPF JITs up to date such that the same user
- experience can be guaranteed when running BPF programs on different
- architectures without having the program punt to the less efficient
- interpreter in case the in-kernel BPF JIT is enabled.
-
- If you are unable to implement or test the required JIT changes for
- certain architectures, please work together with the related BPF JIT
- developers in order to get the feature implemented in a timely manner.
- Please refer to the git log (arch/*/net/) to locate the necessary
- people for helping out.
-
- Also always make sure to add BPF test cases (e.g. test_bpf.c and
- test_verifier.c) for new instructions, so that they can receive
- broad test coverage and help run-time testing the various BPF JITs.
-
- In case of new BPF instructions, once the changes have been accepted
- into the Linux kernel, please implement support into LLVM's BPF back
- end. See LLVM section below for further information.
-
-Stable submission:
-------------------
-
-Q: I need a specific BPF commit in stable kernels. What should I do?
-
-A: In case you need a specific fix in stable kernels, first check whether
- the commit has already been applied in the related linux-*.y branches:
-
- https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git/
-
- If not the case, then drop an email to the BPF maintainers with the
- netdev kernel mailing list in Cc and ask for the fix to be queued up:
-
- netdev@vger.kernel.org
-
- The process in general is the same as on netdev itself, see also the
- netdev FAQ document.
-
-Q: Do you also backport to kernels not currently maintained as stable?
-
-A: No. If you need a specific BPF commit in kernels that are currently not
- maintained by the stable maintainers, then you are on your own.
-
- The current stable and longterm stable kernels are all listed here:
-
- https://www.kernel.org/
-
-Q: The BPF patch I am about to submit needs to go to stable as well. What
- should I do?
-
-A: The same rules apply as with netdev patch submissions in general, see
- netdev FAQ under:
-
- Documentation/networking/netdev-FAQ.txt
-
- Never add "Cc: stable@vger.kernel.org" to the patch description, but
- ask the BPF maintainers to queue the patches instead. This can be done
- with a note, for example, under the "---" part of the patch which does
- not go into the git log. Alternatively, this can be done as a simple
- request by mail instead.
-
-Q: Where do I find currently queued BPF patches that will be submitted
- to stable?
-
-A: Once patches that fix critical bugs got applied into the bpf tree, they
- are queued up for stable submission under:
-
- http://patchwork.ozlabs.org/bundle/bpf/stable/?state=*
-
- They will be on hold there at minimum until the related commit made its
- way into the mainline kernel tree.
-
- After having been under broader exposure, the queued patches will be
- submitted by the BPF maintainers to the stable maintainers.
-
-Testing patches:
-----------------
-
-Q: Which BPF kernel selftests version should I run my kernel against?
-
-A: If you run a kernel xyz, then always run the BPF kernel selftests from
- that kernel xyz as well. Do not expect that the BPF selftest from the
- latest mainline tree will pass all the time.
-
- In particular, test_bpf.c and test_verifier.c have a large number of
- test cases and are constantly updated with new BPF test sequences, or
- existing ones are adapted to verifier changes e.g. due to verifier
- becoming smarter and being able to better track certain things.
-
-LLVM:
------
-
-Q: Where do I find LLVM with BPF support?
-
-A: The BPF back end for LLVM is upstream in LLVM since version 3.7.1.
-
- All major distributions these days ship LLVM with BPF back end enabled,
- so for the majority of use-cases it is not required to compile LLVM by
- hand anymore, just install the distribution provided package.
-
- LLVM's static compiler lists the supported targets through 'llc --version',
- make sure BPF targets are listed. Example:
-
- $ llc --version
- LLVM (http://llvm.org/):
- LLVM version 6.0.0svn
- Optimized build.
- Default target: x86_64-unknown-linux-gnu
- Host CPU: skylake
-
- Registered Targets:
- bpf - BPF (host endian)
- bpfeb - BPF (big endian)
- bpfel - BPF (little endian)
- x86 - 32-bit X86: Pentium-Pro and above
- x86-64 - 64-bit X86: EM64T and AMD64
-
- For developers in order to utilize the latest features added to LLVM's
- BPF back end, it is advisable to run the latest LLVM releases. Support
- for new BPF kernel features such as additions to the BPF instruction
- set are often developed together.
-
- All LLVM releases can be found at: http://releases.llvm.org/
-
-Q: Got it, so how do I build LLVM manually anyway?
-
-A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have
- that set up, proceed with building the latest LLVM and clang version
- from the git repositories:
-
- $ git clone http://llvm.org/git/llvm.git
- $ cd llvm/tools
- $ git clone --depth 1 http://llvm.org/git/clang.git
- $ cd ..; mkdir build; cd build
- $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
- -DBUILD_SHARED_LIBS=OFF \
- -DCMAKE_BUILD_TYPE=Release \
- -DLLVM_BUILD_RUNTIME=OFF
- $ make -j $(getconf _NPROCESSORS_ONLN)
-
- The built binaries can then be found in the build/bin/ directory, where
- you can point the PATH variable to.
-
-Q: Should I notify BPF kernel maintainers about issues in LLVM's BPF code
- generation back end or about LLVM generated code that the verifier
- refuses to accept?
-
-A: Yes, please do! LLVM's BPF back end is a key piece of the whole BPF
- infrastructure and it ties deeply into verification of programs from the
- kernel side. Therefore, any issues on either side need to be investigated
- and fixed whenever necessary.
-
- Therefore, please make sure to bring them up at netdev kernel mailing
- list and Cc BPF maintainers for LLVM and kernel bits:
-
- Yonghong Song <yhs@fb.com>
- Alexei Starovoitov <ast@kernel.org>
- Daniel Borkmann <daniel@iogearbox.net>
-
- LLVM also has an issue tracker where BPF related bugs can be found:
-
- https://bugs.llvm.org/buglist.cgi?quicksearch=bpf
-
- However, it is better to reach out through mailing lists with having
- maintainers in Cc.
-
-Q: I have added a new BPF instruction to the kernel, how can I integrate
- it into LLVM?
-
-A: LLVM has a -mcpu selector for the BPF back end in order to allow the
- selection of BPF instruction set extensions. By default the 'generic'
- processor target is used, which is the base instruction set (v1) of BPF.
-
- LLVM has an option to select -mcpu=probe where it will probe the host
- kernel for supported BPF instruction set extensions and selects the
- optimal set automatically.
-
- For cross-compilation, a specific version can be select manually as well.
-
- $ llc -march bpf -mcpu=help
- Available CPUs for this target:
-
- generic - Select the generic processor.
- probe - Select the probe processor.
- v1 - Select the v1 processor.
- v2 - Select the v2 processor.
- [...]
-
- Newly added BPF instructions to the Linux kernel need to follow the same
- scheme, bump the instruction set version and implement probing for the
- extensions such that -mcpu=probe users can benefit from the optimization
- transparently when upgrading their kernels.
-
- If you are unable to implement support for the newly added BPF instruction
- please reach out to BPF developers for help.
-
- By the way, the BPF kernel selftests run with -mcpu=probe for better
- test coverage.
-
-Q: In some cases clang flag "-target bpf" is used but in other cases the
- default clang target, which matches the underlying architecture, is used.
- What is the difference and when I should use which?
-
-A: Although LLVM IR generation and optimization try to stay architecture
- independent, "-target <arch>" still has some impact on generated code:
-
- - BPF program may recursively include header file(s) with file scope
- inline assembly codes. The default target can handle this well,
- while bpf target may fail if bpf backend assembler does not
- understand these assembly codes, which is true in most cases.
-
- - When compiled without -g, additional elf sections, e.g.,
- .eh_frame and .rela.eh_frame, may be present in the object file
- with default target, but not with bpf target.
-
- - The default target may turn a C switch statement into a switch table
- lookup and jump operation. Since the switch table is placed
- in the global readonly section, the bpf program will fail to load.
- The bpf target does not support switch table optimization.
- The clang option "-fno-jump-tables" can be used to disable
- switch table generation.
-
- - For clang -target bpf, it is guaranteed that pointer or long /
- unsigned long types will always have a width of 64 bit, no matter
- whether underlying clang binary or default target (or kernel) is
- 32 bit. However, when native clang target is used, then it will
- compile these types based on the underlying architecture's conventions,
- meaning in case of 32 bit architecture, pointer or long / unsigned
- long types e.g. in BPF context structure will have width of 32 bit
- while the BPF LLVM back end still operates in 64 bit. The native
- target is mostly needed in tracing for the case of walking pt_regs
- or other kernel structures where CPU's register width matters.
- Otherwise, clang -target bpf is generally recommended.
-
- You should use default target when:
-
- - Your program includes a header file, e.g., ptrace.h, which eventually
- pulls in some header files containing file scope host assembly codes.
- - You can add "-fno-jump-tables" to work around the switch table issue.
-
- Otherwise, you can use bpf target.
-
-Happy BPF hacking!
data device, but just remove the mapping.
read_only: Don't allow any changes to be made to the pool
- metadata.
+ metadata. This mode is only available after the
+ thin-pool has been created and first used in full
+ read/write mode. It cannot be specified on initial
+ thin-pool creation.
error_if_no_space: Error IOs, instead of queueing, if no space.
Optional properties:
- dma-coherent : Present if dma operations are coherent
- clocks : a list of phandle + clock specifier pairs
-- resets : a list of phandle + reset specifier pairs
- target-supply : regulator for SATA target power
- phys : reference to the SATA PHY node
- phy-names : must be "sata-phy"
require specific display timings. The panel-timing subnode expresses those
timings as specified in the timing subnode section of the display timing
bindings defined in
- Documentation/devicetree/bindings/display/display-timing.txt.
+ Documentation/devicetree/bindings/display/panel/display-timing.txt.
Connectivity
- "renesas,dmac-r8a7794" (R-Car E2)
- "renesas,dmac-r8a7795" (R-Car H3)
- "renesas,dmac-r8a7796" (R-Car M3-W)
+ - "renesas,dmac-r8a77965" (R-Car M3-N)
- "renesas,dmac-r8a77970" (R-Car V3M)
- "renesas,dmac-r8a77980" (R-Car V3H)
- compatible:
atmel,maxtouch
+ The following compatibles have been used in various products but are
+ deprecated:
+ atmel,qt602240_ts
+ atmel,atmel_mxt_ts
+ atmel,atmel_mxt_tp
+ atmel,mXT224
+
- reg: The I2C address of the device
- interrupts: The sink for the touchpad's IRQ output
- compatible: Must contain one or more of the following:
- "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller.
- "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
- - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3) compatible controller.
+ - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller.
+ - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller.
+ - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller.
When compatible with the generic version, nodes must list the
SoC-specific version corresponding to the platform first, followed by the
switch0: switch0@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 0>;
switch1: switch1@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 1>;
switch2: switch2@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 2>;
- compatible: must be one of the following string:
"allwinner,sun8i-a83t-emac"
"allwinner,sun8i-h3-emac"
+ "allwinner,sun8i-r40-gmac"
"allwinner,sun8i-v3s-emac"
"allwinner,sun50i-a64-emac"
- reg: address and length of the register for the device.
- phy-handle: See ethernet.txt
- #address-cells: shall be 1
- #size-cells: shall be 0
-- syscon: A phandle to the syscon of the SoC with one of the following
- compatible string:
- - allwinner,sun8i-h3-system-controller
- - allwinner,sun8i-v3s-system-controller
- - allwinner,sun50i-a64-system-controller
- - allwinner,sun8i-a83t-system-controller
+- syscon: A phandle to the device containing the EMAC or GMAC clock register
Optional properties:
-- allwinner,tx-delay-ps: TX clock delay chain value in ps. Range value is 0-700. Default is 0)
-- allwinner,rx-delay-ps: RX clock delay chain value in ps. Range value is 0-3100. Default is 0)
-Both delay properties need to be a multiple of 100. They control the delay for
-external PHY.
+- allwinner,tx-delay-ps: TX clock delay chain value in ps.
+ Range is 0-700. Default is 0.
+ Unavailable for allwinner,sun8i-r40-gmac
+- allwinner,rx-delay-ps: RX clock delay chain value in ps.
+ Range is 0-3100. Default is 0.
+ Range is 0-700 for allwinner,sun8i-r40-gmac
+Both delay properties need to be a multiple of 100. They control the
+clock delay for external RGMII PHY. They do not apply to the internal
+PHY or external non-RGMII PHYs.
Optional properties for the following compatibles:
- "allwinner,sun8i-h3-emac",
- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
- MG clock (only for armada-7k-pp2)
+ - MG Core clock (only for armada-7k-pp2)
- AXI clock (only for armada-7k-pp2)
-- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
- and "axi_clk" (the 2 latter only for armada-7k-pp2).
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk",
+ "mg_core_clk" and "axi_clk" (the 3 latter only for armada-7k-pp2).
The ethernet ports are represented by subnodes. At least one port is
required.
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
- <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
- clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
+ <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>;
+ clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk";
eth0: eth0 {
interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
- "amlogic,meson8b-dwmac"
- "amlogic,meson8m2-dwmac"
- "amlogic,meson-gxbb-dwmac"
+ - "amlogic,meson-axg-dwmac"
Additionally "snps,dwmac" and any applicable more
detailed version number described in net/stmmac.txt
should be used.
- txd2-skew-ps : Skew control of TX data 2 pad
- txd3-skew-ps : Skew control of TX data 3 pad
+ - micrel,force-master:
+ Boolean, force phy to master mode. Only set this option if the phy
+ reference clock provided at CLK125_NDO pin is used as MAC reference
+ clock because the clock jitter in slave mode is to high (errata#2).
+ Attention: The link partner must be configurable as slave otherwise
+ no link will be established.
+
Examples:
mdio {
--- /dev/null
+Microsemi MII Management Controller (MIIM) / MDIO
+=================================================
+
+Properties:
+- compatible: must be "mscc,ocelot-miim"
+- reg: The base address of the MDIO bus controller register bank. Optionally, a
+ second register bank can be defined if there is an associated reset register
+ for internal PHYs
+- #address-cells: Must be <1>.
+- #size-cells: Must be <0>. MDIO addresses have no size component.
+- interrupts: interrupt specifier (refer to the interrupt binding)
+
+Typically an MDIO bus might have several children.
+
+Example:
+ mdio@107009c {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "mscc,ocelot-miim";
+ reg = <0x107009c 0x36>, <0x10700f0 0x8>;
+ interrupts = <14>;
+
+ phy0: ethernet-phy@0 {
+ reg = <0>;
+ };
+ };
--- /dev/null
+Microsemi Ocelot network Switch
+===============================
+
+The Microsemi Ocelot network switch can be found on Microsemi SoCs (VSC7513,
+VSC7514)
+
+Required properties:
+- compatible: Should be "mscc,vsc7514-switch"
+- reg: Must contain an (offset, length) pair of the register set for each
+ entry in reg-names.
+- reg-names: Must include the following entries:
+ - "sys"
+ - "rew"
+ - "qs"
+ - "hsio"
+ - "qsys"
+ - "ana"
+ - "portX" with X from 0 to the number of last port index available on that
+ switch
+- interrupts: Should contain the switch interrupts for frame extraction and
+ frame injection
+- interrupt-names: should contain the interrupt names: "xtr", "inj"
+- ethernet-ports: A container for child nodes representing switch ports.
+
+The ethernet-ports container has the following properties
+
+Required properties:
+
+- #address-cells: Must be 1
+- #size-cells: Must be 0
+
+Each port node must have the following mandatory properties:
+- reg: Describes the port address in the switch
+
+Port nodes may also contain the following optional standardised
+properties, described in binding documents:
+
+- phy-handle: Phandle to a PHY on an MDIO bus. See
+ Documentation/devicetree/bindings/net/ethernet.txt for details.
+
+Example:
+
+ switch@1010000 {
+ compatible = "mscc,vsc7514-switch";
+ reg = <0x1010000 0x10000>,
+ <0x1030000 0x10000>,
+ <0x1080000 0x100>,
+ <0x10d0000 0x10000>,
+ <0x11e0000 0x100>,
+ <0x11f0000 0x100>,
+ <0x1200000 0x100>,
+ <0x1210000 0x100>,
+ <0x1220000 0x100>,
+ <0x1230000 0x100>,
+ <0x1240000 0x100>,
+ <0x1250000 0x100>,
+ <0x1260000 0x100>,
+ <0x1270000 0x100>,
+ <0x1280000 0x100>,
+ <0x1800000 0x80000>,
+ <0x1880000 0x10000>;
+ reg-names = "sys", "rew", "qs", "hsio", "port0",
+ "port1", "port2", "port3", "port4", "port5",
+ "port6", "port7", "port8", "port9", "port10",
+ "qsys", "ana";
+ interrupts = <21 22>;
+ interrupt-names = "xtr", "inj";
+
+ ethernet-ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port0: port@0 {
+ reg = <0>;
+ phy-handle = <&phy0>;
+ };
+ port1: port@1 {
+ reg = <1>;
+ phy-handle = <&phy1>;
+ };
+ };
+ };
--- /dev/null
+Qualcomm Bluetooth Chips
+---------------------
+
+This documents the binding structure and common properties for serial
+attached Qualcomm devices.
+
+Serial attached Qualcomm devices shall be a child node of the host UART
+device the slave device is attached to.
+
+Required properties:
+ - compatible: should contain one of the following:
+ * "qcom,qca6174-bt"
+
+Optional properties:
+ - enable-gpios: gpio specifier used to enable chip
+ - clocks: clock provided to the controller (SUSCLK_32KHZ)
+
+Example:
+
+serial@7570000 {
+ label = "BT-UART";
+ status = "okay";
+
+ bluetooth {
+ compatible = "qcom,qca6174-bt";
+
+ enable-gpios = <&pm8994_gpios 19 GPIO_ACTIVE_HIGH>;
+ clocks = <&divclk4>;
+ };
+};
- "renesas,etheravb-r8a7795" for the R8A7795 SoC.
- "renesas,etheravb-r8a7796" for the R8A7796 SoC.
+ - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
- "renesas,etheravb-r8a77970" for the R8A77970 SoC.
- "renesas,etheravb-r8a77980" for the R8A77980 SoC.
- "renesas,etheravb-r8a77995" for the R8A77995 SoC.
"renesas,ether-r8a7791" if the device is a part of R8A7791 SoC.
"renesas,ether-r8a7793" if the device is a part of R8A7793 SoC.
"renesas,ether-r8a7794" if the device is a part of R8A7794 SoC.
+ "renesas,gether-r8a77980" if the device is a part of R8A77980 SoC.
"renesas,ether-r7s72100" if the device is a part of R7S72100 SoC.
"renesas,rcar-gen1-ether" for a generic R-Car Gen1 device.
"renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1
configuration, drive strength and pullups. If one of these options is
not set, its actual value will be unspecified.
-This driver supports the generic pin multiplexing and configuration
-bindings. For details on each properties, you can refer to
-./pinctrl-bindings.txt.
+Allwinner A1X Pin Controller supports the generic pin multiplexing and
+configuration bindings. For details on each properties, you can refer to
+ ./pinctrl-bindings.txt.
Required sub-node properties:
- pins
- interrupts : identifier to the device interrupt
- clocks : a list of phandle + clock-specifier pairs, one for each
entry in clock names.
-- clocks-names :
+- clock-names :
* "xtal" for external xtal clock identifier
* "pclk" for the bus core clock, either the clk81 clock or the gate clock
* "baud" for the source of the baudrate generator, can be either the xtal
- Must contain two elements for the extended variant of the IP
(marvell,armada-3700-uart-ext): "uart-tx" and "uart-rx",
respectively the UART TX interrupt and the UART RX interrupt. A
- corresponding interrupts-names property must be defined.
+ corresponding interrupt-names property must be defined.
- For backward compatibility reasons, a single element interrupts
property is also supported for the standard variant of the IP,
containing only the UART sum interrupt. This form is deprecated
- "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
- "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
- "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
+ - "renesas,scif-r8a77470" for R8A77470 (RZ/G1C) SCIF compatible UART.
+ - "renesas,hscif-r8a77470" for R8A77470 (RZ/G1C) HSCIF compatible UART.
- "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
- "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
- "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
- "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART.
- "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART.
- "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART.
+ - "renesas,scif-r8a77965" for R8A77965 (R-Car M3-N) SCIF compatible UART.
+ - "renesas,hscif-r8a77965" for R8A77965 (R-Car M3-N) HSCIF compatible UART.
- "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART.
- "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART.
- "renesas,scif-r8a77980" for R8A77980 (R-Car V3H) SCIF compatible UART.
- interrupts: one XHCI interrupt should be described here.
Optional properties:
- - clocks: reference to a clock
+ - clocks: reference to the clocks
+ - clock-names: mandatory if there is a second clock, in this case
+ the name must be "core" for the first clock and "reg" for the
+ second one
- usb2-lpm-disable: indicate if we don't want to enable USB2 HW LPM
- usb3-lpm-capable: determines if platform is USB3 LPM capable
- quirk-broken-port-ped: set if the controller has broken port disable mechanism
keithkoep Keith & Koep GmbH
keymile Keymile GmbH
khadas Khadas
+kiebackpeter Kieback & Peter GmbH
kinetic Kinetic Technologies
kingnovel Kingnovel Technology Co., Ltd.
kosagi Sutajio Ko-Usagi PTE Ltd.
of_overlay_remove_all() which will remove every single one in the correct
order.
+In addition, there is the option to register notifiers that get called on
+overlay operations. See of_overlay_notifier_register/unregister and
+enum of_overlay_notify_action for details.
+
+Note that a notifier callback is not supposed to store pointers to a device
+tree node or its content beyond OF_OVERLAY_POST_REMOVE corresponding to the
+respective node it received.
+
Overlay DTS Format
------------------
****
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
COPYRIGHT
*********
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
request_firmware
----------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware
request_firmware_direct
-----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_direct
request_firmware_into_buf
-------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_into_buf
Asynchronous firmware requests
request_firmware_nowait
-----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_nowait
Special optimizations on reboot
Some devices have an optimization in place to enable the firmware to be
retained during system reboot. When such optimizations are used the driver
author must ensure the firmware is still available on resume from suspend,
-this can be done with firmware_request_cache() insted of requesting for the
-firmare to be loaded.
+this can be done with firmware_request_cache() instead of requesting for the
+firmware to be loaded.
firmware_request_cache()
------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+------------------------
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: firmware_request_cache
request firmware API expected driver use
.. kernel-doc:: drivers/base/node.c
:internal:
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:export:
.. kernel-doc:: drivers/base/transport_class.c
role. USB Type-C Connector Class does not supply separate API for them. The
port drivers can use USB Role Class API with those.
-Illustration of the muxes behind a connector that supports an alternate mode:
+Illustration of the muxes behind a connector that supports an alternate mode::
------------------------
| Connector |
Updated 1997 by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
Updated 2006 by Nico Schottelius <nico-kernel-nfsroot@schottelius.org>
Updated 2006 by Horms <horms@verge.net.au>
+Updated 2018 by Chris Novakovic <chris@chrisn.me.uk>
ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>:
- <dns0-ip>:<dns1-ip>
+ <dns0-ip>:<dns1-ip>:<ntp0-ip>
This parameter tells the kernel how to configure IP addresses of devices
and also how to set up the IP routing table. It was originally called
will not be triggered if it is missing and NFS root is not
in operation.
+ Value is exported to /proc/net/pnp with the prefix "bootserver "
+ (see below).
+
Default: Determined using autoconfiguration.
The address of the autoconfiguration server is used.
Default: Determined using autoconfiguration.
- <hostname> Name of the client. May be supplied by autoconfiguration,
- but its absence will not trigger autoconfiguration.
- If specified and DHCP is used, the user provided hostname will
- be carried in the DHCP request to hopefully update DNS record.
+ <hostname> Name of the client. If a '.' character is present, anything
+ before the first '.' is used as the client's hostname, and anything
+ after it is used as its NIS domain name. May be supplied by
+ autoconfiguration, but its absence will not trigger autoconfiguration.
+ If specified and DHCP is used, the user-provided hostname (and NIS
+ domain name, if present) will be carried in the DHCP request; this
+ may cause a DNS record to be created or updated for the client.
Default: Client IP address is used in ASCII notation.
Default: any
- <dns0-ip> IP address of first nameserver.
- Value gets exported by /proc/net/pnp which is often linked
- on embedded systems by /etc/resolv.conf.
+ <dns0-ip> IP address of primary nameserver.
+ Value is exported to /proc/net/pnp with the prefix "nameserver "
+ (see below).
+
+ Default: None if not using autoconfiguration; determined
+ automatically if using autoconfiguration.
+
+ <dns1-ip> IP address of secondary nameserver.
+ See <dns0-ip>.
+
+ <ntp0-ip> IP address of a Network Time Protocol (NTP) server.
+ Value is exported to /proc/net/ipconfig/ntp_servers, but is
+ otherwise unused (see below).
+
+ Default: None if not using autoconfiguration; determined
+ automatically if using autoconfiguration.
+
+ After configuration (whether manual or automatic) is complete, two files
+ are created in the following format; lines are omitted if their respective
+ value is empty following configuration:
+
+ - /proc/net/pnp:
+
+ #PROTO: <DHCP|BOOTP|RARP|MANUAL> (depending on configuration method)
+ domain <dns-domain> (if autoconfigured, the DNS domain)
+ nameserver <dns0-ip> (primary name server IP)
+ nameserver <dns1-ip> (secondary name server IP)
+ nameserver <dns2-ip> (tertiary name server IP)
+ bootserver <server-ip> (NFS server IP)
+
+ - /proc/net/ipconfig/ntp_servers:
+
+ <ntp0-ip> (NTP server IP)
+ <ntp1-ip> (NTP server IP)
+ <ntp2-ip> (NTP server IP)
+
+ <dns-domain> and <dns2-ip> (in /proc/net/pnp) and <ntp1-ip> and <ntp2-ip>
+ (in /proc/net/ipconfig/ntp_servers) are requested during autoconfiguration;
+ they cannot be specified as part of the "ip=" kernel command line parameter.
+
+ Because the "domain" and "nameserver" options are recognised by DNS
+ resolvers, /etc/resolv.conf is often linked to /proc/net/pnp on systems
+ that use an NFS root filesystem.
- <dns1-ip> IP address of second nameserver.
- Same as above.
+ Note that the kernel will not synchronise the system time with any NTP
+ servers it discovers; this is the responsibility of a user space process
+ (e.g. an initrd/initramfs script that passes the IP addresses listed in
+ /proc/net/ipconfig/ntp_servers to an NTP client before mounting the real
+ root filesystem if it is on NFS).
nfsrootdebug
the i2c-tools package.
I2C device files are character device files with major device number 89
-and a minor device number corresponding to the number assigned as
-explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ...,
+and a minor device number corresponding to the number assigned as
+explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ...,
i2c-10, ...). All 256 minor device numbers are reserved for i2c.
#include <linux/i2c-dev.h>
#include <i2c/smbus.h>
-(Please note that there are two files named "i2c-dev.h" out there. One is
-distributed with the Linux kernel and the other one is included in the
-source tree of i2c-tools. They used to be different in content but since 2012
-they're identical. You should use "linux/i2c-dev.h").
-
Now, you have to decide which adapter you want to access. You should
inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this.
Adapter numbers are assigned somewhat dynamically, so you can not
int file;
int adapter_nr = 2; /* probably dynamically determined */
char filename[20];
-
+
snprintf(filename, 19, "/dev/i2c-%d", adapter_nr);
file = open(filename, O_RDWR);
if (file < 0) {
/* res contains the read word */
}
- /* Using I2C Write, equivalent of
- i2c_smbus_write_word_data(file, reg, 0x6543) */
+ /*
+ * Using I2C Write, equivalent of
+ * i2c_smbus_write_word_data(file, reg, 0x6543)
+ */
buf[0] = reg;
buf[1] = 0x43;
buf[2] = 0x65;
set in each message, overriding the values set with the above ioctl's.
ioctl(file, I2C_SMBUS, struct i2c_smbus_ioctl_data *args)
- Not meant to be called directly; instead, use the access functions
- below.
+ If possible, use the provided i2c_smbus_* methods described below instead
+ of issuing direct ioctls.
You can do plain i2c transactions by using read(2) and write(2) calls.
You do not need to pass the address byte; instead, set it through
ioctl I2C_SLAVE before you try to access the device.
-You can do SMBus level transactions (see documentation file smbus-protocol
+You can do SMBus level transactions (see documentation file smbus-protocol
for details) through the following functions:
__s32 i2c_smbus_write_quick(int file, __u8 value);
__s32 i2c_smbus_read_byte(int file);
__s32 i2c_smbus_write_word_data(int file, __u8 command, __u16 value);
__s32 i2c_smbus_process_call(int file, __u8 command, __u16 value);
__s32 i2c_smbus_read_block_data(int file, __u8 command, __u8 *values);
- __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length,
+ __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length,
__u8 *values);
All these transactions return -1 on failure; you can read errno to see
what happened. The 'write' transactions return 0 on success; the
returns the number of values read. The block buffers need not be longer
than 32 bytes.
-The above functions are all inline functions, that resolve to calls to
-the i2c_smbus_access function, that on its turn calls a specific ioctl
-with the data in a specific format. Read the source code if you
-want to know what happens behind the screens.
+The above functions are made available by linking against the libi2c library,
+which is provided by the i2c-tools project. See:
+https://git.kernel.org/pub/scm/utils/i2c-tools/i2c-tools.git/.
Implementation details
'd' 02-40 pcmcia/ds.h conflict!
'd' F0-FF linux/digi1.h
'e' all linux/digi1.h conflict!
-'e' 00-1F drivers/net/irda/irtty-sir.h conflict!
'f' 00-1F linux/ext2_fs.h conflict!
'f' 00-1F linux/ext3_fs.h conflict!
'f' 00-0F fs/jfs/jfs_dinode.h conflict!
'm' all linux/synclink.h conflict!
'm' 00-19 drivers/message/fusion/mptctl.h conflict!
'm' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict!
-'m' 00-1F net/irda/irmod.h conflict!
'n' 00-7F linux/ncp_fs.h and fs/ncpfs/ioctl.c
'n' 80-8F uapi/linux/nilfs2_api.h NILFS2
'n' E0-FF linux/matroxfb.h matroxfb
/* keytable.c - This program allows checking/replacing keys at IR
- Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+ Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@kernel.org>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
.. code-block:: c
/* V4L2 video picture grabber
- Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+ Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+======
+AF_XDP
+======
+
+Overview
+========
+
+AF_XDP is an address family that is optimized for high performance
+packet processing.
+
+This document assumes that the reader is familiar with BPF and XDP. If
+not, the Cilium project has an excellent reference guide at
+http://cilium.readthedocs.io/en/doc-1.0/bpf/.
+
+Using the XDP_REDIRECT action from an XDP program, the program can
+redirect ingress frames to other XDP enabled netdevs, using the
+bpf_redirect_map() function. AF_XDP sockets enable the possibility for
+XDP programs to redirect frames to a memory buffer in a user-space
+application.
+
+An AF_XDP socket (XSK) is created with the normal socket()
+syscall. Associated with each XSK are two rings: the RX ring and the
+TX ring. A socket can receive packets on the RX ring and it can send
+packets on the TX ring. These rings are registered and sized with the
+setsockopts XDP_RX_RING and XDP_TX_RING, respectively. It is mandatory
+to have at least one of these rings for each socket. An RX or TX
+descriptor ring points to a data buffer in a memory area called a
+UMEM. RX and TX can share the same UMEM so that a packet does not have
+to be copied between RX and TX. Moreover, if a packet needs to be kept
+for a while due to a possible retransmit, the descriptor that points
+to that packet can be changed to point to another and reused right
+away. This again avoids copying data.
+
+The UMEM consists of a number of equally size frames and each frame
+has a unique frame id. A descriptor in one of the rings references a
+frame by referencing its frame id. The user space allocates memory for
+this UMEM using whatever means it feels is most appropriate (malloc,
+mmap, huge pages, etc). This memory area is then registered with the
+kernel using the new setsockopt XDP_UMEM_REG. The UMEM also has two
+rings: the FILL ring and the COMPLETION ring. The fill ring is used by
+the application to send down frame ids for the kernel to fill in with
+RX packet data. References to these frames will then appear in the RX
+ring once each packet has been received. The completion ring, on the
+other hand, contains frame ids that the kernel has transmitted
+completely and can now be used again by user space, for either TX or
+RX. Thus, the frame ids appearing in the completion ring are ids that
+were previously transmitted using the TX ring. In summary, the RX and
+FILL rings are used for the RX path and the TX and COMPLETION rings
+are used for the TX path.
+
+The socket is then finally bound with a bind() call to a device and a
+specific queue id on that device, and it is not until bind is
+completed that traffic starts to flow.
+
+The UMEM can be shared between processes, if desired. If a process
+wants to do this, it simply skips the registration of the UMEM and its
+corresponding two rings, sets the XDP_SHARED_UMEM flag in the bind
+call and submits the XSK of the process it would like to share UMEM
+with as well as its own newly created XSK socket. The new process will
+then receive frame id references in its own RX ring that point to this
+shared UMEM. Note that since the ring structures are single-consumer /
+single-producer (for performance reasons), the new process has to
+create its own socket with associated RX and TX rings, since it cannot
+share this with the other process. This is also the reason that there
+is only one set of FILL and COMPLETION rings per UMEM. It is the
+responsibility of a single process to handle the UMEM.
+
+How is then packets distributed from an XDP program to the XSKs? There
+is a BPF map called XSKMAP (or BPF_MAP_TYPE_XSKMAP in full). The
+user-space application can place an XSK at an arbitrary place in this
+map. The XDP program can then redirect a packet to a specific index in
+this map and at this point XDP validates that the XSK in that map was
+indeed bound to that device and ring number. If not, the packet is
+dropped. If the map is empty at that index, the packet is also
+dropped. This also means that it is currently mandatory to have an XDP
+program loaded (and one XSK in the XSKMAP) to be able to get any
+traffic to user space through the XSK.
+
+AF_XDP can operate in two different modes: XDP_SKB and XDP_DRV. If the
+driver does not have support for XDP, or XDP_SKB is explicitly chosen
+when loading the XDP program, XDP_SKB mode is employed that uses SKBs
+together with the generic XDP support and copies out the data to user
+space. A fallback mode that works for any network device. On the other
+hand, if the driver has support for XDP, it will be used by the AF_XDP
+code to provide better performance, but there is still a copy of the
+data into user space.
+
+Concepts
+========
+
+In order to use an AF_XDP socket, a number of associated objects need
+to be setup.
+
+Jonathan Corbet has also written an excellent article on LWN,
+"Accelerating networking with AF_XDP". It can be found at
+https://lwn.net/Articles/750845/.
+
+UMEM
+----
+
+UMEM is a region of virtual contiguous memory, divided into
+equal-sized frames. An UMEM is associated to a netdev and a specific
+queue id of that netdev. It is created and configured (frame size,
+frame headroom, start address and size) by using the XDP_UMEM_REG
+setsockopt system call. A UMEM is bound to a netdev and queue id, via
+the bind() system call.
+
+An AF_XDP is socket linked to a single UMEM, but one UMEM can have
+multiple AF_XDP sockets. To share an UMEM created via one socket A,
+the next socket B can do this by setting the XDP_SHARED_UMEM flag in
+struct sockaddr_xdp member sxdp_flags, and passing the file descriptor
+of A to struct sockaddr_xdp member sxdp_shared_umem_fd.
+
+The UMEM has two single-producer/single-consumer rings, that are used
+to transfer ownership of UMEM frames between the kernel and the
+user-space application.
+
+Rings
+-----
+
+There are a four different kind of rings: Fill, Completion, RX and
+TX. All rings are single-producer/single-consumer, so the user-space
+application need explicit synchronization of multiple
+processes/threads are reading/writing to them.
+
+The UMEM uses two rings: Fill and Completion. Each socket associated
+with the UMEM must have an RX queue, TX queue or both. Say, that there
+is a setup with four sockets (all doing TX and RX). Then there will be
+one Fill ring, one Completion ring, four TX rings and four RX rings.
+
+The rings are head(producer)/tail(consumer) based rings. A producer
+writes the data ring at the index pointed out by struct xdp_ring
+producer member, and increasing the producer index. A consumer reads
+the data ring at the index pointed out by struct xdp_ring consumer
+member, and increasing the consumer index.
+
+The rings are configured and created via the _RING setsockopt system
+calls and mmapped to user-space using the appropriate offset to mmap()
+(XDP_PGOFF_RX_RING, XDP_PGOFF_TX_RING, XDP_UMEM_PGOFF_FILL_RING and
+XDP_UMEM_PGOFF_COMPLETION_RING).
+
+The size of the rings need to be of size power of two.
+
+UMEM Fill Ring
+~~~~~~~~~~~~~~
+
+The Fill ring is used to transfer ownership of UMEM frames from
+user-space to kernel-space. The UMEM indicies are passed in the
+ring. As an example, if the UMEM is 64k and each frame is 4k, then the
+UMEM has 16 frames and can pass indicies between 0 and 15.
+
+Frames passed to the kernel are used for the ingress path (RX rings).
+
+The user application produces UMEM indicies to this ring.
+
+UMEM Completetion Ring
+~~~~~~~~~~~~~~~~~~~~~~
+
+The Completion Ring is used transfer ownership of UMEM frames from
+kernel-space to user-space. Just like the Fill ring, UMEM indicies are
+used.
+
+Frames passed from the kernel to user-space are frames that has been
+sent (TX ring) and can be used by user-space again.
+
+The user application consumes UMEM indicies from this ring.
+
+
+RX Ring
+~~~~~~~
+
+The RX ring is the receiving side of a socket. Each entry in the ring
+is a struct xdp_desc descriptor. The descriptor contains UMEM index
+(idx), the length of the data (len), the offset into the frame
+(offset).
+
+If no frames have been passed to kernel via the Fill ring, no
+descriptors will (or can) appear on the RX ring.
+
+The user application consumes struct xdp_desc descriptors from this
+ring.
+
+TX Ring
+~~~~~~~
+
+The TX ring is used to send frames. The struct xdp_desc descriptor is
+filled (index, length and offset) and passed into the ring.
+
+To start the transfer a sendmsg() system call is required. This might
+be relaxed in the future.
+
+The user application produces struct xdp_desc descriptors to this
+ring.
+
+XSKMAP / BPF_MAP_TYPE_XSKMAP
+----------------------------
+
+On XDP side there is a BPF map type BPF_MAP_TYPE_XSKMAP (XSKMAP) that
+is used in conjunction with bpf_redirect_map() to pass the ingress
+frame to a socket.
+
+The user application inserts the socket into the map, via the bpf()
+system call.
+
+Note that if an XDP program tries to redirect to a socket that does
+not match the queue configuration and netdev, the frame will be
+dropped. E.g. an AF_XDP socket is bound to netdev eth0 and
+queue 17. Only the XDP program executing for eth0 and queue 17 will
+successfully pass data to the socket. Please refer to the sample
+application (samples/bpf/) in for an example.
+
+Usage
+=====
+
+In order to use AF_XDP sockets there are two parts needed. The
+user-space application and the XDP program. For a complete setup and
+usage example, please refer to the sample application. The user-space
+side is xdpsock_user.c and the XDP side xdpsock_kern.c.
+
+Naive ring dequeue and enqueue could look like this::
+
+ // typedef struct xdp_rxtx_ring RING;
+ // typedef struct xdp_umem_ring RING;
+
+ // typedef struct xdp_desc RING_TYPE;
+ // typedef __u32 RING_TYPE;
+
+ int dequeue_one(RING *ring, RING_TYPE *item)
+ {
+ __u32 entries = ring->ptrs.producer - ring->ptrs.consumer;
+
+ if (entries == 0)
+ return -1;
+
+ // read-barrier!
+
+ *item = ring->desc[ring->ptrs.consumer & (RING_SIZE - 1)];
+ ring->ptrs.consumer++;
+ return 0;
+ }
+
+ int enqueue_one(RING *ring, const RING_TYPE *item)
+ {
+ u32 free_entries = RING_SIZE - (ring->ptrs.producer - ring->ptrs.consumer);
+
+ if (free_entries == 0)
+ return -1;
+
+ ring->desc[ring->ptrs.producer & (RING_SIZE - 1)] = *item;
+
+ // write-barrier!
+
+ ring->ptrs.producer++;
+ return 0;
+ }
+
+
+For a more optimized version, please refer to the sample application.
+
+Sample application
+==================
+
+There is a xdpsock benchmarking/test application included that
+demonstrates how to use AF_XDP sockets with both private and shared
+UMEMs. Say that you would like your UDP traffic from port 4242 to end
+up in queue 16, that we will enable AF_XDP on. Here, we use ethtool
+for this::
+
+ ethtool -N p3p2 rx-flow-hash udp4 fn
+ ethtool -N p3p2 flow-type udp4 src-port 4242 dst-port 4242 \
+ action 16
+
+Running the rxdrop benchmark in XDP_DRV mode can then be done
+using::
+
+ samples/bpf/xdpsock -i p3p2 -q 16 -r -N
+
+For XDP_SKB mode, use the switch "-S" instead of "-N" and all options
+can be displayed with "-h", as usual.
+
+Credits
+=======
+
+- Björn Töpel (AF_XDP core)
+- Magnus Karlsson (AF_XDP core)
+- Alexander Duyck
+- Alexei Starovoitov
+- Daniel Borkmann
+- Jesper Dangaard Brouer
+- John Fastabend
+- Jonathan Corbet (LWN coverage)
+- Michael S. Tsirkin
+- Qi Z Zhang
+- Willem de Bruijn
+
Module options may be given as command line arguments to the
insmod or modprobe command, but are usually specified in either the
-/etc/modrobe.d/*.conf configuration files, or in a distro-specific
+/etc/modprobe.d/*.conf configuration files, or in a distro-specific
configuration file (some of which are detailed in the next section).
Details on bonding support for sysfs is provided in the
[ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00
[ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3
+When CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1 and
+setting any other value than that will return in failure. This is even the case for
+setting bpf_jit_enable to 2, since dumping the final JIT image into the kernel log
+is discouraged and introspection through bpftool (under tools/bpf/bpftool/) is the
+generally recommended approach instead.
+
In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for
generating disassembly out of the kernel log's hexdump:
the low 8 are unknown - which is represented as the tnum (0x0; 0xff). If we
then OR this with 0x40, we get (0x40; 0xbf), then if we add 1 we get (0x0;
0x1ff), because of potential carries.
+
Besides arithmetic, the register state can also be updated by conditional
branches. For instance, if a SCALAR_VALUE is compared > 8, in the 'true' branch
it will have a umin_value (unsigned minimum value) of 9, whereas in the 'false'
from the signed and unsigned bounds can be combined; for instance if a value is
first tested < 8 and then tested s> 4, the verifier will conclude that the value
is also > 4 and s< 8, since the bounds prevent crossing the sign boundary.
+
PTR_TO_PACKETs with a variable offset part have an 'id', which is common to all
pointers sharing that same variable offset. This is important for packet range
-checks: after adding some variable to a packet pointer, if you then copy it to
-another register and (say) add a constant 4, both registers will share the same
-'id' but one will have a fixed offset of +4. Then if it is bounds-checked and
-found to be less than a PTR_TO_PACKET_END, the other register is now known to
-have a safe range of at least 4 bytes. See 'Direct packet access', below, for
-more on PTR_TO_PACKET ranges.
+checks: after adding a variable to a packet pointer register A, if you then copy
+it to another register B and then add a constant 4 to A, both registers will
+share the same 'id' but the A will have a fixed offset of +4. Then if A is
+bounds-checked and found to be less than a PTR_TO_PACKET_END, the register B is
+now known to have a safe range of at least 4 bytes. See 'Direct packet access',
+below, for more on PTR_TO_PACKET ranges.
+
The 'id' field is also used on PTR_TO_MAP_VALUE_OR_NULL, common to all copies of
the pointer returned from a map lookup. This means that when one copy is
checked and found to be non-NULL, all copies can become PTR_TO_MAP_VALUEs.
.. toctree::
:maxdepth: 2
+ af_xdp
batman-adv
can
dpaa2/index
features.
RACK: 0x1 enables the RACK loss detection for fast detection of lost
- retransmissions and tail drops.
+ retransmissions and tail drops. It also subsumes and disables
+ RFC6675 recovery for SACK connections.
RACK: 0x2 makes RACK's reordering window static (min_rtt/4).
+ RACK: 0x4 disables RACK's DUPACK threshold heuristic
Default: 0x1
tcp_sack - BOOLEAN
Enable select acknowledgments (SACKS).
+tcp_comp_sack_delay_ns - LONG INTEGER
+ TCP tries to reduce number of SACK sent, using a timer
+ based on 5% of SRTT, capped by this sysctl, in nano seconds.
+ The default is 1ms, based on TSO autosizing period.
+
+ Default : 1,000,000 ns (1 ms)
+
+tcp_comp_sack_nr - INTEGER
+ Max numer of SACK that can be compressed.
+ Using 0 disables SACK compression.
+
+ Detault : 44
+
tcp_slow_start_after_idle - BOOLEAN
If set, provide RFC2861 behavior and time out the congestion
window after an idle period. An idle period is defined at
ip6frag_time - INTEGER
Time in seconds to keep an IPv6 fragment in memory.
+IPv6 Segment Routing:
+
+seg6_flowlabel - INTEGER
+ Controls the behaviour of computing the flowlabel of outer
+ IPv6 header in case of SR T.encaps
+
+ -1 set flowlabel to zero.
+ 0 copy flowlabel from Inner packet in case of Inner IPv6
+ (Set flowlabel to 0 in case IPv4/L2)
+ 1 Compute the flowlabel using seg6_make_flowlabel()
+
+ Default is 0.
+
conf/default/*:
Change the interface-specific default settings.
Default: 10
-
-UNDOCUMENTED:
-
-/proc/sys/net/irda/*
- fast_poll_increase FIXME
- warn_noreply_time FIXME
- discovery_slots FIXME
- slot_timeout FIXME
- max_baud_rate FIXME
- discovery_timeout FIXME
- lap_keepalive_time FIXME
- max_noreply_time FIXME
- max_tx_data_size FIXME
- max_tx_window FIXME
- min_tx_turn_time FIXME
NETIF_F_TSO_ECN means that hardware can properly split packets with CWR bit
set, be it TCPv4 (when NETIF_F_TSO is enabled) or TCPv6 (NETIF_F_TSO6).
+ * Transmit UDP segmentation offload
+
+NETIF_F_GSO_UDP_GSO_L4 accepts a single UDP header with a payload that exceeds
+gso_size. On segmentation, it segments the payload on gso_size boundaries and
+replicates the network and UDP headers (fixing up the last one if less than
+gso_size).
+
* Transmit DMA from high memory
On platforms where this is relevant, NETIF_F_HIGHDMA signals that
[Please bear in mind that the kernel requests the microcode images from
userspace, using the request_firmware() function defined in
-drivers/base/firmware_class.c]
+drivers/base/firmware_loader/main.c]
a. When all the CPUs are identical:
OSS sound drivers have their magic numbers constructed from the soundcard PCI
ID - these are not listed here as well.
-IrDA subsystem also uses large number of own magic numbers, see
-``include/net/irda/irda.h`` for a complete list of them.
-
HFS is another larger user of magic numbers - you can find them in
``fs/hfs/hfs.h``.
=head1 BUGS
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
=head1 COPYRIGHT
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
translate these BPF proglets into native CPU instructions. There are
two flavors of JITs, the newer eBPF JIT currently supported on:
- x86_64
+ - x86_32
- arm64
- arm32
- ppc64
and ticks at the same rate as the hardware clocksource.
boot:
- Same as mono. Used to be a separate clock which accounted
- for the time spent in suspend while CLOCK_MONOTONIC did
- not.
+ This is the boot clock (CLOCK_BOOTTIME) and is based on the
+ fast monotonic clock, but also accounts for time spent in
+ suspend. Since the clock access is designed for use in
+ tracing in the suspend path, some side effects are possible
+ if clock is accessed after the suspend time is accounted before
+ the fast mono clock is updated. In this case, the clock update
+ appears to happen slightly sooner than it normally would have.
+ Also on 32-bit systems, it's possible that the 64-bit boot offset
+ sees a partial update. These effects are rare and post
+ processing should be able to handle them. See comments in the
+ ktime_get_boot_fast_ns() function for more information.
To set a clock, simply echo the clock name into this file::
help. Contact the Chinese maintainer if this translation is outdated
or if there is a problem with the translation.
-Maintainer: Mauro Carvalho Chehab <mchehab@infradead.org>
+Maintainer: Mauro Carvalho Chehab <mchehab@kernel.org>
Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
---------------------------------------------------------------------
Documentation/video4linux/v4l2-framework.txt 的中文翻译
如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
译存在问题，请联系中文版维护者。
-英文版维护者： Mauro Carvalho Chehab <mchehab@infradead.org>
+英文版维护者： Mauro Carvalho Chehab <mchehab@kernel.org>
中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
ARM 64-bit FP registers have the following id bit patterns:
0x4030 0000 0012 0 <regno:12>
+ARM firmware pseudo-registers have the following bit pattern:
+ 0x4030 0000 0014 <regno:16>
+
arm64 registers are mapped using the lower 32 bits. The upper 16 of
that is the register group type, or coprocessor number:
arm64 system registers have the following id bit patterns:
0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
+arm64 firmware pseudo-registers have the following bit pattern:
+ 0x6030 0000 0014 <regno:16>
+
MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
the register group type:
and execute guest code when KVM_RUN is called.
- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
- - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
+ - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
+ backward compatible with v0.2) for the CPU.
Depends on KVM_CAP_ARM_PSCI_0_2.
- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
Depends on KVM_CAP_ARM_PMU_V3.
--- /dev/null
+KVM implements the PSCI (Power State Coordination Interface)
+specification in order to provide services such as CPU on/off, reset
+and power-off to the guest.
+
+The PSCI specification is regularly updated to provide new features,
+and KVM implements these updates if they make sense from a virtualization
+point of view.
+
+This means that a guest booted on two different versions of KVM can
+observe two different "firmware" revisions. This could cause issues if
+a given guest is tied to a particular PSCI revision (unlikely), or if
+a migration causes a different PSCI version to be exposed out of the
+blue to an unsuspecting guest.
+
+In order to remedy this situation, KVM exposes a set of "firmware
+pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
+interface. These registers can be saved/restored by userspace, and set
+to a convenient value if required.
+
+The following register is defined:
+
+* KVM_REG_ARM_PSCI_VERSION:
+
+ - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
+ (and thus has already been initialized)
+ - Returns the current PSCI version on GET_ONE_REG (defaulting to the
+ highest PSCI version implemented by KVM and compatible with v0.2)
+ - Allows any PSCI version implemented by KVM and compatible with
+ v0.2 to be set with SET_ONE_REG
+ - Affects the whole VM (even if the register view is per-vcpu)
flag || value || meaning
==================================================================================
-KVM_HINTS_DEDICATED || 0 || guest checks this feature bit to
- || || determine if there is vCPU pinning
- || || and there is no vCPU over-commitment,
+KVM_HINTS_REALTIME || 0 || guest checks this feature bit to
+ || || determine that vCPUs are never
+ || || preempted for an unlimited time,
|| || allowing optimizations
----------------------------------------------------------------------------------
-----------------------------------
3C59X NETWORK DRIVER
-M: Steffen Klassert <klassert@mathematik.tu-chemnitz.de>
+M: Steffen Klassert <klassert@kernel.org>
L: netdev@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: Documentation/networking/vortex.txt
F: drivers/net/ethernet/3com/3c59x.c
F: drivers/media/dvb-frontends/af9033*
AFFS FILE SYSTEM
+M: David Sterba <dsterba@suse.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Odd Fixes
F: Documentation/filesystems/affs.txt
F: fs/affs/
M: Laura Abbott <labbott@redhat.com>
M: Sumit Semwal <sumit.semwal@linaro.org>
L: devel@driverdev.osuosl.org
+L: dri-devel@lists.freedesktop.org
+L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
S: Supported
F: drivers/staging/android/ion
F: drivers/staging/android/uapi/ion.h
ARM/ARTPEC MACHINE SUPPORT
M: Jesper Nilsson <jesper.nilsson@axis.com>
M: Lars Persson <lars.persson@axis.com>
-M: Niklas Cassel <niklas.cassel@axis.com>
S: Maintained
L: linux-arm-kernel@axis.com
F: arch/arm/mach-artpec
F: drivers/net/ethernet/amd/am79c961a.*
ARM/ENERGY MICRO (SILICON LABS) EFM32 SUPPORT
-M: Uwe Kleine-König <kernel@pengutronix.de>
+M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
N: efm32
ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
R: Fabio Estevam <fabio.estevam@nxp.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
ARM/FREESCALE VYBRID ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
R: Stefan Agner <stefan@agner.ch>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: sound/soc/atmel/tse850-pcm5142.c
AZ6007 DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
F: drivers/net/hamradio/baycom*
BCACHE (BLOCK LAYER CACHE)
-M: Michael Lyle <mlyle@lyle.org>
+M: Coly Li <colyli@suse.de>
M: Kent Overstreet <kent.overstreet@gmail.com>
L: linux-bcache@vger.kernel.org
W: http://bcache.evilpiepirate.org
F: Documentation/bpf/
F: include/linux/bpf*
F: include/linux/filter.h
-F: include/trace/events/bpf.h
F: include/trace/events/xdp.h
F: include/uapi/linux/bpf*
F: include/uapi/linux/filter.h
F: include/uapi/linux/btrfs*
BTTV VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
CPU POWER MONITORING SUBSYSTEM
M: Thomas Renninger <trenn@suse.com>
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-pm@vger.kernel.org
S: Maintained
F: drivers/media/dvb-frontends/cx24120*
CX88 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
DEVICE DIRECT ACCESS (DAX)
M: Dan Williams <dan.j.williams@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
L: linux-nvdimm@lists.01.org
S: Supported
F: drivers/dax/
T: git git://anongit.freedesktop.org/drm/drm-misc
DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
-M: Vinod Koul <vinod.koul@intel.com>
+M: Vinod Koul <vkoul@kernel.org>
L: dmaengine@vger.kernel.org
Q: https://patchwork.kernel.org/project/linux-dmaengine/list/
S: Maintained
EDAC-CORE
M: Borislav Petkov <bp@alien8.de>
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
F: drivers/edac/fsl_ddr_edac.*
EDAC-GHES
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i5000_edac.c
EDAC-I5400
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i5400_edac.c
EDAC-I7300
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i7300_edac.c
EDAC-I7CORE
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/r82600_edac.c
EDAC-SBRIDGE
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/ibm/ehea/
EM28XX VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
F: Documentation/devicetree/bindings/net/fsl-fec.txt
FREESCALE IMX / MXC FRAMEBUFFER DRIVER
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
L: linux-fbdev@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: drivers/media/usb/hdpvr/
HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER
-M: Jimmy Vance <jimmy.vance@hpe.com>
+M: Jerry Hoemann <jerry.hoemann@hpe.com>
S: Supported
F: Documentation/watchdog/hpwdt.txt
F: drivers/watchdog/hpwdt.c
F: include/uapi/linux/ipx.h
F: drivers/staging/ipx/
-IRDA SUBSYSTEM
-M: Samuel Ortiz <samuel@sortiz.org>
-L: irda-users@lists.sourceforge.net (subscribers-only)
-L: netdev@vger.kernel.org
-W: http://irda.sourceforge.net/
-S: Obsolete
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/irda-2.6.git
-F: Documentation/networking/irda.txt
-F: drivers/staging/irda/
-
IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
M: Marc Zyngier <marc.zyngier@arm.com>
S: Maintained
S: Maintained
F: Documentation/kbuild/
F: Makefile
-F: scripts/Makefile.*
+F: scripts/Kbuild*
+F: scripts/Makefile*
F: scripts/basic/
F: scripts/mk*
+F: scripts/mod/
F: scripts/package/
KERNEL JANITORS
F: include/uapi/linux/sunrpc/
KERNEL SELFTEST FRAMEWORK
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-kselftest@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git
+Q: https://patchwork.kernel.org/project/linux-kselftest/list/
S: Maintained
F: tools/testing/selftests/
F: Documentation/dev-tools/kselftest*
F: arch/x86/kvm/svm.c
KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
-M: Christoffer Dall <christoffer.dall@linaro.org>
+M: Christoffer Dall <christoffer.dall@arm.com>
M: Marc Zyngier <marc.zyngier@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.cs.columbia.edu
F: include/kvm/arm_*
KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
-M: Christoffer Dall <christoffer.dall@linaro.org>
+M: Christoffer Dall <christoffer.dall@arm.com>
M: Marc Zyngier <marc.zyngier@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.cs.columbia.edu
LIBNVDIMM BLK: MMIO-APERTURE DRIVER
M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
LIBNVDIMM BTT: BLOCK TRANSLATION TABLE
M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER
M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
M: Dan Williams <dan.j.williams@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/dsa/mv88e6xxx/
+F: linux/platform_data/mv88e6xxx.h
F: Documentation/devicetree/bindings/net/dsa/marvell.txt
MARVELL ARMADA DRM SUPPORT
F: drivers/staging/media/tegra-vde/
MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
P: LinuxTV.org Project
L: linux-media@vger.kernel.org
Q: http://patchwork.ozlabs.org/project/netdev/list/
F: drivers/net/ethernet/mellanox/mlx5/core/en_*
-MELLANOX ETHERNET INNOVA DRIVER
-M: Ilan Tayari <ilant@mellanox.com>
-R: Boris Pismenny <borisp@mellanox.com>
+MELLANOX ETHERNET INNOVA DRIVERS
+M: Boris Pismenny <borisp@mellanox.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
Q: http://patchwork.ozlabs.org/project/netdev/list/
+F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/*
+F: drivers/net/ethernet/mellanox/mlx5/core/accel/*
F: drivers/net/ethernet/mellanox/mlx5/core/fpga/*
F: include/linux/mlx5/mlx5_ifc_fpga.h
-MELLANOX ETHERNET INNOVA IPSEC DRIVER
-M: Ilan Tayari <ilant@mellanox.com>
-R: Boris Pismenny <borisp@mellanox.com>
-L: netdev@vger.kernel.org
-S: Supported
-W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
-F: drivers/net/ethernet/mellanox/mlx5/core/en_ipsec/*
-F: drivers/net/ethernet/mellanox/mlx5/core/ipsec*
-
MELLANOX ETHERNET SWITCH DRIVERS
M: Jiri Pirko <jiri@mellanox.com>
M: Ido Schimmel <idosch@mellanox.com>
F: include/uapi/linux/cciss*.h
F: Documentation/scsi/smartpqi.txt
+MICROSEMI ETHERNET SWITCH DRIVER
+M: Alexandre Belloni <alexandre.belloni@bootlin.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/ethernet/mscc/
+
MICROSOFT SURFACE PRO 3 BUTTON DRIVER
M: Chen Yu <yu.c.chen@intel.com>
L: platform-driver-x86@vger.kernel.org
F: net/core/drop_monitor.c
NETWORKING DRIVERS
+M: "David S. Miller" <davem@davemloft.net>
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net
Q: http://patchwork.ozlabs.org/project/netdev/list/
F: net/netfilter/xt_SECMARK.c
NETWORKING [TLS]
-M: Ilya Lesokhin <ilyal@mellanox.com>
+M: Boris Pismenny <borisp@mellanox.com>
M: Aviad Yehezkel <aviadye@mellanox.com>
M: Dave Watson <davejwatson@fb.com>
L: netdev@vger.kernel.org
F: Documentation/devicetree/bindings/net/nfc/
NFS, SUNRPC, AND LOCKD CLIENTS
-M: Trond Myklebust <trond.myklebust@primarydata.com>
+M: Trond Myklebust <trond.myklebust@hammerspace.com>
M: Anna Schumaker <anna.schumaker@netapp.com>
L: linux-nfs@vger.kernel.org
W: http://client.linux-nfs.org
F: drivers/pci/dwc/
PCIE DRIVER FOR AXIS ARTPEC
-M: Niklas Cassel <niklas.cassel@axis.com>
M: Jesper Nilsson <jesper.nilsson@axis.com>
L: linux-arm-kernel@axis.com
L: linux-pci@vger.kernel.org
F: include/uapi/linux/vfio_ccw.h
S390 ZCRYPT DRIVER
-M: Harald Freudenberger <freude@de.ibm.com>
+M: Harald Freudenberger <freude@linux.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
S: Supported
F: drivers/media/i2c/saa6588*
SAA7134 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
SCTP PROTOCOL
M: Vlad Yasevich <vyasevich@gmail.com>
M: Neil Horman <nhorman@tuxdriver.com>
+M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
L: linux-sctp@vger.kernel.org
W: http://lksctp.sourceforge.net
S: Maintained
F: drivers/media/radio/si4713/radio-usb-si4713.c
SIANO DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
SIOX
M: Gavin Schenk <g.schenk@eckelmann.de>
-M: Uwe Kleine-König <kernel@pengutronix.de>
+M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
S: Supported
F: drivers/siox/*
F: include/trace/events/siox.h
S: Maintained
F: arch/alpha/kernel/srm_env.c
+ST STM32 I2C/SMBUS DRIVER
+M: Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+L: linux-i2c@vger.kernel.org
+S: Maintained
+F: drivers/i2c/busses/i2c-stm32*
+
STABLE BRANCH
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: stable@vger.kernel.org
STMMAC ETHERNET DRIVER
M: Giuseppe Cavallaro <peppe.cavallaro@st.com>
M: Alexandre Torgue <alexandre.torgue@st.com>
+M: Jose Abreu <joabreu@synopsys.com>
L: netdev@vger.kernel.org
W: http://www.stlinux.com
S: Supported
F: drivers/media/i2c/tda9840*
TEA5761 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
F: drivers/media/tuners/tea5761.*
TEA5767 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
F: drivers/iommu/tegra*
TEGRA KBC DRIVER
-M: Rakesh Iyer <riyer@nvidia.com>
M: Laxman Dewangan <ldewangan@nvidia.com>
S: Supported
F: drivers/input/keyboard/tegra-kbc.c
M: Andreas Noever <andreas.noever@gmail.com>
M: Michael Jamet <michael.jamet@intel.com>
M: Mika Westerberg <mika.westerberg@linux.intel.com>
-M: Yehezkel Bernat <yehezkel.bernat@intel.com>
+M: Yehezkel Bernat <YehezkelShB@gmail.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
S: Maintained
F: Documentation/admin-guide/thunderbolt.rst
THUNDERBOLT NETWORK DRIVER
M: Michael Jamet <michael.jamet@intel.com>
M: Mika Westerberg <mika.westerberg@linux.intel.com>
-M: Yehezkel Bernat <yehezkel.bernat@intel.com>
+M: Yehezkel Bernat <YehezkelShB@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/thunderbolt.c
F: drivers/net/ethernet/ti/tlan.*
TM6000 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
USB OVER IP DRIVER
M: Valentina Manea <valentina.manea.m@gmail.com>
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: arch/x86/entry/vdso/
XC2028/3028 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
S: Maintained
F: drivers/media/tuners/tuner-xc2028.*
+XDP SOCKETS (AF_XDP)
+M: Björn Töpel <bjorn.topel@intel.com>
+M: Magnus Karlsson <magnus.karlsson@intel.com>
+L: netdev@vger.kernel.org
+S: Maintained
+F: kernel/bpf/xskmap.c
+F: net/xdp/
+
XEN BLOCK SUBSYSTEM
M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
M: Roger Pau Monné <roger.pau@citrix.com>
VERSION = 4
PATCHLEVEL = 17
SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Fearless Coyote
+EXTRAVERSION = -rc6
+NAME = Merciless Moray
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
config GCC_PLUGIN_STRUCTLEAK
bool "Force initialization of variables containing userspace addresses"
depends on GCC_PLUGINS
+ # Currently STRUCTLEAK inserts initialization out of live scope of
+ # variables from KASAN point of view. This leads to KASAN false
+ # positive reports. Prohibit this combination for now.
+ depends on !KASAN_EXTRA
help
This plugin zero-initializes any structures containing a
__user attribute. This can prevent some classes of information
asflags-y := -DZIMAGE
# Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell $(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
- perl -e 'while (<>) { \
- $$bss_start=hex($$1) if /^([[:xdigit:]]+) B __bss_start$$/; \
- $$bss_end=hex($$1) if /^([[:xdigit:]]+) B __bss_stop$$/; \
- }; printf "%d\n", $$bss_end - $$bss_start;')
+KBSS_SZ = $(shell echo $$(($$($(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
+ sed -n -e 's/^\([^ ]*\) [AB] __bss_start$$/-0x\1/p' \
+ -e 's/^\([^ ]*\) [AB] __bss_stop$$/+0x\1/p') )) )
LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
# Supply ZRELADDR to the decompressor via a linker symbol.
ifneq ($(CONFIG_AUTO_ZRELADDR),y)
#if defined(CONFIG_DEBUG_ICEDCC)
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c0, c5, 0
.endm
#elif defined(CONFIG_CPU_XSCALE)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c8, c0, 0
.endm
#else
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c1, c0, 0
.endm
#if defined(CONFIG_ARCH_SA1100)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
mov \rb, #0x80000000 @ physical base address
#ifdef CONFIG_DEBUG_LL_SER3
add \rb, \rb, #0x00050000 @ Ser3
#endif
.endm
#else
- .macro loadsp, rb, tmp
- addruart \rb, \tmp
+ .macro loadsp, rb, tmp1, tmp2
+ addruart \rb, \tmp1, \tmp2
.endm
#endif
#endif
bl decompress_kernel
bl cache_clean_flush
bl cache_off
- mov r1, r7 @ restore architecture number
- mov r2, r8 @ restore atags pointer
#ifdef CONFIG_ARM_VIRT_EXT
mrs r0, spsr @ Get saved CPU boot mode
b 1b
@ puts corrupts {r0, r1, r2, r3}
-puts: loadsp r3, r1
+puts: loadsp r3, r2, r1
1: ldrb r2, [r0], #1
teq r2, #0
moveq pc, lr
@ putc corrupts {r0, r1, r2, r3}
putc:
mov r2, r0
+ loadsp r3, r1, r0
mov r0, #0
- loadsp r3, r1
b 2b
@ memdump corrupts {r0, r1, r2, r3, r10, r11, r12, lr}
__enter_kernel:
mov r0, #0 @ must be 0
+ mov r1, r7 @ restore architecture number
+ mov r2, r8 @ restore atags pointer
ARM( mov pc, r4 ) @ call kernel
M_CLASS( add r4, r4, #1 ) @ enter in Thumb mode for M class
THUMB( bx r4 ) @ entry point is always ARM for A/R classes
timer@20200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x20200 0x100>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&periph_clk>;
};
stdout-path = "serial2:115200n8";
};
- memory {
- device_type = "memory";
+ memory@c0000000 {
+ /* 128 MB DDR2 SDRAM @ 0xc0000000 */
reg = <0xc0000000 0x08000000>;
};
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*/
-#include "skeleton.dtsi"
#include <dt-bindings/interrupt-controller/irq.h>
/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ chosen { };
+ aliases { };
+
+ memory@c0000000 {
+ device_type = "memory";
+ reg = <0xc0000000 0x0>;
+ };
+
arm {
#address-cells = <1>;
#size-cells = <1>;
pmx_core: pinmux@14120 {
compatible = "pinctrl-single";
reg = <0x14120 0x50>;
- #address-cells = <1>;
- #size-cells = <0>;
#pinctrl-cells = <2>;
pinctrl-single,bit-per-mux;
pinctrl-single,register-width = <32>;
/ {
model = "DM8148 EVM";
- compatible = "ti,dm8148-evm", "ti,dm8148";
+ compatible = "ti,dm8148-evm", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
/ {
model = "HP t410 Smart Zero Client";
- compatible = "hp,t410", "ti,dm8148";
+ compatible = "hp,t410", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
/ {
model = "DM8168 EVM";
- compatible = "ti,dm8168-evm", "ti,dm8168";
+ compatible = "ti,dm8168-evm", "ti,dm8168", "ti,dm816";
memory@80000000 {
device_type = "memory";
/ {
model = "DRA62x J5 Eco EVM";
- compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148";
+ compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
function = "gmii";
groups = "gmii_gmac0_grp";
};
- /* Settings come from OpenWRT */
+ /* Settings come from OpenWRT, pins on SL3516 */
conf0 {
- pins = "R8 GMAC0 RXDV", "U11 GMAC1 RXDV";
+ pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV";
skew-delay = <0>;
};
conf1 {
- pins = "T8 GMAC0 RXC", "T11 GMAC1 RXC";
+ pins = "Y7 GMAC0 RXC", "Y11 GMAC1 RXC";
skew-delay = <15>;
};
conf2 {
- pins = "P8 GMAC0 TXEN", "V11 GMAC1 TXEN";
+ pins = "T8 GMAC0 TXEN", "W11 GMAC1 TXEN";
skew-delay = <7>;
};
conf3 {
- pins = "V7 GMAC0 TXC";
+ pins = "U8 GMAC0 TXC";
skew-delay = <11>;
};
conf4 {
- pins = "P10 GMAC1 TXC";
+ pins = "V11 GMAC1 TXC";
skew-delay = <10>;
};
conf5 {
/* The data lines all have default skew */
- pins = "U8 GMAC0 RXD0", "V8 GMAC0 RXD1",
- "P9 GMAC0 RXD2", "R9 GMAC0 RXD3",
- "U7 GMAC0 TXD0", "T7 GMAC0 TXD1",
- "R7 GMAC0 TXD2", "P7 GMAC0 TXD3",
- "R11 GMAC1 RXD0", "P11 GMAC1 RXD1",
- "V12 GMAC1 RXD2", "U12 GMAC1 RXD3",
- "R10 GMAC1 TXD0", "T10 GMAC1 TXD1",
- "U10 GMAC1 TXD2", "V10 GMAC1 TXD3";
+ pins = "W8 GMAC0 RXD0", "V9 GMAC0 RXD1",
+ "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3",
+ "T7 GMAC0 TXD0", "U6 GMAC0 TXD1",
+ "V7 GMAC0 TXD2", "U7 GMAC0 TXD3",
+ "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1",
+ "T11 GMAC1 RXD2", "W12 GMAC1 RXD3",
+ "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1",
+ "W10 GMAC1 TXD2", "T9 GMAC1 TXD3";
skew-delay = <7>;
};
/* Set up drive strength on GMAC0 to 16 mA */
};
can1: can@53fe4000 {
- compatible = "fsl,imx35-flexcan";
+ compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
reg = <0x53fe4000 0x1000>;
clocks = <&clks 33>, <&clks 33>;
clock-names = "ipg", "per";
};
can2: can@53fe8000 {
- compatible = "fsl,imx35-flexcan";
+ compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
reg = <0x53fe8000 0x1000>;
clocks = <&clks 34>, <&clks 34>;
clock-names = "ipg", "per";
};
touchscreen@20 {
- compatible = "syna,rmi4_i2c";
+ compatible = "syna,rmi4-i2c";
reg = <0x20>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_ts>;
rmi4-f11@11 {
reg = <0x11>;
- touch-inverted-y;
- touch-swapped-x-y;
+ touchscreen-inverted-y;
+ touchscreen-swapped-x-y;
syna,sensor-type = <1>;
};
};
};
can1: can@53fc8000 {
- compatible = "fsl,imx53-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fc8000 0x4000>;
interrupts = <82>;
clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>,
};
can2: can@53fcc000 {
- compatible = "fsl,imx53-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fcc000 0x4000>;
interrupts = <83>;
clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>,
crypto: caam@30900000 {
compatible = "fsl,sec-v4.0";
+ fsl,sec-era = <8>;
#address-cells = <1>;
#size-cells = <1>;
reg = <0x30900000 0x40000>;
gpio = <&gpio1 3 0>; /* gpio_3 */
startup-delay-us = <70000>;
enable-active-high;
- vin-supply = <&vmmc2>;
+ vin-supply = <&vaux3>;
};
/* HS USB Host PHY on PORT 1 */
twl_audio: audio {
compatible = "ti,twl4030-audio";
codec {
+ ti,hs_extmute_gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>;
};
};
};
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */
OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */
+ OMAP3_CORE1_IOPAD(0x20ba, PIN_OUTPUT | MUX_MODE4) /* gpmc_ncs6.gpio_57 */
>;
};
};
};
wl127x_gpio: pinmux_wl127x_gpio_pin {
pinctrl-single,pins = <
- OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */
+ OMAP3_WKUP_IOPAD(0x2a0a, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */
OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */
>;
};
#include "twl4030.dtsi"
#include "twl4030_omap3.dtsi"
+&vaux3 {
+ regulator-min-microvolt = <2800000>;
+ regulator-max-microvolt = <2800000>;
+};
+
&twl {
twl_power: power {
compatible = "ti,twl4030-power-idle-osc-off", "ti,twl4030-power-idle";
cm2: cm2@8000 {
compatible = "ti,omap4-cm2", "simple-bus";
- reg = <0x8000 0x3000>;
+ reg = <0x8000 0x2000>;
#address-cells = <1>;
#size-cells = <1>;
- ranges = <0 0x8000 0x3000>;
+ ranges = <0 0x8000 0x2000>;
cm2_clocks: clocks {
#address-cells = <1>;
prm: prm@6000 {
compatible = "ti,omap4-prm";
- reg = <0x6000 0x3000>;
+ reg = <0x6000 0x2000>;
interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <1>;
- ranges = <0 0x6000 0x3000>;
+ ranges = <0 0x6000 0x2000>;
prm_clocks: clocks {
#address-cells = <1>;
port@0 {
reg = <0>;
adv7511_in: endpoint {
- remote-endpoint = <&du_out_lvds0>;
+ remote-endpoint = <&lvds0_out>;
};
};
status = "okay";
clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 722>,
- <&cpg CPG_MOD 726>, <&cpg CPG_MOD 725>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "du.2", "lvds.0", "lvds.1",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "du.2", "dclkin.0", "dclkin.1";
ports {
port@0 {
remote-endpoint = <&adv7123_in>;
};
};
+ };
+};
+
+&lvds0 {
+ status = "okay";
+
+ ports {
port@1 {
endpoint {
remote-endpoint = <&adv7511_in>;
};
};
- port@2 {
+ };
+};
+
+&lvds1 {
+ status = "okay";
+
+ ports {
+ port@1 {
lvds_connector: endpoint {
};
};
du: display@feb00000 {
compatible = "renesas,du-r8a7790";
- reg = <0 0xfeb00000 0 0x70000>,
- <0 0xfeb90000 0 0x1c>,
- <0 0xfeb94000 0 0x1c>;
- reg-names = "du", "lvds.0", "lvds.1";
+ reg = <0 0xfeb00000 0 0x70000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 269 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 722>, <&cpg CPG_MOD 726>,
- <&cpg CPG_MOD 725>;
- clock-names = "du.0", "du.1", "du.2", "lvds.0",
- "lvds.1";
+ <&cpg CPG_MOD 722>;
+ clock-names = "du.0", "du.1", "du.2";
status = "disabled";
ports {
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
};
};
port@2 {
reg = <2>;
du_out_lvds1: endpoint {
+ remote-endpoint = <&lvds1_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7790-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
+ };
+ };
+ };
+ };
+
+ lvds1: lvds@feb94000 {
+ compatible = "renesas,r8a7790-lvds";
+ reg = <0 0xfeb94000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 725>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+ resets = <&cpg 725>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds1_in: endpoint {
+ remote-endpoint = <&du_out_lvds1>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds1_out: endpoint {
};
};
};
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
remote-endpoint = <&adv7511_in>;
};
};
+ };
+};
+
+&lvds0 {
+ status = "okay";
+
+ ports {
port@1 {
lvds_connector: endpoint {
};
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x3_clk>, <&x16_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
};
};
+&lvds0 {
+ status = "okay";
+
+ ports {
+ port@1 {
+ lvds_connector: endpoint {
+ };
+ };
+ };
+};
+
&rcar_sound {
pinctrl-0 = <&ssi_pins &audio_clk_pins>;
pinctrl-names = "default";
du: display@feb00000 {
compatible = "renesas,du-r8a7791";
- reg = <0 0xfeb00000 0 0x40000>,
- <0 0xfeb90000 0 0x1c>;
- reg-names = "du", "lvds.0";
+ reg = <0 0xfeb00000 0 0x40000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>,
- <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 726>;
- clock-names = "du.0", "du.1", "lvds.0";
+ <&cpg CPG_MOD 723>;
+ clock-names = "du.0", "du.1";
status = "disabled";
ports {
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7791-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
};
};
};
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
remote-endpoint = <&adv7511_in>;
};
};
+ };
+};
+
+&lvds0 {
+ ports {
port@1 {
lvds_connector: endpoint {
};
du: display@feb00000 {
compatible = "renesas,du-r8a7793";
- reg = <0 0xfeb00000 0 0x40000>,
- <0 0xfeb90000 0 0x1c>;
- reg-names = "du", "lvds.0";
+ reg = <0 0xfeb00000 0 0x40000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>,
- <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 726>;
- clock-names = "du.0", "du.1", "lvds.0";
+ <&cpg CPG_MOD 723>;
+ clock-names = "du.0", "du.1";
status = "disabled";
ports {
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7793-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
};
};
};
phy_type = "ulpi";
clocks = <&tegra_car TEGRA20_CLK_USB2>,
<&tegra_car TEGRA20_CLK_PLL_U>,
- <&tegra_car TEGRA20_CLK_PLL_P_OUT4>;
+ <&tegra_car TEGRA20_CLK_CDEV2>;
clock-names = "reg", "pll_u", "ulpi-link";
resets = <&tegra_car 58>, <&tegra_car 22>;
reset-names = "usb", "utmi-pads";
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SYSVIPC=y
CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_USER_NS=y
CONFIG_RELAY=y
CONFIG_PCI=y
CONFIG_PREEMPT=y
CONFIG_AEABI=y
+CONFIG_HIGHMEM=y
+CONFIG_CMA=y
CONFIG_CMDLINE="console=ttyS0,115200n8"
CONFIG_KEXEC=y
CONFIG_BINFMT_MISC=y
CONFIG_PM=y
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_MTD=y
CONFIG_MTD_BLOCK=y
CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_ATA=y
CONFIG_PATA_FTIDE010=y
+CONFIG_NETDEVICES=y
+CONFIG_GEMINI_ETHERNET=y
+CONFIG_MDIO_BITBANG=y
+CONFIG_MDIO_GPIO=y
+CONFIG_REALTEK_PHY=y
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_SERIAL_8250_RUNTIME_UARTS=1
CONFIG_SERIAL_OF_PLATFORM=y
# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
+CONFIG_I2C_GPIO=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SENSORS_GPIO_FAN=y
+CONFIG_SENSORS_LM75=y
+CONFIG_THERMAL=y
CONFIG_WATCHDOG=y
-CONFIG_GEMINI_WATCHDOG=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_DRM=y
+CONFIG_DRM_PANEL_ILITEK_IL9322=y
+CONFIG_DRM_TVE200=y
+CONFIG_LOGO=y
CONFIG_USB=y
CONFIG_USB_MON=y
CONFIG_USB_FOTG210_HCD=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_RTC_CLASS=y
CONFIG_DMADEVICES=y
CONFIG_MTD_NAND=y
CONFIG_MTD_NAND_DENALI_DT=y
CONFIG_MTD_SPI_NOR=y
+# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set
CONFIG_SPI_CADENCE_QUADSPI=y
CONFIG_OF_OVERLAY=y
CONFIG_OF_CONFIGFS=y
#endif
.endm
+#ifdef CONFIG_KPROBES
+#define _ASM_NOKPROBE(entry) \
+ .pushsection "_kprobe_blacklist", "aw" ; \
+ .balign 4 ; \
+ .long entry; \
+ .popsection
+#else
+#define _ASM_NOKPROBE(entry)
+#endif
+
#endif /* __ASM_ASSEMBLER_H__ */
/* Interrupt controller */
struct vgic_dist vgic;
int max_vcpus;
+
+ /* Mandated version of PSCI */
+ u32 psci_version;
};
#define KVM_NR_MEM_OBJS 40
return 8;
}
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+ gpa_t gpa, void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_read_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
static inline void *kvm_get_hyp_vector(void)
{
return kvm_ksym_ref(__kvm_hyp_vector);
#define KVM_REG_ARM_VFP_FPINST 0x1009
#define KVM_REG_ARM_VFP_FPINST2 0x100A
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+++ /dev/null
-#ifndef __ASM_SIGINFO_H
-#define __ASM_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-#endif
{
struct pt_regs regs;
- crash_setup_regs(®s, NULL);
+ crash_setup_regs(®s, get_irq_regs());
printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n",
smp_processor_id());
crash_save_cpu(®s, smp_processor_id());
cpu_relax();
}
+void crash_smp_send_stop(void)
+{
+ static int cpus_stopped;
+ unsigned long msecs;
+
+ if (cpus_stopped)
+ return;
+
+ atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+ smp_call_function(machine_crash_nonpanic_core, NULL, false);
+ msecs = 1000; /* Wait at most a second for the other cpus to stop */
+ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+ mdelay(1);
+ msecs--;
+ }
+ if (atomic_read(&waiting_for_crash_ipi) > 0)
+ pr_warn("Non-crashing CPUs did not react to IPI\n");
+
+ cpus_stopped = 1;
+}
+
static void machine_kexec_mask_interrupts(void)
{
unsigned int i;
void machine_crash_shutdown(struct pt_regs *regs)
{
- unsigned long msecs;
-
local_irq_disable();
-
- atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
- smp_call_function(machine_crash_nonpanic_core, NULL, false);
- msecs = 1000; /* Wait at most a second for the other cpus to stop */
- while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
- mdelay(1);
- msecs--;
- }
- if (atomic_read(&waiting_for_crash_ipi) > 0)
- pr_warn("Non-crashing CPUs did not react to IPI\n");
+ crash_smp_send_stop();
crash_save_cpu(regs, smp_processor_id());
machine_kexec_mask_interrupts();
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
+#include <linux/kprobes.h>
#include <linux/module.h>
#include <linux/kexec.h>
#include <linux/bug.h>
raw_spin_unlock_irqrestore(&undef_lock, flags);
}
-static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
+static nokprobe_inline
+int call_undef_hook(struct pt_regs *regs, unsigned int instr)
{
struct undef_hook *hook;
unsigned long flags;
arm_notify_die("Oops - undefined instruction", regs, &info, 0, 6);
}
+NOKPROBE_SYMBOL(do_undefinstr)
/*
* Handle FIQ similarly to NMI on x86 systems.
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <kvm/arm_psci.h>
#include <asm/cputype.h>
#include <linux/uaccess.h>
#include <asm/kvm.h>
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+ + kvm_arm_get_fw_num_regs(vcpu)
+ NUM_TIMER_REGS;
}
uindices++;
}
+ ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += kvm_arm_get_fw_num_regs(vcpu);
+
ret = copy_timer_indices(vcpu, uindices);
if (ret)
return ret;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_get_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return get_timer_reg(vcpu, reg);
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_set_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return set_timer_reg(vcpu, reg);
mov r0, #0
ret lr
ENDPROC(__get_user_1)
+_ASM_NOKPROBE(__get_user_1)
ENTRY(__get_user_2)
check_uaccess r0, 2, r1, r2, __get_user_bad
mov r0, #0
ret lr
ENDPROC(__get_user_2)
+_ASM_NOKPROBE(__get_user_2)
ENTRY(__get_user_4)
check_uaccess r0, 4, r1, r2, __get_user_bad
mov r0, #0
ret lr
ENDPROC(__get_user_4)
+_ASM_NOKPROBE(__get_user_4)
ENTRY(__get_user_8)
check_uaccess r0, 8, r1, r2, __get_user_bad8
mov r0, #0
ret lr
ENDPROC(__get_user_8)
+_ASM_NOKPROBE(__get_user_8)
#ifdef __ARMEB__
ENTRY(__get_user_32t_8)
mov r0, #0
ret lr
ENDPROC(__get_user_32t_8)
+_ASM_NOKPROBE(__get_user_32t_8)
ENTRY(__get_user_64t_1)
check_uaccess r0, 1, r1, r2, __get_user_bad8
mov r0, #0
ret lr
ENDPROC(__get_user_64t_1)
+_ASM_NOKPROBE(__get_user_64t_1)
ENTRY(__get_user_64t_2)
check_uaccess r0, 2, r1, r2, __get_user_bad8
mov r0, #0
ret lr
ENDPROC(__get_user_64t_2)
+_ASM_NOKPROBE(__get_user_64t_2)
ENTRY(__get_user_64t_4)
check_uaccess r0, 4, r1, r2, __get_user_bad8
mov r0, #0
ret lr
ENDPROC(__get_user_64t_4)
+_ASM_NOKPROBE(__get_user_64t_4)
#endif
__get_user_bad8:
ret lr
ENDPROC(__get_user_bad)
ENDPROC(__get_user_bad8)
+_ASM_NOKPROBE(__get_user_bad)
+_ASM_NOKPROBE(__get_user_bad8)
.pushsection __ex_table, "a"
.long 1b, __get_user_bad
-1
};
+#define DA830_MMCSD_WP_PIN GPIO_TO_PIN(2, 1)
+#define DA830_MMCSD_CD_PIN GPIO_TO_PIN(2, 2)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
/* gpio chip 1 contains gpio range 32-63 */
- GPIO_LOOKUP("davinci_gpio.1", 2, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.1", 1, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
-1
};
+#define DA850_MMCSD_CD_PIN GPIO_TO_PIN(4, 0)
+#define DA850_MMCSD_WP_PIN GPIO_TO_PIN(4, 1)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
/* gpio chip 2 contains gpio range 64-95 */
- GPIO_LOOKUP("davinci_gpio.2", 0, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.2", 1, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
#include <linux/gpio.h>
#include <linux/gpio/machine.h>
#include <linux/clk.h>
+#include <linux/dm9000.h>
#include <linux/videodev2.h>
#include <media/i2c/tvp514x.h>
#include <linux/spi/spi.h>
},
};
+#define DM355_I2C_SDA_PIN GPIO_TO_PIN(0, 15)
+#define DM355_I2C_SCL_PIN GPIO_TO_PIN(0, 14)
+
static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
- .dev_id = "i2c_davinci",
+ .dev_id = "i2c_davinci.1",
.table = {
- GPIO_LOOKUP("davinci_gpio", 15, "sda",
+ GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SDA_PIN, "sda",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
- GPIO_LOOKUP("davinci_gpio", 14, "scl",
+ GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SCL_PIN, "scl",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
},
};
},
};
+static struct dm9000_plat_data dm335evm_dm9000_platdata;
+
static struct platform_device dm355evm_dm9000 = {
.name = "dm9000",
.id = -1,
.resource = dm355evm_dm9000_rsrc,
.num_resources = ARRAY_SIZE(dm355evm_dm9000_rsrc),
+ .dev = {
+ .platform_data = &dm335evm_dm9000_platdata,
+ },
};
static struct tvp514x_platform_data tvp5146_pdata = {
#include <linux/i2c.h>
#include <linux/platform_data/pcf857x.h>
#include <linux/platform_data/at24.h>
+#include <linux/platform_data/gpio-davinci.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/rawnand.h>
#include <linux/mtd/partitions.h>
},
};
+#define DM644X_I2C_SDA_PIN GPIO_TO_PIN(2, 12)
+#define DM644X_I2C_SCL_PIN GPIO_TO_PIN(2, 11)
+
static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
- .dev_id = "i2c_davinci",
+ .dev_id = "i2c_davinci.1",
.table = {
- GPIO_LOOKUP("davinci_gpio", 44, "sda",
+ GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SDA_PIN, "sda",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
- GPIO_LOOKUP("davinci_gpio", 43, "scl",
+ GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SCL_PIN, "scl",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
},
};
.set_clock = set_vpif_clock,
.subdevinfo = dm646x_vpif_subdev,
.subdev_count = ARRAY_SIZE(dm646x_vpif_subdev),
+ .i2c_adapter_id = 1,
.chan_config[0] = {
.outputs = dm6467_ch0_outputs,
.output_count = ARRAY_SIZE(dm6467_ch0_outputs),
},
- .card_name = "DM646x EVM",
+ .card_name = "DM646x EVM Video Display",
};
/**
.setup_input_channel_mode = setup_vpif_input_channel_mode,
.subdev_info = vpif_capture_sdev_info,
.subdev_count = ARRAY_SIZE(vpif_capture_sdev_info),
+ .i2c_adapter_id = 1,
.chan_config[0] = {
.inputs = dm6467_ch0_inputs,
.input_count = ARRAY_SIZE(dm6467_ch0_inputs),
.fid_pol = 0,
},
},
+ .card_name = "DM646x EVM Video Capture",
};
static void __init evm_init_video(void)
-1
};
+#define DA850_HAWK_MMCSD_CD_PIN GPIO_TO_PIN(3, 12)
+#define DA850_HAWK_MMCSD_WP_PIN GPIO_TO_PIN(3, 13)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
- /* CD: gpio3_12: gpio60: chip 1 contains gpio range 32-63*/
- GPIO_LOOKUP("davinci_gpio.0", 28, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.0", 29, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
[IRQ_DM646X_MCASP0TXINT] = 7,
[IRQ_DM646X_MCASP0RXINT] = 7,
[IRQ_DM646X_RESERVED_3] = 7,
- [IRQ_DM646X_MCASP1TXINT] = 7, /* clockevent */
+ [IRQ_DM646X_MCASP1TXINT] = 7,
+ [IRQ_TINT0_TINT12] = 7, /* clockevent */
[IRQ_TINT0_TINT34] = 7, /* clocksource */
[IRQ_TINT1_TINT12] = 7, /* DSP timer */
[IRQ_TINT1_TINT34] = 7, /* system tick */
static struct pm_clk_notifier_block platform_domain_notifier = {
.pm_domain = &keystone_pm_domain,
+ .con_ids = { NULL },
};
static const struct of_device_id of_keystone_table[] = {
irq_num = gpio_to_irq(gpio);
fiq_count = fiq_buffer[FIQ_CNT_INT_00 + gpio];
- while (irq_counter[gpio] < fiq_count) {
- if (gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
- struct irq_data *d = irq_get_irq_data(irq_num);
-
- /*
- * It looks like handle_edge_irq() that
- * OMAP GPIO edge interrupts default to,
- * expects interrupt already unmasked.
- */
- if (irq_chip && irq_chip->irq_unmask)
+ if (irq_counter[gpio] < fiq_count &&
+ gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
+ struct irq_data *d = irq_get_irq_data(irq_num);
+
+ /*
+ * handle_simple_irq() that OMAP GPIO edge
+ * interrupts default to since commit 80ac93c27441
+ * requires interrupt already acked and unmasked.
+ */
+ if (irq_chip) {
+ if (irq_chip->irq_ack)
+ irq_chip->irq_ack(d);
+ if (irq_chip->irq_unmask)
irq_chip->irq_unmask(d);
}
- generic_handle_irq(irq_num);
-
- irq_counter[gpio]++;
}
+ for (; irq_counter[gpio] < fiq_count; irq_counter[gpio]++)
+ generic_handle_irq(irq_num);
}
return IRQ_HANDLED;
}
include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORCE
$(call filechk,offsets,__TI_PM_ASM_OFFSETS_H__)
-# For rule to generate ti-emif-asm-offsets.h dependency
-include drivers/memory/Makefile.asm-offsets
-
-arch/arm/mach-omap2/sleep33xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
-arch/arm/mach-omap2/sleep43xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
+$(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
#include <linux/kbuild.h>
#include <linux/platform_data/pm33xx.h>
+#include <linux/ti-emif-sram.h>
int main(void)
{
+ ti_emif_asm_offsets();
+
DEFINE(AMX3_PM_WFI_FLAGS_OFFSET,
offsetof(struct am33xx_pm_sram_data, wfi_flags));
DEFINE(AMX3_PM_L2_AUX_CTRL_VAL_OFFSET,
((prev & OMAP_POWERSTATE_MASK) << 0));
trace_power_domain_target_rcuidle(pwrdm->name,
trace_state,
- smp_processor_id());
+ raw_smp_processor_id());
}
break;
default:
if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
/* Trace the pwrdm desired target state */
trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
- smp_processor_id());
+ raw_smp_processor_id());
/* Program the pwrdm desired target state */
ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
}
* Dave Gerlach, Vaibhav Bedia
*/
-#include <generated/ti-emif-asm-offsets.h>
#include <generated/ti-pm-asm-offsets.h>
#include <linux/linkage.h>
#include <linux/ti-emif-sram.h>
* Dave Gerlach, Vaibhav Bedia
*/
-#include <generated/ti-emif-asm-offsets.h>
#include <generated/ti-pm-asm-offsets.h>
#include <linux/linkage.h>
#include <linux/ti-emif-sram.h>
.dev_id = "spi_gpio",
.table = {
GPIO_LOOKUP("GPIOB", 4,
- "gpio-sck", GPIO_ACTIVE_HIGH),
+ "sck", GPIO_ACTIVE_HIGH),
GPIO_LOOKUP("GPIOB", 9,
- "gpio-mosi", GPIO_ACTIVE_HIGH),
+ "mosi", GPIO_ACTIVE_HIGH),
GPIO_LOOKUP("GPIOH", 10,
"cs", GPIO_ACTIVE_HIGH),
{ },
#define SCRATCH_SIZE 80
/* total stack size used in JITed code */
-#define _STACK_SIZE \
- (ctx->prog->aux->stack_depth + \
- + SCRATCH_SIZE + \
- + 4 /* extra for skb_copy_bits buffer */)
-
-#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
+#define _STACK_SIZE (ctx->prog->aux->stack_depth + SCRATCH_SIZE)
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
/* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE-off-4)
-
-/* Offset of skb_copy_bits buffer */
-#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE)
+#define STACK_VAR(off) (STACK_SIZE - off)
#if __LINUX_ARM_ARCH__ < 7
emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
break;
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
- case BPF_LD | BPF_ABS | BPF_W:
- case BPF_LD | BPF_ABS | BPF_H:
- case BPF_LD | BPF_ABS | BPF_B:
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
- case BPF_LD | BPF_IND | BPF_W:
- case BPF_LD | BPF_IND | BPF_H:
- case BPF_LD | BPF_IND | BPF_B:
- {
- const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */
- const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/
- /* rtn value */
- const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */
- const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */
- const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */
- const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */
- int size;
-
- /* Setting up first argument */
- emit(ARM_MOV_R(r0, r4), ctx);
-
- /* Setting up second argument */
- emit_a32_mov_i(r1, imm, false, ctx);
- if (BPF_MODE(code) == BPF_IND)
- emit_a32_alu_r(r1, src_lo, false, sstk, ctx,
- false, false, BPF_ADD);
-
- /* Setting up third argument */
- switch (BPF_SIZE(code)) {
- case BPF_W:
- size = 4;
- break;
- case BPF_H:
- size = 2;
- break;
- case BPF_B:
- size = 1;
- break;
- default:
- return -EINVAL;
- }
- emit_a32_mov_i(r2, size, false, ctx);
-
- /* Setting up fourth argument */
- emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx);
-
- /* Setting up function pointer to call */
- emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx);
- emit_blx_r(r6, ctx);
-
- emit(ARM_EOR_R(r1, r1, r1), ctx);
- /* Check if return address is NULL or not.
- * if NULL then jump to epilogue
- * else continue to load the value from retn address
- */
- emit(ARM_CMP_I(r0, 0), ctx);
- jmp_offset = epilogue_offset(ctx);
- check_imm24(jmp_offset);
- _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
-
- /* Load value from the address */
- switch (BPF_SIZE(code)) {
- case BPF_W:
- emit(ARM_LDR_I(r0, r0, 0), ctx);
- emit_rev32(r0, r0, ctx);
- break;
- case BPF_H:
- emit(ARM_LDRH_I(r0, r0, 0), ctx);
- emit_rev16(r0, r0, ctx);
- break;
- case BPF_B:
- emit(ARM_LDRB_I(r0, r0, 0), ctx);
- /* No need to reverse */
- break;
- }
- break;
- }
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
{
unsigned long flags;
struct kprobe *p = &op->kp;
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ struct kprobe_ctlblk *kcb;
/* Save skipped registers */
regs->ARM_pc = (unsigned long)op->kp.addr;
regs->ARM_ORIG_r0 = ~0UL;
local_irq_save(flags);
+ kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
local_irq_restore(flags);
}
+NOKPROBE_SYMBOL(optimized_callback)
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig)
{
if (exceptions == VFP_EXCEPTION_ERROR) {
vfp_panic("unhandled bounce", inst);
- vfp_raise_sigfpe(FPE_FIXME, regs);
+ vfp_raise_sigfpe(FPE_FLTINV, regs);
return;
}
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS += -DCONFIG_ARCH_SUPPORTS_INT128
+else
KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128)
+endif
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
+
+&usb2_phy0 {
+ /*
+ * even though the schematics don't show it:
+ * HDMI_5V is also used as supply for the USB VBUS.
+ */
+ phy-supply = <&hdmi_5v>;
+};
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
no-map;
};
};
+
+ soc {
+ usb0: usb@c9000000 {
+ status = "disabled";
+ compatible = "amlogic,meson-gxl-dwc3";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "usb_general";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "usb_otg";
+
+ dwc3: dwc3@c9000000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0xc9000000 0x0 0x100000>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ maximum-speed = "high-speed";
+ snps,dis_u2_susphy_quirk;
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>;
+ };
+ };
+ };
+};
+
+&apb {
+ usb2_phy0: phy@78000 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78000 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb2_phy1: phy@78020 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78020 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb3_phy: phy@78080 {
+ compatible = "amlogic,meson-gxl-usb3-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78080 0x0 0x20>;
+ interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc CLKID_USB>, <&clkc_AO CLKID_AO_CEC_32K>;
+ clock-names = "phy", "peripheral";
+ resets = <&reset RESET_USB_OTG>, <&reset RESET_USB_OTG>;
+ reset-names = "phy", "peripheral";
+ status = "okay";
+ };
};
ðmac {
status = "okay";
vref-supply = <&vddio_ao18>;
};
+
+&usb0 {
+ status = "okay";
+};
};
};
+&apb {
+ usb2_phy2: phy@78040 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78040 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+};
+
&clkc_AO {
compatible = "amlogic,meson-gxm-aoclkc", "amlogic,meson-gx-aoclkc";
};
&hdmi_tx {
compatible = "amlogic,meson-gxm-dw-hdmi", "amlogic,meson-gx-dw-hdmi";
};
+
+&dwc3 {
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>, <&usb2_phy2>;
+};
gpio_keys {
compatible = "gpio-keys";
- #address-cells = <1>;
- #size-cells = <0>;
power-button {
debounce_interval = <50>;
#size-cells = <1>;
ranges = <0x0 0x0 0x67d00000 0x00800000>;
- sata0: ahci@210000 {
+ sata0: ahci@0 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00210000 0x1000>;
+ reg = <0x00000000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy0: sata_phy@212100 {
+ sata_phy0: sata_phy@2100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00212100 0x1000>;
+ reg = <0x00002100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata1: ahci@310000 {
+ sata1: ahci@10000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00310000 0x1000>;
+ reg = <0x00010000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy1: sata_phy@312100 {
+ sata_phy1: sata_phy@12100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00312100 0x1000>;
+ reg = <0x00012100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata2: ahci@120000 {
+ sata2: ahci@20000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00120000 0x1000>;
+ reg = <0x00020000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy2: sata_phy@122100 {
+ sata_phy2: sata_phy@22100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00122100 0x1000>;
+ reg = <0x00022100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata3: ahci@130000 {
+ sata3: ahci@30000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00130000 0x1000>;
+ reg = <0x00030000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy3: sata_phy@132100 {
+ sata_phy3: sata_phy@32100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00132100 0x1000>;
+ reg = <0x00032100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata4: ahci@330000 {
+ sata4: ahci@100000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00330000 0x1000>;
+ reg = <0x00100000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy4: sata_phy@332100 {
+ sata_phy4: sata_phy@102100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00332100 0x1000>;
+ reg = <0x00102100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata5: ahci@400000 {
+ sata5: ahci@110000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00400000 0x1000>;
+ reg = <0x00110000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy5: sata_phy@402100 {
+ sata_phy5: sata_phy@112100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00402100 0x1000>;
+ reg = <0x00112100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata6: ahci@410000 {
+ sata6: ahci@120000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00410000 0x1000>;
+ reg = <0x00120000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy6: sata_phy@412100 {
+ sata_phy6: sata_phy@122100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00412100 0x1000>;
+ reg = <0x00122100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
};
};
- sata7: ahci@420000 {
+ sata7: ahci@130000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00420000 0x1000>;
+ reg = <0x00130000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
};
};
- sata_phy7: sata_phy@422100 {
+ sata_phy7: sata_phy@132100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00422100 0x1000>;
+ reg = <0x00132100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
reg = <0x14d60000 0x100>;
dmas = <&pdma0 31 &pdma0 30>;
dma-names = "tx", "rx";
- interrupts = <GIC_SPI 435 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_SCLK_I2S1>;
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
- <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
+ <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>,
+ <&CP110_LABEL(clk) 1 18>;
clock-names = "pp_clk", "gop_clk",
- "mg_clk", "axi_clk";
+ "mg_clk", "mg_core_clk", "axi_clk";
marvell,system-controller = <&CP110_LABEL(syscon0)>;
status = "disabled";
dma-coherent;
#size-cells = <0>;
compatible = "marvell,xmdio";
reg = <0x12a600 0x10>;
+ clocks = <&CP110_LABEL(clk) 1 5>,
+ <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
status = "disabled";
};
compatible = "ethernet-phy-ieee802.3-c22";
reg = <0x0>;
interrupt-parent = <&gpio>;
- interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_LOW>;
};
};
};
drive-strength = <2>; /* 2 MA */
};
};
+
+ blsp1_uart1_default: blsp1_uart1_default {
+ mux {
+ pins = "gpio41", "gpio42", "gpio43", "gpio44";
+ function = "blsp_uart2";
+ };
+
+ config {
+ pins = "gpio41", "gpio42", "gpio43", "gpio44";
+ drive-strength = <16>;
+ bias-disable;
+ };
+ };
+
+ blsp1_uart1_sleep: blsp1_uart1_sleep {
+ mux {
+ pins = "gpio41", "gpio42", "gpio43", "gpio44";
+ function = "gpio";
+ };
+
+ config {
+ pins = "gpio41", "gpio42", "gpio43", "gpio44";
+ drive-strength = <2>;
+ bias-disable;
+ };
+ };
};
};
};
+ bt_en_gpios: bt_en_gpios {
+ pinconf {
+ pins = "gpio19";
+ function = PMIC_GPIO_FUNC_NORMAL;
+ output-low;
+ power-source = <PM8994_GPIO_S4>; // 1.8V
+ qcom,drive-strength = <PMIC_GPIO_STRENGTH_LOW>;
+ bias-pull-down;
+ };
+ };
+
+ wlan_en_gpios: wlan_en_gpios {
+ pinconf {
+ pins = "gpio8";
+ function = PMIC_GPIO_FUNC_NORMAL;
+ output-low;
+ power-source = <PM8994_GPIO_S4>; // 1.8V
+ qcom,drive-strength = <PMIC_GPIO_STRENGTH_LOW>;
+ bias-pull-down;
+ };
+ };
+
volume_up_gpio: pm8996_gpio2 {
pinconf {
pins = "gpio2";
};
};
+ divclk4_pin_a: divclk4 {
+ pinconf {
+ pins = "gpio18";
+ function = PMIC_GPIO_FUNC_FUNC2;
+
+ bias-disable;
+ power-source = <PM8994_GPIO_S4>;
+ };
+ };
+
usb3_vbus_det_gpio: pm8996_gpio22 {
pinconf {
pins = "gpio22";
aliases {
serial0 = &blsp2_uart1;
serial1 = &blsp2_uart2;
+ serial2 = &blsp1_uart1;
i2c0 = &blsp1_i2c2;
i2c1 = &blsp2_i2c1;
i2c2 = &blsp2_i2c0;
stdout-path = "serial0:115200n8";
};
+ clocks {
+ divclk4: divclk4 {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "divclk4";
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&divclk4_pin_a>;
+ };
+ };
+
soc {
+ serial@7570000 {
+ label = "BT-UART";
+ status = "okay";
+ pinctrl-names = "default", "sleep";
+ pinctrl-0 = <&blsp1_uart1_default>;
+ pinctrl-1 = <&blsp1_uart1_sleep>;
+
+ bluetooth {
+ compatible = "qcom,qca6174-bt";
+
+ /* bt_disable_n gpio */
+ enable-gpios = <&pm8994_gpios 19 GPIO_ACTIVE_HIGH>;
+
+ clocks = <&divclk4>;
+ };
+ };
+
serial@75b0000 {
label = "LS-UART1";
status = "okay";
pinctrl-0 = <&usb2_vbus_det_gpio>;
};
+ bt_en: bt-en-1-8v {
+ pinctrl-names = "default";
+ pinctrl-0 = <&bt_en_gpios>;
+ compatible = "regulator-fixed";
+ regulator-name = "bt-en-regulator";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+
+ /* WLAN card specific delay */
+ startup-delay-us = <70000>;
+ enable-active-high;
+ };
+
+ wlan_en: wlan-en-1-8v {
+ pinctrl-names = "default";
+ pinctrl-0 = <&wlan_en_gpios>;
+ compatible = "regulator-fixed";
+ regulator-name = "wlan-en-regulator";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+
+ gpio = <&pm8994_gpios 8 0>;
+
+ /* WLAN card specific delay */
+ startup-delay-us = <70000>;
+ enable-active-high;
+ };
+
agnoc@0 {
qcom,pcie@600000 {
+ status = "okay";
perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>;
+ vddpe-supply = <&wlan_en>;
+ vddpe1-supply = <&bt_en>;
};
qcom,pcie@608000 {
#clock-cells = <1>;
};
+ blsp1_uart1: serial@7570000 {
+ compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+ reg = <0x07570000 0x1000>;
+ interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>,
+ <&gcc GCC_BLSP1_AHB_CLK>;
+ clock-names = "core", "iface";
+ status = "disabled";
+ };
+
blsp1_spi0: spi@7575000 {
compatible = "qcom,spi-qup-v2.2.1";
reg = <0x07575000 0x600>;
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
reg = <0>;
};
};
+
+&pinctrl_ether_rgmii {
+ tx {
+ pins = "RGMII_TXCLK", "RGMII_TXD0", "RGMII_TXD1",
+ "RGMII_TXD2", "RGMII_TXD3", "RGMII_TXCTL";
+ drive-strength = <9>;
+ };
+};
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
#define ARM_CPU_IMP_CAVIUM 0x43
#define ARM_CPU_IMP_BRCM 0x42
#define ARM_CPU_IMP_QCOM 0x51
+#define ARM_CPU_IMP_NVIDIA 0x4E
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
#define QCOM_CPU_PART_FALKOR 0xC00
#define QCOM_CPU_PART_KRYO 0x200
+#define NVIDIA_CPU_PART_DENVER 0x003
+#define NVIDIA_CPU_PART_CARMEL 0x004
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
+#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
#ifndef __ASSEMBLY__
} else {
u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
sctlr |= (1 << 25);
- vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr);
+ vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
}
}
/* Interrupt controller */
struct vgic_dist vgic;
+
+ /* Mandated version of PSCI */
+ u32 psci_version;
};
#define KVM_NR_MEM_OBJS 40
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+ gpa_t gpa, void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_read_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
#ifdef CONFIG_KVM_INDIRECT_VECTORS
/*
* EL2 vectors can be mapped and rerouted in a number of ways,
u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
Elf64_Sym *sym);
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val);
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val);
#ifdef CONFIG_RANDOMIZE_BASE
extern u64 module_alloc_base;
}
}
-extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
+extern void __sync_icache_dcache(pte_t pteval);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
pte_t old_pte;
if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
- __sync_icache_dcache(pte, addr);
+ __sync_icache_dcache(pte);
/*
* If the existing pte is valid, check for potential race with
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+ MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
{},
};
static const struct midr_range kpti_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+ { /* sentinel */ }
};
char const *str = "command line option";
}
#ifdef CONFIG_ARM64_ERRATUM_843419
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val)
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val)
{
struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
&mod->arch.init;
insn &= ~BIT(31);
} else {
/* out of range for ADR -> emit a veneer */
- val = module_emit_adrp_veneer(mod, place, val & ~0xfff);
+ val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff);
if (!val)
return -ENOEXEC;
insn = aarch64_insn_gen_branch_imm((u64)place, val,
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
+#include <linux/nospec.h>
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
switch (note_type) {
case NT_ARM_HW_BREAK:
- if (idx < ARM_MAX_BRP)
- bp = tsk->thread.debug.hbp_break[idx];
+ if (idx >= ARM_MAX_BRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_BRP);
+ bp = tsk->thread.debug.hbp_break[idx];
break;
case NT_ARM_HW_WATCH:
- if (idx < ARM_MAX_WRP)
- bp = tsk->thread.debug.hbp_watch[idx];
+ if (idx >= ARM_MAX_WRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_WRP);
+ bp = tsk->thread.debug.hbp_watch[idx];
break;
}
+out:
return bp;
}
{
int ret;
u32 kdata;
- mm_segment_t old_fs = get_fs();
- set_fs(KERNEL_DS);
/* Watchpoint */
if (num < 0) {
ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata);
} else {
ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata);
}
- set_fs(old_fs);
if (!ret)
ret = put_user(kdata, data);
{
int ret;
u32 kdata = 0;
- mm_segment_t old_fs = get_fs();
if (num == 0)
return 0;
if (ret)
return ret;
- set_fs(KERNEL_DS);
if (num < 0)
ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata);
else
ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata);
- set_fs(old_fs);
return ret;
}
* If we were single stepping, we want to get the step exception after
* we return from the trap.
*/
- user_fastforward_single_step(current);
+ if (user_mode(regs))
+ user_fastforward_single_step(current);
}
static LIST_HEAD(undef_hook);
}
/* Force signals we don't understand to SIGKILL */
- if (WARN_ON(signal != SIGKILL ||
+ if (WARN_ON(signal != SIGKILL &&
siginfo_layout(signal, code) != SIL_FAULT)) {
signal = SIGKILL;
}
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <kvm/arm_psci.h>
#include <asm/cputype.h>
#include <linux/uaccess.h>
#include <asm/kvm.h>
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
- + NUM_TIMER_REGS;
+ + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS;
}
/**
uindices++;
}
+ ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += kvm_arm_get_fw_num_regs(vcpu);
+
ret = copy_timer_indices(vcpu, uindices);
if (ret)
return ret;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_get_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return get_timer_reg(vcpu, reg);
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_set_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return set_timer_reg(vcpu, reg);
#include <linux/compiler.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/kvm_host.h>
+#include <linux/swab.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
+static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+
+ return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+}
+
/*
* __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the
* guest.
addr += fault_ipa - vgic->vgic_cpu_base;
if (kvm_vcpu_dabt_iswrite(vcpu)) {
- u32 data = vcpu_data_guest_to_host(vcpu,
- vcpu_get_reg(vcpu, rd),
- sizeof(u32));
+ u32 data = vcpu_get_reg(vcpu, rd);
+ if (__is_be(vcpu)) {
+ /* guest pre-swabbed data, undo this for writel() */
+ data = swab32(data);
+ }
writel_relaxed(data, addr);
} else {
u32 data = readl_relaxed(addr);
- vcpu_set_reg(vcpu, rd, vcpu_data_host_to_guest(vcpu, data,
- sizeof(u32)));
+ if (__is_be(vcpu)) {
+ /* guest expects swabbed data */
+ data = swab32(data);
+ }
+ vcpu_set_reg(vcpu, rd, data);
}
return 1;
if (id == SYS_ID_AA64PFR0_EL1) {
if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
- pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("SVE unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
} else if (id == SYS_ID_AA64MMFR1_EL1) {
if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
- pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("LORegions unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
}
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
-fcall-saved-x18 -fomit-frame-pointer
CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+GCOV_PROFILE_atomic_ll_sc.o := n
+KASAN_SANITIZE_atomic_ll_sc.o := n
+KCOV_INSTRUMENT_atomic_ll_sc.o := n
+UBSAN_SANITIZE_atomic_ll_sc.o := n
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
flush_ptrace_access(vma, page, uaddr, dst, len);
}
-void __sync_icache_dcache(pte_t pte, unsigned long addr)
+void __sync_icache_dcache(pte_t pte)
{
struct page *page = pte_page(pte);
void __init free_initrd_mem(unsigned long start, unsigned long end)
{
- if (!keep_initrd)
+ if (!keep_initrd) {
free_reserved_area((void *)start, (void *)end, 0, "initrd");
+ memblock_free(__virt_to_phys(start), end - start);
+ }
}
static int __init keepinitrd_setup(char *__unused)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+ early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
(void *)mod_shadow_start);
kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
(unsigned long)kasan_mem_to_shadow(end),
- pfn_to_nid(virt_to_pfn(start)));
+ early_pfn_to_nid(virt_to_pfn(start)));
}
/*
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/printk.h>
-#include <linux/skbuff.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
ctx->idx++;
}
+static inline void emit_a64_mov_i(const int is64, const int reg,
+ const s32 val, struct jit_ctx *ctx)
+{
+ u16 hi = val >> 16;
+ u16 lo = val & 0xffff;
+
+ if (hi & 0x8000) {
+ if (hi == 0xffff) {
+ emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
+ } else {
+ emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
+ if (lo != 0xffff)
+ emit(A64_MOVK(is64, reg, lo, 0), ctx);
+ }
+ } else {
+ emit(A64_MOVZ(is64, reg, lo, 0), ctx);
+ if (hi)
+ emit(A64_MOVK(is64, reg, hi, 16), ctx);
+ }
+}
+
+static int i64_i16_blocks(const u64 val, bool inverse)
+{
+ return (((val >> 0) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 16) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 32) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+ (((val >> 48) & 0xffff) != (inverse ? 0xffff : 0x0000));
+}
+
static inline void emit_a64_mov_i64(const int reg, const u64 val,
struct jit_ctx *ctx)
{
- u64 tmp = val;
- int shift = 0;
-
- emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
- tmp >>= 16;
- shift += 16;
- while (tmp) {
- if (tmp & 0xffff)
- emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
- tmp >>= 16;
- shift += 16;
+ u64 nrm_tmp = val, rev_tmp = ~val;
+ bool inverse;
+ int shift;
+
+ if (!(nrm_tmp >> 32))
+ return emit_a64_mov_i(0, reg, (u32)val, ctx);
+
+ inverse = i64_i16_blocks(nrm_tmp, true) < i64_i16_blocks(nrm_tmp, false);
+ shift = max(round_down((inverse ? (fls64(rev_tmp) - 1) :
+ (fls64(nrm_tmp) - 1)), 16), 0);
+ if (inverse)
+ emit(A64_MOVN(1, reg, (rev_tmp >> shift) & 0xffff, shift), ctx);
+ else
+ emit(A64_MOVZ(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+ shift -= 16;
+ while (shift >= 0) {
+ if (((nrm_tmp >> shift) & 0xffff) != (inverse ? 0xffff : 0x0000))
+ emit(A64_MOVK(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+ shift -= 16;
}
}
+/*
+ * This is an unoptimized 64 immediate emission used for BPF to BPF call
+ * addresses. It will always do a full 64 bit decomposition as otherwise
+ * more complexity in the last extra pass is required since we previously
+ * reserved 4 instructions for the address.
+ */
static inline void emit_addr_mov_i64(const int reg, const u64 val,
struct jit_ctx *ctx)
{
}
}
-static inline void emit_a64_mov_i(const int is64, const int reg,
- const s32 val, struct jit_ctx *ctx)
-{
- u16 hi = val >> 16;
- u16 lo = val & 0xffff;
-
- if (hi & 0x8000) {
- if (hi == 0xffff) {
- emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
- } else {
- emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
- emit(A64_MOVK(is64, reg, lo, 0), ctx);
- }
- } else {
- emit(A64_MOVZ(is64, reg, lo, 0), ctx);
- if (hi)
- emit(A64_MOVK(is64, reg, hi, 16), ctx);
- }
-}
-
static inline int bpf2a64_offset(int bpf_to, int bpf_from,
const struct jit_ctx *ctx)
{
/* Tail call offset to jump into */
#define PROLOGUE_OFFSET 7
-static int build_prologue(struct jit_ctx *ctx)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
{
const struct bpf_prog *prog = ctx->prog;
const u8 r6 = bpf2a64[BPF_REG_6];
* | ... | BPF prog stack
* | |
* +-----+ <= (BPF_FP - prog->aux->stack_depth)
- * |RSVD | JIT scratchpad
+ * |RSVD | padding
* current A64_SP => +-----+ <= (BPF_FP - ctx->stack_size)
* | |
* | ... | Function call stack
/* Set up BPF prog stack base register */
emit(A64_MOV(1, fp, A64_SP), ctx);
- /* Initialize tail_call_cnt */
- emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+ if (!ebpf_from_cbpf) {
+ /* Initialize tail_call_cnt */
+ emit(A64_MOVZ(1, tcc, 0, 0), ctx);
- cur_offset = ctx->idx - idx0;
- if (cur_offset != PROLOGUE_OFFSET) {
- pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
- cur_offset, PROLOGUE_OFFSET);
- return -1;
+ cur_offset = ctx->idx - idx0;
+ if (cur_offset != PROLOGUE_OFFSET) {
+ pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+ cur_offset, PROLOGUE_OFFSET);
+ return -1;
+ }
}
- /* 4 byte extra for skb_copy_bits buffer */
- ctx->stack_size = prog->aux->stack_depth + 4;
- ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+ ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
/* Set up function call stack */
emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
break;
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
- case BPF_LD | BPF_ABS | BPF_W:
- case BPF_LD | BPF_ABS | BPF_H:
- case BPF_LD | BPF_ABS | BPF_B:
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
- case BPF_LD | BPF_IND | BPF_W:
- case BPF_LD | BPF_IND | BPF_H:
- case BPF_LD | BPF_IND | BPF_B:
- {
- const u8 r0 = bpf2a64[BPF_REG_0]; /* r0 = return value */
- const u8 r6 = bpf2a64[BPF_REG_6]; /* r6 = pointer to sk_buff */
- const u8 fp = bpf2a64[BPF_REG_FP];
- const u8 r1 = bpf2a64[BPF_REG_1]; /* r1: struct sk_buff *skb */
- const u8 r2 = bpf2a64[BPF_REG_2]; /* r2: int k */
- const u8 r3 = bpf2a64[BPF_REG_3]; /* r3: unsigned int size */
- const u8 r4 = bpf2a64[BPF_REG_4]; /* r4: void *buffer */
- const u8 r5 = bpf2a64[BPF_REG_5]; /* r5: void *(*func)(...) */
- int size;
-
- emit(A64_MOV(1, r1, r6), ctx);
- emit_a64_mov_i(0, r2, imm, ctx);
- if (BPF_MODE(code) == BPF_IND)
- emit(A64_ADD(0, r2, r2, src), ctx);
- switch (BPF_SIZE(code)) {
- case BPF_W:
- size = 4;
- break;
- case BPF_H:
- size = 2;
- break;
- case BPF_B:
- size = 1;
- break;
- default:
- return -EINVAL;
- }
- emit_a64_mov_i64(r3, size, ctx);
- emit(A64_SUB_I(1, r4, fp, ctx->stack_size), ctx);
- emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
- emit(A64_BLR(r5), ctx);
- emit(A64_MOV(1, r0, A64_R(0)), ctx);
-
- jmp_offset = epilogue_offset(ctx);
- check_imm19(jmp_offset);
- emit(A64_CBZ(1, r0, jmp_offset), ctx);
- emit(A64_MOV(1, r5, r0), ctx);
- switch (BPF_SIZE(code)) {
- case BPF_W:
- emit(A64_LDR32(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
- emit(A64_REV32(0, r0, r0), ctx);
-#endif
- break;
- case BPF_H:
- emit(A64_LDRH(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
- emit(A64_REV16(0, r0, r0), ctx);
-#endif
- break;
- case BPF_B:
- emit(A64_LDRB(r0, r5, A64_ZR), ctx);
- break;
- }
- break;
- }
default:
pr_err_once("unknown opcode %02x\n", code);
return -EINVAL;
struct bpf_prog *tmp, *orig_prog = prog;
struct bpf_binary_header *header;
struct arm64_jit_data *jit_data;
+ bool was_classic = bpf_prog_was_classic(prog);
bool tmp_blinded = false;
bool extra_pass = false;
struct jit_ctx ctx;
goto out_off;
}
- if (build_prologue(&ctx)) {
+ if (build_prologue(&ctx, was_classic)) {
prog = orig_prog;
goto out_off;
}
skip_init_ctx:
ctx.idx = 0;
- build_prologue(&ctx);
+ build_prologue(&ctx, was_classic);
if (build_body(&ctx)) {
bpf_jit_binary_free(header);
memcpy((void *) dst, src, count);
}
+static inline void memset_io(volatile void __iomem *addr, int value,
+ size_t size)
+{
+ memset((void __force *)addr, value, size);
+}
+
#define PCI_IO_ADDR (volatile void __iomem *)
/*
memcpy(dst, src, len);
return csum_partial(dst, len, sum);
}
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
#define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
#endif
-#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780)
-#include <asm/mach-jz4740/base.h>
-#define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset))
+#ifdef CONFIG_MACH_INGENIC
+#define INGENIC_UART0_BASE_ADDR 0x10030000
+#define PORT(offset) (CKSEG1ADDR(INGENIC_UART0_BASE_ADDR) + (4 * offset))
#endif
#ifdef CONFIG_CPU_XLR
# SPDX-License-Identifier: GPL-2.0
dtb-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += nexys4ddr.dtb
-
-obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
its-y := vmlinux.its.S
its-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += board-boston.its.S
its-$(CONFIG_FIT_IMAGE_FDT_NI169445) += board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += board-xilfpga.its.S
/*
* Copy the floating-point context to the supplied NT_PRFPREG buffer.
* Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR and FIR registers separately.
*/
static int fpr_get(struct task_struct *target,
const struct user_regset *regset,
void *kbuf, void __user *ubuf)
{
const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+ const int fir_pos = fcr31_pos + sizeof(u32);
int err;
if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&target->thread.fpu.fcr31,
fcr31_pos, fcr31_pos + sizeof(u32));
+ if (err)
+ return err;
+
+ err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &boot_cpu_data.fpu_id,
+ fir_pos, fir_pos + sizeof(u32));
return err;
}
/*
* Copy the supplied NT_PRFPREG buffer to the floating-point context.
* Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR register separately. Ignore the incoming FIR register
+ * contents though, as the register is read-only.
*
* We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
* which is supposed to have been guaranteed by the kernel before
const void *kbuf, const void __user *ubuf)
{
const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+ const int fir_pos = fcr31_pos + sizeof(u32);
u32 fcr31;
int err;
ptrace_setfcr31(target, fcr31);
}
+ if (count > 0)
+ err = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ fir_pos,
+ fir_pos + sizeof(u32));
+
return err;
}
fregs = get_fpu_regs(child);
#ifdef CONFIG_32BIT
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
init_fp_ctx(child);
#ifdef CONFIG_32BIT
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
break;
}
fregs = get_fpu_regs(child);
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
sizeof(child->thread.fpu));
child->thread.fpu.fcr31 = 0;
}
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
{ "cache", VCPU_STAT(cache_exits), KVM_STAT_VCPU },
{ "signal", VCPU_STAT(signal_exits), KVM_STAT_VCPU },
{ "interrupt", VCPU_STAT(int_exits), KVM_STAT_VCPU },
- { "cop_unsuable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
+ { "cop_unusable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
{ "tlbmod", VCPU_STAT(tlbmod_exits), KVM_STAT_VCPU },
{ "tlbmiss_ld", VCPU_STAT(tlbmiss_ld_exits), KVM_STAT_VCPU },
{ "tlbmiss_st", VCPU_STAT(tlbmiss_st_exits), KVM_STAT_VCPU },
/*
* Either no secondary cache or the available caches don't have the
* subset property so we have to flush the primary caches
- * explicitly
+ * explicitly.
+ * If we would need IPI to perform an INDEX-type operation, then
+ * we have to use the HIT-type alternative as IPI cannot be used
+ * here due to interrupts possibly being disabled.
*/
- if (size >= dcache_size) {
+ if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
return;
}
- if (size >= dcache_size) {
+ if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
* struct jit_ctx - JIT context
* @skf: The sk_filter
* @stack_size: eBPF stack size
- * @tmp_offset: eBPF $sp offset to 8-byte temporary memory
* @idx: Instruction index
* @flags: JIT flags
* @offsets: Instruction offsets
struct jit_ctx {
const struct bpf_prog *skf;
int stack_size;
- int tmp_offset;
u32 idx;
u32 flags;
u32 *offsets;
locals_size = (ctx->flags & EBPF_SEEN_FP) ? MAX_BPF_STACK : 0;
stack_adjust += locals_size;
- ctx->tmp_offset = locals_size;
ctx->stack_size = stack_adjust;
emit_instr(ctx, lui, reg, upper >> 16);
emit_instr(ctx, addiu, reg, reg, lower);
}
-
}
static int gen_imm_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
return 0;
}
-static void * __must_check
-ool_skb_header_pointer(const struct sk_buff *skb, int offset,
- int len, void *buffer)
-{
- return skb_header_pointer(skb, offset, len, buffer);
-}
-
-static int size_to_len(const struct bpf_insn *insn)
-{
- switch (BPF_SIZE(insn->code)) {
- case BPF_B:
- return 1;
- case BPF_H:
- return 2;
- case BPF_W:
- return 4;
- case BPF_DW:
- return 8;
- }
- return 0;
-}
-
static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value)
{
if (value >= 0xffffffffffff8000ull || value < 0x8000ull) {
return -EINVAL;
break;
- case BPF_LD | BPF_B | BPF_ABS:
- case BPF_LD | BPF_H | BPF_ABS:
- case BPF_LD | BPF_W | BPF_ABS:
- case BPF_LD | BPF_DW | BPF_ABS:
- ctx->flags |= EBPF_SAVE_RA;
-
- gen_imm_to_reg(insn, MIPS_R_A1, ctx);
- emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
-
- if (insn->imm < 0) {
- emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper);
- } else {
- emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
- emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
- }
- goto ld_skb_common;
-
- case BPF_LD | BPF_B | BPF_IND:
- case BPF_LD | BPF_H | BPF_IND:
- case BPF_LD | BPF_W | BPF_IND:
- case BPF_LD | BPF_DW | BPF_IND:
- ctx->flags |= EBPF_SAVE_RA;
- src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
- if (src < 0)
- return src;
- ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
- if (ts == REG_32BIT_ZERO_EX) {
- /* sign extend */
- emit_instr(ctx, sll, MIPS_R_A1, src, 0);
- src = MIPS_R_A1;
- }
- if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) {
- emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm);
- } else {
- gen_imm_to_reg(insn, MIPS_R_AT, ctx);
- emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src);
- }
- /* truncate to 32-bit int */
- emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0);
- emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
- emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO);
-
- emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper);
- emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
- emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
- emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT);
-
-ld_skb_common:
- emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9);
- /* delay slot move */
- emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO);
-
- /* Check the error value */
- b_off = b_imm(exit_idx, ctx);
- if (is_bad_offset(b_off)) {
- target = j_target(ctx, exit_idx);
- if (target == (unsigned int)-1)
- return -E2BIG;
-
- if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
- ctx->offsets[this_idx] |= OFFSETS_B_CONV;
- ctx->long_b_conversion = 1;
- }
- emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3);
- emit_instr(ctx, nop);
- emit_instr(ctx, j, target);
- emit_instr(ctx, nop);
- } else {
- emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off);
- emit_instr(ctx, nop);
- }
-
-#ifdef __BIG_ENDIAN
- need_swap = false;
-#else
- need_swap = true;
-#endif
- dst = MIPS_R_V0;
- switch (BPF_SIZE(insn->code)) {
- case BPF_B:
- emit_instr(ctx, lbu, dst, 0, MIPS_R_V0);
- break;
- case BPF_H:
- emit_instr(ctx, lhu, dst, 0, MIPS_R_V0);
- if (need_swap)
- emit_instr(ctx, wsbh, dst, dst);
- break;
- case BPF_W:
- emit_instr(ctx, lw, dst, 0, MIPS_R_V0);
- if (need_swap) {
- emit_instr(ctx, wsbh, dst, dst);
- emit_instr(ctx, rotr, dst, dst, 16);
- }
- break;
- case BPF_DW:
- emit_instr(ctx, ld, dst, 0, MIPS_R_V0);
- if (need_swap) {
- emit_instr(ctx, dsbh, dst, dst);
- emit_instr(ctx, dshd, dst, dst);
- }
- break;
- }
-
- break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
case BPF_ALU | BPF_END | BPF_FROM_LE:
dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+# Default kernel to build
+all: bzImage
+
zImage: vmlinuz
Image: vmlinux
* Walks up the device tree looking for a device of the specified type.
* If it finds it, it returns it. If not, it returns NULL.
*/
-const struct parisc_device * __init
+const struct parisc_device *
find_pa_parent_type(const struct parisc_device *padev, int type)
{
const struct device *dev = &padev->dev;
* Checks all the children of @parent for a matching @id. If none
* found, it allocates a new device and returns it.
*/
-static struct parisc_device * alloc_tree_node(struct device *parent, char id)
+static struct parisc_device * __init alloc_tree_node(
+ struct device *parent, char id)
{
struct match_id_data d = {
.id = id,
* devices which are not physically connected (such as extra serial &
* keyboard ports). This problem is not yet solved.
*/
-static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high,
- struct device *parent)
+static void __init walk_native_bus(unsigned long io_io_low,
+ unsigned long io_io_high, struct device *parent)
{
int i, devices_found = 0;
unsigned long hpa = io_io_low;
* pcibios_init_bridge() initializes cache line and default latency
* for pci controllers and pci-pci bridges
*/
-void __init pcibios_init_bridge(struct pci_dev *dev)
+void __ref pcibios_init_bridge(struct pci_dev *dev)
{
unsigned short bridge_ctl, bridge_ctl_new;
}
#ifdef CONFIG_PROC_FS
-int __init
-setup_profiling_timer(unsigned int multiplier)
+int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
device_initcall(rtc_init);
#endif
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
{
static struct pdc_tod tod_data;
if (pdc_tod_read(&tod_data) == 0) {
if (pdc_instr(&instr) == PDC_OK)
ivap[0] = instr;
+ /*
+ * Rules for the checksum of the HPMC handler:
+ * 1. The IVA does not point to PDC/PDH space (ie: the OS has installed
+ * its own IVA).
+ * 2. The word at IVA + 32 is nonzero.
+ * 3. If Length (IVA + 60) is not zero, then Length (IVA + 60) and
+ * Address (IVA + 56) are word-aligned.
+ * 4. The checksum of the 8 words starting at IVA + 32 plus the sum of
+ * the Length/4 words starting at Address is zero.
+ */
+
/* Compute Checksum for HPMC handler */
length = os_hpmc_size;
ivap[7] = length;
}
}
-void free_initmem(void)
+void __ref free_initmem(void)
{
unsigned long init_begin = (unsigned long)__init_begin;
unsigned long init_end = (unsigned long)__init_end;
#endif
#if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__)
-#ifdef PPC64_ELF_ABI_v1
+/*
+ * Some syscall entry functions on powerpc start with "ppc_" (fork and clone,
+ * for instance) or ppc32_/ppc64_. We should also match the sys_ variant with
+ * those.
+ */
#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+#ifdef PPC64_ELF_ABI_v1
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+ /* We need to skip past the initial dot, and the __se_sys alias */
+ return !strcmp(sym + 1, name) ||
+ (!strncmp(sym, ".__se_sys", 9) && !strcmp(sym + 6, name)) ||
+ (!strncmp(sym, ".ppc_", 5) && !strcmp(sym + 5, name + 4)) ||
+ (!strncmp(sym, ".ppc32_", 7) && !strcmp(sym + 7, name + 4)) ||
+ (!strncmp(sym, ".ppc64_", 7) && !strcmp(sym + 7, name + 4));
+}
+#else
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
{
- /*
- * Compare the symbol name with the system call name. Skip the .sys or .SyS
- * prefix from the symbol name and the sys prefix from the system call name and
- * just match the rest. This is only needed on ppc64 since symbol names on
- * 32bit do not start with a period so the generic function will work.
- */
- return !strcmp(sym + 4, name + 3);
+ return !strcmp(sym, name) ||
+ (!strncmp(sym, "__se_sys", 8) && !strcmp(sym + 5, name)) ||
+ (!strncmp(sym, "ppc_", 4) && !strcmp(sym + 4, name + 4)) ||
+ (!strncmp(sym, "ppc32_", 6) && !strcmp(sym + 6, name + 4)) ||
+ (!strncmp(sym, "ppc64_", 6) && !strcmp(sym + 6, name + 4));
}
#endif
#endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */
u64 saved_msr; /* MSR saved here by enter_rtas */
u16 trap_save; /* Used when bad stack is encountered */
u8 irq_soft_mask; /* mask for irq soft masking */
- u8 soft_enabled; /* irq soft-enable flag */
u8 irq_happened; /* irq happened while soft-disabled */
u8 io_sync; /* writel() needs spin_unlock sync */
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
unsigned long flags,
- struct npu_context *(*cb)(struct npu_context *, void *),
+ void (*cb)(struct npu_context *, void *),
void *priv);
extern void pnv_npu2_destroy_context(struct npu_context *context,
struct pci_dev *gpdev);
extern int stop_topology_update(void);
extern int prrn_is_enabled(void);
extern int find_and_online_cpu_nid(int cpu);
+extern int timed_topology_update(int nsecs);
#else
static inline int start_topology_update(void)
{
{
return 0;
}
+static inline int timed_topology_update(int nsecs)
+{
+ return 0;
+}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
-#if defined(CONFIG_PPC_SPLPAR)
-extern int timed_topology_update(int nsecs);
-#else
-#define timed_topology_update(nsecs)
-#endif /* CONFIG_PPC_SPLPAR */
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
-
#include <asm-generic/topology.h>
#ifdef CONFIG_SMP
if (pfn != ULONG_MAX) {
*phys_addr =
(pfn << PAGE_SHIFT);
- handled = 1;
}
}
}
* kernel/exception-64s.h
*/
if (get_paca()->in_mce < MAX_MCE_DEPTH)
- if (!mce_find_instr_ea_and_pfn(regs, addr,
- phys_addr))
- handled = 1;
+ mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
}
found = 1;
}
const struct mce_ierror_table itable[])
{
struct mce_error_info mce_err = { 0 };
- uint64_t addr, phys_addr;
+ uint64_t addr, phys_addr = ULONG_MAX;
uint64_t srr1 = regs->msr;
long handled;
#endif
#ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+ /*
+ * This is a special case because it never returns, so the NMI IPI
+ * handling would never mark it as done, which makes any later
+ * smp_send_nmi_ipi() call spin forever. Mark it done now.
+ *
+ * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+ */
+ nmi_ipi_lock();
+ nmi_ipi_busy_count--;
+ nmi_ipi_unlock();
+
+ /* Remove this CPU */
+ set_cpu_online(smp_processor_id(), false);
+
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
static void stop_this_cpu(void *dummy)
-#endif
{
/* Remove this CPU */
set_cpu_online(smp_processor_id(), false);
void smp_send_stop(void)
{
-#ifdef CONFIG_NMI_IPI
- smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
+ static bool stopped = false;
+
+ /*
+ * Prevent waiting on csd lock from a previous smp_send_stop.
+ * This is racy, but in general callers try to do the right
+ * thing and only fire off one smp_send_stop (e.g., see
+ * kernel/panic.c)
+ */
+ if (stopped)
+ return;
+
+ stopped = true;
+
smp_call_function(stop_this_cpu, NULL, 0);
-#endif
}
+#endif /* CONFIG_NMI_IPI */
struct thread_info *current_set[NR_CPUS];
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
}
+#ifdef CONFIG_ALTIVEC
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+ kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL);
+}
+#endif
+
void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
start, start + size, rc);
return -EFAULT;
}
+ flush_inval_dcache_range(start, start + size);
return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
}
/* Remove htab bolted mappings for this section of memory */
start = (unsigned long)__va(start);
+ flush_inval_dcache_range(start, start + size);
ret = remove_section_mapping(start, start + size);
/* Ensure all vmalloc mappings are flushed in case they also
# Arch-specific network modules
#
ifeq ($(CONFIG_PPC64),y)
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
else
obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
endif
* with our redzone usage.
*
* [ prev sp ] <-------------
- * [ nv gpr save area ] 8*8 |
+ * [ nv gpr save area ] 6*8 |
* [ tail_call_cnt ] 8 |
* [ local_tmp_var ] 8 |
* fp (r31) --> [ ebpf stack space ] upto 512 |
* sp (r1) ---> [ stack pointer ] --------------
*/
-/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
-#define BPF_PPC_STACK_SAVE (8*8)
+/* for gpr non volatile registers BPG_REG_6 to 10 */
+#define BPF_PPC_STACK_SAVE (6*8)
/* for bpf JIT code internal usage */
#define BPF_PPC_STACK_LOCALS 16
/* stack frame excluding BPF stack, ensure this is quadword aligned */
#ifndef __ASSEMBLY__
/* BPF register usage */
-#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 0)
-#define SKB_DATA_REG (MAX_BPF_JIT_REG + 1)
-#define TMP_REG_1 (MAX_BPF_JIT_REG + 2)
-#define TMP_REG_2 (MAX_BPF_JIT_REG + 3)
+#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
/* BPF to ppc register mappings */
static const int b2p[] = {
[BPF_REG_FP] = 31,
/* eBPF jit internal registers */
[BPF_REG_AX] = 2,
- [SKB_HLEN_REG] = 25,
- [SKB_DATA_REG] = 26,
[TMP_REG_1] = 9,
[TMP_REG_2] = 10
};
-/* PPC NVR range -- update this if we ever use NVRs below r24 */
-#define BPF_PPC_NVR_MIN 24
-
-/* Assembly helpers */
-#define DECLARE_LOAD_FUNC(func) u64 func(u64 r3, u64 r4); \
- u64 func##_negative_offset(u64 r3, u64 r4); \
- u64 func##_positive_offset(u64 r3, u64 r4);
-
-DECLARE_LOAD_FUNC(sk_load_word);
-DECLARE_LOAD_FUNC(sk_load_half);
-DECLARE_LOAD_FUNC(sk_load_byte);
-
-#define CHOOSE_LOAD_FUNC(imm, func) \
- (imm < 0 ? \
- (imm >= SKF_LL_OFF ? func##_negative_offset : func) : \
- func##_positive_offset)
+/* PPC NVR range -- update this if we ever use NVRs below r27 */
+#define BPF_PPC_NVR_MIN 27
#define SEEN_FUNC 0x1000 /* might call external helpers */
#define SEEN_STACK 0x2000 /* uses BPF stack */
-#define SEEN_SKB 0x4000 /* uses sk_buff */
-#define SEEN_TAILCALL 0x8000 /* uses tail calls */
+#define SEEN_TAILCALL 0x4000 /* uses tail calls */
struct codegen_context {
/*
* This is used to track register usage as well
* as calls to external helpers.
* - register usage is tracked with corresponding
- * bits (r3-r10 and r25-r31)
+ * bits (r3-r10 and r27-r31)
* - rest of the bits can be used to track other
* things -- for now, we use bits 16 to 23
* encoded in SEEN_* macros above
+++ /dev/null
-/*
- * bpf_jit_asm64.S: Packet/header access helper functions
- * for PPC64 BPF compiler.
- *
- * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
- * IBM Corporation
- *
- * Based on bpf_jit_asm.S by Matt Evans
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/ptrace.h>
-#include "bpf_jit64.h"
-
-/*
- * All of these routines are called directly from generated code,
- * with the below register usage:
- * r27 skb pointer (ctx)
- * r25 skb header length
- * r26 skb->data pointer
- * r4 offset
- *
- * Result is passed back in:
- * r8 data read in host endian format (accumulator)
- *
- * r9 is used as a temporary register
- */
-
-#define r_skb r27
-#define r_hlen r25
-#define r_data r26
-#define r_off r4
-#define r_val r8
-#define r_tmp r9
-
-_GLOBAL_TOC(sk_load_word)
- cmpdi r_off, 0
- blt bpf_slow_path_word_neg
- b sk_load_word_positive_offset
-
-_GLOBAL_TOC(sk_load_word_positive_offset)
- /* Are we accessing past headlen? */
- subi r_tmp, r_hlen, 4
- cmpd r_tmp, r_off
- blt bpf_slow_path_word
- /* Nope, just hitting the header. cr0 here is eq or gt! */
- LWZX_BE r_val, r_data, r_off
- blr /* Return success, cr0 != LT */
-
-_GLOBAL_TOC(sk_load_half)
- cmpdi r_off, 0
- blt bpf_slow_path_half_neg
- b sk_load_half_positive_offset
-
-_GLOBAL_TOC(sk_load_half_positive_offset)
- subi r_tmp, r_hlen, 2
- cmpd r_tmp, r_off
- blt bpf_slow_path_half
- LHZX_BE r_val, r_data, r_off
- blr
-
-_GLOBAL_TOC(sk_load_byte)
- cmpdi r_off, 0
- blt bpf_slow_path_byte_neg
- b sk_load_byte_positive_offset
-
-_GLOBAL_TOC(sk_load_byte_positive_offset)
- cmpd r_hlen, r_off
- ble bpf_slow_path_byte
- lbzx r_val, r_data, r_off
- blr
-
-/*
- * Call out to skb_copy_bits:
- * Allocate a new stack frame here to remain ABI-compliant in
- * stashing LR.
- */
-#define bpf_slow_path_common(SIZE) \
- mflr r0; \
- std r0, PPC_LR_STKOFF(r1); \
- stdu r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1); \
- mr r3, r_skb; \
- /* r4 = r_off as passed */ \
- addi r5, r1, STACK_FRAME_MIN_SIZE; \
- li r6, SIZE; \
- bl skb_copy_bits; \
- nop; \
- /* save r5 */ \
- addi r5, r1, STACK_FRAME_MIN_SIZE; \
- /* r3 = 0 on success */ \
- addi r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS; \
- ld r0, PPC_LR_STKOFF(r1); \
- mtlr r0; \
- cmpdi r3, 0; \
- blt bpf_error; /* cr0 = LT */
-
-bpf_slow_path_word:
- bpf_slow_path_common(4)
- /* Data value is on stack, and cr0 != LT */
- LWZX_BE r_val, 0, r5
- blr
-
-bpf_slow_path_half:
- bpf_slow_path_common(2)
- LHZX_BE r_val, 0, r5
- blr
-
-bpf_slow_path_byte:
- bpf_slow_path_common(1)
- lbzx r_val, 0, r5
- blr
-
-/*
- * Call out to bpf_internal_load_pointer_neg_helper
- */
-#define sk_negative_common(SIZE) \
- mflr r0; \
- std r0, PPC_LR_STKOFF(r1); \
- stdu r1, -STACK_FRAME_MIN_SIZE(r1); \
- mr r3, r_skb; \
- /* r4 = r_off, as passed */ \
- li r5, SIZE; \
- bl bpf_internal_load_pointer_neg_helper; \
- nop; \
- addi r1, r1, STACK_FRAME_MIN_SIZE; \
- ld r0, PPC_LR_STKOFF(r1); \
- mtlr r0; \
- /* R3 != 0 on success */ \
- cmpldi r3, 0; \
- beq bpf_error_slow; /* cr0 = EQ */
-
-bpf_slow_path_word_neg:
- lis r_tmp, -32 /* SKF_LL_OFF */
- cmpd r_off, r_tmp /* addr < SKF_* */
- blt bpf_error /* cr0 = LT */
- b sk_load_word_negative_offset
-
-_GLOBAL_TOC(sk_load_word_negative_offset)
- sk_negative_common(4)
- LWZX_BE r_val, 0, r3
- blr
-
-bpf_slow_path_half_neg:
- lis r_tmp, -32 /* SKF_LL_OFF */
- cmpd r_off, r_tmp /* addr < SKF_* */
- blt bpf_error /* cr0 = LT */
- b sk_load_half_negative_offset
-
-_GLOBAL_TOC(sk_load_half_negative_offset)
- sk_negative_common(2)
- LHZX_BE r_val, 0, r3
- blr
-
-bpf_slow_path_byte_neg:
- lis r_tmp, -32 /* SKF_LL_OFF */
- cmpd r_off, r_tmp /* addr < SKF_* */
- blt bpf_error /* cr0 = LT */
- b sk_load_byte_negative_offset
-
-_GLOBAL_TOC(sk_load_byte_negative_offset)
- sk_negative_common(1)
- lbzx r_val, 0, r3
- blr
-
-bpf_error_slow:
- /* fabricate a cr0 = lt */
- li r_tmp, -1
- cmpdi r_tmp, 0
-bpf_error:
- /*
- * Entered with cr0 = lt
- * Generated code will 'blt epilogue', returning 0.
- */
- li r_val, 0
- blr
* [ prev sp ] <-------------
* [ ... ] |
* sp (r1) ---> [ stack pointer ] --------------
- * [ nv gpr save area ] 8*8
+ * [ nv gpr save area ] 6*8
* [ tail_call_cnt ] 8
* [ local_tmp_var ] 8
* [ unused red zone ] 208 bytes protected
BUG();
}
-static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
-{
- /*
- * Load skb->len and skb->data_len
- * r3 points to skb
- */
- PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
- PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
- /* header_len = len - data_len */
- PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);
-
- /* skb->data pointer */
- PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
-}
-
static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
int i;
if (bpf_is_seen_register(ctx, i))
PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
- /*
- * Save additional non-volatile regs if we cache skb
- * Also, setup skb data
- */
- if (ctx->seen & SEEN_SKB) {
- PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
- bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
- PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
- bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
- bpf_jit_emit_skb_loads(image, ctx);
- }
-
/* Setup frame pointer to point to the bpf stack area */
if (bpf_is_seen_register(ctx, BPF_REG_FP))
PPC_ADDI(b2p[BPF_REG_FP], 1,
if (bpf_is_seen_register(ctx, i))
PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
- /* Restore non-volatile registers used for skb cache */
- if (ctx->seen & SEEN_SKB) {
- PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
- bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
- PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
- bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
- }
-
/* Tear down our stack frame */
if (bpf_has_stack_frame(ctx)) {
PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
ctx->seen |= SEEN_FUNC;
func = (u8 *) __bpf_call_base + imm;
- /* Save skb pointer if we need to re-cache skb data */
- if ((ctx->seen & SEEN_SKB) &&
- bpf_helper_changes_pkt_data(func))
- PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
-
bpf_jit_emit_func_call(image, ctx, (u64)func);
/* move return value from r3 to BPF_REG_0 */
PPC_MR(b2p[BPF_REG_0], 3);
-
- /* refresh skb cache */
- if ((ctx->seen & SEEN_SKB) &&
- bpf_helper_changes_pkt_data(func)) {
- /* reload skb pointer to r3 */
- PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
- bpf_jit_emit_skb_loads(image, ctx);
- }
break;
/*
PPC_BCC(true_cond, addrs[i + 1 + off]);
break;
- /*
- * Loads from packet header/data
- * Assume 32-bit input value in imm and X (src_reg)
- */
-
- /* Absolute loads */
- case BPF_LD | BPF_W | BPF_ABS:
- func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
- goto common_load_abs;
- case BPF_LD | BPF_H | BPF_ABS:
- func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
- goto common_load_abs;
- case BPF_LD | BPF_B | BPF_ABS:
- func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
-common_load_abs:
- /*
- * Load from [imm]
- * Load into r4, which can just be passed onto
- * skb load helpers as the second parameter
- */
- PPC_LI32(4, imm);
- goto common_load;
-
- /* Indirect loads */
- case BPF_LD | BPF_W | BPF_IND:
- func = (u8 *)sk_load_word;
- goto common_load_ind;
- case BPF_LD | BPF_H | BPF_IND:
- func = (u8 *)sk_load_half;
- goto common_load_ind;
- case BPF_LD | BPF_B | BPF_IND:
- func = (u8 *)sk_load_byte;
-common_load_ind:
- /*
- * Load from [src_reg + imm]
- * Treat src_reg as a 32-bit value
- */
- PPC_EXTSW(4, src_reg);
- if (imm) {
- if (imm >= -32768 && imm < 32768)
- PPC_ADDI(4, 4, IMM_L(imm));
- else {
- PPC_LI32(b2p[TMP_REG_1], imm);
- PPC_ADD(4, 4, b2p[TMP_REG_1]);
- }
- }
-
-common_load:
- ctx->seen |= SEEN_SKB;
- ctx->seen |= SEEN_FUNC;
- bpf_jit_emit_func_call(image, ctx, (u64)func);
-
- /*
- * Helper returns 'lt' condition on error, and an
- * appropriate return value in BPF_REG_0
- */
- PPC_BCC(COND_LT, exit_addr);
- break;
-
/*
* Tail call
*/
LOAD_INT(c), LOAD_FRAC(c),
count_active_contexts(),
atomic_read(&nr_spu_contexts),
- idr_get_cursor(&task_active_pid_ns(current)->idr));
+ idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
return 0;
}
.open = simple_open,
};
-static void flush_memory_region(u64 base, u64 size)
-{
- unsigned long line_size = ppc64_caches.l1d.size;
- u64 end = base + size;
- u64 addr;
-
- base = round_down(base, line_size);
- end = round_up(end, line_size);
-
- for (addr = base; addr < end; addr += line_size)
- asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory");
-}
-
static int check_memblock_online(struct memory_block *mem, void *arg)
{
if (mem->state != MEM_ONLINE)
walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
change_memblock_state);
- /* RCU grace period? */
- flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT),
- nr_pages << PAGE_SHIFT);
-
lock_device_hotplug();
remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
unlock_device_hotplug();
#define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
+/*
+ * spinlock to protect initialisation of an npu_context for a particular
+ * mm_struct.
+ */
+static DEFINE_SPINLOCK(npu_context_lock);
+
+/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
bool nmmu_flush;
/* Callback to stop translation requests on a given GPU */
- struct npu_context *(*release_cb)(struct npu_context *, void *);
+ void (*release_cb)(struct npu_context *context, void *priv);
/*
* Private pointer passed to the above callback for usage by
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- for (address = start; address < end; address += PAGE_SIZE)
- mmio_invalidate(npu_context, 1, address, false);
+ if (end - start > ATSD_THRESHOLD) {
+ /*
+ * Just invalidate the entire PID if the address range is too
+ * large.
+ */
+ mmio_invalidate(npu_context, 0, 0, true);
+ } else {
+ for (address = start; address < end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address, false);
- /* Do the flush only on the final addess == end */
- mmio_invalidate(npu_context, 1, address, true);
+ /* Do the flush only on the final addess == end */
+ mmio_invalidate(npu_context, 1, address, true);
+ }
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
* Returns an error if there no contexts are currently available or a
* npu_context which should be passed to pnv_npu2_handle_fault().
*
- * mmap_sem must be held in write mode.
+ * mmap_sem must be held in write mode and must not be called from interrupt
+ * context.
*/
struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
unsigned long flags,
- struct npu_context *(*cb)(struct npu_context *, void *),
+ void (*cb)(struct npu_context *, void *),
void *priv)
{
int rc;
/*
* Setup the NPU context table for a particular GPU. These need to be
* per-GPU as we need the tables to filter ATSDs when there are no
- * active contexts on a particular GPU.
+ * active contexts on a particular GPU. It is safe for these to be
+ * called concurrently with destroy as the OPAL call takes appropriate
+ * locks and refcounts on init/destroy.
*/
rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
* We store the npu pci device so we can more easily get at the
* associated npus.
*/
+ spin_lock(&npu_context_lock);
npu_context = mm->context.npu_context;
+ if (npu_context) {
+ if (npu_context->release_cb != cb ||
+ npu_context->priv != priv) {
+ spin_unlock(&npu_context_lock);
+ opal_npu_destroy_context(nphb->opal_id, mm->context.id,
+ PCI_DEVID(gpdev->bus->number,
+ gpdev->devfn));
+ return ERR_PTR(-EINVAL);
+ }
+
+ WARN_ON(!kref_get_unless_zero(&npu_context->kref));
+ }
+ spin_unlock(&npu_context_lock);
+
if (!npu_context) {
+ /*
+ * We can set up these fields without holding the
+ * npu_context_lock as the npu_context hasn't been returned to
+ * the caller meaning it can't be destroyed. Parallel allocation
+ * is protected against by mmap_sem.
+ */
rc = -ENOMEM;
npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
if (npu_context) {
}
mm->context.npu_context = npu_context;
- } else {
- WARN_ON(!kref_get_unless_zero(&npu_context->kref));
}
npu_context->release_cb = cb;
mm_context_remove_copro(npu_context->mm);
npu_context->mm->context.npu_context = NULL;
- mmu_notifier_unregister(&npu_context->mn,
- npu_context->mm);
-
- kfree(npu_context);
}
+/*
+ * Destroy a context on the given GPU. May free the npu_context if it is no
+ * longer active on any GPUs. Must not be called from interrupt context.
+ */
void pnv_npu2_destroy_context(struct npu_context *npu_context,
struct pci_dev *gpdev)
{
+ int removed;
struct pnv_phb *nphb;
struct npu *npu;
struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
- kref_put(&npu_context->kref, pnv_npu2_release_context);
+ spin_lock(&npu_context_lock);
+ removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
+ spin_unlock(&npu_context_lock);
+
+ /*
+ * We need to do this outside of pnv_npu2_release_context so that it is
+ * outside the spinlock as mmu_notifier_destroy uses SRCU.
+ */
+ if (removed) {
+ mmu_notifier_unregister(&npu_context->mn,
+ npu_context->mm);
+
+ kfree(npu_context);
+ }
+
}
EXPORT_SYMBOL(pnv_npu2_destroy_context);
return count;
}
+/*
+ * This can be called in the panic path with interrupts off, so use
+ * mdelay in that case.
+ */
static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
{
s64 rc = OPAL_BUSY;
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_write_nvram(__pa(buf), count, off);
if (rc == OPAL_BUSY_EVENT) {
- msleep(OPAL_BUSY_DELAY_MS);
+ if (in_interrupt() || irqs_disabled())
+ mdelay(OPAL_BUSY_DELAY_MS);
+ else
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
} else if (rc == OPAL_BUSY) {
- msleep(OPAL_BUSY_DELAY_MS);
+ if (in_interrupt() || irqs_disabled())
+ mdelay(OPAL_BUSY_DELAY_MS);
+ else
+ msleep(OPAL_BUSY_DELAY_MS);
}
}
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ mdelay(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (rc == OPAL_BUSY)
- mdelay(10);
+ } else if (rc == OPAL_BUSY) {
+ mdelay(OPAL_BUSY_DELAY_MS);
+ }
}
if (rc != OPAL_SUCCESS)
return 0;
select ARCH_WANT_FRAME_POINTERS
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_DIRECT_OPS
select GENERIC_CLOCKEVENTS
select GENERIC_CPU_DEVICES
select GENERIC_IRQ_SHOW
config HAVE_KPROBES
def_bool n
-config DMA_DIRECT_OPS
- def_bool y
-
menu "Platform type"
choice
generic-y += futex.h
generic-y += hardirq.h
generic-y += hash.h
-generic-y += handle_irq.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
# Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions.
# Make sure only to export the intended __vdso_xxx symbol offsets.
quiet_cmd_vdsold = VDSOLD $@
- cmd_vdsold = $(CC) $(KCFLAGS) -nostdlib $(SYSCFLAGS_$(@F)) \
+ cmd_vdsold = $(CC) $(KCFLAGS) $(call cc-option, -no-pie) -nostdlib $(SYSCFLAGS_$(@F)) \
-Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \
$(CROSS_COMPILE)objcopy \
$(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
CONFIG_WQ_WATCHDOG=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCK_STAT=y
CONFIG_DEBUG_LOCKDEP=y
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
*/
#include <linux/linkage.h>
+#include <asm/nospec-insn.h>
#include <asm/vx-insn.h>
/* Vector register range containing CRC-32 constants */
.previous
+ GEN_BR_THUNK %r14
+
.text
/*
* The CRC-32 function(s) use these calling conventions:
.Ldone:
VLGVF %r2,%v2,3
- br %r14
+ BR_EX %r14
.previous
*/
#include <linux/linkage.h>
+#include <asm/nospec-insn.h>
#include <asm/vx-insn.h>
/* Vector register range containing CRC-32 constants */
.previous
+ GEN_BR_THUNK %r14
.text
.Ldone:
VLGVF %r2,%v2,2
- br %r14
+ BR_EX %r14
.previous
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_NOSPEC_ASM_H
+#define _ASM_S390_NOSPEC_ASM_H
+
+#include <asm/alternative-asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_EXPOLINE
+
+_LC_BR_R1 = __LC_BR_R1
+
+/*
+ * The expoline macros are used to create thunks in the same format
+ * as gcc generates them. The 'comdat' section flag makes sure that
+ * the various thunks are merged into a single copy.
+ */
+ .macro __THUNK_PROLOG_NAME name
+ .pushsection .text.\name,"axG",@progbits,\name,comdat
+ .globl \name
+ .hidden \name
+ .type \name,@function
+\name:
+ CFI_STARTPROC
+ .endm
+
+ .macro __THUNK_EPILOG
+ CFI_ENDPROC
+ .popsection
+ .endm
+
+ .macro __THUNK_PROLOG_BR r1,r2
+ __THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+ .endm
+
+ .macro __THUNK_PROLOG_BC d0,r1,r2
+ __THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ .endm
+
+ .macro __THUNK_BR r1,r2
+ jg __s390x_indirect_jump_r\r2\()use_r\r1
+ .endm
+
+ .macro __THUNK_BC d0,r1,r2
+ jg __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ .endm
+
+ .macro __THUNK_BRASL r1,r2,r3
+ brasl \r1,__s390x_indirect_jump_r\r3\()use_r\r2
+ .endm
+
+ .macro __DECODE_RR expand,reg,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \reg,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r2
+ \expand \r1,\r2
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_RR failed"
+ .endif
+ .endm
+
+ .macro __DECODE_RRR expand,rsave,rtarget,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \rsave,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \rtarget,%r\r2
+ .irp r3,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r3
+ \expand \r1,\r2,\r3
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_RRR failed"
+ .endif
+ .endm
+
+ .macro __DECODE_DRR expand,disp,reg,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \reg,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r2
+ \expand \disp,\r1,\r2
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_DRR failed"
+ .endif
+ .endm
+
+ .macro __THUNK_EX_BR reg,ruse
+ # Be very careful when adding instructions to this macro!
+ # The ALTERNATIVE replacement code has a .+10 which targets
+ # the "br \reg" after the code has been patched.
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+ exrl 0,555f
+ j .
+#else
+ .ifc \reg,%r1
+ ALTERNATIVE "ex %r0,_LC_BR_R1", ".insn ril,0xc60000000000,0,.+10", 35
+ j .
+ .else
+ larl \ruse,555f
+ ex 0,0(\ruse)
+ j .
+ .endif
+#endif
+555: br \reg
+ .endm
+
+ .macro __THUNK_EX_BC disp,reg,ruse
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+ exrl 0,556f
+ j .
+#else
+ larl \ruse,556f
+ ex 0,0(\ruse)
+ j .
+#endif
+556: b \disp(\reg)
+ .endm
+
+ .macro GEN_BR_THUNK reg,ruse=%r1
+ __DECODE_RR __THUNK_PROLOG_BR,\reg,\ruse
+ __THUNK_EX_BR \reg,\ruse
+ __THUNK_EPILOG
+ .endm
+
+ .macro GEN_B_THUNK disp,reg,ruse=%r1
+ __DECODE_DRR __THUNK_PROLOG_BC,\disp,\reg,\ruse
+ __THUNK_EX_BC \disp,\reg,\ruse
+ __THUNK_EPILOG
+ .endm
+
+ .macro BR_EX reg,ruse=%r1
+557: __DECODE_RR __THUNK_BR,\reg,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 557b-.
+ .popsection
+ .endm
+
+ .macro B_EX disp,reg,ruse=%r1
+558: __DECODE_DRR __THUNK_BC,\disp,\reg,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 558b-.
+ .popsection
+ .endm
+
+ .macro BASR_EX rsave,rtarget,ruse=%r1
+559: __DECODE_RRR __THUNK_BRASL,\rsave,\rtarget,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 559b-.
+ .popsection
+ .endm
+
+#else
+ .macro GEN_BR_THUNK reg,ruse=%r1
+ .endm
+
+ .macro GEN_B_THUNK disp,reg,ruse=%r1
+ .endm
+
+ .macro BR_EX reg,ruse=%r1
+ br \reg
+ .endm
+
+ .macro B_EX disp,reg,ruse=%r1
+ b \disp(\reg)
+ .endm
+
+ .macro BASR_EX rsave,rtarget,ruse=%r1
+ basr \rsave,\rtarget
+ .endm
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_NOSPEC_ASM_H */
int verify_sha256_digest(void);
+extern u64 kernel_entry;
+extern u64 kernel_type;
+
+extern u64 crash_start;
+extern u64 crash_size;
+
#endif /* __ASSEMBLY__ */
#endif /* _S390_PURGATORY_H_ */
void arch_release_task_struct(struct task_struct *tsk);
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+
#endif
/*
extra-y += head.o head64.o vmlinux.lds
+obj-$(CONFIG_SYSFS) += nospec-sysfs.o
CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE)
obj-$(CONFIG_MODULES) += module.o
OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
OFFSET(__LC_GMAP, lowcore, gmap);
+ OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline);
/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
/* hardware defined lowcore locations 0x1000 - 0x18ff */
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
#include <asm/sigp.h>
+ GEN_BR_THUNK %r9
+ GEN_BR_THUNK %r14
+
ENTRY(s390_base_mcck_handler)
basr %r13,0
0: lg %r15,__LC_PANIC_STACK # load panic stack
aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_mcck_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
1: la %r1,4095
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
lpswe __LC_MCK_OLD_PSW
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_ext_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC
ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit
lpswe __LC_EXT_OLD_PSW
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_pgm_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
lmg %r0,%r15,__LC_SAVE_AREA_SYNC
lpswe __LC_PGM_OLD_PSW
1: lpswe disabled_wait_psw-0b(%r13)
larl %r4,.Lcontinue_psw # Restore PSW flags
lpswe 0(%r4)
.Lcontinue:
- br %r14
+ BR_EX %r14
.align 16
.Lrestart_psw:
.long 0x00080000,0x80000000 + .Lrestart_part2
#include <asm/setup.h>
#include <asm/nmi.h>
#include <asm/export.h>
+#include <asm/nospec-insn.h>
__PT_R0 = __PT_GPRS
__PT_R1 = __PT_GPRS + 8
"jnz .+8; .long 0xb2e8d000", 82
.endm
-#ifdef CONFIG_EXPOLINE
-
- .macro GEN_BR_THUNK name,reg,tmp
- .section .text.\name,"axG",@progbits,\name,comdat
- .globl \name
- .hidden \name
- .type \name,@function
-\name:
- CFI_STARTPROC
-#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
- exrl 0,0f
-#else
- larl \tmp,0f
- ex 0,0(\tmp)
-#endif
- j .
-0: br \reg
- CFI_ENDPROC
- .endm
-
- GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
- GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1
- GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11
-
- .macro BASR_R14_R9
-0: brasl %r14,__s390x_indirect_jump_r1use_r9
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
- .macro BR_R1USE_R14
-0: jg __s390x_indirect_jump_r1use_r14
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
- .macro BR_R11USE_R14
-0: jg __s390x_indirect_jump_r11use_r14
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
-#else /* CONFIG_EXPOLINE */
-
- .macro BASR_R14_R9
- basr %r14,%r9
- .endm
-
- .macro BR_R1USE_R14
- br %r14
- .endm
-
- .macro BR_R11USE_R14
- br %r14
- .endm
-
-#endif /* CONFIG_EXPOLINE */
-
+ GEN_BR_THUNK %r9
+ GEN_BR_THUNK %r14
+ GEN_BR_THUNK %r14,%r11
.section .kprobes.text, "ax"
.Ldummy:
ENTRY(__bpon)
.globl __bpon
BPON
- BR_R1USE_R14
+ BR_EX %r14
/*
* Scheduler resume function, called by switch_to
mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
- BR_R1USE_R14
+ BR_EX %r14
.L__critical_start:
xgr %r5,%r5
lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers
lg %r2,__SF_SIE_REASON(%r15) # return exit reason code
- BR_R1USE_R14
+ BR_EX %r14
.Lsie_fault:
lghi %r14,-EFAULT
stg %r14,__SF_SIE_REASON(%r15) # set exit reason code
lgf %r9,0(%r8,%r10) # get system call add.
TSTMSK __TI_flags(%r12),_TIF_TRACE
jnz .Lsysc_tracesys
- BASR_R14_R9 # call sys_xxxx
+ BASR_EX %r14,%r9 # call sys_xxxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_return:
lmg %r3,%r7,__PT_R3(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
lg %r2,__PT_ORIG_GPR2(%r11)
- BASR_R14_R9 # call sys_xxx
+ BASR_EX %r14,%r9 # call sys_xxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_tracenogo:
TSTMSK __TI_flags(%r12),_TIF_TRACE
lmg %r9,%r10,__PT_R9(%r11) # load gprs
ENTRY(kernel_thread_starter)
la %r2,0(%r10)
- BASR_R14_R9
+ BASR_EX %r14,%r9
j .Lsysc_tracenogo
/*
je .Lpgm_return
lgf %r9,0(%r10,%r1) # load address of handler routine
lgr %r2,%r11 # pass pointer to pt_regs
- BASR_R14_R9 # branch to interrupt-handler
+ BASR_EX %r14,%r9 # branch to interrupt-handler
.Lpgm_return:
LOCKDEP_SYS_EXIT
tm __PT_PSW+1(%r11),0x01 # returning to user ?
stpt __TIMER_IDLE_ENTER(%r2)
.Lpsw_idle_lpsw:
lpswe __SF_EMPTY(%r15)
- BR_R1USE_R14
+ BR_EX %r14
.Lpsw_idle_end:
/*
.Lsave_fpu_regs_done:
oi __LC_CPU_FLAGS+7,_CIF_FPU
.Lsave_fpu_regs_exit:
- BR_R1USE_R14
+ BR_EX %r14
.Lsave_fpu_regs_end:
EXPORT_SYMBOL(save_fpu_regs)
.Lload_fpu_regs_done:
ni __LC_CPU_FLAGS+7,255-_CIF_FPU
.Lload_fpu_regs_exit:
- BR_R1USE_R14
+ BR_EX %r14
.Lload_fpu_regs_end:
.L__critical_end:
jl 0f
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
-0: BR_R11USE_R14
+0: BR_EX %r14
.align 8
.Lcleanup_table:
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
- BR_R11USE_R14
+ BR_EX %r14
#endif
.Lcleanup_system_call:
stg %r15,56(%r11) # r15 stack pointer
# set new psw address and exit
larl %r9,.Lsysc_do_svc
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_system_call_insn:
.quad system_call
.quad .Lsysc_stmg
.Lcleanup_sysc_tif:
larl %r9,.Lsysc_tif
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_sysc_restore:
# check if stpt has been executed
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_sysc_restore_insn:
.quad .Lsysc_exit_timer
.quad .Lsysc_done - 4
.Lcleanup_io_tif:
larl %r9,.Lio_tif
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_io_restore:
# check if stpt has been executed
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_io_restore_insn:
.quad .Lio_exit_timer
.quad .Lio_done - 4
# prepare return psw
nihh %r8,0xfcfd # clear irq & wait state bits
lg %r9,48(%r11) # return from psw_idle
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_idle_insn:
.quad .Lpsw_idle_lpsw
.Lcleanup_save_fpu_regs:
larl %r9,save_fpu_regs
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_load_fpu_regs:
larl %r9,load_fpu_regs
- BR_R11USE_R14
+ BR_EX %r14,%r11
/*
* Integer constants
new -= STACK_FRAME_OVERHEAD;
((struct stack_frame *) new)->back_chain = old;
asm volatile(" la 15,0(%0)\n"
- " basr 14,%2\n"
+ " brasl 14,__do_softirq\n"
" la 15,0(%1)\n"
- : : "a" (new), "a" (old),
- "a" (__do_softirq)
+ : : "a" (new), "a" (old)
: "0", "1", "2", "3", "4", "5", "14",
"cc", "memory" );
} else {
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/ftrace.h>
+#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
#include <asm/export.h>
+ GEN_BR_THUNK %r1
+ GEN_BR_THUNK %r14
+
.section .kprobes.text, "ax"
ENTRY(ftrace_stub)
- br %r14
+ BR_EX %r14
#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE)
#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
ENTRY(_mcount)
- br %r14
+ BR_EX %r14
EXPORT_SYMBOL(_mcount)
#endif
lgr %r3,%r14
la %r5,STACK_PTREGS(%r15)
- basr %r14,%r1
+ BASR_EX %r14,%r1
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
# The j instruction gets runtime patched to a nop instruction.
# See ftrace_enable_ftrace_graph_caller.
#endif
lg %r1,(STACK_PTREGS_PSW+8)(%r15)
lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
- br %r1
+ BR_EX %r1
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
aghi %r15,STACK_FRAME_OVERHEAD
lgr %r14,%r2
lmg %r2,%r5,32(%r15)
- br %r14
+ BR_EX %r14
#endif
apply_alternatives(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_call_table", secname)))
+ (!strncmp(".s390_indirect", secname, 14)))
nospec_revert(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_return_table", secname)))
+ (!strncmp(".s390_return", secname, 12)))
nospec_revert(aseg, aseg + s->sh_size);
}
// SPDX-License-Identifier: GPL-2.0
#include <linux/module.h>
#include <linux/device.h>
-#include <linux/cpu.h>
#include <asm/nospec-branch.h>
static int __init nobp_setup_early(char *str)
}
arch_initcall(nospec_report);
-#ifdef CONFIG_SYSFS
-ssize_t cpu_show_spectre_v1(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
-}
-
-ssize_t cpu_show_spectre_v2(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
- return sprintf(buf, "Mitigation: execute trampolines\n");
- if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
- return sprintf(buf, "Mitigation: limited branch prediction.\n");
- return sprintf(buf, "Vulnerable\n");
-}
-#endif
-
#ifdef CONFIG_EXPOLINE
int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
s32 *epo;
/* Second part of the instruction replace is always a nop */
- memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4);
for (epo = start; epo < end; epo++) {
instr = (u8 *) epo + *epo;
if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04)
br = thunk + (*(int *)(thunk + 2)) * 2;
else
continue;
- if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
+ /* Check for unconditional branch 0x07f? or 0x47f???? */
+ if ((br[0] & 0xbf) != 0x07 || (br[1] & 0xf0) != 0xf0)
continue;
+
+ memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x07, 0x00 }, 4);
switch (type) {
case BRCL_EXPOLINE:
- /* brcl to thunk, replace with br + nop */
insnbuf[0] = br[0];
insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ if (br[0] == 0x47) {
+ /* brcl to b, replace with bc + nopr */
+ insnbuf[2] = br[2];
+ insnbuf[3] = br[3];
+ } else {
+ /* brcl to br, replace with bcr + nop */
+ }
break;
case BRASL_EXPOLINE:
- /* brasl to thunk, replace with basr + nop */
- insnbuf[0] = 0x0d;
insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ if (br[0] == 0x47) {
+ /* brasl to b, replace with bas + nopr */
+ insnbuf[0] = 0x4d;
+ insnbuf[2] = br[2];
+ insnbuf[3] = br[3];
+ } else {
+ /* brasl to br, replace with basr + nop */
+ insnbuf[0] = 0x0d;
+ }
break;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+ return sprintf(buf, "Mitigation: execute trampolines\n");
+ if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
+ return sprintf(buf, "Mitigation: limited branch prediction\n");
+ return sprintf(buf, "Vulnerable\n");
+}
CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
-CPUMF_EVENT_ATTR(cf_z13, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z13, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_HPAGE_WRITES, 0x0083);
CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_SPECIAL, 0x00dc);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-CPUMF_EVENT_ATTR(cf_z14, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z14, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_HPAGE_WRITES, 0x0083);
};
static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z13, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z13, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_MISSES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_HPAGE_WRITES),
};
static struct attribute *cpumcf_z14_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z14, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z14, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_MISSES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_HPAGE_WRITES),
*/
rate = 0;
if (attr->freq) {
+ if (!attr->sample_freq) {
+ err = -EINVAL;
+ goto out;
+ }
rate = freq_to_sample_rate(&si, attr->sample_freq);
rate = hw_limit_rate(&si, rate);
attr->freq = 0;
#include <linux/random.h>
#include <linux/export.h>
#include <linux/init_task.h>
+#include <asm/cpu_mf.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/vtimer.h>
{
}
+void arch_setup_new_exec(void)
+{
+ if (S390_lowcore.current_pid != current->pid) {
+ S390_lowcore.current_pid = current->pid;
+ if (test_facility(40))
+ lpp(&S390_lowcore.lpp);
+ }
+}
+
void arch_release_task_struct(struct task_struct *tsk)
{
runtime_instr_release(tsk);
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/sigp.h>
+ GEN_BR_THUNK %r9
+
#
# Issue "store status" for the current CPU to its prefix page
# and call passed function afterwards
st %r4,0(%r1)
st %r5,4(%r1)
stg %r2,8(%r1)
- lgr %r1,%r2
+ lgr %r9,%r2
lgr %r2,%r3
- br %r1
+ BR_EX %r9
.section .bss
.align 8
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/sigp.h>
/*
* (see below) in the resume process.
* This function runs with disabled interrupts.
*/
+ GEN_BR_THUNK %r14
+
.section .text
ENTRY(swsusp_arch_suspend)
stmg %r6,%r15,__SF_GPRS(%r15)
spx 0x318(%r1)
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
- br %r14
+ BR_EX %r14
/*
* Restore saved memory image to correct place and restore register context.
larl %r15,init_thread_union
ahi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
larl %r2,.Lpanic_string
- larl %r3,sclp_early_printk
lghi %r1,0
sam31
sigp %r1,%r0,SIGP_SET_ARCHITECTURE
- basr %r14,%r3
+ brasl %r14,sclp_early_printk
larl %r3,.Ldisabled_wait_31
lpsw 0(%r3)
4:
/* Return 0 */
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
- br %r14
+ BR_EX %r14
.section .data..nosave,"aw",@progbits
.align 8
return orig;
}
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+ struct pt_regs *regs)
+{
+ if (ctx == RP_CHECK_CHAIN_CALL)
+ return user_stack_pointer(regs) <= ret->stack;
+ else
+ return user_stack_pointer(regs) < ret->stack;
+}
+
/* Instruction Emulation */
static void adjust_psw_addr(psw_t *psw, unsigned long len)
#include <linux/linkage.h>
#include <asm/export.h>
+#include <asm/nospec-insn.h>
+
+ GEN_BR_THUNK %r14
/*
* void *memmove(void *dest, const void *src, size_t n)
.Lmemmove_forward_remainder:
larl %r5,.Lmemmove_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemmove_reverse:
ic %r0,0(%r4,%r3)
stc %r0,0(%r4,%r1)
brctg %r4,.Lmemmove_reverse
ic %r0,0(%r4,%r3)
stc %r0,0(%r4,%r1)
- br %r14
+ BR_EX %r14
.Lmemmove_mvc:
mvc 0(1,%r1),0(%r3)
EXPORT_SYMBOL(memmove)
.Lmemset_clear_remainder:
larl %r3,.Lmemset_xc
ex %r4,0(%r3)
- br %r14
+ BR_EX %r14
.Lmemset_fill:
cghi %r4,1
lgr %r1,%r2
stc %r3,0(%r1)
larl %r5,.Lmemset_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemset_fill_exit:
stc %r3,0(%r1)
- br %r14
+ BR_EX %r14
.Lmemset_xc:
xc 0(1,%r1),0(%r1)
.Lmemset_mvc:
.Lmemcpy_remainder:
larl %r5,.Lmemcpy_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemcpy_loop:
mvc 0(256,%r1),0(%r3)
la %r1,256(%r1)
\insn %r3,0(%r1)
larl %r5,.L__memset_mvc\bits
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.L__memset_exit\bits:
\insn %r3,0(%r2)
- br %r14
+ BR_EX %r14
.L__memset_mvc\bits:
mvc \bytes(1,%r1),0(%r1)
.endm
#
# Arch-specific network modules
#
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * BPF Jit compiler for s390, help functions.
- *
- * Copyright IBM Corp. 2012,2015
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- * Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <linux/linkage.h>
-#include "bpf_jit.h"
-
-/*
- * Calling convention:
- * registers %r7-%r10, %r11,%r13, and %r15 are call saved
- *
- * Input (64 bit):
- * %r3 (%b2) = offset into skb data
- * %r6 (%b5) = return address
- * %r7 (%b6) = skb pointer
- * %r12 = skb data pointer
- *
- * Output:
- * %r14= %b0 = return value (read skb value)
- *
- * Work registers: %r2,%r4,%r5,%r14
- *
- * skb_copy_bits takes 4 parameters:
- * %r2 = skb pointer
- * %r3 = offset into skb data
- * %r4 = pointer to temp buffer
- * %r5 = length to copy
- * Return value in %r2: 0 = ok
- *
- * bpf_internal_load_pointer_neg_helper takes 3 parameters:
- * %r2 = skb pointer
- * %r3 = offset into data
- * %r4 = length to copy
- * Return value in %r2: Pointer to data
- */
-
-#define SKF_MAX_NEG_OFF -0x200000 /* SKF_LL_OFF from filter.h */
-
-/*
- * Load SIZE bytes from SKB
- */
-#define sk_load_common(NAME, SIZE, LOAD) \
-ENTRY(sk_load_##NAME); \
- ltgr %r3,%r3; /* Is offset negative? */ \
- jl sk_load_##NAME##_slow_neg; \
-ENTRY(sk_load_##NAME##_pos); \
- aghi %r3,SIZE; /* Offset + SIZE */ \
- clg %r3,STK_OFF_HLEN(%r15); /* Offset + SIZE > hlen? */ \
- jh sk_load_##NAME##_slow; \
- LOAD %r14,-SIZE(%r3,%r12); /* Get data from skb */ \
- b OFF_OK(%r6); /* Return */ \
- \
-sk_load_##NAME##_slow:; \
- lgr %r2,%r7; /* Arg1 = skb pointer */ \
- aghi %r3,-SIZE; /* Arg2 = offset */ \
- la %r4,STK_OFF_TMP(%r15); /* Arg3 = temp bufffer */ \
- lghi %r5,SIZE; /* Arg4 = size */ \
- brasl %r14,skb_copy_bits; /* Get data from skb */ \
- LOAD %r14,STK_OFF_TMP(%r15); /* Load from temp bufffer */ \
- ltgr %r2,%r2; /* Set cc to (%r2 != 0) */ \
- br %r6; /* Return */
-
-sk_load_common(word, 4, llgf) /* r14 = *(u32 *) (skb->data+offset) */
-sk_load_common(half, 2, llgh) /* r14 = *(u16 *) (skb->data+offset) */
-
-/*
- * Load 1 byte from SKB (optimized version)
- */
- /* r14 = *(u8 *) (skb->data+offset) */
-ENTRY(sk_load_byte)
- ltgr %r3,%r3 # Is offset negative?
- jl sk_load_byte_slow_neg
-ENTRY(sk_load_byte_pos)
- clg %r3,STK_OFF_HLEN(%r15) # Offset >= hlen?
- jnl sk_load_byte_slow
- llgc %r14,0(%r3,%r12) # Get byte from skb
- b OFF_OK(%r6) # Return OK
-
-sk_load_byte_slow:
- lgr %r2,%r7 # Arg1 = skb pointer
- # Arg2 = offset
- la %r4,STK_OFF_TMP(%r15) # Arg3 = pointer to temp buffer
- lghi %r5,1 # Arg4 = size (1 byte)
- brasl %r14,skb_copy_bits # Get data from skb
- llgc %r14,STK_OFF_TMP(%r15) # Load result from temp buffer
- ltgr %r2,%r2 # Set cc to (%r2 != 0)
- br %r6 # Return cc
-
-#define sk_negative_common(NAME, SIZE, LOAD) \
-sk_load_##NAME##_slow_neg:; \
- cgfi %r3,SKF_MAX_NEG_OFF; \
- jl bpf_error; \
- lgr %r2,%r7; /* Arg1 = skb pointer */ \
- /* Arg2 = offset */ \
- lghi %r4,SIZE; /* Arg3 = size */ \
- brasl %r14,bpf_internal_load_pointer_neg_helper; \
- ltgr %r2,%r2; \
- jz bpf_error; \
- LOAD %r14,0(%r2); /* Get data from pointer */ \
- xr %r3,%r3; /* Set cc to zero */ \
- br %r6; /* Return cc */
-
-sk_negative_common(word, 4, llgf)
-sk_negative_common(half, 2, llgh)
-sk_negative_common(byte, 1, llgc)
-
-bpf_error:
-# force a return 0 from jit handler
- ltgr %r15,%r15 # Set condition code
- br %r6
#include <linux/filter.h>
#include <linux/types.h>
-extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[];
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-
#endif /* __ASSEMBLY__ */
/*
* | | |
* | BPF stack | |
* | | |
- * +---------------+ |
- * | 8 byte skbp | |
- * R15+176 -> +---------------+ |
- * | 8 byte hlen | |
- * R15+168 -> +---------------+ |
- * | 4 byte align | |
- * +---------------+ |
- * | 4 byte temp | |
- * | for bpf_jit.S | |
* R15+160 -> +---------------+ |
* | new backchain | |
* R15+152 -> +---------------+ |
* The stack size used by the BPF program ("BPF stack" above) is passed
* via "aux->stack_depth".
*/
-#define STK_SPACE_ADD (8 + 8 + 4 + 4 + 160)
+#define STK_SPACE_ADD (160)
#define STK_160_UNUSED (160 - 12 * 8)
#define STK_OFF (STK_SPACE_ADD - STK_160_UNUSED)
-#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */
-#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */
-#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */
#define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */
#define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */
-/* Offset to skip condition code check */
-#define OFF_OK 4
-
#endif /* __ARCH_S390_NET_BPF_JIT_H */
#include <linux/bpf.h>
#include <asm/cacheflush.h>
#include <asm/dis.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
#include <asm/set_memory.h>
#include "bpf_jit.h"
int base_ip; /* Base address for literal pool */
int ret0_ip; /* Address of return 0 */
int exit_ip; /* Address of exit */
+ int r1_thunk_ip; /* Address of expoline thunk for 'br %r1' */
+ int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */
int tail_call_start; /* Tail call start offset */
int labels[1]; /* Labels for local jumps */
};
#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */
-#define SEEN_SKB 1 /* skb access */
-#define SEEN_MEM 2 /* use mem[] for temporary storage */
-#define SEEN_RET0 4 /* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL 8 /* code uses literals */
-#define SEEN_FUNC 16 /* calls C functions */
-#define SEEN_TAIL_CALL 32 /* code uses tail calls */
-#define SEEN_REG_AX 64 /* code uses constant blinding */
-#define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB)
+#define SEEN_MEM (1 << 0) /* use mem[] for temporary storage */
+#define SEEN_RET0 (1 << 1) /* ret0_ip points to a valid return 0 */
+#define SEEN_LITERAL (1 << 2) /* code uses literals */
+#define SEEN_FUNC (1 << 3) /* calls C functions */
+#define SEEN_TAIL_CALL (1 << 4) /* code uses tail calls */
+#define SEEN_REG_AX (1 << 5) /* code uses constant blinding */
+#define SEEN_STACK (SEEN_FUNC | SEEN_MEM)
/*
* s390 registers
*/
#define REG_W0 (MAX_BPF_JIT_REG + 0) /* Work register 1 (even) */
#define REG_W1 (MAX_BPF_JIT_REG + 1) /* Work register 2 (odd) */
-#define REG_SKB_DATA (MAX_BPF_JIT_REG + 2) /* SKB data register */
-#define REG_L (MAX_BPF_JIT_REG + 3) /* Literal pool register */
-#define REG_15 (MAX_BPF_JIT_REG + 4) /* Register 15 */
+#define REG_L (MAX_BPF_JIT_REG + 2) /* Literal pool register */
+#define REG_15 (MAX_BPF_JIT_REG + 3) /* Register 15 */
#define REG_0 REG_W0 /* Register 0 */
#define REG_1 REG_W1 /* Register 1 */
#define REG_2 BPF_REG_1 /* Register 2 */
[BPF_REG_9] = 10,
/* BPF stack pointer */
[BPF_REG_FP] = 13,
- /* Register for blinding (shared with REG_SKB_DATA) */
+ /* Register for blinding */
[BPF_REG_AX] = 12,
- /* SKB data pointer */
- [REG_SKB_DATA] = 12,
/* Work registers for s390x backend */
[REG_W0] = 0,
[REG_W1] = 1,
REG_SET_SEEN(b2); \
})
+#define EMIT6_PCREL_RILB(op, b, target) \
+({ \
+ int rel = (target - jit->prg) / 2; \
+ _EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff); \
+ REG_SET_SEEN(b); \
+})
+
+#define EMIT6_PCREL_RIL(op, target) \
+({ \
+ int rel = (target - jit->prg) / 2; \
+ _EMIT6(op | rel >> 16, rel & 0xffff); \
+})
+
#define _EMIT6_IMM(op, imm) \
({ \
unsigned int __imm = (imm); \
} while (re <= 15);
}
-/*
- * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
- * we store the SKB header length on the stack and the SKB data
- * pointer in REG_SKB_DATA if BPF_REG_AX is not used.
- */
-static void emit_load_skb_data_hlen(struct bpf_jit *jit)
-{
- /* Header length: llgf %w1,<len>(%b1) */
- EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
- offsetof(struct sk_buff, len));
- /* s %w1,<data_len>(%b1) */
- EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
- offsetof(struct sk_buff, data_len));
- /* stg %w1,ST_OFF_HLEN(%r0,%r15) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
- if (!(jit->seen & SEEN_REG_AX))
- /* lg %skb_data,data_off(%b1) */
- EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
- BPF_REG_1, offsetof(struct sk_buff, data));
-}
-
/*
* Emit function prologue
*
EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
REG_15, 152);
}
- if (jit->seen & SEEN_SKB) {
- emit_load_skb_data_hlen(jit);
- /* stg %b1,ST_OFF_SKBP(%r0,%r15) */
- EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
- STK_OFF_SKBP);
- }
}
/*
EMIT4(0xb9040000, REG_2, BPF_REG_0);
/* Restore registers */
save_restore_regs(jit, REGS_RESTORE, stack_depth);
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ jit->r14_thunk_ip = jit->prg;
+ /* Generate __s390_indirect_jump_r14 thunk */
+ if (test_facility(35)) {
+ /* exrl %r0,.+10 */
+ EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+ } else {
+ /* larl %r1,.+14 */
+ EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+ /* ex 0,0(%r1) */
+ EMIT4_DISP(0x44000000, REG_0, REG_1, 0);
+ }
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ }
/* br %r14 */
_EMIT2(0x07fe);
+
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+ (jit->seen & SEEN_FUNC)) {
+ jit->r1_thunk_ip = jit->prg;
+ /* Generate __s390_indirect_jump_r1 thunk */
+ if (test_facility(35)) {
+ /* exrl %r0,.+10 */
+ EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ /* br %r1 */
+ _EMIT2(0x07f1);
+ } else {
+ /* larl %r1,.+14 */
+ EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+ /* ex 0,S390_lowcore.br_r1_tampoline */
+ EMIT4_DISP(0x44000000, REG_0, REG_0,
+ offsetof(struct lowcore, br_r1_trampoline));
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ }
+ }
}
/*
{
struct bpf_insn *insn = &fp->insnsi[i];
int jmp_off, last, insn_count = 1;
- unsigned int func_addr, mask;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
u32 *addrs = jit->addrs;
s32 imm = insn->imm;
s16 off = insn->off;
+ unsigned int mask;
if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
jit->seen |= SEEN_REG_AX;
/* lg %w1,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
EMIT_CONST_U64(func));
- /* basr %r14,%w1 */
- EMIT2(0x0d00, REG_14, REG_W1);
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ /* brasl %r14,__s390_indirect_jump_r1 */
+ EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
+ } else {
+ /* basr %r14,%w1 */
+ EMIT2(0x0d00, REG_14, REG_W1);
+ }
/* lgr %b0,%r2: load return value into %b0 */
EMIT4(0xb9040000, BPF_REG_0, REG_2);
- if ((jit->seen & SEEN_SKB) &&
- bpf_helper_changes_pkt_data((void *)func)) {
- /* lg %b1,ST_OFF_SKBP(%r15) */
- EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
- REG_15, STK_OFF_SKBP);
- emit_load_skb_data_hlen(jit);
- }
break;
}
case BPF_JMP | BPF_TAIL_CALL:
jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
break;
- /*
- * BPF_LD
- */
- case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */
- case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */
- if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
- func_addr = __pa(sk_load_byte_pos);
- else
- func_addr = __pa(sk_load_byte);
- goto call_fn;
- case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */
- case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */
- if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
- func_addr = __pa(sk_load_half_pos);
- else
- func_addr = __pa(sk_load_half);
- goto call_fn;
- case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */
- case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */
- if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
- func_addr = __pa(sk_load_word_pos);
- else
- func_addr = __pa(sk_load_word);
- goto call_fn;
-call_fn:
- jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC;
- REG_SET_SEEN(REG_14); /* Return address of possible func call */
-
- /*
- * Implicit input:
- * BPF_REG_6 (R7) : skb pointer
- * REG_SKB_DATA (R12): skb data pointer (if no BPF_REG_AX)
- *
- * Calculated input:
- * BPF_REG_2 (R3) : offset of byte(s) to fetch in skb
- * BPF_REG_5 (R6) : return address
- *
- * Output:
- * BPF_REG_0 (R14): data read from skb
- *
- * Scratch registers (BPF_REG_1-5)
- */
-
- /* Call function: llilf %w1,func_addr */
- EMIT6_IMM(0xc00f0000, REG_W1, func_addr);
-
- /* Offset: lgfi %b2,imm */
- EMIT6_IMM(0xc0010000, BPF_REG_2, imm);
- if (BPF_MODE(insn->code) == BPF_IND)
- /* agfr %b2,%src (%src is s32 here) */
- EMIT4(0xb9180000, BPF_REG_2, src_reg);
-
- /* Reload REG_SKB_DATA if BPF_REG_AX is used */
- if (jit->seen & SEEN_REG_AX)
- /* lg %skb_data,data_off(%b6) */
- EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
- BPF_REG_6, offsetof(struct sk_buff, data));
- /* basr %b5,%w1 (%b5 is call saved) */
- EMIT2(0x0d00, BPF_REG_5, REG_W1);
-
- /*
- * Note: For fast access we jump directly after the
- * jnz instruction from bpf_jit.S
- */
- /* jnz <ret0> */
- EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg);
- break;
default: /* too complex, give up */
pr_err("Unknown opcode %02x\n", insn->code);
return -1;
select HAVE_IDE if HAS_IOPORT_MAP
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
+ select NO_BOOTMEM
select ARCH_DISCARD_MEMBLOCK
select HAVE_OPROFILE
select HAVE_GENERIC_DMA_COHERENT
#endif
#if defined(CONFIG_CPU_J2)
+#if defined(CONFIG_SMP)
unsigned cpu = hard_smp_processor_id();
+#else
+ unsigned cpu = 0;
+#endif
if (cpu == 0) of_scan_flat_dt(scan_cache, NULL);
if (j2_ccr_base) __raw_writel(0x80000303, j2_ccr_base + 4*cpu);
if (cpu != 0) return;
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/initrd.h>
-#include <linux/bootmem.h>
#include <linux/console.h>
#include <linux/root_dev.h>
#include <linux/utsname.h>
split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
- *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+ *dma_handle = virt_to_phys(ret);
+ if (!WARN_ON(!dev))
+ *dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
return ret_nocache;
}
unsigned long attrs)
{
int order = get_order(size);
- unsigned long pfn = (dma_handle >> PAGE_SHIFT) + dev->dma_pfn_offset;
+ unsigned long pfn = dma_handle >> PAGE_SHIFT;
int k;
+ if (!WARN_ON(!dev))
+ pfn += dev->dma_pfn_offset;
+
for (k = 0; k < (1 << order); k++)
__free_pages(pfn_to_page(pfn + k), 0);
if (!memsize)
return 0;
- buf = dma_alloc_coherent(NULL, memsize, &dma_handle, GFP_KERNEL);
+ buf = dma_alloc_coherent(&pdev->dev, memsize, &dma_handle, GFP_KERNEL);
if (!buf) {
pr_warning("%s: unable to allocate memory\n", name);
return -ENOMEM;
NODE_DATA(nid) = __va(phys);
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
-
- NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
#endif
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
}
-static void __init bootmem_init_one_node(unsigned int nid)
-{
- unsigned long total_pages, paddr;
- unsigned long end_pfn;
- struct pglist_data *p;
-
- p = NODE_DATA(nid);
-
- /* Nothing to do.. */
- if (!p->node_spanned_pages)
- return;
-
- end_pfn = pgdat_end_pfn(p);
-
- total_pages = bootmem_bootmap_pages(p->node_spanned_pages);
-
- paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE);
- if (!paddr)
- panic("Can't allocate bootmap for nid[%d]\n", nid);
-
- init_bootmem_node(p, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn);
-
- free_bootmem_with_active_regions(nid, end_pfn);
-
- /*
- * XXX Handle initial reservations for the system memory node
- * only for the moment, we'll refactor this later for handling
- * reservations in other nodes.
- */
- if (nid == 0) {
- struct memblock_region *reg;
-
- /* Reserve the sections we're already using. */
- for_each_memblock(reserved, reg) {
- reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
- }
- }
-
- sparse_memory_present_with_active_regions(nid);
-}
-
static void __init do_init_bootmem(void)
{
struct memblock_region *reg;
- int i;
/* Add active regions with valid PFNs. */
for_each_memblock(memory, reg) {
plat_mem_setup();
- for_each_online_node(i)
- bootmem_init_one_node(i);
+ for_each_memblock(memory, reg) {
+ int nid = memblock_get_region_node(reg);
+ memory_present(nid, memblock_region_memory_base_pfn(reg),
+ memblock_region_memory_end_pfn(reg));
+ }
sparse_init();
}
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long vaddr, end;
- int nid;
sh_mv.mv_mem_init();
kmap_coherent_init();
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-
- for_each_online_node(nid) {
- pg_data_t *pgdat = NODE_DATA(nid);
- unsigned long low, start_pfn;
-
- start_pfn = pgdat->bdata->node_min_pfn;
- low = pgdat->bdata->node_low_pfn;
-
- if (max_zone_pfns[ZONE_NORMAL] < low)
- max_zone_pfns[ZONE_NORMAL] = low;
-
- printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
- nid, start_pfn, low);
- }
-
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
}
* for more details.
*/
#include <linux/module.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/numa.h>
*/
void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
{
- unsigned long bootmap_pages;
unsigned long start_pfn, end_pfn;
- unsigned long bootmem_paddr;
/* Don't allow bogus node assignment */
BUG_ON(nid >= MAX_NUMNODES || nid <= 0);
SMP_CACHE_BYTES, end));
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
- NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
- /* Node-local bootmap */
- bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
- bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT,
- PAGE_SIZE, end);
- init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
- start_pfn, end_pfn);
-
- free_bootmem_with_active_regions(nid, end_pfn);
-
- /* Reserve the pgdat and bootmap space with the bootmem allocator */
- reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT,
- sizeof(struct pglist_data), BOOTMEM_DEFAULT);
- reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr,
- bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
-
/* It's up */
node_set_online(nid);
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
if (err) {
printk(KERN_ERR "VIO: Could not register device %s, err=%d\n",
dev_name(&vdev->dev), err);
- kfree(vdev);
+ put_device(&vdev->dev);
return NULL;
}
if (vdev->dp)
#
# Arch-specific network modules
#
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp_$(BITS).o
+ifeq ($(BITS),32)
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_32.o
+endif
#define I5 0x1d
#define FP 0x1e
#define I7 0x1f
-
-#define r_SKB L0
-#define r_HEADLEN L4
-#define r_SKB_DATA L5
-#define r_TMP G1
-#define r_TMP2 G3
-
-/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
-extern u32 bpf_jit_load_word[];
-extern u32 bpf_jit_load_half[];
-extern u32 bpf_jit_load_byte[];
-extern u32 bpf_jit_load_byte_msh[];
-extern u32 bpf_jit_load_word_positive_offset[];
-extern u32 bpf_jit_load_half_positive_offset[];
-extern u32 bpf_jit_load_byte_positive_offset[];
-extern u32 bpf_jit_load_byte_msh_positive_offset[];
-extern u32 bpf_jit_load_word_negative_offset[];
-extern u32 bpf_jit_load_half_negative_offset[];
-extern u32 bpf_jit_load_byte_negative_offset[];
-extern u32 bpf_jit_load_byte_msh_negative_offset[];
-
-#else
-#define r_RESULT %o0
-#define r_SKB %o0
-#define r_OFF %o1
-#define r_HEADLEN %l4
-#define r_SKB_DATA %l5
-#define r_TMP %g1
-#define r_TMP2 %g3
#endif
#endif /* _BPF_JIT_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/ptrace.h>
-
-#include "bpf_jit_64.h"
-
-#define SAVE_SZ 176
-#define SCRATCH_OFF STACK_BIAS + 128
-#define BE_PTR(label) be,pn %xcc, label
-#define SIGN_EXTEND(reg) sra reg, 0, reg
-
-#define SKF_MAX_NEG_OFF (-0x200000) /* SKF_LL_OFF from filter.h */
-
- .text
- .globl bpf_jit_load_word
-bpf_jit_load_word:
- cmp r_OFF, 0
- bl bpf_slow_path_word_neg
- nop
- .globl bpf_jit_load_word_positive_offset
-bpf_jit_load_word_positive_offset:
- sub r_HEADLEN, r_OFF, r_TMP
- cmp r_TMP, 3
- ble bpf_slow_path_word
- add r_SKB_DATA, r_OFF, r_TMP
- andcc r_TMP, 3, %g0
- bne load_word_unaligned
- nop
- retl
- ld [r_TMP], r_RESULT
-load_word_unaligned:
- ldub [r_TMP + 0x0], r_OFF
- ldub [r_TMP + 0x1], r_TMP2
- sll r_OFF, 8, r_OFF
- or r_OFF, r_TMP2, r_OFF
- ldub [r_TMP + 0x2], r_TMP2
- sll r_OFF, 8, r_OFF
- or r_OFF, r_TMP2, r_OFF
- ldub [r_TMP + 0x3], r_TMP2
- sll r_OFF, 8, r_OFF
- retl
- or r_OFF, r_TMP2, r_RESULT
-
- .globl bpf_jit_load_half
-bpf_jit_load_half:
- cmp r_OFF, 0
- bl bpf_slow_path_half_neg
- nop
- .globl bpf_jit_load_half_positive_offset
-bpf_jit_load_half_positive_offset:
- sub r_HEADLEN, r_OFF, r_TMP
- cmp r_TMP, 1
- ble bpf_slow_path_half
- add r_SKB_DATA, r_OFF, r_TMP
- andcc r_TMP, 1, %g0
- bne load_half_unaligned
- nop
- retl
- lduh [r_TMP], r_RESULT
-load_half_unaligned:
- ldub [r_TMP + 0x0], r_OFF
- ldub [r_TMP + 0x1], r_TMP2
- sll r_OFF, 8, r_OFF
- retl
- or r_OFF, r_TMP2, r_RESULT
-
- .globl bpf_jit_load_byte
-bpf_jit_load_byte:
- cmp r_OFF, 0
- bl bpf_slow_path_byte_neg
- nop
- .globl bpf_jit_load_byte_positive_offset
-bpf_jit_load_byte_positive_offset:
- cmp r_OFF, r_HEADLEN
- bge bpf_slow_path_byte
- nop
- retl
- ldub [r_SKB_DATA + r_OFF], r_RESULT
-
-#define bpf_slow_path_common(LEN) \
- save %sp, -SAVE_SZ, %sp; \
- mov %i0, %o0; \
- mov %i1, %o1; \
- add %fp, SCRATCH_OFF, %o2; \
- call skb_copy_bits; \
- mov (LEN), %o3; \
- cmp %o0, 0; \
- restore;
-
-bpf_slow_path_word:
- bpf_slow_path_common(4)
- bl bpf_error
- ld [%sp + SCRATCH_OFF], r_RESULT
- retl
- nop
-bpf_slow_path_half:
- bpf_slow_path_common(2)
- bl bpf_error
- lduh [%sp + SCRATCH_OFF], r_RESULT
- retl
- nop
-bpf_slow_path_byte:
- bpf_slow_path_common(1)
- bl bpf_error
- ldub [%sp + SCRATCH_OFF], r_RESULT
- retl
- nop
-
-#define bpf_negative_common(LEN) \
- save %sp, -SAVE_SZ, %sp; \
- mov %i0, %o0; \
- mov %i1, %o1; \
- SIGN_EXTEND(%o1); \
- call bpf_internal_load_pointer_neg_helper; \
- mov (LEN), %o2; \
- mov %o0, r_TMP; \
- cmp %o0, 0; \
- BE_PTR(bpf_error); \
- restore;
-
-bpf_slow_path_word_neg:
- sethi %hi(SKF_MAX_NEG_OFF), r_TMP
- cmp r_OFF, r_TMP
- bl bpf_error
- nop
- .globl bpf_jit_load_word_negative_offset
-bpf_jit_load_word_negative_offset:
- bpf_negative_common(4)
- andcc r_TMP, 3, %g0
- bne load_word_unaligned
- nop
- retl
- ld [r_TMP], r_RESULT
-
-bpf_slow_path_half_neg:
- sethi %hi(SKF_MAX_NEG_OFF), r_TMP
- cmp r_OFF, r_TMP
- bl bpf_error
- nop
- .globl bpf_jit_load_half_negative_offset
-bpf_jit_load_half_negative_offset:
- bpf_negative_common(2)
- andcc r_TMP, 1, %g0
- bne load_half_unaligned
- nop
- retl
- lduh [r_TMP], r_RESULT
-
-bpf_slow_path_byte_neg:
- sethi %hi(SKF_MAX_NEG_OFF), r_TMP
- cmp r_OFF, r_TMP
- bl bpf_error
- nop
- .globl bpf_jit_load_byte_negative_offset
-bpf_jit_load_byte_negative_offset:
- bpf_negative_common(1)
- retl
- ldub [r_TMP], r_RESULT
-
-bpf_error:
- /* Make the JIT program itself return zero. */
- ret
- restore %g0, %g0, %o0
}
}
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG 2 /* ebx is used */
-#define SEEN_MEM 4 /* use mem[] for temporary storage */
-
#define S13(X) ((X) & 0x1fff)
#define S5(X) ((X) & 0x1f)
#define IMMED 0x00002000
bool tmp_1_used;
bool tmp_2_used;
bool tmp_3_used;
- bool saw_ld_abs_ind;
bool saw_frame_pointer;
bool saw_call;
bool saw_tail_call;
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
-#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 2)
-#define SKB_DATA_REG (MAX_BPF_JIT_REG + 3)
-#define TMP_REG_3 (MAX_BPF_JIT_REG + 4)
+#define TMP_REG_3 (MAX_BPF_JIT_REG + 2)
/* Map BPF registers to SPARC registers */
static const int bpf2sparc[] = {
[TMP_REG_1] = G1,
[TMP_REG_2] = G2,
[TMP_REG_3] = G3,
-
- [SKB_HLEN_REG] = L4,
- [SKB_DATA_REG] = L5,
};
static void emit(const u32 insn, struct jit_ctx *ctx)
return 0;
}
-static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
-{
- const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
- const u8 r_data = bpf2sparc[SKB_DATA_REG];
- const u8 r_tmp = bpf2sparc[TMP_REG_1];
- unsigned int off;
-
- off = offsetof(struct sk_buff, len);
- emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
-
- off = offsetof(struct sk_buff, data_len);
- emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
-
- emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
-
- off = offsetof(struct sk_buff, data);
- emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
-}
-
/* Just skip the save instruction and the ctx register move. */
#define BPF_TAILCALL_PROLOGUE_SKIP 16
#define BPF_TAILCALL_CNT_SP_OFF (STACK_BIAS + 128)
emit_reg_move(I0, O0, ctx);
/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
-
- if (ctx->saw_ld_abs_ind)
- load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
}
static void build_epilogue(struct jit_ctx *ctx)
const int i = insn - ctx->prog->insnsi;
const s16 off = insn->off;
const s32 imm = insn->imm;
- u32 *func;
if (insn->src_reg == BPF_REG_FP)
ctx->saw_frame_pointer = true;
u8 *func = ((u8 *)__bpf_call_base) + imm;
ctx->saw_call = true;
- if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
- emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
emit_call((u32 *)func, ctx);
emit_nop(ctx);
emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-
- if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
- load_skb_regs(ctx, L7);
break;
}
emit_nop(ctx);
break;
}
-#define CHOOSE_LOAD_FUNC(K, func) \
- ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
- case BPF_LD | BPF_ABS | BPF_W:
- func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
- goto common_load;
- case BPF_LD | BPF_ABS | BPF_H:
- func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
- goto common_load;
- case BPF_LD | BPF_ABS | BPF_B:
- func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
- goto common_load;
- /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
- case BPF_LD | BPF_IND | BPF_W:
- func = bpf_jit_load_word;
- goto common_load;
- case BPF_LD | BPF_IND | BPF_H:
- func = bpf_jit_load_half;
- goto common_load;
-
- case BPF_LD | BPF_IND | BPF_B:
- func = bpf_jit_load_byte;
- common_load:
- ctx->saw_ld_abs_ind = true;
-
- emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
- emit_loadimm(imm, O1, ctx);
-
- if (BPF_MODE(code) == BPF_IND)
- emit_alu(ADD, src, O1, ctx);
-
- emit_call(func, ctx);
- emit_alu_K(SRA, O1, 0, ctx);
-
- emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
- break;
default:
pr_err_once("unknown opcode %02x\n", code);
build_epilogue(&ctx);
if (bpf_jit_enable > 1)
- pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass,
+ pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
image_size - (ctx.idx * 4),
ctx.tmp_1_used ? '1' : ' ',
ctx.tmp_2_used ? '2' : ' ',
ctx.tmp_3_used ? '3' : ' ',
- ctx.saw_ld_abs_ind ? 'L' : ' ',
ctx.saw_frame_pointer ? 'F' : ' ',
ctx.saw_call ? 'C' : ' ',
ctx.saw_tail_call ? 'T' : ' ');
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
+ select ARCH_HAS_FILTER_PGPROT
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
- select HAVE_EBPF_JIT if X86_64
+ select HAVE_EBPF_JIT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EXIT_THREAD
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_HAS_FILTER_PGPROT
+ def_bool y
+
config HAVE_SETUP_PER_CPU_AREA
def_bool y
if (status != EFI_SUCCESS)
goto free_struct;
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ memcpy(rom->romdata, (void *)(unsigned long)pci->romimage,
+ pci->romsize);
return status;
free_struct:
if (status != EFI_SUCCESS)
goto free_struct;
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ memcpy(rom->romdata, (void *)(unsigned long)pci->romimage,
+ pci->romsize);
return status;
free_struct:
/* Set up the stack */
leaq boot_stack_end(%rbx), %rsp
+ /*
+ * paging_prepare() and cleanup_trampoline() below can have GOT
+ * references. Adjust the table with address we are running at.
+ *
+ * Zero RAX for adjust_got: the GOT was not adjusted before;
+ * there's no adjustment to undo.
+ */
+ xorq %rax, %rax
+
+ /*
+ * Calculate the address the binary is loaded at and use it as
+ * a GOT adjustment.
+ */
+ call 1f
+1: popq %rdi
+ subq $1b, %rdi
+
+ call adjust_got
+
/*
* At this point we are in long mode with 4-level paging enabled,
* but we might want to enable 5-level paging or vice versa.
/*
* cleanup_trampoline() would restore trampoline memory.
*
+ * RDI is address of the page table to use instead of page table
+ * in trampoline memory (if required).
+ *
* RSI holds real mode data and needs to be preserved across
* this function call.
*/
pushq %rsi
+ leaq top_pgtable(%rbx), %rdi
call cleanup_trampoline
popq %rsi
pushq $0
popfq
+ /*
+ * Previously we've adjusted the GOT with address the binary was
+ * loaded at. Now we need to re-adjust for relocation address.
+ *
+ * Calculate the address the binary is loaded at, so that we can
+ * undo the previous GOT adjustment.
+ */
+ call 1f
+1: popq %rax
+ subq $1b, %rax
+
+ /* The new adjustment is the relocation address */
+ movq %rbx, %rdi
+ call adjust_got
+
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
shrq $3, %rcx
rep stosq
-/*
- * Adjust our own GOT
- */
- leaq _got(%rip), %rdx
- leaq _egot(%rip), %rcx
-1:
- cmpq %rcx, %rdx
- jae 2f
- addq %rbx, (%rdx)
- addq $8, %rdx
- jmp 1b
-2:
-
/*
* Do the extraction, and jump to the new kernel..
*/
*/
jmp *%rax
+/*
+ * Adjust the global offset table
+ *
+ * RAX is the previous adjustment of the table to undo (use 0 if it's the
+ * first time we touch GOT).
+ * RDI is the new adjustment to apply.
+ */
+adjust_got:
+ /* Walk through the GOT adding the address to the entries */
+ leaq _got(%rip), %rdx
+ leaq _egot(%rip), %rcx
+1:
+ cmpq %rcx, %rdx
+ jae 2f
+ subq %rax, (%rdx) /* Undo previous adjustment */
+ addq %rdi, (%rdx) /* Apply the new adjustment */
+ addq $8, %rdx
+ jmp 1b
+2:
+ ret
+
.code32
/*
* This is the 32-bit trampoline that will be copied over to low memory.
.balign 4096
pgtable:
.fill BOOT_PGT_SIZE, 1, 0
+
+/*
+ * The page table is going to be used instead of page table in the trampoline
+ * memory.
+ */
+top_pgtable:
+ .fill PAGE_SIZE, 1, 0
/* Buffer to preserve trampoline memory */
static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
-/*
- * The page table is going to be used instead of page table in the trampoline
- * memory.
- *
- * It must not be in BSS as BSS is cleared after cleanup_trampoline().
- */
-static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
-
/*
* Trampoline address will be printed by extract_kernel() for debugging
* purposes.
return paging_config;
}
-void cleanup_trampoline(void)
+void cleanup_trampoline(void *pgtable)
{
void *trampoline_pgtable;
* if it's there.
*/
if ((void *)__native_read_cr3() == trampoline_pgtable) {
- memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE);
- native_write_cr3((unsigned long)top_pgtable);
+ memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
+ native_write_cr3((unsigned long)pgtable);
}
/* Restore trampoline memory */
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq $0 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r8 */
xorl %r8d, %r8d /* nospec r8 */
- pushq $0 /* pt_regs->r9 = 0 */
+ pushq %r9 /* pt_regs->r9 */
xorl %r9d, %r9d /* nospec r9 */
- pushq $0 /* pt_regs->r10 = 0 */
+ pushq %r10 /* pt_regs->r10 */
xorl %r10d, %r10d /* nospec r10 */
- pushq $0 /* pt_regs->r11 = 0 */
+ pushq %r11 /* pt_regs->r11 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
+++ /dev/null
-#include "../vdso-fakesections.c"
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/device.h>
+#include <linux/nospec.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
config = attr->config;
- cache_type = (config >> 0) & 0xff;
+ cache_type = (config >> 0) & 0xff;
if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
return -EINVAL;
+ cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX);
cache_op = (config >> 8) & 0xff;
if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
return -EINVAL;
+ cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX);
cache_result = (config >> 16) & 0xff;
if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
return -EINVAL;
+ cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX);
val = hw_cache_event_ids[cache_type][cache_op][cache_result];
if (attr->config >= x86_pmu.max_events)
return -EINVAL;
+ attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events);
+
/*
* The generic map:
*/
cpuc->lbr_sel = NULL;
- flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+ if (x86_pmu.version > 1)
+ flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
if (!cpuc->shared_regs)
return;
.cpu_dying = intel_pmu_cpu_dying,
};
+static struct attribute *intel_pmu_attrs[];
+
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
+ .attrs = intel_pmu_attrs,
+
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
-
- x86_pmu.attrs = intel_pmu_attrs;
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events, when not running in a hypervisor:
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
} else if (event->pmu == &cstate_pkg_pmu) {
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
if (!pkg_msr[cfg].attr)
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
.format_group = &hswep_uncore_cbox_format_group,
};
+static struct intel_uncore_type bdx_uncore_sbox = {
+ .name = "sbox",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .event_ctl = HSWEP_S0_MSR_PMON_CTL0,
+ .perf_ctr = HSWEP_S0_MSR_PMON_CTR0,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_SBOX_MSR_OFFSET,
+ .ops = &hswep_uncore_sbox_msr_ops,
+ .format_group = &hswep_uncore_sbox_format_group,
+};
+
+#define BDX_MSR_UNCORE_SBOX 3
+
static struct intel_uncore_type *bdx_msr_uncores[] = {
&bdx_uncore_ubox,
&bdx_uncore_cbox,
&hswep_uncore_pcu,
+ &bdx_uncore_sbox,
NULL,
};
void bdx_uncore_cpu_init(void)
{
+ int pkg = topology_phys_to_logical_pkg(0);
+
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
uncore_msr_uncores = bdx_msr_uncores;
+ /* BDX-DE doesn't have SBOX */
+ if (boot_cpu_data.x86_model == 86) {
+ uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+ /* Detect systems with no SBOXes */
+ } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
+ struct pci_dev *pdev;
+ u32 capid4;
+
+ pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3];
+ pci_read_config_dword(pdev, 0x94, &capid4);
+ if (((capid4 >> 6) & 0x3) == 0)
+ bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+ }
hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
}
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
},
+ { /* PCU.3 (for Capability registers) */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ HSWEP_PCI_PCU_3),
+ },
{ /* end: all zeroes */ }
};
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/intel-family.h>
enum perf_msr_id {
if (event->attr.type != event->pmu->type)
return -ENOENT;
- if (cfg >= PERF_MSR_EVENT_MAX)
- return -EINVAL;
-
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
event->attr.sample_period) /* no sampling */
return -EINVAL;
+ if (cfg >= PERF_MSR_EVENT_MAX)
+ return -EINVAL;
+
+ cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
+
if (!msr[cfg].attr)
return -EINVAL;
#endif
#ifndef __ASSEMBLY__
-#ifndef __BPF__
/*
* This output constraint should be used for any inline asm which has a "call"
* instruction. Otherwise the asm may be inserted before the frame pointer
register unsigned long current_stack_pointer asm(_ASM_SP);
#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
#endif
-#endif
#endif /* _ASM_X86_ASM_H */
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit) boot_cpu_has(bit)
+
+#else
+
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
+#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
#endif /* CONFIG_FUNCTION_TRACER */
-#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+#ifndef __ASSEMBLY__
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+ /*
+ * Compare the symbol name with the system call name. Skip the
+ * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+ */
+ return !strcmp(sym + 3, name + 3) ||
+ (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
+ (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+}
+
+#ifndef COMPILE_OFFSETS
#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
#include <asm/compat.h>
return false;
}
#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
-#endif /* !__ASSEMBLY__ && !COMPILE_OFFSETS */
+#endif /* !COMPILE_OFFSETS */
+#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_FTRACE_H */
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
* (0x80 is the syscall vector, 0x30-0x3f are for ISA)
*/
#define FIRST_EXTERNAL_VECTOR 0x20
-/*
- * We start allocating at 0x21 to spread out vectors evenly between
- * priority levels. (0x80 is the syscall vector)
- */
-#define VECTOR_OFFSET_START 1
/*
* Reserve the lowest usable vector (and hence lowest priority) 0x20 for
#define FIRST_SYSTEM_VECTOR NR_VECTORS
#endif
-#define FPU_IRQ 13
-
/*
* Size the maximum number of interrupts.
*
-/* SPDX-License-Identifier: GPL2.0 */
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Jailhouse paravirt detection
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
- /* pkey 0 is the default and always allocated */
+ /* pkey 0 is the default and allocated implicitly */
mm->context.pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->context.execute_only_pkey = -1;
* lfence
* jmp spec_trap
* do_rop:
- * mov %rax,(%rsp)
+ * mov %rax,(%rsp) for x86_64
+ * mov %edx,(%esp) for x86_32
* retq
*
* Without retpolines configured:
*
- * jmp *%rax
+ * jmp *%rax for x86_64
+ * jmp *%edx for x86_32
*/
#ifdef CONFIG_RETPOLINE
-# define RETPOLINE_RAX_BPF_JIT_SIZE 17
-# define RETPOLINE_RAX_BPF_JIT() \
+# ifdef CONFIG_X86_64
+# define RETPOLINE_RAX_BPF_JIT_SIZE 17
+# define RETPOLINE_RAX_BPF_JIT() \
+do { \
EMIT1_off32(0xE8, 7); /* callq do_rop */ \
/* spec_trap: */ \
EMIT2(0xF3, 0x90); /* pause */ \
EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
/* do_rop: */ \
EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \
- EMIT1(0xC3); /* retq */
-#else
-# define RETPOLINE_RAX_BPF_JIT_SIZE 2
-# define RETPOLINE_RAX_BPF_JIT() \
- EMIT2(0xFF, 0xE0); /* jmp *%rax */
+ EMIT1(0xC3); /* retq */ \
+} while (0)
+# else /* !CONFIG_X86_64 */
+# define RETPOLINE_EDX_BPF_JIT() \
+do { \
+ EMIT1_off32(0xE8, 7); /* call do_rop */ \
+ /* spec_trap: */ \
+ EMIT2(0xF3, 0x90); /* pause */ \
+ EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \
+ EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
+ /* do_rop: */ \
+ EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */ \
+ EMIT1(0xC3); /* ret */ \
+} while (0)
+# endif
+#else /* !CONFIG_RETPOLINE */
+# ifdef CONFIG_X86_64
+# define RETPOLINE_RAX_BPF_JIT_SIZE 2
+# define RETPOLINE_RAX_BPF_JIT() \
+ EMIT2(0xFF, 0xE0); /* jmp *%rax */
+# else /* !CONFIG_X86_64 */
+# define RETPOLINE_EDX_BPF_JIT() \
+ EMIT2(0xFF, 0xE2) /* jmp *%edx */
+# endif
#endif
#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
#define canon_pgprot(p) __pgprot(massage_pgprot(p))
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ return canon_pgprot(prot);
+}
+
static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
enum page_cache_mode pcm,
enum page_cache_mode new_pcm)
#define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
-#define __VMALLOC_BASE_L4 0xffffc90000000000
-#define __VMALLOC_BASE_L5 0xffa0000000000000
+#define __VMALLOC_BASE_L4 0xffffc90000000000UL
+#define __VMALLOC_BASE_L5 0xffa0000000000000UL
#define VMALLOC_SIZE_TB_L4 32UL
#define VMALLOC_SIZE_TB_L5 12800UL
-#define __VMEMMAP_BASE_L4 0xffffea0000000000
-#define __VMEMMAP_BASE_L5 0xffd4000000000000
+#define __VMEMMAP_BASE_L4 0xffffea0000000000UL
+#define __VMEMMAP_BASE_L5 0xffd4000000000000UL
#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
# define VMALLOC_START vmalloc_base
#ifndef _ASM_X86_PKEYS_H
#define _ASM_X86_PKEYS_H
+#define ARCH_DEFAULT_PKEY 0
+
#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
static inline int execute_only_pkey(struct mm_struct *mm)
{
if (!boot_cpu_has(X86_FEATURE_OSPKE))
- return 0;
+ return ARCH_DEFAULT_PKEY;
return __execute_only_pkey(mm);
}
{
/*
* "Allocated" pkeys are those that have been returned
- * from pkey_alloc(). pkey 0 is special, and never
- * returned from pkey_alloc().
+ * from pkey_alloc() or pkey 0 which is allocated
+ * implicitly when the mm is created.
*/
- if (pkey <= 0)
+ if (pkey < 0)
return false;
if (pkey >= arch_max_pkey())
return false;
+ /*
+ * The exec-only pkey is set in the allocation map, but
+ * is not available to any of the user interfaces like
+ * mprotect_pkey().
+ */
+ if (pkey == mm->context.execute_only_pkey)
+ return false;
+
return mm_pkey_allocation_map(mm) & (1U << pkey);
}
extern void enable_sep_cpu(void);
extern int sysenter_setup(void);
-extern void early_trap_init(void);
void early_trap_pf_init(void);
/* Defined in head.S */
extern struct desc_ptr early_gdt_descr;
-extern void cpu_set_gdt(int);
extern void switch_to_new_gdt(int);
extern void load_direct_gdt(int);
extern void load_fixmap_gdt(int);
#define KVM_FEATURE_PV_TLB_FLUSH 9
#define KVM_FEATURE_ASYNC_PF_VMEXIT 10
-#define KVM_HINTS_DEDICATED 0
+#define KVM_HINTS_REALTIME 0
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X64_MSGBUF_H
+#define __ASM_X64_MSGBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
#include <asm-generic/msgbuf.h>
+#else
+/*
+ * The msqid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ __kernel_time_t msg_stime; /* last msgsnd time */
+ __kernel_time_t msg_rtime; /* last msgrcv time */
+ __kernel_time_t msg_ctime; /* last change time */
+ __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */
+ __kernel_ulong_t msg_qnum; /* number of messages in queue */
+ __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ __kernel_ulong_t __unused4;
+ __kernel_ulong_t __unused5;
+};
+
+#endif
+
+#endif /* __ASM_GENERIC_MSGBUF_H */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X86_SHMBUF_H
+#define __ASM_X86_SHMBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
#include <asm-generic/shmbuf.h>
+#else
+/*
+ * The shmid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct shmid64_ds {
+ struct ipc64_perm shm_perm; /* operation perms */
+ size_t shm_segsz; /* size of segment (bytes) */
+ __kernel_time_t shm_atime; /* last attach time */
+ __kernel_time_t shm_dtime; /* last detach time */
+ __kernel_time_t shm_ctime; /* last change time */
+ __kernel_pid_t shm_cpid; /* pid of creator */
+ __kernel_pid_t shm_lpid; /* pid of last operator */
+ __kernel_ulong_t shm_nattch; /* no. of current attaches */
+ __kernel_ulong_t __unused4;
+ __kernel_ulong_t __unused5;
+};
+
+struct shminfo64 {
+ __kernel_ulong_t shmmax;
+ __kernel_ulong_t shmmin;
+ __kernel_ulong_t shmmni;
+ __kernel_ulong_t shmseg;
+ __kernel_ulong_t shmall;
+ __kernel_ulong_t __unused1;
+ __kernel_ulong_t __unused2;
+ __kernel_ulong_t __unused3;
+ __kernel_ulong_t __unused4;
+};
+
+#endif
+
+#endif /* __ASM_X86_SHMBUF_H */
apic_id = processor->local_apic_id;
enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
+ /* Ignore invalid ID */
+ if (apic_id == 0xffffffff)
+ return 0;
+
/*
* We need to register disabled CPU as well to permit
* counting disabled CPUs. This allows us to size
#include <asm/amd_nb.h>
#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450
+#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
static const struct pci_device_id amd_root_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
{}
};
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{}
};
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
goto update;
}
cmsk = cluster_hotplug_mask;
+ cmsk->clusterid = cluster;
cluster_hotplug_mask = NULL;
update:
this_cpu_write(cluster_masks, cmsk);
c->x86_power = edx;
}
+ if (c->extended_cpuid_level >= 0x80000008) {
+ cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+ }
+
if (c->extended_cpuid_level >= 0x8000000a)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
- c->x86_capability[CPUID_8000_0008_EBX] = ebx;
}
#ifdef CONFIG_X86_32
else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
{ 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" },
{ 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" },
{ 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" },
+ { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" },
+ { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
+ { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" },
{ 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
{ 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" },
{ 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
[SMCA_SMU] = { "smu", "System Management Unit" },
};
+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
+{
+ [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
+};
+
const char *smca_get_name(enum smca_bank_types t)
{
if (t >= N_SMCA_BANK_TYPES)
if (!block)
return MSR_AMD64_SMCA_MCx_MISC(bank);
+ /* Check our cache first: */
+ if (smca_bank_addrs[bank][block] != -1)
+ return smca_bank_addrs[bank][block];
+
/*
* For SMCA enabled processors, BLKPTR field of the first MISC register
* (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
*/
if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ goto out;
if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ goto out;
if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
- return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+out:
+ smca_bank_addrs[bank][block] = addr;
return addr;
}
if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
return addr;
- /* Get address from already initialized block. */
- if (per_cpu(threshold_banks, cpu)) {
- struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
-
- if (bankp && bankp->blocks) {
- struct threshold_block *blockp = &bankp->blocks[block];
-
- if (blockp)
- return blockp->address;
- }
- }
-
if (mce_flags.smca)
return smca_get_block_address(cpu, bank, block);
apply_microcode_local(&err);
spin_unlock(&update_lock);
+ /* siblings return UCODE_OK because their engine got updated already */
if (err > UCODE_NFOUND) {
pr_warn("Error reloading microcode on CPU %d\n", cpu);
- return -1;
- /* siblings return UCODE_OK because their engine got updated already */
+ ret = -1;
} else if (err == UCODE_UPDATED || err == UCODE_OK) {
ret = 1;
- } else {
- return ret;
}
/*
*/
static void save_mc_for_early(u8 *mc, unsigned int size)
{
-#ifdef CONFIG_HOTPLUG_CPU
/* Synchronization during CPU hotplug. */
static DEFINE_MUTEX(x86_cpu_microcode_mutex);
show_saved_mc();
mutex_unlock(&x86_cpu_microcode_mutex);
-#endif
}
static bool load_builtin_intel_microcode(struct cpio_data *cp)
}
#endif
+/* Code in __startup_64() can be relocated during execution, but the compiler
+ * doesn't have to generate PC-relative relocations when accessing globals from
+ * that function. Clang actually does not generate them, which leads to
+ * boot-time crashes. To work around this problem, every global pointer must
+ * be adjusted using fixup_pointer().
+ */
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
p4dval_t *p4d;
pudval_t *pud;
pmdval_t *pmd, pmd_entry;
+ pteval_t *mask_ptr;
bool la57;
int i;
unsigned int *next_pgt_ptr;
pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
/* Filter out unsupported __PAGE_KERNEL_* bits: */
- pmd_entry &= __supported_pte_mask;
+ mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
+ pmd_entry &= *mask_ptr;
pmd_entry += sme_get_me_mask();
pmd_entry += physaddr;
-// SPDX-License-Identifier: GPL2.0
+// SPDX-License-Identifier: GPL-2.0
/*
* Jailhouse paravirt_ops implementation
*
* little bit simple
*/
efi_map_sz = efi_get_runtime_map_size();
- efi_map_sz = ALIGN(efi_map_sz, 16);
params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
MAX_ELFCOREHDR_STR_LEN;
params_cmdline_sz = ALIGN(params_cmdline_sz, 16);
- kbuf.bufsz = params_cmdline_sz + efi_map_sz +
+ kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) +
sizeof(struct setup_data) +
sizeof(struct efi_setup_data);
if (!params)
return ERR_PTR(-ENOMEM);
efi_map_offset = params_cmdline_sz;
- efi_setup_data_offset = efi_map_offset + efi_map_sz;
+ efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16);
/* Copy setup header onto bootparams. Documentation/x86/boot.txt */
setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset;
if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return 0;
+
#ifdef CONFIG_X86_64
/* Only x86_64 has RIP relative instructions */
if (insn_rip_relative(insn)) {
static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
static_branch_disable(&virt_spin_lock_key);
}
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
int cpu;
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
return;
__pv_init_lock_hash();
static void machine_kexec_free_page_tables(struct kimage *image)
{
free_page((unsigned long)image->arch.pgd);
+ image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
+ image->arch.pmd0 = NULL;
free_page((unsigned long)image->arch.pmd1);
+ image->arch.pmd1 = NULL;
#endif
free_page((unsigned long)image->arch.pte0);
+ image->arch.pte0 = NULL;
free_page((unsigned long)image->arch.pte1);
+ image->arch.pte1 = NULL;
}
static int machine_kexec_alloc_page_tables(struct kimage *image)
!image->arch.pmd0 || !image->arch.pmd1 ||
#endif
!image->arch.pte0 || !image->arch.pte1) {
- machine_kexec_free_page_tables(image);
return -ENOMEM;
}
return 0;
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
+ image->arch.p4d = NULL;
free_page((unsigned long)image->arch.pud);
+ image->arch.pud = NULL;
free_page((unsigned long)image->arch.pmd);
+ image->arch.pmd = NULL;
free_page((unsigned long)image->arch.pte);
+ image->arch.pte = NULL;
}
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
return 0;
err:
- free_transition_pgtable(image);
return result;
}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/* Fallback functions when the main IOMMU code is not compiled in. This
- code is roughly equivalent to i386. */
-#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/pci.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-
-#define NOMMU_MAPPING_ERROR 0
-
-static int
-check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
-{
- if (hwdev && !dma_capable(hwdev, bus, size)) {
- if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
- printk(KERN_ERR
- "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
- name, (long long)bus, size,
- (long long)*hwdev->dma_mask);
- return 0;
- }
- return 1;
-}
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset;
- WARN_ON(size == 0);
- if (!check_addr("map_single", dev, bus, size))
- return NOMMU_MAPPING_ERROR;
- return bus;
-}
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA. This is the scatter-gather version of the
- * above pci_map_single interface. Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length. They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *s;
- int i;
-
- WARN_ON(nents == 0 || sg[0].length == 0);
-
- for_each_sg(sg, s, nents, i) {
- BUG_ON(!sg_page(s));
- s->dma_address = sg_phys(s);
- if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
- return 0;
- s->dma_length = s->length;
- }
- return nents;
-}
-
-static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
- return dma_addr == NOMMU_MAPPING_ERROR;
-}
-
-const struct dma_map_ops nommu_dma_ops = {
- .alloc = dma_generic_alloc_coherent,
- .free = dma_generic_free_coherent,
- .map_sg = nommu_map_sg,
- .map_page = nommu_map_page,
- .is_phys = 1,
- .mapping_error = nommu_mapping_error,
- .dma_supported = x86_dma_supported,
-};
clear_thread_flag(TIF_X32);
/* Pretend that this comes from a 64bit execve */
task_pt_regs(current)->orig_ax = __NR_execve;
+ current_thread_info()->status &= ~TS_COMPAT;
/* Ensure the corresponding mm is not marked. */
if (current->mm)
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
#include <linux/dma-contiguous.h>
+#include <xen/xen.h>
#include <linux/errno.h>
#include <linux/kernel.h>
high = true;
}
+ if (xen_pv_domain()) {
+ pr_info("Ignoring crashkernel for a Xen PV domain\n");
+ return;
+ }
+
/* 0 means: find the address automatically */
if (crash_base <= 0) {
/*
#include <asm/i8259.h>
#include <asm/misc.h>
#include <asm/qspinlock.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
/* Number of siblings per CPU package */
int smp_num_siblings = 1;
return false;
}
+/*
+ * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ *
+ * These are Intel CPUs that enumerate an LLC that is shared by
+ * multiple NUMA nodes. The LLC on these systems is shared for
+ * off-package data access but private to the NUMA node (half
+ * of the package) for on-package access.
+ *
+ * CPUID (the source of the information about the LLC) can only
+ * enumerate the cache as being shared *or* unshared, but not
+ * this particular configuration. The CPU in this case enumerates
+ * the cache to be shared across the entire package (spanning both
+ * NUMA nodes).
+ */
+
+static const struct x86_cpu_id snc_cpu[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+ {}
+};
+
static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
- return topology_sane(c, o, "llc");
+ /* Do not match if we do not have a valid APICID for cpu: */
+ if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+ return false;
- return false;
+ /* Do not match if LLC id does not match: */
+ if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+ return false;
+
+ /*
+ * Allow the SNC topology without warning. Return of false
+ * means 'c' does not share the LLC of 'o'. This will be
+ * reflected to userspace.
+ */
+ if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+ return false;
+
+ return topology_sane(c, o, "llc");
}
/*
/*
* Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours and Intel Cluster-on-Die have this.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
*/
static bool x86_has_numa_in_package;
void *mwait_ptr;
int i;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ return;
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
if (!this_cpu_has(X86_FEATURE_CLFLUSH))
hpet2 -= hpet1;
tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
do_div(tmp, 1000000);
- do_div(deltatsc, tmp);
+ deltatsc = div64_u64(deltatsc, tmp);
return (unsigned long) deltatsc;
}
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
+ .list = LIST_HEAD_INIT(clocksource_tsc_early.list),
};
/*
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
+ .list = LIST_HEAD_INIT(clocksource_tsc.list),
};
void mark_tsc_unstable(char *reason)
clear_sched_clock_stable();
disable_sched_clock_irqtime();
pr_info("Marking TSC unstable due to %s\n", reason);
- /* Change only the rating, when not registered */
- if (clocksource_tsc.mult) {
- clocksource_mark_unstable(&clocksource_tsc);
- } else {
- clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
- clocksource_tsc.rating = 0;
- }
+
+ clocksource_mark_unstable(&clocksource_tsc_early);
+ clocksource_mark_unstable(&clocksource_tsc);
}
EXPORT_SYMBOL_GPL(mark_tsc_unstable);
/* Don't bother refining TSC on unstable systems */
if (tsc_unstable)
- return;
+ goto unreg;
/*
* Since the work is started early in boot, we may be
out:
if (tsc_unstable)
- return;
+ goto unreg;
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
clocksource_unregister(&clocksource_tsc_early);
}
if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
return 0;
- if (check_tsc_unstable())
- return 0;
+ if (tsc_unstable)
+ goto unreg;
if (tsc_clocksource_reliable)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
clocksource_unregister(&clocksource_tsc_early);
return 0;
}
if (is_prefix_bad(insn))
return -ENOTSUPP;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return -ENOTSUPP;
+
if (x86_64)
good_insns = good_insns_64;
else
struct kvm_run *run = vcpu->run;
kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
- return 1;
+ return kvm_skip_emulated_instruction(vcpu);
}
static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
if (param & ~KVM_HYPERV_CONN_ID_MASK)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- /* conn_to_evt is protected by vcpu->kvm->srcu */
+ /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+ rcu_read_lock();
eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+ rcu_read_unlock();
if (!eventfd)
return HV_STATUS_INVALID_PORT_ID;
local_irq_restore(flags);
}
-static void start_sw_period(struct kvm_lapic *apic)
-{
- if (!apic->lapic_timer.period)
- return;
-
- if (apic_lvtt_oneshot(apic) &&
- ktime_after(ktime_get(),
- apic->lapic_timer.target_expiration)) {
- apic_timer_expired(apic);
- return;
- }
-
- hrtimer_start(&apic->lapic_timer.timer,
- apic->lapic_timer.target_expiration,
- HRTIMER_MODE_ABS_PINNED);
-}
-
static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
{
ktime_t now, remaining;
apic->lapic_timer.period);
}
+static void start_sw_period(struct kvm_lapic *apic)
+{
+ if (!apic->lapic_timer.period)
+ return;
+
+ if (ktime_after(ktime_get(),
+ apic->lapic_timer.target_expiration)) {
+ apic_timer_expired(apic);
+
+ if (apic_lvtt_oneshot(apic))
+ return;
+
+ advance_periodic_target_expiration(apic);
+ }
+
+ hrtimer_start(&apic->lapic_timer.timer,
+ apic->lapic_timer.target_expiration,
+ HRTIMER_MODE_ABS_PINNED);
+}
+
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
{
if (!lapic_in_kernel(vcpu))
SECONDARY_EXEC_ENABLE_VMFUNC;
}
+static bool vmx_umip_emulated(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_DESC;
+}
+
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
}
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
- if (enable_ept)
- vmx_flush_tlb(vcpu, true);
-}
-
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
else
hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
- if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
- vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_DESC);
- hw_cr4 &= ~X86_CR4_UMIP;
- } else if (!is_guest_mode(vcpu) ||
- !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
- vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+ if (cr4 & X86_CR4_UMIP) {
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_DESC);
+ hw_cr4 &= ~X86_CR4_UMIP;
+ } else if (!is_guest_mode(vcpu) ||
+ !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+ }
if (cr4 & X86_CR4_VMXE) {
/*
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
}
SECONDARY_EXEC_XSAVES;
}
-static bool vmx_umip_emulated(void)
-{
- return vmcs_config.cpu_based_2nd_exec_ctrl &
- SECONDARY_EXEC_DESC;
-}
-
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
}
} else if (nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
/*
} else if (!nested_cpu_has_ept(vmcs12) &&
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
static bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
static bool __read_mostly kvmclock_periodic_sync = true;
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
#ifdef CONFIG_X86_64
- cr3 &= ~CR3_PCID_INVD;
+ bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+ if (pcid_enabled)
+ cr3 &= ~CR3_PCID_INVD;
#endif
if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
- int op_64_bit, r;
-
- r = kvm_skip_emulated_instruction(vcpu);
+ int op_64_bit;
- if (kvm_hv_hypercall_enabled(vcpu->kvm))
- return kvm_hv_hypercall(vcpu);
+ if (kvm_hv_hypercall_enabled(vcpu->kvm)) {
+ if (!kvm_hv_hypercall(vcpu))
+ return 0;
+ goto out;
+ }
nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
if (kvm_x86_ops->get_cpl(vcpu) != 0) {
ret = -KVM_EPERM;
- goto out;
+ goto out_error;
}
switch (nr) {
ret = -KVM_ENOSYS;
break;
}
-out:
+out_error:
if (!op_64_bit)
ret = (u32)ret;
kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
+out:
++vcpu->stat.hypercalls;
- return r;
+ return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
__rem; \
})
-#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
-#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
- KVM_X86_DISABLE_EXITS_HTL | \
- KVM_X86_DISABLE_EXITS_PAUSE)
-
static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
return kvm->arch.mwait_in_guest;
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
+#include <linux/highmem.h>
#include <asm/pgtable.h>
pgprotval_t eff_in, unsigned long P)
{
int i;
- pte_t *start;
+ pte_t *pte;
pgprotval_t prot, eff;
- start = (pte_t *)pmd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PTE; i++) {
- prot = pte_flags(*start);
- eff = effective_prot(eff_in, prot);
st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
+ pte = pte_offset_map(&addr, st->current_address);
+ prot = pte_flags(*pte);
+ eff = effective_prot(eff_in, prot);
note_page(m, st, __pgprot(prot), eff, 5);
- start++;
+ pte_unmap(pte);
}
}
#ifdef CONFIG_KASAN
static inline void split_page_count(int level) { }
#endif
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+ return addr >= start && addr < end;
+}
+
+static inline int
+within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+{
+ return addr >= start && addr <= end;
+}
+
#ifdef CONFIG_X86_64
static inline unsigned long highmap_start_pfn(void)
return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT;
}
-#endif
-
-static inline int
-within(unsigned long addr, unsigned long start, unsigned long end)
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
{
- return addr >= start && addr < end;
+ /*
+ * Kernel text has an alias mapping at a high address, known
+ * here as "highmap".
+ */
+ return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn());
}
-static inline int
-within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+#else
+
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
{
- return addr >= start && addr <= end;
+ /* There is no highmap on 32-bit */
+ return false;
}
+#endif
+
/*
* Flushing functions
*/
static void cpa_flush_all(unsigned long cache)
{
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}
unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
#endif
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
cpa->numpages = 1;
cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
return 0;
+
+ } else if (__cpa_pfn_in_highmap(cpa->pfn)) {
+ /* Faults in the highmap are OK, so do not warn: */
+ return -EFAULT;
} else {
WARN(1, KERN_WARNING "CPA: called for zero pte. "
"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
* to touch the high mapped kernel as well:
*/
if (!within(vaddr, (unsigned long)_text, _brk_end) &&
- within_inclusive(cpa->pfn, highmap_start_pfn(),
- highmap_end_pfn())) {
+ __cpa_pfn_in_highmap(cpa->pfn)) {
unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
__START_KERNEL_map - phys_base;
alias_cpa = *cpa;
*/
if (pkey != -1)
return pkey;
- /*
- * Look for a protection-key-drive execute-only mapping
- * which is now being given permissions that are not
- * execute-only. Move it back to the default pkey.
- */
- if (vma_is_pkey_exec_only(vma) &&
- (prot & (PROT_READ|PROT_WRITE))) {
- return 0;
- }
+
/*
* The mapping is execute-only. Go try to get the
* execute-only protection key. If we fail to do that,
* fall through as if we do not have execute-only
- * support.
+ * support in this mm.
*/
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(vma->vm_mm);
if (pkey > 0)
return pkey;
+ } else if (vma_is_pkey_exec_only(vma)) {
+ /*
+ * Protections are *not* PROT_EXEC, but the mapping
+ * is using the exec-only pkey. This mapping was
+ * PROT_EXEC and will no longer be. Move back to
+ * the default pkey.
+ */
+ return ARCH_DEFAULT_PKEY;
}
+
/*
* This is a vanilla, non-pkey mprotect (or we failed to
* setup execute-only), inherit the pkey from the VMA we
if (boot_cpu_has(X86_FEATURE_K8))
return false;
+ /*
+ * RANDSTRUCT derives its hardening benefits from the
+ * attacker's lack of knowledge about the layout of kernel
+ * data structures. Keep the kernel image non-global in
+ * cases where RANDSTRUCT is in use to help keep the layout a
+ * secret.
+ */
+ if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT))
+ return false;
+
return true;
}
*/
void pti_clone_kernel_text(void)
{
+ /*
+ * rodata is part of the kernel image and is normally
+ * readable on the filesystem or on the web. But, do not
+ * clone the areas past rodata, they might contain secrets.
+ */
unsigned long start = PFN_ALIGN(_text);
- unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
+ unsigned long end = (unsigned long)__end_rodata_hpage_align;
if (!pti_kernel_image_global_ok())
return;
+ pr_debug("mapping partial kernel image into user address space\n");
+
+ /*
+ * Note that this will undo _some_ of the work that
+ * pti_set_kernel_image_nonglobal() did to clear the
+ * global bit.
+ */
pti_clone_pmds(start, end, _PAGE_RW);
}
if (pti_kernel_image_global_ok())
return;
- pr_debug("set kernel image non-global\n");
-
set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
}
#
# Arch-specific network modules
#
-OBJECT_FILES_NON_STANDARD_bpf_jit.o += y
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+ifeq ($(CONFIG_X86_32),y)
+ obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
+else
+ obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+endif
+++ /dev/null
-/* bpf_jit.S : BPF JIT helper functions
- *
- * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <linux/linkage.h>
-#include <asm/frame.h>
-
-/*
- * Calling convention :
- * rbx : skb pointer (callee saved)
- * esi : offset of byte(s) to fetch in skb (can be scratched)
- * r10 : copy of skb->data
- * r9d : hlen = skb->len - skb->data_len
- */
-#define SKBDATA %r10
-#define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */
-
-#define FUNC(name) \
- .globl name; \
- .type name, @function; \
- name:
-
-FUNC(sk_load_word)
- test %esi,%esi
- js bpf_slow_path_word_neg
-
-FUNC(sk_load_word_positive_offset)
- mov %r9d,%eax # hlen
- sub %esi,%eax # hlen - offset
- cmp $3,%eax
- jle bpf_slow_path_word
- mov (SKBDATA,%rsi),%eax
- bswap %eax /* ntohl() */
- ret
-
-FUNC(sk_load_half)
- test %esi,%esi
- js bpf_slow_path_half_neg
-
-FUNC(sk_load_half_positive_offset)
- mov %r9d,%eax
- sub %esi,%eax # hlen - offset
- cmp $1,%eax
- jle bpf_slow_path_half
- movzwl (SKBDATA,%rsi),%eax
- rol $8,%ax # ntohs()
- ret
-
-FUNC(sk_load_byte)
- test %esi,%esi
- js bpf_slow_path_byte_neg
-
-FUNC(sk_load_byte_positive_offset)
- cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */
- jle bpf_slow_path_byte
- movzbl (SKBDATA,%rsi),%eax
- ret
-
-/* rsi contains offset and can be scratched */
-#define bpf_slow_path_common(LEN) \
- lea 32(%rbp), %rdx;\
- FRAME_BEGIN; \
- mov %rbx, %rdi; /* arg1 == skb */ \
- push %r9; \
- push SKBDATA; \
-/* rsi already has offset */ \
- mov $LEN,%ecx; /* len */ \
- call skb_copy_bits; \
- test %eax,%eax; \
- pop SKBDATA; \
- pop %r9; \
- FRAME_END
-
-
-bpf_slow_path_word:
- bpf_slow_path_common(4)
- js bpf_error
- mov 32(%rbp),%eax
- bswap %eax
- ret
-
-bpf_slow_path_half:
- bpf_slow_path_common(2)
- js bpf_error
- mov 32(%rbp),%ax
- rol $8,%ax
- movzwl %ax,%eax
- ret
-
-bpf_slow_path_byte:
- bpf_slow_path_common(1)
- js bpf_error
- movzbl 32(%rbp),%eax
- ret
-
-#define sk_negative_common(SIZE) \
- FRAME_BEGIN; \
- mov %rbx, %rdi; /* arg1 == skb */ \
- push %r9; \
- push SKBDATA; \
-/* rsi already has offset */ \
- mov $SIZE,%edx; /* size */ \
- call bpf_internal_load_pointer_neg_helper; \
- test %rax,%rax; \
- pop SKBDATA; \
- pop %r9; \
- FRAME_END; \
- jz bpf_error
-
-bpf_slow_path_word_neg:
- cmp SKF_MAX_NEG_OFF, %esi /* test range */
- jl bpf_error /* offset lower -> error */
-
-FUNC(sk_load_word_negative_offset)
- sk_negative_common(4)
- mov (%rax), %eax
- bswap %eax
- ret
-
-bpf_slow_path_half_neg:
- cmp SKF_MAX_NEG_OFF, %esi
- jl bpf_error
-
-FUNC(sk_load_half_negative_offset)
- sk_negative_common(2)
- mov (%rax),%ax
- rol $8,%ax
- movzwl %ax,%eax
- ret
-
-bpf_slow_path_byte_neg:
- cmp SKF_MAX_NEG_OFF, %esi
- jl bpf_error
-
-FUNC(sk_load_byte_negative_offset)
- sk_negative_common(1)
- movzbl (%rax), %eax
- ret
-
-bpf_error:
-# force a return 0 from jit handler
- xor %eax,%eax
- mov (%rbp),%rbx
- mov 8(%rbp),%r13
- mov 16(%rbp),%r14
- mov 24(%rbp),%r15
- add $40, %rbp
- leaveq
- ret
-/* bpf_jit_comp.c : BPF JIT compiler
+/*
+ * bpf_jit_comp.c: BPF JIT compiler
*
* Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
* Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
-/*
- * assembly code in arch/x86/net/bpf_jit.S
- */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
-extern u8 sk_load_byte_positive_offset[];
-extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
-extern u8 sk_load_byte_negative_offset[];
-
static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
if (len == 1)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
#define EMIT1_off32(b1, off) \
- do {EMIT1(b1); EMIT(off, 4); } while (0)
+ do { EMIT1(b1); EMIT(off, 4); } while (0)
#define EMIT2_off32(b1, b2, off) \
- do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+ do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
#define EMIT3_off32(b1, b2, b3, off) \
- do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+ do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
#define EMIT4_off32(b1, b2, b3, b4, off) \
- do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+ do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
static bool is_imm8(int value)
{
}
/* mov dst, src */
-#define EMIT_mov(DST, SRC) \
- do {if (DST != SRC) \
- EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+#define EMIT_mov(DST, SRC) \
+ do { \
+ if (DST != SRC) \
+ EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
} while (0)
static int bpf_size_to_x86_bytes(int bpf_size)
return 0;
}
-/* list of x86 cond jumps opcodes (. + s8)
+/*
+ * List of x86 cond jumps opcodes (. + s8)
* Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
*/
#define X86_JB 0x72
#define X86_JLE 0x7E
#define X86_JG 0x7F
-#define CHOOSE_LOAD_FUNC(K, func) \
- ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
-/* pick a register outside of BPF range for JIT internal work */
+/* Pick a register outside of BPF range for JIT internal work */
#define AUX_REG (MAX_BPF_JIT_REG + 1)
-/* The following table maps BPF registers to x64 registers.
+/*
+ * The following table maps BPF registers to x86-64 registers.
*
- * x64 register r12 is unused, since if used as base address
+ * x86-64 register R12 is unused, since if used as base address
* register in load/store instructions, it always needs an
* extra byte of encoding and is callee saved.
*
- * r9 caches skb->len - skb->data_len
- * r10 caches skb->data, and used for blinding (if enabled)
+ * Also x86-64 register R9 is unused. x86-64 register R10 is
+ * used for blinding (if enabled).
*/
static const int reg2hex[] = {
- [BPF_REG_0] = 0, /* rax */
- [BPF_REG_1] = 7, /* rdi */
- [BPF_REG_2] = 6, /* rsi */
- [BPF_REG_3] = 2, /* rdx */
- [BPF_REG_4] = 1, /* rcx */
- [BPF_REG_5] = 0, /* r8 */
- [BPF_REG_6] = 3, /* rbx callee saved */
- [BPF_REG_7] = 5, /* r13 callee saved */
- [BPF_REG_8] = 6, /* r14 callee saved */
- [BPF_REG_9] = 7, /* r15 callee saved */
- [BPF_REG_FP] = 5, /* rbp readonly */
- [BPF_REG_AX] = 2, /* r10 temp register */
- [AUX_REG] = 3, /* r11 temp register */
+ [BPF_REG_0] = 0, /* RAX */
+ [BPF_REG_1] = 7, /* RDI */
+ [BPF_REG_2] = 6, /* RSI */
+ [BPF_REG_3] = 2, /* RDX */
+ [BPF_REG_4] = 1, /* RCX */
+ [BPF_REG_5] = 0, /* R8 */
+ [BPF_REG_6] = 3, /* RBX callee saved */
+ [BPF_REG_7] = 5, /* R13 callee saved */
+ [BPF_REG_8] = 6, /* R14 callee saved */
+ [BPF_REG_9] = 7, /* R15 callee saved */
+ [BPF_REG_FP] = 5, /* RBP readonly */
+ [BPF_REG_AX] = 2, /* R10 temp register */
+ [AUX_REG] = 3, /* R11 temp register */
};
-/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+/*
+ * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
* which need extra byte of encoding.
* rax,rcx,...,rbp have simpler encoding
*/
return reg == BPF_REG_0;
}
-/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
static u8 add_1mod(u8 byte, u32 reg)
{
if (is_ereg(reg))
return byte;
}
-/* encode 'dst_reg' register into x64 opcode 'byte' */
+/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
static u8 add_1reg(u8 byte, u32 dst_reg)
{
return byte + reg2hex[dst_reg];
}
-/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
{
return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
static void jit_fill_hole(void *area, unsigned int size)
{
- /* fill whole space with int3 instructions */
+ /* Fill whole space with INT3 instructions */
memset(area, 0xcc, size);
}
struct jit_context {
- int cleanup_addr; /* epilogue code offset */
- bool seen_ld_abs;
- bool seen_ax_reg;
+ int cleanup_addr; /* Epilogue code offset */
};
-/* maximum number of bytes emitted while JITing one eBPF insn */
+/* Maximum number of bytes emitted while JITing one eBPF insn */
#define BPF_MAX_INSN_SIZE 128
#define BPF_INSN_SAFETY 64
-#define AUX_STACK_SPACE \
- (32 /* space for rbx, r13, r14, r15 */ + \
- 8 /* space for skb_copy_bits() buffer */)
+#define AUX_STACK_SPACE 40 /* Space for RBX, R13, R14, R15, tailcnt */
-#define PROLOGUE_SIZE 37
+#define PROLOGUE_SIZE 37
-/* emit x64 prologue code for BPF program and check it's size.
+/*
+ * Emit x86-64 prologue code for BPF program and check its size.
* bpf_tail_call helper will skip it while jumping into another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
u8 *prog = *pprog;
int cnt = 0;
- EMIT1(0x55); /* push rbp */
- EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+ /* push rbp */
+ EMIT1(0x55);
+
+ /* mov rbp,rsp */
+ EMIT3(0x48, 0x89, 0xE5);
/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
EMIT3_off32(0x48, 0x81, 0xEC,
/* sub rbp, AUX_STACK_SPACE */
EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
- /* all classic BPF filters use R6(rbx) save it */
-
/* mov qword ptr [rbp+0],rbx */
EMIT4(0x48, 0x89, 0x5D, 0);
-
- /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
- * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
- * R8(r14). R9(r15) spill could be made conditional, but there is only
- * one 'bpf_error' return path out of helper functions inside bpf_jit.S
- * The overhead of extra spill is negligible for any filter other
- * than synthetic ones. Therefore not worth adding complexity.
- */
-
/* mov qword ptr [rbp+8],r13 */
EMIT4(0x4C, 0x89, 0x6D, 8);
/* mov qword ptr [rbp+16],r14 */
EMIT4(0x4C, 0x89, 0x7D, 24);
if (!ebpf_from_cbpf) {
- /* Clear the tail call counter (tail_call_cnt): for eBPF tail
+ /*
+ * Clear the tail call counter (tail_call_cnt): for eBPF tail
* calls we need to reset the counter to 0. It's done in two
- * instructions, resetting rax register to 0, and moving it
+ * instructions, resetting RAX register to 0, and moving it
* to the counter location.
*/
*pprog = prog;
}
-/* generate the following code:
+/*
+ * Generate the following code:
+ *
* ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
* if (index >= array->map.max_entries)
* goto out;
int label1, label2, label3;
int cnt = 0;
- /* rdi - pointer to ctx
+ /*
+ * rdi - pointer to ctx
* rsi - pointer to bpf_array
* rdx - index in bpf_array
*/
- /* if (index >= array->map.max_entries)
- * goto out;
+ /*
+ * if (index >= array->map.max_entries)
+ * goto out;
*/
EMIT2(0x89, 0xD2); /* mov edx, edx */
EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */
offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
- /* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
- * goto out;
+ /*
+ * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
*/
EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
offsetof(struct bpf_array, ptrs));
- /* if (prog == NULL)
- * goto out;
+ /*
+ * if (prog == NULL)
+ * goto out;
*/
EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */
#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
offsetof(struct bpf_prog, bpf_func));
EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */
- /* now we're ready to jump into next BPF program
+ /*
+ * Wow we're ready to jump into next BPF program
* rdi == ctx (1st arg)
* rax == prog->bpf_func + prologue_size
*/
*pprog = prog;
}
-
-static void emit_load_skb_data_hlen(u8 **pprog)
-{
- u8 *prog = *pprog;
- int cnt = 0;
-
- /* r9d = skb->len - skb->data_len (headlen)
- * r10 = skb->data
- */
- /* mov %r9d, off32(%rdi) */
- EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
-
- /* sub %r9d, off32(%rdi) */
- EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
-
- /* mov %r10, off32(%rdi) */
- EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
- *pprog = prog;
-}
-
static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
u32 dst_reg, const u32 imm32)
{
u8 b1, b2, b3;
int cnt = 0;
- /* optimization: if imm32 is positive, use 'mov %eax, imm32'
+ /*
+ * Optimization: if imm32 is positive, use 'mov %eax, imm32'
* (which zero-extends imm32) to save 2 bytes.
*/
if (sign_propagate && (s32)imm32 < 0) {
goto done;
}
- /* optimization: if imm32 is zero, use 'xor %eax, %eax'
+ /*
+ * Optimization: if imm32 is zero, use 'xor %eax, %eax'
* to save 3 bytes.
*/
if (imm32 == 0) {
int cnt = 0;
if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
- /* For emitting plain u32, where sign bit must not be
+ /*
+ * For emitting plain u32, where sign bit must not be
* propagated LLVM tends to load imm64 over mov32
* directly, so save couple of bytes by just doing
* 'mov %eax, imm32' instead.
{
struct bpf_insn *insn = bpf_prog->insnsi;
int insn_cnt = bpf_prog->len;
- bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
- bool seen_ax_reg = ctx->seen_ax_reg | (oldproglen == 0);
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
int i, cnt = 0;
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog));
- if (seen_ld_abs)
- emit_load_skb_data_hlen(&prog);
-
for (i = 0; i < insn_cnt; i++, insn++) {
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u8 b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
- bool reload_skb_data;
int ilen;
u8 *func;
- if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
- ctx->seen_ax_reg = seen_ax_reg = true;
-
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
- /* b3 holds 'normal' opcode, b2 short form only valid
+ /*
+ * b3 holds 'normal' opcode, b2 short form only valid
* in case dst is eax/rax.
*/
switch (BPF_OP(insn->code)) {
/* mov rax, dst_reg */
EMIT_mov(BPF_REG_0, dst_reg);
- /* xor edx, edx
+ /*
+ * xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
}
break;
}
- /* shifts */
+ /* Shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_ARSH | BPF_K:
case BPF_ALU64 | BPF_RSH | BPF_X:
case BPF_ALU64 | BPF_ARSH | BPF_X:
- /* check for bad case when dst_reg == rcx */
+ /* Check for bad case when dst_reg == rcx */
if (dst_reg == BPF_REG_4) {
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
- /* emit 'ror %ax, 8' to swap lower 2 bytes */
+ /* Emit 'ror %ax, 8' to swap lower 2 bytes */
EMIT1(0x66);
if (is_ereg(dst_reg))
EMIT1(0x41);
EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
- /* emit 'movzwl eax, ax' */
+ /* Emit 'movzwl eax, ax' */
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
- /* emit 'bswap eax' to swap lower 4 bytes */
+ /* Emit 'bswap eax' to swap lower 4 bytes */
if (is_ereg(dst_reg))
EMIT2(0x41, 0x0F);
else
EMIT1(add_1reg(0xC8, dst_reg));
break;
case 64:
- /* emit 'bswap rax' to swap 8 bytes */
+ /* Emit 'bswap rax' to swap 8 bytes */
EMIT3(add_1mod(0x48, dst_reg), 0x0F,
add_1reg(0xC8, dst_reg));
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm32) {
case 16:
- /* emit 'movzwl eax, ax' to zero extend 16-bit
+ /*
+ * Emit 'movzwl eax, ax' to zero extend 16-bit
* into 64 bit
*/
if (is_ereg(dst_reg))
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
- /* emit 'mov eax, eax' to clear upper 32-bits */
+ /* Emit 'mov eax, eax' to clear upper 32-bits */
if (is_ereg(dst_reg))
EMIT1(0x45);
EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
/* STX: *(u8*)(dst_reg + off) = src_reg */
case BPF_STX | BPF_MEM | BPF_B:
- /* emit 'mov byte ptr [rax + off], al' */
+ /* Emit 'mov byte ptr [rax + off], al' */
if (is_ereg(dst_reg) || is_ereg(src_reg) ||
- /* have to add extra byte for x86 SIL, DIL regs */
+ /* We have to add extra byte for x86 SIL, DIL regs */
src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
else
/* LDX: dst_reg = *(u8*)(src_reg + off) */
case BPF_LDX | BPF_MEM | BPF_B:
- /* emit 'movzx rax, byte ptr [rax + off]' */
+ /* Emit 'movzx rax, byte ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_H:
- /* emit 'movzx rax, word ptr [rax + off]' */
+ /* Emit 'movzx rax, word ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_W:
- /* emit 'mov eax, dword ptr [rax+0x14]' */
+ /* Emit 'mov eax, dword ptr [rax+0x14]' */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
else
EMIT1(0x8B);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_DW:
- /* emit 'mov rax, qword ptr [rax+0x14]' */
+ /* Emit 'mov rax, qword ptr [rax+0x14]' */
EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx: /* if insn->off == 0 we can save one extra byte, but
- * special case of x86 r13 which always needs an offset
+ldx: /*
+ * If insn->off == 0 we can save one extra byte, but
+ * special case of x86 R13 which always needs an offset
* is not worth the hassle
*/
if (is_imm8(insn->off))
/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
case BPF_STX | BPF_XADD | BPF_W:
- /* emit 'lock add dword ptr [rax + off], eax' */
+ /* Emit 'lock add dword ptr [rax + off], eax' */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
else
case BPF_JMP | BPF_CALL:
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
- if (seen_ld_abs) {
- reload_skb_data = bpf_helper_changes_pkt_data(func);
- if (reload_skb_data) {
- EMIT1(0x57); /* push %rdi */
- jmp_offset += 22; /* pop, mov, sub, mov */
- } else {
- EMIT2(0x41, 0x52); /* push %r10 */
- EMIT2(0x41, 0x51); /* push %r9 */
- /* need to adjust jmp offset, since
- * pop %r9, pop %r10 take 4 bytes after call insn
- */
- jmp_offset += 4;
- }
- }
if (!imm32 || !is_simm32(jmp_offset)) {
- pr_err("unsupported bpf func %d addr %p image %p\n",
+ pr_err("unsupported BPF func %d addr %p image %p\n",
imm32, func, image);
return -EINVAL;
}
EMIT1_off32(0xE8, jmp_offset);
- if (seen_ld_abs) {
- if (reload_skb_data) {
- EMIT1(0x5F); /* pop %rdi */
- emit_load_skb_data_hlen(&prog);
- } else {
- EMIT2(0x41, 0x59); /* pop %r9 */
- EMIT2(0x41, 0x5A); /* pop %r10 */
- }
- }
break;
case BPF_JMP | BPF_TAIL_CALL:
else
EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
-emit_cond_jmp: /* convert BPF opcode to x86 */
+emit_cond_jmp: /* Convert BPF opcode to x86 */
switch (BPF_OP(insn->code)) {
case BPF_JEQ:
jmp_cond = X86_JE;
jmp_cond = X86_JBE;
break;
case BPF_JSGT:
- /* signed '>', GT in x86 */
+ /* Signed '>', GT in x86 */
jmp_cond = X86_JG;
break;
case BPF_JSLT:
- /* signed '<', LT in x86 */
+ /* Signed '<', LT in x86 */
jmp_cond = X86_JL;
break;
case BPF_JSGE:
- /* signed '>=', GE in x86 */
+ /* Signed '>=', GE in x86 */
jmp_cond = X86_JGE;
break;
case BPF_JSLE:
- /* signed '<=', LE in x86 */
+ /* Signed '<=', LE in x86 */
jmp_cond = X86_JLE;
break;
- default: /* to silence gcc warning */
+ default: /* to silence GCC warning */
return -EFAULT;
}
jmp_offset = addrs[i + insn->off] - addrs[i];
break;
case BPF_JMP | BPF_JA:
- jmp_offset = addrs[i + insn->off] - addrs[i];
+ if (insn->off == -1)
+ /* -1 jmp instructions will always jump
+ * backwards two bytes. Explicitly handling
+ * this case avoids wasting too many passes
+ * when there are long sequences of replaced
+ * dead code.
+ */
+ jmp_offset = -2;
+ else
+ jmp_offset = addrs[i + insn->off] - addrs[i];
+
if (!jmp_offset)
- /* optimize out nop jumps */
+ /* Optimize out nop jumps */
break;
emit_jmp:
if (is_imm8(jmp_offset)) {
}
break;
- case BPF_LD | BPF_IND | BPF_W:
- func = sk_load_word;
- goto common_load;
- case BPF_LD | BPF_ABS | BPF_W:
- func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:
- ctx->seen_ld_abs = seen_ld_abs = true;
- jmp_offset = func - (image + addrs[i]);
- if (!func || !is_simm32(jmp_offset)) {
- pr_err("unsupported bpf func %d addr %p image %p\n",
- imm32, func, image);
- return -EINVAL;
- }
- if (BPF_MODE(insn->code) == BPF_ABS) {
- /* mov %esi, imm32 */
- EMIT1_off32(0xBE, imm32);
- } else {
- /* mov %rsi, src_reg */
- EMIT_mov(BPF_REG_2, src_reg);
- if (imm32) {
- if (is_imm8(imm32))
- /* add %esi, imm8 */
- EMIT3(0x83, 0xC6, imm32);
- else
- /* add %esi, imm32 */
- EMIT2_off32(0x81, 0xC6, imm32);
- }
- }
- /* skb pointer is in R6 (%rbx), it will be copied into
- * %rdi if skb_copy_bits() call is necessary.
- * sk_load_* helpers also use %r10 and %r9d.
- * See bpf_jit.S
- */
- if (seen_ax_reg)
- /* r10 = skb->data, mov %r10, off32(%rbx) */
- EMIT3_off32(0x4c, 0x8b, 0x93,
- offsetof(struct sk_buff, data));
- EMIT1_off32(0xE8, jmp_offset); /* call */
- break;
-
- case BPF_LD | BPF_IND | BPF_H:
- func = sk_load_half;
- goto common_load;
- case BPF_LD | BPF_ABS | BPF_H:
- func = CHOOSE_LOAD_FUNC(imm32, sk_load_half);
- goto common_load;
- case BPF_LD | BPF_IND | BPF_B:
- func = sk_load_byte;
- goto common_load;
- case BPF_LD | BPF_ABS | BPF_B:
- func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte);
- goto common_load;
-
case BPF_JMP | BPF_EXIT:
if (seen_exit) {
jmp_offset = ctx->cleanup_addr - addrs[i];
goto emit_jmp;
}
seen_exit = true;
- /* update cleanup_addr */
+ /* Update cleanup_addr */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp+0] */
EMIT4(0x48, 0x8B, 0x5D, 0);
break;
default:
- /* By design x64 JIT should support all BPF instructions
+ /*
+ * By design x86-64 JIT should support all BPF instructions.
* This error will be seen if new instruction was added
- * to interpreter, but not to JIT
- * or if there is junk in bpf_prog
+ * to the interpreter, but not to the JIT, or if there is
+ * junk in bpf_prog.
*/
pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
return -EINVAL;
return orig_prog;
tmp = bpf_jit_blind_constants(prog);
- /* If blinding was requested and we failed during blinding,
+ /*
+ * If blinding was requested and we failed during blinding,
* we must fall back to the interpreter.
*/
if (IS_ERR(tmp))
goto out_addrs;
}
- /* Before first pass, make a rough estimation of addrs[]
- * each bpf instruction is translated to less than 64 bytes
+ /*
+ * Before first pass, make a rough estimation of addrs[]
+ * each BPF instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < prog->len; i++) {
proglen += 64;
ctx.cleanup_addr = proglen;
skip_init_addrs:
- /* JITed image shrinks with every pass and the loop iterates
- * until the image stops shrinking. Very large bpf programs
+ /*
+ * JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large BPF programs
* may converge on the last pass. In such case do one more
- * pass to emit the final image
+ * pass to emit the final image.
*/
for (pass = 0; pass < 20 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
+out_image:
image = NULL;
if (header)
bpf_jit_binary_free(header);
if (proglen != oldproglen) {
pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
proglen, oldproglen);
- prog = orig_prog;
- goto out_addrs;
+ goto out_image;
}
break;
}
prog = orig_prog;
}
- if (!prog->is_func || extra_pass) {
+ if (!image || !prog->is_func || extra_pass) {
out_addrs:
kfree(addrs);
kfree(jit_data);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Just-In-Time compiler for eBPF filters on IA32 (32bit x86)
+ *
+ * Author: Wang YanQing (udknight@gmail.com)
+ * The code based on code and ideas from:
+ * Eric Dumazet (eric.dumazet@gmail.com)
+ * and from:
+ * Shubham Bansal <illusionist.neo@gmail.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+#include <linux/if_vlan.h>
+#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
+#include <asm/nospec-branch.h>
+#include <linux/bpf.h>
+
+/*
+ * eBPF prog stack layout:
+ *
+ * high
+ * original ESP => +-----+
+ * | | callee saved registers
+ * +-----+
+ * | ... | eBPF JIT scratch space
+ * BPF_FP,IA32_EBP => +-----+
+ * | ... | eBPF prog stack
+ * +-----+
+ * |RSVD | JIT scratchpad
+ * current ESP => +-----+
+ * | |
+ * | ... | Function call stack
+ * | |
+ * +-----+
+ * low
+ *
+ * The callee saved registers:
+ *
+ * high
+ * original ESP => +------------------+ \
+ * | ebp | |
+ * current EBP => +------------------+ } callee saved registers
+ * | ebx,esi,edi | |
+ * +------------------+ /
+ * low
+ */
+
+static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
+{
+ if (len == 1)
+ *ptr = bytes;
+ else if (len == 2)
+ *(u16 *)ptr = bytes;
+ else {
+ *(u32 *)ptr = bytes;
+ barrier();
+ }
+ return ptr + len;
+}
+
+#define EMIT(bytes, len) \
+ do { prog = emit_code(prog, bytes, len); cnt += len; } while (0)
+
+#define EMIT1(b1) EMIT(b1, 1)
+#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
+#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
+#define EMIT4(b1, b2, b3, b4) \
+ EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
+#define EMIT1_off32(b1, off) \
+ do { EMIT1(b1); EMIT(off, 4); } while (0)
+#define EMIT2_off32(b1, b2, off) \
+ do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
+#define EMIT3_off32(b1, b2, b3, off) \
+ do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+#define EMIT4_off32(b1, b2, b3, b4, off) \
+ do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+
+#define jmp_label(label, jmp_insn_len) (label - cnt - jmp_insn_len)
+
+static bool is_imm8(int value)
+{
+ return value <= 127 && value >= -128;
+}
+
+static bool is_simm32(s64 value)
+{
+ return value == (s64) (s32) value;
+}
+
+#define STACK_OFFSET(k) (k)
+#define TCALL_CNT (MAX_BPF_JIT_REG + 0) /* Tail Call Count */
+
+#define IA32_EAX (0x0)
+#define IA32_EBX (0x3)
+#define IA32_ECX (0x1)
+#define IA32_EDX (0x2)
+#define IA32_ESI (0x6)
+#define IA32_EDI (0x7)
+#define IA32_EBP (0x5)
+#define IA32_ESP (0x4)
+
+/*
+ * List of x86 cond jumps opcodes (. + s8)
+ * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
+ */
+#define IA32_JB 0x72
+#define IA32_JAE 0x73
+#define IA32_JE 0x74
+#define IA32_JNE 0x75
+#define IA32_JBE 0x76
+#define IA32_JA 0x77
+#define IA32_JL 0x7C
+#define IA32_JGE 0x7D
+#define IA32_JLE 0x7E
+#define IA32_JG 0x7F
+
+/*
+ * Map eBPF registers to IA32 32bit registers or stack scratch space.
+ *
+ * 1. All the registers, R0-R10, are mapped to scratch space on stack.
+ * 2. We need two 64 bit temp registers to do complex operations on eBPF
+ * registers.
+ * 3. For performance reason, the BPF_REG_AX for blinding constant, is
+ * mapped to real hardware register pair, IA32_ESI and IA32_EDI.
+ *
+ * As the eBPF registers are all 64 bit registers and IA32 has only 32 bit
+ * registers, we have to map each eBPF registers with two IA32 32 bit regs
+ * or scratch memory space and we have to build eBPF 64 bit register from those.
+ *
+ * We use IA32_EAX, IA32_EDX, IA32_ECX, IA32_EBX as temporary registers.
+ */
+static const u8 bpf2ia32[][2] = {
+ /* Return value from in-kernel function, and exit value from eBPF */
+ [BPF_REG_0] = {STACK_OFFSET(0), STACK_OFFSET(4)},
+
+ /* The arguments from eBPF program to in-kernel function */
+ /* Stored on stack scratch space */
+ [BPF_REG_1] = {STACK_OFFSET(8), STACK_OFFSET(12)},
+ [BPF_REG_2] = {STACK_OFFSET(16), STACK_OFFSET(20)},
+ [BPF_REG_3] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+ [BPF_REG_4] = {STACK_OFFSET(32), STACK_OFFSET(36)},
+ [BPF_REG_5] = {STACK_OFFSET(40), STACK_OFFSET(44)},
+
+ /* Callee saved registers that in-kernel function will preserve */
+ /* Stored on stack scratch space */
+ [BPF_REG_6] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+ [BPF_REG_7] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+ [BPF_REG_8] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+ [BPF_REG_9] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+
+ /* Read only Frame Pointer to access Stack */
+ [BPF_REG_FP] = {STACK_OFFSET(80), STACK_OFFSET(84)},
+
+ /* Temporary register for blinding constants. */
+ [BPF_REG_AX] = {IA32_ESI, IA32_EDI},
+
+ /* Tail call count. Stored on stack scratch space. */
+ [TCALL_CNT] = {STACK_OFFSET(88), STACK_OFFSET(92)},
+};
+
+#define dst_lo dst[0]
+#define dst_hi dst[1]
+#define src_lo src[0]
+#define src_hi src[1]
+
+#define STACK_ALIGNMENT 8
+/*
+ * Stack space for BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4,
+ * BPF_REG_5, BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+ * BPF_REG_FP, BPF_REG_AX and Tail call counts.
+ */
+#define SCRATCH_SIZE 96
+
+/* Total stack size used in JITed code */
+#define _STACK_SIZE (stack_depth + SCRATCH_SIZE)
+
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
+
+/* Get the offset of eBPF REGISTERs stored on scratch space. */
+#define STACK_VAR(off) (off)
+
+/* Encode 'dst_reg' register into IA32 opcode 'byte' */
+static u8 add_1reg(u8 byte, u32 dst_reg)
+{
+ return byte + dst_reg;
+}
+
+/* Encode 'dst_reg' and 'src_reg' registers into IA32 opcode 'byte' */
+static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
+{
+ return byte + dst_reg + (src_reg << 3);
+}
+
+static void jit_fill_hole(void *area, unsigned int size)
+{
+ /* Fill whole space with int3 instructions */
+ memset(area, 0xcc, size);
+}
+
+static inline void emit_ia32_mov_i(const u8 dst, const u32 val, bool dstk,
+ u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (dstk) {
+ if (val == 0) {
+ /* xor eax,eax */
+ EMIT2(0x33, add_2reg(0xC0, IA32_EAX, IA32_EAX));
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst));
+ } else {
+ EMIT3_off32(0xC7, add_1reg(0x40, IA32_EBP),
+ STACK_VAR(dst), val);
+ }
+ } else {
+ if (val == 0)
+ EMIT2(0x33, add_2reg(0xC0, dst, dst));
+ else
+ EMIT2_off32(0xC7, add_1reg(0xC0, dst),
+ val);
+ }
+ *pprog = prog;
+}
+
+/* dst = imm (4 bytes)*/
+static inline void emit_ia32_mov_r(const u8 dst, const u8 src, bool dstk,
+ bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 sreg = sstk ? IA32_EAX : src;
+
+ if (sstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src));
+ if (dstk)
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, sreg), STACK_VAR(dst));
+ else
+ /* mov dst,sreg */
+ EMIT2(0x89, add_2reg(0xC0, dst, sreg));
+
+ *pprog = prog;
+}
+
+/* dst = src */
+static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[],
+ const u8 src[], bool dstk,
+ bool sstk, u8 **pprog)
+{
+ emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog);
+ if (is64)
+ /* complete 8 byte move */
+ emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog);
+ else
+ /* zero out high 4 bytes */
+ emit_ia32_mov_i(dst_hi, 0, dstk, pprog);
+}
+
+/* Sign extended move */
+static inline void emit_ia32_mov_i64(const bool is64, const u8 dst[],
+ const u32 val, bool dstk, u8 **pprog)
+{
+ u32 hi = 0;
+
+ if (is64 && (val & (1<<31)))
+ hi = (u32)~0;
+ emit_ia32_mov_i(dst_lo, val, dstk, pprog);
+ emit_ia32_mov_i(dst_hi, hi, dstk, pprog);
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst * src
+ */
+static inline void emit_ia32_mul_r(const u8 dst, const u8 src, bool dstk,
+ bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 sreg = sstk ? IA32_ECX : src;
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src));
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+ else
+ /* mov eax,dst */
+ EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX));
+
+
+ EMIT2(0xF7, add_1reg(0xE0, sreg));
+
+ if (dstk)
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst));
+ else
+ /* mov dst,eax */
+ EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX));
+
+ *pprog = prog;
+}
+
+static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk && val != 64) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+ switch (val) {
+ case 16:
+ /*
+ * Emit 'movzwl eax,ax' to zero extend 16-bit
+ * into 64 bit
+ */
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ break;
+ case 32:
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ break;
+ case 64:
+ /* nop */
+ break;
+ }
+
+ if (dstk && val != 64) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+ switch (val) {
+ case 16:
+ /* Emit 'ror %ax, 8' to swap lower 2 bytes */
+ EMIT1(0x66);
+ EMIT3(0xC1, add_1reg(0xC8, dreg_lo), 8);
+
+ EMIT2(0x0F, 0xB7);
+ EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
+
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ break;
+ case 32:
+ /* Emit 'bswap eax' to swap lower 4 bytes */
+ EMIT1(0x0F);
+ EMIT1(add_1reg(0xC8, dreg_lo));
+
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ break;
+ case 64:
+ /* Emit 'bswap eax' to swap lower 4 bytes */
+ EMIT1(0x0F);
+ EMIT1(add_1reg(0xC8, dreg_lo));
+
+ /* Emit 'bswap edx' to swap lower 4 bytes */
+ EMIT1(0x0F);
+ EMIT1(add_1reg(0xC8, dreg_hi));
+
+ /* mov ecx,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, IA32_ECX, dreg_hi));
+ /* mov dreg_hi,dreg_lo */
+ EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+ /* mov dreg_lo,ecx */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX));
+
+ break;
+ }
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (div|mod) src
+ */
+static inline void emit_ia32_div_mod_r(const u8 op, const u8 dst, const u8 src,
+ bool dstk, bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src));
+ else if (src != IA32_ECX)
+ /* mov ecx,src */
+ EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX));
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst));
+ else
+ /* mov eax,dst */
+ EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX));
+
+ /* xor edx,edx */
+ EMIT2(0x31, add_2reg(0xC0, IA32_EDX, IA32_EDX));
+ /* div ecx */
+ EMIT2(0xF7, add_1reg(0xF0, IA32_ECX));
+
+ if (op == BPF_MOD) {
+ if (dstk)
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst));
+ else
+ EMIT2(0x89, add_2reg(0xC0, dst, IA32_EDX));
+ } else {
+ if (dstk)
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst));
+ else
+ EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX));
+ }
+ *pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (shift) src
+ */
+static inline void emit_ia32_shift_r(const u8 op, const u8 dst, const u8 src,
+ bool dstk, bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg = dstk ? IA32_EAX : dst;
+ u8 b2;
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src));
+ else if (src != IA32_ECX)
+ /* mov ecx,src */
+ EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX));
+
+ switch (op) {
+ case BPF_LSH:
+ b2 = 0xE0; break;
+ case BPF_RSH:
+ b2 = 0xE8; break;
+ case BPF_ARSH:
+ b2 = 0xF8; break;
+ default:
+ return;
+ }
+ EMIT2(0xD3, add_1reg(b2, dreg));
+
+ if (dstk)
+ /* mov dword ptr [ebp+off],dreg */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg), STACK_VAR(dst));
+ *pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (op) src
+ */
+static inline void emit_ia32_alu_r(const bool is64, const bool hi, const u8 op,
+ const u8 dst, const u8 src, bool dstk,
+ bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 sreg = sstk ? IA32_EAX : src;
+ u8 dreg = dstk ? IA32_EDX : dst;
+
+ if (sstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src));
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst));
+
+ switch (BPF_OP(op)) {
+ /* dst = dst + src */
+ case BPF_ADD:
+ if (hi && is64)
+ EMIT2(0x11, add_2reg(0xC0, dreg, sreg));
+ else
+ EMIT2(0x01, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst - src */
+ case BPF_SUB:
+ if (hi && is64)
+ EMIT2(0x19, add_2reg(0xC0, dreg, sreg));
+ else
+ EMIT2(0x29, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst | src */
+ case BPF_OR:
+ EMIT2(0x09, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst & src */
+ case BPF_AND:
+ EMIT2(0x21, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst ^ src */
+ case BPF_XOR:
+ EMIT2(0x31, add_2reg(0xC0, dreg, sreg));
+ break;
+ }
+
+ if (dstk)
+ /* mov dword ptr [ebp+off],dreg */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg),
+ STACK_VAR(dst));
+ *pprog = prog;
+}
+
+/* ALU operation (64 bit) */
+static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
+ const u8 dst[], const u8 src[],
+ bool dstk, bool sstk,
+ u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ emit_ia32_alu_r(is64, false, op, dst_lo, src_lo, dstk, sstk, &prog);
+ if (is64)
+ emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk,
+ &prog);
+ else
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ *pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (op) val
+ */
+static inline void emit_ia32_alu_i(const bool is64, const bool hi, const u8 op,
+ const u8 dst, const s32 val, bool dstk,
+ u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg = dstk ? IA32_EAX : dst;
+ u8 sreg = IA32_EDX;
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+
+ if (!is_imm8(val))
+ /* mov edx,imm32*/
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EDX), val);
+
+ switch (op) {
+ /* dst = dst + val */
+ case BPF_ADD:
+ if (hi && is64) {
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xD0, dreg), val);
+ else
+ EMIT2(0x11, add_2reg(0xC0, dreg, sreg));
+ } else {
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xC0, dreg), val);
+ else
+ EMIT2(0x01, add_2reg(0xC0, dreg, sreg));
+ }
+ break;
+ /* dst = dst - val */
+ case BPF_SUB:
+ if (hi && is64) {
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xD8, dreg), val);
+ else
+ EMIT2(0x19, add_2reg(0xC0, dreg, sreg));
+ } else {
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xE8, dreg), val);
+ else
+ EMIT2(0x29, add_2reg(0xC0, dreg, sreg));
+ }
+ break;
+ /* dst = dst | val */
+ case BPF_OR:
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xC8, dreg), val);
+ else
+ EMIT2(0x09, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst & val */
+ case BPF_AND:
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xE0, dreg), val);
+ else
+ EMIT2(0x21, add_2reg(0xC0, dreg, sreg));
+ break;
+ /* dst = dst ^ val */
+ case BPF_XOR:
+ if (is_imm8(val))
+ EMIT3(0x83, add_1reg(0xF0, dreg), val);
+ else
+ EMIT2(0x31, add_2reg(0xC0, dreg, sreg));
+ break;
+ case BPF_NEG:
+ EMIT2(0xF7, add_1reg(0xD8, dreg));
+ break;
+ }
+
+ if (dstk)
+ /* mov dword ptr [ebp+off],dreg */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg),
+ STACK_VAR(dst));
+ *pprog = prog;
+}
+
+/* ALU operation (64 bit) */
+static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
+ const u8 dst[], const u32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ u32 hi = 0;
+
+ if (is64 && (val & (1<<31)))
+ hi = (u32)~0;
+
+ emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog);
+ if (is64)
+ emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog);
+ else
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+
+ *pprog = prog;
+}
+
+/* dst = ~dst (64 bit) */
+static inline void emit_ia32_neg64(const u8 dst[], bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ /* xor ecx,ecx */
+ EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+ /* sub dreg_lo,ecx */
+ EMIT2(0x2B, add_2reg(0xC0, dreg_lo, IA32_ECX));
+ /* mov dreg_lo,ecx */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX));
+
+ /* xor ecx,ecx */
+ EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+ /* sbb dreg_hi,ecx */
+ EMIT2(0x19, add_2reg(0xC0, dreg_hi, IA32_ECX));
+ /* mov dreg_hi,ecx */
+ EMIT2(0x89, add_2reg(0xC0, dreg_hi, IA32_ECX));
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+/* dst = dst << src */
+static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
+ bool dstk, bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ static int jmp_label1 = -1;
+ static int jmp_label2 = -1;
+ static int jmp_label3 = -1;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src_lo));
+ else
+ /* mov ecx,src_lo */
+ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* Jumps when >= 32 */
+ if (is_imm8(jmp_label(jmp_label1, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+ /* < 32 */
+ /* shl dreg_hi,cl */
+ EMIT2(0xD3, add_1reg(0xE0, dreg_hi));
+ /* mov ebx,dreg_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ /* shl dreg_lo,cl */
+ EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
+
+ /* IA32_ECX = -IA32_ECX + 32 */
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shr ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
+ /* or dreg_hi,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 32 */
+ if (jmp_label1 == -1)
+ jmp_label1 = cnt;
+
+ /* cmp ecx,64 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+ /* Jumps when >= 64 */
+ if (is_imm8(jmp_label(jmp_label2, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+ /* >= 32 && < 64 */
+ /* sub ecx,32 */
+ EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+ /* shl dreg_lo,cl */
+ EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
+ /* mov dreg_hi,dreg_lo */
+ EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 64 */
+ if (jmp_label2 == -1)
+ jmp_label2 = cnt;
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+ if (jmp_label3 == -1)
+ jmp_label3 = cnt;
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ /* out: */
+ *pprog = prog;
+}
+
+/* dst = dst >> src (signed)*/
+static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
+ bool dstk, bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ static int jmp_label1 = -1;
+ static int jmp_label2 = -1;
+ static int jmp_label3 = -1;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src_lo));
+ else
+ /* mov ecx,src_lo */
+ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* Jumps when >= 32 */
+ if (is_imm8(jmp_label(jmp_label1, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+ /* < 32 */
+ /* lshr dreg_lo,cl */
+ EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
+ /* mov ebx,dreg_hi */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* ashr dreg_hi,cl */
+ EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
+
+ /* IA32_ECX = -IA32_ECX + 32 */
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shl ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+ /* or dreg_lo,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 32 */
+ if (jmp_label1 == -1)
+ jmp_label1 = cnt;
+
+ /* cmp ecx,64 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+ /* Jumps when >= 64 */
+ if (is_imm8(jmp_label(jmp_label2, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+ /* >= 32 && < 64 */
+ /* sub ecx,32 */
+ EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+ /* ashr dreg_hi,cl */
+ EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 64 */
+ if (jmp_label2 == -1)
+ jmp_label2 = cnt;
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+ if (jmp_label3 == -1)
+ jmp_label3 = cnt;
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ /* out: */
+ *pprog = prog;
+}
+
+/* dst = dst >> src */
+static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ static int jmp_label1 = -1;
+ static int jmp_label2 = -1;
+ static int jmp_label3 = -1;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ if (sstk)
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src_lo));
+ else
+ /* mov ecx,src_lo */
+ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+ /* cmp ecx,32 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+ /* Jumps when >= 32 */
+ if (is_imm8(jmp_label(jmp_label1, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+ /* < 32 */
+ /* lshr dreg_lo,cl */
+ EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
+ /* mov ebx,dreg_hi */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* shr dreg_hi,cl */
+ EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
+
+ /* IA32_ECX = -IA32_ECX + 32 */
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shl ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+ /* or dreg_lo,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 32 */
+ if (jmp_label1 == -1)
+ jmp_label1 = cnt;
+ /* cmp ecx,64 */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+ /* Jumps when >= 64 */
+ if (is_imm8(jmp_label(jmp_label2, 2)))
+ EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+ else
+ EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+ /* >= 32 && < 64 */
+ /* sub ecx,32 */
+ EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+ /* shr dreg_hi,cl */
+ EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+ /* goto out; */
+ if (is_imm8(jmp_label(jmp_label3, 2)))
+ EMIT2(0xEB, jmp_label(jmp_label3, 2));
+ else
+ EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+ /* >= 64 */
+ if (jmp_label2 == -1)
+ jmp_label2 = cnt;
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+ if (jmp_label3 == -1)
+ jmp_label3 = cnt;
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ /* out: */
+ *pprog = prog;
+}
+
+/* dst = dst << val */
+static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+ /* Do LSH operation */
+ if (val < 32) {
+ /* shl dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val);
+ /* mov ebx,dreg_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ /* shl dreg_lo,imm8 */
+ EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val);
+
+ /* IA32_ECX = 32 - val */
+ /* mov ecx,val */
+ EMIT2(0xB1, val);
+ /* movzx ecx,ecx */
+ EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shr ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
+ /* or dreg_hi,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ } else if (val >= 32 && val < 64) {
+ u32 value = val - 32;
+
+ /* shl dreg_lo,imm8 */
+ EMIT3(0xC1, add_1reg(0xE0, dreg_lo), value);
+ /* mov dreg_hi,dreg_lo */
+ EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+ } else {
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ }
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+/* dst = dst >> val */
+static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ /* Do RSH operation */
+ if (val < 32) {
+ /* shr dreg_lo,imm8 */
+ EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
+ /* mov ebx,dreg_hi */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* shr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val);
+
+ /* IA32_ECX = 32 - val */
+ /* mov ecx,val */
+ EMIT2(0xB1, val);
+ /* movzx ecx,ecx */
+ EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shl ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+ /* or dreg_lo,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ } else if (val >= 32 && val < 64) {
+ u32 value = val - 32;
+
+ /* shr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xE8, dreg_hi), value);
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ } else {
+ /* xor dreg_lo,dreg_lo */
+ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+ /* xor dreg_hi,dreg_hi */
+ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+ }
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+/* dst = dst >> val (signed) */
+static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+ /* Do RSH operation */
+ if (val < 32) {
+ /* shr dreg_lo,imm8 */
+ EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
+ /* mov ebx,dreg_hi */
+ EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val);
+
+ /* IA32_ECX = 32 - val */
+ /* mov ecx,val */
+ EMIT2(0xB1, val);
+ /* movzx ecx,ecx */
+ EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+ /* neg ecx */
+ EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+ /* add ecx,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+ /* shl ebx,cl */
+ EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+ /* or dreg_lo,ebx */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+ } else if (val >= 32 && val < 64) {
+ u32 value = val - 32;
+
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), value);
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+ } else {
+ /* ashr dreg_hi,imm8 */
+ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+ /* mov dreg_lo,dreg_hi */
+ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+ }
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],dreg_lo */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],dreg_hi */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+ STACK_VAR(dst_hi));
+ }
+ *pprog = prog;
+}
+
+static inline void emit_ia32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
+ bool sstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_hi));
+ else
+ /* mov eax,dst_hi */
+ EMIT2(0x8B, add_2reg(0xC0, dst_hi, IA32_EAX));
+
+ if (sstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo));
+ else
+ /* mul src_lo */
+ EMIT2(0xF7, add_1reg(0xE0, src_lo));
+
+ /* mov ecx,eax */
+ EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ else
+ /* mov eax,dst_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+ if (sstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_hi));
+ else
+ /* mul src_hi */
+ EMIT2(0xF7, add_1reg(0xE0, src_hi));
+
+ /* add eax,eax */
+ EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ else
+ /* mov eax,dst_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+ if (sstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo));
+ else
+ /* mul src_lo */
+ EMIT2(0xF7, add_1reg(0xE0, src_lo));
+
+ /* add ecx,edx */
+ EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX));
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],ecx */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(dst_hi));
+ } else {
+ /* mov dst_lo,eax */
+ EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX));
+ /* mov dst_hi,ecx */
+ EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX));
+ }
+
+ *pprog = prog;
+}
+
+static inline void emit_ia32_mul_i64(const u8 dst[], const u32 val,
+ bool dstk, u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ u32 hi;
+
+ hi = val & (1<<31) ? (u32)~0 : 0;
+ /* movl eax,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val);
+ if (dstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_hi));
+ else
+ /* mul dst_hi */
+ EMIT2(0xF7, add_1reg(0xE0, dst_hi));
+
+ /* mov ecx,eax */
+ EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+ /* movl eax,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), hi);
+ if (dstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo));
+ else
+ /* mul dst_lo */
+ EMIT2(0xF7, add_1reg(0xE0, dst_lo));
+ /* add ecx,eax */
+ EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+ /* movl eax,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val);
+ if (dstk)
+ /* mul dword ptr [ebp+off] */
+ EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo));
+ else
+ /* mul dst_lo */
+ EMIT2(0xF7, add_1reg(0xE0, dst_lo));
+
+ /* add ecx,edx */
+ EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX));
+
+ if (dstk) {
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ /* mov dword ptr [ebp+off],ecx */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(dst_hi));
+ } else {
+ /* mov dword ptr [ebp+off],eax */
+ EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX));
+ /* mov dword ptr [ebp+off],ecx */
+ EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX));
+ }
+
+ *pprog = prog;
+}
+
+static int bpf_size_to_x86_bytes(int bpf_size)
+{
+ if (bpf_size == BPF_W)
+ return 4;
+ else if (bpf_size == BPF_H)
+ return 2;
+ else if (bpf_size == BPF_B)
+ return 1;
+ else if (bpf_size == BPF_DW)
+ return 4; /* imm32 */
+ else
+ return 0;
+}
+
+struct jit_context {
+ int cleanup_addr; /* Epilogue code offset */
+};
+
+/* Maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE 128
+#define BPF_INSN_SAFETY 64
+
+#define PROLOGUE_SIZE 35
+
+/*
+ * Emit prologue code for BPF program and check it's size.
+ * bpf_tail_call helper will skip it while jumping into another program.
+ */
+static void emit_prologue(u8 **pprog, u32 stack_depth)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ const u8 *r1 = bpf2ia32[BPF_REG_1];
+ const u8 fplo = bpf2ia32[BPF_REG_FP][0];
+ const u8 fphi = bpf2ia32[BPF_REG_FP][1];
+ const u8 *tcc = bpf2ia32[TCALL_CNT];
+
+ /* push ebp */
+ EMIT1(0x55);
+ /* mov ebp,esp */
+ EMIT2(0x89, 0xE5);
+ /* push edi */
+ EMIT1(0x57);
+ /* push esi */
+ EMIT1(0x56);
+ /* push ebx */
+ EMIT1(0x53);
+
+ /* sub esp,STACK_SIZE */
+ EMIT2_off32(0x81, 0xEC, STACK_SIZE);
+ /* sub ebp,SCRATCH_SIZE+4+12*/
+ EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+ /* xor ebx,ebx */
+ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
+
+ /* Set up BPF prog stack base register */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBP), STACK_VAR(fplo));
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(fphi));
+
+ /* Move BPF_CTX (EAX) to BPF_REG_R1 */
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0]));
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(r1[1]));
+
+ /* Initialize Tail Count */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[0]));
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+ BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+ *pprog = prog;
+}
+
+/* Emit epilogue code for BPF program */
+static void emit_epilogue(u8 **pprog, u32 stack_depth)
+{
+ u8 *prog = *pprog;
+ const u8 *r0 = bpf2ia32[BPF_REG_0];
+ int cnt = 0;
+
+ /* mov eax,dword ptr [ebp+off]*/
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r0[0]));
+ /* mov edx,dword ptr [ebp+off]*/
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
+
+ /* add ebp,SCRATCH_SIZE+4+12*/
+ EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+
+ /* mov ebx,dword ptr [ebp-12]*/
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
+ /* mov esi,dword ptr [ebp-8]*/
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ESI), -8);
+ /* mov edi,dword ptr [ebp-4]*/
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDI), -4);
+
+ EMIT1(0xC9); /* leave */
+ EMIT1(0xC3); /* ret */
+ *pprog = prog;
+}
+
+/*
+ * Generate the following code:
+ * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
+ * if (index >= array->map.max_entries)
+ * goto out;
+ * if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ * prog = array->ptrs[index];
+ * if (prog == NULL)
+ * goto out;
+ * goto *(prog->bpf_func + prologue_size);
+ * out:
+ */
+static void emit_bpf_tail_call(u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+ const u8 *r1 = bpf2ia32[BPF_REG_1];
+ const u8 *r2 = bpf2ia32[BPF_REG_2];
+ const u8 *r3 = bpf2ia32[BPF_REG_3];
+ const u8 *tcc = bpf2ia32[TCALL_CNT];
+ u32 lo, hi;
+ static int jmp_label1 = -1;
+
+ /*
+ * if (index >= array->map.max_entries)
+ * goto out;
+ */
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r2[0]));
+ /* mov edx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r3[0]));
+
+ /* cmp dword ptr [eax+off],edx */
+ EMIT3(0x39, add_2reg(0x40, IA32_EAX, IA32_EDX),
+ offsetof(struct bpf_array, map.max_entries));
+ /* jbe out */
+ EMIT2(IA32_JBE, jmp_label(jmp_label1, 2));
+
+ /*
+ * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ */
+ lo = (u32)MAX_TAIL_CALL_CNT;
+ hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0]));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+ /* cmp edx,hi */
+ EMIT3(0x83, add_1reg(0xF8, IA32_EBX), hi);
+ EMIT2(IA32_JNE, 3);
+ /* cmp ecx,lo */
+ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo);
+
+ /* ja out */
+ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+
+ /* add eax,0x1 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 0x01);
+ /* adc ebx,0x0 */
+ EMIT3(0x83, add_1reg(0xD0, IA32_EBX), 0x00);
+
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0]));
+ /* mov dword ptr [ebp+off],edx */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+ /* prog = array->ptrs[index]; */
+ /* mov edx, [eax + edx * 4 + offsetof(...)] */
+ EMIT3_off32(0x8B, 0x94, 0x90, offsetof(struct bpf_array, ptrs));
+
+ /*
+ * if (prog == NULL)
+ * goto out;
+ */
+ /* test edx,edx */
+ EMIT2(0x85, add_2reg(0xC0, IA32_EDX, IA32_EDX));
+ /* je out */
+ EMIT2(IA32_JE, jmp_label(jmp_label1, 2));
+
+ /* goto *(prog->bpf_func + prologue_size); */
+ /* mov edx, dword ptr [edx + 32] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EDX, IA32_EDX),
+ offsetof(struct bpf_prog, bpf_func));
+ /* add edx,prologue_size */
+ EMIT3(0x83, add_1reg(0xC0, IA32_EDX), PROLOGUE_SIZE);
+
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0]));
+
+ /*
+ * Now we're ready to jump into next BPF program:
+ * eax == ctx (1st arg)
+ * edx == prog->bpf_func + prologue_size
+ */
+ RETPOLINE_EDX_BPF_JIT();
+
+ if (jmp_label1 == -1)
+ jmp_label1 = cnt;
+
+ /* out: */
+ *pprog = prog;
+}
+
+/* Push the scratch stack register on top of the stack. */
+static inline void emit_push_r64(const u8 src[], u8 **pprog)
+{
+ u8 *prog = *pprog;
+ int cnt = 0;
+
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_hi));
+ /* push ecx */
+ EMIT1(0x51);
+
+ /* mov ecx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_lo));
+ /* push ecx */
+ EMIT1(0x51);
+
+ *pprog = prog;
+}
+
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+ int oldproglen, struct jit_context *ctx)
+{
+ struct bpf_insn *insn = bpf_prog->insnsi;
+ int insn_cnt = bpf_prog->len;
+ bool seen_exit = false;
+ u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+ int i, cnt = 0;
+ int proglen = 0;
+ u8 *prog = temp;
+
+ emit_prologue(&prog, bpf_prog->aux->stack_depth);
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ const s32 imm32 = insn->imm;
+ const bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+ const bool dstk = insn->dst_reg == BPF_REG_AX ? false : true;
+ const bool sstk = insn->src_reg == BPF_REG_AX ? false : true;
+ const u8 code = insn->code;
+ const u8 *dst = bpf2ia32[insn->dst_reg];
+ const u8 *src = bpf2ia32[insn->src_reg];
+ const u8 *r0 = bpf2ia32[BPF_REG_0];
+ s64 jmp_offset;
+ u8 jmp_cond;
+ int ilen;
+ u8 *func;
+
+ switch (code) {
+ /* ALU operations */
+ /* dst = src */
+ case BPF_ALU | BPF_MOV | BPF_K:
+ case BPF_ALU | BPF_MOV | BPF_X:
+ case BPF_ALU64 | BPF_MOV | BPF_K:
+ case BPF_ALU64 | BPF_MOV | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_mov_r64(is64, dst, src, dstk,
+ sstk, &prog);
+ break;
+ case BPF_K:
+ /* Sign-extend immediate value to dst reg */
+ emit_ia32_mov_i64(is64, dst, imm32,
+ dstk, &prog);
+ break;
+ }
+ break;
+ /* dst = dst + src/imm */
+ /* dst = dst - src/imm */
+ /* dst = dst | src/imm */
+ /* dst = dst & src/imm */
+ /* dst = dst ^ src/imm */
+ /* dst = dst * src/imm */
+ /* dst = dst << src */
+ /* dst = dst >> src */
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_ADD | BPF_X:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_X:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_X:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_X:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_X:
+ case BPF_ALU64 | BPF_ADD | BPF_K:
+ case BPF_ALU64 | BPF_ADD | BPF_X:
+ case BPF_ALU64 | BPF_SUB | BPF_K:
+ case BPF_ALU64 | BPF_SUB | BPF_X:
+ case BPF_ALU64 | BPF_OR | BPF_K:
+ case BPF_ALU64 | BPF_OR | BPF_X:
+ case BPF_ALU64 | BPF_AND | BPF_K:
+ case BPF_ALU64 | BPF_AND | BPF_X:
+ case BPF_ALU64 | BPF_XOR | BPF_K:
+ case BPF_ALU64 | BPF_XOR | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_alu_r64(is64, BPF_OP(code), dst,
+ src, dstk, sstk, &prog);
+ break;
+ case BPF_K:
+ emit_ia32_alu_i64(is64, BPF_OP(code), dst,
+ imm32, dstk, &prog);
+ break;
+ }
+ break;
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_mul_r(dst_lo, src_lo, dstk,
+ sstk, &prog);
+ break;
+ case BPF_K:
+ /* mov ecx,imm32*/
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+ imm32);
+ emit_ia32_mul_r(dst_lo, IA32_ECX, dstk,
+ false, &prog);
+ break;
+ }
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ break;
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_ARSH | BPF_K:
+ case BPF_ALU | BPF_ARSH | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_shift_r(BPF_OP(code), dst_lo, src_lo,
+ dstk, sstk, &prog);
+ break;
+ case BPF_K:
+ /* mov ecx,imm32*/
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+ imm32);
+ emit_ia32_shift_r(BPF_OP(code), dst_lo,
+ IA32_ECX, dstk, false,
+ &prog);
+ break;
+ }
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ break;
+ /* dst = dst / src(imm) */
+ /* dst = dst % src(imm) */
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_X:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_div_mod_r(BPF_OP(code), dst_lo,
+ src_lo, dstk, sstk, &prog);
+ break;
+ case BPF_K:
+ /* mov ecx,imm32*/
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+ imm32);
+ emit_ia32_div_mod_r(BPF_OP(code), dst_lo,
+ IA32_ECX, dstk, false,
+ &prog);
+ break;
+ }
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ break;
+ case BPF_ALU64 | BPF_DIV | BPF_K:
+ case BPF_ALU64 | BPF_DIV | BPF_X:
+ case BPF_ALU64 | BPF_MOD | BPF_K:
+ case BPF_ALU64 | BPF_MOD | BPF_X:
+ goto notyet;
+ /* dst = dst >> imm */
+ /* dst = dst << imm */
+ case BPF_ALU | BPF_RSH | BPF_K:
+ case BPF_ALU | BPF_LSH | BPF_K:
+ if (unlikely(imm32 > 31))
+ return -EINVAL;
+ /* mov ecx,imm32*/
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+ emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk,
+ false, &prog);
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ break;
+ /* dst = dst << imm */
+ case BPF_ALU64 | BPF_LSH | BPF_K:
+ if (unlikely(imm32 > 63))
+ return -EINVAL;
+ emit_ia32_lsh_i64(dst, imm32, dstk, &prog);
+ break;
+ /* dst = dst >> imm */
+ case BPF_ALU64 | BPF_RSH | BPF_K:
+ if (unlikely(imm32 > 63))
+ return -EINVAL;
+ emit_ia32_rsh_i64(dst, imm32, dstk, &prog);
+ break;
+ /* dst = dst << src */
+ case BPF_ALU64 | BPF_LSH | BPF_X:
+ emit_ia32_lsh_r64(dst, src, dstk, sstk, &prog);
+ break;
+ /* dst = dst >> src */
+ case BPF_ALU64 | BPF_RSH | BPF_X:
+ emit_ia32_rsh_r64(dst, src, dstk, sstk, &prog);
+ break;
+ /* dst = dst >> src (signed) */
+ case BPF_ALU64 | BPF_ARSH | BPF_X:
+ emit_ia32_arsh_r64(dst, src, dstk, sstk, &prog);
+ break;
+ /* dst = dst >> imm (signed) */
+ case BPF_ALU64 | BPF_ARSH | BPF_K:
+ if (unlikely(imm32 > 63))
+ return -EINVAL;
+ emit_ia32_arsh_i64(dst, imm32, dstk, &prog);
+ break;
+ /* dst = ~dst */
+ case BPF_ALU | BPF_NEG:
+ emit_ia32_alu_i(is64, false, BPF_OP(code),
+ dst_lo, 0, dstk, &prog);
+ emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+ break;
+ /* dst = ~dst (64 bit) */
+ case BPF_ALU64 | BPF_NEG:
+ emit_ia32_neg64(dst, dstk, &prog);
+ break;
+ /* dst = dst * src/imm */
+ case BPF_ALU64 | BPF_MUL | BPF_X:
+ case BPF_ALU64 | BPF_MUL | BPF_K:
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ emit_ia32_mul_r64(dst, src, dstk, sstk, &prog);
+ break;
+ case BPF_K:
+ emit_ia32_mul_i64(dst, imm32, dstk, &prog);
+ break;
+ }
+ break;
+ /* dst = htole(dst) */
+ case BPF_ALU | BPF_END | BPF_FROM_LE:
+ emit_ia32_to_le_r64(dst, imm32, dstk, &prog);
+ break;
+ /* dst = htobe(dst) */
+ case BPF_ALU | BPF_END | BPF_FROM_BE:
+ emit_ia32_to_be_r64(dst, imm32, dstk, &prog);
+ break;
+ /* dst = imm64 */
+ case BPF_LD | BPF_IMM | BPF_DW: {
+ s32 hi, lo = imm32;
+
+ hi = insn[1].imm;
+ emit_ia32_mov_i(dst_lo, lo, dstk, &prog);
+ emit_ia32_mov_i(dst_hi, hi, dstk, &prog);
+ insn++;
+ i++;
+ break;
+ }
+ /* ST: *(u8*)(dst_reg + off) = imm */
+ case BPF_ST | BPF_MEM | BPF_H:
+ case BPF_ST | BPF_MEM | BPF_B:
+ case BPF_ST | BPF_MEM | BPF_W:
+ case BPF_ST | BPF_MEM | BPF_DW:
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ else
+ /* mov eax,dst_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ EMIT(0xC6, 1); break;
+ case BPF_H:
+ EMIT2(0x66, 0xC7); break;
+ case BPF_W:
+ case BPF_DW:
+ EMIT(0xC7, 1); break;
+ }
+
+ if (is_imm8(insn->off))
+ EMIT2(add_1reg(0x40, IA32_EAX), insn->off);
+ else
+ EMIT1_off32(add_1reg(0x80, IA32_EAX),
+ insn->off);
+ EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(code)));
+
+ if (BPF_SIZE(code) == BPF_DW) {
+ u32 hi;
+
+ hi = imm32 & (1<<31) ? (u32)~0 : 0;
+ EMIT2_off32(0xC7, add_1reg(0x80, IA32_EAX),
+ insn->off + 4);
+ EMIT(hi, 4);
+ }
+ break;
+
+ /* STX: *(u8*)(dst_reg + off) = src_reg */
+ case BPF_STX | BPF_MEM | BPF_B:
+ case BPF_STX | BPF_MEM | BPF_H:
+ case BPF_STX | BPF_MEM | BPF_W:
+ case BPF_STX | BPF_MEM | BPF_DW:
+ if (dstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ else
+ /* mov eax,dst_lo */
+ EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+ if (sstk)
+ /* mov edx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(src_lo));
+ else
+ /* mov edx,src_lo */
+ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EDX));
+
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ EMIT(0x88, 1); break;
+ case BPF_H:
+ EMIT2(0x66, 0x89); break;
+ case BPF_W:
+ case BPF_DW:
+ EMIT(0x89, 1); break;
+ }
+
+ if (is_imm8(insn->off))
+ EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX),
+ insn->off);
+ else
+ EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX),
+ insn->off);
+
+ if (BPF_SIZE(code) == BPF_DW) {
+ if (sstk)
+ /* mov edi,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP,
+ IA32_EDX),
+ STACK_VAR(src_hi));
+ else
+ /* mov edi,src_hi */
+ EMIT2(0x8B, add_2reg(0xC0, src_hi,
+ IA32_EDX));
+ EMIT1(0x89);
+ if (is_imm8(insn->off + 4)) {
+ EMIT2(add_2reg(0x40, IA32_EAX,
+ IA32_EDX),
+ insn->off + 4);
+ } else {
+ EMIT1(add_2reg(0x80, IA32_EAX,
+ IA32_EDX));
+ EMIT(insn->off + 4, 4);
+ }
+ }
+ break;
+
+ /* LDX: dst_reg = *(u8*)(src_reg + off) */
+ case BPF_LDX | BPF_MEM | BPF_B:
+ case BPF_LDX | BPF_MEM | BPF_H:
+ case BPF_LDX | BPF_MEM | BPF_W:
+ case BPF_LDX | BPF_MEM | BPF_DW:
+ if (sstk)
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(src_lo));
+ else
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EAX));
+
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ EMIT2(0x0F, 0xB6); break;
+ case BPF_H:
+ EMIT2(0x0F, 0xB7); break;
+ case BPF_W:
+ case BPF_DW:
+ EMIT(0x8B, 1); break;
+ }
+
+ if (is_imm8(insn->off))
+ EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX),
+ insn->off);
+ else
+ EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX),
+ insn->off);
+
+ if (dstk)
+ /* mov dword ptr [ebp+off],edx */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_lo));
+ else
+ /* mov dst_lo,edx */
+ EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EDX));
+ switch (BPF_SIZE(code)) {
+ case BPF_B:
+ case BPF_H:
+ case BPF_W:
+ if (dstk) {
+ EMIT3(0xC7, add_1reg(0x40, IA32_EBP),
+ STACK_VAR(dst_hi));
+ EMIT(0x0, 4);
+ } else {
+ EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0);
+ }
+ break;
+ case BPF_DW:
+ EMIT2_off32(0x8B,
+ add_2reg(0x80, IA32_EAX, IA32_EDX),
+ insn->off + 4);
+ if (dstk)
+ EMIT3(0x89,
+ add_2reg(0x40, IA32_EBP,
+ IA32_EDX),
+ STACK_VAR(dst_hi));
+ else
+ EMIT2(0x89,
+ add_2reg(0xC0, dst_hi, IA32_EDX));
+ break;
+ default:
+ break;
+ }
+ break;
+ /* call */
+ case BPF_JMP | BPF_CALL:
+ {
+ const u8 *r1 = bpf2ia32[BPF_REG_1];
+ const u8 *r2 = bpf2ia32[BPF_REG_2];
+ const u8 *r3 = bpf2ia32[BPF_REG_3];
+ const u8 *r4 = bpf2ia32[BPF_REG_4];
+ const u8 *r5 = bpf2ia32[BPF_REG_5];
+
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ goto notyet;
+
+ func = (u8 *) __bpf_call_base + imm32;
+ jmp_offset = func - (image + addrs[i]);
+
+ if (!imm32 || !is_simm32(jmp_offset)) {
+ pr_err("unsupported BPF func %d addr %p image %p\n",
+ imm32, func, image);
+ return -EINVAL;
+ }
+
+ /* mov eax,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(r1[0]));
+ /* mov edx,dword ptr [ebp+off] */
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(r1[1]));
+
+ emit_push_r64(r5, &prog);
+ emit_push_r64(r4, &prog);
+ emit_push_r64(r3, &prog);
+ emit_push_r64(r2, &prog);
+
+ EMIT1_off32(0xE8, jmp_offset + 9);
+
+ /* mov dword ptr [ebp+off],eax */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(r0[0]));
+ /* mov dword ptr [ebp+off],edx */
+ EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(r0[1]));
+
+ /* add esp,32 */
+ EMIT3(0x83, add_1reg(0xC0, IA32_ESP), 32);
+ break;
+ }
+ case BPF_JMP | BPF_TAIL_CALL:
+ emit_bpf_tail_call(&prog);
+ break;
+
+ /* cond jump */
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JNE | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JLT | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ case BPF_JMP | BPF_JLE | BPF_X:
+ case BPF_JMP | BPF_JSGT | BPF_X:
+ case BPF_JMP | BPF_JSLE | BPF_X:
+ case BPF_JMP | BPF_JSLT | BPF_X:
+ case BPF_JMP | BPF_JSGE | BPF_X: {
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+ u8 sreg_lo = sstk ? IA32_ECX : src_lo;
+ u8 sreg_hi = sstk ? IA32_EBX : src_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ if (sstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
+ STACK_VAR(src_hi));
+ }
+
+ /* cmp dreg_hi,sreg_hi */
+ EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+ EMIT2(IA32_JNE, 2);
+ /* cmp dreg_lo,sreg_lo */
+ EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+ goto emit_cond_jmp;
+ }
+ case BPF_JMP | BPF_JSET | BPF_X: {
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+ u8 sreg_lo = sstk ? IA32_ECX : src_lo;
+ u8 sreg_hi = sstk ? IA32_EBX : src_hi;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ if (sstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+ STACK_VAR(src_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
+ STACK_VAR(src_hi));
+ }
+ /* and dreg_lo,sreg_lo */
+ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
+ /* and dreg_hi,sreg_hi */
+ EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+ /* or dreg_lo,dreg_hi */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+ goto emit_cond_jmp;
+ }
+ case BPF_JMP | BPF_JSET | BPF_K: {
+ u32 hi;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+ u8 sreg_lo = IA32_ECX;
+ u8 sreg_hi = IA32_EBX;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+ hi = imm32 & (1<<31) ? (u32)~0 : 0;
+
+ /* mov ecx,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+ /* mov ebx,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+
+ /* and dreg_lo,sreg_lo */
+ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
+ /* and dreg_hi,sreg_hi */
+ EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+ /* or dreg_lo,dreg_hi */
+ EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+ goto emit_cond_jmp;
+ }
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JNE | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JLT | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JLE | BPF_K:
+ case BPF_JMP | BPF_JSGT | BPF_K:
+ case BPF_JMP | BPF_JSLE | BPF_K:
+ case BPF_JMP | BPF_JSLT | BPF_K:
+ case BPF_JMP | BPF_JSGE | BPF_K: {
+ u32 hi;
+ u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+ u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+ u8 sreg_lo = IA32_ECX;
+ u8 sreg_hi = IA32_EBX;
+
+ if (dstk) {
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+ STACK_VAR(dst_lo));
+ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+ STACK_VAR(dst_hi));
+ }
+
+ hi = imm32 & (1<<31) ? (u32)~0 : 0;
+ /* mov ecx,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+ /* mov ebx,imm32 */
+ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+
+ /* cmp dreg_hi,sreg_hi */
+ EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+ EMIT2(IA32_JNE, 2);
+ /* cmp dreg_lo,sreg_lo */
+ EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+
+emit_cond_jmp: /* Convert BPF opcode to x86 */
+ switch (BPF_OP(code)) {
+ case BPF_JEQ:
+ jmp_cond = IA32_JE;
+ break;
+ case BPF_JSET:
+ case BPF_JNE:
+ jmp_cond = IA32_JNE;
+ break;
+ case BPF_JGT:
+ /* GT is unsigned '>', JA in x86 */
+ jmp_cond = IA32_JA;
+ break;
+ case BPF_JLT:
+ /* LT is unsigned '<', JB in x86 */
+ jmp_cond = IA32_JB;
+ break;
+ case BPF_JGE:
+ /* GE is unsigned '>=', JAE in x86 */
+ jmp_cond = IA32_JAE;
+ break;
+ case BPF_JLE:
+ /* LE is unsigned '<=', JBE in x86 */
+ jmp_cond = IA32_JBE;
+ break;
+ case BPF_JSGT:
+ /* Signed '>', GT in x86 */
+ jmp_cond = IA32_JG;
+ break;
+ case BPF_JSLT:
+ /* Signed '<', LT in x86 */
+ jmp_cond = IA32_JL;
+ break;
+ case BPF_JSGE:
+ /* Signed '>=', GE in x86 */
+ jmp_cond = IA32_JGE;
+ break;
+ case BPF_JSLE:
+ /* Signed '<=', LE in x86 */
+ jmp_cond = IA32_JLE;
+ break;
+ default: /* to silence GCC warning */
+ return -EFAULT;
+ }
+ jmp_offset = addrs[i + insn->off] - addrs[i];
+ if (is_imm8(jmp_offset)) {
+ EMIT2(jmp_cond, jmp_offset);
+ } else if (is_simm32(jmp_offset)) {
+ EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+ } else {
+ pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+ return -EFAULT;
+ }
+
+ break;
+ }
+ case BPF_JMP | BPF_JA:
+ if (insn->off == -1)
+ /* -1 jmp instructions will always jump
+ * backwards two bytes. Explicitly handling
+ * this case avoids wasting too many passes
+ * when there are long sequences of replaced
+ * dead code.
+ */
+ jmp_offset = -2;
+ else
+ jmp_offset = addrs[i + insn->off] - addrs[i];
+
+ if (!jmp_offset)
+ /* Optimize out nop jumps */
+ break;
+emit_jmp:
+ if (is_imm8(jmp_offset)) {
+ EMIT2(0xEB, jmp_offset);
+ } else if (is_simm32(jmp_offset)) {
+ EMIT1_off32(0xE9, jmp_offset);
+ } else {
+ pr_err("jmp gen bug %llx\n", jmp_offset);
+ return -EFAULT;
+ }
+ break;
+ /* STX XADD: lock *(u32 *)(dst + off) += src */
+ case BPF_STX | BPF_XADD | BPF_W:
+ /* STX XADD: lock *(u64 *)(dst + off) += src */
+ case BPF_STX | BPF_XADD | BPF_DW:
+ goto notyet;
+ case BPF_JMP | BPF_EXIT:
+ if (seen_exit) {
+ jmp_offset = ctx->cleanup_addr - addrs[i];
+ goto emit_jmp;
+ }
+ seen_exit = true;
+ /* Update cleanup_addr */
+ ctx->cleanup_addr = proglen;
+ emit_epilogue(&prog, bpf_prog->aux->stack_depth);
+ break;
+notyet:
+ pr_info_once("*** NOT YET: opcode %02x ***\n", code);
+ return -EFAULT;
+ default:
+ /*
+ * This error will be seen if new instruction was added
+ * to interpreter, but not to JIT or if there is junk in
+ * bpf_prog
+ */
+ pr_err("bpf_jit: unknown opcode %02x\n", code);
+ return -EINVAL;
+ }
+
+ ilen = prog - temp;
+ if (ilen > BPF_MAX_INSN_SIZE) {
+ pr_err("bpf_jit: fatal insn size error\n");
+ return -EFAULT;
+ }
+
+ if (image) {
+ if (unlikely(proglen + ilen > oldproglen)) {
+ pr_err("bpf_jit: fatal error\n");
+ return -EFAULT;
+ }
+ memcpy(image + proglen, temp, ilen);
+ }
+ proglen += ilen;
+ addrs[i] = proglen;
+ prog = temp;
+ }
+ return proglen;
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+ struct bpf_binary_header *header = NULL;
+ struct bpf_prog *tmp, *orig_prog = prog;
+ int proglen, oldproglen = 0;
+ struct jit_context ctx = {};
+ bool tmp_blinded = false;
+ u8 *image = NULL;
+ int *addrs;
+ int pass;
+ int i;
+
+ if (!prog->jit_requested)
+ return orig_prog;
+
+ tmp = bpf_jit_blind_constants(prog);
+ /*
+ * If blinding was requested and we failed during blinding,
+ * we must fall back to the interpreter.
+ */
+ if (IS_ERR(tmp))
+ return orig_prog;
+ if (tmp != prog) {
+ tmp_blinded = true;
+ prog = tmp;
+ }
+
+ addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
+ if (!addrs) {
+ prog = orig_prog;
+ goto out;
+ }
+
+ /*
+ * Before first pass, make a rough estimation of addrs[]
+ * each BPF instruction is translated to less than 64 bytes
+ */
+ for (proglen = 0, i = 0; i < prog->len; i++) {
+ proglen += 64;
+ addrs[i] = proglen;
+ }
+ ctx.cleanup_addr = proglen;
+
+ /*
+ * JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large BPF programs
+ * may converge on the last pass. In such case do one more
+ * pass to emit the final image.
+ */
+ for (pass = 0; pass < 20 || image; pass++) {
+ proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
+ if (proglen <= 0) {
+out_image:
+ image = NULL;
+ if (header)
+ bpf_jit_binary_free(header);
+ prog = orig_prog;
+ goto out_addrs;
+ }
+ if (image) {
+ if (proglen != oldproglen) {
+ pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
+ proglen, oldproglen);
+ goto out_image;
+ }
+ break;
+ }
+ if (proglen == oldproglen) {
+ header = bpf_jit_binary_alloc(proglen, &image,
+ 1, jit_fill_hole);
+ if (!header) {
+ prog = orig_prog;
+ goto out_addrs;
+ }
+ }
+ oldproglen = proglen;
+ cond_resched();
+ }
+
+ if (bpf_jit_enable > 1)
+ bpf_jit_dump(prog->len, proglen, pass + 1, image);
+
+ if (image) {
+ bpf_jit_binary_lock_ro(header);
+ prog->bpf_func = (void *)image;
+ prog->jited = 1;
+ prog->jited_len = proglen;
+ } else {
+ prog = orig_prog;
+ }
+
+out_addrs:
+ kfree(addrs);
+out:
+ if (tmp_blinded)
+ bpf_jit_prog_release_other(prog, prog == orig_prog ?
+ tmp : orig_prog);
+ return prog;
+}
set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
} else {
/* No p4d for 4-level paging: point the pgd to the pud page table */
- pgd_t new_pgd = __pgd(__pa(p4d) | pgprot_val(pgtable_prot));
+ pgd_t new_pgd = __pgd(__pa(pud) | pgprot_val(pgtable_prot));
set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
}
{
early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+
+ /*
+ * The virtual address of the shared_info page has changed, so
+ * the vcpu_info pointer for VCPU 0 is now stale.
+ *
+ * The prepare_boot_cpu callback will re-initialize it via
+ * xen_vcpu_setup, but we can't rely on that to be called for
+ * old Xen versions (xen_have_vector_callback == 0).
+ *
+ * It is, in any case, bad to have a stale vcpu_info pointer
+ * so reset it now.
+ */
+ xen_vcpu_info_reset(0);
}
static void __init init_hvm_pv_info(void)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
- unsigned long frames[pages];
- int f;
-
- /*
- * A GDT can be up to 64k in size, which corresponds to 8192
- * 8-byte entries, or 16 4k pages..
- */
+ unsigned long pfn, mfn;
+ int level;
+ pte_t *ptep;
+ void *virt;
- BUG_ON(size > 65536);
+ /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+ BUG_ON(size > PAGE_SIZE);
BUG_ON(va & ~PAGE_MASK);
- for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
- int level;
- pte_t *ptep;
- unsigned long pfn, mfn;
- void *virt;
-
- /*
- * The GDT is per-cpu and is in the percpu data area.
- * That can be virtually mapped, so we need to do a
- * page-walk to get the underlying MFN for the
- * hypercall. The page can also be in the kernel's
- * linear range, so we need to RO that mapping too.
- */
- ptep = lookup_address(va, &level);
- BUG_ON(ptep == NULL);
-
- pfn = pte_pfn(*ptep);
- mfn = pfn_to_mfn(pfn);
- virt = __va(PFN_PHYS(pfn));
+ /*
+ * The GDT is per-cpu and is in the percpu data area.
+ * That can be virtually mapped, so we need to do a
+ * page-walk to get the underlying MFN for the
+ * hypercall. The page can also be in the kernel's
+ * linear range, so we need to RO that mapping too.
+ */
+ ptep = lookup_address(va, &level);
+ BUG_ON(ptep == NULL);
- frames[f] = mfn;
+ pfn = pte_pfn(*ptep);
+ mfn = pfn_to_mfn(pfn);
+ virt = __va(PFN_PHYS(pfn));
- make_lowmem_page_readonly((void *)va);
- make_lowmem_page_readonly(virt);
- }
+ make_lowmem_page_readonly((void *)va);
+ make_lowmem_page_readonly(virt);
- if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+ if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
BUG();
}
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
- unsigned long frames[pages];
- int f;
-
- /*
- * A GDT can be up to 64k in size, which corresponds to 8192
- * 8-byte entries, or 16 4k pages..
- */
+ unsigned long pfn, mfn;
+ pte_t pte;
- BUG_ON(size > 65536);
+ /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+ BUG_ON(size > PAGE_SIZE);
BUG_ON(va & ~PAGE_MASK);
- for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
- pte_t pte;
- unsigned long pfn, mfn;
+ pfn = virt_to_pfn(va);
+ mfn = pfn_to_mfn(pfn);
- pfn = virt_to_pfn(va);
- mfn = pfn_to_mfn(pfn);
+ pte = pfn_pte(pfn, PAGE_KERNEL_RO);
- pte = pfn_pte(pfn, PAGE_KERNEL_RO);
-
- if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
- BUG();
-
- frames[f] = mfn;
- }
+ if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+ BUG();
- if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+ if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
BUG();
}
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-static void xen_flush_tlb_all(void)
+static noinline void xen_flush_tlb_all(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb_all(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
return this_cpu_read(xen_vcpu_info.arch.cr2);
}
-static void xen_flush_tlb(void)
+static noinline void xen_flush_tlb(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
bool new_queue = false;
bool bfqq_already_existing = false, split = false;
- if (!rq->elv.icq)
+ /*
+ * Even if we don't have an icq attached, we should still clear
+ * the scheduler pointers, as they might point to previously
+ * allocated bic/bfqq structs.
+ */
+ if (!rq->elv.icq) {
+ rq->elv.priv[0] = rq->elv.priv[1] = NULL;
return;
+ }
+
bic = icq_to_bic(rq->elv.icq);
spin_lock_irq(&bfqd->lock);
preloaded = !radix_tree_preload(GFP_KERNEL);
- /*
- * Make sure the root blkg exists and count the existing blkgs. As
- * @q is bypassing at this point, blkg_lookup_create() can't be
- * used. Open code insertion.
- */
+ /* Make sure the root blkg exists. */
rcu_read_lock();
spin_lock_irq(q->queue_lock);
blkg = blkg_create(&blkcg_root, q, new_blkg);
+ if (IS_ERR(blkg))
+ goto err_unlock;
+ q->root_blkg = blkg;
+ q->root_rl.blkg = blkg;
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
if (preloaded)
radix_tree_preload_end();
- if (IS_ERR(blkg))
- return PTR_ERR(blkg);
-
- q->root_blkg = blkg;
- q->root_rl.blkg = blkg;
-
ret = blk_throtl_init(q);
if (ret) {
spin_lock_irq(q->queue_lock);
spin_unlock_irq(q->queue_lock);
}
return ret;
+
+err_unlock:
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+ if (preloaded)
+ radix_tree_preload_end();
+ return PTR_ERR(blkg);
}
/**
__clear_bit(pol->plid, q->blkcg_pols);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
- /* grab blkcg lock too while removing @pd from @blkg */
- spin_lock(&blkg->blkcg->lock);
-
if (blkg->pd[pol->plid]) {
if (!blkg->pd[pol->plid]->offline &&
pol->pd_offline_fn) {
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
-
- spin_unlock(&blkg->blkcg->lock);
}
spin_unlock_irq(q->queue_lock);
rq->part = NULL;
seqcount_init(&rq->gstate_seq);
u64_stats_init(&rq->aborted_gstate_sync);
+ /*
+ * See comment of blk_mq_init_request
+ */
+ WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
}
EXPORT_SYMBOL(blk_rq_init);
while (true) {
bool success = false;
- int ret;
rcu_read_lock();
if (percpu_ref_tryget_live(&q->q_usage_counter)) {
*/
smp_rmb();
- ret = wait_event_interruptible(q->mq_freeze_wq,
- (atomic_read(&q->mq_freeze_depth) == 0 &&
- (preempt || !blk_queue_preempt_only(q))) ||
- blk_queue_dying(q));
+ wait_event(q->mq_freeze_wq,
+ (atomic_read(&q->mq_freeze_depth) == 0 &&
+ (preempt || !blk_queue_preempt_only(q))) ||
+ blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
- if (ret)
- return ret;
}
}
{
struct mq_inflight *mi = priv;
- if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
- /*
- * index[0] counts the specific partition that was asked
- * for. index[1] counts the ones that are active on the
- * whole device, so increment that if mi->part is indeed
- * a partition, and not a whole device.
- */
- if (rq->part == mi->part)
- mi->inflight[0]++;
- if (mi->part->partno)
- mi->inflight[1]++;
- }
+ /*
+ * index[0] counts the specific partition that was asked for. index[1]
+ * counts the ones that are active on the whole device, so increment
+ * that if mi->part is indeed a partition, and not a whole device.
+ */
+ if (rq->part == mi->part)
+ mi->inflight[0]++;
+ if (mi->part->partno)
+ mi->inflight[1]++;
}
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
}
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, void *priv,
+ bool reserved)
+{
+ struct mq_inflight *mi = priv;
+
+ if (rq->part == mi->part)
+ mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
+{
+ struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+ inflight[0] = inflight[1] = 0;
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
seqcount_init(&rq->gstate_seq);
u64_stats_init(&rq->aborted_gstate_sync);
+ /*
+ * start gstate with gen 1 instead of 0, otherwise it will be equal
+ * to aborted_gstate, and be identified timed out by
+ * blk_mq_terminate_expired.
+ */
+ WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
+
return 0;
}
static void blk_mq_map_swqueue(struct request_queue *q)
{
- unsigned int i;
+ unsigned int i, hctx_idx;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
/*
* Map software to hardware queues.
+ *
+ * If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
+ hctx_idx = q->mq_map[i];
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[hctx_idx] &&
+ !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+ /*
+ * If tags initialization fail for some hctx,
+ * that hctx won't be brought online. In this
+ * case, remap the current ctx to hctx[0] which
+ * is guaranteed to always have tags allocated
+ */
+ q->mq_map[i] = 0;
+ }
+
ctx = per_cpu_ptr(q->queue_ctx, i);
hctx = blk_mq_map_queue(q, i);
mutex_unlock(&q->sysfs_lock);
queue_for_each_hw_ctx(q, hctx, i) {
- /* every hctx should get mapped by at least one CPU */
- WARN_ON(!hctx->nr_ctx);
+ /*
+ * If no software queues are mapped to this hardware queue,
+ * disable it and free the request entries.
+ */
+ if (!hctx->nr_ctx) {
+ /* Never unmap queue 0. We need it as a
+ * fallback in case of a new remap fails
+ * allocation
+ */
+ if (i && set->tags[i])
+ blk_mq_free_map_and_requests(set, i);
+
+ hctx->tags = NULL;
+ continue;
+ }
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
struct blk_mq_tag_set;
+/**
+ * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
+ */
struct blk_mq_ctx {
struct {
spinlock_t lock;
}
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
+ unsigned int inflight[2]);
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2]);
static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
}
}
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
+{
+ if (q->mq_ops) {
+ blk_mq_in_flight_rw(q, part, inflight);
+ return;
+ }
+
+ inflight[0] = atomic_read(&part->in_flight[0]);
+ inflight[1] = atomic_read(&part->in_flight[1]);
+}
+
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
{
struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
jiffies_to_msecs(part_stat_read(p, time_in_queue)));
}
-ssize_t part_inflight_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ unsigned int inflight[2];
- return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]),
- atomic_read(&p->in_flight[1]));
+ part_in_flight_rw(q, p, inflight);
+ return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
down_read(&crypto_alg_sem);
alg = __crypto_alg_lookup(name, type | test, mask | test);
- if (!alg && test)
- alg = __crypto_alg_lookup(name, type, mask) ?
- ERR_PTR(-ELIBBAD) : NULL;
+ if (!alg && test) {
+ alg = __crypto_alg_lookup(name, type, mask);
+ if (alg && !crypto_is_larval(alg)) {
+ /* Test failed */
+ crypto_mod_put(alg);
+ alg = ERR_PTR(-ELIBBAD);
+ }
+ }
up_read(&crypto_alg_sem);
return alg;
if (!drbg)
return;
kzfree(drbg->Vbuf);
+ drbg->Vbuf = NULL;
drbg->V = NULL;
kzfree(drbg->Cbuf);
+ drbg->Cbuf = NULL;
drbg->C = NULL;
kzfree(drbg->scratchpadbuf);
drbg->scratchpadbuf = NULL;
return opregion;
}
+static bool dmi_is_desktop(void)
+{
+ const char *chassis_type;
+
+ chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
+ if (!chassis_type)
+ return false;
+
+ if (!strcmp(chassis_type, "3") || /* 3: Desktop */
+ !strcmp(chassis_type, "4") || /* 4: Low Profile Desktop */
+ !strcmp(chassis_type, "5") || /* 5: Pizza Box */
+ !strcmp(chassis_type, "6") || /* 6: Mini Tower */
+ !strcmp(chassis_type, "7") || /* 7: Tower */
+ !strcmp(chassis_type, "11")) /* 11: Main Server Chassis */
+ return true;
+
+ return false;
+}
+
int acpi_video_register(void)
{
int ret = 0;
* win8 ready (where we also prefer the native backlight driver, so
* normally the acpi_video code should not register there anyways).
*/
- if (only_lcd == -1)
- only_lcd = acpi_osi_is_win8();
+ if (only_lcd == -1) {
+ if (dmi_is_desktop() && acpi_osi_is_win8())
+ only_lcd = true;
+ else
+ only_lcd = false;
+ }
dmi_check_system(video_dmi_table);
#define pr_fmt(fmt) "ACPI: watchdog: " fmt
#include <linux/acpi.h>
+#include <linux/dmi.h>
#include <linux/ioport.h>
#include <linux/platform_device.h>
#include "internal.h"
+static const struct dmi_system_id acpi_watchdog_skip[] = {
+ {
+ /*
+ * On Lenovo Z50-70 there are two issues with the WDAT
+ * table. First some of the instructions use RTC SRAM
+ * to store persistent information. This does not work well
+ * with Linux RTC driver. Second, more important thing is
+ * that the instructions do not actually reset the system.
+ *
+ * On this particular system iTCO_wdt seems to work just
+ * fine so we prefer that over WDAT for now.
+ *
+ * See also https://bugzilla.kernel.org/show_bug.cgi?id=199033.
+ */
+ .ident = "Lenovo Z50-70",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "20354"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Z50-70"),
+ },
+ },
+ {}
+};
+
+static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
+{
+ const struct acpi_table_wdat *wdat = NULL;
+ acpi_status status;
+
+ if (acpi_disabled)
+ return NULL;
+
+ if (dmi_check_system(acpi_watchdog_skip))
+ return NULL;
+
+ status = acpi_get_table(ACPI_SIG_WDAT, 0,
+ (struct acpi_table_header **)&wdat);
+ if (ACPI_FAILURE(status)) {
+ /* It is fine if there is no WDAT */
+ return NULL;
+ }
+
+ return wdat;
+}
+
/**
* Returns true if this system should prefer ACPI based watchdog instead of
* the native one (which are typically the same hardware).
*/
bool acpi_has_watchdog(void)
{
- struct acpi_table_header hdr;
-
- if (acpi_disabled)
- return false;
-
- return ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_WDAT, 0, &hdr));
+ return !!acpi_watchdog_get_wdat();
}
EXPORT_SYMBOL_GPL(acpi_has_watchdog);
struct platform_device *pdev;
struct resource *resources;
size_t nresources = 0;
- acpi_status status;
int i;
- status = acpi_get_table(ACPI_SIG_WDAT, 0,
- (struct acpi_table_header **)&wdat);
- if (ACPI_FAILURE(status)) {
+ wdat = acpi_watchdog_get_wdat();
+ if (!wdat) {
/* It is fine if there is no WDAT */
return;
}
acpi_status acpi_ns_initialize_devices(u32 flags);
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+ u32 level, void *context, void **return_value);
+
/*
* nsload - Namespace loading
*/
return_ACPI_STATUS(status);
}
+ /* Complete the initialization/resolution of package objects */
+
+ status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+ ACPI_UINT32_MAX, 0,
+ acpi_ns_init_one_package, NULL, NULL,
+ NULL);
+
/* Parameter Data (optional) */
if (parameter_node) {
return_ACPI_STATUS(status);
}
+ /* Complete the initialization/resolution of package objects */
+
+ status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+ ACPI_UINT32_MAX, 0,
+ acpi_ns_init_one_package, NULL, NULL,
+ NULL);
+
/* Store the ddb_handle into the Target operand */
status = acpi_ex_store(ddb_handle, target, walk_state);
return_ACPI_STATUS(status);
}
+/*******************************************************************************
+ *
+ * FUNCTION: acpi_ns_init_one_package
+ *
+ * PARAMETERS: obj_handle - Node
+ * level - Current nesting level
+ * context - Not used
+ * return_value - Not used
+ *
+ * RETURN: Status
+ *
+ * DESCRIPTION: Callback from acpi_walk_namespace. Invoked for every package
+ * within the namespace. Used during dynamic load of an SSDT.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+ u32 level, void *context, void **return_value)
+{
+ acpi_status status;
+ union acpi_operand_object *obj_desc;
+ struct acpi_namespace_node *node =
+ (struct acpi_namespace_node *)obj_handle;
+
+ obj_desc = acpi_ns_get_attached_object(node);
+ if (!obj_desc) {
+ return (AE_OK);
+ }
+
+ /* Exit if package is already initialized */
+
+ if (obj_desc->package.flags & AOPOBJ_DATA_VALID) {
+ return (AE_OK);
+ }
+
+ status = acpi_ds_get_package_arguments(obj_desc);
+ if (ACPI_FAILURE(status)) {
+ return (AE_OK);
+ }
+
+ status =
+ acpi_ut_walk_package_tree(obj_desc, NULL,
+ acpi_ds_init_package_element, NULL);
+ if (ACPI_FAILURE(status)) {
+ return (AE_OK);
+ }
+
+ obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+ return (AE_OK);
+}
+
/*******************************************************************************
*
* FUNCTION: acpi_ns_init_one_object
case ACPI_TYPE_PACKAGE:
- info->package_init++;
- status = acpi_ds_get_package_arguments(obj_desc);
- if (ACPI_FAILURE(status)) {
- break;
- }
-
- ACPI_DEBUG_PRINT_RAW((ACPI_DB_PARSE,
- "%s: Completing resolution of Package elements\n",
- ACPI_GET_FUNCTION_NAME));
+ /* Complete the initialization/resolution of the package object */
- /*
- * Resolve all named references in package objects (and all
- * sub-packages). This action has been deferred until the entire
- * namespace has been loaded, in order to support external and
- * forward references from individual package elements (05/2017).
- */
- status = acpi_ut_walk_package_tree(obj_desc, NULL,
- acpi_ds_init_package_element,
- NULL);
-
- obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+ info->package_init++;
+ status =
+ acpi_ns_init_one_package(obj_handle, level, NULL, NULL);
break;
default:
NULL, 0644);
MODULE_PARM_DESC(lid_init_state, "Behavior for reporting LID initial state");
-module_acpi_driver(acpi_button_driver);
+static int acpi_button_register_driver(struct acpi_driver *driver)
+{
+ /*
+ * Modules such as nouveau.ko and i915.ko have a link time dependency
+ * on acpi_lid_open(), and would therefore not be loadable on ACPI
+ * capable kernels booted in non-ACPI mode if the return value of
+ * acpi_bus_register_driver() is returned from here with ACPI disabled
+ * when this driver is built as a module.
+ */
+ if (acpi_disabled)
+ return 0;
+
+ return acpi_bus_register_driver(driver);
+}
+
+static void acpi_button_unregister_driver(struct acpi_driver *driver)
+{
+ if (!acpi_disabled)
+ acpi_bus_unregister_driver(driver);
+}
+
+module_driver(acpi_button_driver, acpi_button_register_driver,
+ acpi_button_unregister_driver);
acpi_cmos_rtc_init();
acpi_container_init();
acpi_memory_hotplug_init();
+ acpi_watchdog_init();
acpi_pnp_init();
acpi_int340x_thermal_init();
acpi_amba_init();
- acpi_watchdog_init();
acpi_init_lpit();
acpi_scan_add_handler(&generic_device_handler);
DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
},
},
+ /*
+ * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
+ * the Low Power S0 Idle firmware interface (see
+ * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
+ */
+ {
+ .callback = init_no_lps0,
+ .ident = "ThinkPad X1 Tablet(2016)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"),
+ },
+ },
{},
};
struct device_attribute *attr, char *buf)
{
struct amba_device *dev = to_amba_device(_dev);
+ ssize_t len;
- if (!dev->driver_override)
- return 0;
-
- return sprintf(buf, "%s\n", dev->driver_override);
+ device_lock(_dev);
+ len = sprintf(buf, "%s\n", dev->driver_override);
+ device_unlock(_dev);
+ return len;
}
static ssize_t driver_override_store(struct device *_dev,
const char *buf, size_t count)
{
struct amba_device *dev = to_amba_device(_dev);
- char *driver_override, *old = dev->driver_override, *cp;
+ char *driver_override, *old, *cp;
- if (count > PATH_MAX)
+ /* We need to keep extra room for a newline */
+ if (count >= (PAGE_SIZE - 1))
return -EINVAL;
driver_override = kstrndup(buf, count, GFP_KERNEL);
if (cp)
*cp = '\0';
+ device_lock(_dev);
+ old = dev->driver_override;
if (strlen(driver_override)) {
dev->driver_override = driver_override;
} else {
kfree(driver_override);
dev->driver_override = NULL;
}
+ device_unlock(_dev);
kfree(old);
else
return_error = BR_DEAD_REPLY;
mutex_unlock(&context->context_mgr_node_lock);
+ if (target_node && target_proc == proc) {
+ binder_user_error("%d:%d got transaction to context manager from process owning it\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_invalid_target_handle;
+ }
}
if (!target_node) {
/*
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
deadline, &online, NULL);
bool online;
int rc;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
for (i = 0; i < 2; i++) {
u16 val;
u32 em_msg_type; /* EM message type */
bool got_runtime_pm; /* Did we do pm_runtime_get? */
struct clk *clks[AHCI_MAX_CLKS]; /* Optional */
- struct reset_control *rsts; /* Optional */
struct regulator **target_pwrs; /* Optional */
/*
* If platform uses PHYs. There is a 1:1 relation between the port number and
* be overridden anytime before the host is activated.
*/
void (*start_engine)(struct ata_port *ap);
+ /*
+ * Optional ahci_stop_engine override, if not set this gets set to the
+ * default ahci_stop_engine during ahci_save_initial_config, this can
+ * be overridden anytime before the host is activated.
+ */
+ int (*stop_engine)(struct ata_port *ap);
+
irqreturn_t (*irq_handler)(int irq, void *dev_instance);
/* only required for per-port MSI(-X) support */
writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
}
+/**
+ * ahci_mvebu_stop_engine
+ *
+ * @ap: Target ata port
+ *
+ * Errata Ref#226 - SATA Disk HOT swap issue when connected through
+ * Port Multiplier in FIS-based Switching mode.
+ *
+ * To avoid the issue, according to design, the bits[11:8, 0] of
+ * register PxFBS are cleared when Port Command and Status (0x18) bit[0]
+ * changes its value from 1 to 0, i.e. falling edge of Port
+ * Command and Status bit[0] sends PULSE that resets PxFBS
+ * bits[11:8; 0].
+ *
+ * This function is used to override function of "ahci_stop_engine"
+ * from libahci.c by adding the mvebu work around(WA) to save PxFBS
+ * value before the PxCMD ST write of 0, then restore PxFBS value.
+ *
+ * Return: 0 on success; Error code otherwise.
+ */
+int ahci_mvebu_stop_engine(struct ata_port *ap)
+{
+ void __iomem *port_mmio = ahci_port_base(ap);
+ u32 tmp, port_fbs;
+
+ tmp = readl(port_mmio + PORT_CMD);
+
+ /* check if the HBA is idle */
+ if ((tmp & (PORT_CMD_START | PORT_CMD_LIST_ON)) == 0)
+ return 0;
+
+ /* save the port PxFBS register for later restore */
+ port_fbs = readl(port_mmio + PORT_FBS);
+
+ /* setting HBA to idle */
+ tmp &= ~PORT_CMD_START;
+ writel(tmp, port_mmio + PORT_CMD);
+
+ /*
+ * bit #15 PxCMD signal doesn't clear PxFBS,
+ * restore the PxFBS register right after clearing the PxCMD ST,
+ * no need to wait for the PxCMD bit #15.
+ */
+ writel(port_fbs, port_mmio + PORT_FBS);
+
+ /* wait for engine to stop. This could be as long as 500 msec */
+ tmp = ata_wait_register(ap, port_mmio + PORT_CMD,
+ PORT_CMD_LIST_ON, PORT_CMD_LIST_ON, 1, 500);
+ if (tmp & PORT_CMD_LIST_ON)
+ return -EIO;
+
+ return 0;
+}
+
#ifdef CONFIG_PM_SLEEP
static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
{
if (rc)
return rc;
+ hpriv->stop_engine = ahci_mvebu_stop_engine;
+
if (of_device_is_compatible(pdev->dev.of_node,
"marvell,armada-380-ahci")) {
dram = mv_mbus_dram_info();
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/*
* There is a errata on ls1021a Rev1.0 and Rev2.0 which is:
PORT_CMD_ISSUE, 0x0, 1, 100))
return -EBUSY;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
ahci_start_fis_rx(ap);
/*
portrxfis_saved = readl(port_mmio + PORT_FIS_ADDR);
portrxfishi_saved = readl(port_mmio + PORT_FIS_ADDR_HI);
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
rc = xgene_ahci_do_hardreset(link, deadline, &online);
if (!hpriv->start_engine)
hpriv->start_engine = ahci_start_engine;
+ if (!hpriv->stop_engine)
+ hpriv->stop_engine = ahci_stop_engine;
+
if (!hpriv->irq_handler)
hpriv->irq_handler = ahci_single_level_irq_intr;
}
static int ahci_deinit_port(struct ata_port *ap, const char **emsg)
{
int rc;
+ struct ahci_host_priv *hpriv = ap->host->private_data;
/* disable DMA */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc) {
*emsg = "failed to stop engine";
return rc;
int busy, rc;
/* stop engine */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
goto out_restart;
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
if (!(ap->pflags & ATA_PFLAG_FROZEN)) {
/* restart engine */
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
hpriv->start_engine(ap);
}
sata_pmp_error_handler(ap);
if (!ata_dev_enabled(ap->link.device))
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
}
EXPORT_SYMBOL_GPL(ahci_error_handler);
return;
/* set DITO, MDAT, DETO and enable DevSlp, need to stop engine first */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
return;
}
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
return;
}
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
#include <linux/phy/phy.h>
#include <linux/pm_runtime.h>
#include <linux/of_platform.h>
-#include <linux/reset.h>
#include "ahci.h"
static void ahci_host_stop(struct ata_host *host);
* following order:
* 1) Regulator
* 2) Clocks (through ahci_platform_enable_clks)
- * 3) Resets
- * 4) Phys
+ * 3) Phys
*
* If resource enabling fails at any point the previous enabled resources
* are disabled in reverse order.
if (rc)
goto disable_regulator;
- rc = reset_control_deassert(hpriv->rsts);
- if (rc)
- goto disable_clks;
-
rc = ahci_platform_enable_phys(hpriv);
if (rc)
- goto disable_resets;
+ goto disable_clks;
return 0;
-disable_resets:
- reset_control_assert(hpriv->rsts);
-
disable_clks:
ahci_platform_disable_clks(hpriv);
* following order:
* 1) Phys
* 2) Clocks (through ahci_platform_disable_clks)
- * 3) Resets
- * 4) Regulator
+ * 3) Regulator
*/
void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
{
ahci_platform_disable_phys(hpriv);
- reset_control_assert(hpriv->rsts);
-
ahci_platform_disable_clks(hpriv);
ahci_platform_disable_regulators(hpriv);
hpriv->clks[i] = clk;
}
- hpriv->rsts = devm_reset_control_array_get_optional_shared(dev);
- if (IS_ERR(hpriv->rsts)) {
- rc = PTR_ERR(hpriv->rsts);
- goto err_out;
- }
-
hpriv->nports = child_nodes = of_get_child_count(dev->of_node);
/*
ATA_HORKAGE_ZERO_AFTER_TRIM |
ATA_HORKAGE_NOLPM, },
+ /* This specific Samsung model/firmware-rev does not handle LPM well */
+ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, },
+
+ /* Sandisk devices which are known to not handle LPM well */
+ { "SanDisk SD7UB3Q*G1001", NULL, ATA_HORKAGE_NOLPM, },
+
/* devices that don't properly handle queued TRIM commands */
{ "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM, },
{ }
#endif /* CONFIG_PM */
-static void __ata_ehi_pushv_desc(struct ata_eh_info *ehi, const char *fmt,
- va_list args)
+static __printf(2, 0) void __ata_ehi_pushv_desc(struct ata_eh_info *ehi,
+ const char *fmt, va_list args)
{
ehi->desc_len += vscnprintf(ehi->desc + ehi->desc_len,
ATA_EH_DESC_LEN - ehi->desc_len,
int rc;
int retry = 100;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
[PORT_CERR_INCONSISTENT] = { AC_ERR_HSM, ATA_EH_RESET,
"protocol mismatch" },
[PORT_CERR_DIRECTION] = { AC_ERR_HSM, ATA_EH_RESET,
- "data directon mismatch" },
+ "data direction mismatch" },
[PORT_CERR_UNDERRUN] = { AC_ERR_HSM, ATA_EH_RESET,
"ran out of SGEs while writing" },
[PORT_CERR_OVERRUN] = { AC_ERR_HSM, ATA_EH_RESET,
"ran out of SGEs while reading" },
[PORT_CERR_PKT_PROT] = { AC_ERR_HSM, ATA_EH_RESET,
- "invalid data directon for ATAPI CDB" },
+ "invalid data direction for ATAPI CDB" },
[PORT_CERR_SGT_BOUNDARY] = { AC_ERR_SYSTEM, ATA_EH_RESET,
"SGT not on qword boundary" },
[PORT_CERR_SGT_TGTABRT] = { AC_ERR_HOST_BUS, ATA_EH_RESET,
"reserved 37",
"reserved 38",
"reserved 39",
- "reseverd 40",
+ "reserved 40",
"reserved 41",
"reserved 42",
"reserved 43",
#include <asm/io.h>
#include <linux/atomic.h>
#include <linux/uaccess.h>
+#include <linux/nospec.h>
#include "uPD98401.h"
#include "uPD98402.h"
return -EFAULT;
if (pool < 0 || pool > ZATM_LAST_POOL)
return -EINVAL;
+ pool = array_index_nospec(pool,
+ ZATM_LAST_POOL + 1);
spin_lock_irqsave(&zatm_dev->lock, flags);
info = zatm_dev->pool_info[pool];
if (cmd == ZATM_GETPOOLZ) {
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, maps that memory to the provided vma.
*
- * Returns 1 if we correctly mapped the memory, or 0 if the caller should
- * proceed with mapping memory from generic pools.
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
*/
int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
void *vaddr, size_t size, int *ret)
#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
unsigned long off = vma->vm_pgoff;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
- if (off < count && user_count <= (count - off)) {
+ if (off < count && user_count <= (count - off))
ret = remap_pfn_range(vma, vma->vm_start,
- pfn + off,
+ page_to_pfn(virt_to_page(cpu_addr)) + off,
user_count << PAGE_SHIFT,
vma->vm_page_prot);
- }
#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
return ret;
}
/**
- * fw_load_sysfs_fallback - load a firmware via the syfs fallback mechanism
- * @fw_sysfs: firmware syfs information for the firmware to load
+ * fw_load_sysfs_fallback - load a firmware via the sysfs fallback mechanism
+ * @fw_sysfs: firmware sysfs information for the firmware to load
* @opt_flags: flags of options, FW_OPT_*
* @timeout: timeout to wait for the load
*
#include <linux/device.h>
/**
- * struct firmware_fallback_config - firmware fallback configuratioon settings
+ * struct firmware_fallback_config - firmware fallback configuration settings
*
* Helps describe and fine tune the fallback mechanism.
*
static void lo_complete_rq(struct request *rq)
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ blk_status_t ret = BLK_STS_OK;
- if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
- cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
- struct bio *bio = cmd->rq->bio;
-
- bio_advance(bio, cmd->ret);
- zero_fill_bio(bio);
+ if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+ req_op(rq) != REQ_OP_READ) {
+ if (cmd->ret < 0)
+ ret = BLK_STS_IOERR;
+ goto end_io;
}
- blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
+ /*
+ * Short READ - if we got some data, advance our request and
+ * retry it. If we got no data, end the rest with EIO.
+ */
+ if (cmd->ret) {
+ blk_update_request(rq, BLK_STS_OK, cmd->ret);
+ cmd->ret = 0;
+ blk_mq_requeue_request(rq, true);
+ } else {
+ if (cmd->use_aio) {
+ struct bio *bio = rq->bio;
+
+ while (bio) {
+ zero_fill_bio(bio);
+ bio = bio->bi_next;
+ }
+ }
+ ret = BLK_STS_IOERR;
+end_io:
+ blk_mq_end_request(rq, ret);
+ }
}
static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
{
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+
if (!atomic_dec_and_test(&cmd->ref))
return;
kfree(cmd->bvec);
cmd->bvec = NULL;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
{
struct iov_iter iter;
struct bio_vec *bvec;
- struct request *rq = cmd->rq;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
struct bio *bio = rq->bio;
struct file *file = lo->lo_backing_file;
unsigned int offset;
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
- struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = bd->rq;
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ struct loop_device *lo = rq->q->queuedata;
- blk_mq_start_request(bd->rq);
+ blk_mq_start_request(rq);
if (lo->lo_state != Lo_bound)
return BLK_STS_IOERR;
- switch (req_op(cmd->rq)) {
+ switch (req_op(rq)) {
case REQ_OP_FLUSH:
case REQ_OP_DISCARD:
case REQ_OP_WRITE_ZEROES:
/* always use the first bio's css */
#ifdef CONFIG_BLK_CGROUP
- if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) {
- cmd->css = cmd->rq->bio->bi_css;
+ if (cmd->use_aio && rq->bio && rq->bio->bi_css) {
+ cmd->css = rq->bio->bi_css;
css_get(cmd->css);
} else
#endif
static void loop_handle_cmd(struct loop_cmd *cmd)
{
- const bool write = op_is_write(req_op(cmd->rq));
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+ const bool write = op_is_write(req_op(rq));
+ struct loop_device *lo = rq->q->queuedata;
int ret = 0;
if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
goto failed;
}
- ret = do_req_filebacked(lo, cmd->rq);
+ ret = do_req_filebacked(lo, rq);
failed:
/* complete non-aio request */
if (!cmd->use_aio || ret) {
cmd->ret = ret ? -EIO : 0;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
}
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
- cmd->rq = rq;
kthread_init_work(&cmd->work, loop_queue_work);
-
return 0;
}
struct loop_cmd {
struct kthread_work work;
- struct request *rq;
bool use_aio; /* use AIO interface to handle I/O */
atomic_t ref; /* only for aio */
long ret;
osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
"copyup");
osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0,
- obj_req->copyup_bvecs, bytes);
+ obj_req->copyup_bvecs,
+ obj_req->copyup_bvec_count,
+ bytes);
switch (obj_req->img_request->op_type) {
case OBJ_OP_WRITE:
/* Select values for swim_select and swim_readbit */
#define READ_DATA_0 0x074
-#define TWOMEG_DRIVE 0x075
+#define ONEMEG_DRIVE 0x075
#define SINGLE_SIDED 0x076
#define DRIVE_PRESENT 0x077
#define DISK_IN 0x170
#define TRACK_ZERO 0x172
#define TACHO 0x173
#define READ_DATA_1 0x174
-#define MFM_MODE 0x175
+#define GCR_MODE 0x175
#define SEEK_COMPLETE 0x176
-#define ONEMEG_MEDIA 0x177
+#define TWOMEG_MEDIA 0x177
/* Bits in handshake register */
struct floppy_struct *g;
fs->disk_in = 1;
fs->write_protected = swim_readbit(base, WRITE_PROT);
- fs->type = swim_readbit(base, ONEMEG_MEDIA);
if (swim_track00(base))
printk(KERN_ERR
swim_track00(base);
+ fs->type = swim_readbit(base, TWOMEG_MEDIA) ?
+ HD_MEDIA : DD_MEDIA;
+ fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2;
get_floppy_geometry(fs, 0, &g);
fs->total_secs = g->size;
fs->secpercyl = g->head * g->sect;
swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2);
udelay(10);
- swim_drive(base, INTERNAL_DRIVE);
+ swim_drive(base, fs->location);
swim_motor(base, ON);
swim_action(base, SETMFM);
if (fs->ejected)
goto out;
}
+ set_capacity(fs->disk, fs->total_secs);
+
if (mode & FMODE_NDELAY)
return 0;
if (copy_to_user((void __user *) param, (void *) &floppy_type,
sizeof(struct floppy_struct)))
return -EFAULT;
- break;
-
- default:
- printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n",
- cmd);
- return -ENOSYS;
+ return 0;
}
- return 0;
+ return -ENOTTY;
}
static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo)
struct swim_priv *swd = data;
int drive = (*part & 3);
- if (drive > swd->floppy_count)
+ if (drive >= swd->floppy_count)
return NULL;
*part = 0;
swim_motor(base, OFF);
- if (swim_readbit(base, SINGLE_SIDED))
- fs->head_number = 1;
- else
- fs->head_number = 2;
+ fs->type = HD_MEDIA;
+ fs->head_number = 2;
+
fs->ref_count = 0;
fs->ejected = 1;
/* scan floppy drives */
swim_drive(base, INTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, INTERNAL_DRIVE);
swim_drive(base, EXTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, EXTERNAL_DRIVE);
/* register floppy drives */
&swd->lock);
if (!swd->unit[drive].disk->queue) {
err = -ENOMEM;
- put_disk(swd->unit[drive].disk);
goto exit_put_disks;
}
blk_queue_bounce_limit(swd->unit[drive].disk->queue,
goto out;
}
- swim_base = ioremap(res->start, resource_size(res));
+ swim_base = (struct swim __iomem *)res->start;
if (!swim_base) {
ret = -ENOMEM;
goto out_release_io;
if (!get_swim_mode(swim_base)) {
printk(KERN_INFO "SWIM device not found !\n");
ret = -ENODEV;
- goto out_iounmap;
+ goto out_release_io;
}
/* set platform driver data */
swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL);
if (!swd) {
ret = -ENOMEM;
- goto out_iounmap;
+ goto out_release_io;
}
platform_set_drvdata(dev, swd);
out_kfree:
kfree(swd);
-out_iounmap:
- iounmap(swim_base);
out_release_io:
release_mem_region(res->start, resource_size(res));
out:
for (drive = 0; drive < swd->floppy_count; drive++)
floppy_eject(&swd->unit[drive]);
- iounmap(swd->base);
-
res = platform_get_resource(dev, IORESOURCE_MEM, 0);
if (res)
release_mem_region(res->start, resource_size(res));
#define MOTOR_ON 2
#define RELAX 3 /* also eject in progress */
#define READ_DATA_0 4
-#define TWOMEG_DRIVE 5
+#define ONEMEG_DRIVE 5
#define SINGLE_SIDED 6 /* drive or diskette is 4MB type? */
#define DRIVE_PRESENT 7
#define DISK_IN 8
#define TRACK_ZERO 10
#define TACHO 11
#define READ_DATA_1 12
-#define MFM_MODE 13
+#define GCR_MODE 13
#define SEEK_COMPLETE 14
-#define ONEMEG_MEDIA 15
+#define TWOMEG_MEDIA 15
/* Definitions of values used in writing and formatting */
#define DATA_ESCAPE 0x99
config BT_HCIUART_QCA
bool "Qualcomm Atheros protocol support"
depends on BT_HCIUART
+ depends on BT_HCIUART_SERDEV
select BT_HCIUART_H4
select BT_QCA
help
return 0;
}
-static const struct {
+struct bcm_subver_table {
u16 subver;
const char *name;
-} bcm_uart_subver_table[] = {
+};
+
+static const struct bcm_subver_table bcm_uart_subver_table[] = {
{ 0x4103, "BCM4330B1" }, /* 002.001.003 */
{ 0x410e, "BCM43341B0" }, /* 002.001.014 */
{ 0x4406, "BCM4324B3" }, /* 002.004.006 */
{ }
};
-int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len)
+static const struct bcm_subver_table bcm_usb_subver_table[] = {
+ { 0x210b, "BCM43142A0" }, /* 001.001.011 */
+ { 0x2112, "BCM4314A0" }, /* 001.001.018 */
+ { 0x2118, "BCM20702A0" }, /* 001.001.024 */
+ { 0x2126, "BCM4335A0" }, /* 001.001.038 */
+ { 0x220e, "BCM20702A1" }, /* 001.002.014 */
+ { 0x230f, "BCM4354A2" }, /* 001.003.015 */
+ { 0x4106, "BCM4335B0" }, /* 002.001.006 */
+ { 0x410e, "BCM20702B0" }, /* 002.001.014 */
+ { 0x6109, "BCM4335C0" }, /* 003.001.009 */
+ { 0x610c, "BCM4354" }, /* 003.001.012 */
+ { }
+};
+
+int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len,
+ bool reinit)
{
- u16 subver, rev;
- const char *hw_name = NULL;
+ u16 subver, rev, pid, vid;
+ const char *hw_name = "BCM";
struct sk_buff *skb;
struct hci_rp_read_local_version *ver;
+ const struct bcm_subver_table *bcm_subver_table;
int i, err;
/* Reset */
kfree_skb(skb);
/* Read controller information */
- err = btbcm_read_info(hdev);
- if (err)
- return err;
+ if (!reinit) {
+ err = btbcm_read_info(hdev);
+ if (err)
+ return err;
+ }
- switch ((rev & 0xf000) >> 12) {
- case 0:
- case 1:
- case 2:
- case 3:
- for (i = 0; bcm_uart_subver_table[i].name; i++) {
- if (subver == bcm_uart_subver_table[i].subver) {
- hw_name = bcm_uart_subver_table[i].name;
- break;
- }
+ /* Upper nibble of rev should be between 0 and 3? */
+ if (((rev & 0xf000) >> 12) > 3)
+ return 0;
+
+ bcm_subver_table = (hdev->bus == HCI_USB) ? bcm_usb_subver_table :
+ bcm_uart_subver_table;
+
+ for (i = 0; bcm_subver_table[i].name; i++) {
+ if (subver == bcm_subver_table[i].subver) {
+ hw_name = bcm_subver_table[i].name;
+ break;
}
+ }
- snprintf(fw_name, len, "brcm/%s.hcd", hw_name ? : "BCM");
- break;
- default:
- return 0;
+ if (hdev->bus == HCI_USB) {
+ /* Read USB Product Info */
+ skb = btbcm_read_usb_product(hdev);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
+
+ vid = get_unaligned_le16(skb->data + 1);
+ pid = get_unaligned_le16(skb->data + 3);
+ kfree_skb(skb);
+
+ snprintf(fw_name, len, "brcm/%s-%4.4x-%4.4x.hcd",
+ hw_name, vid, pid);
+ } else {
+ snprintf(fw_name, len, "brcm/%s.hcd", hw_name);
}
bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
- hw_name ? : "BCM", (subver & 0xe000) >> 13,
+ hw_name, (subver & 0xe000) >> 13,
(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
return 0;
int btbcm_finalize(struct hci_dev *hdev)
{
- struct sk_buff *skb;
- struct hci_rp_read_local_version *ver;
- u16 subver, rev;
+ char fw_name[64];
int err;
- /* Reset */
- err = btbcm_reset(hdev);
+ /* Re-initialize */
+ err = btbcm_initialize(hdev, fw_name, sizeof(fw_name), true);
if (err)
return err;
- /* Read Local Version Info */
- skb = btbcm_read_local_version(hdev);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
-
- ver = (struct hci_rp_read_local_version *)skb->data;
- rev = le16_to_cpu(ver->hci_rev);
- subver = le16_to_cpu(ver->lmp_subver);
- kfree_skb(skb);
-
- bt_dev_info(hdev, "BCM (%3.3u.%3.3u.%3.3u) build %4.4u",
- (subver & 0xe000) >> 13, (subver & 0x1f00) >> 8,
- (subver & 0x00ff), rev & 0x0fff);
-
btbcm_check_bdaddr(hdev);
set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
}
EXPORT_SYMBOL_GPL(btbcm_finalize);
-static const struct {
- u16 subver;
- const char *name;
-} bcm_usb_subver_table[] = {
- { 0x210b, "BCM43142A0" }, /* 001.001.011 */
- { 0x2112, "BCM4314A0" }, /* 001.001.018 */
- { 0x2118, "BCM20702A0" }, /* 001.001.024 */
- { 0x2126, "BCM4335A0" }, /* 001.001.038 */
- { 0x220e, "BCM20702A1" }, /* 001.002.014 */
- { 0x230f, "BCM4354A2" }, /* 001.003.015 */
- { 0x4106, "BCM4335B0" }, /* 002.001.006 */
- { 0x410e, "BCM20702B0" }, /* 002.001.014 */
- { 0x6109, "BCM4335C0" }, /* 003.001.009 */
- { 0x610c, "BCM4354" }, /* 003.001.012 */
- { }
-};
-
int btbcm_setup_patchram(struct hci_dev *hdev)
{
char fw_name[64];
const struct firmware *fw;
- u16 subver, rev, pid, vid;
- const char *hw_name = NULL;
struct sk_buff *skb;
- struct hci_rp_read_local_version *ver;
- int i, err;
-
- /* Reset */
- err = btbcm_reset(hdev);
- if (err)
- return err;
-
- /* Read Local Version Info */
- skb = btbcm_read_local_version(hdev);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
-
- ver = (struct hci_rp_read_local_version *)skb->data;
- rev = le16_to_cpu(ver->hci_rev);
- subver = le16_to_cpu(ver->lmp_subver);
- kfree_skb(skb);
+ int err;
- /* Read controller information */
- err = btbcm_read_info(hdev);
+ /* Initialize */
+ err = btbcm_initialize(hdev, fw_name, sizeof(fw_name), false);
if (err)
return err;
- switch ((rev & 0xf000) >> 12) {
- case 0:
- case 3:
- for (i = 0; bcm_uart_subver_table[i].name; i++) {
- if (subver == bcm_uart_subver_table[i].subver) {
- hw_name = bcm_uart_subver_table[i].name;
- break;
- }
- }
-
- snprintf(fw_name, sizeof(fw_name), "brcm/%s.hcd",
- hw_name ? : "BCM");
- break;
- case 1:
- case 2:
- /* Read USB Product Info */
- skb = btbcm_read_usb_product(hdev);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
-
- vid = get_unaligned_le16(skb->data + 1);
- pid = get_unaligned_le16(skb->data + 3);
- kfree_skb(skb);
-
- for (i = 0; bcm_usb_subver_table[i].name; i++) {
- if (subver == bcm_usb_subver_table[i].subver) {
- hw_name = bcm_usb_subver_table[i].name;
- break;
- }
- }
-
- snprintf(fw_name, sizeof(fw_name), "brcm/%s-%4.4x-%4.4x.hcd",
- hw_name ? : "BCM", vid, pid);
- break;
- default:
- return 0;
- }
-
- bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
- hw_name ? : "BCM", (subver & 0xe000) >> 13,
- (subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
-
err = request_firmware(&fw, fw_name, &hdev->dev);
if (err < 0) {
bt_dev_info(hdev, "BCM: Patch %s not found", fw_name);
release_firmware(fw);
- /* Reset */
- err = btbcm_reset(hdev);
+ /* Re-initialize */
+ err = btbcm_initialize(hdev, fw_name, sizeof(fw_name), true);
if (err)
return err;
- /* Read Local Version Info */
- skb = btbcm_read_local_version(hdev);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
-
- ver = (struct hci_rp_read_local_version *)skb->data;
- rev = le16_to_cpu(ver->hci_rev);
- subver = le16_to_cpu(ver->lmp_subver);
- kfree_skb(skb);
-
- bt_dev_info(hdev, "%s (%3.3u.%3.3u.%3.3u) build %4.4u",
- hw_name ? : "BCM", (subver & 0xe000) >> 13,
- (subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
-
/* Read Local Name */
skb = btbcm_read_local_name(hdev);
if (IS_ERR(skb))
int btbcm_setup_patchram(struct hci_dev *hdev);
int btbcm_setup_apple(struct hci_dev *hdev);
-int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len);
+int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len,
+ bool reinit);
int btbcm_finalize(struct hci_dev *hdev);
#else
}
static inline int btbcm_initialize(struct hci_dev *hdev, char *fw_name,
- size_t len)
+ size_t len, bool reinit)
{
return 0;
}
BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff);
BT_DBG("Length\t\t : %d bytes", length);
+ config->dnld_mode = ROME_SKIP_EVT_NONE;
+
switch (config->type) {
case TLV_TYPE_PATCH:
tlv_patch = (struct tlv_type_patch *)tlv->data;
- BT_DBG("Total Length\t\t : %d bytes",
+
+ /* For Rome version 1.1 to 3.1, all segment commands
+ * are acked by a vendor specific event (VSE).
+ * For Rome >= 3.2, the download mode field indicates
+ * if VSE is skipped by the controller.
+ * In case VSE is skipped, only the last segment is acked.
+ */
+ config->dnld_mode = tlv_patch->download_mode;
+
+ BT_DBG("Total Length : %d bytes",
le32_to_cpu(tlv_patch->total_size));
- BT_DBG("Patch Data Length\t : %d bytes",
+ BT_DBG("Patch Data Length : %d bytes",
le32_to_cpu(tlv_patch->data_length));
BT_DBG("Signing Format Version : 0x%x",
tlv_patch->format_version);
- BT_DBG("Signature Algorithm\t : 0x%x",
+ BT_DBG("Signature Algorithm : 0x%x",
tlv_patch->signature);
- BT_DBG("Reserved\t\t : 0x%x",
- le16_to_cpu(tlv_patch->reserved1));
- BT_DBG("Product ID\t\t : 0x%04x",
+ BT_DBG("Download mode : 0x%x",
+ tlv_patch->download_mode);
+ BT_DBG("Reserved : 0x%x",
+ tlv_patch->reserved1);
+ BT_DBG("Product ID : 0x%04x",
le16_to_cpu(tlv_patch->product_id));
- BT_DBG("Rom Build Version\t : 0x%04x",
+ BT_DBG("Rom Build Version : 0x%04x",
le16_to_cpu(tlv_patch->rom_build));
- BT_DBG("Patch Version\t\t : 0x%04x",
+ BT_DBG("Patch Version : 0x%04x",
le16_to_cpu(tlv_patch->patch_version));
- BT_DBG("Reserved\t\t : 0x%x",
+ BT_DBG("Reserved : 0x%x",
le16_to_cpu(tlv_patch->reserved2));
- BT_DBG("Patch Entry Address\t : 0x%x",
+ BT_DBG("Patch Entry Address : 0x%x",
le32_to_cpu(tlv_patch->entry));
break;
}
}
-static int rome_tlv_send_segment(struct hci_dev *hdev, int idx, int seg_size,
- const u8 *data)
+static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
+ const u8 *data, enum rome_tlv_dnld_mode mode)
{
struct sk_buff *skb;
struct edl_event_hdr *edl;
u8 cmd[MAX_SIZE_PER_TLV_SEGMENT + 2];
int err = 0;
- BT_DBG("%s: Download segment #%d size %d", hdev->name, idx, seg_size);
-
cmd[0] = EDL_PATCH_TLV_REQ_CMD;
cmd[1] = seg_size;
memcpy(cmd + 2, data, seg_size);
+ if (mode == ROME_SKIP_EVT_VSE_CC || mode == ROME_SKIP_EVT_VSE)
+ return __hci_cmd_send(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2,
+ cmd);
+
skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2, cmd,
HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
if (IS_ERR(skb)) {
return err;
}
-static int rome_tlv_download_request(struct hci_dev *hdev,
- const struct firmware *fw)
-{
- const u8 *buffer, *data;
- int total_segment, remain_size;
- int ret, i;
-
- if (!fw || !fw->data)
- return -EINVAL;
-
- total_segment = fw->size / MAX_SIZE_PER_TLV_SEGMENT;
- remain_size = fw->size % MAX_SIZE_PER_TLV_SEGMENT;
-
- BT_DBG("%s: Total segment num %d remain size %d total size %zu",
- hdev->name, total_segment, remain_size, fw->size);
-
- data = fw->data;
- for (i = 0; i < total_segment; i++) {
- buffer = data + i * MAX_SIZE_PER_TLV_SEGMENT;
- ret = rome_tlv_send_segment(hdev, i, MAX_SIZE_PER_TLV_SEGMENT,
- buffer);
- if (ret < 0)
- return -EIO;
- }
-
- if (remain_size) {
- buffer = data + total_segment * MAX_SIZE_PER_TLV_SEGMENT;
- ret = rome_tlv_send_segment(hdev, total_segment, remain_size,
- buffer);
- if (ret < 0)
- return -EIO;
- }
-
- return 0;
-}
-
static int rome_download_firmware(struct hci_dev *hdev,
struct rome_config *config)
{
const struct firmware *fw;
- int ret;
+ const u8 *segment;
+ int ret, remain, i = 0;
bt_dev_info(hdev, "ROME Downloading %s", config->fwname);
rome_tlv_check_data(config, fw);
- ret = rome_tlv_download_request(hdev, fw);
- if (ret) {
- BT_ERR("%s: Failed to download file: %s (%d)", hdev->name,
- config->fwname, ret);
+ segment = fw->data;
+ remain = fw->size;
+ while (remain > 0) {
+ int segsize = min(MAX_SIZE_PER_TLV_SEGMENT, remain);
+
+ bt_dev_dbg(hdev, "Send segment %d, size %d", i++, segsize);
+
+ remain -= segsize;
+ /* The last segment is always acked regardless download mode */
+ if (!remain || segsize < MAX_SIZE_PER_TLV_SEGMENT)
+ config->dnld_mode = ROME_SKIP_EVT_NONE;
+
+ ret = rome_tlv_send_segment(hdev, segsize, segment,
+ config->dnld_mode);
+ if (ret)
+ break;
+
+ segment += segsize;
}
release_firmware(fw);
QCA_BAUDRATE_RESERVED
};
+enum rome_tlv_dnld_mode {
+ ROME_SKIP_EVT_NONE,
+ ROME_SKIP_EVT_VSE,
+ ROME_SKIP_EVT_CC,
+ ROME_SKIP_EVT_VSE_CC
+};
+
enum rome_tlv_type {
TLV_TYPE_PATCH = 1,
TLV_TYPE_NVM
u8 type;
char fwname[64];
uint8_t user_baud_rate;
+ enum rome_tlv_dnld_mode dnld_mode;
};
struct edl_event_hdr {
__le32 data_length;
__u8 format_version;
__u8 signature;
- __le16 reserved1;
+ __u8 download_mode;
+ __u8 reserved1;
__le16 product_id;
__le16 rom_build;
__le16 patch_version;
{
struct btqcomsmd *btq = priv;
+ btq->hdev->stat.byte_rx += count;
return btqcomsmd_recv(btq->hdev, HCI_EVENT_PKT, data, count);
}
switch (hci_skb_pkt_type(skb)) {
case HCI_ACLDATA_PKT:
ret = rpmsg_send(btq->acl_channel, skb->data, skb->len);
+ if (ret) {
+ hdev->stat.err_tx++;
+ break;
+ }
hdev->stat.acl_tx++;
hdev->stat.byte_tx += skb->len;
break;
case HCI_COMMAND_PKT:
ret = rpmsg_send(btq->cmd_channel, skb->data, skb->len);
+ if (ret) {
+ hdev->stat.err_tx++;
+ break;
+ }
hdev->stat.cmd_tx++;
+ hdev->stat.byte_tx += skb->len;
break;
default:
ret = -EILSEQ;
{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
/* QCA ROME chipset */
- { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
+ { USB_DEVICE(0x04ca, 0x301a), .driver_info = BTUSB_QCA_ROME },
+ { USB_DEVICE(0x13d3, 0x3496), .driver_info = BTUSB_QCA_ROME },
/* Broadcom BCM2035 */
{ USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 },
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"),
},
},
+ {
+ /* Dell XPS 9360 (QCA ROME device 0cf3:e300) */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
+ },
+ },
{}
};
}
#endif
+static void btusb_check_needs_reset_resume(struct usb_interface *intf)
+{
+ if (dmi_check_system(btusb_needs_reset_resume_table))
+ interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
+}
+
static int btusb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
hdev->send = btusb_send_frame;
hdev->notify = btusb_notify;
- if (dmi_check_system(btusb_needs_reset_resume_table))
- interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
-
#ifdef CONFIG_PM
err = btusb_config_oob_wake(hdev);
if (err)
data->setup_on_usb = btusb_setup_qca;
hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
+ btusb_check_needs_reset_resume(intf);
}
#ifdef CONFIG_BT_HCIBTUSB_RTL
hu->hdev->set_diag = bcm_set_diag;
hu->hdev->set_bdaddr = btbcm_set_bdaddr;
- err = btbcm_initialize(hu->hdev, fw_name, sizeof(fw_name));
+ err = btbcm_initialize(hu->hdev, fw_name, sizeof(fw_name), false);
if (err)
return err;
{ },
};
-#ifdef CONFIG_ACPI
-/* IRQ polarity of some chipsets are not defined correctly in ACPI table. */
-static const struct dmi_system_id bcm_active_low_irq_dmi_table[] = {
- { /* Handle ThinkPad 8 tablets with BCM2E55 chipset ACPI ID */
- .ident = "Lenovo ThinkPad 8",
+/* Some firmware reports an IRQ which does not work (wrong pin in fw table?) */
+static const struct dmi_system_id bcm_broken_irq_dmi_table[] = {
+ {
+ .ident = "Meegopad T08",
.matches = {
- DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "ThinkPad 8"),
+ DMI_EXACT_MATCH(DMI_BOARD_VENDOR,
+ "To be filled by OEM."),
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "T3 MRD"),
+ DMI_EXACT_MATCH(DMI_BOARD_VERSION, "V1.1"),
},
},
{ }
};
+#ifdef CONFIG_ACPI
static int bcm_resource(struct acpi_resource *ares, void *data)
{
struct bcm_device *dev = data;
static int bcm_get_resources(struct bcm_device *dev)
{
+ const struct dmi_system_id *dmi_id;
+
dev->name = dev_name(dev->dev);
if (x86_apple_machine && !bcm_apple_get_resources(dev))
dev->irq = gpiod_to_irq(gpio);
}
+ dmi_id = dmi_first_match(bcm_broken_irq_dmi_table);
+ if (dmi_id) {
+ dev_info(dev->dev, "%s: Has a broken IRQ config, disabling IRQ support / runtime-pm\n",
+ dmi_id->ident);
+ dev->irq = 0;
+ }
+
dev_dbg(dev->dev, "BCM irq: %d\n", dev->irq);
return 0;
}
static int bcm_acpi_probe(struct bcm_device *dev)
{
LIST_HEAD(resources);
- const struct dmi_system_id *dmi_id;
const struct acpi_gpio_mapping *gpio_mapping = acpi_bcm_int_last_gpios;
struct resource_entry *entry;
int ret;
dev->irq_active_low = irq_polarity;
dev_warn(dev->dev, "Overwriting IRQ polarity to active %s by module-param\n",
dev->irq_active_low ? "low" : "high");
- } else {
- dmi_id = dmi_first_match(bcm_active_low_irq_dmi_table);
- if (dmi_id) {
- dev_warn(dev->dev, "%s: Overwriting IRQ polarity to active low",
- dmi_id->ident);
- dev->irq_active_low = true;
- }
}
return 0;
btbcm_check_bdaddr(hdev);
break;
#endif
+ default:
+ break;
}
done:
*/
#include <linux/kernel.h>
+#include <linux/clk.h>
#include <linux/debugfs.h>
+#include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/serdev.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
#define IBS_TX_IDLE_TIMEOUT_MS 2000
#define BAUDRATE_SETTLE_TIMEOUT_MS 300
+/* susclk rate */
+#define SUSCLK_RATE_32KHZ 32768
+
/* HCI_IBS transmit side sleep protocol states */
enum tx_ibs_states {
HCI_IBS_TX_ASLEEP,
u64 votes_off;
};
+struct qca_serdev {
+ struct hci_uart serdev_hu;
+ struct gpio_desc *bt_en;
+ struct clk *susclk;
+};
+
static void __serial_clock_on(struct tty_struct *tty)
{
/* TODO: Some chipset requires to enable UART clock on client
/* Initialize protocol */
static int qca_open(struct hci_uart *hu)
{
+ struct qca_serdev *qcadev;
struct qca_data *qca;
BT_DBG("hu %p qca_open", hu);
timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
+ if (hu->serdev) {
+ serdev_device_open(hu->serdev);
+
+ qcadev = serdev_device_get_drvdata(hu->serdev);
+ gpiod_set_value_cansleep(qcadev->bt_en, 1);
+ }
+
BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u",
qca->tx_idle_delay, qca->wake_retrans);
/* Close protocol */
static int qca_close(struct hci_uart *hu)
{
+ struct qca_serdev *qcadev;
struct qca_data *qca = hu->priv;
BT_DBG("hu %p qca close", hu);
destroy_workqueue(qca->workqueue);
qca->hu = NULL;
+ if (hu->serdev) {
+ serdev_device_close(hu->serdev);
+
+ qcadev = serdev_device_get_drvdata(hu->serdev);
+ gpiod_set_value_cansleep(qcadev->bt_en, 0);
+ }
+
kfree_skb(qca->rx_skb);
hu->priv = NULL;
return 0;
}
+static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed)
+{
+ if (hu->serdev)
+ serdev_device_set_baudrate(hu->serdev, speed);
+ else
+ hci_uart_set_baudrate(hu, speed);
+}
+
static int qca_setup(struct hci_uart *hu)
{
struct hci_dev *hdev = hu->hdev;
speed = hu->proto->init_speed;
if (speed)
- hci_uart_set_baudrate(hu, speed);
+ host_set_baudrate(hu, speed);
/* Setup user speed if needed */
speed = 0;
ret);
return ret;
}
- hci_uart_set_baudrate(hu, speed);
+ host_set_baudrate(hu, speed);
}
/* Setup patch / NVM configurations */
} else if (ret == -ENOENT) {
/* No patch/nvm-config found, run with original fw/config */
ret = 0;
+ } else if (ret == -EAGAIN) {
+ /*
+ * Userspace firmware loader will return -EAGAIN in case no
+ * patch/nvm-config is found, so run with original fw/config.
+ */
+ ret = 0;
}
/* Setup bdaddr */
.dequeue = qca_dequeue,
};
+static int qca_serdev_probe(struct serdev_device *serdev)
+{
+ struct qca_serdev *qcadev;
+ int err;
+
+ qcadev = devm_kzalloc(&serdev->dev, sizeof(*qcadev), GFP_KERNEL);
+ if (!qcadev)
+ return -ENOMEM;
+
+ qcadev->serdev_hu.serdev = serdev;
+ serdev_device_set_drvdata(serdev, qcadev);
+
+ qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable",
+ GPIOD_OUT_LOW);
+ if (IS_ERR(qcadev->bt_en)) {
+ dev_err(&serdev->dev, "failed to acquire enable gpio\n");
+ return PTR_ERR(qcadev->bt_en);
+ }
+
+ qcadev->susclk = devm_clk_get(&serdev->dev, NULL);
+ if (IS_ERR(qcadev->susclk)) {
+ dev_err(&serdev->dev, "failed to acquire clk\n");
+ return PTR_ERR(qcadev->susclk);
+ }
+
+ err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ);
+ if (err)
+ return err;
+
+ err = clk_prepare_enable(qcadev->susclk);
+ if (err)
+ return err;
+
+ err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
+ if (err)
+ clk_disable_unprepare(qcadev->susclk);
+
+ return err;
+}
+
+static void qca_serdev_remove(struct serdev_device *serdev)
+{
+ struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
+
+ hci_uart_unregister_device(&qcadev->serdev_hu);
+
+ clk_disable_unprepare(qcadev->susclk);
+}
+
+static const struct of_device_id qca_bluetooth_of_match[] = {
+ { .compatible = "qcom,qca6174-bt" },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match);
+
+static struct serdev_device_driver qca_serdev_driver = {
+ .probe = qca_serdev_probe,
+ .remove = qca_serdev_remove,
+ .driver = {
+ .name = "hci_uart_qca",
+ .of_match_table = qca_bluetooth_of_match,
+ },
+};
+
int __init qca_init(void)
{
+ serdev_device_driver_register(&qca_serdev_driver);
+
return hci_uart_register_proto(&qca_proto);
}
int __exit qca_deinit(void)
{
+ serdev_device_driver_unregister(&qca_serdev_driver);
+
return hci_uart_unregister_proto(&qca_proto);
}
bool "Support for ISA I/O space on HiSilicon Hip06/7"
depends on ARM64 && (ARCH_HISI || COMPILE_TEST)
select INDIRECT_PIO
+ select MFD_CORE if ACPI
help
Driver to enable I/O access to devices attached to the Low Pin
Count bus on the HiSilicon Hip06/7 SoC.
if (!CDROM_CAN(CDC_SELECT_DISC) || arg == CDSL_CURRENT)
return media_changed(cdi, 1);
- if ((unsigned int)arg >= cdi->capacity)
+ if (arg >= cdi->capacity)
return -EINVAL;
info = kmalloc(sizeof(*info), GFP_KERNEL);
return 0;
}
-int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
+static int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
{
size_t i;
u32 *gp;
return 0;
}
-void null_cache_flush(void)
+static void null_cache_flush(void)
{
mb();
}
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
+#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
* its value (from 0->1->2).
*/
static int crng_init = 0;
-#define crng_ready() (likely(crng_init > 0))
+#define crng_ready() (likely(crng_init > 1))
static int crng_init_cnt = 0;
+static unsigned long crng_global_init_time = 0;
#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
static void _extract_crng(struct crng_state *crng,
__u32 out[CHACHA20_BLOCK_WORDS]);
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);
+static struct ratelimit_state unseeded_warning =
+ RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
+static struct ratelimit_state urandom_warning =
+ RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
+
+static int ratelimit_disable __read_mostly;
+
+module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
+MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
+
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
}
+#ifdef CONFIG_NUMA
+static void do_numa_crng_init(struct work_struct *work)
+{
+ int i;
+ struct crng_state *crng;
+ struct crng_state **pool;
+
+ pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
+ for_each_online_node(i) {
+ crng = kmalloc_node(sizeof(struct crng_state),
+ GFP_KERNEL | __GFP_NOFAIL, i);
+ spin_lock_init(&crng->lock);
+ crng_initialize(crng);
+ pool[i] = crng;
+ }
+ mb();
+ if (cmpxchg(&crng_node_pool, NULL, pool)) {
+ for_each_node(i)
+ kfree(pool[i]);
+ kfree(pool);
+ }
+}
+
+static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+
+static void numa_crng_init(void)
+{
+ schedule_work(&numa_crng_init_work);
+}
+#else
+static void numa_crng_init(void) {}
+#endif
+
+/*
+ * crng_fast_load() can be called by code in the interrupt service
+ * path. So we can't afford to dilly-dally.
+ */
static int crng_fast_load(const char *cp, size_t len)
{
unsigned long flags;
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
return 0;
- if (crng_ready()) {
+ if (crng_init != 0) {
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 0;
}
return 1;
}
+/*
+ * crng_slow_load() is called by add_device_randomness, which has two
+ * attributes. (1) We can't trust the buffer passed to it is
+ * guaranteed to be unpredictable (so it might not have any entropy at
+ * all), and (2) it doesn't have the performance constraints of
+ * crng_fast_load().
+ *
+ * So we do something more comprehensive which is guaranteed to touch
+ * all of the primary_crng's state, and which uses a LFSR with a
+ * period of 255 as part of the mixing algorithm. Finally, we do
+ * *not* advance crng_init_cnt since buffer we may get may be something
+ * like a fixed DMI table (for example), which might very well be
+ * unique to the machine, but is otherwise unvarying.
+ */
+static int crng_slow_load(const char *cp, size_t len)
+{
+ unsigned long flags;
+ static unsigned char lfsr = 1;
+ unsigned char tmp;
+ unsigned i, max = CHACHA20_KEY_SIZE;
+ const char * src_buf = cp;
+ char * dest_buf = (char *) &primary_crng.state[4];
+
+ if (!spin_trylock_irqsave(&primary_crng.lock, flags))
+ return 0;
+ if (crng_init != 0) {
+ spin_unlock_irqrestore(&primary_crng.lock, flags);
+ return 0;
+ }
+ if (len > max)
+ max = len;
+
+ for (i = 0; i < max ; i++) {
+ tmp = lfsr;
+ lfsr >>= 1;
+ if (tmp & 1)
+ lfsr ^= 0xE1;
+ tmp = dest_buf[i % CHACHA20_KEY_SIZE];
+ dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
+ lfsr += (tmp << 3) | (tmp >> 5);
+ }
+ spin_unlock_irqrestore(&primary_crng.lock, flags);
+ return 1;
+}
+
static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
{
unsigned long flags;
_crng_backtrack_protect(&primary_crng, buf.block,
CHACHA20_KEY_SIZE);
}
- spin_lock_irqsave(&primary_crng.lock, flags);
+ spin_lock_irqsave(&crng->lock, flags);
for (i = 0; i < 8; i++) {
unsigned long rv;
if (!arch_get_random_seed_long(&rv) &&
}
memzero_explicit(&buf, sizeof(buf));
crng->init_time = jiffies;
- spin_unlock_irqrestore(&primary_crng.lock, flags);
+ spin_unlock_irqrestore(&crng->lock, flags);
if (crng == &primary_crng && crng_init < 2) {
invalidate_batched_entropy();
+ numa_crng_init();
crng_init = 2;
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
pr_notice("random: crng init done\n");
+ if (unseeded_warning.missed) {
+ pr_notice("random: %d get_random_xx warning(s) missed "
+ "due to ratelimiting\n",
+ unseeded_warning.missed);
+ unseeded_warning.missed = 0;
+ }
+ if (urandom_warning.missed) {
+ pr_notice("random: %d urandom warning(s) missed "
+ "due to ratelimiting\n",
+ urandom_warning.missed);
+ urandom_warning.missed = 0;
+ }
}
}
{
unsigned long v, flags;
- if (crng_init > 1 &&
- time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
+ if (crng_ready() &&
+ (time_after(crng_global_init_time, crng->init_time) ||
+ time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)))
crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL);
spin_lock_irqsave(&crng->lock, flags);
if (arch_get_random_long(&v))
unsigned long time = random_get_entropy() ^ jiffies;
unsigned long flags;
- if (!crng_ready()) {
- crng_fast_load(buf, size);
- return;
- }
+ if (!crng_ready() && size)
+ crng_slow_load(buf, size);
trace_add_device_randomness(size, _RET_IP_);
spin_lock_irqsave(&input_pool.lock, flags);
fast_mix(fast_pool);
add_interrupt_bench(cycles);
- if (!crng_ready()) {
+ if (unlikely(crng_init == 0)) {
if ((fast_pool->count >= 64) &&
crng_fast_load((char *) fast_pool->pool,
sizeof(fast_pool->pool))) {
#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
print_once = true;
#endif
- pr_notice("random: %s called from %pS with crng_init=%d\n",
- func_name, caller, crng_init);
+ if (__ratelimit(&unseeded_warning))
+ pr_notice("random: %s called from %pS with crng_init=%d\n",
+ func_name, caller, crng_init);
}
/*
*/
static int rand_initialize(void)
{
-#ifdef CONFIG_NUMA
- int i;
- struct crng_state *crng;
- struct crng_state **pool;
-#endif
-
init_std_data(&input_pool);
init_std_data(&blocking_pool);
crng_initialize(&primary_crng);
-
-#ifdef CONFIG_NUMA
- pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
- for_each_online_node(i) {
- crng = kmalloc_node(sizeof(struct crng_state),
- GFP_KERNEL | __GFP_NOFAIL, i);
- spin_lock_init(&crng->lock);
- crng_initialize(crng);
- pool[i] = crng;
+ crng_global_init_time = jiffies;
+ if (ratelimit_disable) {
+ urandom_warning.interval = 0;
+ unseeded_warning.interval = 0;
}
- mb();
- crng_node_pool = pool;
-#endif
return 0;
}
early_initcall(rand_initialize);
if (!crng_ready() && maxwarn > 0) {
maxwarn--;
- printk(KERN_NOTICE "random: %s: uninitialized urandom read "
- "(%zd bytes read)\n",
- current->comm, nbytes);
+ if (__ratelimit(&urandom_warning))
+ printk(KERN_NOTICE "random: %s: uninitialized "
+ "urandom read (%zd bytes read)\n",
+ current->comm, nbytes);
spin_lock_irqsave(&primary_crng.lock, flags);
crng_init_cnt = 0;
spin_unlock_irqrestore(&primary_crng.lock, flags);
input_pool.entropy_count = 0;
blocking_pool.entropy_count = 0;
return 0;
+ case RNDRESEEDCRNG:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (crng_init < 2)
+ return -ENODATA;
+ crng_reseed(&primary_crng, NULL);
+ crng_global_init_time = jiffies - 1;
+ return 0;
default:
return -EINVAL;
}
{
struct entropy_store *poolp = &input_pool;
- if (!crng_ready()) {
+ if (unlikely(crng_init == 0)) {
crng_fast_load(buffer, count);
return;
}
}
}
-static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size,
int pages)
{
struct port_buffer *buf;
return buf;
}
- if (is_rproc_serial(vq->vdev)) {
+ if (is_rproc_serial(vdev)) {
/*
* Allocate DMA memory from ancestor. When a virtio
* device is created by remoteproc, the DMA memory is
* associated with the grandparent device:
* vdev => rproc => platform-dev.
*/
- if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+ if (!vdev->dev.parent || !vdev->dev.parent->parent)
goto free_buf;
- buf->dev = vq->vdev->dev.parent->parent;
+ buf->dev = vdev->dev.parent->parent;
/* Increase device refcnt to avoid freeing it */
get_device(buf->dev);
count = min((size_t)(32 * 1024), count);
- buf = alloc_buf(port->out_vq, count, 0);
+ buf = alloc_buf(port->portdev->vdev, count, 0);
if (!buf)
return -ENOMEM;
if (ret < 0)
goto error_out;
- buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+ buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs);
if (!buf) {
ret = -ENOMEM;
goto error_out;
nr_added_bufs = 0;
do {
- buf = alloc_buf(vq, PAGE_SIZE, 0);
+ buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
if (!buf)
break;
{
char debugfs_name[16];
struct port *port;
- struct port_buffer *buf;
dev_t devt;
unsigned int nr_added_bufs;
int err;
return 0;
free_inbufs:
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf, true);
free_device:
device_destroy(pdrvdata.class, port->dev->devt);
free_cdev:
static void remove_port_data(struct port *port)
{
- struct port_buffer *buf;
-
spin_lock_irq(&port->inbuf_lock);
/* Remove unused data this port might have received. */
discard_port_data(port);
spin_unlock_irq(&port->inbuf_lock);
- /* Remove buffers we queued up for the Host to send us data in. */
- do {
- spin_lock_irq(&port->inbuf_lock);
- buf = virtqueue_detach_unused_buf(port->in_vq);
- spin_unlock_irq(&port->inbuf_lock);
- if (buf)
- free_buf(buf, true);
- } while (buf);
-
spin_lock_irq(&port->outvq_lock);
reclaim_consumed_buffers(port);
spin_unlock_irq(&port->outvq_lock);
-
- /* Free pending buffers from the out-queue. */
- do {
- spin_lock_irq(&port->outvq_lock);
- buf = virtqueue_detach_unused_buf(port->out_vq);
- spin_unlock_irq(&port->outvq_lock);
- if (buf)
- free_buf(buf, true);
- } while (buf);
}
/*
spin_unlock(&portdev->c_ivq_lock);
}
+static void flush_bufs(struct virtqueue *vq, bool can_sleep)
+{
+ struct port_buffer *buf;
+ unsigned int len;
+
+ while ((buf = virtqueue_get_buf(vq, &len)))
+ free_buf(buf, can_sleep);
+}
+
static void out_intr(struct virtqueue *vq)
{
struct port *port;
port = find_port_by_vq(vq->vdev->priv, vq);
- if (!port)
+ if (!port) {
+ flush_bufs(vq, false);
return;
+ }
wake_up_interruptible(&port->waitqueue);
}
unsigned long flags;
port = find_port_by_vq(vq->vdev->priv, vq);
- if (!port)
+ if (!port) {
+ flush_bufs(vq, false);
return;
+ }
spin_lock_irqsave(&port->inbuf_lock, flags);
port->inbuf = get_inbuf(port);
static void remove_vqs(struct ports_device *portdev)
{
+ struct virtqueue *vq;
+
+ virtio_device_for_each_vq(portdev->vdev, vq) {
+ struct port_buffer *buf;
+
+ flush_bufs(vq, true);
+ while ((buf = virtqueue_detach_unused_buf(vq)))
+ free_buf(buf, true);
+ }
portdev->vdev->config->del_vqs(portdev->vdev);
kfree(portdev->in_vqs);
kfree(portdev->out_vqs);
}
-static void remove_controlq_data(struct ports_device *portdev)
+static void virtcons_remove(struct virtio_device *vdev)
{
- struct port_buffer *buf;
- unsigned int len;
+ struct ports_device *portdev;
+ struct port *port, *port2;
- if (!use_multiport(portdev))
- return;
+ portdev = vdev->priv;
- while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
- free_buf(buf, true);
+ spin_lock_irq(&pdrvdata_lock);
+ list_del(&portdev->list);
+ spin_unlock_irq(&pdrvdata_lock);
- while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
- free_buf(buf, true);
+ /* Disable interrupts for vqs */
+ vdev->config->reset(vdev);
+ /* Finish up work that's lined up */
+ if (use_multiport(portdev))
+ cancel_work_sync(&portdev->control_work);
+ else
+ cancel_work_sync(&portdev->config_work);
+
+ list_for_each_entry_safe(port, port2, &portdev->ports, list)
+ unplug_port(port);
+
+ unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+ /*
+ * When yanking out a device, we immediately lose the
+ * (device-side) queues. So there's no point in keeping the
+ * guest side around till we drop our final reference. This
+ * also means that any ports which are in an open state will
+ * have to just stop using the port, as the vqs are going
+ * away.
+ */
+ remove_vqs(portdev);
+ kfree(portdev);
}
/*
spin_lock_init(&portdev->ports_lock);
INIT_LIST_HEAD(&portdev->ports);
+ INIT_LIST_HEAD(&portdev->list);
virtio_device_ready(portdev->vdev);
if (!nr_added_bufs) {
dev_err(&vdev->dev,
"Error allocating buffers for control queue\n");
- err = -ENOMEM;
- goto free_vqs;
+ /*
+ * The host might want to notify mgmt sw about device
+ * add failure.
+ */
+ __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+ VIRTIO_CONSOLE_DEVICE_READY, 0);
+ /* Device was functional: we need full cleanup. */
+ virtcons_remove(vdev);
+ return -ENOMEM;
}
} else {
/*
return 0;
-free_vqs:
- /* The host might want to notify mgmt sw about device add failure */
- __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
- VIRTIO_CONSOLE_DEVICE_READY, 0);
- remove_vqs(portdev);
free_chrdev:
unregister_chrdev(portdev->chr_major, "virtio-portsdev");
free:
return err;
}
-static void virtcons_remove(struct virtio_device *vdev)
-{
- struct ports_device *portdev;
- struct port *port, *port2;
-
- portdev = vdev->priv;
-
- spin_lock_irq(&pdrvdata_lock);
- list_del(&portdev->list);
- spin_unlock_irq(&pdrvdata_lock);
-
- /* Disable interrupts for vqs */
- vdev->config->reset(vdev);
- /* Finish up work that's lined up */
- if (use_multiport(portdev))
- cancel_work_sync(&portdev->control_work);
- else
- cancel_work_sync(&portdev->config_work);
-
- list_for_each_entry_safe(port, port2, &portdev->ports, list)
- unplug_port(port);
-
- unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
- /*
- * When yanking out a device, we immediately lose the
- * (device-side) queues. So there's no point in keeping the
- * guest side around till we drop our final reference. This
- * also means that any ports which are in an open state will
- * have to just stop using the port, as the vqs are going
- * away.
- */
- remove_controlq_data(portdev);
- remove_vqs(portdev);
- kfree(portdev);
-}
-
static struct virtio_device_id id_table[] = {
{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
{ 0 },
*/
if (use_multiport(portdev))
virtqueue_disable_cb(portdev->c_ivq);
- remove_controlq_data(portdev);
list_for_each_entry(port, &portdev->ports, list) {
virtqueue_disable_cb(port->in_vq);
Support for stm32mp157 SoC family clocks
config COMMON_CLK_STM32F
- bool "Clock driver for stm32f4 and stm32f7 SoC families"
- depends on MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746
+ def_bool COMMON_CLK && (MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746)
help
---help---
Support for stm32f4 and stm32f7 SoC families clocks
config COMMON_CLK_STM32H7
- bool "Clock driver for stm32h7 SoC family"
- depends on MACH_STM32H743
+ def_bool COMMON_CLK && MACH_STM32H743
help
---help---
Support for stm32h7 SoC family clocks
return ret;
}
-static int cs2000_resume(struct device *dev)
+static int __maybe_unused cs2000_resume(struct device *dev)
{
struct cs2000_priv *priv = dev_get_drvdata(dev);
return 0;
}
+static int clk_mux_determine_rate(struct clk_hw *hw,
+ struct clk_rate_request *req)
+{
+ struct clk_mux *mux = to_clk_mux(hw);
+
+ return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
const struct clk_ops clk_mux_ops = {
.get_parent = clk_mux_get_parent,
.set_parent = clk_mux_set_parent,
- .determine_rate = __clk_mux_determine_rate,
+ .determine_rate = clk_mux_determine_rate,
};
EXPORT_SYMBOL_GPL(clk_mux_ops);
"pclk5", "pll3_q", "ck_hsi", "ck_csi", "pll4_q", "ck_hse"
};
-const char * const usart234578_src[] = {
+static const char * const usart234578_src[] = {
"pclk1", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
};
"pclk2", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
};
-static const char * const dfsdm_src[] = {
- "pclk2", "ck_mcu"
-};
-
static const char * const fdcan_src[] = {
"ck_hse", "pll3_q", "pll4_q"
};
struct clock_config {
u32 id;
const char *name;
- union {
- const char *parent_name;
- const char * const *parent_names;
- };
+ const char *parent_name;
+ const char * const *parent_names;
int num_parents;
unsigned long flags;
void *cfg;
}
}
-const struct clk_ops mp1_gate_clk_ops = {
+static const struct clk_ops mp1_gate_clk_ops = {
.enable = mp1_gate_clk_enable,
.disable = mp1_gate_clk_disable,
.is_enabled = clk_gate_is_enabled,
mp1_gate_clk_disable(hw);
}
-const struct clk_ops mp1_mgate_clk_ops = {
+static const struct clk_ops mp1_mgate_clk_ops = {
.enable = mp1_mgate_clk_enable,
.disable = mp1_mgate_clk_disable,
.is_enabled = clk_gate_is_enabled,
return 0;
}
-const struct clk_ops clk_mmux_ops = {
+static const struct clk_ops clk_mmux_ops = {
.get_parent = clk_mmux_get_parent,
.set_parent = clk_mmux_set_parent,
.determine_rate = __clk_mux_determine_rate,
u32 offset;
};
-struct clk_hw *_clk_register_pll(struct device *dev,
- struct clk_hw_onecell_data *clk_data,
- void __iomem *base, spinlock_t *lock,
- const struct clock_config *cfg)
+static struct clk_hw *_clk_register_pll(struct device *dev,
+ struct clk_hw_onecell_data *clk_data,
+ void __iomem *base, spinlock_t *lock,
+ const struct clock_config *cfg)
{
struct stm32_pll_cfg *stm_pll_cfg = cfg->cfg;
G_USBH,
G_ETHSTP,
G_RTCAPB,
- G_TZC,
+ G_TZC1,
+ G_TZC2,
G_TZPC,
G_IWDG1,
G_BSEC,
G_LAST
};
-struct stm32_mgate mp1_mgate[G_LAST];
+static struct stm32_mgate mp1_mgate[G_LAST];
#define _K_GATE(_id, _gate_offset, _gate_bit_idx, _gate_flags,\
_mgate, _ops)\
&mp1_mgate[_id], &mp1_mgate_clk_ops)
/* Peripheral gates */
-struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
+static struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
/* Multi gates */
K_GATE(G_MDIO, RCC_APB1ENSETR, 31, 0),
K_MGATE(G_DAC12, RCC_APB1ENSETR, 29, 0),
K_GATE(G_BSEC, RCC_APB5ENSETR, 16, 0),
K_GATE(G_IWDG1, RCC_APB5ENSETR, 15, 0),
K_GATE(G_TZPC, RCC_APB5ENSETR, 13, 0),
- K_GATE(G_TZC, RCC_APB5ENSETR, 12, 0),
+ K_GATE(G_TZC2, RCC_APB5ENSETR, 12, 0),
+ K_GATE(G_TZC1, RCC_APB5ENSETR, 11, 0),
K_GATE(G_RTCAPB, RCC_APB5ENSETR, 8, 0),
K_MGATE(G_USART1, RCC_APB5ENSETR, 4, 0),
K_MGATE(G_I2C6, RCC_APB5ENSETR, 3, 0),
M_LAST
};
-struct stm32_mmux ker_mux[M_LAST];
+static struct stm32_mmux ker_mux[M_LAST];
#define _K_MUX(_id, _offset, _shift, _width, _mux_flags, _mmux, _ops)\
[_id] = {\
_K_MUX(_id, _offset, _shift, _width, _mux_flags,\
&ker_mux[_id], &clk_mmux_ops)
-const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
+static const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
/* Kernel multi mux */
K_MMUX(M_SDMMC12, RCC_SDMMC12CKSELR, 0, 3, 0),
K_MMUX(M_SPI23, RCC_SPI2S23CKSELR, 0, 3, 0),
PCLK(USART1, "usart1", "pclk5", 0, G_USART1),
PCLK(RTCAPB, "rtcapb", "pclk5", CLK_IGNORE_UNUSED |
CLK_IS_CRITICAL, G_RTCAPB),
- PCLK(TZC, "tzc", "pclk5", CLK_IGNORE_UNUSED, G_TZC),
+ PCLK(TZC1, "tzc1", "ck_axi", CLK_IGNORE_UNUSED, G_TZC1),
+ PCLK(TZC2, "tzc2", "ck_axi", CLK_IGNORE_UNUSED, G_TZC2),
PCLK(TZPC, "tzpc", "pclk5", CLK_IGNORE_UNUSED, G_TZPC),
PCLK(IWDG1, "iwdg1", "pclk5", 0, G_IWDG1),
PCLK(BSEC, "bsec", "pclk5", CLK_IGNORE_UNUSED, G_BSEC),
KCLK(RNG1_K, "rng1_k", rng_src, 0, G_RNG1, M_RNG1),
KCLK(RNG2_K, "rng2_k", rng_src, 0, G_RNG2, M_RNG2),
KCLK(USBPHY_K, "usbphy_k", usbphy_src, 0, G_USBPHY, M_USBPHY),
- KCLK(STGEN_K, "stgen_k", stgen_src, CLK_IGNORE_UNUSED,
- G_STGEN, M_STGEN),
+ KCLK(STGEN_K, "stgen_k", stgen_src, CLK_IS_CRITICAL, G_STGEN, M_STGEN),
KCLK(SPDIF_K, "spdif_k", spdif_src, 0, G_SPDIF, M_SPDIF),
KCLK(SPI1_K, "spi1_k", spi123_src, 0, G_SPI1, M_SPI1),
KCLK(SPI2_K, "spi2_k", spi123_src, 0, G_SPI2, M_SPI23),
KCLK(FDCAN_K, "fdcan_k", fdcan_src, 0, G_FDCAN, M_FDCAN),
KCLK(SAI1_K, "sai1_k", sai_src, 0, G_SAI1, M_SAI1),
KCLK(SAI2_K, "sai2_k", sai2_src, 0, G_SAI2, M_SAI2),
- KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI2, M_SAI3),
- KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI2, M_SAI4),
+ KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI3, M_SAI3),
+ KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI4, M_SAI4),
KCLK(ADC12_K, "adc12_k", adc12_src, 0, G_ADC12, M_ADC12),
KCLK(DSI_K, "dsi_k", dsi_src, 0, G_DSI, M_DSI),
KCLK(ADFSDM_K, "adfsdm_k", sai_src, 0, G_ADFSDM, M_SAI1),
_DIV(RCC_MCO2CFGR, 4, 4, 0, NULL)),
/* Debug clocks */
- FIXED_FACTOR(NO_ID, "ck_axi_div2", "ck_axi", 0, 1, 2),
-
- GATE(DBG, "ck_apb_dbg", "ck_axi_div2", 0, RCC_DBGCFGR, 8, 0),
-
GATE(CK_DBG, "ck_sys_dbg", "ck_axi", 0, RCC_DBGCFGR, 8, 0),
COMPOSITE(CK_TRACE, "ck_trace", ck_trace_src, CLK_OPS_PARENT_ENABLE,
return now <= rate && now > best;
}
-static int
-clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req,
- unsigned long flags)
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+ struct clk_rate_request *req,
+ unsigned long flags)
{
struct clk_core *core = hw->core, *parent, *best_parent = NULL;
int i, num_parents, ret;
return 0;
}
+EXPORT_SYMBOL_GPL(clk_mux_determine_rate_flags);
struct clk *__clk_lookup(const char *name)
{
clk_set_rate(clks[IMX6UL_CLK_AHB], 99000000);
/* Change periph_pre clock to pll2_bus to adjust AXI rate to 264MHz */
- clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_PLL3_USB_OTG]);
+ clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_OSC]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_CLK2]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH_PRE], clks[IMX6UL_CLK_PLL2_BUS]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_PRE]);
val << mux->shift);
}
+static int clk_regmap_mux_determine_rate(struct clk_hw *hw,
+ struct clk_rate_request *req)
+{
+ struct clk_regmap *clk = to_clk_regmap(hw);
+ struct clk_regmap_mux_data *mux = clk_get_regmap_mux_data(clk);
+
+ return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
const struct clk_ops clk_regmap_mux_ops = {
.get_parent = clk_regmap_mux_get_parent,
.set_parent = clk_regmap_mux_set_parent,
- .determine_rate = __clk_mux_determine_rate,
+ .determine_rate = clk_regmap_mux_determine_rate,
};
EXPORT_SYMBOL_GPL(clk_regmap_mux_ops);
#define AO_RTC_ALT_CLK_CNTL0 0x94
#define AO_RTC_ALT_CLK_CNTL1 0x98
-extern const struct clk_ops meson_aoclk_gate_regmap_ops;
-
struct aoclk_cec_32k {
struct clk_hw hw;
struct regmap *regmap;
.mult = 1,
.div = 3,
.hw.init = &(struct clk_init_data){
- .name = "fclk_div_div3",
+ .name = "fclk_div3_div",
.ops = &clk_fixed_factor_ops,
.parent_names = (const char *[]){ "fixed_pll" },
.num_parents = 1,
.hw.init = &(struct clk_init_data){
.name = "cpu_clk",
.ops = &clk_regmap_mux_ro_ops,
- .parent_names = (const char *[]){ "xtal", "cpu_out_sel" },
+ .parent_names = (const char *[]){ "xtal",
+ "cpu_scale_out_sel" },
.num_parents = 2,
.flags = (CLK_SET_RATE_PARENT |
CLK_SET_RATE_NO_REPARENT),
* of writing CNT registers which may cause the min_delta event got
* missed, so we need add a ETIME check here in case it happened.
*/
- return (int)((next - now) <= 0) ? -ETIME : 0;
+ return (int)(next - now) <= 0 ? -ETIME : 0;
}
static int tpm_set_state_oneshot(struct clock_event_device *evt)
ev->what = PROC_EVENT_COREDUMP;
ev->event_data.coredump.process_pid = task->pid;
ev->event_data.coredump.process_tgid = task->tgid;
+ ev->event_data.coredump.parent_pid = task->real_parent->pid;
+ ev->event_data.coredump.parent_tgid = task->real_parent->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
ev->event_data.exit.process_tgid = task->tgid;
ev->event_data.exit.exit_code = task->exit_code;
ev->event_data.exit.exit_signal = task->exit_signal;
+ ev->event_data.exit.parent_pid = task->real_parent->pid;
+ ev->event_data.exit.parent_tgid = task->real_parent->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
config ARM_ARMADA_37XX_CPUFREQ
tristate "Armada 37xx CPUFreq support"
- depends on ARCH_MVEBU
+ depends on ARCH_MVEBU && CPUFREQ_DT
help
This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
The Armada 37xx PMU supports 4 frequency and VDD levels.
Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS.
-config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- bool "Broadcom STB AVS CPUfreq driver sysfs debug capability"
- depends on ARM_BRCMSTB_AVS_CPUFREQ
- help
- Enabling this option turns on debug support via sysfs under
- /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and
- write some AVS mailbox registers through sysfs entries.
-
- If in doubt, say N.
-
config ARM_EXYNOS5440_CPUFREQ
tristate "SAMSUNG EXYNOS5440"
depends on SOC_EXYNOS5440
#include <linux/platform_device.h>
#include <linux/semaphore.h>
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#endif
-
/* Max number of arguments AVS calls take */
#define AVS_MAX_CMD_ARGS 4
/*
void __iomem *base;
void __iomem *avs_intr_base;
struct device *dev;
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- struct dentry *debugfs;
-#endif
struct completion done;
struct semaphore sem;
struct pmap pmap;
};
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-enum debugfs_format {
- DEBUGFS_NORMAL,
- DEBUGFS_FLOAT,
- DEBUGFS_REV,
-};
-
-struct debugfs_data {
- struct debugfs_entry *entry;
- struct private_data *priv;
-};
-
-struct debugfs_entry {
- char *name;
- u32 offset;
- fmode_t mode;
- enum debugfs_format format;
-};
-
-#define DEBUGFS_ENTRY(name, mode, format) { \
- #name, AVS_MBOX_##name, mode, format \
-}
-
-/*
- * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly.
- */
-#define AVS_MBOX_PARAM1 AVS_MBOX_PARAM(0)
-#define AVS_MBOX_PARAM2 AVS_MBOX_PARAM(1)
-#define AVS_MBOX_PARAM3 AVS_MBOX_PARAM(2)
-#define AVS_MBOX_PARAM4 AVS_MBOX_PARAM(3)
-
-/*
- * This table stores the name, access permissions and offset for each hardware
- * register and is used to generate debugfs entries.
- */
-static struct debugfs_entry debugfs_entries[] = {
- DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV),
- DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL),
-};
-
-static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int);
-
-static char *__strtolower(char *s)
-{
- char *p;
-
- for (p = s; *p; p++)
- *p = tolower(*p);
-
- return s;
-}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
static void __iomem *__map_region(const char *name)
{
struct device_node *np;
return table;
}
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-#define MANT(x) (unsigned int)(abs((x)) / 1000)
-#define FRAC(x) (unsigned int)(abs((x)) - abs((x)) / 1000 * 1000)
-
-static int brcm_avs_debug_show(struct seq_file *s, void *data)
-{
- struct debugfs_data *dbgfs = s->private;
- void __iomem *base;
- u32 val, offset;
-
- if (!dbgfs) {
- seq_puts(s, "No device pointer\n");
- return 0;
- }
-
- base = dbgfs->priv->base;
- offset = dbgfs->entry->offset;
- val = readl(base + offset);
- switch (dbgfs->entry->format) {
- case DEBUGFS_NORMAL:
- seq_printf(s, "%u\n", val);
- break;
- case DEBUGFS_FLOAT:
- seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val));
- break;
- case DEBUGFS_REV:
- seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff),
- (val >> 16 & 0xff), (val >> 8 & 0xff),
- val & 0xff);
- break;
- }
- seq_printf(s, "0x%08x\n", val);
-
- return 0;
-}
-
-#undef MANT
-#undef FRAC
-
-static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf,
- size_t size, loff_t *ppos)
-{
- struct seq_file *s = file->private_data;
- struct debugfs_data *dbgfs = s->private;
- struct private_data *priv = dbgfs->priv;
- void __iomem *base, *avs_intr_base;
- bool use_issue_command = false;
- unsigned long val, offset;
- char str[128];
- int ret;
- char *str_ptr = str;
-
- if (size >= sizeof(str))
- return -E2BIG;
-
- memset(str, 0, sizeof(str));
- ret = copy_from_user(str, buf, size);
- if (ret)
- return ret;
-
- base = priv->base;
- avs_intr_base = priv->avs_intr_base;
- offset = dbgfs->entry->offset;
- /*
- * Special case writing to "command" entry only: if the string starts
- * with a 'c', we use the driver's __issue_avs_command() function.
- * Otherwise, we perform a raw write. This should allow testing of raw
- * access as well as using the higher level function. (Raw access
- * doesn't clear the firmware return status after issuing the command.)
- */
- if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) {
- use_issue_command = true;
- str_ptr++;
- }
- if (kstrtoul(str_ptr, 0, &val) != 0)
- return -EINVAL;
-
- /*
- * Setting the P-state is a special case. We need to update the CPU
- * frequency we report.
- */
- if (val == AVS_CMD_SET_PSTATE) {
- struct cpufreq_policy *policy;
- unsigned int pstate;
-
- policy = cpufreq_cpu_get(smp_processor_id());
- /* Read back the P-state we are about to set */
- pstate = readl(base + AVS_MBOX_PARAM(0));
- if (use_issue_command) {
- ret = brcm_avs_target_index(policy, pstate);
- return ret ? ret : size;
- }
- policy->cur = policy->freq_table[pstate].frequency;
- }
-
- if (use_issue_command) {
- ret = __issue_avs_command(priv, val, false, NULL);
- } else {
- /* Locking here is not perfect, but is only for debug. */
- ret = down_interruptible(&priv->sem);
- if (ret)
- return ret;
-
- writel(val, base + offset);
- /* We have to wake up the firmware to process a command. */
- if (offset == AVS_MBOX_COMMAND)
- writel(AVS_CPU_L2_INT_MASK,
- avs_intr_base + AVS_CPU_L2_SET0);
- up(&priv->sem);
- }
-
- return ret ? ret : size;
-}
-
-static struct debugfs_entry *__find_debugfs_entry(const char *name)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++)
- if (strcasecmp(debugfs_entries[i].name, name) == 0)
- return &debugfs_entries[i];
-
- return NULL;
-}
-
-static int brcm_avs_debug_open(struct inode *inode, struct file *file)
-{
- struct debugfs_data *data;
- fmode_t fmode;
- int ret;
-
- /*
- * seq_open(), which is called by single_open(), clears "write" access.
- * We need write access to some files, so we preserve our access mode
- * and restore it.
- */
- fmode = file->f_mode;
- /*
- * Check access permissions even for root. We don't want to be writing
- * to read-only registers. Access for regular users has already been
- * checked by the VFS layer.
- */
- if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR))
- return -EACCES;
-
- data = kmalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
- /*
- * We use the same file system operations for all our debug files. To
- * produce specific output, we look up the file name upon opening a
- * debugfs entry and map it to a memory offset. This offset is then used
- * in the generic "show" function to read a specific register.
- */
- data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname);
- data->priv = inode->i_private;
-
- ret = single_open(file, brcm_avs_debug_show, data);
- if (ret)
- kfree(data);
- file->f_mode = fmode;
-
- return ret;
-}
-
-static int brcm_avs_debug_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq_priv = file->private_data;
- struct debugfs_data *data = seq_priv->private;
-
- kfree(data);
- return single_release(inode, file);
-}
-
-static const struct file_operations brcm_avs_debug_ops = {
- .open = brcm_avs_debug_open,
- .read = seq_read,
- .write = brcm_avs_seq_write,
- .llseek = seq_lseek,
- .release = brcm_avs_debug_release,
-};
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
- struct dentry *dir;
- int i;
-
- if (!priv)
- return;
-
- dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL);
- if (IS_ERR_OR_NULL(dir))
- return;
- priv->debugfs = dir;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) {
- /*
- * The DEBUGFS_ENTRY macro generates uppercase strings. We
- * convert them to lowercase before creating the debugfs
- * entries.
- */
- char *entry = __strtolower(debugfs_entries[i].name);
- fmode_t mode = debugfs_entries[i].mode;
-
- if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode,
- dir, priv, &brcm_avs_debug_ops)) {
- priv->debugfs = NULL;
- debugfs_remove_recursive(dir);
- break;
- }
- }
-}
-
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
-
- if (priv && priv->debugfs) {
- debugfs_remove_recursive(priv->debugfs);
- priv->debugfs = NULL;
- }
-}
-
-#else
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {}
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
/*
* To ensure the right firmware is running we need to
* - check the MAGIC matches what we expect
return ret;
brcm_avs_driver.driver_data = pdev;
- ret = cpufreq_register_driver(&brcm_avs_driver);
- if (!ret)
- brcm_avs_cpufreq_debug_init(pdev);
- return ret;
+ return cpufreq_register_driver(&brcm_avs_driver);
}
static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
if (ret)
return ret;
- brcm_avs_cpufreq_debug_exit(pdev);
-
priv = platform_get_drvdata(pdev);
iounmap(priv->base);
iounmap(priv->avs_intr_base);
cpu->perf_caps.lowest_perf, cpu_num, ret);
}
+/*
+ * The PCC subspace describes the rate at which platform can accept commands
+ * on the shared PCC channel (including READs which do not count towards freq
+ * trasition requests), so ideally we need to use the PCC values as a fallback
+ * if we don't have a platform specific transition_delay_us
+ */
+#ifdef CONFIG_ARM64
+#include <asm/cputype.h>
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+ unsigned long implementor = read_cpuid_implementor();
+ unsigned long part_num = read_cpuid_part_number();
+ unsigned int delay_us = 0;
+
+ switch (implementor) {
+ case ARM_CPU_IMP_QCOM:
+ switch (part_num) {
+ case QCOM_CPU_PART_FALKOR_V1:
+ case QCOM_CPU_PART_FALKOR:
+ delay_us = 10000;
+ break;
+ default:
+ delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+ break;
+ }
+ break;
+ default:
+ delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+ break;
+ }
+
+ return delay_us;
+}
+
+#else
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+ return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+}
+#endif
+
static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
struct cppc_cpudata *cpu;
cpu->perf_caps.highest_perf;
policy->cpuinfo.max_freq = cppc_dmi_max_khz;
- policy->transition_delay_us = cppc_get_transition_latency(cpu_num) /
- NSEC_PER_USEC;
+ policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num);
policy->shared_type = cpu->shared_type;
if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
if (!spin_trylock(&gpstates->gpstate_lock))
return;
+ /*
+ * If the timer has migrated to the different cpu then bring
+ * it back to one of the policy->cpus
+ */
+ if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
+ gpstates->timer.expires = jiffies + msecs_to_jiffies(1);
+ add_timer_on(&gpstates->timer, cpumask_first(policy->cpus));
+ spin_unlock(&gpstates->gpstate_lock);
+ return;
+ }
/*
* If PMCR was last updated was using fast_swtich then
if (gpstate_idx != gpstates->last_lpstate_idx)
queue_gpstate_timer(gpstates);
+ set_pstate(&freq_data);
spin_unlock(&gpstates->gpstate_lock);
-
- /* Timer may get migrated to a different cpu on cpu hot unplug */
- smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
}
/*
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/mman.h>
#include "dax-private.h"
#include "dax.h"
.release = dax_release,
.get_unmapped_area = dax_get_unmapped_area,
.mmap = dax_mmap,
+ .mmap_supported_flags = MAP_SYNC,
};
static void dev_dax_release(struct device *dev)
return 0;
}
+static int bam_pm_runtime_get_sync(struct device *dev)
+{
+ if (pm_runtime_enabled(dev))
+ return pm_runtime_get_sync(dev);
+
+ return 0;
+}
+
/**
* bam_free_chan - Frees dma resources associated with specific channel
* @chan: specified channel
unsigned long flags;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return;
unsigned long flag;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
unsigned long flag;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
if (srcs & P_IRQ)
tasklet_schedule(&bdev->task);
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
if (!vd)
return;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return;
struct clock_info *ci = handle->clk_priv;
struct scmi_clock_info *clk = ci->clk + clk_id;
- if (!clk->name || !clk->name[0])
+ if (!clk->name[0])
return NULL;
return clk;
if (scmi_mbox_chan_setup(info, &sdev->dev, prot_id)) {
dev_err(&sdev->dev, "failed to setup transport\n");
scmi_device_destroy(sdev);
+ return;
}
/* setup handle now as the transport is ready */
u32 offset = !IS_ENABLED(CONFIG_DEBUG_ALIGN_RODATA) ?
(phys_seed >> 32) & mask : TEXT_OFFSET;
+ /*
+ * With CONFIG_RANDOMIZE_TEXT_OFFSET=y, TEXT_OFFSET may not
+ * be a multiple of EFI_KIMG_ALIGN, and we must ensure that
+ * we preserve the misalignment of 'offset' relative to
+ * EFI_KIMG_ALIGN so that statically allocated objects whose
+ * alignment exceeds PAGE_SIZE appear correctly aligned in
+ * memory.
+ */
+ offset |= TEXT_OFFSET % EFI_KIMG_ALIGN;
+
/*
* If KASLR is enabled, and we have some randomness available,
* locate the kernel at a randomized offset in physical memory.
conf->data = of_id->data;
conf->spi = spi;
- conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_HIGH);
+ conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_LOW);
if (IS_ERR(conf->config)) {
dev_err(&spi->dev, "Failed to get config gpio: %ld\n",
PTR_ERR(conf->config));
if (set)
reg |= bit;
else
- reg &= bit;
+ reg &= ~bit;
iowrite32(reg, addr);
spin_unlock_irqrestore(&gpio->lock, flags);
unsigned long word_mask;
const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
unsigned long port_state;
- u8 __iomem ports[] = {
- idio16gpio->reg->out0_7, idio16gpio->reg->out8_15,
- idio16gpio->reg->in0_7, idio16gpio->reg->in8_15,
+ void __iomem *ports[] = {
+ &idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
+ &idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15,
};
/* clear bits array to a clean slate */
}
/* read bits from current gpio port */
- port_state = ioread8(ports + i);
+ port_state = ioread8(ports[i]);
/* store acquired bits at respective bits array offset */
bits[word_index] |= port_state << word_offset;
unsigned long word_mask;
const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
unsigned long port_state;
- u8 __iomem ports[] = {
- idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
- idio24gpio->reg->out16_23, idio24gpio->reg->in0_7,
- idio24gpio->reg->in8_15, idio24gpio->reg->in16_23,
+ void __iomem *ports[] = {
+ &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+ &idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7,
+ &idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23,
};
const unsigned long out_mode_mask = BIT(1);
bitmap_zero(bits, chip->ngpio);
/* get bits are evaluated a gpio port register at a time */
- for (i = 0; i < ARRAY_SIZE(ports); i++) {
+ for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) {
/* gpio offset in bits array */
bits_offset = i * gpio_reg_size;
/* read bits from current gpio port (port 6 is TTL GPIO) */
if (i < 6)
- port_state = ioread8(ports + i);
+ port_state = ioread8(ports[i]);
else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
port_state = ioread8(&idio24gpio->reg->ttl_out0_7);
else
const unsigned long port_mask = GENMASK(gpio_reg_size, 0);
unsigned long flags;
unsigned int out_state;
- u8 __iomem ports[] = {
- idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
- idio24gpio->reg->out16_23
+ void __iomem *ports[] = {
+ &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+ &idio24gpio->reg->out16_23
};
const unsigned long out_mode_mask = BIT(1);
const unsigned int ttl_offset = 48;
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
/* process output lines */
- out_state = ioread8(ports + i) & ~gpio_mask;
+ out_state = ioread8(ports[i]) & ~gpio_mask;
out_state |= (*bits >> bits_offset) & gpio_mask;
- iowrite8(out_state, ports + i);
+ iowrite8(out_state, ports[i]);
raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
}
struct gpiohandle_request handlereq;
struct linehandle_state *lh;
struct file *file;
- int fd, i, ret;
+ int fd, i, count = 0, ret;
u32 lflags;
if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
if (ret)
goto out_free_descs;
lh->descs[i] = desc;
+ count = i;
if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
set_bit(FLAG_ACTIVE_LOW, &desc->flags);
out_put_unused_fd:
put_unused_fd(fd);
out_free_descs:
- for (; i >= 0; i--)
+ for (i = 0; i < count; i++)
gpiod_free(lh->descs[i]);
kfree(lh->label);
out_free_lh:
desc = &gdev->descs[offset];
ret = gpiod_request(desc, le->label);
if (ret)
- goto out_free_desc;
+ goto out_free_label;
le->desc = desc;
le->eflags = eflags;
if (other) {
signed long r;
- r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+ r = dma_fence_wait(other, true);
if (r < 0) {
- DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+
return r;
}
}
static const u32 vgpr_init_regs[] =
{
mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0xffffffff,
- mmCOMPUTE_RESOURCE_LIMITS, 0,
+ mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
mmCOMPUTE_NUM_THREAD_X, 256*4,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x100004f, /* VGPRS=15 (64 logical VGPRs), SGPRS=1 (16 SGPRs), BULKY=1 */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
static const u32 sgpr1_init_regs[] =
{
mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0x0f,
- mmCOMPUTE_RESOURCE_LIMITS, 0x1000000,
+ mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
mmCOMPUTE_NUM_THREAD_X, 256*5,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
mmCOMPUTE_NUM_THREAD_X, 256*5,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
tristate "HSA kernel driver for AMD GPU devices"
depends on DRM_AMDGPU && X86_64
imply AMD_IOMMU_V2
+ select MMU_NOTIFIER
help
Enable this if you want to use HSA features on AMD GPU devices.
struct timespec64 time;
dev = kfd_device_by_id(args->gpu_id);
- if (dev == NULL)
- return -EINVAL;
-
- /* Reading GPU clock counter from KGD */
- args->gpu_clock_counter =
- dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+ if (dev)
+ /* Reading GPU clock counter from KGD */
+ args->gpu_clock_counter =
+ dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+ else
+ /* Node without GPU resource */
+ args->gpu_clock_counter = 0;
/* No access to rdtsc. Using raw monotonic time */
getrawmonotonic64(&time);
return ret;
}
-bool kfd_dev_is_large_bar(struct kfd_dev *dev)
+static bool kfd_dev_is_large_bar(struct kfd_dev *dev)
{
struct kfd_local_mem_info mem_info;
pdd = kfd_get_process_device_data(dev, p);
if (!pdd) {
- err = PTR_ERR(pdd);
+ err = -EINVAL;
goto bind_process_to_device_failed;
}
struct amdgpu_dm_connector *aconnector = NULL;
struct drm_connector_state *new_con_state = NULL;
struct dm_connector_state *dm_conn_state = NULL;
+ struct drm_plane_state *new_plane_state = NULL;
new_stream = NULL;
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
acrtc = to_amdgpu_crtc(crtc);
+ new_plane_state = drm_atomic_get_new_plane_state(state, new_crtc_state->crtc->primary);
+
+ if (new_crtc_state->enable && new_plane_state && !new_plane_state->fb) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
aconnector = amdgpu_dm_find_first_crtc_matching_connector(state, crtc);
/* TODO This hack should go away */
if (!dm_old_crtc_state->stream)
continue;
- DRM_DEBUG_DRIVER("Disabling DRM plane: %d on DRM crtc %d\n",
+ DRM_DEBUG_ATOMIC("Disabling DRM plane: %d on DRM crtc %d\n",
plane->base.id, old_plane_crtc->base.id);
if (!dc_remove_plane_from_context(
lut = (struct drm_color_lut *)blob->data;
lut_size = blob->length / sizeof(struct drm_color_lut);
- if (__is_lut_linear(lut, lut_size)) {
- /* Set to bypass if lut is set to linear */
- stream->out_transfer_func->type = TF_TYPE_BYPASS;
- stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
- return 0;
- }
-
gamma = dc_create_gamma();
if (!gamma)
return -ENOMEM;
{
int src;
struct irq_list_head *lh;
+ unsigned long irq_table_flags;
DRM_DEBUG_KMS("DM_IRQ: releasing resources.\n");
-
for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) {
-
+ DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
/* The handler was removed from the table,
* it means it is safe to flush all the 'work'
* (because no code can schedule a new one). */
lh = &adev->dm.irq_handler_list_low_tab[src];
+ DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
flush_work(&lh->work);
}
}
enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
I2C_MOT_TRUE : I2C_MOT_FALSE;
enum ddc_result res;
- ssize_t read_bytes;
+ uint32_t read_bytes = msg->size;
if (WARN_ON(msg->size > 16))
return -E2BIG;
switch (msg->request & ~DP_AUX_I2C_MOT) {
case DP_AUX_NATIVE_READ:
- read_bytes = dal_ddc_service_read_dpcd_data(
+ res = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
false,
I2C_MOT_UNDEF,
msg->address,
msg->buffer,
- msg->size);
- return read_bytes;
+ msg->size,
+ &read_bytes);
+ break;
case DP_AUX_NATIVE_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
msg->size);
break;
case DP_AUX_I2C_READ:
- read_bytes = dal_ddc_service_read_dpcd_data(
+ res = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
true,
mot,
msg->address,
msg->buffer,
- msg->size);
- return read_bytes;
+ msg->size,
+ &read_bytes);
+ break;
case DP_AUX_I2C_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
r == DDC_RESULT_SUCESSFULL);
#endif
- return msg->size;
+ if (res != DDC_RESULT_SUCESSFULL)
+ return -EIO;
+ return read_bytes;
}
static enum drm_connector_status
struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
struct amdgpu_encoder *amdgpu_encoder = amdgpu_dm_connector->mst_encoder;
+ if (amdgpu_dm_connector->edid) {
+ kfree(amdgpu_dm_connector->edid);
+ amdgpu_dm_connector->edid = NULL;
+ }
+
drm_encoder_cleanup(&amdgpu_encoder->base);
kfree(amdgpu_encoder);
drm_connector_cleanup(connector);
void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
{
struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
- struct edid *edid;
struct dc_sink *dc_sink;
struct dc_sink_init_data init_params = {
.link = aconnector->dc_link,
.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
+ /* FIXME none of this is safe. we shouldn't touch aconnector here in
+ * atomic_check
+ */
+
/*
* TODO: Need to further figure out why ddc.algo is NULL while MST port exists
*/
if (!aconnector->port || !aconnector->port->aux.ddc.algo)
return;
- edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
-
- if (!edid) {
- drm_mode_connector_update_edid_property(
- &aconnector->base,
- NULL);
- return;
- }
-
- aconnector->edid = edid;
+ ASSERT(aconnector->edid);
dc_sink = dc_link_add_remote_sink(
aconnector->dc_link,
amdgpu_dm_add_sink_to_freesync_module(
connector, aconnector->edid);
-
- drm_mode_connector_update_edid_property(
- &aconnector->base, aconnector->edid);
}
static int dm_dp_mst_get_modes(struct drm_connector *connector)
if (!aconnector->edid) {
struct edid *edid;
- struct dc_sink *dc_sink;
- struct dc_sink_init_data init_params = {
- .link = aconnector->dc_link,
- .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
if (!edid) {
}
aconnector->edid = edid;
+ }
+ if (!aconnector->dc_sink) {
+ struct dc_sink *dc_sink;
+ struct dc_sink_init_data init_params = {
+ .link = aconnector->dc_link,
+ .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
dc_sink = dc_link_add_remote_sink(
aconnector->dc_link,
- (uint8_t *)edid,
- (edid->extensions + 1) * EDID_LENGTH,
+ (uint8_t *)aconnector->edid,
+ (aconnector->edid->extensions + 1) * EDID_LENGTH,
&init_params);
dc_sink->priv = aconnector;
if (aconnector->dc_sink)
amdgpu_dm_add_sink_to_freesync_module(
- connector, edid);
-
- drm_mode_connector_update_edid_property(
- &aconnector->base, edid);
+ connector, aconnector->edid);
}
+ drm_mode_connector_update_edid_property(
+ &aconnector->base, aconnector->edid);
+
ret = drm_add_edid_modes(connector, aconnector->edid);
return ret;
dc_sink_release(aconnector->dc_sink);
aconnector->dc_sink = NULL;
}
- if (aconnector->edid) {
- kfree(aconnector->edid);
- aconnector->edid = NULL;
- }
-
- drm_mode_connector_update_edid_property(
- &aconnector->base,
- NULL);
aconnector->mst_connected = false;
}
struct bios_parser *bp,
struct dc_firmware_info *info);
+static enum bp_result get_firmware_info_v3_2(
+ struct bios_parser *bp,
+ struct dc_firmware_info *info);
+
static struct atom_hpd_int_record *get_hpd_record(struct bios_parser *bp,
struct atom_display_object_path_v2 *object);
case 3:
switch (revision.minor) {
case 1:
- case 2:
result = get_firmware_info_v3_1(bp, info);
break;
+ case 2:
+ result = get_firmware_info_v3_2(bp, info);
+ break;
default:
break;
}
return BP_RESULT_OK;
}
+static enum bp_result get_firmware_info_v3_2(
+ struct bios_parser *bp,
+ struct dc_firmware_info *info)
+{
+ struct atom_firmware_info_v3_2 *firmware_info;
+ struct atom_display_controller_info_v4_1 *dce_info = NULL;
+ struct atom_common_table_header *header;
+ struct atom_data_revision revision;
+ struct atom_smu_info_v3_2 *smu_info_v3_2 = NULL;
+ struct atom_smu_info_v3_3 *smu_info_v3_3 = NULL;
+
+ if (!info)
+ return BP_RESULT_BADINPUT;
+
+ firmware_info = GET_IMAGE(struct atom_firmware_info_v3_2,
+ DATA_TABLES(firmwareinfo));
+
+ dce_info = GET_IMAGE(struct atom_display_controller_info_v4_1,
+ DATA_TABLES(dce_info));
+
+ if (!firmware_info || !dce_info)
+ return BP_RESULT_BADBIOSTABLE;
+
+ memset(info, 0, sizeof(*info));
+
+ header = GET_IMAGE(struct atom_common_table_header,
+ DATA_TABLES(smu_info));
+ get_atom_data_table_revision(header, &revision);
+
+ if (revision.minor == 2) {
+ /* Vega12 */
+ smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
+ DATA_TABLES(smu_info));
+
+ if (!smu_info_v3_2)
+ return BP_RESULT_BADBIOSTABLE;
+
+ info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
+ } else if (revision.minor == 3) {
+ /* Vega20 */
+ smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
+ DATA_TABLES(smu_info));
+
+ if (!smu_info_v3_3)
+ return BP_RESULT_BADBIOSTABLE;
+
+ info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
+ }
+
+ // We need to convert from 10KHz units into KHz units.
+ info->default_memory_clk = firmware_info->bootup_mclk_in10khz * 10;
+
+ /* 27MHz for Vega10 & Vega12; 100MHz for Vega20 */
+ info->pll_info.crystal_frequency = dce_info->dce_refclk_10khz * 10;
+ /* Hardcode frequency if BIOS gives no DCE Ref Clk */
+ if (info->pll_info.crystal_frequency == 0) {
+ if (revision.minor == 2)
+ info->pll_info.crystal_frequency = 27000;
+ else if (revision.minor == 3)
+ info->pll_info.crystal_frequency = 100000;
+ }
+ /*dp_phy_ref_clk is not correct for atom_display_controller_info_v4_2, but we don't use it*/
+ info->dp_phy_ref_clk = dce_info->dpphy_refclk_10khz * 10;
+ info->i2c_engine_ref_clk = dce_info->i2c_engine_refclk_10khz * 10;
+
+ /* Get GPU PLL VCO Clock */
+ if (bp->cmd_tbl.get_smu_clock_info != NULL) {
+ if (revision.minor == 2)
+ info->smu_gpu_pll_output_freq =
+ bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10;
+ else if (revision.minor == 3)
+ info->smu_gpu_pll_output_freq =
+ bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10;
+ }
+
+ return BP_RESULT_OK;
+}
+
static enum bp_result bios_parser_get_encoder_cap_info(
struct dc_bios *dcb,
struct graphics_object_id object_id,
return ret;
}
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len)
+ uint32_t len,
+ uint32_t *read)
{
struct aux_payload read_payload = {
.i2c_over_aux = i2c,
.mot = mot
};
+ *read = 0;
+
if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
BREAK_TO_DEBUGGER();
return DDC_RESULT_FAILED_INVALID_OPERATION;
ddc->ctx->i2caux,
ddc->ddc_pin,
&command)) {
- return (ssize_t)command.payloads->length;
+ *read = command.payloads->length;
+ return DDC_RESULT_SUCESSFULL;
}
return DDC_RESULT_FAILED_OPERATION;
{
struct dc *core_dc = dc;
- struct dc_plane_state *plane_state = kzalloc(sizeof(*plane_state),
- GFP_KERNEL);
+ struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state),
+ GFP_KERNEL);
if (NULL == plane_state)
return NULL;
{
struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount);
destruct(plane_state);
- kfree(plane_state);
+ kvfree(plane_state);
}
void dc_plane_state_release(struct dc_plane_state *plane_state)
static void dc_gamma_free(struct kref *kref)
{
struct dc_gamma *gamma = container_of(kref, struct dc_gamma, refcount);
- kfree(gamma);
+ kvfree(gamma);
}
void dc_gamma_release(struct dc_gamma **gamma)
struct dc_gamma *dc_create_gamma(void)
{
- struct dc_gamma *gamma = kzalloc(sizeof(*gamma), GFP_KERNEL);
+ struct dc_gamma *gamma = kvzalloc(sizeof(*gamma), GFP_KERNEL);
if (gamma == NULL)
goto alloc_fail;
static void dc_transfer_func_free(struct kref *kref)
{
struct dc_transfer_func *tf = container_of(kref, struct dc_transfer_func, refcount);
- kfree(tf);
+ kvfree(tf);
}
void dc_transfer_func_release(struct dc_transfer_func *tf)
struct dc_transfer_func *dc_create_transfer_func(void)
{
- struct dc_transfer_func *tf = kzalloc(sizeof(*tf), GFP_KERNEL);
+ struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL);
if (tf == NULL)
goto alloc_fail;
uint8_t *read_buf,
uint32_t read_size);
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len);
+ uint32_t len,
+ uint32_t *read);
enum ddc_result dal_ddc_service_write_dpcd_data(
struct ddc_service *ddc,
#define AI_GREENLAND_P_A0 1
#define AI_GREENLAND_P_A1 2
+#define AI_UNKNOWN 0xFF
-#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_UNKNOWN)
-#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_UNKNOWN)
+#define AI_VEGA12_P_A0 20
+#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_VEGA12_P_A0)
+#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_VEGA12_P_A0)
+
+#define ASICREV_IS_VEGA12_P(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN))
+#define ASICREV_IS_VEGA12_p(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN))
/* DCN1_0 */
#define INTERNAL_REV_RAVEN_A0 0x00 /* First spin of Raven */
output_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
- rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_user)
goto rgb_user_alloc_fail;
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
- axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
- GFP_KERNEL);
+ axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
+ GFP_KERNEL);
if (!axix_x)
goto axix_x_alloc_fail;
- coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+ coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
if (!coeff)
goto coeff_alloc_fail;
ret = true;
- kfree(coeff);
+ kvfree(coeff);
coeff_alloc_fail:
- kfree(axix_x);
+ kvfree(axix_x);
axix_x_alloc_fail:
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
rgb_regamma_alloc_fail:
- kfree(rgb_user);
+ kvfree(rgb_user);
rgb_user_alloc_fail:
return ret;
}
input_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
- rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_user)
goto rgb_user_alloc_fail;
- curve = kzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
- GFP_KERNEL);
+ curve = kvzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!curve)
goto curve_alloc_fail;
- axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!axix_x)
goto axix_x_alloc_fail;
- coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+ coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
if (!coeff)
goto coeff_alloc_fail;
ret = true;
- kfree(coeff);
+ kvfree(coeff);
coeff_alloc_fail:
- kfree(axix_x);
+ kvfree(axix_x);
axix_x_alloc_fail:
- kfree(curve);
+ kvfree(curve);
curve_alloc_fail:
- kfree(rgb_user);
+ kvfree(rgb_user);
rgb_user_alloc_fail:
return ret;
}
ret = true;
} else if (trans == TRANSFER_FUNCTION_PQ) {
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
points->end_exponent = 7;
}
ret = true;
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
} else if (trans == TRANSFER_FUNCTION_SRGB ||
trans == TRANSFER_FUNCTION_BT709) {
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
points->end_exponent = 0;
}
ret = true;
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
}
rgb_regamma_alloc_fail:
return ret;
}
ret = true;
} else if (trans == TRANSFER_FUNCTION_PQ) {
- rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_degamma)
goto rgb_degamma_alloc_fail;
}
ret = true;
- kfree(rgb_degamma);
+ kvfree(rgb_degamma);
} else if (trans == TRANSFER_FUNCTION_SRGB ||
trans == TRANSFER_FUNCTION_BT709) {
- rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_degamma)
goto rgb_degamma_alloc_fail;
}
ret = true;
- kfree(rgb_degamma);
+ kvfree(rgb_degamma);
}
points->end_exponent = 0;
points->x_point_at_y1_red = 1;
LIQUID_COOLING = 0x01
};
+struct atom_firmware_info_v3_2 {
+ struct atom_common_table_header table_header;
+ uint32_t firmware_revision;
+ uint32_t bootup_sclk_in10khz;
+ uint32_t bootup_mclk_in10khz;
+ uint32_t firmware_capability; // enum atombios_firmware_capability
+ uint32_t main_call_parser_entry; /* direct address of main parser call in VBIOS binary. */
+ uint32_t bios_scratch_reg_startaddr; // 1st bios scratch register dword address
+ uint16_t bootup_vddc_mv;
+ uint16_t bootup_vddci_mv;
+ uint16_t bootup_mvddc_mv;
+ uint16_t bootup_vddgfx_mv;
+ uint8_t mem_module_id;
+ uint8_t coolingsolution_id; /*0: Air cooling; 1: Liquid cooling ... */
+ uint8_t reserved1[2];
+ uint32_t mc_baseaddr_high;
+ uint32_t mc_baseaddr_low;
+ uint8_t board_i2c_feature_id; // enum of atom_board_i2c_feature_id_def
+ uint8_t board_i2c_feature_gpio_id; // i2c id find in gpio_lut data table gpio_id
+ uint8_t board_i2c_feature_slave_addr;
+ uint8_t reserved3;
+ uint16_t bootup_mvddq_mv;
+ uint16_t bootup_mvpp_mv;
+ uint32_t zfbstartaddrin16mb;
+ uint32_t reserved2[3];
+};
/*
***************************************************************************
uint32_t rlc_gpu_timer_refclk;
};
-
+struct atom_gfx_info_v2_3 {
+ struct atom_common_table_header table_header;
+ uint8_t gfxip_min_ver;
+ uint8_t gfxip_max_ver;
+ uint8_t max_shader_engines;
+ uint8_t max_tile_pipes;
+ uint8_t max_cu_per_sh;
+ uint8_t max_sh_per_se;
+ uint8_t max_backends_per_se;
+ uint8_t max_texture_channel_caches;
+ uint32_t regaddr_cp_dma_src_addr;
+ uint32_t regaddr_cp_dma_src_addr_hi;
+ uint32_t regaddr_cp_dma_dst_addr;
+ uint32_t regaddr_cp_dma_dst_addr_hi;
+ uint32_t regaddr_cp_dma_command;
+ uint32_t regaddr_cp_status;
+ uint32_t regaddr_rlc_gpu_clock_32;
+ uint32_t rlc_gpu_timer_refclk;
+ uint8_t active_cu_per_sh;
+ uint8_t active_rb_per_se;
+ uint16_t gcgoldenoffset;
+ uint32_t rm21_sram_vmin_value;
+};
/*
***************************************************************************
uint8_t fw_ctf_polarity; // GPIO polarity for CTF
};
+struct atom_smu_info_v3_2 {
+ struct atom_common_table_header table_header;
+ uint8_t smuip_min_ver;
+ uint8_t smuip_max_ver;
+ uint8_t smu_rsd1;
+ uint8_t gpuclk_ss_mode;
+ uint16_t sclk_ss_percentage;
+ uint16_t sclk_ss_rate_10hz;
+ uint16_t gpuclk_ss_percentage; // in unit of 0.001%
+ uint16_t gpuclk_ss_rate_10hz;
+ uint32_t core_refclk_10khz;
+ uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid
+ uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching
+ uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid
+ uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event
+ uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+ uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event
+ uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+ uint8_t fw_ctf_polarity; // GPIO polarity for CTF
+ uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+ uint8_t pcc_gpio_polarity; // GPIO polarity for CTF
+ uint16_t smugoldenoffset;
+ uint32_t gpupll_vco_freq_10khz;
+ uint32_t bootup_smnclk_10khz;
+ uint32_t bootup_socclk_10khz;
+ uint32_t bootup_mp0clk_10khz;
+ uint32_t bootup_mp1clk_10khz;
+ uint32_t bootup_lclk_10khz;
+ uint32_t bootup_dcefclk_10khz;
+ uint32_t ctf_threshold_override_value;
+ uint32_t reserved[5];
+};
+
+struct atom_smu_info_v3_3 {
+ struct atom_common_table_header table_header;
+ uint8_t smuip_min_ver;
+ uint8_t smuip_max_ver;
+ uint8_t smu_rsd1;
+ uint8_t gpuclk_ss_mode;
+ uint16_t sclk_ss_percentage;
+ uint16_t sclk_ss_rate_10hz;
+ uint16_t gpuclk_ss_percentage; // in unit of 0.001%
+ uint16_t gpuclk_ss_rate_10hz;
+ uint32_t core_refclk_10khz;
+ uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid
+ uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching
+ uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid
+ uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event
+ uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+ uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event
+ uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+ uint8_t fw_ctf_polarity; // GPIO polarity for CTF
+ uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+ uint8_t pcc_gpio_polarity; // GPIO polarity for CTF
+ uint16_t smugoldenoffset;
+ uint32_t gpupll_vco_freq_10khz;
+ uint32_t bootup_smnclk_10khz;
+ uint32_t bootup_socclk_10khz;
+ uint32_t bootup_mp0clk_10khz;
+ uint32_t bootup_mp1clk_10khz;
+ uint32_t bootup_lclk_10khz;
+ uint32_t bootup_dcefclk_10khz;
+ uint32_t ctf_threshold_override_value;
+ uint32_t syspll3_0_vco_freq_10khz;
+ uint32_t syspll3_1_vco_freq_10khz;
+ uint32_t bootup_fclk_10khz;
+ uint32_t bootup_waflclk_10khz;
+ uint32_t reserved[3];
+};
+
/*
***************************************************************************
Data Table smc_dpm_info structure
uint32_t boardreserved[10];
};
-
/*
***************************************************************************
Data Table asic_profiling_info structure
SMU9_SYSPLL0_DISPCLK_ID = 11, // DISPCLK
};
+enum atom_smu11_syspll_id {
+ SMU11_SYSPLL0_ID = 0,
+ SMU11_SYSPLL1_0_ID = 1,
+ SMU11_SYSPLL1_1_ID = 2,
+ SMU11_SYSPLL1_2_ID = 3,
+ SMU11_SYSPLL2_ID = 4,
+ SMU11_SYSPLL3_0_ID = 5,
+ SMU11_SYSPLL3_1_ID = 6,
+};
+
+
+enum atom_smu11_syspll0_clock_id {
+ SMU11_SYSPLL0_SOCCLK_ID = 0, // SOCCLK
+ SMU11_SYSPLL0_MP0CLK_ID = 1, // MP0CLK
+ SMU11_SYSPLL0_DCLK_ID = 2, // DCLK
+ SMU11_SYSPLL0_VCLK_ID = 3, // VCLK
+ SMU11_SYSPLL0_ECLK_ID = 4, // ECLK
+ SMU11_SYSPLL0_DCEFCLK_ID = 5, // DCEFCLK
+};
+
+
+enum atom_smu11_syspll1_0_clock_id {
+ SMU11_SYSPLL1_0_UCLKA_ID = 0, // UCLK_a
+};
+
+enum atom_smu11_syspll1_1_clock_id {
+ SMU11_SYSPLL1_0_UCLKB_ID = 0, // UCLK_b
+};
+
+enum atom_smu11_syspll1_2_clock_id {
+ SMU11_SYSPLL1_0_FCLK_ID = 0, // FCLK
+};
+
+enum atom_smu11_syspll2_clock_id {
+ SMU11_SYSPLL2_GFXCLK_ID = 0, // GFXCLK
+};
+
+enum atom_smu11_syspll3_0_clock_id {
+ SMU11_SYSPLL3_0_WAFCLK_ID = 0, // WAFCLK
+ SMU11_SYSPLL3_0_DISPCLK_ID = 1, // DISPCLK
+ SMU11_SYSPLL3_0_DPREFCLK_ID = 2, // DPREFCLK
+};
+
+enum atom_smu11_syspll3_1_clock_id {
+ SMU11_SYSPLL3_1_MP1CLK_ID = 0, // MP1CLK
+ SMU11_SYSPLL3_1_SMNCLK_ID = 1, // SMNCLK
+ SMU11_SYSPLL3_1_LCLK_ID = 2, // LCLK
+};
+
struct atom_get_smu_clock_info_output_parameters_v3_1
{
union {
#define PCIE_BUS_CLK 10000
#define TCLK (PCIE_BUS_CLK / 10)
-static const struct profile_mode_setting smu7_profiling[5] =
+static const struct profile_mode_setting smu7_profiling[6] =
{{1, 0, 100, 30, 1, 0, 100, 10},
{1, 10, 0, 30, 0, 0, 0, 0},
{0, 0, 0, 0, 1, 10, 16, 31},
{1, 0, 11, 50, 1, 0, 100, 10},
{1, 0, 5, 30, 0, 0, 0, 0},
+ {0, 0, 0, 0, 0, 0, 0, 0},
};
/** Values for the CG_THERMAL_CTRL::DPM_EVENT_SRC field. */
for (i=0; i < dep_table->count; i++) {
if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
- data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
- break;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+ return;
}
}
- if (i == dep_table->count)
+ if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+ }
dep_table = table_info->vdd_dep_on_sclk;
odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
for (i=0; i < dep_table->count; i++) {
if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
- data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
- break;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+ return;
}
}
- if (i == dep_table->count)
+ if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+ }
}
static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting);
for (i = 0; i < len; i++) {
+ if (i == hwmgr->power_profile_mode) {
+ size += sprintf(buf + size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n",
+ i, profile_name[i], "*",
+ data->current_profile_setting.sclk_up_hyst,
+ data->current_profile_setting.sclk_down_hyst,
+ data->current_profile_setting.sclk_activity,
+ data->current_profile_setting.mclk_up_hyst,
+ data->current_profile_setting.mclk_down_hyst,
+ data->current_profile_setting.mclk_activity);
+ continue;
+ }
if (smu7_profiling[i].bupdate_sclk)
size += sprintf(buf + size, "%3d %16s: %8d %16d %16d ",
i, profile_name[i], smu7_profiling[i].sclk_up_hyst,
"-", "-", "-");
}
- size += sprintf(buf + size, "%3d %16s: %8d %16d %16d %16d %16d %16d\n",
- i, profile_name[i],
- data->custom_profile_setting.sclk_up_hyst,
- data->custom_profile_setting.sclk_down_hyst,
- data->custom_profile_setting.sclk_activity,
- data->custom_profile_setting.mclk_up_hyst,
- data->custom_profile_setting.mclk_down_hyst,
- data->custom_profile_setting.mclk_activity);
-
- size += sprintf(buf + size, "%3s %16s: %8d %16d %16d %16d %16d %16d\n",
- "*", "CURRENT",
- data->current_profile_setting.sclk_up_hyst,
- data->current_profile_setting.sclk_down_hyst,
- data->current_profile_setting.sclk_activity,
- data->current_profile_setting.mclk_up_hyst,
- data->current_profile_setting.mclk_down_hyst,
- data->current_profile_setting.mclk_activity);
-
return size;
}
if (size < 8)
return -EINVAL;
- data->custom_profile_setting.bupdate_sclk = input[0];
- data->custom_profile_setting.sclk_up_hyst = input[1];
- data->custom_profile_setting.sclk_down_hyst = input[2];
- data->custom_profile_setting.sclk_activity = input[3];
- data->custom_profile_setting.bupdate_mclk = input[4];
- data->custom_profile_setting.mclk_up_hyst = input[5];
- data->custom_profile_setting.mclk_down_hyst = input[6];
- data->custom_profile_setting.mclk_activity = input[7];
- if (!smum_update_dpm_settings(hwmgr, &data->custom_profile_setting)) {
- memcpy(&data->current_profile_setting, &data->custom_profile_setting, sizeof(struct profile_mode_setting));
+ tmp.bupdate_sclk = input[0];
+ tmp.sclk_up_hyst = input[1];
+ tmp.sclk_down_hyst = input[2];
+ tmp.sclk_activity = input[3];
+ tmp.bupdate_mclk = input[4];
+ tmp.mclk_up_hyst = input[5];
+ tmp.mclk_down_hyst = input[6];
+ tmp.mclk_activity = input[7];
+ if (!smum_update_dpm_settings(hwmgr, &tmp)) {
+ memcpy(&data->current_profile_setting, &tmp, sizeof(struct profile_mode_setting));
hwmgr->power_profile_mode = mode;
}
break;
uint16_t mem_latency_high;
uint16_t mem_latency_low;
uint32_t vr_config;
- struct profile_mode_setting custom_profile_setting;
struct profile_mode_setting current_profile_setting;
};
{
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
- n = (n & 0xff) << 8;
-
if (data->power_containment_features &
POWERCONTAINMENT_FEATURE_PkgPwrLimit)
return smum_send_msg_to_smc_with_parameter(hwmgr,
- PPSMC_MSG_PkgPwrSetLimit, n);
+ PPSMC_MSG_PkgPwrSetLimit, n<<8);
return 0;
}
QuadraticInt_t ReservedEquation2;
QuadraticInt_t ReservedEquation3;
+ uint16_t MinVoltageUlvGfx;
+ uint16_t MinVoltageUlvSoc;
- uint32_t Reserved[15];
+ uint32_t Reserved[14];
tristate "Silicon Image SII8620 HDMI/MHL bridge"
depends on OF && RC_CORE
select DRM_KMS_HELPER
+ imply EXTCON
help
Silicon Image SII8620 HDMI/MHL bridge chip driver.
}
drm_mode_connector_update_edid_property(connector, edid);
- return drm_add_edid_modes(connector, edid);
+ ret = drm_add_edid_modes(connector, edid);
+ kfree(edid);
+ return ret;
fallback:
/*
state->connectors[i].state);
state->connectors[i].ptr = NULL;
state->connectors[i].state = NULL;
+ state->connectors[i].old_state = NULL;
+ state->connectors[i].new_state = NULL;
drm_connector_put(connector);
}
state->crtcs[i].ptr = NULL;
state->crtcs[i].state = NULL;
+ state->crtcs[i].old_state = NULL;
+ state->crtcs[i].new_state = NULL;
}
for (i = 0; i < config->num_total_plane; i++) {
state->planes[i].state);
state->planes[i].ptr = NULL;
state->planes[i].state = NULL;
+ state->planes[i].old_state = NULL;
+ state->planes[i].new_state = NULL;
}
for (i = 0; i < state->num_private_objs; i++) {
state->private_objs[i].state);
state->private_objs[i].ptr = NULL;
state->private_objs[i].state = NULL;
+ state->private_objs[i].old_state = NULL;
+ state->private_objs[i].new_state = NULL;
}
state->num_private_objs = 0;
{
uint8_t tmds_oen = enable ? 0 : DP_DUAL_MODE_TMDS_DISABLE;
ssize_t ret;
+ int retry;
if (type < DRM_DP_DUAL_MODE_TYPE2_DVI)
return 0;
- ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
- &tmds_oen, sizeof(tmds_oen));
- if (ret) {
- DRM_DEBUG_KMS("Failed to %s TMDS output buffers\n",
- enable ? "enable" : "disable");
- return ret;
+ /*
+ * LSPCON adapters in low-power state may ignore the first write, so
+ * read back and verify the written value a few times.
+ */
+ for (retry = 0; retry < 3; retry++) {
+ uint8_t tmp;
+
+ ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmds_oen, sizeof(tmds_oen));
+ if (ret) {
+ DRM_DEBUG_KMS("Failed to %s TMDS output buffers (%d attempts)\n",
+ enable ? "enable" : "disable",
+ retry + 1);
+ return ret;
+ }
+
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmp, sizeof(tmp));
+ if (ret) {
+ DRM_DEBUG_KMS("I2C read failed during TMDS output buffer %s (%d attempts)\n",
+ enable ? "enabling" : "disabling",
+ retry + 1);
+ return ret;
+ }
+
+ if (tmp == tmds_oen)
+ return 0;
}
- return 0;
+ DRM_DEBUG_KMS("I2C write value mismatch during TMDS output buffer %s\n",
+ enable ? "enabling" : "disabling");
+
+ return -EIO;
}
EXPORT_SYMBOL(drm_dp_dual_mode_set_tmds_output);
if (!minor)
return;
- name = kasprintf(GFP_KERNEL, "controlD%d", minor->index);
+ name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64);
if (!name)
return;
return -EINVAL;
/* overflow checks for 32bit size calculations */
- /* NOTE: DIV_ROUND_UP() can overflow */
+ if (args->bpp > U32_MAX - 8)
+ return -EINVAL;
cpp = DIV_ROUND_UP(args->bpp, 8);
- if (!cpp || cpp > 0xffffffffU / args->width)
+ if (cpp > U32_MAX / args->width)
return -EINVAL;
stride = cpp * args->width;
- if (args->height > 0xffffffffU / stride)
+ if (args->height > U32_MAX / stride)
return -EINVAL;
/* test for wrap-around */
info->max_tmds_clock = 0;
info->dvi_dual = false;
info->has_hdmi_infoframe = false;
+ memset(&info->hdmi, 0, sizeof(info->hdmi));
info->non_desktop = 0;
}
u32 quirks = edid_get_quirks(edid);
+ drm_reset_display_info(connector);
+
info->width_mm = edid->width_cm * 10;
info->height_mm = edid->height_cm * 10;
- /* driver figures it out in this case */
- info->bpc = 0;
- info->color_formats = 0;
- info->cea_rev = 0;
- info->max_tmds_clock = 0;
- info->dvi_dual = false;
- info->has_hdmi_infoframe = false;
-
info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP);
DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop);
return -ENOMEM;
filp->private_data = priv;
+ filp->f_mode |= FMODE_UNSIGNED_OFFSET;
priv->filp = filp;
priv->pid = get_pid(task_pid(current));
priv->minor = minor;
#include <drm/drm_fb_helper.h>
#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
#include <uapi/drm/exynos_drm.h>
#include "exynos_drm_drv.h"
#include "exynos_drm_iommu.h"
#include "exynos_drm_crtc.h"
-#define to_exynos_fb(x) container_of(x, struct exynos_drm_fb, fb)
-
-/*
- * exynos specific framebuffer structure.
- *
- * @fb: drm framebuffer obejct.
- * @exynos_gem: array of exynos specific gem object containing a gem object.
- */
-struct exynos_drm_fb {
- struct drm_framebuffer fb;
- struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
- dma_addr_t dma_addr[MAX_FB_BUFFER];
-};
-
static int check_fb_gem_memory_type(struct drm_device *drm_dev,
struct exynos_drm_gem *exynos_gem)
{
return 0;
}
-static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
-{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
- unsigned int i;
-
- drm_framebuffer_cleanup(fb);
-
- for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem); i++) {
- struct drm_gem_object *obj;
-
- if (exynos_fb->exynos_gem[i] == NULL)
- continue;
-
- obj = &exynos_fb->exynos_gem[i]->base;
- drm_gem_object_unreference_unlocked(obj);
- }
-
- kfree(exynos_fb);
- exynos_fb = NULL;
-}
-
-static int exynos_drm_fb_create_handle(struct drm_framebuffer *fb,
- struct drm_file *file_priv,
- unsigned int *handle)
-{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
-
- return drm_gem_handle_create(file_priv,
- &exynos_fb->exynos_gem[0]->base, handle);
-}
-
static const struct drm_framebuffer_funcs exynos_drm_fb_funcs = {
- .destroy = exynos_drm_fb_destroy,
- .create_handle = exynos_drm_fb_create_handle,
+ .destroy = drm_gem_fb_destroy,
+ .create_handle = drm_gem_fb_create_handle,
};
struct drm_framebuffer *
struct exynos_drm_gem **exynos_gem,
int count)
{
- struct exynos_drm_fb *exynos_fb;
+ struct drm_framebuffer *fb;
int i;
int ret;
- exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL);
- if (!exynos_fb)
+ fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+ if (!fb)
return ERR_PTR(-ENOMEM);
for (i = 0; i < count; i++) {
if (ret < 0)
goto err;
- exynos_fb->exynos_gem[i] = exynos_gem[i];
- exynos_fb->dma_addr[i] = exynos_gem[i]->dma_addr
- + mode_cmd->offsets[i];
+ fb->obj[i] = &exynos_gem[i]->base;
}
- drm_helper_mode_fill_fb_struct(dev, &exynos_fb->fb, mode_cmd);
+ drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
- ret = drm_framebuffer_init(dev, &exynos_fb->fb, &exynos_drm_fb_funcs);
+ ret = drm_framebuffer_init(dev, fb, &exynos_drm_fb_funcs);
if (ret < 0) {
DRM_ERROR("failed to initialize framebuffer\n");
goto err;
}
- return &exynos_fb->fb;
+ return fb;
err:
- kfree(exynos_fb);
+ kfree(fb);
return ERR_PTR(ret);
}
dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
+ struct exynos_drm_gem *exynos_gem;
if (WARN_ON_ONCE(index >= MAX_FB_BUFFER))
return 0;
- return exynos_fb->dma_addr[index];
+ exynos_gem = to_exynos_gem(fb->obj[index]);
+ return exynos_gem->dma_addr + fb->offsets[index];
}
static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = {
drm_mode_connector_attach_encoder(connector, encoder);
if (hdata->bridge) {
- encoder->bridge = hdata->bridge;
- hdata->bridge->encoder = encoder;
ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
if (ret)
DRM_ERROR("Failed to attach bridge\n");
chroma_addr[1] = chroma_addr[0] + 0x40;
} else {
luma_addr[1] = luma_addr[0] + fb->pitches[0];
- chroma_addr[1] = chroma_addr[0] + fb->pitches[0];
+ chroma_addr[1] = chroma_addr[0] + fb->pitches[1];
}
} else {
luma_addr[1] = 0;
spin_lock_irqsave(&ctx->reg_slock, flags);
+ vp_reg_write(ctx, VP_SHADOW_UPDATE, 1);
/* interlace or progressive scan mode */
val = (test_bit(MXR_BIT_INTERLACE, &ctx->flags) ? ~0 : 0);
vp_reg_writemask(ctx, VP_MODE, val, VP_MODE_LINE_SKIP);
vp_reg_write(ctx, VP_IMG_SIZE_Y, VP_IMG_HSIZE(fb->pitches[0]) |
VP_IMG_VSIZE(fb->height));
/* chroma plane for NV12/NV21 is half the height of the luma plane */
- vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[0]) |
+ vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[1]) |
VP_IMG_VSIZE(fb->height / 2));
vp_reg_write(ctx, VP_SRC_WIDTH, state->src.w);
- vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
vp_reg_write(ctx, VP_SRC_H_POSITION,
VP_SRC_H_POSITION_VAL(state->src.x));
- vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
-
vp_reg_write(ctx, VP_DST_WIDTH, state->crtc.w);
vp_reg_write(ctx, VP_DST_H_POSITION, state->crtc.x);
+
if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+ vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h / 2);
+ vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y / 2);
vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h / 2);
vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y / 2);
} else {
+ vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
+ vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h);
vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y);
}
/* interlace scan need to check shadow register */
if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+ if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) &&
+ vp_reg_read(ctx, VP_SHADOW_UPDATE))
+ goto out;
+
+ base = mixer_reg_read(ctx, MXR_CFG);
+ shadow = mixer_reg_read(ctx, MXR_CFG_S);
+ if (base != shadow)
+ goto out;
+
base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0));
shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0));
if (base != shadow)
#define MXR_MO 0x0304
#define MXR_RESOLUTION 0x0310
+#define MXR_CFG_S 0x2004
#define MXR_GRAPHIC0_BASE_S 0x2024
#define MXR_GRAPHIC1_BASE_S 0x2044
{
set_bit(cmd_interrupt_events[s->ring_id].mi_user_interrupt,
s->workload->pending_events);
+ patch_value(s, cmd_ptr(s, 0), MI_NOOP);
return 0;
}
static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+ int pipe;
+
vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT |
SDE_PORTC_HOTPLUG_CPT |
SDE_PORTD_HOTPLUG_CPT);
if (IS_BROADWELL(dev_priv))
vgpu_vreg_t(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK;
+ /* Disable Primary/Sprite/Cursor plane */
+ for_each_pipe(dev_priv, pipe) {
+ vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
+ vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
+ vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE;
+ vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE;
+ }
+
vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
}
struct intel_vgpu_fb_info *fb_info)
{
gvt_dmabuf->drm_format = fb_info->drm_format;
+ gvt_dmabuf->drm_format_mod = fb_info->drm_format_mod;
gvt_dmabuf->width = fb_info->width;
gvt_dmabuf->height = fb_info->height;
gvt_dmabuf->stride = fb_info->stride;
plane->hw_format = fmt;
plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate primary plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
alpha_plane, alpha_force);
plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate cursor plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
plane->drm_format = drm_format;
plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate sprite plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
false, 0, mm->vgpu);
}
+static void ggtt_get_host_entry(struct intel_vgpu_mm *mm,
+ struct intel_gvt_gtt_entry *entry, unsigned long index)
+{
+ struct intel_gvt_gtt_pte_ops *pte_ops = mm->vgpu->gvt->gtt.pte_ops;
+
+ GEM_BUG_ON(mm->type != INTEL_GVT_MM_GGTT);
+
+ pte_ops->get_entry(NULL, entry, index, false, 0, mm->vgpu);
+}
+
static void ggtt_set_host_entry(struct intel_vgpu_mm *mm,
struct intel_gvt_gtt_entry *entry, unsigned long index)
{
return ret;
}
+static void ggtt_invalidate_pte(struct intel_vgpu *vgpu,
+ struct intel_gvt_gtt_entry *entry)
+{
+ struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
+ unsigned long pfn;
+
+ pfn = pte_ops->get_pfn(entry);
+ if (pfn != vgpu->gvt->gtt.scratch_mfn)
+ intel_gvt_hypervisor_dma_unmap_guest_page(vgpu,
+ pfn << PAGE_SHIFT);
+}
+
static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
void *p_data, unsigned int bytes)
{
memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
bytes);
- m = e;
if (ops->test_present(&e)) {
gfn = ops->get_pfn(&e);
+ m = e;
/* one PTE update may be issued in multiple writes and the
* first write may not construct a valid gfn
ops->set_pfn(&m, gvt->gtt.scratch_mfn);
} else
ops->set_pfn(&m, dma_addr >> PAGE_SHIFT);
- } else
+ } else {
+ ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index);
+ ggtt_invalidate_pte(vgpu, &m);
ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+ ops->clear_present(&m);
+ }
out:
ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index);
return PTR_ERR(gtt->ggtt_mm);
}
- intel_vgpu_reset_ggtt(vgpu);
+ intel_vgpu_reset_ggtt(vgpu, false);
return create_scratch_page_tree(vgpu);
}
/**
* intel_vgpu_reset_ggtt - reset the GGTT entry
* @vgpu: a vGPU
+ * @invalidate_old: invalidate old entries
*
* This function is called at the vGPU create stage
* to reset all the GGTT entries.
*
*/
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
{
struct intel_gvt *gvt = vgpu->gvt;
struct drm_i915_private *dev_priv = gvt->dev_priv;
struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
struct intel_gvt_gtt_entry entry = {.type = GTT_TYPE_GGTT_PTE};
+ struct intel_gvt_gtt_entry old_entry;
u32 index;
u32 num_entries;
index = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT;
num_entries = vgpu_aperture_sz(vgpu) >> PAGE_SHIFT;
- while (num_entries--)
+ while (num_entries--) {
+ if (invalidate_old) {
+ ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+ ggtt_invalidate_pte(vgpu, &old_entry);
+ }
ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+ }
index = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT;
num_entries = vgpu_hidden_sz(vgpu) >> PAGE_SHIFT;
- while (num_entries--)
+ while (num_entries--) {
+ if (invalidate_old) {
+ ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+ ggtt_invalidate_pte(vgpu, &old_entry);
+ }
ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+ }
ggtt_invalidate(dev_priv);
}
* removing the shadow pages.
*/
intel_vgpu_destroy_all_ppgtt_mm(vgpu);
- intel_vgpu_reset_ggtt(vgpu);
+ intel_vgpu_reset_ggtt(vgpu, true);
}
extern int intel_vgpu_init_gtt(struct intel_vgpu *vgpu);
extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu);
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
switch (notification) {
case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE:
root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY;
+ /* fall through */
case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE:
mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps);
return PTR_ERR_OR_ZERO(mm);
}
- return 0;
+ return -ENOTTY;
}
static ssize_t
ret = i915_ggtt_probe_hw(dev_priv);
if (ret)
- return ret;
+ goto err_perf;
- /* WARNING: Apparently we must kick fbdev drivers before vgacon,
- * otherwise the vga fbdev driver falls over. */
+ /*
+ * WARNING: Apparently we must kick fbdev drivers before vgacon,
+ * otherwise the vga fbdev driver falls over.
+ */
ret = i915_kick_out_firmware_fb(dev_priv);
if (ret) {
DRM_ERROR("failed to remove conflicting framebuffer drivers\n");
- goto out_ggtt;
+ goto err_ggtt;
}
ret = i915_kick_out_vgacon(dev_priv);
if (ret) {
DRM_ERROR("failed to remove conflicting VGA console\n");
- goto out_ggtt;
+ goto err_ggtt;
}
ret = i915_ggtt_init_hw(dev_priv);
if (ret)
- return ret;
+ goto err_ggtt;
ret = i915_ggtt_enable_hw(dev_priv);
if (ret) {
DRM_ERROR("failed to enable GGTT\n");
- goto out_ggtt;
+ goto err_ggtt;
}
pci_set_master(pdev);
if (ret) {
DRM_ERROR("failed to set DMA mask\n");
- goto out_ggtt;
+ goto err_ggtt;
}
}
if (ret) {
DRM_ERROR("failed to set DMA mask\n");
- goto out_ggtt;
+ goto err_ggtt;
}
}
ret = intel_gvt_init(dev_priv);
if (ret)
- goto out_ggtt;
+ goto err_ggtt;
return 0;
-out_ggtt:
+err_ggtt:
i915_ggtt_cleanup_hw(dev_priv);
-
+err_perf:
+ i915_perf_fini(dev_priv);
return ret;
}
err = radix_tree_insert(handles_vma, handle, vma);
if (unlikely(err)) {
- kfree(lut);
+ kmem_cache_free(eb->i915->luts, lut);
goto err_obj;
}
I915_USERPTR_UNSYNCHRONIZED))
return -EINVAL;
+ if (!args->user_size)
+ return -EINVAL;
+
if (offset_in_page(args->user_ptr | args->user_size))
return -EINVAL;
spin_lock_irqsave(&i915->pmu.lock, flags);
spin_lock(&kdev->power.lock);
- if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
- i915->pmu.suspended_jiffies_last =
- kdev->power.suspended_jiffies;
+ /*
+ * After the above branch intel_runtime_pm_get_if_in_use failed
+ * to get the runtime PM reference we cannot assume we are in
+ * runtime suspend since we can either: a) race with coming out
+ * of it before we took the power.lock, or b) there are other
+ * states than suspended which can bring us here.
+ *
+ * We need to double-check that we are indeed currently runtime
+ * suspended and if not we cannot do better than report the last
+ * known RC6 value.
+ */
+ if (kdev->power.runtime_status == RPM_SUSPENDED) {
+ if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
+ i915->pmu.suspended_jiffies_last =
+ kdev->power.suspended_jiffies;
- val = kdev->power.suspended_jiffies -
- i915->pmu.suspended_jiffies_last;
- val += jiffies - kdev->power.accounting_timestamp;
+ val = kdev->power.suspended_jiffies -
+ i915->pmu.suspended_jiffies_last;
+ val += jiffies - kdev->power.accounting_timestamp;
- spin_unlock(&kdev->power.lock);
+ val = jiffies_to_nsecs(val);
+ val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
- val = jiffies_to_nsecs(val);
- val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
- i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+ i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+ } else if (i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+ val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+ } else {
+ val = i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+ }
+ spin_unlock(&kdev->power.lock);
spin_unlock_irqrestore(&i915->pmu.lock, flags);
}
#define SLICE_ECO_CHICKEN0 _MMIO(0x7308)
#define PIXEL_MASK_CAMMING_DISABLE (1 << 14)
+#define GEN9_WM_CHICKEN3 _MMIO(0x5588)
+#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9)
+
/* WaCatErrorRejectionIssue */
#define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG _MMIO(0x9030)
#define GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB (1<<11)
struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
u32 tmp;
- if (!IS_GEN9_BC(dev_priv))
+ if (!IS_GEN9(dev_priv))
return;
i915_audio_component_get_power(kdev);
return;
aux_channel = child->aux_channel;
- ddc_pin = child->ddc_pin;
is_dvi = child->device_type & DEVICE_TYPE_TMDS_DVI_SIGNALING;
is_dp = child->device_type & DEVICE_TYPE_DISPLAYPORT_OUTPUT;
DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
if (is_dvi) {
- info->alternate_ddc_pin = map_ddc_pin(dev_priv, ddc_pin);
-
- sanitize_ddc_pin(dev_priv, port);
+ ddc_pin = map_ddc_pin(dev_priv, child->ddc_pin);
+ if (intel_gmbus_is_valid_pin(dev_priv, ddc_pin)) {
+ info->alternate_ddc_pin = ddc_pin;
+ sanitize_ddc_pin(dev_priv, port);
+ } else {
+ DRM_DEBUG_KMS("Port %c has invalid DDC pin %d, "
+ "sticking to defaults\n",
+ port_name(port), ddc_pin);
+ }
}
if (is_dp) {
}
}
- /* According to BSpec, "The CD clock frequency must be at least twice
+ /*
+ * According to BSpec, "The CD clock frequency must be at least twice
* the frequency of the Azalia BCLK." and BCLK is 96 MHz by default.
+ *
+ * FIXME: Check the actual, not default, BCLK being used.
+ *
+ * FIXME: This does not depend on ->has_audio because the higher CDCLK
+ * is required for audio probe, also when there are no audio capable
+ * displays connected at probe time. This leads to unnecessarily high
+ * CDCLK when audio is not required.
+ *
+ * FIXME: This limit is only applied when there are displays connected
+ * at probe time. If we probe without displays, we'll still end up using
+ * the platform minimum CDCLK, failing audio probe.
*/
- if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
+ if (INTEL_GEN(dev_priv) >= 9)
min_cdclk = max(2 * 96000, min_cdclk);
/*
return 0;
}
+static int skl_dpll0_vco(struct intel_atomic_state *intel_state)
+{
+ struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev);
+ struct intel_crtc *crtc;
+ struct intel_crtc_state *crtc_state;
+ int vco, i;
+
+ vco = intel_state->cdclk.logical.vco;
+ if (!vco)
+ vco = dev_priv->skl_preferred_vco_freq;
+
+ for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
+ if (!crtc_state->base.enable)
+ continue;
+
+ if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
+ continue;
+
+ /*
+ * DPLL0 VCO may need to be adjusted to get the correct
+ * clock for eDP. This will affect cdclk as well.
+ */
+ switch (crtc_state->port_clock / 2) {
+ case 108000:
+ case 216000:
+ vco = 8640000;
+ break;
+ default:
+ vco = 8100000;
+ break;
+ }
+ }
+
+ return vco;
+}
+
static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
{
- struct drm_i915_private *dev_priv = to_i915(state->dev);
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
int min_cdclk, cdclk, vco;
if (min_cdclk < 0)
return min_cdclk;
- vco = intel_state->cdclk.logical.vco;
- if (!vco)
- vco = dev_priv->skl_preferred_vco_freq;
+ vco = skl_dpll0_vco(intel_state);
/*
* FIXME should also account for plane ratio
*/
#define I915_CSR_GLK "i915/glk_dmc_ver1_04.bin"
+MODULE_FIRMWARE(I915_CSR_GLK);
#define GLK_CSR_VERSION_REQUIRED CSR_VERSION(1, 4)
#define I915_CSR_CNL "i915/cnl_dmc_ver1_07.bin"
memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
if (crtc_state->base.active) {
intel_mode_from_pipe_config(&crtc->base.mode, crtc_state);
+ crtc->base.mode.hdisplay = crtc_state->pipe_src_w;
+ crtc->base.mode.vdisplay = crtc_state->pipe_src_h;
intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state);
WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
reduce_m_n);
}
- /*
- * DPLL0 VCO may need to be adjusted to get the correct
- * clock for eDP. This will affect cdclk as well.
- */
- if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) {
- int vco;
-
- switch (pipe_config->port_clock / 2) {
- case 108000:
- case 216000:
- vco = 8640000;
- break;
- default:
- vco = 8100000;
- break;
- }
-
- to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco;
- }
-
if (!HAS_DDI(dev_priv))
intel_dp_set_clock(encoder, pipe_config);
* check the condition before the timeout.
*/
#define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
- unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1; \
+ const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \
long wait__ = (Wmin); /* recommended min for usleep is 10 us */ \
int ret__; \
might_sleep(); \
for (;;) { \
- bool expired__ = time_after(jiffies, timeout__); \
+ const bool expired__ = ktime_after(ktime_get_raw(), end__); \
OP; \
if (COND) { \
ret__ = 0; \
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
+ /* WaClearHIZ_WM_CHICKEN3:bxt,glk */
+ if (IS_GEN9_LP(dev_priv))
+ WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
+
/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
if (ret)
return;
intel_fbdev_sync(ifbdev);
- if (ifbdev->vma)
+ if (ifbdev->vma || ifbdev->helper.deferred_setup)
drm_fb_helper_hotplug_event(&ifbdev->helper);
}
* know the next preemption status we see corresponds
* to this ELSP update.
*/
+ GEM_BUG_ON(!execlists_is_active(execlists,
+ EXECLISTS_ACTIVE_USER));
GEM_BUG_ON(!port_count(&port[0]));
if (port_count(&port[0]) > 1)
goto unlock;
memset(port, 0, sizeof(*port));
port++;
}
+
+ execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
}
static void execlists_cancel_requests(struct intel_engine_cs *engine)
head = execlists->csb_head;
tail = READ_ONCE(buf[write_idx]);
+ rmb(); /* Hopefully paired with a wmb() in HW */
}
GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
engine->name,
if (fw)
intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+
+ /* If the engine is now idle, so should be the flag; and vice versa. */
+ GEM_BUG_ON(execlists_is_active(&engine->execlists,
+ EXECLISTS_ACTIVE_USER) ==
+ !port_isset(engine->execlists.port));
}
static void queue_request(struct intel_engine_cs *engine,
I915_WRITE(PP_CONTROL(0), I915_READ(PP_CONTROL(0)) | PANEL_POWER_ON);
POSTING_READ(lvds_encoder->reg);
- if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 1000))
+
+ if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 5000))
DRM_ERROR("timed out waiting for panel to power on\n");
intel_panel_enable_backlight(pipe_config, conn_state);
DRM_DEBUG_KMS("Enabling DC6\n");
- gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
+ /* Wa Display #1183: skl,kbl,cfl */
+ if (IS_GEN9_BC(dev_priv))
+ I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
+ SKL_SELECT_ALTERNATE_DC_EXIT);
+ gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
}
void skl_disable_dc6(struct drm_i915_private *dev_priv)
{
DRM_DEBUG_KMS("Disabling DC6\n");
- /* Wa Display #1183: skl,kbl,cfl */
- if (IS_GEN9_BC(dev_priv))
- I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
- SKL_SELECT_ALTERNATE_DC_EXIT);
-
gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
}
spin_lock_irqsave(&dev->event_lock, flags);
mdp4_crtc->event = crtc->state->event;
+ crtc->state->event = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
blend_setup(crtc);
spin_lock_irqsave(&dev->event_lock, flags);
mdp5_crtc->event = crtc->state->event;
+ crtc->state->event = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
/*
return i;
}
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format)
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format,
+ uint64_t modifier)
{
int i;
for (i = 0; i < ARRAY_SIZE(formats); i++) {
#define MDP_FORMAT_IS_YUV(mdp_format) ((mdp_format)->is_yuv)
uint32_t mdp_get_formats(uint32_t *formats, uint32_t max_formats, bool rgb_only);
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format);
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
/* MDP capabilities */
#define MDP_CAP_SMP BIT(0) /* Shared Memory Pool */
bool registered;
bool power_on;
+ bool enabled;
int irq;
};
switch (mipi_fmt) {
case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888;
case MIPI_DSI_FMT_RGB666_PACKED:
- case MIPI_DSI_FMT_RGB666: return VID_DST_FORMAT_RGB666;
+ case MIPI_DSI_FMT_RGB666: return CMD_DST_FORMAT_RGB666;
case MIPI_DSI_FMT_RGB565: return CMD_DST_FORMAT_RGB565;
default: return CMD_DST_FORMAT_RGB888;
}
static void dsi_wait4video_done(struct msm_dsi_host *msm_host)
{
+ u32 ret = 0;
+ struct device *dev = &msm_host->pdev->dev;
+
dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 1);
reinit_completion(&msm_host->video_comp);
- wait_for_completion_timeout(&msm_host->video_comp,
+ ret = wait_for_completion_timeout(&msm_host->video_comp,
msecs_to_jiffies(70));
+ if (ret <= 0)
+ dev_err(dev, "wait for video done timed out\n");
+
dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 0);
}
if (!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
return;
- if (msm_host->power_on) {
+ if (msm_host->power_on && msm_host->enabled) {
dsi_wait4video_done(msm_host);
/* delay 4 ms to skip BLLP */
usleep_range(2000, 4000);
* pm_runtime_put_autosuspend(&msm_host->pdev->dev);
* }
*/
-
+ msm_host->enabled = true;
return 0;
}
{
struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+ msm_host->enabled = false;
dsi_op_mode_config(msm_host,
!!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO), false);
return 0;
}
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+ struct msm_dsi_phy_clk_request *clk_req)
+{
+ const unsigned long bit_rate = clk_req->bitclk_rate;
+ const unsigned long esc_rate = clk_req->escclk_rate;
+ s32 ui, ui_x8, lpx;
+ s32 tmax, tmin;
+ s32 pcnt0 = 50;
+ s32 pcnt1 = 50;
+ s32 pcnt2 = 10;
+ s32 pcnt3 = 30;
+ s32 pcnt4 = 10;
+ s32 pcnt5 = 2;
+ s32 coeff = 1000; /* Precision, should avoid overflow */
+ s32 hb_en, hb_en_ckln;
+ s32 temp;
+
+ if (!bit_rate || !esc_rate)
+ return -EINVAL;
+
+ timing->hs_halfbyte_en = 0;
+ hb_en = 0;
+ timing->hs_halfbyte_en_ckln = 0;
+ hb_en_ckln = 0;
+
+ ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
+ ui_x8 = ui << 3;
+ lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
+
+ temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
+ tmin = max_t(s32, temp, 0);
+ temp = (95 * coeff) / ui_x8;
+ tmax = max_t(s32, temp, 0);
+ timing->clk_prepare = linear_inter(tmax, tmin, pcnt0, 0, false);
+
+ temp = 300 * coeff - (timing->clk_prepare << 3) * ui;
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = (tmin > 255) ? 511 : 255;
+ timing->clk_zero = linear_inter(tmax, tmin, pcnt5, 0, false);
+
+ tmin = DIV_ROUND_UP(60 * coeff + 3 * ui, ui_x8);
+ temp = 105 * coeff + 12 * ui - 20 * coeff;
+ tmax = (temp + 3 * ui) / ui_x8;
+ timing->clk_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+ temp = S_DIV_ROUND_UP(40 * coeff + 4 * ui, ui_x8);
+ tmin = max_t(s32, temp, 0);
+ temp = (85 * coeff + 6 * ui) / ui_x8;
+ tmax = max_t(s32, temp, 0);
+ timing->hs_prepare = linear_inter(tmax, tmin, pcnt1, 0, false);
+
+ temp = 145 * coeff + 10 * ui - (timing->hs_prepare << 3) * ui;
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 255;
+ timing->hs_zero = linear_inter(tmax, tmin, pcnt4, 0, false);
+
+ tmin = DIV_ROUND_UP(60 * coeff + 4 * ui, ui_x8) - 1;
+ temp = 105 * coeff + 12 * ui - 20 * coeff;
+ tmax = (temp / ui_x8) - 1;
+ timing->hs_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+ temp = 50 * coeff + ((hb_en << 2) - 8) * ui;
+ timing->hs_rqst = S_DIV_ROUND_UP(temp, ui_x8);
+
+ tmin = DIV_ROUND_UP(100 * coeff, ui_x8) - 1;
+ tmax = 255;
+ timing->hs_exit = linear_inter(tmax, tmin, pcnt2, 0, false);
+
+ temp = 50 * coeff + ((hb_en_ckln << 2) - 8) * ui;
+ timing->hs_rqst_ckln = S_DIV_ROUND_UP(temp, ui_x8);
+
+ temp = 60 * coeff + 52 * ui - 43 * ui;
+ tmin = DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 63;
+ timing->shared_timings.clk_post =
+ linear_inter(tmax, tmin, pcnt2, 0, false);
+
+ temp = 8 * ui + (timing->clk_prepare << 3) * ui;
+ temp += (((timing->clk_zero + 3) << 3) + 11) * ui;
+ temp += hb_en_ckln ? (((timing->hs_rqst_ckln << 3) + 4) * ui) :
+ (((timing->hs_rqst_ckln << 3) + 8) * ui);
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 63;
+ if (tmin > tmax) {
+ temp = linear_inter(tmax << 1, tmin, pcnt2, 0, false);
+ timing->shared_timings.clk_pre = temp >> 1;
+ timing->shared_timings.clk_pre_inc_by_2 = 1;
+ } else {
+ timing->shared_timings.clk_pre =
+ linear_inter(tmax, tmin, pcnt2, 0, false);
+ timing->shared_timings.clk_pre_inc_by_2 = 0;
+ }
+
+ timing->ta_go = 3;
+ timing->ta_sure = 0;
+ timing->ta_get = 4;
+
+ DBG("%d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d",
+ timing->shared_timings.clk_pre, timing->shared_timings.clk_post,
+ timing->shared_timings.clk_pre_inc_by_2, timing->clk_zero,
+ timing->clk_trail, timing->clk_prepare, timing->hs_exit,
+ timing->hs_zero, timing->hs_prepare, timing->hs_trail,
+ timing->hs_rqst, timing->hs_rqst_ckln, timing->hs_halfbyte_en,
+ timing->hs_halfbyte_en_ckln, timing->hs_prep_dly,
+ timing->hs_prep_dly_ckln);
+
+ return 0;
+}
+
void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
u32 bit_mask)
{
struct msm_dsi_phy_clk_request *clk_req);
int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
struct msm_dsi_phy_clk_request *clk_req);
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+ struct msm_dsi_phy_clk_request *clk_req);
void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
u32 bit_mask);
int msm_dsi_phy_init_common(struct msm_dsi_phy *phy);
dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x04);
}
-static int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
- struct msm_dsi_phy_clk_request *clk_req)
-{
- /*
- * TODO: These params need to be computed, they're currently hardcoded
- * for a 1440x2560@60Hz panel with a byteclk of 100.618 Mhz, and a
- * default escape clock of 19.2 Mhz.
- */
-
- timing->hs_halfbyte_en = 0;
- timing->clk_zero = 0x1c;
- timing->clk_prepare = 0x07;
- timing->clk_trail = 0x07;
- timing->hs_exit = 0x23;
- timing->hs_zero = 0x21;
- timing->hs_prepare = 0x07;
- timing->hs_trail = 0x07;
- timing->hs_rqst = 0x05;
- timing->ta_sure = 0x00;
- timing->ta_go = 0x03;
- timing->ta_get = 0x04;
-
- timing->shared_timings.clk_pre = 0x2d;
- timing->shared_timings.clk_post = 0x0d;
-
- return 0;
-}
-
static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
struct msm_dsi_phy_clk_request *clk_req)
{
hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format);
vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format);
- format = kms->funcs->get_format(kms, mode_cmd->pixel_format);
+ format = kms->funcs->get_format(kms, mode_cmd->pixel_format,
+ mode_cmd->modifier[0]);
if (!format) {
dev_err(dev->dev, "unsupported pixel format: %4.4s\n",
(char *)&mode_cmd->pixel_format);
if (IS_ERR(fb)) {
dev_err(dev->dev, "failed to allocate fb\n");
- ret = PTR_ERR(fb);
- goto fail;
+ return PTR_ERR(fb);
}
bo = msm_framebuffer_bo(fb, 0);
fail_unlock:
mutex_unlock(&dev->struct_mutex);
-fail:
-
- if (ret) {
- if (fb)
- drm_framebuffer_remove(fb);
- }
-
+ drm_framebuffer_remove(fb);
return ret;
}
struct msm_gem_object *msm_obj = to_msm_bo(obj);
if (msm_obj->pages) {
- /* For non-cached buffers, ensure the new pages are clean
- * because display controller, GPU, etc. are not coherent:
- */
- if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
- dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
- msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ if (msm_obj->sgt) {
+ /* For non-cached buffers, ensure the new
+ * pages are clean because display controller,
+ * GPU, etc. are not coherent:
+ */
+ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
+ dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents,
+ DMA_BIDIRECTIONAL);
- if (msm_obj->sgt)
sg_free_table(msm_obj->sgt);
-
- kfree(msm_obj->sgt);
+ kfree(msm_obj->sgt);
+ }
if (use_pages(obj))
drm_gem_put_pages(obj, msm_obj->pages, true, false);
/* functions to wait for atomic commit completed on each CRTC */
void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
struct drm_crtc *crtc);
+ /* get msm_format w/ optional format modifiers from drm_mode_fb_cmd2 */
+ const struct msm_format *(*get_format)(struct msm_kms *kms,
+ const uint32_t format,
+ const uint64_t modifiers);
/* misc: */
- const struct msm_format *(*get_format)(struct msm_kms *kms, uint32_t format);
long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
struct drm_encoder *encoder);
int (*set_split_display)(struct msm_kms *kms,
INIT_LIST_HEAD(&nvbo->entry);
INIT_LIST_HEAD(&nvbo->vma_list);
nvbo->bo.bdev = &drm->ttm.bdev;
- nvbo->cli = cli;
/* This is confusing, and doesn't actually mean we want an uncached
* mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated
struct list_head vma_list;
- struct nouveau_cli *cli;
-
unsigned contig:1;
unsigned page:5;
unsigned kind:8;
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
drm_connector_unregister(&mstc->connector);
- drm_modeset_lock_all(drm->dev);
drm_fb_helper_remove_one_connector(&drm->fbcon->helper, &mstc->connector);
+
+ drm_modeset_lock(&drm->dev->mode_config.connection_mutex, NULL);
mstc->port = NULL;
- drm_modeset_unlock_all(drm->dev);
+ drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
drm_connector_unreference(&mstc->connector);
}
{
struct nouveau_drm *drm = nouveau_drm(connector->dev);
- drm_modeset_lock_all(drm->dev);
drm_fb_helper_add_one_connector(&drm->fbcon->helper, connector);
- drm_modeset_unlock_all(drm->dev);
drm_connector_register(connector);
}
h_coef = dispc_ovl_get_scale_coef(fir_hinc, true);
v_coef = dispc_ovl_get_scale_coef(fir_vinc, five_taps);
+ if (!h_coef || !v_coef) {
+ dev_err(&dispc->pdev->dev, "%s: failed to find scale coefs\n",
+ __func__);
+ return;
+ }
+
for (i = 0; i < 8; i++) {
u32 h, hv;
}
if (in_width > maxsinglelinewidth) {
- DSSERR("Cannot scale max input width exceeded");
+ DSSERR("Cannot scale max input width exceeded\n");
return -EINVAL;
}
return 0;
}
if (in_width > (maxsinglelinewidth * 2)) {
- DSSERR("Cannot setup scaling");
- DSSERR("width exceeds maximum width possible");
+ DSSERR("Cannot setup scaling\n");
+ DSSERR("width exceeds maximum width possible\n");
return -EINVAL;
}
if (in_width > maxsinglelinewidth && *five_taps) {
- DSSERR("cannot setup scaling with five taps");
+ DSSERR("cannot setup scaling with five taps\n");
return -EINVAL;
}
return 0;
in_width > maxsinglelinewidth && ++*decim_x);
if (in_width > maxsinglelinewidth) {
- DSSERR("Cannot scale width exceeds max line width");
+ DSSERR("Cannot scale width exceeds max line width\n");
return -EINVAL;
}
* bandwidth. Despite what theory says this appears to
* be true also for 16-bit color formats.
*/
- DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)", *decim_x);
+ DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)\n", *decim_x);
return -EINVAL;
}
i734_buf.size, &i734_buf.paddr,
GFP_KERNEL);
if (!i734_buf.vaddr) {
- dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed",
+ dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed\n",
__func__);
return -ENOMEM;
}
struct omap_dss_audio *dss_audio)
{
struct omap_hdmi *hd = dev_get_drvdata(dev);
- int ret;
+ int ret = 0;
mutex_lock(&hd->lock);
{
const struct hdmi4_features *features;
struct resource *res;
+ const struct soc_device_attribute *soc;
- features = soc_device_match(hdmi4_soc_devices)->data;
+ soc = soc_device_match(hdmi4_soc_devices);
+ if (!soc)
+ return -ENODEV;
+
+ features = soc->data;
core->cts_swmode = features->cts_swmode;
core->audio_use_mclk = features->audio_use_mclk;
struct omap_dss_audio *dss_audio)
{
struct omap_hdmi *hd = dev_get_drvdata(dev);
- int ret;
+ int ret = 0;
mutex_lock(&hd->lock);
if (dssdrv->read_edid) {
void *edid = kzalloc(MAX_EDID, GFP_KERNEL);
+ if (!edid)
+ return 0;
+
if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
drm_edid_is_valid(edid)) {
drm_mode_connector_update_edid_property(
struct drm_display_mode *mode = drm_mode_create(dev);
struct videomode vm = {0};
+ if (!mode)
+ return 0;
+
dssdrv->get_timings(dssdev, &vm);
drm_display_mode_from_videomode(&vm, mode);
if (!r) {
/* check if vrefresh is still valid */
new_mode = drm_mode_duplicate(dev, mode);
+
+ if (!new_mode)
+ return MODE_BAD;
+
new_mode->clock = vm.pixelclock / 1000;
new_mode->vrefresh = 0;
if (mode->vrefresh == drm_mode_vrefresh(new_mode))
struct tiler_block *tiler_reserve_2d(enum tiler_fmt fmt, u16 w,
u16 h, u16 align)
{
- struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
+ struct tiler_block *block;
u32 min_align = 128;
int ret;
unsigned long flags;
u32 slot_bytes;
+ block = kzalloc(sizeof(*block), GFP_KERNEL);
+ if (!block)
+ return ERR_PTR(-ENOMEM);
+
BUG_ON(!validfmt(fmt));
/* convert width/height to slots */
{
int i;
unsigned long index;
- bool area_free;
+ bool area_free = false;
unsigned long slots_per_band = PAGE_SIZE / slot_bytes;
unsigned long bit_offset = (offset > 0) ? offset / slot_bytes : 0;
unsigned long curr_bit = bit_offset;
uint32_t type, bool interruptible)
{
struct qxl_command cmd;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
cmd.type = type;
- cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+ cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
return qxl_ring_push(qdev->command_ring, &cmd, interruptible);
}
uint32_t type, bool interruptible)
{
struct qxl_command cmd;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
cmd.type = type;
- cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+ cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible);
}
int id;
int type;
+ struct qxl_bo *release_bo;
uint32_t release_offset;
uint32_t surface_release_id;
struct ww_acquire_ctx ticket;
goto out_free_reloc;
/* TODO copy slow path code from i915 */
- fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE));
+ fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_MASK));
unwritten = __copy_from_user_inatomic_nocache
- (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE),
+ (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_MASK),
u64_to_user_ptr(cmd->command), cmd->command_size);
{
list_del(&entry->tv.head);
kfree(entry);
}
+ release->release_bo = NULL;
}
void
{
if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) {
int idr_ret;
- struct qxl_bo_list *entry = list_first_entry(&create_rel->bos, struct qxl_bo_list, tv.head);
struct qxl_bo *bo;
union qxl_release_info *info;
idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release);
if (idr_ret < 0)
return idr_ret;
- bo = to_qxl_bo(entry->tv.bo);
+ bo = create_rel->release_bo;
+ (*release)->release_bo = bo;
(*release)->release_offset = create_rel->release_offset + 64;
qxl_release_list_add(*release, bo);
bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]);
+ (*release)->release_bo = bo;
(*release)->release_offset = qdev->current_release_bo_offset[cur_idx] * release_size_per_bo[cur_idx];
qdev->current_release_bo_offset[cur_idx]++;
{
void *ptr;
union qxl_release_info *info;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
- struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+ struct qxl_bo *bo = release->release_bo;
- ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_SIZE);
+ ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_MASK);
if (!ptr)
return NULL;
- info = ptr + (release->release_offset & ~PAGE_SIZE);
+ info = ptr + (release->release_offset & ~PAGE_MASK);
return info;
}
struct qxl_release *release,
union qxl_release_info *info)
{
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
- struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+ struct qxl_bo *bo = release->release_bo;
void *ptr;
- ptr = ((void *)info) - (release->release_offset & ~PAGE_SIZE);
+ ptr = ((void *)info) - (release->release_offset & ~PAGE_MASK);
qxl_bo_kunmap_atomic_page(qdev, bo, ptr);
}
}
}
-static enum drm_mode_status sun4i_lvds_encoder_mode_valid(struct drm_encoder *crtc,
- const struct drm_display_mode *mode)
-{
- struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(crtc);
- struct sun4i_tcon *tcon = lvds->tcon;
- u32 hsync = mode->hsync_end - mode->hsync_start;
- u32 vsync = mode->vsync_end - mode->vsync_start;
- unsigned long rate = mode->clock * 1000;
- long rounded_rate;
-
- DRM_DEBUG_DRIVER("Validating modes...\n");
-
- if (hsync < 1)
- return MODE_HSYNC_NARROW;
-
- if (hsync > 0x3ff)
- return MODE_HSYNC_WIDE;
-
- if ((mode->hdisplay < 1) || (mode->htotal < 1))
- return MODE_H_ILLEGAL;
-
- if ((mode->hdisplay > 0x7ff) || (mode->htotal > 0xfff))
- return MODE_BAD_HVALUE;
-
- DRM_DEBUG_DRIVER("Horizontal parameters OK\n");
-
- if (vsync < 1)
- return MODE_VSYNC_NARROW;
-
- if (vsync > 0x3ff)
- return MODE_VSYNC_WIDE;
-
- if ((mode->vdisplay < 1) || (mode->vtotal < 1))
- return MODE_V_ILLEGAL;
-
- if ((mode->vdisplay > 0x7ff) || (mode->vtotal > 0xfff))
- return MODE_BAD_VVALUE;
-
- DRM_DEBUG_DRIVER("Vertical parameters OK\n");
-
- tcon->dclk_min_div = 7;
- tcon->dclk_max_div = 7;
- rounded_rate = clk_round_rate(tcon->dclk, rate);
- if (rounded_rate < rate)
- return MODE_CLOCK_LOW;
-
- if (rounded_rate > rate)
- return MODE_CLOCK_HIGH;
-
- DRM_DEBUG_DRIVER("Clock rate OK\n");
-
- return MODE_OK;
-}
-
static const struct drm_encoder_helper_funcs sun4i_lvds_enc_helper_funcs = {
.disable = sun4i_lvds_encoder_disable,
.enable = sun4i_lvds_encoder_enable,
- .mode_valid = sun4i_lvds_encoder_mode_valid,
};
static const struct drm_encoder_funcs sun4i_lvds_enc_funcs = {
while (npages >= HPAGE_PMD_NR) {
gfp_t huge_flags = gfp_flags;
- huge_flags |= GFP_TRANSHUGE;
+ huge_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM;
huge_flags &= ~__GFP_MOVABLE;
huge_flags &= ~__GFP_COMP;
p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
GFP_USER | GFP_DMA32, "uc dma", 0);
ttm_page_pool_init_locked(&_manager->wc_pool_huge,
- GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP),
+ (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM) &
+ ~(__GFP_MOVABLE | __GFP_COMP),
"wc huge", order);
ttm_page_pool_init_locked(&_manager->uc_pool_huge,
- GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP)
+ (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM) &
+ ~(__GFP_MOVABLE | __GFP_COMP)
, "uc huge", order);
_manager->options.max_size = max_pages;
gfp_flags |= __GFP_ZERO;
if (huge) {
- gfp_flags |= GFP_TRANSHUGE;
+ gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM;
gfp_flags &= ~__GFP_MOVABLE;
gfp_flags &= ~__GFP_COMP;
}
vc4_bo_set_label(obj, -1);
if (bo->validated_shader) {
+ kfree(bo->validated_shader->uniform_addr_offsets);
kfree(bo->validated_shader->texture_samples);
kfree(bo->validated_shader);
bo->validated_shader = NULL;
}
if (bo->validated_shader) {
+ kfree(bo->validated_shader->uniform_addr_offsets);
kfree(bo->validated_shader->texture_samples);
kfree(bo->validated_shader);
bo->validated_shader = NULL;
struct vc4_async_flip_state {
struct drm_crtc *crtc;
struct drm_framebuffer *fb;
+ struct drm_framebuffer *old_fb;
struct drm_pending_vblank_event *event;
struct vc4_seqno_cb cb;
drm_crtc_vblank_put(crtc);
drm_framebuffer_put(flip_state->fb);
+
+ /* Decrement the BO usecnt in order to keep the inc/dec calls balanced
+ * when the planes are updated through the async update path.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made cleanup_fb()
+ * logic.
+ */
+ if (flip_state->old_fb) {
+ struct drm_gem_cma_object *cma_bo;
+ struct vc4_bo *bo;
+
+ cma_bo = drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
+ bo = to_vc4_bo(&cma_bo->base);
+ vc4_bo_dec_usecnt(bo);
+ drm_framebuffer_put(flip_state->old_fb);
+ }
+
kfree(flip_state);
up(&vc4->async_modeset);
struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+ /* Increment the BO usecnt here, so that we never end up with an
+ * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the
+ * plane is later updated through the non-async path.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made prepare_fb()
+ * logic.
+ */
+ ret = vc4_bo_inc_usecnt(bo);
+ if (ret)
+ return ret;
+
flip_state = kzalloc(sizeof(*flip_state), GFP_KERNEL);
- if (!flip_state)
+ if (!flip_state) {
+ vc4_bo_dec_usecnt(bo);
return -ENOMEM;
+ }
drm_framebuffer_get(fb);
flip_state->fb = fb;
ret = down_interruptible(&vc4->async_modeset);
if (ret) {
drm_framebuffer_put(fb);
+ vc4_bo_dec_usecnt(bo);
kfree(flip_state);
return ret;
}
+ /* Save the current FB before it's replaced by the new one in
+ * drm_atomic_set_fb_for_plane(). We'll need the old FB in
+ * vc4_async_page_flip_complete() to decrement the BO usecnt and keep
+ * it consistent.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made cleanup_fb()
+ * logic.
+ */
+ flip_state->old_fb = plane->state->fb;
+ if (flip_state->old_fb)
+ drm_framebuffer_get(flip_state->old_fb);
+
WARN_ON(drm_crtc_vblank_get(crtc) != 0);
/* Immediately update the plane's legacy fb pointer, so that later
struct platform_device *pdev;
struct drm_encoder *encoder;
- struct drm_connector *connector;
void __iomem *regs;
static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
{
+ struct drm_device *dev = encoder->dev;
struct drm_display_mode *mode = &encoder->crtc->mode;
struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder);
struct vc4_dpi *dpi = vc4_encoder->dpi;
+ struct drm_connector_list_iter conn_iter;
+ struct drm_connector *connector = NULL, *connector_scan;
u32 dpi_c = DPI_ENABLE | DPI_OUTPUT_ENABLE_MODE;
int ret;
- if (dpi->connector->display_info.num_bus_formats) {
- u32 bus_format = dpi->connector->display_info.bus_formats[0];
+ /* Look up the connector attached to DPI so we can get the
+ * bus_format. Ideally the bridge would tell us the
+ * bus_format we want, but it doesn't yet, so assume that it's
+ * uniform throughout the bridge chain.
+ */
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ drm_for_each_connector_iter(connector_scan, &conn_iter) {
+ if (connector_scan->encoder == encoder) {
+ connector = connector_scan;
+ break;
+ }
+ }
+ drm_connector_list_iter_end(&conn_iter);
+
+ if (connector && connector->display_info.num_bus_formats) {
+ u32 bus_format = connector->display_info.bus_formats[0];
switch (bus_format) {
case MEDIA_BUS_FMT_RGB888_1X24:
DRM_ERROR("Unknown media bus format %d\n", bus_format);
break;
}
+ } else {
+ /* Default to 24bit if no connector found. */
+ dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, DPI_FORMAT);
}
if (mode->flags & DRM_MODE_FLAG_NHSYNC)
struct vc4_file *vc4file = file->driver_priv;
vc4_perfmon_close_file(vc4file);
+ kfree(vc4file);
}
static const struct vm_operations_struct vc4_vm_ops = {
* the scl fields here.
*/
if (num_planes == 1) {
- scl0 = vc4_get_scl_field(state, 1);
+ scl0 = vc4_get_scl_field(state, 0);
scl1 = scl0;
} else {
scl0 = vc4_get_scl_field(state, 1);
fail:
kfree(validation_state.branch_targets);
if (validated_shader) {
+ kfree(validated_shader->uniform_addr_offsets);
kfree(validated_shader->texture_samples);
kfree(validated_shader);
}
ret = virtqueue_add_sgs(vq, sgs, outcnt, incnt, vbuf, GFP_ATOMIC);
if (ret == -ENOSPC) {
spin_unlock(&vgdev->ctrlq.qlock);
- wait_event(vgdev->ctrlq.ack_queue, vq->num_free);
+ wait_event(vgdev->ctrlq.ack_queue, vq->num_free >= outcnt + incnt);
spin_lock(&vgdev->ctrlq.qlock);
goto retry;
} else {
ret = virtqueue_add_sgs(vq, sgs, outcnt, 0, vbuf, GFP_ATOMIC);
if (ret == -ENOSPC) {
spin_unlock(&vgdev->cursorq.qlock);
- wait_event(vgdev->cursorq.ack_queue, vq->num_free);
+ wait_event(vgdev->cursorq.ack_queue, vq->num_free >= outcnt);
spin_lock(&vgdev->cursorq.qlock);
goto retry;
} else {
struct drm_crtc *crtc = set->crtc;
struct drm_framebuffer *fb;
struct drm_crtc *tmp;
- struct drm_modeset_acquire_ctx *ctx;
struct drm_device *dev = set->crtc->dev;
+ struct drm_modeset_acquire_ctx ctx;
int ret;
- ctx = dev->mode_config.acquire_ctx;
+ drm_modeset_acquire_init(&ctx, 0);
restart:
/*
fb = set->fb;
- ret = crtc->funcs->set_config(set, ctx);
+ ret = crtc->funcs->set_config(set, &ctx);
if (ret == 0) {
crtc->primary->crtc = crtc;
crtc->primary->fb = fb;
}
if (ret == -EDEADLK) {
- dev->mode_config.acquire_ctx = NULL;
-
-retry_locking:
- drm_modeset_backoff(ctx);
-
- ret = drm_modeset_lock_all_ctx(dev, ctx);
- if (ret)
- goto retry_locking;
-
- dev->mode_config.acquire_ctx = ctx;
-
+ drm_modeset_backoff(&ctx);
goto restart;
}
+ drm_modeset_drop_locks(&ctx);
+ drm_modeset_acquire_fini(&ctx);
+
return ret;
}
}
mutex_lock(&par->bo_mutex);
- drm_modeset_lock_all(vmw_priv->dev);
ret = vmw_fb_kms_framebuffer(info);
if (ret)
goto out_unlock;
drm_mode_destroy(vmw_priv->dev, old_mode);
par->set_mode = mode;
- drm_modeset_unlock_all(vmw_priv->dev);
mutex_unlock(&par->bo_mutex);
return ret;
par->max_width = fb_width;
par->max_height = fb_height;
- drm_modeset_lock_all(vmw_priv->dev);
ret = vmw_kms_fbdev_init_data(vmw_priv, 0, par->max_width,
par->max_height, &par->con,
&par->crtc, &init_mode);
- if (ret) {
- drm_modeset_unlock_all(vmw_priv->dev);
+ if (ret)
goto err_kms;
- }
info->var.xres = init_mode->hdisplay;
info->var.yres = init_mode->vdisplay;
- drm_modeset_unlock_all(vmw_priv->dev);
/*
* Create buffers and alloc memory
cancel_delayed_work_sync(&par->local_work);
unregister_framebuffer(info);
+ mutex_lock(&par->bo_mutex);
(void) vmw_fb_kms_detach(par, true, true);
+ mutex_unlock(&par->bo_mutex);
vfree(par->vmalloc);
framebuffer_release(info);
vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
out_fence, NULL);
+ vmw_dmabuf_unreference(&ctx->buf);
vmw_resource_unreserve(res, false, NULL, 0);
mutex_unlock(&res->dev_priv->cmdbuf_mutex);
}
struct vmw_display_unit *du;
struct drm_display_mode *mode;
int i = 0;
+ int ret = 0;
+ mutex_lock(&dev_priv->dev->mode_config.mutex);
list_for_each_entry(con, &dev_priv->dev->mode_config.connector_list,
head) {
if (i == unit)
if (i != unit) {
DRM_ERROR("Could not find initial display unit.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
if (list_empty(&con->modes))
if (list_empty(&con->modes)) {
DRM_ERROR("Could not find initial display mode.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
du = vmw_connector_to_du(con);
head);
}
- return 0;
+ out_unlock:
+ mutex_unlock(&dev_priv->dev->mode_config.mutex);
+
+ return ret;
}
/**
return ret;
}
+ vps->dmabuf_size = size;
+
/*
* TTM already thinks the buffer is pinned, but make sure the
* pin_count is upped.
select NEW_LEDS
select LEDS_CLASS
---help---
- Support for Lenovo devices that are not fully compliant with HID standard.
+ Support for IBM/Lenovo devices that are not fully compliant with HID standard.
- Say Y if you want support for the non-compliant features of the Lenovo
- Thinkpad standalone keyboards, e.g:
+ Say Y if you want support for horizontal scrolling of the IBM/Lenovo
+ Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad
+ standalone keyboards, e.g:
- ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint
configuration)
- ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys)
#define USB_VENDOR_ID_HUION 0x256c
#define USB_DEVICE_ID_HUION_TABLET 0x006e
+#define USB_VENDOR_ID_IBM 0x04b3
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_III 0x3100
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_PRO 0x3103
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL 0x3105
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL 0x3108
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO 0x3109
+
#define USB_VENDOR_ID_IDEACOM 0x1cb6
#define USB_DEVICE_ID_IDEACOM_IDC6650 0x6650
#define USB_DEVICE_ID_IDEACOM_IDC6651 0x6651
#define USB_DEVICE_ID_LENOVO_TPKBD 0x6009
#define USB_DEVICE_ID_LENOVO_CUSBKBD 0x6047
#define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048
+#define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL 0x6049
#define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067
#define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085
#define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3
#define USB_DEVICE_ID_SIS817_TOUCH 0x0817
#define USB_DEVICE_ID_SIS_TS 0x1013
#define USB_DEVICE_ID_SIS1030_TOUCH 0x1030
+#define USB_DEVICE_ID_SIS10FB_TOUCH 0x10fb
#define USB_VENDOR_ID_SKYCABLE 0x1223
#define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07
*
* Copyright (c) 2012 Bernhard Seibold
* Copyright (c) 2014 Jamie Lentin <jm@lentin.co.uk>
+ *
+ * Linux IBM/Lenovo Scrollpoint mouse driver:
+ * - IBM Scrollpoint III
+ * - IBM Scrollpoint Pro
+ * - IBM Scrollpoint Optical
+ * - IBM Scrollpoint Optical 800dpi
+ * - IBM Scrollpoint Optical 800dpi Pro
+ * - Lenovo Scrollpoint Optical
+ *
+ * Copyright (c) 2012 Peter De Wachter <pdewacht@gmail.com>
+ * Copyright (c) 2018 Peter Ganzhorn <peter.ganzhorn@gmail.com>
*/
/*
return 0;
}
+static int lenovo_input_mapping_scrollpoint(struct hid_device *hdev,
+ struct hid_input *hi, struct hid_field *field,
+ struct hid_usage *usage, unsigned long **bit, int *max)
+{
+ if (usage->hid == HID_GD_Z) {
+ hid_map_usage(hi, usage, bit, max, EV_REL, REL_HWHEEL);
+ return 1;
+ }
+ return 0;
+}
+
static int lenovo_input_mapping(struct hid_device *hdev,
struct hid_input *hi, struct hid_field *field,
struct hid_usage *usage, unsigned long **bit, int *max)
case USB_DEVICE_ID_LENOVO_CBTKBD:
return lenovo_input_mapping_cptkbd(hdev, hi, field,
usage, bit, max);
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_III:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_PRO:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO:
+ case USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL:
+ return lenovo_input_mapping_scrollpoint(hdev, hi, field,
+ usage, bit, max);
default:
return 0;
}
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_III) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_PRO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL) },
{ }
};
I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
{ I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118,
I2C_HID_QUIRK_RESEND_REPORT_DESCR },
+ { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH,
+ I2C_HID_QUIRK_RESEND_REPORT_DESCR },
{ 0, 0 }
};
struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data;
int curr_hid_dev = client_data->cur_hid_dev;
- if (data_len < sizeof(struct hostif_msg_hdr)) {
- dev_err(&client_data->cl_device->dev,
- "[hid-ish]: error, received %u which is less than data header %u\n",
- (unsigned int)data_len,
- (unsigned int)sizeof(struct hostif_msg_hdr));
- ++client_data->bad_recv_cnt;
- ish_hw_reset(hid_ishtp_cl->dev);
- return;
- }
-
payload = recv_buf + sizeof(struct hostif_msg_hdr);
total_len = data_len;
cur_pos = 0;
do {
+ if (cur_pos + sizeof(struct hostif_msg) > total_len) {
+ dev_err(&client_data->cl_device->dev,
+ "[hid-ish]: error, received %u which is less than data header %u\n",
+ (unsigned int)data_len,
+ (unsigned int)sizeof(struct hostif_msg_hdr));
+ ++client_data->bad_recv_cnt;
+ ish_hw_reset(hid_ishtp_cl->dev);
+ break;
+ }
+
recv_msg = (struct hostif_msg *)(recv_buf + cur_pos);
payload_len = recv_msg->hdr.size;
{
struct ishtp_hid_data *hid_data = hid->driver_data;
struct ishtp_cl_data *client_data = hid_data->client_data;
- static unsigned char buf[10];
- unsigned int len;
- struct hostif_msg_to_sensor *msg = (struct hostif_msg_to_sensor *)buf;
+ struct hostif_msg_to_sensor msg = {};
int rv;
int i;
return;
}
- len = sizeof(struct hostif_msg_to_sensor);
-
- memset(msg, 0, sizeof(struct hostif_msg_to_sensor));
- msg->hdr.command = (report_type == HID_FEATURE_REPORT) ?
+ msg.hdr.command = (report_type == HID_FEATURE_REPORT) ?
HOSTIF_GET_FEATURE_REPORT : HOSTIF_GET_INPUT_REPORT;
for (i = 0; i < client_data->num_hid_devices; ++i) {
if (hid == client_data->hid_sensor_hubs[i]) {
- msg->hdr.device_id =
+ msg.hdr.device_id =
client_data->hid_devices[i].dev_id;
break;
}
if (i == client_data->num_hid_devices)
return;
- msg->report_id = report_id;
- rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len);
+ msg.report_id = report_id;
+ rv = ishtp_cl_send(client_data->hid_ishtp_cl, (uint8_t *)&msg,
+ sizeof(msg));
if (rv)
hid_ishtp_trace(client_data, "%s hid %p send failed\n",
__func__, hid);
list_del(&device->device_link);
spin_unlock_irqrestore(&dev->device_list_lock, flags);
dev_err(dev->devc, "Failed to register ISHTP client device\n");
- kfree(device);
+ put_device(&device->dev);
return NULL;
}
devres->root = root;
error = sysfs_create_group(devres->root, group);
- if (error)
+ if (error) {
+ devres_free(devres);
return error;
+ }
devres_add(&wacom->hdev->dev, devres);
config SENSORS_K10TEMP
tristate "AMD Family 10h+ temperature sensor"
- depends on X86 && PCI
+ depends on X86 && PCI && AMD_NB
help
If you say yes here you get support for the temperature
sensor(s) inside your CPU. Supported are later revisions of
#include <linux/init.h>
#include <linux/module.h>
#include <linux/pci.h>
+#include <asm/amd_nb.h>
#include <asm/processor.h>
MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor");
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#endif
+#ifndef PCI_DEVICE_ID_AMD_17H_M10H_DF_F3
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#endif
+
/* CPUID function 0x80000001, ebx */
#define CPUID_PKGTYPE_MASK 0xf0000000
#define CPUID_PKGTYPE_F 0x00000000
#define NB_CAP_HTC 0x00000400
/*
- * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE
- * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature
- * Control]
+ * For F15h M60h and M70h, REG_HARDWARE_THERMAL_CONTROL
+ * and REG_REPORTED_TEMPERATURE have been moved to
+ * D0F0xBC_xD820_0C64 [Hardware Temperature Control]
+ * D0F0xBC_xD820_0CA4 [Reported Temperature Control]
*/
+#define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET 0xd8200c64
#define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET 0xd8200ca4
/* F17h M01h Access througn SMN */
struct k10temp_data {
struct pci_dev *pdev;
+ void (*read_htcreg)(struct pci_dev *pdev, u32 *regval);
void (*read_tempreg)(struct pci_dev *pdev, u32 *regval);
int temp_offset;
+ u32 temp_adjust_mask;
};
struct tctl_offset {
{ 0x17, "AMD Ryzen 5 1600X", 20000 },
{ 0x17, "AMD Ryzen 7 1700X", 20000 },
{ 0x17, "AMD Ryzen 7 1800X", 20000 },
+ { 0x17, "AMD Ryzen 7 2700X", 10000 },
{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
};
+static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
+{
+ pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval);
+}
+
static void read_tempreg_pci(struct pci_dev *pdev, u32 *regval)
{
pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, regval);
mutex_unlock(&nb_smu_ind_mutex);
}
+static void read_htcreg_nb_f15(struct pci_dev *pdev, u32 *regval)
+{
+ amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
+ F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET, regval);
+}
+
static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
{
amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval)
{
- amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60,
- F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
+ amd_smn_read(amd_pci_dev_to_node_id(pdev),
+ F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
}
static ssize_t temp1_input_show(struct device *dev,
data->read_tempreg(data->pdev, ®val);
temp = (regval >> 21) * 125;
+ if (regval & data->temp_adjust_mask)
+ temp -= 49000;
if (temp > data->temp_offset)
temp -= data->temp_offset;
else
u32 regval;
int value;
- pci_read_config_dword(data->pdev,
- REG_HARDWARE_THERMAL_CONTROL, ®val);
+ data->read_htcreg(data->pdev, ®val);
value = ((regval >> 16) & 0x7f) * 500 + 52000;
if (show_hyst)
value -= ((regval >> 24) & 0xf) * 500;
struct pci_dev *pdev = data->pdev;
if (index >= 2) {
- u32 reg_caps, reg_htc;
+ u32 reg;
+
+ if (!data->read_htcreg)
+ return 0;
pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES,
- ®_caps);
- pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL,
- ®_htc);
- if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE))
+ ®);
+ if (!(reg & NB_CAP_HTC))
+ return 0;
+
+ data->read_htcreg(data->pdev, ®);
+ if (!(reg & HTC_ENABLE))
return 0;
}
return attr->mode;
data->pdev = pdev;
if (boot_cpu_data.x86 == 0x15 && (boot_cpu_data.x86_model == 0x60 ||
- boot_cpu_data.x86_model == 0x70))
+ boot_cpu_data.x86_model == 0x70)) {
+ data->read_htcreg = read_htcreg_nb_f15;
data->read_tempreg = read_tempreg_nb_f15;
- else if (boot_cpu_data.x86 == 0x17)
+ } else if (boot_cpu_data.x86 == 0x17) {
+ data->temp_adjust_mask = 0x80000;
data->read_tempreg = read_tempreg_nb_f17;
- else
+ } else {
+ data->read_htcreg = read_htcreg_pci;
data->read_tempreg = read_tempreg_pci;
+ }
for (i = 0; i < ARRAY_SIZE(tctl_offset_table); i++) {
const struct tctl_offset *entry = &tctl_offset_table[i];
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{}
};
MODULE_DEVICE_TABLE(pci, k10temp_id_table);
/* Activate logical device if needed */
val = superio_inb(sioaddr, SIO_REG_ENABLE);
if (!(val & 0x01)) {
- pr_err("EC is disabled\n");
- goto fail;
+ pr_warn("Forcibly enabling EC access. Data may be unusable.\n");
+ superio_outb(sioaddr, SIO_REG_ENABLE, val | 0x01);
}
superio_exit(sioaddr);
scmi_chip_info.info = ptr_scmi_ci;
chip_info = &scmi_chip_info;
- for (type = 0; type < hwmon_max && nr_count[type]; type++) {
+ for (type = 0; type < hwmon_max; type++) {
+ if (!nr_count[type])
+ continue;
+
scmi_hwmon_add_chan_info(scmi_hwmon_chan, dev, nr_count[type],
type, hwmon_attributes[type]);
*ptr_scmi_ci++ = scmi_hwmon_chan++;
config I2C_MT65XX
tristate "MediaTek I2C adapter"
depends on ARCH_MEDIATEK || COMPILE_TEST
- depends on HAS_DMA
help
This selects the MediaTek(R) Integrated Inter Circuit bus driver
for MT65xx and MT81xx.
config I2C_SH_MOBILE
tristate "SuperH Mobile I2C Controller"
- depends on HAS_DMA
depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST
help
If you say yes to this option, support will be included for the
config I2C_RCAR
tristate "Renesas R-Car I2C Controller"
- depends on HAS_DMA
depends on ARCH_RENESAS || COMPILE_TEST
select I2C_SLAVE
help
i2c_dw_disable_int(dev);
/* Enable the adapter */
- __i2c_dw_enable_and_wait(dev, true);
+ __i2c_dw_enable(dev, true);
+
+ /* Dummy read to avoid the register getting stuck on Bay Trail */
+ dw_readl(dev, DW_IC_ENABLE_STATUS);
/* Clear and enable interrupts */
dw_readl(dev, DW_IC_CLR_INTR);
* TODO: We could potentially loop and retry in the case
* of MSP_TWI_XFER_TIMEOUT.
*/
- return -1;
+ return -EIO;
}
- return 0;
+ return num;
}
static u32 pmcmsptwi_i2c_func(struct i2c_adapter *adapter)
u32 count;
int irq;
int err;
+ bool is_suspended;
};
static void sprd_i2c_set_count(struct sprd_i2c *i2c_dev, u32 count)
struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
int im, ret;
+ if (i2c_dev->is_suspended)
+ return -EBUSY;
+
ret = pm_runtime_get_sync(i2c_dev->dev);
if (ret < 0)
return ret;
struct sprd_i2c *i2c_dev = dev_id;
struct i2c_msg *msg = i2c_dev->msg;
bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
- u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
u32 i2c_tran;
if (msg->flags & I2C_M_RD)
i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
else
- i2c_tran = i2c_count;
+ i2c_tran = i2c_dev->count;
/*
* If we got one ACK from slave when writing data, and we did not
{
struct sprd_i2c *i2c_dev = dev_id;
struct i2c_msg *msg = i2c_dev->msg;
- u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
u32 i2c_tran;
if (msg->flags & I2C_M_RD)
i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
else
- i2c_tran = i2c_count;
+ i2c_tran = i2c_dev->count;
/*
* If we did not get one ACK from slave when writing data, then we
static int __maybe_unused sprd_i2c_suspend_noirq(struct device *pdev)
{
+ struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+ i2c_lock_adapter(&i2c_dev->adap);
+ i2c_dev->is_suspended = true;
+ i2c_unlock_adapter(&i2c_dev->adap);
+
return pm_runtime_force_suspend(pdev);
}
static int __maybe_unused sprd_i2c_resume_noirq(struct device *pdev)
{
+ struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+ i2c_lock_adapter(&i2c_dev->adap);
+ i2c_dev->is_suspended = false;
+ i2c_unlock_adapter(&i2c_dev->adap);
+
return pm_runtime_force_resume(pdev);
}
}
mutex_unlock(&vb->lock);
}
- return 0;
+ return num;
error:
mutex_unlock(&vb->lock);
return error;
msgs[1].buf = buffer;
ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
- if (ret < 0)
- dev_err(&client->adapter->dev, "i2c read failed\n");
- else
+ if (ret < 0) {
+ /* Getting a NACK is unfortunately normal with some DSTDs */
+ if (ret == -EREMOTEIO)
+ dev_dbg(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+ data_len, client->addr, cmd, ret);
+ else
+ dev_err(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+ data_len, client->addr, cmd, ret);
+ } else {
memcpy(data, buffer, data_len);
+ }
kfree(buffer);
return ret;
*/
if (msgs[i].flags & I2C_M_RECV_LEN) {
if (!(msgs[i].flags & I2C_M_RD) ||
- msgs[i].buf[0] < 1 ||
+ msgs[i].len < 1 || msgs[i].buf[0] < 1 ||
msgs[i].len < msgs[i].buf[0] +
I2C_SMBUS_BLOCK_MAX) {
res = -EINVAL;
pages on demand instead.
config INFINIBAND_ADDR_TRANS
- bool
+ bool "RDMA/CM"
depends on INFINIBAND
default y
+ ---help---
+ Support for RDMA communication manager (CM).
+ This allows for a generic connection abstraction over RDMA.
config INFINIBAND_ADDR_TRANS_CONFIGFS
bool
* so lookup free slot only if requested.
*/
if (pempty && empty < 0) {
- if (data->props & GID_TABLE_ENTRY_INVALID) {
- /* Found an invalid (free) entry; allocate it */
- if (data->props & GID_TABLE_ENTRY_DEFAULT) {
- if (default_gid)
- empty = curr_index;
- } else {
- empty = curr_index;
- }
+ if (data->props & GID_TABLE_ENTRY_INVALID &&
+ (default_gid ==
+ !!(data->props & GID_TABLE_ENTRY_DEFAULT))) {
+ /*
+ * Found an invalid (free) entry; allocate it.
+ * If default GID is requested, then our
+ * found slot must be one of the DEFAULT
+ * reserved slots or we fail.
+ * This ensures that only DEFAULT reserved
+ * slots are used for default property GIDs.
+ */
+ empty = curr_index;
}
}
return ret;
}
-int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
- union ib_gid *gid, struct ib_gid_attr *attr)
+static int
+_ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+ union ib_gid *gid, struct ib_gid_attr *attr,
+ unsigned long mask, bool default_gid)
{
struct ib_gid_table *table;
int ret = 0;
mutex_lock(&table->lock);
- ix = find_gid(table, gid, attr, false,
- GID_ATTR_FIND_MASK_GID |
- GID_ATTR_FIND_MASK_GID_TYPE |
- GID_ATTR_FIND_MASK_NETDEV,
- NULL);
+ ix = find_gid(table, gid, attr, default_gid, mask, NULL);
if (ix < 0) {
ret = -EINVAL;
goto out_unlock;
return ret;
}
+int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+ union ib_gid *gid, struct ib_gid_attr *attr)
+{
+ unsigned long mask = GID_ATTR_FIND_MASK_GID |
+ GID_ATTR_FIND_MASK_GID_TYPE |
+ GID_ATTR_FIND_MASK_DEFAULT |
+ GID_ATTR_FIND_MASK_NETDEV;
+
+ return _ib_cache_gid_del(ib_dev, port, gid, attr, mask, false);
+}
+
int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
struct net_device *ndev)
{
unsigned long gid_type_mask,
enum ib_cache_gid_default_mode mode)
{
- union ib_gid gid;
+ union ib_gid gid = { };
struct ib_gid_attr gid_attr;
struct ib_gid_table *table;
unsigned int gid_type;
table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
- make_default_gid(ndev, &gid);
+ mask = GID_ATTR_FIND_MASK_GID_TYPE |
+ GID_ATTR_FIND_MASK_DEFAULT |
+ GID_ATTR_FIND_MASK_NETDEV;
memset(&gid_attr, 0, sizeof(gid_attr));
gid_attr.ndev = ndev;
gid_attr.gid_type = gid_type;
if (mode == IB_CACHE_GID_DEFAULT_MODE_SET) {
- mask = GID_ATTR_FIND_MASK_GID_TYPE |
- GID_ATTR_FIND_MASK_DEFAULT;
+ make_default_gid(ndev, &gid);
__ib_cache_gid_add(ib_dev, port, &gid,
&gid_attr, mask, true);
} else if (mode == IB_CACHE_GID_DEFAULT_MODE_DELETE) {
- ib_cache_gid_del(ib_dev, port, &gid, &gid_attr);
+ _ib_cache_gid_del(ib_dev, port, &gid,
+ &gid_attr, mask, true);
}
}
}
#define CMA_VERSION 0x00
struct cma_req_info {
+ struct sockaddr_storage listen_addr_storage;
+ struct sockaddr_storage src_addr_storage;
struct ib_device *device;
int port;
union ib_gid local_gid;
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
- union ib_gid sgid;
mutex_lock(&id_priv->qp_mutex);
if (!id_priv->id.qp) {
if (ret)
goto out;
- ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
- rdma_ah_read_grh(&qp_attr.ah_attr)->sgid_index,
- &sgid, NULL);
- if (ret)
- goto out;
-
BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
if (conn_param)
}
static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
- const struct cma_req_info *req)
+ struct cma_req_info *req)
{
- struct sockaddr_storage listen_addr_storage, src_addr_storage;
- struct sockaddr *listen_addr = (struct sockaddr *)&listen_addr_storage,
- *src_addr = (struct sockaddr *)&src_addr_storage;
+ struct sockaddr *listen_addr =
+ (struct sockaddr *)&req->listen_addr_storage;
+ struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage;
struct net_device *net_dev;
const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL;
int err;
if (!net_dev)
return ERR_PTR(-ENODEV);
- if (!validate_net_dev(net_dev, listen_addr, src_addr)) {
- dev_put(net_dev);
- return ERR_PTR(-EHOSTUNREACH);
- }
-
return net_dev;
}
}
}
+ /*
+ * Net namespace might be getting deleted while route lookup,
+ * cm_id lookup is in progress. Therefore, perform netdevice
+ * validation, cm_id lookup under rcu lock.
+ * RCU lock along with netdevice state check, synchronizes with
+ * netdevice migrating to different net namespace and also avoids
+ * case where net namespace doesn't get deleted while lookup is in
+ * progress.
+ * If the device state is not IFF_UP, its properties such as ifindex
+ * and nd_net cannot be trusted to remain valid without rcu lock.
+ * net/core/dev.c change_net_namespace() ensures to synchronize with
+ * ongoing operations on net device after device is closed using
+ * synchronize_net().
+ */
+ rcu_read_lock();
+ if (*net_dev) {
+ /*
+ * If netdevice is down, it is likely that it is administratively
+ * down or it might be migrating to different namespace.
+ * In that case avoid further processing, as the net namespace
+ * or ifindex may change.
+ */
+ if (((*net_dev)->flags & IFF_UP) == 0) {
+ id_priv = ERR_PTR(-EHOSTUNREACH);
+ goto err;
+ }
+
+ if (!validate_net_dev(*net_dev,
+ (struct sockaddr *)&req.listen_addr_storage,
+ (struct sockaddr *)&req.src_addr_storage)) {
+ id_priv = ERR_PTR(-EHOSTUNREACH);
+ goto err;
+ }
+ }
+
bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net,
rdma_ps_from_service_id(req.service_id),
cma_port_from_service_id(req.service_id));
id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
+err:
+ rcu_read_unlock();
if (IS_ERR(id_priv) && *net_dev) {
dev_put(*net_dev);
*net_dev = NULL;
}
-
return id_priv;
}
struct sockaddr_storage *mapped_sockaddr,
u8 nl_client)
{
- struct hlist_head *hash_bucket_head;
+ struct hlist_head *hash_bucket_head = NULL;
struct iwpm_mapping_info *map_info;
unsigned long flags;
int ret = -EINVAL;
}
}
spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+
+ if (!hash_bucket_head)
+ kfree(map_info);
return ret;
}
MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
static struct list_head ib_mad_port_list;
-static u32 ib_mad_client_id = 0;
+static atomic_t ib_mad_client_id = ATOMIC_INIT(0);
/* Port list lock */
static DEFINE_SPINLOCK(ib_mad_port_list_lock);
}
spin_lock_irqsave(&port_priv->reg_lock, flags);
- mad_agent_priv->agent.hi_tid = ++ib_mad_client_id;
+ mad_agent_priv->agent.hi_tid = atomic_inc_return(&ib_mad_client_id);
/*
* Make sure MAD registration (if supplied)
struct net_device *rdma_ndev)
{
struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev);
+ unsigned long gid_type_mask;
if (!rdma_ndev)
return;
rcu_read_lock();
- if (rdma_is_upper_dev_rcu(rdma_ndev, event_ndev) &&
- is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) ==
- BONDING_SLAVE_STATE_INACTIVE) {
- unsigned long gid_type_mask;
-
+ if (((rdma_ndev != event_ndev &&
+ !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) ||
+ is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev)
+ ==
+ BONDING_SLAVE_STATE_INACTIVE)) {
rcu_read_unlock();
+ return;
+ }
- gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
+ rcu_read_unlock();
- ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
- gid_type_mask,
- IB_CACHE_GID_DEFAULT_MODE_DELETE);
- } else {
- rcu_read_unlock();
- }
+ gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
+
+ ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
+ gid_type_mask,
+ IB_CACHE_GID_DEFAULT_MODE_DELETE);
}
static void enum_netdev_ipv4_ips(struct ib_device *ib_dev,
complete(&ctx->comp);
}
+/*
+ * Same as ucm_get_ctx but requires that ->cm_id->device is valid, eg that the
+ * CM_ID is bound.
+ */
+static struct ucma_context *ucma_get_ctx_dev(struct ucma_file *file, int id)
+{
+ struct ucma_context *ctx = ucma_get_ctx(file, id);
+
+ if (IS_ERR(ctx))
+ return ctx;
+ if (!ctx->cm_id->device) {
+ ucma_put_ctx(ctx);
+ return ERR_PTR(-EINVAL);
+ }
+ return ctx;
+}
+
static void ucma_close_event_id(struct work_struct *work)
{
struct ucma_event *uevent_close = container_of(work, struct ucma_event, close_work);
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- if (!rdma_addr_size_in6(&cmd.src_addr) ||
+ if ((cmd.src_addr.sin6_family && !rdma_addr_size_in6(&cmd.src_addr)) ||
!rdma_addr_size_in6(&cmd.dst_addr))
return -EINVAL;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
if (!cmd.conn_param.valid)
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
if (cmd.qp_state > IB_QPS_ERR)
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- if (!ctx->cm_id->device) {
- ret = -EINVAL;
- goto out;
- }
-
resp.qp_attr_mask = 0;
memset(&qp_attr, 0, sizeof qp_attr);
qp_attr.qp_state = cmd.qp_state;
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
+ if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
+ return -EINVAL;
+
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
- return -EINVAL;
-
optval = memdup_user(u64_to_user_ptr(cmd.optval),
cmd.optlen);
if (IS_ERR(optval)) {
else
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd->id);
+ ctx = ucma_get_ctx_dev(file, cmd->id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
mr->device = pd->device;
mr->pd = pd;
+ mr->dm = NULL;
mr->uobject = uobj;
atomic_inc(&pd->usecnt);
mr->res.type = RDMA_RESTRACK_MR;
mr = uobj->object;
+ if (mr->dm) {
+ ret = -EINVAL;
+ goto put_uobjs;
+ }
+
if (cmd.flags & IB_MR_REREG_ACCESS) {
ret = ib_check_mr_access(cmd.access_flags);
if (ret)
return -EINVAL;
}
+ for (; i < method_spec->num_buckets; i++) {
+ struct uverbs_attr_spec_hash *attr_spec_bucket =
+ method_spec->attr_buckets[i];
+
+ if (!bitmap_empty(attr_spec_bucket->mandatory_attrs_bitmask,
+ attr_spec_bucket->num_attrs))
+ return -EINVAL;
+ }
+
return 0;
}
static const struct uverbs_attr_spec uverbs_flow_action_esp_keymat[] = {
[IB_UVERBS_FLOW_ACTION_ESP_KEYMAT_AES_GCM] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
UVERBS_ATTR_TYPE(struct ib_uverbs_flow_action_esp_keymat_aes_gcm),
.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
- },
+ } },
},
};
static const struct uverbs_attr_spec uverbs_flow_action_esp_replay[] = {
[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_NONE] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
/* No need to specify any data */
.len = 0,
- }
+ } }
},
[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_BMP] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
UVERBS_ATTR_STRUCT(struct ib_uverbs_flow_action_esp_replay_bmp, size),
.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
- }
+ } }
},
};
if (!IS_ERR(mr)) {
mr->device = pd->device;
mr->pd = pd;
+ mr->dm = NULL;
mr->uobject = NULL;
atomic_inc(&pd->usecnt);
mr->need_inval = false;
* Deal with out-of-order and/or completions that complete
* prior unsignalled WRs.
*/
-void c4iw_flush_hw_cq(struct c4iw_cq *chp)
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp)
{
struct t4_cqe *hw_cqe, *swcqe, read_cqe;
struct c4iw_qp *qhp;
if (qhp == NULL)
goto next_cqe;
+ if (flush_qhp != qhp) {
+ spin_lock(&qhp->lock);
+
+ if (qhp->wq.flushed == 1)
+ goto next_cqe;
+ }
+
if (CQE_OPCODE(hw_cqe) == FW_RI_TERMINATE)
goto next_cqe;
next_cqe:
t4_hwcq_consume(&chp->cq);
ret = t4_next_hw_cqe(&chp->cq, &hw_cqe);
+ if (qhp && flush_qhp != qhp)
+ spin_unlock(&qhp->lock);
}
}
rdev->status_page->db_off = 0;
+ init_completion(&rdev->rqt_compl);
+ init_completion(&rdev->pbl_compl);
+ kref_init(&rdev->rqt_kref);
+ kref_init(&rdev->pbl_kref);
+
return 0;
err_free_status_page_and_wr_log:
if (c4iw_wr_log && rdev->wr_log)
static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
- destroy_workqueue(rdev->free_workq);
kfree(rdev->wr_log);
c4iw_release_dev_ucontext(rdev, &rdev->uctx);
free_page((unsigned long)rdev->status_page);
c4iw_pblpool_destroy(rdev);
c4iw_rqtpool_destroy(rdev);
+ wait_for_completion(&rdev->pbl_compl);
+ wait_for_completion(&rdev->rqt_compl);
c4iw_ocqp_pool_destroy(rdev);
+ destroy_workqueue(rdev->free_workq);
c4iw_destroy_resource(&rdev->resource);
}
struct wr_log_entry *wr_log;
int wr_log_size;
struct workqueue_struct *free_workq;
+ struct completion rqt_compl;
+ struct completion pbl_compl;
+ struct kref rqt_kref;
+ struct kref pbl_kref;
};
static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size);
void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size);
-void c4iw_flush_hw_cq(struct c4iw_cq *chp);
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp);
void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count);
int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp);
int c4iw_flush_rq(struct t4_wq *wq, struct t4_cq *cq, int count);
qhp->wq.flushed = 1;
t4_set_wq_in_error(&qhp->wq);
- c4iw_flush_hw_cq(rchp);
+ c4iw_flush_hw_cq(rchp, qhp);
c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
rq_flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
if (schp != rchp)
- c4iw_flush_hw_cq(schp);
+ c4iw_flush_hw_cq(schp, qhp);
sq_flushed = c4iw_flush_sq(qhp);
spin_unlock(&qhp->lock);
rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT);
if (rdev->stats.pbl.cur > rdev->stats.pbl.max)
rdev->stats.pbl.max = rdev->stats.pbl.cur;
+ kref_get(&rdev->pbl_kref);
} else
rdev->stats.pbl.fail++;
mutex_unlock(&rdev->stats.lock);
return (u32)addr;
}
+static void destroy_pblpool(struct kref *kref)
+{
+ struct c4iw_rdev *rdev;
+
+ rdev = container_of(kref, struct c4iw_rdev, pbl_kref);
+ gen_pool_destroy(rdev->pbl_pool);
+ complete(&rdev->pbl_compl);
+}
+
void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
{
pr_debug("addr 0x%x size %d\n", addr, size);
rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT);
mutex_unlock(&rdev->stats.lock);
gen_pool_free(rdev->pbl_pool, (unsigned long)addr, size);
+ kref_put(&rdev->pbl_kref, destroy_pblpool);
}
int c4iw_pblpool_create(struct c4iw_rdev *rdev)
void c4iw_pblpool_destroy(struct c4iw_rdev *rdev)
{
- gen_pool_destroy(rdev->pbl_pool);
+ kref_put(&rdev->pbl_kref, destroy_pblpool);
}
/*
rdev->stats.rqt.cur += roundup(size << 6, 1 << MIN_RQT_SHIFT);
if (rdev->stats.rqt.cur > rdev->stats.rqt.max)
rdev->stats.rqt.max = rdev->stats.rqt.cur;
+ kref_get(&rdev->rqt_kref);
} else
rdev->stats.rqt.fail++;
mutex_unlock(&rdev->stats.lock);
return (u32)addr;
}
+static void destroy_rqtpool(struct kref *kref)
+{
+ struct c4iw_rdev *rdev;
+
+ rdev = container_of(kref, struct c4iw_rdev, rqt_kref);
+ gen_pool_destroy(rdev->rqt_pool);
+ complete(&rdev->rqt_compl);
+}
+
void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
{
pr_debug("addr 0x%x size %d\n", addr, size << 6);
rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT);
mutex_unlock(&rdev->stats.lock);
gen_pool_free(rdev->rqt_pool, (unsigned long)addr, size << 6);
+ kref_put(&rdev->rqt_kref, destroy_rqtpool);
}
int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
{
- gen_pool_destroy(rdev->rqt_pool);
+ kref_put(&rdev->rqt_kref, destroy_rqtpool);
}
/*
static int get_irq_affinity(struct hfi1_devdata *dd,
struct hfi1_msix_entry *msix)
{
- int ret;
cpumask_var_t diff;
struct hfi1_affinity_node *entry;
struct cpu_mask_set *set = NULL;
extra[0] = '\0';
cpumask_clear(&msix->mask);
- ret = zalloc_cpumask_var(&diff, GFP_KERNEL);
- if (!ret)
- return -ENOMEM;
-
entry = node_affinity_lookup(dd->node);
switch (msix->type) {
* finds its CPU here.
*/
if (cpu == -1 && set) {
+ if (!zalloc_cpumask_var(&diff, GFP_KERNEL))
+ return -ENOMEM;
+
if (cpumask_equal(&set->mask, &set->used)) {
/*
* We've used up all the CPUs, bump up the generation
cpumask_andnot(diff, &set->mask, &set->used);
cpu = cpumask_first(diff);
cpumask_set_cpu(cpu, &set->used);
+
+ free_cpumask_var(diff);
}
cpumask_set_cpu(cpu, &msix->mask);
hfi1_setup_sdma_notifier(msix);
}
- free_cpumask_var(diff);
return 0;
}
bool do_cnp)
{
struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+ struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
struct ib_other_headers *ohdr = pkt->ohdr;
struct ib_grh *grh = pkt->grh;
u32 rqpn = 0, bth1;
- u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+ u16 pkey;
+ u32 rlid, slid, dlid = 0;
u8 hdr_type, sc, svc_type;
bool is_mcast = false;
+ /* can be called from prescan */
if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
is_mcast = hfi1_is_16B_mcast(dlid);
pkey = hfi1_16B_get_pkey(pkt->hdr);
sc = hfi1_16B_get_sc(pkt->hdr);
+ dlid = hfi1_16B_get_dlid(pkt->hdr);
+ slid = hfi1_16B_get_slid(pkt->hdr);
hdr_type = HFI1_PKT_TYPE_16B;
} else {
is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
(dlid != be16_to_cpu(IB_LID_PERMISSIVE));
pkey = ib_bth_get_pkey(ohdr);
sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+ dlid = ib_get_dlid(pkt->hdr);
+ slid = ib_get_slid(pkt->hdr);
hdr_type = HFI1_PKT_TYPE_9B;
}
switch (qp->ibqp.qp_type) {
+ case IB_QPT_UD:
+ dlid = ppd->lid;
+ rlid = slid;
+ rqpn = ib_get_sqpn(pkt->ohdr);
+ svc_type = IB_CC_SVCTYPE_UD;
+ break;
case IB_QPT_SMI:
case IB_QPT_GSI:
- case IB_QPT_UD:
- rlid = ib_get_slid(pkt->hdr);
+ rlid = slid;
rqpn = ib_get_sqpn(pkt->ohdr);
svc_type = IB_CC_SVCTYPE_UD;
break;
dlid, rlid, sc, grh);
if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
- struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
u32 lqpn = bth1 & RVT_QPN_MASK;
u8 sl = ibp->sc_to_sl[sc];
void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
u32 rqpn, u8 svc_type);
void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
- u32 pkey, u32 slid, u32 dlid, u8 sc5,
+ u16 pkey, u32 slid, u32 dlid, u8 sc5,
const struct ib_grh *old_grh);
void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh);
typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh);
#define PKEY_CHECK_INVALID -1
((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
- lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+ lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | ((u32)pkey << OPA_16B_PKEY_SHIFT);
lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
hdr->lrh[0] = lrh0;
* pio buffers per ctxt, etc.) Zero means use one user context per CPU.
*/
int num_user_contexts = -1;
-module_param_named(num_user_contexts, num_user_contexts, uint, S_IRUGO);
+module_param_named(num_user_contexts, num_user_contexts, int, 0444);
MODULE_PARM_DESC(
- num_user_contexts, "Set max number of user contexts to use");
+ num_user_contexts, "Set max number of user contexts to use (default: -1 will use the real (non-HT) CPU count)");
uint krcvqs[RXE_NUM_DATA_VL];
int krcvqsset;
kfree(ad);
}
-static void __hfi1_free_devdata(struct kobject *kobj)
+/**
+ * hfi1_clean_devdata - cleans up per-unit data structure
+ * @dd: pointer to a valid devdata structure
+ *
+ * It cleans up all data structures set up by
+ * by hfi1_alloc_devdata().
+ */
+static void hfi1_clean_devdata(struct hfi1_devdata *dd)
{
- struct hfi1_devdata *dd =
- container_of(kobj, struct hfi1_devdata, kobj);
struct hfi1_asic_data *ad;
unsigned long flags;
spin_lock_irqsave(&hfi1_devs_lock, flags);
- idr_remove(&hfi1_unit_table, dd->unit);
- list_del(&dd->list);
+ if (!list_empty(&dd->list)) {
+ idr_remove(&hfi1_unit_table, dd->unit);
+ list_del_init(&dd->list);
+ }
ad = release_asic_data(dd);
spin_unlock_irqrestore(&hfi1_devs_lock, flags);
- if (ad)
- finalize_asic_data(dd, ad);
+
+ finalize_asic_data(dd, ad);
free_platform_config(dd);
rcu_barrier(); /* wait for rcu callbacks to complete */
free_percpu(dd->int_counter);
free_percpu(dd->rcv_limit);
free_percpu(dd->send_schedule);
free_percpu(dd->tx_opstats);
+ dd->int_counter = NULL;
+ dd->rcv_limit = NULL;
+ dd->send_schedule = NULL;
+ dd->tx_opstats = NULL;
sdma_clean(dd, dd->num_sdma);
rvt_dealloc_device(&dd->verbs_dev.rdi);
}
+static void __hfi1_free_devdata(struct kobject *kobj)
+{
+ struct hfi1_devdata *dd =
+ container_of(kobj, struct hfi1_devdata, kobj);
+
+ hfi1_clean_devdata(dd);
+}
+
static struct kobj_type hfi1_devdata_type = {
.release = __hfi1_free_devdata,
};
return ERR_PTR(-ENOMEM);
dd->num_pports = nports;
dd->pport = (struct hfi1_pportdata *)(dd + 1);
+ dd->pcidev = pdev;
+ pci_set_drvdata(pdev, dd);
INIT_LIST_HEAD(&dd->list);
idr_preload(GFP_KERNEL);
return dd;
bail:
- if (!list_empty(&dd->list))
- list_del_init(&dd->list);
- rvt_dealloc_device(&dd->verbs_dev.rdi);
+ hfi1_clean_devdata(dd);
return ERR_PTR(ret);
}
resource_size_t addr;
int ret = 0;
- dd->pcidev = pdev;
- pci_set_drvdata(pdev, dd);
-
addr = pci_resource_start(pdev, 0);
len = pci_resource_len(pdev, 0);
{
/* Release memory allocated for eprom or fallback file read. */
kfree(dd->platform_config.data);
+ dd->platform_config.data = NULL;
}
void get_port_type(struct hfi1_pportdata *ppd)
void clean_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
{
+ if (!ad)
+ return;
clean_i2c_bus(ad->i2c_bus0);
ad->i2c_bus0 = NULL;
clean_i2c_bus(ad->i2c_bus1);
ohdr->bth[2] = cpu_to_be32(bth2);
}
+/**
+ * hfi1_make_ruc_header_16B - build a 16B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ becn = true;
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- becn = true;
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
if (!ppd->lid)
pkey, becn, 0, l4, priv->s_sc);
}
+/**
+ * hfi1_make_ruc_header_9B - build a 9B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
lrh0,
}
void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh)
{
u64 pbc, pbc_flags = 0;
}
void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
- u32 pkey, u32 slid, u32 dlid, u8 sc5,
+ u16 pkey, u32 slid, u32 dlid, u8 sc5,
const struct ib_grh *old_grh)
{
u64 pbc, pbc_flags = 0;
obj_per_chunk = buf_chunk_size / obj_size;
num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk;
bt_chunk_num = bt_chunk_size / 8;
- if (table->type >= HEM_TYPE_MTT)
+ if (type >= HEM_TYPE_MTT)
num_bt_l0 = bt_chunk_num;
table->hem = kcalloc(num_hem, sizeof(*table->hem),
if (!table->hem)
goto err_kcalloc_hem_buf;
- if (check_whether_bt_num_3(table->type, hop_num)) {
+ if (check_whether_bt_num_3(type, hop_num)) {
unsigned long num_bt_l1;
num_bt_l1 = (num_hem + bt_chunk_num - 1) /
goto err_kcalloc_l1_dma;
}
- if (check_whether_bt_num_2(table->type, hop_num) ||
- check_whether_bt_num_3(table->type, hop_num)) {
+ if (check_whether_bt_num_2(type, hop_num) ||
+ check_whether_bt_num_3(type, hop_num)) {
table->bt_l0 = kcalloc(num_bt_l0, sizeof(*table->bt_l0),
GFP_KERNEL);
if (!table->bt_l0)
void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev)
{
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->cq_table.table);
- hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
if (hr_dev->caps.trrl_entry_sz)
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->qp_table.trrl_table);
+ hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.qp_table);
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table);
- hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE))
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->mr_table.mtt_cqe_table);
+ hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
}
return -EINVAL;
}
+ if (wr->opcode == IB_WR_RDMA_READ) {
+ dev_err(hr_dev->dev, "Not support inline data!\n");
+ return -EINVAL;
+ }
+
for (i = 0; i < wr->num_sge; i++) {
memcpy(wqe, ((void *)wr->sg_list[i].addr),
wr->sg_list[i].length);
ibqp->qp_type != IB_QPT_GSI &&
ibqp->qp_type != IB_QPT_UD)) {
dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type);
- *bad_wr = NULL;
+ *bad_wr = wr;
return -EOPNOTSUPP;
}
qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
wr->wr_id;
- owner_bit = ~(qp->sq.head >> ilog2(qp->sq.wqe_cnt)) & 0x1;
+ owner_bit =
+ ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
/* Corresponding to the QP type, wqe process separately */
if (ibqp->qp_type == IB_QPT_GSI) {
} else {
dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type);
spin_unlock_irqrestore(&qp->sq.lock, flags);
+ *bad_wr = wr;
return -EOPNOTSUPP;
}
}
roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M,
V2_QPC_BYTE_4_SQPN_S, 0);
- roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
- roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, 0);
+ if (attr_mask & IB_QP_DEST_QPN) {
+ roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+ V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
+ roce_set_field(qpc_mask->byte_56_dqpn_err,
+ V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+ }
roce_set_field(context->byte_168_irrl_idx,
V2_QPC_BYTE_168_SQ_SHIFT_BAK_M,
V2_QPC_BYTE_168_SQ_SHIFT_BAK_S,
return -EINVAL;
}
- if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
- (attr_mask & IB_QP_PKEY_INDEX) || (attr_mask & IB_QP_QKEY)) {
+ if (attr_mask & IB_QP_ALT_PATH) {
dev_err(dev, "INIT2RTR attr_mask (0x%x) error\n", attr_mask);
return -EINVAL;
}
V2_QPC_BYTE_140_RR_MAX_S, 0);
}
- roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
- roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, 0);
+ if (attr_mask & IB_QP_DEST_QPN) {
+ roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+ V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
+ roce_set_field(qpc_mask->byte_56_dqpn_err,
+ V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+ }
/* Configure GID index */
port_num = rdma_ah_get_port_num(&attr->ah_attr);
if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_UD)
roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
V2_QPC_BYTE_24_MTU_S, IB_MTU_4096);
- else
+ else if (attr_mask & IB_QP_PATH_MTU)
roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
V2_QPC_BYTE_24_MTU_S, attr->path_mtu);
return -EINVAL;
}
- /* If exist optional param, return error */
- if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
- (attr_mask & IB_QP_QKEY) || (attr_mask & IB_QP_PATH_MIG_STATE) ||
- (attr_mask & IB_QP_CUR_STATE) ||
- (attr_mask & IB_QP_MIN_RNR_TIMER)) {
+ /* Not support alternate path and path migration */
+ if ((attr_mask & IB_QP_ALT_PATH) ||
+ (attr_mask & IB_QP_PATH_MIG_STATE)) {
dev_err(dev, "RTR2RTS attr_mask (0x%x)error\n", attr_mask);
return -EINVAL;
}
(cur_state == IB_QPS_RTR && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_RTS && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_SQD && new_state == IB_QPS_ERR) ||
- (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR)) {
+ (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR) ||
+ (cur_state == IB_QPS_ERR && new_state == IB_QPS_ERR)) {
/* Nothing */
;
} else {
ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, eq->eqn, 0,
eq_cmd, HNS_ROCE_CMD_TIMEOUT_MSECS);
if (ret) {
- dev_err(dev, "[mailbox cmd] creat eqc failed.\n");
+ dev_err(dev, "[mailbox cmd] create eqc failed.\n");
goto err_cmd_mbox;
}
to_hr_ucontext(ib_pd->uobject->context),
ucmd.db_addr, &hr_qp->rdb);
if (ret) {
- dev_err(dev, "rp record doorbell map failed!\n");
+ dev_err(dev, "rq record doorbell map failed!\n");
goto err_mtt;
}
}
/* Add to the first block the misalignment that it suffers from. */
total_len += (first_block_start & ((1ULL << block_shift) - 1ULL));
last_block_end = current_block_start + current_block_len;
- last_block_aligned_end = round_up(last_block_end, 1 << block_shift);
+ last_block_aligned_end = round_up(last_block_end, 1ULL << block_shift);
total_len += (last_block_aligned_end - last_block_end);
if (total_len & ((1ULL << block_shift) - 1ULL))
MLX4_IB_RX_HASH_SRC_PORT_TCP |
MLX4_IB_RX_HASH_DST_PORT_TCP |
MLX4_IB_RX_HASH_SRC_PORT_UDP |
- MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+ MLX4_IB_RX_HASH_DST_PORT_UDP |
+ MLX4_IB_RX_HASH_INNER)) {
pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n",
ucmd->rx_hash_fields_mask);
return (-EOPNOTSUPP);
config MLX5_INFINIBAND
tristate "Mellanox Connect-IB HCA support"
depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+ depends on INFINIBAND_USER_ACCESS || INFINIBAND_USER_ACCESS=n
---help---
This driver provides low-level InfiniBand support for
Mellanox Connect-IB PCI Express host channel adapters (HCAs).
return 0;
err_cqb:
- kfree(*cqb);
+ kvfree(*cqb);
err_db:
mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);
#include <linux/mlx5/port.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
-#include <linux/mlx5/fs_helpers.h>
#include <linux/list.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_umem.h>
if (rep_ndev == ndev)
roce->netdev = (event == NETDEV_UNREGISTER) ?
NULL : ndev;
- } else if (ndev->dev.parent == &ibdev->mdev->pdev->dev) {
+ } else if (ndev->dev.parent == &mdev->pdev->dev) {
roce->netdev = (event == NETDEV_UNREGISTER) ?
NULL : ndev;
}
{
struct mlx5_ib_dev *dev = to_mdev(ibdev);
- return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+ return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
}
/* The mlx5_ib_multiport_mutex should be held when calling this function */
static int mlx5_ib_stage_uar_init(struct mlx5_ib_dev *dev)
{
dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
- if (!dev->mdev->priv.uar)
- return -ENOMEM;
- return 0;
+ return PTR_ERR_OR_ZERO(dev->mdev->priv.uar);
}
static void mlx5_ib_stage_uar_cleanup(struct mlx5_ib_dev *dev)
int *order)
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ struct ib_umem *u;
int err;
- *umem = ib_umem_get(pd->uobject->context, start, length,
- access_flags, 0);
- err = PTR_ERR_OR_ZERO(*umem);
+ *umem = NULL;
+
+ u = ib_umem_get(pd->uobject->context, start, length, access_flags, 0);
+ err = PTR_ERR_OR_ZERO(u);
if (err) {
- *umem = NULL;
- mlx5_ib_err(dev, "umem get failed (%d)\n", err);
+ mlx5_ib_dbg(dev, "umem get failed (%d)\n", err);
return err;
}
- mlx5_ib_cont_pages(*umem, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
+ mlx5_ib_cont_pages(u, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
page_shift, ncont, order);
if (!*npages) {
mlx5_ib_warn(dev, "avoid zero region\n");
- ib_umem_release(*umem);
+ ib_umem_release(u);
return -EINVAL;
}
+ *umem = u;
+
mlx5_ib_dbg(dev, "npages %d, ncont %d, order %d, page_shift %d\n",
*npages, *ncont, *order, *page_shift);
int access_flags = flags & IB_MR_REREG_ACCESS ?
new_access_flags :
mr->access_flags;
- u64 addr = (flags & IB_MR_REREG_TRANS) ? virt_addr : mr->umem->address;
- u64 len = (flags & IB_MR_REREG_TRANS) ? length : mr->umem->length;
int page_shift = 0;
int upd_flags = 0;
int npages = 0;
int ncont = 0;
int order = 0;
+ u64 addr, len;
int err;
mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
atomic_sub(mr->npages, &dev->mdev->priv.reg_pages);
+ if (!mr->umem)
+ return -EINVAL;
+
+ if (flags & IB_MR_REREG_TRANS) {
+ addr = virt_addr;
+ len = length;
+ } else {
+ addr = mr->umem->address;
+ len = mr->umem->length;
+ }
+
if (flags != IB_MR_REREG_PD) {
/*
* Replace umem. This needs to be done whether or not UMR is
*/
flags |= IB_MR_REREG_TRANS;
ib_umem_release(mr->umem);
+ mr->umem = NULL;
err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
&npages, &page_shift, &ncont, &order);
if (err)
} else {
if (ucmd) {
qp->rq.wqe_cnt = ucmd->rq_wqe_count;
+ if (ucmd->rq_wqe_shift > BITS_PER_BYTE * sizeof(ucmd->rq_wqe_shift))
+ return -EINVAL;
qp->rq.wqe_shift = ucmd->rq_wqe_shift;
+ if ((1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) < qp->wq_sig)
+ return -EINVAL;
qp->rq.max_gs = (1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) - qp->wq_sig;
qp->rq.max_post = qp->rq.wqe_cnt;
} else {
static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
{
- if (rate == IB_RATE_PORT_CURRENT) {
+ if (rate == IB_RATE_PORT_CURRENT)
return 0;
- } else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) {
+
+ if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS)
return -EINVAL;
- } else {
- while (rate != IB_RATE_2_5_GBPS &&
- !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
- MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
- --rate;
- }
- return rate + MLX5_STAT_RATE_OFFSET;
+ while (rate != IB_RATE_PORT_CURRENT &&
+ !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
+ MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
+ --rate;
+
+ return rate ? rate + MLX5_STAT_RATE_OFFSET : rate;
}
static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
/**
* nes_netdev_start_xmit
*/
-static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct nes_vnic *nesvnic = netdev_priv(netdev);
struct nes_device *nesdev = nesvnic->nesdev;
.name = "IB_OPCODE_RC_SEND_ONLY_INV",
.mask = RXE_IETH_MASK | RXE_PAYLOAD_MASK | RXE_REQ_MASK
| RXE_COMP_MASK | RXE_RWR_MASK | RXE_SEND_MASK
- | RXE_END_MASK,
+ | RXE_END_MASK | RXE_START_MASK,
.length = RXE_BTH_BYTES + RXE_IETH_BYTES,
.offset = {
[RXE_BTH] = 0,
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
if (ret == -EAGAIN) {
- kfree_skb(skb);
rxe_run_task(&qp->req.task, 1);
goto exit;
}
err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
if (err) {
pr_err("Failed sending RDMA reply.\n");
- kfree_skb(skb);
return RESPST_ERR_RNR;
}
}
err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
- if (err) {
+ if (err)
pr_err_ratelimited("Failed sending ack\n");
- kfree_skb(skb);
- }
err1:
return err;
if (rc) {
pr_err("Failed resending result. This flow is not handled - skb ignored\n");
rxe_drop_ref(qp);
- kfree_skb(skb_copy);
rc = RESPST_CLEANUP;
goto out;
}
spin_unlock_irqrestore(&priv->lock, flags);
}
-static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
struct rdma_netdev *rn = netdev_priv(dev);
}
/* opa_vnic_calc_entropy - calculate the packet entropy */
-u8 opa_vnic_calc_entropy(struct opa_vnic_adapter *adapter, struct sk_buff *skb)
+u8 opa_vnic_calc_entropy(struct sk_buff *skb)
{
- u16 hash16;
-
- /*
- * Get flow based 16-bit hash and then XOR the upper and lower bytes
- * to get the entropy.
- * __skb_tx_hash limits qcount to 16 bits. Hence, get 15-bit hash.
- */
- hash16 = __skb_tx_hash(adapter->netdev, skb, BIT(15));
- return (u8)((hash16 >> 8) ^ (hash16 & 0xff));
+ u32 hash = skb_get_hash(skb);
+
+ /* store XOR of all bytes in lower 8 bits */
+ hash ^= hash >> 8;
+ hash ^= hash >> 16;
+
+ /* return lower 8 bits as entropy */
+ return (u8)(hash & 0xFF);
}
/* opa_vnic_get_def_port - get default port based on entropy */
hdr = skb_push(skb, OPA_VNIC_HDR_LEN);
- entropy = opa_vnic_calc_entropy(adapter, skb);
+ entropy = opa_vnic_calc_entropy(skb);
def_port = opa_vnic_get_def_port(adapter, entropy);
len = opa_vnic_wire_length(skb);
dlid = opa_vnic_get_dlid(adapter, skb, def_port);
void opa_vnic_rem_netdev(struct opa_vnic_adapter *adapter);
void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb);
u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb);
-u8 opa_vnic_calc_entropy(struct opa_vnic_adapter *adapter, struct sk_buff *skb);
+u8 opa_vnic_calc_entropy(struct sk_buff *skb);
void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter);
void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter);
void opa_vnic_query_mac_tbl(struct opa_vnic_adapter *adapter,
/* pass entropy and vl as metadata in skb */
mdata = skb_push(skb, sizeof(*mdata));
- mdata->entropy = opa_vnic_calc_entropy(adapter, skb);
+ mdata->entropy = opa_vnic_calc_entropy(skb);
mdata->vl = opa_vnic_get_vl(adapter, skb);
rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
accel_priv, fallback);
config INFINIBAND_SRP
tristate "InfiniBand SCSI RDMA Protocol"
- depends on SCSI
+ depends on SCSI && INFINIBAND_ADDR_TRANS
select SCSI_SRP_ATTRS
---help---
Support for the SCSI RDMA Protocol over InfiniBand. This
config INFINIBAND_SRPT
tristate "InfiniBand SCSI RDMA Protocol target support"
- depends on INFINIBAND && TARGET_CORE
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS && TARGET_CORE
---help---
Support for the SCSI RDMA Protocol (SRP) Target driver. The
enum evdev_clock_type {
EV_CLK_REAL = 0,
EV_CLK_MONO,
+ EV_CLK_BOOT,
EV_CLK_MAX
};
case CLOCK_REALTIME:
clk_type = EV_CLK_REAL;
break;
- case CLOCK_BOOTTIME:
case CLOCK_MONOTONIC:
clk_type = EV_CLK_MONO;
break;
+ case CLOCK_BOOTTIME:
+ clk_type = EV_CLK_BOOT;
+ break;
default:
return -EINVAL;
}
ev_time[EV_CLK_MONO] = ktime_get();
ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]);
+ ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO],
+ TK_OFFS_BOOT);
rcu_read_lock();
const struct input_device_id *id)
{
struct input_leds *leds;
+ struct input_led *led;
unsigned int num_leds;
unsigned int led_code;
int led_no;
led_no = 0;
for_each_set_bit(led_code, dev->ledbit, LED_CNT) {
- struct input_led *led = &leds->leds[led_no];
+ if (!input_led_info[led_code].name)
+ continue;
+ led = &leds->leds[led_no];
led->handle = &leds->handle;
led->code = led_code;
- if (!input_led_info[led_code].name)
- continue;
-
led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
dev_name(&dev->dev),
input_led_info[led_code].name);
x = (s8)(((packet[0] & 0x20) << 2) | (packet[1] & 0x7f));
y = (s8)(((packet[0] & 0x10) << 3) | (packet[2] & 0x7f));
- z = packet[4] & 0x7c;
+ z = packet[4] & 0x7f;
/*
* The x and y values tend to be quite large, and when used
if (len > RMI_SPI_XFER_SIZE_LIMIT)
return -EINVAL;
- if (rmi_spi->xfer_buf_size < len)
- rmi_spi_manage_pools(rmi_spi, len);
+ if (rmi_spi->xfer_buf_size < len) {
+ ret = rmi_spi_manage_pools(rmi_spi, len);
+ if (ret < 0)
+ return ret;
+ }
if (addr == 0)
/*
If unsure, say N.
- To compile this driver as a moudle, choose M here : the
+ To compile this driver as a module, choose M here : the
module will be called hideep_ts.
config TOUCHSCREEN_ILI210X
struct input_dev *input_dev;
char phys[64]; /* device physical location */
struct mxt_object *object_table;
- struct mxt_info info;
+ struct mxt_info *info;
+ void *raw_info_block;
unsigned int irq;
unsigned int max_x;
unsigned int max_y;
{
u8 appmode = data->client->addr;
u8 bootloader;
+ u8 family_id = data->info ? data->info->family_id : 0;
switch (appmode) {
case 0x4a:
case 0x4b:
/* Chips after 1664S use different scheme */
- if (retry || data->info.family_id >= 0xa2) {
+ if (retry || family_id >= 0xa2) {
bootloader = appmode - 0x24;
break;
}
struct mxt_object *object;
int i;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
object = data->object_table + i;
if (object->type == type)
return object;
data_pos += offset;
}
- if (cfg_info.family_id != data->info.family_id) {
+ if (cfg_info.family_id != data->info->family_id) {
dev_err(dev, "Family ID mismatch!\n");
return -EINVAL;
}
- if (cfg_info.variant_id != data->info.variant_id) {
+ if (cfg_info.variant_id != data->info->variant_id) {
dev_err(dev, "Variant ID mismatch!\n");
return -EINVAL;
}
/* Malloc memory to store configuration */
cfg_start_ofs = MXT_OBJECT_START +
- data->info.object_num * sizeof(struct mxt_object) +
+ data->info->object_num * sizeof(struct mxt_object) +
MXT_INFO_CHECKSUM_SIZE;
config_mem_size = data->mem_size - cfg_start_ofs;
config_mem = kzalloc(config_mem_size, GFP_KERNEL);
return ret;
}
-static int mxt_get_info(struct mxt_data *data)
-{
- struct i2c_client *client = data->client;
- struct mxt_info *info = &data->info;
- int error;
-
- /* Read 7-byte info block starting at address 0 */
- error = __mxt_read_reg(client, 0, sizeof(*info), info);
- if (error)
- return error;
-
- return 0;
-}
-
static void mxt_free_input_device(struct mxt_data *data)
{
if (data->input_dev) {
video_unregister_device(&data->dbg.vdev);
v4l2_device_unregister(&data->dbg.v4l2);
#endif
-
- kfree(data->object_table);
data->object_table = NULL;
+ data->info = NULL;
+ kfree(data->raw_info_block);
+ data->raw_info_block = NULL;
kfree(data->msg_buf);
data->msg_buf = NULL;
data->T5_address = 0;
data->max_reportid = 0;
}
-static int mxt_get_object_table(struct mxt_data *data)
+static int mxt_parse_object_table(struct mxt_data *data,
+ struct mxt_object *object_table)
{
struct i2c_client *client = data->client;
- size_t table_size;
- struct mxt_object *object_table;
- int error;
int i;
u8 reportid;
u16 end_address;
- table_size = data->info.object_num * sizeof(struct mxt_object);
- object_table = kzalloc(table_size, GFP_KERNEL);
- if (!object_table) {
- dev_err(&data->client->dev, "Failed to allocate memory\n");
- return -ENOMEM;
- }
-
- error = __mxt_read_reg(client, MXT_OBJECT_START, table_size,
- object_table);
- if (error) {
- kfree(object_table);
- return error;
- }
-
/* Valid Report IDs start counting from 1 */
reportid = 1;
data->mem_size = 0;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
struct mxt_object *object = object_table + i;
u8 min_id, max_id;
switch (object->type) {
case MXT_GEN_MESSAGE_T5:
- if (data->info.family_id == 0x80 &&
- data->info.version < 0x20) {
+ if (data->info->family_id == 0x80 &&
+ data->info->version < 0x20) {
/*
* On mXT224 firmware versions prior to V2.0
* read and discard unused CRC byte otherwise
/* If T44 exists, T5 position has to be directly after */
if (data->T44_address && (data->T5_address != data->T44_address + 1)) {
dev_err(&client->dev, "Invalid T44 position\n");
- error = -EINVAL;
- goto free_object_table;
+ return -EINVAL;
}
data->msg_buf = kcalloc(data->max_reportid,
data->T5_msg_size, GFP_KERNEL);
- if (!data->msg_buf) {
- dev_err(&client->dev, "Failed to allocate message buffer\n");
+ if (!data->msg_buf)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int mxt_read_info_block(struct mxt_data *data)
+{
+ struct i2c_client *client = data->client;
+ int error;
+ size_t size;
+ void *id_buf, *buf;
+ uint8_t num_objects;
+ u32 calculated_crc;
+ u8 *crc_ptr;
+
+ /* If info block already allocated, free it */
+ if (data->raw_info_block)
+ mxt_free_object_table(data);
+
+ /* Read 7-byte ID information block starting at address 0 */
+ size = sizeof(struct mxt_info);
+ id_buf = kzalloc(size, GFP_KERNEL);
+ if (!id_buf)
+ return -ENOMEM;
+
+ error = __mxt_read_reg(client, 0, size, id_buf);
+ if (error)
+ goto err_free_mem;
+
+ /* Resize buffer to give space for rest of info block */
+ num_objects = ((struct mxt_info *)id_buf)->object_num;
+ size += (num_objects * sizeof(struct mxt_object))
+ + MXT_INFO_CHECKSUM_SIZE;
+
+ buf = krealloc(id_buf, size, GFP_KERNEL);
+ if (!buf) {
error = -ENOMEM;
- goto free_object_table;
+ goto err_free_mem;
+ }
+ id_buf = buf;
+
+ /* Read rest of info block */
+ error = __mxt_read_reg(client, MXT_OBJECT_START,
+ size - MXT_OBJECT_START,
+ id_buf + MXT_OBJECT_START);
+ if (error)
+ goto err_free_mem;
+
+ /* Extract & calculate checksum */
+ crc_ptr = id_buf + size - MXT_INFO_CHECKSUM_SIZE;
+ data->info_crc = crc_ptr[0] | (crc_ptr[1] << 8) | (crc_ptr[2] << 16);
+
+ calculated_crc = mxt_calculate_crc(id_buf, 0,
+ size - MXT_INFO_CHECKSUM_SIZE);
+
+ /*
+ * CRC mismatch can be caused by data corruption due to I2C comms
+ * issue or else device is not using Object Based Protocol (eg i2c-hid)
+ */
+ if ((data->info_crc == 0) || (data->info_crc != calculated_crc)) {
+ dev_err(&client->dev,
+ "Info Block CRC error calculated=0x%06X read=0x%06X\n",
+ calculated_crc, data->info_crc);
+ error = -EIO;
+ goto err_free_mem;
+ }
+
+ data->raw_info_block = id_buf;
+ data->info = (struct mxt_info *)id_buf;
+
+ dev_info(&client->dev,
+ "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
+ data->info->family_id, data->info->variant_id,
+ data->info->version >> 4, data->info->version & 0xf,
+ data->info->build, data->info->object_num);
+
+ /* Parse object table information */
+ error = mxt_parse_object_table(data, id_buf + MXT_OBJECT_START);
+ if (error) {
+ dev_err(&client->dev, "Error %d parsing object table\n", error);
+ mxt_free_object_table(data);
+ goto err_free_mem;
}
- data->object_table = object_table;
+ data->object_table = (struct mxt_object *)(id_buf + MXT_OBJECT_START);
return 0;
-free_object_table:
- mxt_free_object_table(data);
+err_free_mem:
+ kfree(id_buf);
return error;
}
int error;
while (1) {
- error = mxt_get_info(data);
+ error = mxt_read_info_block(data);
if (!error)
break;
msleep(MXT_FW_RESET_TIME);
}
- /* Get object table information */
- error = mxt_get_object_table(data);
- if (error) {
- dev_err(&client->dev, "Error %d reading object table\n", error);
- return error;
- }
-
error = mxt_acquire_irq(data);
if (error)
- goto err_free_object_table;
+ return error;
error = request_firmware_nowait(THIS_MODULE, true, MXT_CFG_NAME,
&client->dev, GFP_KERNEL, data,
if (error) {
dev_err(&client->dev, "Failed to invoke firmware loader: %d\n",
error);
- goto err_free_object_table;
+ return error;
}
return 0;
-
-err_free_object_table:
- mxt_free_object_table(data);
- return error;
}
static int mxt_set_t7_power_cfg(struct mxt_data *data, u8 sleep)
static u16 mxt_get_debug_value(struct mxt_data *data, unsigned int x,
unsigned int y)
{
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
struct mxt_dbg *dbg = &data->dbg;
unsigned int ofs, page;
unsigned int col = 0;
static void mxt_debug_init(struct mxt_data *data)
{
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
struct mxt_dbg *dbg = &data->dbg;
struct mxt_object *object;
int error;
const struct firmware *cfg)
{
struct device *dev = &data->client->dev;
- struct mxt_info *info = &data->info;
int error;
error = mxt_init_t7_power_cfg(data);
mxt_debug_init(data);
- dev_info(dev,
- "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
- info->family_id, info->variant_id, info->version >> 4,
- info->version & 0xf, info->build, info->object_num);
-
return 0;
}
struct device_attribute *attr, char *buf)
{
struct mxt_data *data = dev_get_drvdata(dev);
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n",
info->version >> 4, info->version & 0xf, info->build);
}
struct device_attribute *attr, char *buf)
{
struct mxt_data *data = dev_get_drvdata(dev);
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
return scnprintf(buf, PAGE_SIZE, "%u.%u\n",
info->family_id, info->variant_id);
}
return -ENOMEM;
error = 0;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
object = data->object_table + i;
if (!mxt_object_readable(object->type))
},
.driver_data = samus_platform_data,
},
+ {
+ /* Samsung Chromebook Pro */
+ .ident = "Samsung Chromebook Pro",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Caroline"),
+ },
+ .driver_data = samus_platform_data,
+ },
{
/* Other Google Chromebooks */
.ident = "Chromebook",
static const struct of_device_id mxt_of_match[] = {
{ .compatible = "atmel,maxtouch", },
+ /* Compatibles listed below are deprecated */
+ { .compatible = "atmel,qt602240_ts", },
+ { .compatible = "atmel,atmel_mxt_ts", },
+ { .compatible = "atmel,atmel_mxt_tp", },
+ { .compatible = "atmel,mXT224", },
{},
};
MODULE_DEVICE_TABLE(of, mxt_of_match);
static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
static DEFINE_SPINLOCK(pd_bitmap_lock);
-static DEFINE_SPINLOCK(iommu_table_lock);
/* List of all available dev_data structures */
static LLIST_HEAD(dev_data_list);
*****************************************************************************/
static struct irq_chip amd_ir_chip;
+static DEFINE_SPINLOCK(iommu_table_lock);
static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
{
* @list: Reserved region list from iommu_get_resv_regions()
*
* IOMMU drivers can use this to implement their .get_resv_regions callback
- * for general non-IOMMU-specific reservations. Currently, this covers host
- * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI
- * based ARM platforms that may require HW MSI reservation.
+ * for general non-IOMMU-specific reservations. Currently, this covers GICv3
+ * ITS region reservation on ACPI based ARM platforms that may require HW MSI
+ * reservation.
*/
void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
{
- struct pci_host_bridge *bridge;
- struct resource_entry *window;
-
- if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) &&
- iort_iommu_msi_get_resv_regions(dev, list) < 0)
- return;
-
- if (!dev_is_pci(dev))
- return;
-
- bridge = pci_find_host_bridge(to_pci_dev(dev)->bus);
- resource_list_for_each_entry(window, &bridge->windows) {
- struct iommu_resv_region *region;
- phys_addr_t start;
- size_t length;
-
- if (resource_type(window->res) != IORESOURCE_MEM)
- continue;
- start = window->res->start - window->offset;
- length = window->res->end - window->res->start + 1;
- region = iommu_alloc_resv_region(start, length, 0,
- IOMMU_RESV_RESERVED);
- if (!region)
- return;
+ if (!is_of_node(dev->iommu_fwspec->iommu_fwnode))
+ iort_iommu_msi_get_resv_regions(dev, list);
- list_add_tail(®ion->list, list);
- }
}
EXPORT_SYMBOL(iommu_dma_get_resv_regions);
return 0;
}
+static void iova_reserve_pci_windows(struct pci_dev *dev,
+ struct iova_domain *iovad)
+{
+ struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+ struct resource_entry *window;
+ unsigned long lo, hi;
+
+ resource_list_for_each_entry(window, &bridge->windows) {
+ if (resource_type(window->res) != IORESOURCE_MEM)
+ continue;
+
+ lo = iova_pfn(iovad, window->res->start - window->offset);
+ hi = iova_pfn(iovad, window->res->end - window->offset);
+ reserve_iova(iovad, lo, hi);
+ }
+}
+
static int iova_reserve_iommu_regions(struct device *dev,
struct iommu_domain *domain)
{
LIST_HEAD(resv_regions);
int ret = 0;
+ if (dev_is_pci(dev))
+ iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+
iommu_get_resv_regions(dev, &resv_regions);
list_for_each_entry(region, &resv_regions, list) {
unsigned long lo, hi;
struct qi_desc desc;
if (mask) {
- BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+ WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
} else
irte->dest_id = IRTE_DEST(cfg->dest_apicid);
/* Update the hardware only if the interrupt is in remapped mode. */
- if (!force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+ if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
modify_irte(&ir_data->irq_2_iommu, irte);
}
data->iommu = platform_get_drvdata(iommu_dev);
dev->archdata.iommu = data;
- of_dev_put(iommu_dev);
+ platform_device_put(iommu_dev);
return 0;
}
for (i = 0; i < iommu->num_clocks; ++i)
iommu->clocks[i].id = rk_iommu_clocks[i];
+ /*
+ * iommu clocks should be present for all new devices and devicetrees
+ * but there are older devicetrees without clocks out in the wild.
+ * So clocks as optional for the time being.
+ */
err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
- if (err)
+ if (err == -ENOENT)
+ iommu->num_clocks = 0;
+ else if (err)
return err;
err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
-/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 and
bit = readl_relaxed(combiner->regs[reg].addr);
status = bit & combiner->regs[reg].enabled;
- if (!status)
+ if (bit && !status)
pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n",
smp_processor_id(), bit,
combiner->regs[reg].enabled,
if (kthread_should_stop() || \
test_bit(CACHE_SET_IO_DISABLE, &ca->set->flags)) { \
set_current_state(TASK_RUNNING); \
- return 0; \
+ goto out; \
} \
\
schedule(); \
bch_prio_write(ca);
}
}
+out:
+ wait_for_kthread_stop();
+ return 0;
}
/* Allocation */
#define DEFAULT_CACHED_DEV_ERROR_LIMIT 64
atomic_t io_errors;
unsigned error_limit;
+
+ char backing_dev_name[BDEVNAME_SIZE];
};
enum alloc_reserve {
atomic_long_t meta_sectors_written;
atomic_long_t btree_sectors_written;
atomic_long_t sectors_written;
+
+ char cache_dev_name[BDEVNAME_SIZE];
};
struct gc_stat {
void bch_data_verify(struct cached_dev *dc, struct bio *bio)
{
- char name[BDEVNAME_SIZE];
struct bio *check;
struct bio_vec bv, cbv;
struct bvec_iter iter, citer = { 0 };
bv.bv_len),
dc->disk.c,
"verify failed at dev %s sector %llu",
- bdevname(dc->bdev, name),
+ dc->backing_dev_name,
(uint64_t) bio->bi_iter.bi_sector);
kunmap_atomic(p1);
int __init bch_debug_init(struct kobject *kobj)
{
- bcache_debug = debugfs_create_dir("bcache", NULL);
+ if (!IS_ENABLED(CONFIG_DEBUG_FS))
+ return 0;
+ bcache_debug = debugfs_create_dir("bcache", NULL);
return IS_ERR_OR_NULL(bcache_debug);
}
/* IO errors */
void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
{
- char buf[BDEVNAME_SIZE];
unsigned errors;
WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
pr_err("%s: IO error on backing device, unrecoverable",
- bio_devname(bio, buf));
+ dc->backing_dev_name);
else
bch_cached_dev_error(dc);
}
}
if (error) {
- char buf[BDEVNAME_SIZE];
unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
&ca->io_errors);
errors >>= IO_ERROR_SHIFT;
if (errors < ca->set->error_limit)
pr_err("%s: IO error on %s%s",
- bdevname(ca->bdev, buf), m,
+ ca->cache_dev_name, m,
is_read ? ", recovering." : ".");
else
bch_cache_set_error(ca->set,
"%s: too many IO errors %s",
- bdevname(ca->bdev, buf), m);
+ ca->cache_dev_name, m);
}
}
*/
if (unlikely(s->iop.writeback &&
bio->bi_opf & REQ_PREFLUSH)) {
- char buf[BDEVNAME_SIZE];
-
- bio_devname(bio, buf);
pr_err("Can't flush %s: returned bi_status %i",
- buf, bio->bi_status);
+ dc->backing_dev_name, bio->bi_status);
} else {
/* set to orig_bio->bi_status in bio_complete() */
s->iop.status = bio->bi_status;
static void cached_dev_detach_finish(struct work_struct *w)
{
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
- char buf[BDEVNAME_SIZE];
struct closure cl;
closure_init_stack(&cl);
mutex_unlock(&bch_register_lock);
- pr_info("Caching disabled for %s", bdevname(dc->bdev, buf));
+ pr_info("Caching disabled for %s", dc->backing_dev_name);
/* Drop ref we took in cached_dev_detach() */
closure_put(&dc->disk.cl);
{
uint32_t rtime = cpu_to_le32(get_seconds());
struct uuid_entry *u;
- char buf[BDEVNAME_SIZE];
struct cached_dev *exist_dc, *t;
- bdevname(dc->bdev, buf);
-
if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
(!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
return -ENOENT;
if (dc->disk.c) {
- pr_err("Can't attach %s: already attached", buf);
+ pr_err("Can't attach %s: already attached",
+ dc->backing_dev_name);
return -EINVAL;
}
if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
- pr_err("Can't attach %s: shutting down", buf);
+ pr_err("Can't attach %s: shutting down",
+ dc->backing_dev_name);
return -EINVAL;
}
if (dc->sb.block_size < c->sb.block_size) {
/* Will die */
pr_err("Couldn't attach %s: block size less than set's block size",
- buf);
+ dc->backing_dev_name);
return -EINVAL;
}
list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
pr_err("Tried to attach %s but duplicate UUID already attached",
- buf);
+ dc->backing_dev_name);
return -EINVAL;
}
if (!u) {
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- pr_err("Couldn't find uuid for %s in set", buf);
+ pr_err("Couldn't find uuid for %s in set",
+ dc->backing_dev_name);
return -ENOENT;
}
u = uuid_find_empty(c);
if (!u) {
- pr_err("Not caching %s, no room for UUID", buf);
+ pr_err("Not caching %s, no room for UUID",
+ dc->backing_dev_name);
return -EINVAL;
}
}
up_write(&dc->writeback_lock);
pr_info("Caching %s as %s on set %pU",
- bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
+ dc->backing_dev_name,
+ dc->disk.disk->disk_name,
dc->disk.c->sb.set_uuid);
return 0;
}
struct block_device *bdev,
struct cached_dev *dc)
{
- char name[BDEVNAME_SIZE];
const char *err = "cannot allocate memory";
struct cache_set *c;
+ bdevname(bdev, dc->backing_dev_name);
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
dc->bdev = bdev;
dc->bdev->bd_holder = dc;
bio_first_bvec_all(&dc->sb_bio)->bv_page = sb_page;
get_page(sb_page);
+
if (cached_dev_init(dc, sb->block_size << 9))
goto err;
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
goto err;
- pr_info("registered backing device %s", bdevname(bdev, name));
+ pr_info("registered backing device %s", dc->backing_dev_name);
list_add(&dc->list, &uncached_devices);
list_for_each_entry(c, &bch_cache_sets, list)
return;
err:
- pr_notice("error %s: %s", bdevname(bdev, name), err);
+ pr_notice("error %s: %s", dc->backing_dev_name, err);
bcache_device_stop(&dc->disk);
}
bool bch_cached_dev_error(struct cached_dev *dc)
{
- char name[BDEVNAME_SIZE];
+ struct cache_set *c;
if (!dc || test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags))
return false;
smp_mb();
pr_err("stop %s: too many IO errors on backing device %s\n",
- dc->disk.disk->disk_name, bdevname(dc->bdev, name));
+ dc->disk.disk->disk_name, dc->backing_dev_name);
+
+ /*
+ * If the cached device is still attached to a cache set,
+ * even dc->io_disable is true and no more I/O requests
+ * accepted, cache device internal I/O (writeback scan or
+ * garbage collection) may still prevent bcache device from
+ * being stopped. So here CACHE_SET_IO_DISABLE should be
+ * set to c->flags too, to make the internal I/O to cache
+ * device rejected and stopped immediately.
+ * If c is NULL, that means the bcache device is not attached
+ * to any cache set, then no CACHE_SET_IO_DISABLE bit to set.
+ */
+ c = dc->disk.c;
+ if (c && test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
+ pr_info("CACHE_SET_IO_DISABLE already set");
bcache_device_stop(&dc->disk);
return true;
return false;
if (test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
- pr_warn("CACHE_SET_IO_DISABLE already set");
+ pr_info("CACHE_SET_IO_DISABLE already set");
/* XXX: we can be called from atomic context
acquire_console_sem();
*/
pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.",
d->disk->disk_name);
+ /*
+ * There might be a small time gap that cache set is
+ * released but bcache device is not. Inside this time
+ * gap, regular I/O requests will directly go into
+ * backing device as no cache set attached to. This
+ * behavior may also introduce potential inconsistence
+ * data in writeback mode while cache is dirty.
+ * Therefore before calling bcache_device_stop() due
+ * to a broken cache device, dc->io_disable should be
+ * explicitly set to true.
+ */
+ dc->io_disable = true;
+ /* make others know io_disable is true earlier */
+ smp_mb();
bcache_device_stop(d);
} else {
/*
static int register_cache(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev, struct cache *ca)
{
- char name[BDEVNAME_SIZE];
const char *err = NULL; /* must be set for any error case */
int ret = 0;
- bdevname(bdev, name);
-
+ bdevname(bdev, ca->cache_dev_name);
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
ca->bdev->bd_holder = ca;
goto out;
}
- pr_info("registered cache device %s", name);
+ pr_info("registered cache device %s", ca->cache_dev_name);
out:
kobject_put(&ca->kobj);
err:
if (err)
- pr_notice("error %s: %s", name, err);
+ pr_notice("error %s: %s", ca->cache_dev_name, err);
return ret;
}
struct keybuf_key *w = bio->bi_private;
struct dirty_io *io = w->private;
- if (bio->bi_status)
+ if (bio->bi_status) {
SET_KEY_DIRTY(&w->key, false);
+ bch_count_backing_io_errors(io->dc, bio);
+ }
closure_put(&io->cl);
}
if (block_size <= KMALLOC_MAX_SIZE &&
(block_size < PAGE_SIZE || !is_power_of_2(block_size))) {
- snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", c->block_size);
- c->slab_cache = kmem_cache_create(slab_name, c->block_size, ARCH_KMALLOC_MINALIGN,
+ unsigned align = min(1U << __ffs(block_size), (unsigned)PAGE_SIZE);
+ snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", block_size);
+ c->slab_cache = kmem_cache_create(slab_name, block_size, align,
SLAB_RECLAIM_ACCOUNT, NULL);
if (!c->slab_cache) {
r = -ENOMEM;
atomic_read(&b->pending_demotes) >= b->max_work;
}
-struct bt_work *alloc_work(struct background_tracker *b)
+static struct bt_work *alloc_work(struct background_tracker *b)
{
if (max_work_reached(b))
return NULL;
unsigned i;
for (i = 0; i < ic->journal_sections; i++)
kvfree(sl[i]);
- kfree(sl);
+ kvfree(sl);
}
static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_integrity_c *ic, struct page_list *pl)
#define MAX_RECOVERY 1 /* Maximum number of regions recovered in parallel. */
+#define MAX_NR_MIRRORS (DM_KCOPYD_MAX_REGIONS + 1)
+
#define DM_RAID1_HANDLE_ERRORS 0x01
#define DM_RAID1_KEEP_LOG 0x02
#define errors_handled(p) ((p)->features & DM_RAID1_HANDLE_ERRORS)
unsigned long error_bits;
unsigned int i;
- struct dm_io_region io[ms->nr_mirrors];
+ struct dm_io_region io[MAX_NR_MIRRORS];
struct mirror *m;
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
static void do_write(struct mirror_set *ms, struct bio *bio)
{
unsigned int i;
- struct dm_io_region io[ms->nr_mirrors], *dest = io;
+ struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
struct mirror *m;
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
argc -= args_used;
if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 ||
- nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) {
+ nr_mirrors < 2 || nr_mirrors > MAX_NR_MIRRORS) {
ti->error = "Invalid number of mirrors";
dm_dirty_log_destroy(dl);
return -EINVAL;
int num_feature_args = 0;
struct mirror_set *ms = (struct mirror_set *) ti->private;
struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
- char buffer[ms->nr_mirrors + 1];
+ char buffer[MAX_NR_MIRRORS + 1];
switch (type) {
case STATUSTYPE_INFO:
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
- sector_t sector, int *srcu_idx)
+ sector_t sector, int *srcu_idx)
+ __acquires(md->io_barrier)
{
struct dm_table *map;
struct dm_target *ti;
}
static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
+ long nr_pages, void **kaddr, pfn_t *pfn)
{
struct mapped_device *md = dax_get_private(dax_dev);
sector_t sector = pgoff * PAGE_SECTORS;
}
static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
- void *addr, size_t bytes, struct iov_iter *i)
+ void *addr, size_t bytes, struct iov_iter *i)
{
struct mapped_device *md = dax_get_private(dax_dev);
sector_t sector = pgoff * PAGE_SECTORS;
//
// VBI support (2004) and cleanups (2005) by Hans Verkuil <hverkuil@xs4all.nl>
//
-// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
// SAA7111, SAA7113 and SAA7118 support
#include "saa711x_regs.h"
* SPDX-License-Identifier: GPL-2.0+
* saa711x - Philips SAA711x video decoder register specifications
*
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#define R_00_CHIP_VERSION 0x00
* Muting and tone control by Jonathan Isom <jisom@ematic.com>
*
* Copyright (c) 2000 Eric Sandeen <eric_sandeen@bigfoot.com>
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
* Based on tda9855.c by Steve VanDeBogart (vandebo@uclink.berkeley.edu)
* Which was based on tda8425.c by Greg Alexander (c) 1998
//
// tvp5150 - Texas Instruments TVP5150A/AM1 and TVP5151 video decoder driver
//
-// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <dt-bindings/media/tvp5150.h>
#include <linux/i2c.h>
*
* tvp5150 - Texas Instruments TVP5150A/AM1 video decoder registers
*
- * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#define TVP5150_VD_IN_SRC_SEL_1 0x00 /* Video input source selection #1 */
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14. Revisions by
* Muralidharan Karicheri and Snehaprabha Narnakaje (TI).
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14
*
* Copyright (C) 2010 Nokia Corporation
*
* Based on drivers/media/video/v4l2_dev.c code authored by
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
* Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
*
* Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
/*
* Handlers for board audio hooks, splitted from bttv-cards
*
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
*/
/*
* Handlers for board audio hooks, splitted from bttv-cards
*
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
*/
},
/* ---- card 0x88---------------------------------- */
[BTTV_BOARD_ACORP_Y878F] = {
- /* Mauro Carvalho Chehab <mchehab@infradead.org> */
+ /* Mauro Carvalho Chehab <mchehab@kernel.org> */
.name = "Acorp Y878F",
.video_inputs = 3,
/* .audio_inputs= 1, */
},
[BTTV_BOARD_ENLTV_FM_2] = {
/* Encore TV Tuner Pro ENL TV-FM-2
- Mauro Carvalho Chehab <mchehab@infradead.org */
+ Mauro Carvalho Chehab <mchehab@kernel.org> */
.name = "Encore ENL TV-FM-2",
.video_inputs = 3,
/* .audio_inputs= 1, */
(c) 2005-2006 Nickolay V. Shmyrev <nshmyrev@yandex.ru>
Fixes to be fully V4L2 compliant by
- (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
Cropping and overscan support
Copyright (C) 2005, 2006 Michael H. Schimek <mschimek@gmx.at>
& Marcus Metzler (mocm@thp.uni-koeln.de)
(c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
- (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
- Multituner support and i2c address binding
This program is free software; you can redistribute it and/or modify
* Copyright (C) 2008 <srinivasa.deevi at conexant dot com>
* Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
* Markus Rechberger <mrechberger@gmail.com>
- * Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Mauro Carvalho Chehab <mchehab@kernel.org>
* Sascha Sommer <saschasommer@freenet.de>
* Copyright (C) 2004, 2005 Chris Pascoe
* Copyright (C) 2003, 2004 Gerd Knorr
*
* (c) 2007 Trent Piepho <xyzzy@speakeasy.org>
* (c) 2005,2006 Ricardo Cerqueira <v4l@cerqueira.org>
- * (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
* Based on a dummy cx88 module by Gerd Knorr <kraxel@bytesex.org>
* Based on dummy.c by Jaroslav Kysela <perex@perex.cz>
*
MODULE_DESCRIPTION("ALSA driver module for cx2388x based TV cards");
MODULE_AUTHOR("Ricardo Cerqueira");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
MODULE_VERSION(CX88_VERSION);
* (c) 2004 Jelle Foks <jelle@foks.us>
* (c) 2004 Gerd Knorr <kraxel@bytesex.org>
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - video_ioctl2 conversion
*
* Includes parts from the ivtv driver <http://sourceforge.net/projects/ivtv/>
*
* (c) 2003 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support
* - video_ioctl2 conversion
* - PAL/M fixes
* (c) 2002 Yurij Sysoev <yurij@naturesoft.net>
* (c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
*
- * (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support and i2c address binding
*
* This program is free software; you can redistribute it and/or modify
*
* (c) 2003-04 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support
* - video_ioctl2 conversion
* - PAL/M fixes
* Copyright 1997 M. Kirkwood
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
* Converted to new API by Alan Cox <alan@lxorguk.ukuu.org.uk>
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
* radio-aztech.c - Aztech radio card driver
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@xs4all.nl>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
* Adapted to support the Video for Linux API by
* Russell Kroll <rkroll@exploits.org>. Based on original tuner code by:
*
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Note: this card seems to swap the left and right audio channels!
*
* BUGS:
* - card unmutes if you change frequency
*
- * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@infradead.org>:
+ * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@kernel.org>:
* - Conversion to V4L2 API
* - Uses video_ioctl2 for parsing and to add debug support
*/
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Fully tested with actual hardware and the v4l2-compliance tool.
*/
* No volume control - only mute/unmute - you have to use line volume
* control on SB-part of SF16-FMI/SF16-FMP/SF16-FMD
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/kernel.h> /* __setup */
* Volume Control is done digitally
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/module.h> /* Modules */
* Scott McGrath (smcgrath@twilight.vtc.vsc.edu)
* William McGrath (wmcgrath@twilight.vtc.vsc.edu)
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <stdarg.h>
* The frequency change is necessary since the card never seems to be
* completely silent.
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/module.h> /* Modules */
* 2002-07-15 - Fix Stereo typo
*
* 2006-07-24 - Converted to V4L2 API
- * by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
*
*
* On Avermedia M135A with IR model RM-JX, the same codes exist on both
* Positivo (BR) and original IR, initial version and remote control codes
- * added by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * added by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Positivo also ships Avermedia M135A with model RM-K6, extra control
* codes added by Herton Ronaldo Krzesinski <herton@mandriva.com.br>
#include <linux/module.h>
/* Encore ENLTV-FM v5.3
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table encore_enltv_fm53[] = {
#include <linux/module.h>
/* Encore ENLTV2-FM - silver plastic - "Wand Media" written at the botton
- Mauro Carvalho Chehab <mchehab@infradead.org> */
+ Mauro Carvalho Chehab <mchehab@kernel.org> */
static struct rc_map_table encore_enltv2[] = {
{ 0x4c, KEY_POWER2 },
#include <linux/module.h>
/* Kaiomy TVnPC U2
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table kaiomy[] = {
#include <linux/module.h>
/* Kworld Plus TV Analog Lite PCI IR
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table kworld_plus_tv_analog[] = {
#include <linux/module.h>
/*
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
present on PV MPEG 8000GT
*/
// For Philips TEA5761 FM Chip
// I2C address is always 0x20 (0x10 at 7-bit mode).
//
-// Copyright (c) 2005-2007 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <linux/i2c.h>
#include <linux/slab.h>
EXPORT_SYMBOL_GPL(tea5761_autodetection);
MODULE_DESCRIPTION("Philips TEA5761 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
// For Philips TEA5767 FM Chip used on some TV Cards like Prolink Pixelview
// I2C address is always 0xC0.
//
-// Copyright (c) 2005 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// tea5767 autodetection thanks to Torsten Seeboth and Atsushi Nakagawa
// from their contributions on DScaler.
EXPORT_SYMBOL_GPL(tea5767_autodetection);
MODULE_DESCRIPTION("Philips TEA5767 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
* This file includes internal tipes to be used inside tuner-xc2028.
* Shouldn't be included outside tuner-xc2028
*
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
/* xc3028 firmware types */
// SPDX-License-Identifier: GPL-2.0
// tuner-xc2028
//
-// Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig (michel.ludwig@gmail.com)
// - frontend interface
MODULE_DESCRIPTION("Xceive xc2028/xc3028 tuner driver");
MODULE_AUTHOR("Michel Ludwig <michel.ludwig@gmail.com>");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
MODULE_FIRMWARE(XC2028_DEFAULT_FIRMWARE);
MODULE_FIRMWARE(XC3028L_DEFAULT_FIRMWARE);
* SPDX-License-Identifier: GPL-2.0
* tuner-xc2028
*
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#ifndef __TUNER_XC2028_H__
//
// em28xx-camera.c - driver for Empia EM25xx/27xx/28xx USB video capture devices
//
-// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
// Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
//
// This program is free software; you can redistribute it and/or modify
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
#define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
"Markus Rechberger <mrechberger@gmail.com>, " \
- "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+ "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
"Sascha Sommer <saschasommer@freenet.de>"
MODULE_AUTHOR(DRIVER_AUTHOR);
//
// DVB device driver for em28xx
//
-// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@infradead.org>
+// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// (c) 2008 Devin Heitmueller <devin.heitmueller@gmail.com>
// - Fixes for the driver to properly work with HVR-950
#include "tc90522.h"
#include "qm1d1c0042.h"
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION(DRIVER_DESC " - digital TV interface");
MODULE_VERSION(EM28XX_VERSION);
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
//
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
//
// This program is free software; you can redistribute it and/or modify
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
#define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
"Markus Rechberger <mrechberger@gmail.com>, " \
- "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+ "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
"Sascha Sommer <saschasommer@freenet.de>"
static unsigned int isoc_debug;
*
* Copyright (C) 2005 Markus Rechberger <mrechberger@gmail.com>
* Ludovico Cavedon <cavedon@sssup.it>
- * Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Mauro Carvalho Chehab <mchehab@kernel.org>
* Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
*
* Based on the em2800 driver from Sascha Sommer <saschasommer@freenet.de>
/*
* zc030x registers
*
- * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*
* The register aliases used here came from this driver:
* http://zc0302.sourceforge.net/zc0302.php
// SPDX-License-Identifier: GPL-2.0
// tm6000-cards.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <linux/init.h>
#include <linux/module.h>
// SPDX-License-Identifier: GPL-2.0
// tm6000-core.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - DVB-T support
// SPDX-License-Identifier: GPL-2.0
// tm6000-i2c.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - Fix SMBus Read Byte command
* SPDX-License-Identifier: GPL-2.0
* tm6000-regs.h - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
/*
* SPDX-License-Identifier: GPL-2.0
* tm6000-buf.c - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/videodev2.h>
// SPDX-License-Identifier: GPL-2.0
// tm6000-video.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - Fixed module load/unload
* SPDX-License-Identifier: GPL-2.0
* tm6000.h - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
* - DVB-T support
* 2 of the License, or (at your option) any later version.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
*
* Fixes: 20000516 Claudio Matsuoka <claudio@conectiva.com>
* - Added procfs support
subsys_initcall(videodev_init);
module_exit(videodev_exit)
-MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_DESCRIPTION("Device registrar for Video4Linux drivers v2");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CHARDEV_MAJOR(VIDEO_MAJOR);
* 2 of the License, or (at your option) any later version.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
*/
#include <linux/mm.h>
/*
* generic helper functions for handling video4linux capture buffers
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
* Copyright (c) 2008 Magnus Damm
*
* Based on videobuf-vmalloc.c,
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux dma sg buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux vmalloc buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
int main(void)
{
- DEFINE(EMIF_SDCFG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_sdcfg_val));
- DEFINE(EMIF_TIMING1_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing1_val));
- DEFINE(EMIF_TIMING2_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing2_val));
- DEFINE(EMIF_TIMING3_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing3_val));
- DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
- DEFINE(EMIF_ZQCFG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_zqcfg_val));
- DEFINE(EMIF_PMCR_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_pmcr_val));
- DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
- DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
- DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
- offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
- DEFINE(EMIF_COS_CONFIG_OFFSET,
- offsetof(struct emif_regs_amx3, emif_cos_config));
- DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
- offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
- DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
- offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
- DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
- offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
- DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ocp_config_val));
- DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
- offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
- DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
- offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
- DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
- DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
- offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
- DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
- DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
- DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
-
- BLANK();
-
- DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
- DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
- DEFINE(EMIF_PM_CONFIG_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
- DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
- offsetof(struct ti_emif_pm_data, regs_virt));
- DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
- offsetof(struct ti_emif_pm_data, regs_phys));
- DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
-
- BLANK();
-
- DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
- offsetof(struct ti_emif_pm_functions, save_context));
- DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
- offsetof(struct ti_emif_pm_functions, restore_context));
- DEFINE(EMIF_PM_ENTER_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, enter_sr));
- DEFINE(EMIF_PM_EXIT_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, exit_sr));
- DEFINE(EMIF_PM_ABORT_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, abort_sr));
- DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+ ti_emif_asm_offsets();
return 0;
}
.cmd_per_lun = 7,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = mptscsih_host_attrs,
+ .no_write_same = 1,
};
static int mptsas_get_linkerrors(struct sas_phy *phy)
bool perst_select_user;
bool perst_same_image;
bool psl_timebase_synced;
+ bool tunneled_ops_supported;
/*
* number of contexts mapped on to this card. Possible values are:
/* Required for devices using CAPP DMA mode, harmless for others */
pci_set_master(dev);
+ adapter->tunneled_ops_supported = false;
+
+ if (cxl_is_power9()) {
+ if (pnv_pci_set_tunnel_bar(dev, 0x00020000E0000000ull, 1))
+ dev_info(&dev->dev, "Tunneled operations unsupported\n");
+ else
+ adapter->tunneled_ops_supported = true;
+ }
+
if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode)))
goto err;
{
struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
+ if (cxl_is_power9())
+ pnv_pci_set_tunnel_bar(pdev, 0x00020000E0000000ull, 0);
+
cxl_native_release_psl_err_irq(adapter);
cxl_unmap_adapter_regs(adapter);
return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced);
}
+static ssize_t tunneled_ops_supported_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->tunneled_ops_supported);
+}
+
static ssize_t reset_adapter_store(struct device *device,
struct device_attribute *attr,
const char *buf, size_t count)
__ATTR_RO(base_image),
__ATTR_RO(image_loaded),
__ATTR_RO(psl_timebase_synced),
+ __ATTR_RO(tunneled_ops_supported),
__ATTR_RW(load_image_on_perst),
__ATTR_RW(perst_reloads_same_image),
__ATTR(reset, S_IWUSR, NULL, reset_adapter_store),
if (of_node && of_match_device(at24_of_match, dev))
cdata = of_device_get_match_data(dev);
else if (id)
- cdata = (void *)&id->driver_data;
+ cdata = (void *)id->driver_data;
else
cdata = acpi_device_get_match_data(dev);
#define I82802AB 0x00ad
#define I82802AC 0x00ac
#define PF38F4476 0x881c
+#define M28F00AP30 0x8963
/* STMicroelectronics chips */
#define M50LPW080 0x002F
#define M50FLW080A 0x0080
extp->MinorVersion = '1';
}
+static int cfi_is_micron_28F00AP30(struct cfi_private *cfi, struct flchip *chip)
+{
+ /*
+ * Micron(was Numonyx) 1Gbit bottom boot are buggy w.r.t
+ * Erase Supend for their small Erase Blocks(0x8000)
+ */
+ if (cfi->mfr == CFI_MFR_INTEL && cfi->id == M28F00AP30)
+ return 1;
+ return 0;
+}
+
static inline struct cfi_pri_intelext *
read_pri_intelext(struct map_info *map, __u16 adr)
{
(mode == FL_WRITING && (cfip->SuspendCmdSupport & 1))))
goto sleep;
+ /* Do not allow suspend iff read/write to EB address */
+ if ((adr & chip->in_progress_block_mask) ==
+ chip->in_progress_block_addr)
+ goto sleep;
+
+ /* do not suspend small EBs, buggy Micron Chips */
+ if (cfi_is_micron_28F00AP30(cfi, chip) &&
+ (chip->in_progress_block_mask == ~(0x8000-1)))
+ goto sleep;
/* Erase suspend */
- map_write(map, CMD(0xB0), adr);
+ map_write(map, CMD(0xB0), chip->in_progress_block_addr);
/* If the flash has finished erasing, then 'erase suspend'
* appears to make some (28F320) flash devices switch to
* 'read' mode. Make sure that we switch to 'read status'
* mode so we get the right data. --rmk
*/
- map_write(map, CMD(0x70), adr);
+ map_write(map, CMD(0x70), chip->in_progress_block_addr);
chip->oldstate = FL_ERASING;
chip->state = FL_ERASE_SUSPENDING;
chip->erase_suspended = 1;
for (;;) {
- status = map_read(map, adr);
+ status = map_read(map, chip->in_progress_block_addr);
if (map_word_andequal(map, status, status_OK, status_OK))
break;
sending the 0x70 (Read Status) command to an erasing
chip and expecting it to be ignored, that's what we
do. */
- map_write(map, CMD(0xd0), adr);
- map_write(map, CMD(0x70), adr);
+ map_write(map, CMD(0xd0), chip->in_progress_block_addr);
+ map_write(map, CMD(0x70), chip->in_progress_block_addr);
chip->oldstate = FL_READY;
chip->state = FL_ERASING;
break;
map_write(map, CMD(0xD0), adr);
chip->state = FL_ERASING;
chip->erase_suspended = 0;
+ chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(len - 1);
ret = INVAL_CACHE_AND_WAIT(map, chip, adr,
adr, len,
(mode == FL_WRITING && (cfip->EraseSuspend & 0x2))))
goto sleep;
- /* We could check to see if we're trying to access the sector
- * that is currently being erased. However, no user will try
- * anything like that so we just wait for the timeout. */
+ /* Do not allow suspend iff read/write to EB address */
+ if ((adr & chip->in_progress_block_mask) ==
+ chip->in_progress_block_addr)
+ goto sleep;
/* Erase suspend */
/* It's harmless to issue the Erase-Suspend and Erase-Resume
chip->state = FL_ERASING;
chip->erase_suspended = 0;
chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(map->size - 1);
INVALIDATE_CACHE_UDELAY(map, chip,
adr, map->size,
chip->state = FL_ERASING;
chip->erase_suspended = 0;
chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(len - 1);
INVALIDATE_CACHE_UDELAY(map, chip,
adr, len,
ret = nanddev_erase(nand, &pos);
if (ret) {
einfo->fail_addr = nanddev_pos_to_offs(nand, &pos);
- einfo->state = MTD_ERASE_FAILED;
return ret;
}
nanddev_pos_next_eraseblock(nand, &pos);
}
- einfo->state = MTD_ERASE_DONE;
-
return 0;
}
EXPORT_SYMBOL_GPL(nanddev_mtd_erase);
{
struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
struct onenand_chip *this = mtd->priv;
- dma_addr_t dma_src, dma_dst;
- int bram_offset;
+ struct device *dev = &c->pdev->dev;
void *buf = (void *)buffer;
+ dma_addr_t dma_src, dma_dst;
+ int bram_offset, err;
size_t xtra;
- int ret;
bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
- if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
- goto out_copy;
-
- /* panic_write() may be in an interrupt context */
- if (in_interrupt() || oops_in_progress)
+ /*
+ * If the buffer address is not DMA-able, len is not long enough to make
+ * DMA transfers profitable or panic_write() may be in an interrupt
+ * context fallback to PIO mode.
+ */
+ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+ count < 384 || in_interrupt() || oops_in_progress )
goto out_copy;
- if (buf >= high_memory) {
- struct page *p1;
-
- if (((size_t)buf & PAGE_MASK) !=
- ((size_t)(buf + count - 1) & PAGE_MASK))
- goto out_copy;
- p1 = vmalloc_to_page(buf);
- if (!p1)
- goto out_copy;
- buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
- }
-
xtra = count & 3;
if (xtra) {
count -= xtra;
memcpy(buf + count, this->base + bram_offset + count, xtra);
}
+ dma_dst = dma_map_single(dev, buf, count, DMA_FROM_DEVICE);
dma_src = c->phys_base + bram_offset;
- dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE);
- if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
- dev_err(&c->pdev->dev,
- "Couldn't DMA map a %d byte buffer\n",
- count);
- goto out_copy;
- }
- ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
- dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE);
-
- if (ret) {
- dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+ if (dma_mapping_error(dev, dma_dst)) {
+ dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
goto out_copy;
}
- return 0;
+ err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+ dma_unmap_single(dev, dma_dst, count, DMA_FROM_DEVICE);
+ if (!err)
+ return 0;
+
+ dev_err(dev, "timeout waiting for DMA\n");
out_copy:
memcpy(buf, this->base + bram_offset, count);
{
struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
struct onenand_chip *this = mtd->priv;
- dma_addr_t dma_src, dma_dst;
- int bram_offset;
+ struct device *dev = &c->pdev->dev;
void *buf = (void *)buffer;
- int ret;
+ dma_addr_t dma_src, dma_dst;
+ int bram_offset, err;
bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
- if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
- goto out_copy;
-
- /* panic_write() may be in an interrupt context */
- if (in_interrupt() || oops_in_progress)
+ /*
+ * If the buffer address is not DMA-able, len is not long enough to make
+ * DMA transfers profitable or panic_write() may be in an interrupt
+ * context fallback to PIO mode.
+ */
+ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+ count < 384 || in_interrupt() || oops_in_progress )
goto out_copy;
- if (buf >= high_memory) {
- struct page *p1;
-
- if (((size_t)buf & PAGE_MASK) !=
- ((size_t)(buf + count - 1) & PAGE_MASK))
- goto out_copy;
- p1 = vmalloc_to_page(buf);
- if (!p1)
- goto out_copy;
- buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
- }
-
- dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE);
+ dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE);
dma_dst = c->phys_base + bram_offset;
- if (dma_mapping_error(&c->pdev->dev, dma_src)) {
- dev_err(&c->pdev->dev,
- "Couldn't DMA map a %d byte buffer\n",
- count);
- return -1;
- }
-
- ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
- dma_unmap_single(&c->pdev->dev, dma_src, count, DMA_TO_DEVICE);
-
- if (ret) {
- dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+ if (dma_mapping_error(dev, dma_src)) {
+ dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
goto out_copy;
}
- return 0;
+ err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+ dma_unmap_page(dev, dma_src, count, DMA_TO_DEVICE);
+ if (!err)
+ return 0;
+
+ dev_err(dev, "timeout waiting for DMA\n");
out_copy:
memcpy(this->base + bram_offset, buf, count);
return ret;
ret = marvell_nfc_wait_op(chip,
- chip->data_interface.timings.sdr.tPROG_max);
+ PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
return ret;
}
NDCB0_CMD2(NAND_CMD_READSTART);
/*
- * Trigger the naked read operation only on the last chunk.
- * Otherwise, use monolithic read.
+ * Trigger the monolithic read on the first chunk, then naked read on
+ * intermediate chunks and finally a last naked read on the last chunk.
*/
- if (lt->nchunks == 1 || (chunk < lt->nchunks - 1))
+ if (chunk == 0)
nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW);
+ else if (chunk < lt->nchunks - 1)
+ nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_NAKED_RW);
else
nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_LAST_NAKED_RW);
struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout;
+ u32 xtype;
int ret;
struct marvell_nfc_op nfc_op = {
.ndcb[0] = NDCB0_CMD_TYPE(TYPE_WRITE) | NDCB0_LEN_OVRD,
* last naked write.
*/
if (chunk == 0) {
- nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_WRITE_DISPATCH) |
+ if (lt->nchunks == 1)
+ xtype = XTYPE_MONOLITHIC_RW;
+ else
+ xtype = XTYPE_WRITE_DISPATCH;
+
+ nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(xtype) |
NDCB0_ADDR_CYC(marvell_nand->addr_cyc) |
NDCB0_CMD1(NAND_CMD_SEQIN);
nfc_op.ndcb[1] |= NDCB1_ADDRS_PAGE(page);
}
ret = marvell_nfc_wait_op(chip,
- chip->data_interface.timings.sdr.tPROG_max);
+ PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
marvell_nfc_disable_hw_ecc(chip);
/*
* The legacy "num-cs" property indicates the number of CS on the only
* chip connected to the controller (legacy bindings does not support
- * more than one chip). CS are only incremented one by one while the RB
- * pin is always the #0.
+ * more than one chip). The CS and RB pins are always the #0.
*
* When not using legacy bindings, a couple of "reg" and "nand-rb"
* properties must be filled. For each chip, expressed as a subnode,
* "reg" points to the CS lines and "nand-rb" to the RB line.
*/
- if (pdata) {
+ if (pdata || nfc->caps->legacy_of_bindings) {
nsels = 1;
- } else if (nfc->caps->legacy_of_bindings &&
- !of_get_property(np, "num-cs", &nsels)) {
- dev_err(dev, "missing num-cs property\n");
- return -EINVAL;
- } else if (!of_get_property(np, "reg", &nsels)) {
- dev_err(dev, "missing reg property\n");
- return -EINVAL;
- }
-
- if (!pdata)
- nsels /= sizeof(u32);
- if (!nsels) {
- dev_err(dev, "invalid reg property size\n");
- return -EINVAL;
+ } else {
+ nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32));
+ if (nsels <= 0) {
+ dev_err(dev, "missing/invalid reg property\n");
+ return -EINVAL;
+ }
}
/* Alloc the nand chip structure */
*/
int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
{
+ const struct nand_sdr_timings *timings;
u8 status = 0;
int ret;
if (!chip->exec_op)
return -ENOTSUPP;
+ /* Wait tWB before polling the STATUS reg. */
+ timings = nand_get_sdr_timings(&chip->data_interface);
+ ndelay(PSEC_TO_NSEC(timings->tWB_max));
+
ret = nand_status_op(chip, NULL);
if (ret)
return ret;
writel_relaxed(MODE_RAW, nfc->pbus_base + PBUS_PAD_MODE);
- clk = clk_get(&pdev->dev, NULL);
+ clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(clk))
return PTR_ERR(clk);
void __iomem *reg_base = cqspi->iobase;
void __iomem *ahb_base = cqspi->ahb_base;
unsigned int remaining = n_rx;
+ unsigned int mod_bytes = n_rx % 4;
unsigned int bytes_to_read = 0;
+ u8 *rxbuf_end = rxbuf + n_rx;
int ret = 0;
writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
}
while (bytes_to_read != 0) {
+ unsigned int word_remain = round_down(remaining, 4);
+
bytes_to_read *= cqspi->fifo_width;
bytes_to_read = bytes_to_read > remaining ?
remaining : bytes_to_read;
- ioread32_rep(ahb_base, rxbuf,
- DIV_ROUND_UP(bytes_to_read, 4));
+ bytes_to_read = round_down(bytes_to_read, 4);
+ /* Read 4 byte word chunks then single bytes */
+ if (bytes_to_read) {
+ ioread32_rep(ahb_base, rxbuf,
+ (bytes_to_read / 4));
+ } else if (!word_remain && mod_bytes) {
+ unsigned int temp = ioread32(ahb_base);
+
+ bytes_to_read = mod_bytes;
+ memcpy(rxbuf, &temp, min((unsigned int)
+ (rxbuf_end - rxbuf),
+ bytes_to_read));
+ }
rxbuf += bytes_to_read;
remaining -= bytes_to_read;
bytes_to_read = cqspi_get_rd_sram_level(cqspi);
config GENEVE
tristate "Generic Network Virtualization Encapsulation"
depends on INET && NET_UDP_TUNNEL
+ depends on IPV6 || !IPV6
select NET_IP_TUNNEL
select GRO_CELLS
---help---
#include <net/bonding.h>
#include <net/bond_alb.h>
-
-
-static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {
- 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
-};
static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
0x33, 0x33, 0x00, 0x00, 0x00, 0x01
};
if (assigned_slave) {
rx_hash_table[index].slave = assigned_slave;
- if (!ether_addr_equal_64bits(rx_hash_table[index].mac_dst,
- mac_bcast)) {
+ if (is_valid_ether_addr(rx_hash_table[index].mac_dst)) {
bond_info->rx_hashtbl[index].ntt = 1;
bond_info->rx_ntt = 1;
/* A slave has been removed from the
{
int i;
- if (!client_info->slave)
+ if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst))
return;
for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
client_info = &(bond_info->rx_hashtbl[hash_index]);
if ((client_info->slave == slave) &&
- !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {
+ is_valid_ether_addr(client_info->mac_dst)) {
client_info->ntt = 1;
ntt = 1;
}
if ((client_info->ip_src == src_ip) &&
!ether_addr_equal_64bits(client_info->slave->dev->dev_addr,
bond->dev->dev_addr) &&
- !ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {
+ is_valid_ether_addr(client_info->mac_dst)) {
client_info->ntt = 1;
bond_info->rx_ntt = 1;
}
if ((client_info->ip_src == arp->ip_src) &&
(client_info->ip_dst == arp->ip_dst)) {
/* the entry is already assigned to this client */
- if (!ether_addr_equal_64bits(arp->mac_dst, mac_bcast)) {
+ if (!is_broadcast_ether_addr(arp->mac_dst)) {
/* update mac address from arp */
ether_addr_copy(client_info->mac_dst, arp->mac_dst);
}
ether_addr_copy(client_info->mac_src, arp->mac_src);
client_info->slave = assigned_slave;
- if (!ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {
+ if (is_valid_ether_addr(client_info->mac_dst)) {
client_info->ntt = 1;
bond->alb_info.rx_ntt = 1;
} else {
assigned_slave = __rlb_next_rx_slave(bond);
if (assigned_slave && (client_info->slave != assigned_slave)) {
client_info->slave = assigned_slave;
- client_info->ntt = 1;
- ntt = 1;
+ if (!is_zero_ether_addr(client_info->mac_dst)) {
+ client_info->ntt = 1;
+ ntt = 1;
+ }
}
}
skb->priority = TC_PRIO_CONTROL;
skb->dev = slave->dev;
+ netdev_dbg(slave->bond->dev,
+ "Send learning packet: dev %s mac %pM vlan %d\n",
+ slave->dev->name, mac_addr, vid);
+
if (vid)
__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
u8 *mac_addr = data->mac_addr;
struct bond_vlan_tag *tags;
- if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
- if (strict_match &&
- ether_addr_equal_64bits(mac_addr,
- upper->dev_addr)) {
+ if (is_vlan_dev(upper) &&
+ bond->nest_level == vlan_get_encap_level(upper) - 1) {
+ if (upper->addr_assign_type == NET_ADDR_STOLEN) {
alb_send_lp_vid(slave, mac_addr,
vlan_dev_vlan_proto(upper),
vlan_dev_vlan_id(upper));
- } else if (!strict_match) {
+ } else {
alb_send_lp_vid(slave, upper->dev_addr,
vlan_dev_vlan_proto(upper),
vlan_dev_vlan_id(upper));
rlb_deinitialize(bond);
}
-static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
- struct slave *tx_slave)
+static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
+ struct slave *tx_slave)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
struct ethhdr *eth_data = eth_hdr(skb);
return NETDEV_TX_OK;
}
-int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct ethhdr *eth_data;
return bond_do_alb_xmit(skb, bond, tx_slave);
}
-int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct ethhdr *eth_data;
case ETH_P_IP: {
const struct iphdr *iph = ip_hdr(skb);
- if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast) ||
- (iph->daddr == ip_bcast) ||
- (iph->protocol == IPPROTO_IGMP)) {
+ if (is_broadcast_ether_addr(eth_data->h_dest) ||
+ iph->daddr == ip_bcast ||
+ iph->protocol == IPPROTO_IGMP) {
do_tx_balance = false;
break;
}
/* IPv6 doesn't really use broadcast mac address, but leave
* that here just in case.
*/
- if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast)) {
+ if (is_broadcast_ether_addr(eth_data->h_dest)) {
do_tx_balance = false;
break;
}
}
if (do_tx_balance) {
- hash_index = _simple_hash(hash_start, hash_size);
- tx_slave = tlb_choose_channel(bond, hash_index, skb->len);
+ if (bond->params.tlb_dynamic_lb) {
+ hash_index = _simple_hash(hash_start, hash_size);
+ tx_slave = tlb_choose_channel(bond, hash_index, skb->len);
+ } else {
+ /*
+ * do_tx_balance means we are free to select the tx_slave
+ * So we do exactly what tlb would do for hash selection
+ */
+
+ struct bond_up_slave *slaves;
+ unsigned int count;
+
+ slaves = rcu_dereference(bond->slave_arr);
+ count = slaves ? READ_ONCE(slaves->count) : 0;
+ if (likely(count))
+ tx_slave = slaves->arr[bond_xmit_hash(bond, skb) %
+ count];
+ }
}
return bond_do_alb_xmit(skb, bond, tx_slave);
MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier");
module_param(xmit_hash_policy, charp, 0);
-MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "
+MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; "
"0 for layer 2 (default), 1 for layer 3+4, "
"2 for layer 2+3, 3 for encap layer 2+3, "
"4 for encap layer 3+4");
BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping));
- skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+ skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
if (unlikely(netpoll_tx_running(bond->dev)))
bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
- slave_dev->npinfo = bond->dev->npinfo;
- if (slave_dev->npinfo) {
+ if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
unblock_netpoll_tx();
}
- if (bond_mode_uses_xmit_hash(bond))
+ if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
+ bond->nest_level = dev_get_nest_level(bond_dev);
+
netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
slave_dev->name,
bond_is_active_slave(new_slave) ? "an active" : "a backup",
if (BOND_MODE(bond) == BOND_MODE_8023AD)
bond_3ad_unbind_slave(slave);
- if (bond_mode_uses_xmit_hash(bond))
+ if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, slave);
netdev_info(bond_dev, "Releasing %s interface %s\n",
return commit;
}
+static void bond_miimon_link_change(struct bonding *bond,
+ struct slave *slave,
+ char link)
+{
+ switch (BOND_MODE(bond)) {
+ case BOND_MODE_8023AD:
+ bond_3ad_handle_link_change(slave, link);
+ break;
+ case BOND_MODE_TLB:
+ case BOND_MODE_ALB:
+ bond_alb_handle_link_change(bond, slave, link);
+ break;
+ case BOND_MODE_XOR:
+ bond_update_slave_arr(bond, NULL);
+ break;
+ }
+}
+
static void bond_miimon_commit(struct bonding *bond)
{
struct list_head *iter;
slave->speed == SPEED_UNKNOWN ? 0 : slave->speed,
slave->duplex ? "full" : "half");
- /* notify ad that the link status has changed */
- if (BOND_MODE(bond) == BOND_MODE_8023AD)
- bond_3ad_handle_link_change(slave, BOND_LINK_UP);
-
- if (bond_is_lb(bond))
- bond_alb_handle_link_change(bond, slave,
- BOND_LINK_UP);
-
- if (BOND_MODE(bond) == BOND_MODE_XOR)
- bond_update_slave_arr(bond, NULL);
+ bond_miimon_link_change(bond, slave, BOND_LINK_UP);
if (!bond->curr_active_slave || slave == primary)
goto do_failover;
netdev_info(bond->dev, "link status definitely down for interface %s, disabling it\n",
slave->dev->name);
- if (BOND_MODE(bond) == BOND_MODE_8023AD)
- bond_3ad_handle_link_change(slave,
- BOND_LINK_DOWN);
-
- if (bond_is_lb(bond))
- bond_alb_handle_link_change(bond, slave,
- BOND_LINK_DOWN);
-
- if (BOND_MODE(bond) == BOND_MODE_XOR)
- bond_update_slave_arr(bond, NULL);
+ bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);
if (slave == rcu_access_pointer(bond->curr_active_slave))
goto do_failover;
* events. If these (miimon/arpmon) parameters are configured
* then array gets refreshed twice and that should be fine!
*/
- if (bond_mode_uses_xmit_hash(bond))
+ if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
break;
case NETDEV_CHANGEMTU:
*/
if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB)))
return -ENOMEM;
- if (bond->params.tlb_dynamic_lb)
+ if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB)
queue_delayed_work(bond->wq, &bond->alb_work, 0);
}
bond_3ad_initiate_agg_selection(bond, 1);
}
- if (bond_mode_uses_xmit_hash(bond))
+ if (bond_mode_can_use_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
return 0;
return slave_id;
}
-static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev)
+static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
+ struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct iphdr *iph = ip_hdr(skb);
/* In active-backup mode, we know that bond->curr_active_slave is always valid if
* the bond has a usable interface.
*/
-static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev)
+static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
+ struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave;
* to determine the slave interface -
* (a) BOND_MODE_8023AD
* (b) BOND_MODE_XOR
- * (c) BOND_MODE_TLB && tlb_dynamic_lb == 0
+ * (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0
*
* The caller is expected to hold RTNL only and NO other lock!
*/
continue;
if (skipslave == slave)
continue;
+
+ netdev_dbg(bond->dev,
+ "Adding slave dev %s to tx hash array[%d]\n",
+ slave->dev->name, new_arr->count);
+
new_arr->arr[new_arr->count++] = slave;
}
* usable slave array is formed in the control path. The xmit function
* just calculates hash and sends the packet out.
*/
-static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
+ struct net_device *dev)
{
struct bonding *bond = netdev_priv(dev);
struct slave *slave;
}
/* in broadcast mode, we send everything to all usable interfaces. */
-static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
+static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
+ struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave = NULL;
struct slave *slave = NULL;
struct list_head *iter;
- if (!skb->queue_mapping)
+ if (!skb_rx_queue_recorded(skb))
return 1;
/* Find out if any slaves have the same mapping as this skb. */
bond_for_each_slave_rcu(bond, slave, iter) {
- if (slave->queue_id == skb->queue_mapping) {
+ if (slave->queue_id == skb_get_queue_mapping(skb)) {
if (bond_slave_is_up(slave) &&
slave->link == BOND_LINK_UP) {
bond_dev_queue_xmit(bond, skb, slave->dev);
u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
/* Save the original txq to restore before passing to the driver */
- qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb);
if (unlikely(txq >= dev->real_num_tx_queues)) {
do {
}
if (xmit_hash_policy) {
- if ((bond_mode != BOND_MODE_XOR) &&
- (bond_mode != BOND_MODE_8023AD) &&
- (bond_mode != BOND_MODE_TLB)) {
+ if (bond_mode == BOND_MODE_ROUNDROBIN ||
+ bond_mode == BOND_MODE_ACTIVEBACKUP ||
+ bond_mode == BOND_MODE_BROADCAST) {
pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
bond_mode_name(bond_mode));
} else {
.id = BOND_OPT_TLB_DYNAMIC_LB,
.name = "tlb_dynamic_lb",
.desc = "Enable dynamic flow shuffling",
- .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB)),
+ .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB) | BIT(BOND_MODE_ALB)),
.values = bond_tlb_dynamic_lb_tbl,
.flags = BOND_OPTFLAG_IFDOWN,
.set = bond_option_tlb_dynamic_lb_set,
{
struct can_priv *priv = netdev_priv(dev);
- netdev_dbg(dev, "bus-off\n");
+ netdev_info(dev, "bus-off\n");
netif_carrier_off(dev);
#define FLEXCAN_QUIRK_DISABLE_MECR BIT(4) /* Disable Memory error detection */
#define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP BIT(5) /* Use timestamp based offloading */
#define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6) /* No interrupt for error passive */
+#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN BIT(7) /* default to BE register access */
/* Structure of the message buffer */
struct flexcan_mb {
};
static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
+ .quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+ FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN,
+};
+
+static const struct flexcan_devtype_data fsl_imx25_devtype_data = {
.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
FLEXCAN_QUIRK_BROKEN_PERR_STATE,
};
static const struct of_device_id flexcan_of_match[] = {
{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
- { .compatible = "fsl,imx53-flexcan", .data = &fsl_p1010_devtype_data, },
- { .compatible = "fsl,imx35-flexcan", .data = &fsl_p1010_devtype_data, },
- { .compatible = "fsl,imx25-flexcan", .data = &fsl_p1010_devtype_data, },
+ { .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, },
+ { .compatible = "fsl,imx35-flexcan", .data = &fsl_imx25_devtype_data, },
+ { .compatible = "fsl,imx25-flexcan", .data = &fsl_imx25_devtype_data, },
{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
priv = netdev_priv(dev);
- if (of_property_read_bool(pdev->dev.of_node, "big-endian")) {
+ if (of_property_read_bool(pdev->dev.of_node, "big-endian") ||
+ devtype_data->quirks & FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN) {
priv->read = flexcan_read_be;
priv->write = flexcan_write_be;
} else {
- if (of_device_is_compatible(pdev->dev.of_node,
- "fsl,p1010-flexcan")) {
- priv->read = flexcan_read_be;
- priv->write = flexcan_write_be;
- } else {
- priv->read = flexcan_read_le;
- priv->write = flexcan_write_le;
- }
+ priv->read = flexcan_read_le;
+ priv->write = flexcan_write_le;
}
priv->can.clock.freq = clock_freq;
#define HI3110_STAT_BUSOFF BIT(2)
#define HI3110_STAT_ERRP BIT(3)
#define HI3110_STAT_ERRW BIT(4)
+#define HI3110_STAT_TXMTY BIT(7)
#define HI3110_BTR0_SJW_SHIFT 6
#define HI3110_BTR0_BRP_SHIFT 0
struct hi3110_priv *priv = netdev_priv(net);
struct spi_device *spi = priv->spi;
+ mutex_lock(&priv->hi3110_lock);
bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+ mutex_unlock(&priv->hi3110_lock);
return 0;
}
}
}
- if (intf == 0)
- break;
-
- if (intf & HI3110_INT_TXCPLT) {
+ if (priv->tx_len && statf & HI3110_STAT_TXMTY) {
net->stats.tx_packets++;
net->stats.tx_bytes += priv->tx_len - 1;
can_led_event(net, CAN_LED_EVENT_TX);
}
netif_wake_queue(net);
}
+
+ if (intf == 0)
+ break;
}
mutex_unlock(&priv->hi3110_lock);
return IRQ_HANDLED;
skb = alloc_can_skb(priv->netdev, &cf);
if (!skb) {
- stats->tx_dropped++;
+ stats->rx_dropped++;
return;
}
return B53_MIBS_SIZE;
}
-void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+static struct phy_device *b53_get_phy_device(struct dsa_switch *ds, int port)
+{
+ /* These ports typically do not have built-in PHYs */
+ switch (port) {
+ case B53_CPU_PORT_25:
+ case 7:
+ case B53_CPU_PORT:
+ return NULL;
+ }
+
+ return mdiobus_get_phy(ds->slave_mii_bus, port);
+}
+
+void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data)
{
struct b53_device *dev = ds->priv;
const struct b53_mib_desc *mibs = b53_get_mib(dev);
unsigned int mib_size = b53_get_mib_size(dev);
+ struct phy_device *phydev;
unsigned int i;
- for (i = 0; i < mib_size; i++)
- strlcpy(data + i * ETH_GSTRING_LEN,
- mibs[i].name, ETH_GSTRING_LEN);
+ if (stringset == ETH_SS_STATS) {
+ for (i = 0; i < mib_size; i++)
+ strlcpy(data + i * ETH_GSTRING_LEN,
+ mibs[i].name, ETH_GSTRING_LEN);
+ } else if (stringset == ETH_SS_PHY_STATS) {
+ phydev = b53_get_phy_device(ds, port);
+ if (!phydev)
+ return;
+
+ phy_ethtool_get_strings(phydev, data);
+ }
}
EXPORT_SYMBOL(b53_get_strings);
}
EXPORT_SYMBOL(b53_get_ethtool_stats);
-int b53_get_sset_count(struct dsa_switch *ds, int port)
+void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+ struct phy_device *phydev;
+
+ phydev = b53_get_phy_device(ds, port);
+ if (!phydev)
+ return;
+
+ phy_ethtool_get_stats(phydev, NULL, data);
+}
+EXPORT_SYMBOL(b53_get_ethtool_phy_stats);
+
+int b53_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
struct b53_device *dev = ds->priv;
+ struct phy_device *phydev;
+
+ if (sset == ETH_SS_STATS) {
+ return b53_get_mib_size(dev);
+ } else if (sset == ETH_SS_PHY_STATS) {
+ phydev = b53_get_phy_device(ds, port);
+ if (!phydev)
+ return 0;
+
+ return phy_ethtool_get_sset_count(phydev);
+ }
- return b53_get_mib_size(dev);
+ return 0;
}
EXPORT_SYMBOL(b53_get_sset_count);
}
EXPORT_SYMBOL(b53_br_fast_age);
-static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port)
+static bool b53_possible_cpu_port(struct dsa_switch *ds, int port)
{
/* Broadcom switches will accept enabling Broadcom tags on the
* following ports: 5, 7 and 8, any other port is not supported
return true;
}
- dev_warn(ds->dev, "Port %d is not Broadcom tag capable\n", port);
return false;
}
+static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port)
+{
+ bool ret = b53_possible_cpu_port(ds, port);
+
+ if (!ret)
+ dev_warn(ds->dev, "Port %d is not Broadcom tag capable\n",
+ port);
+ return ret;
+}
+
enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port)
{
struct b53_device *dev = ds->priv;
.get_strings = b53_get_strings,
.get_ethtool_stats = b53_get_ethtool_stats,
.get_sset_count = b53_get_sset_count,
+ .get_ethtool_phy_stats = b53_get_ethtool_phy_stats,
.phy_read = b53_phy_read16,
.phy_write = b53_phy_write16,
.adjust_link = b53_adjust_link,
dev->num_ports = dev->cpu_port + 1;
dev->enabled_ports |= BIT(dev->cpu_port);
+ /* Include non standard CPU port built-in PHYs to be probed */
+ if (is539x(dev) || is531x5(dev)) {
+ for (i = 0; i < dev->num_ports; i++) {
+ if (!(dev->ds->phys_mii_mask & BIT(i)) &&
+ !b53_possible_cpu_port(dev->ds, i))
+ dev->ds->phys_mii_mask |= BIT(i);
+ }
+ }
+
dev->ports = devm_kzalloc(dev->dev,
sizeof(struct b53_port) * dev->num_ports,
GFP_KERNEL);
/* Exported functions towards other drivers */
void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port);
int b53_configure_vlan(struct dsa_switch *ds);
-void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data);
+void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data);
void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
-int b53_get_sset_count(struct dsa_switch *ds, int port);
+int b53_get_sset_count(struct dsa_switch *ds, int port, int sset);
+void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data);
int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge);
void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge);
void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state);
#include <linux/platform_device.h>
#include <linux/phy.h>
#include <linux/phy_fixed.h>
+#include <linux/phylink.h>
#include <linux/mii.h>
#include <linux/of.h>
#include <linux/of_irq.h>
static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)
{
- struct bcm_sf2_priv *priv = dev_id;
+ struct dsa_switch *ds = dev_id;
+ struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) &
~priv->irq0_mask;
static irqreturn_t bcm_sf2_switch_1_isr(int irq, void *dev_id)
{
- struct bcm_sf2_priv *priv = dev_id;
+ struct dsa_switch *ds = dev_id;
+ struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
priv->irq1_stat = intrl2_1_readl(priv, INTRL2_CPU_STATUS) &
~priv->irq1_mask;
intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
- if (priv->irq1_stat & P_LINK_UP_IRQ(P7_IRQ_OFF))
- priv->port_sts[7].link = 1;
- if (priv->irq1_stat & P_LINK_DOWN_IRQ(P7_IRQ_OFF))
- priv->port_sts[7].link = 0;
+ if (priv->irq1_stat & P_LINK_UP_IRQ(P7_IRQ_OFF)) {
+ priv->port_sts[7].link = true;
+ dsa_port_phylink_mac_change(ds, 7, true);
+ }
+ if (priv->irq1_stat & P_LINK_DOWN_IRQ(P7_IRQ_OFF)) {
+ priv->port_sts[7].link = false;
+ dsa_port_phylink_mac_change(ds, 7, false);
+ }
return IRQ_HANDLED;
}
priv->slave_mii_bus->parent = ds->dev->parent;
priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
- if (dn)
- err = of_mdiobus_register(priv->slave_mii_bus, dn);
- else
- err = mdiobus_register(priv->slave_mii_bus);
-
- if (err)
+ err = of_mdiobus_register(priv->slave_mii_bus, dn);
+ if (err && dn)
of_node_put(dn);
return err;
return priv->hw_params.gphy_rev;
}
-static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
- struct phy_device *phydev)
+static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port,
+ unsigned long *supported,
+ struct phylink_link_state *state)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+ if (!phy_interface_mode_is_rgmii(state->interface) &&
+ state->interface != PHY_INTERFACE_MODE_MII &&
+ state->interface != PHY_INTERFACE_MODE_REVMII &&
+ state->interface != PHY_INTERFACE_MODE_GMII &&
+ state->interface != PHY_INTERFACE_MODE_INTERNAL &&
+ state->interface != PHY_INTERFACE_MODE_MOCA) {
+ bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+ dev_err(ds->dev,
+ "Unsupported interface: %d\n", state->interface);
+ return;
+ }
+
+ /* Allow all the expected bits */
+ phylink_set(mask, Autoneg);
+ phylink_set_port_modes(mask);
+ phylink_set(mask, Pause);
+ phylink_set(mask, Asym_Pause);
+
+ /* With the exclusion of MII and Reverse MII, we support Gigabit,
+ * including Half duplex
+ */
+ if (state->interface != PHY_INTERFACE_MODE_MII &&
+ state->interface != PHY_INTERFACE_MODE_REVMII) {
+ phylink_set(mask, 1000baseT_Full);
+ phylink_set(mask, 1000baseT_Half);
+ }
+
+ phylink_set(mask, 10baseT_Half);
+ phylink_set(mask, 10baseT_Full);
+ phylink_set(mask, 100baseT_Half);
+ phylink_set(mask, 100baseT_Full);
+
+ bitmap_and(supported, supported, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+ bitmap_and(state->advertising, state->advertising, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ const struct phylink_link_state *state)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- struct ethtool_eee *p = &priv->dev->ports[port].eee;
u32 id_mode_dis = 0, port_mode;
- const char *str = NULL;
u32 reg, offset;
if (priv->type == BCM7445_DEVICE_ID)
else
offset = CORE_STS_OVERRIDE_GMIIP2_PORT(port);
- switch (phydev->interface) {
+ switch (state->interface) {
case PHY_INTERFACE_MODE_RGMII:
- str = "RGMII (no delay)";
id_mode_dis = 1;
+ /* fallthrough */
case PHY_INTERFACE_MODE_RGMII_TXID:
- if (!str)
- str = "RGMII (TX delay)";
port_mode = EXT_GPHY;
break;
case PHY_INTERFACE_MODE_MII:
- str = "MII";
port_mode = EXT_EPHY;
break;
case PHY_INTERFACE_MODE_REVMII:
- str = "Reverse MII";
port_mode = EXT_REVMII;
break;
default:
- /* All other PHYs: internal and MoCA */
+ /* all other PHYs: internal and MoCA */
goto force_link;
}
- /* If the link is down, just disable the interface to conserve power */
- if (!phydev->link) {
- reg = reg_readl(priv, REG_RGMII_CNTRL_P(port));
- reg &= ~RGMII_MODE_EN;
- reg_writel(priv, reg, REG_RGMII_CNTRL_P(port));
- goto force_link;
- }
-
- /* Clear id_mode_dis bit, and the existing port mode, but
- * make sure we enable the RGMII block for data to pass
+ /* Clear id_mode_dis bit, and the existing port mode, let
+ * RGMII_MODE_EN bet set by mac_link_{up,down}
*/
reg = reg_readl(priv, REG_RGMII_CNTRL_P(port));
reg &= ~ID_MODE_DIS;
reg &= ~(PORT_MODE_MASK << PORT_MODE_SHIFT);
reg &= ~(RX_PAUSE_EN | TX_PAUSE_EN);
- reg |= port_mode | RGMII_MODE_EN;
+ reg |= port_mode;
if (id_mode_dis)
reg |= ID_MODE_DIS;
- if (phydev->pause) {
- if (phydev->asym_pause)
+ if (state->pause & MLO_PAUSE_TXRX_MASK) {
+ if (state->pause & MLO_PAUSE_TX)
reg |= TX_PAUSE_EN;
reg |= RX_PAUSE_EN;
}
reg_writel(priv, reg, REG_RGMII_CNTRL_P(port));
- pr_info("Port %d configured for %s\n", port, str);
-
force_link:
/* Force link settings detected from the PHY */
reg = SW_OVERRIDE;
- switch (phydev->speed) {
+ switch (state->speed) {
case SPEED_1000:
reg |= SPDSTS_1000 << SPEED_SHIFT;
break;
break;
}
- if (phydev->link)
+ if (state->link)
reg |= LINK_STS;
- if (phydev->duplex == DUPLEX_FULL)
+ if (state->duplex == DUPLEX_FULL)
reg |= DUPLX_MODE;
core_writel(priv, reg, offset);
-
- if (!phydev->is_pseudo_fixed_link)
- p->eee_enabled = b53_eee_init(ds, port, phydev);
}
-static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
- struct fixed_phy_status *status)
+static void bcm_sf2_sw_mac_link_set(struct dsa_switch *ds, int port,
+ phy_interface_t interface, bool link)
{
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- u32 duplex, pause, offset;
u32 reg;
- if (priv->type == BCM7445_DEVICE_ID)
- offset = CORE_STS_OVERRIDE_GMIIP_PORT(port);
+ if (!phy_interface_mode_is_rgmii(interface) &&
+ interface != PHY_INTERFACE_MODE_MII &&
+ interface != PHY_INTERFACE_MODE_REVMII)
+ return;
+
+ /* If the link is down, just disable the interface to conserve power */
+ reg = reg_readl(priv, REG_RGMII_CNTRL_P(port));
+ if (link)
+ reg |= RGMII_MODE_EN;
else
- offset = CORE_STS_OVERRIDE_GMIIP2_PORT(port);
+ reg &= ~RGMII_MODE_EN;
+ reg_writel(priv, reg, REG_RGMII_CNTRL_P(port));
+}
- duplex = core_readl(priv, CORE_DUPSTS);
- pause = core_readl(priv, CORE_PAUSESTS);
+static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ phy_interface_t interface)
+{
+ bcm_sf2_sw_mac_link_set(ds, port, interface, false);
+}
- status->link = 0;
+static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ phy_interface_t interface,
+ struct phy_device *phydev)
+{
+ struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+ struct ethtool_eee *p = &priv->dev->ports[port].eee;
+
+ bcm_sf2_sw_mac_link_set(ds, port, interface, true);
+
+ if (mode == MLO_AN_PHY && phydev)
+ p->eee_enabled = b53_eee_init(ds, port, phydev);
+}
+
+static void bcm_sf2_sw_fixed_state(struct dsa_switch *ds, int port,
+ struct phylink_link_state *status)
+{
+ struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+
+ status->link = false;
/* MoCA port is special as we do not get link status from CORE_LNKSTS,
* which means that we need to force the link at the port override
*/
if (!status->link)
netif_carrier_off(ds->ports[port].slave);
- status->duplex = 1;
+ status->duplex = DUPLEX_FULL;
} else {
- status->link = 1;
- status->duplex = !!(duplex & (1 << port));
- }
-
- reg = core_readl(priv, offset);
- reg |= SW_OVERRIDE;
- if (status->link)
- reg |= LINK_STS;
- else
- reg &= ~LINK_STS;
- core_writel(priv, reg, offset);
-
- if ((pause & (1 << port)) &&
- (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) {
- status->asym_pause = 1;
- status->pause = 1;
+ status->link = true;
}
-
- if (pause & (1 << port))
- status->pause = 1;
}
static void bcm_sf2_enable_acb(struct dsa_switch *ds)
.get_strings = b53_get_strings,
.get_ethtool_stats = b53_get_ethtool_stats,
.get_sset_count = b53_get_sset_count,
+ .get_ethtool_phy_stats = b53_get_ethtool_phy_stats,
.get_phy_flags = bcm_sf2_sw_get_phy_flags,
- .adjust_link = bcm_sf2_sw_adjust_link,
- .fixed_link_update = bcm_sf2_sw_fixed_link_update,
+ .phylink_validate = bcm_sf2_sw_validate,
+ .phylink_mac_config = bcm_sf2_sw_mac_config,
+ .phylink_mac_link_down = bcm_sf2_sw_mac_link_down,
+ .phylink_mac_link_up = bcm_sf2_sw_mac_link_up,
+ .phylink_fixed_state = bcm_sf2_sw_fixed_state,
.suspend = bcm_sf2_sw_suspend,
.resume = bcm_sf2_sw_resume,
.get_wol = bcm_sf2_sw_get_wol,
bcm_sf2_intr_disable(priv);
ret = devm_request_irq(&pdev->dev, priv->irq0, bcm_sf2_switch_0_isr, 0,
- "switch_0", priv);
+ "switch_0", ds);
if (ret < 0) {
pr_err("failed to request switch_0 IRQ\n");
goto out_mdio;
}
ret = devm_request_irq(&pdev->dev, priv->irq1, bcm_sf2_switch_1_isr, 0,
- "switch_1", priv);
+ "switch_1", ds);
if (ret < 0) {
pr_err("failed to request switch_1 IRQ\n");
goto out_mdio;
/* Locate the first rule available */
if (fs->location == RX_CLS_LOC_ANY)
rule_index = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
+ priv->num_cfp_rules);
else
rule_index = fs->location;
+ if (rule_index > bcm_sf2_cfp_rule_size(priv))
+ return -ENOSPC;
+
layout = &udf_tcpip4_layout;
/* We only use one UDF slice for now */
slice_num = bcm_sf2_get_slice_number(layout, 0);
* first half because the HW search is by incrementing addresses.
*/
if (fs->location == RX_CLS_LOC_ANY)
- rule_index[0] = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
+ rule_index[1] = find_first_zero_bit(priv->cfp.used,
+ priv->num_cfp_rules);
else
- rule_index[0] = fs->location;
+ rule_index[1] = fs->location;
+ if (rule_index[1] > bcm_sf2_cfp_rule_size(priv))
+ return -ENOSPC;
/* Flag it as used (cleared on error path) such that we can immediately
* obtain a second one to chain from.
*/
- set_bit(rule_index[0], priv->cfp.used);
+ set_bit(rule_index[1], priv->cfp.used);
- rule_index[1] = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
- if (rule_index[1] > bcm_sf2_cfp_rule_size(priv)) {
+ rule_index[0] = find_first_zero_bit(priv->cfp.used,
+ priv->num_cfp_rules);
+ if (rule_index[0] > bcm_sf2_cfp_rule_size(priv)) {
ret = -ENOSPC;
goto out_err;
}
/* Flag the second half rule as being used now, return it as the
* location, and flag it as unique while dumping rules
*/
- set_bit(rule_index[1], priv->cfp.used);
+ set_bit(rule_index[0], priv->cfp.used);
set_bit(rule_index[1], priv->cfp.unique);
fs->location = rule_index[1];
return ret;
out_err:
- clear_bit(rule_index[0], priv->cfp.used);
+ clear_bit(rule_index[1], priv->cfp.used);
return ret;
}
int ret;
u32 reg;
- /* Refuse deletion of unused rules, and the default reserved rule */
- if (!test_bit(loc, priv->cfp.used) || loc == 0)
- return -EINVAL;
-
/* Indicate which rule we want to read */
bcm_sf2_cfp_rule_addr_set(priv, loc);
u32 next_loc = 0;
int ret;
+ /* Refuse deleting unused rules, and those that are not unique since
+ * that could leave IPv6 rules with one of the chained rule in the
+ * table.
+ */
+ if (!test_bit(loc, priv->cfp.unique) || loc == 0)
+ return -EINVAL;
+
ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
if (ret)
return ret;
return 0;
}
-static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port)
+static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
+ if (sset != ETH_SS_STATS && sset != ETH_SS_PHY_STATS)
+ return 0;
+
return __DSA_LOOP_CNT_MAX;
}
-static void dsa_loop_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+static void dsa_loop_get_strings(struct dsa_switch *ds, int port,
+ u32 stringset, uint8_t *data)
{
struct dsa_loop_priv *ps = ds->priv;
unsigned int i;
+ if (stringset != ETH_SS_STATS && stringset != ETH_SS_PHY_STATS)
+ return;
+
for (i = 0; i < __DSA_LOOP_CNT_MAX; i++)
memcpy(data + i * ETH_GSTRING_LEN,
ps->ports[port].mib[i].name, ETH_GSTRING_LEN);
.get_strings = dsa_loop_get_strings,
.get_ethtool_stats = dsa_loop_get_ethtool_stats,
.get_sset_count = dsa_loop_get_sset_count,
+ .get_ethtool_phy_stats = dsa_loop_get_ethtool_stats,
.phy_read = dsa_loop_phy_read,
.phy_write = dsa_loop_phy_write,
.port_bridge_join = dsa_loop_port_bridge_join,
{ .offset = LAN9303_MAC_TX_LATECOL_0, .name = "TxLateCol", },
};
-static void lan9303_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+static void lan9303_get_strings(struct dsa_switch *ds, int port,
+ u32 stringset, uint8_t *data)
{
unsigned int u;
+ if (stringset != ETH_SS_STATS)
+ return;
+
for (u = 0; u < ARRAY_SIZE(lan9303_mib); u++) {
strncpy(data + u * ETH_GSTRING_LEN, lan9303_mib[u].name,
ETH_GSTRING_LEN);
}
}
-static int lan9303_get_sset_count(struct dsa_switch *ds, int port)
+static int lan9303_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
+ if (sset != ETH_SS_STATS)
+ return 0;
+
return ARRAY_SIZE(lan9303_mib);
}
ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, true);
}
-static int ksz_sset_count(struct dsa_switch *ds, int port)
+static int ksz_sset_count(struct dsa_switch *ds, int port, int sset)
{
+ if (sset != ETH_SS_STATS)
+ return 0;
+
return TOTAL_SWITCH_COUNTER_NUM;
}
-static void ksz_get_strings(struct dsa_switch *ds, int port, uint8_t *buf)
+static void ksz_get_strings(struct dsa_switch *ds, int port,
+ u32 stringset, uint8_t *buf)
{
int i;
+ if (stringset != ETH_SS_STATS)
+ return;
+
for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) {
memcpy(buf + i * ETH_GSTRING_LEN, mib_names[i].string,
ETH_GSTRING_LEN);
}
static void
-mt7530_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+ uint8_t *data)
{
int i;
+ if (stringset != ETH_SS_STATS)
+ return;
+
for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++)
strncpy(data + i * ETH_GSTRING_LEN, mt7530_mib[i].name,
ETH_GSTRING_LEN);
}
static int
-mt7530_get_sset_count(struct dsa_switch *ds, int port)
+mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
+ if (sset != ETH_SS_STATS)
+ return 0;
+
return ARRAY_SIZE(mt7530_mib);
}
#include <linux/of_device.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
+#include <linux/platform_data/mv88e6xxx.h>
#include <linux/netdevice.h>
#include <linux/gpio/consumer.h>
#include <linux/phy.h>
+#include <linux/phylink.h>
#include <net/dsa.h>
#include "chip.h"
dev_err(ds->dev, "p%d: failed to configure MAC\n", port);
}
+static void mv88e6xxx_validate(struct dsa_switch *ds, int port,
+ unsigned long *supported,
+ struct phylink_link_state *state)
+{
+}
+
+static int mv88e6xxx_link_state(struct dsa_switch *ds, int port,
+ struct phylink_link_state *state)
+{
+ struct mv88e6xxx_chip *chip = ds->priv;
+ int err;
+
+ mutex_lock(&chip->reg_lock);
+ err = mv88e6xxx_port_link_state(chip, port, state);
+ mutex_unlock(&chip->reg_lock);
+
+ return err;
+}
+
+static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ struct mv88e6xxx_chip *chip = ds->priv;
+ int speed, duplex, link, err;
+
+ if (mode == MLO_AN_PHY)
+ return;
+
+ if (mode == MLO_AN_FIXED) {
+ link = LINK_FORCED_UP;
+ speed = state->speed;
+ duplex = state->duplex;
+ } else {
+ speed = SPEED_UNFORCED;
+ duplex = DUPLEX_UNFORCED;
+ link = LINK_UNFORCED;
+ }
+
+ mutex_lock(&chip->reg_lock);
+ err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex,
+ state->interface);
+ mutex_unlock(&chip->reg_lock);
+
+ if (err && err != -EOPNOTSUPP)
+ dev_err(ds->dev, "p%d: failed to configure MAC\n", port);
+}
+
+static void mv88e6xxx_mac_link_force(struct dsa_switch *ds, int port, int link)
+{
+ struct mv88e6xxx_chip *chip = ds->priv;
+ int err;
+
+ mutex_lock(&chip->reg_lock);
+ err = chip->info->ops->port_set_link(chip, port, link);
+ mutex_unlock(&chip->reg_lock);
+
+ if (err)
+ dev_err(chip->dev, "p%d: failed to force MAC link\n", port);
+}
+
+static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ phy_interface_t interface)
+{
+ if (mode == MLO_AN_FIXED)
+ mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_DOWN);
+}
+
+static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port,
+ unsigned int mode, phy_interface_t interface,
+ struct phy_device *phydev)
+{
+ if (mode == MLO_AN_FIXED)
+ mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_UP);
+}
+
static int mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port)
{
if (!chip->info->ops->stats_snapshot)
case STATS_TYPE_PORT:
err = mv88e6xxx_port_read(chip, port, s->reg, ®);
if (err)
- return UINT64_MAX;
+ return U64_MAX;
low = reg;
if (s->size == 4) {
err = mv88e6xxx_port_read(chip, port, s->reg + 1, ®);
if (err)
- return UINT64_MAX;
+ return U64_MAX;
high = reg;
}
break;
mv88e6xxx_g1_stats_read(chip, reg + 1, &high);
break;
default:
- return UINT64_MAX;
+ return U64_MAX;
}
value = (((u64)high) << 16) | low;
return value;
}
static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port,
- uint8_t *data)
+ u32 stringset, uint8_t *data)
{
struct mv88e6xxx_chip *chip = ds->priv;
int count = 0;
+ if (stringset != ETH_SS_STATS)
+ return;
+
mutex_lock(&chip->reg_lock);
if (chip->info->ops->stats_get_strings)
STATS_TYPE_BANK1);
}
-static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port)
+static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
struct mv88e6xxx_chip *chip = ds->priv;
int serdes_count = 0;
int count = 0;
+ if (sset != ETH_SS_STATS)
+ return 0;
+
mutex_lock(&chip->reg_lock);
if (chip->info->ops->stats_get_sset_count)
count = chip->info->ops->stats_get_sset_count(chip);
}
-static int mv88e6xxx_stats_set_histogram(struct mv88e6xxx_chip *chip)
-{
- if (chip->info->ops->stats_set_histogram)
- return chip->info->ops->stats_set_histogram(chip);
-
- return 0;
-}
-
static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port)
{
return 32 * sizeof(u16);
dev_err(ds->dev, "p%d: failed to update state\n", port);
}
+static int mv88e6xxx_pri_setup(struct mv88e6xxx_chip *chip)
+{
+ int err;
+
+ if (chip->info->ops->ieee_pri_map) {
+ err = chip->info->ops->ieee_pri_map(chip);
+ if (err)
+ return err;
+ }
+
+ if (chip->info->ops->ip_pri_map) {
+ err = chip->info->ops->ip_pri_map(chip);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int mv88e6xxx_devmap_setup(struct mv88e6xxx_chip *chip)
+{
+ int target, port;
+ int err;
+
+ if (!chip->info->global2_addr)
+ return 0;
+
+ /* Initialize the routing port to the 32 possible target devices */
+ for (target = 0; target < 32; target++) {
+ port = 0x1f;
+ if (target < DSA_MAX_SWITCHES)
+ if (chip->ds->rtable[target] != DSA_RTABLE_NONE)
+ port = chip->ds->rtable[target];
+
+ err = mv88e6xxx_g2_device_mapping_write(chip, target, port);
+ if (err)
+ return err;
+ }
+
+ if (chip->info->ops->set_cascade_port) {
+ port = MV88E6XXX_CASCADE_PORT_MULTIPLE;
+ err = chip->info->ops->set_cascade_port(chip, port);
+ if (err)
+ return err;
+ }
+
+ err = mv88e6xxx_g1_set_device_number(chip, chip->ds->index);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int mv88e6xxx_trunk_setup(struct mv88e6xxx_chip *chip)
+{
+ /* Clear all trunk masks and mapping */
+ if (chip->info->global2_addr)
+ return mv88e6xxx_g2_trunk_clear(chip);
+
+ return 0;
+}
+
+static int mv88e6xxx_rmu_setup(struct mv88e6xxx_chip *chip)
+{
+ if (chip->info->ops->rmu_disable)
+ return chip->info->ops->rmu_disable(chip);
+
+ return 0;
+}
+
static int mv88e6xxx_pot_setup(struct mv88e6xxx_chip *chip)
{
if (chip->info->ops->pot_clear)
return err;
}
-static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip)
+static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
{
- struct dsa_switch *ds = chip->ds;
int err;
- /* Disable remote management, and set the switch's DSA device number. */
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL2,
- MV88E6XXX_G1_CTL2_MULTIPLE_CASCADE |
- (ds->index & 0x1f));
- if (err)
- return err;
-
- /* Configure the IP ToS mapping registers. */
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_0, 0x0000);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_1, 0x0000);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_2, 0x5555);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_3, 0x5555);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_4, 0xaaaa);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_5, 0xaaaa);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_6, 0xffff);
- if (err)
- return err;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_7, 0xffff);
- if (err)
- return err;
-
- /* Configure the IEEE 802.1p priority mapping register. */
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IEEE_PRI, 0xfa41);
- if (err)
- return err;
-
/* Initialize the statistics unit */
- err = mv88e6xxx_stats_set_histogram(chip);
- if (err)
- return err;
+ if (chip->info->ops->stats_set_histogram) {
+ err = chip->info->ops->stats_set_histogram(chip);
+ if (err)
+ return err;
+ }
return mv88e6xxx_g1_stats_clear(chip);
}
goto unlock;
}
- /* Setup Switch Global 1 Registers */
- err = mv88e6xxx_g1_setup(chip);
- if (err)
- goto unlock;
-
- /* Setup Switch Global 2 Registers */
- if (chip->info->global2_addr) {
- err = mv88e6xxx_g2_setup(chip);
- if (err)
- goto unlock;
- }
-
err = mv88e6xxx_irl_setup(chip);
if (err)
goto unlock;
if (err)
goto unlock;
+ err = mv88e6xxx_rmu_setup(chip);
+ if (err)
+ goto unlock;
+
err = mv88e6xxx_rsvd2cpu_setup(chip);
if (err)
goto unlock;
+ err = mv88e6xxx_trunk_setup(chip);
+ if (err)
+ goto unlock;
+
+ err = mv88e6xxx_devmap_setup(chip);
+ if (err)
+ goto unlock;
+
+ err = mv88e6xxx_pri_setup(chip);
+ if (err)
+ goto unlock;
+
/* Setup PTP Hardware Clock and timestamping */
if (chip->info->ptp_support) {
err = mv88e6xxx_ptp_setup(chip);
goto unlock;
}
+ err = mv88e6xxx_stats_setup(chip);
+ if (err)
+ goto unlock;
+
unlock:
mutex_unlock(&chip->reg_lock);
return err;
}
- if (np)
- err = of_mdiobus_register(bus, np);
- else
- err = mdiobus_register(bus);
+ err = of_mdiobus_register(bus, np);
if (err) {
dev_err(chip->dev, "Cannot register MDIO bus (%d)\n", err);
mv88e6xxx_g2_irq_mdio_free(chip, bus);
static const struct mv88e6xxx_ops mv88e6085_ops = {
/* MV88E6XXX_FAMILY_6097 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6185_phy_ppu_read,
.ppu_enable = mv88e6185_g1_ppu_enable,
.ppu_disable = mv88e6185_g1_ppu_disable,
.reset = mv88e6185_g1_reset,
+ .rmu_disable = mv88e6085_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+ .serdes_power = mv88e6341_serdes_power,
};
static const struct mv88e6xxx_ops mv88e6095_ops = {
/* MV88E6XXX_FAMILY_6095 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
static const struct mv88e6xxx_ops mv88e6097_ops = {
/* MV88E6XXX_FAMILY_6097 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6085_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
};
static const struct mv88e6xxx_ops mv88e6123_ops = {
/* MV88E6XXX_FAMILY_6165 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
static const struct mv88e6xxx_ops mv88e6131_ops = {
/* MV88E6XXX_FAMILY_6185 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.watchdog_ops = &mv88e6097_watchdog_ops,
.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
.ppu_enable = mv88e6185_g1_ppu_enable,
+ .set_cascade_port = mv88e6185_g1_set_cascade_port,
.ppu_disable = mv88e6185_g1_ppu_disable,
.reset = mv88e6185_g1_reset,
.vtu_getnext = mv88e6185_g1_vtu_getnext,
static const struct mv88e6xxx_ops mv88e6141_ops = {
/* MV88E6XXX_FAMILY_6341 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom8,
.set_eeprom = mv88e6xxx_g2_set_eeprom8,
static const struct mv88e6xxx_ops mv88e6161_ops = {
/* MV88E6XXX_FAMILY_6165 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
static const struct mv88e6xxx_ops mv88e6165_ops = {
/* MV88E6XXX_FAMILY_6165 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6165_phy_read,
static const struct mv88e6xxx_ops mv88e6171_ops = {
/* MV88E6XXX_FAMILY_6351 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
static const struct mv88e6xxx_ops mv88e6172_ops = {
/* MV88E6XXX_FAMILY_6352 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6352_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6352_serdes_power,
static const struct mv88e6xxx_ops mv88e6175_ops = {
/* MV88E6XXX_FAMILY_6351 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.reset = mv88e6352_g1_reset,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+ .serdes_power = mv88e6341_serdes_power,
};
static const struct mv88e6xxx_ops mv88e6176_ops = {
/* MV88E6XXX_FAMILY_6352 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6352_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6352_serdes_power,
static const struct mv88e6xxx_ops mv88e6185_ops = {
/* MV88E6XXX_FAMILY_6185 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6185_phy_ppu_read,
.phy_write = mv88e6185_phy_ppu_write,
.set_egress_port = mv88e6095_g1_set_egress_port,
.watchdog_ops = &mv88e6097_watchdog_ops,
.mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu,
+ .set_cascade_port = mv88e6185_g1_set_cascade_port,
.ppu_enable = mv88e6185_g1_ppu_enable,
.ppu_disable = mv88e6185_g1_ppu_disable,
.reset = mv88e6185_g1_reset,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
static const struct mv88e6xxx_ops mv88e6240_ops = {
/* MV88E6XXX_FAMILY_6352 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6352_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6352_serdes_power,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
static const struct mv88e6xxx_ops mv88e6320_ops = {
/* MV88E6XXX_FAMILY_6320 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
static const struct mv88e6xxx_ops mv88e6321_ops = {
/* MV88E6XXX_FAMILY_6320 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
static const struct mv88e6xxx_ops mv88e6341_ops = {
/* MV88E6XXX_FAMILY_6341 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom8,
.set_eeprom = mv88e6xxx_g2_set_eeprom8,
static const struct mv88e6xxx_ops mv88e6350_ops = {
/* MV88E6XXX_FAMILY_6351 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
static const struct mv88e6xxx_ops mv88e6351_ops = {
/* MV88E6XXX_FAMILY_6351 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
static const struct mv88e6xxx_ops mv88e6352_ops = {
/* MV88E6XXX_FAMILY_6352 */
+ .ieee_pri_map = mv88e6085_g1_ieee_pri_map,
+ .ip_pri_map = mv88e6085_g1_ip_pri_map,
.irl_init_all = mv88e6352_g2_irl_init_all,
.get_eeprom = mv88e6xxx_g2_get_eeprom16,
.set_eeprom = mv88e6xxx_g2_set_eeprom16,
.mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6352_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6352_serdes_power,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
.vtu_getnext = mv88e6390_g1_vtu_getnext,
.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 8,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 11,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x10,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.tag_protocol = DSA_TAG_PROTO_DSA,
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_internal_phys = 11,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 11,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x10,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
.get_tag_protocol = mv88e6xxx_get_tag_protocol,
.setup = mv88e6xxx_setup,
.adjust_link = mv88e6xxx_adjust_link,
+ .phylink_validate = mv88e6xxx_validate,
+ .phylink_mac_link_state = mv88e6xxx_link_state,
+ .phylink_mac_config = mv88e6xxx_mac_config,
+ .phylink_mac_link_down = mv88e6xxx_mac_link_down,
+ .phylink_mac_link_up = mv88e6xxx_mac_link_up,
.get_strings = mv88e6xxx_get_strings,
.get_ethtool_stats = mv88e6xxx_get_ethtool_stats,
.get_sset_count = mv88e6xxx_get_sset_count,
return -ENOMEM;
ds->priv = chip;
+ ds->dev = dev;
ds->ops = &mv88e6xxx_switch_ops;
ds->ageing_time_min = chip->info->age_time_coeff;
ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX;
dsa_unregister_switch(chip->ds);
}
+static const void *pdata_device_get_match_data(struct device *dev)
+{
+ const struct of_device_id *matches = dev->driver->of_match_table;
+ const struct dsa_mv88e6xxx_pdata *pdata = dev->platform_data;
+
+ for (; matches->name[0] || matches->type[0] || matches->compatible[0];
+ matches++) {
+ if (!strcmp(pdata->compatible, matches->compatible))
+ return matches->data;
+ }
+ return NULL;
+}
+
static int mv88e6xxx_probe(struct mdio_device *mdiodev)
{
+ struct dsa_mv88e6xxx_pdata *pdata = mdiodev->dev.platform_data;
+ const struct mv88e6xxx_info *compat_info = NULL;
struct device *dev = &mdiodev->dev;
struct device_node *np = dev->of_node;
- const struct mv88e6xxx_info *compat_info;
struct mv88e6xxx_chip *chip;
- u32 eeprom_len;
+ int port;
int err;
- compat_info = of_device_get_match_data(dev);
+ if (np)
+ compat_info = of_device_get_match_data(dev);
+
+ if (pdata) {
+ compat_info = pdata_device_get_match_data(dev);
+
+ if (!pdata->netdev)
+ return -EINVAL;
+
+ for (port = 0; port < DSA_MAX_PORTS; port++) {
+ if (!(pdata->enabled_ports & (1 << port)))
+ continue;
+ if (strcmp(pdata->cd.port_names[port], "cpu"))
+ continue;
+ pdata->cd.netdev[port] = &pdata->netdev->dev;
+ break;
+ }
+ }
+
if (!compat_info)
return -EINVAL;
chip = mv88e6xxx_alloc_chip(dev);
- if (!chip)
- return -ENOMEM;
+ if (!chip) {
+ err = -ENOMEM;
+ goto out;
+ }
chip->info = compat_info;
err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr);
if (err)
- return err;
+ goto out;
chip->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
- if (IS_ERR(chip->reset))
- return PTR_ERR(chip->reset);
+ if (IS_ERR(chip->reset)) {
+ err = PTR_ERR(chip->reset);
+ goto out;
+ }
err = mv88e6xxx_detect(chip);
if (err)
- return err;
+ goto out;
mv88e6xxx_phy_init(chip);
- if (chip->info->ops->get_eeprom &&
- !of_property_read_u32(np, "eeprom-length", &eeprom_len))
- chip->eeprom_len = eeprom_len;
+ if (chip->info->ops->get_eeprom) {
+ if (np)
+ of_property_read_u32(np, "eeprom-length",
+ &chip->eeprom_len);
+ else
+ chip->eeprom_len = pdata->eeprom_len;
+ }
mutex_lock(&chip->reg_lock);
err = mv88e6xxx_switch_reset(chip);
mv88e6xxx_irq_poll_free(chip);
mutex_unlock(&chip->reg_lock);
out:
+ if (pdata)
+ dev_put(pdata->netdev);
+
return err;
}
#include <linux/timecounter.h>
#include <net/dsa.h>
-#ifndef UINT64_MAX
-#define UINT64_MAX (u64)(~((u64)0))
-#endif
-
#define SMI_CMD 0x00
#define SMI_CMD_BUSY BIT(15)
#define SMI_CMD_CLAUSE_22 BIT(12)
unsigned int num_gpio;
unsigned int max_vid;
unsigned int port_base_addr;
+ unsigned int phy_base_addr;
unsigned int global1_addr;
unsigned int global2_addr;
unsigned int age_time_coeff;
struct gpio_desc *reset;
/* set to size of eeprom if supported by the switch */
- int eeprom_len;
+ u32 eeprom_len;
/* List of mdio busses */
struct list_head mdios;
};
struct mv88e6xxx_ops {
+ int (*ieee_pri_map)(struct mv88e6xxx_chip *chip);
+ int (*ip_pri_map)(struct mv88e6xxx_chip *chip);
+
/* Ingress Rate Limit unit (IRL) operations */
int (*irl_init_all)(struct mv88e6xxx_chip *chip, int port);
uint64_t *data);
int (*set_cpu_port)(struct mv88e6xxx_chip *chip, int port);
int (*set_egress_port)(struct mv88e6xxx_chip *chip, int port);
+
+#define MV88E6XXX_CASCADE_PORT_NONE 0xe
+#define MV88E6XXX_CASCADE_PORT_MULTIPLE 0xf
+
+ int (*set_cascade_port)(struct mv88e6xxx_chip *chip, int port);
+
const struct mv88e6xxx_irq_ops *watchdog_ops;
int (*mgmt_rsvd2cpu)(struct mv88e6xxx_chip *chip);
/* Interface to the AVB/PTP registers */
const struct mv88e6xxx_avb_ops *avb_ops;
+
+ /* Remote Management Unit operations */
+ int (*rmu_disable)(struct mv88e6xxx_chip *chip);
};
struct mv88e6xxx_irq_ops {
return mv88e6185_g1_wait_ppu_disabled(chip);
}
+/* Offset 0x10: IP-PRI Mapping Register 0
+ * Offset 0x11: IP-PRI Mapping Register 1
+ * Offset 0x12: IP-PRI Mapping Register 2
+ * Offset 0x13: IP-PRI Mapping Register 3
+ * Offset 0x14: IP-PRI Mapping Register 4
+ * Offset 0x15: IP-PRI Mapping Register 5
+ * Offset 0x16: IP-PRI Mapping Register 6
+ * Offset 0x17: IP-PRI Mapping Register 7
+ */
+
+int mv88e6085_g1_ip_pri_map(struct mv88e6xxx_chip *chip)
+{
+ int err;
+
+ /* Reset the IP TOS/DiffServ/Traffic priorities to defaults */
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_0, 0x0000);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_1, 0x0000);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_2, 0x5555);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_3, 0x5555);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_4, 0xaaaa);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_5, 0xaaaa);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_6, 0xffff);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_7, 0xffff);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+/* Offset 0x18: IEEE-PRI Register */
+
+int mv88e6085_g1_ieee_pri_map(struct mv88e6xxx_chip *chip)
+{
+ /* Reset the IEEE Tag priorities to defaults */
+ return mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IEEE_PRI, 0xfa41);
+}
+
/* Offset 0x1a: Monitor Control */
/* Offset 0x1a: Monitor & MGMT Control on some devices */
/* Offset 0x1c: Global Control 2 */
-int mv88e6390_g1_stats_set_histogram(struct mv88e6xxx_chip *chip)
+static int mv88e6xxx_g1_ctl2_mask(struct mv88e6xxx_chip *chip, u16 mask,
+ u16 val)
{
- u16 val;
+ u16 reg;
int err;
- err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL2, &val);
+ err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL2, ®);
if (err)
return err;
- val |= MV88E6XXX_G1_CTL2_HIST_RX_TX;
+ reg &= ~mask;
+ reg |= val & mask;
- err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL2, val);
+ return mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL2, reg);
+}
- return err;
+int mv88e6185_g1_set_cascade_port(struct mv88e6xxx_chip *chip, int port)
+{
+ const u16 mask = MV88E6185_G1_CTL2_CASCADE_PORT_MASK;
+
+ return mv88e6xxx_g1_ctl2_mask(chip, mask, port << __bf_shf(mask));
+}
+
+int mv88e6085_g1_rmu_disable(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g1_ctl2_mask(chip, MV88E6085_G1_CTL2_P10RM |
+ MV88E6085_G1_CTL2_RM_ENABLE, 0);
+}
+
+int mv88e6352_g1_rmu_disable(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g1_ctl2_mask(chip, MV88E6352_G1_CTL2_RMU_MODE_MASK,
+ MV88E6352_G1_CTL2_RMU_MODE_DISABLED);
+}
+
+int mv88e6390_g1_rmu_disable(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g1_ctl2_mask(chip, MV88E6390_G1_CTL2_RMU_MODE_MASK,
+ MV88E6390_G1_CTL2_RMU_MODE_DISABLED);
+}
+
+int mv88e6390_g1_stats_set_histogram(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g1_ctl2_mask(chip, MV88E6390_G1_CTL2_HIST_MODE_MASK,
+ MV88E6390_G1_CTL2_HIST_MODE_RX |
+ MV88E6390_G1_CTL2_HIST_MODE_TX);
+}
+
+int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index)
+{
+ return mv88e6xxx_g1_ctl2_mask(chip,
+ MV88E6XXX_G1_CTL2_DEVICE_NUMBER_MASK,
+ index);
}
/* Offset 0x1d: Statistics Operation 2 */
/* Offset 0x1C: Global Control 2 */
#define MV88E6XXX_G1_CTL2 0x1c
-#define MV88E6XXX_G1_CTL2_NO_CASCADE 0xe000
-#define MV88E6XXX_G1_CTL2_MULTIPLE_CASCADE 0xf000
-#define MV88E6XXX_G1_CTL2_HIST_RX 0x0040
-#define MV88E6XXX_G1_CTL2_HIST_TX 0x0080
-#define MV88E6XXX_G1_CTL2_HIST_RX_TX 0x00c0
+#define MV88E6185_G1_CTL2_CASCADE_PORT_MASK 0xf000
+#define MV88E6185_G1_CTL2_CASCADE_PORT_NONE 0xe000
+#define MV88E6185_G1_CTL2_CASCADE_PORT_MULTI 0xf000
+#define MV88E6352_G1_CTL2_HEADER_TYPE_MASK 0xc000
+#define MV88E6352_G1_CTL2_HEADER_TYPE_ORIG 0x0000
+#define MV88E6352_G1_CTL2_HEADER_TYPE_MGMT 0x4000
+#define MV88E6390_G1_CTL2_HEADER_TYPE_LAG 0x8000
+#define MV88E6352_G1_CTL2_RMU_MODE_MASK 0x3000
+#define MV88E6352_G1_CTL2_RMU_MODE_DISABLED 0x0000
+#define MV88E6352_G1_CTL2_RMU_MODE_PORT_4 0x1000
+#define MV88E6352_G1_CTL2_RMU_MODE_PORT_5 0x2000
+#define MV88E6352_G1_CTL2_RMU_MODE_PORT_6 0x3000
+#define MV88E6085_G1_CTL2_DA_CHECK 0x4000
+#define MV88E6085_G1_CTL2_P10RM 0x2000
+#define MV88E6085_G1_CTL2_RM_ENABLE 0x1000
+#define MV88E6352_G1_CTL2_DA_CHECK 0x0800
+#define MV88E6390_G1_CTL2_RMU_MODE_MASK 0x0700
+#define MV88E6390_G1_CTL2_RMU_MODE_PORT_0 0x0000
+#define MV88E6390_G1_CTL2_RMU_MODE_PORT_1 0x0100
+#define MV88E6390_G1_CTL2_RMU_MODE_PORT_9 0x0200
+#define MV88E6390_G1_CTL2_RMU_MODE_PORT_10 0x0300
+#define MV88E6390_G1_CTL2_RMU_MODE_ALL_DSA 0x0600
+#define MV88E6390_G1_CTL2_RMU_MODE_DISABLED 0x0700
+#define MV88E6390_G1_CTL2_HIST_MODE_MASK 0x00c0
+#define MV88E6390_G1_CTL2_HIST_MODE_RX 0x0040
+#define MV88E6390_G1_CTL2_HIST_MODE_TX 0x0080
+#define MV88E6352_G1_CTL2_CTR_MODE_MASK 0x0060
+#define MV88E6390_G1_CTL2_CTR_MODE 0x0020
+#define MV88E6XXX_G1_CTL2_DEVICE_NUMBER_MASK 0x001f
/* Offset 0x1D: Stats Operation Register */
#define MV88E6XXX_G1_STATS_OP 0x1d
int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip);
+int mv88e6085_g1_ip_pri_map(struct mv88e6xxx_chip *chip);
+int mv88e6085_g1_ieee_pri_map(struct mv88e6xxx_chip *chip);
+
+int mv88e6185_g1_set_cascade_port(struct mv88e6xxx_chip *chip, int port);
+
+int mv88e6085_g1_rmu_disable(struct mv88e6xxx_chip *chip);
+int mv88e6352_g1_rmu_disable(struct mv88e6xxx_chip *chip);
+int mv88e6390_g1_rmu_disable(struct mv88e6xxx_chip *chip);
+
+int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index);
+
int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all);
int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
unsigned int msecs);
/* Offset 0x06: Device Mapping Table register */
-static int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip,
- int target, int port)
+int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target,
+ int port)
{
- u16 val = (target << 8) | (port & 0xf);
+ u16 val = (target << 8) | (port & 0x1f);
+ /* Modern chips use 5 bits to define a device mapping port,
+ * but bit 4 is reserved on older chips, so it is safe to use.
+ */
return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_DEVICE_MAPPING, val);
}
-static int mv88e6xxx_g2_set_device_mapping(struct mv88e6xxx_chip *chip)
-{
- int target, port;
- int err;
-
- /* Initialize the routing port to the 32 possible target devices */
- for (target = 0; target < 32; ++target) {
- port = 0xf;
-
- if (target < DSA_MAX_SWITCHES) {
- port = chip->ds->rtable[target];
- if (port == DSA_RTABLE_NONE)
- port = 0xf;
- }
-
- err = mv88e6xxx_g2_device_mapping_write(chip, target, port);
- if (err)
- break;
- }
-
- return err;
-}
-
/* Offset 0x07: Trunk Mask Table register */
static int mv88e6xxx_g2_trunk_mask_write(struct mv88e6xxx_chip *chip, int num,
return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MAPPING, val);
}
-static int mv88e6xxx_g2_clear_trunk(struct mv88e6xxx_chip *chip)
+int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip)
{
const u16 port_mask = BIT(mv88e6xxx_num_ports(chip)) - 1;
int i, err;
{
int err, irq, virq;
- if (!chip->dev->of_node)
- return -EINVAL;
-
chip->g2_irq.domain = irq_domain_add_simple(
chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
if (!chip->g2_irq.domain)
err = irq;
goto out;
}
- bus->irq[chip->info->port_base_addr + phy] = irq;
+ bus->irq[chip->info->phy_base_addr + phy] = irq;
}
return 0;
out:
for (phy = 0; phy < chip->info->num_internal_phys; phy++)
irq_dispose_mapping(bus->irq[phy]);
}
-
-int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
-{
- u16 reg;
- int err;
-
- /* Ignore removed tag data on doubly tagged packets, disable
- * flow control messages, force flow control priority to the
- * highest, and send all special multicast frames to the CPU
- * port at the highest priority.
- */
- reg = MV88E6XXX_G2_SWITCH_MGMT_FORCE_FLOW_CTL_PRI | (0x7 << 4);
- err = mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SWITCH_MGMT, reg);
- if (err)
- return err;
-
- /* Program the DSA routing table. */
- err = mv88e6xxx_g2_set_device_mapping(chip);
- if (err)
- return err;
-
- /* Clear all trunk masks and mapping. */
- err = mv88e6xxx_g2_clear_trunk(chip);
- if (err)
- return err;
-
- return 0;
-}
#define MV88E6XXX_G2_DEVICE_MAPPING 0x06
#define MV88E6XXX_G2_DEVICE_MAPPING_UPDATE 0x8000
#define MV88E6XXX_G2_DEVICE_MAPPING_DEV_MASK 0x1f00
-#define MV88E6XXX_G2_DEVICE_MAPPING_PORT_MASK 0x000f
+#define MV88E6352_G2_DEVICE_MAPPING_PORT_MASK 0x000f
+#define MV88E6390_G2_DEVICE_MAPPING_PORT_MASK 0x001f
/* Offset 0x07: Trunk Mask Table Register */
#define MV88E6XXX_G2_TRUNK_MASK 0x07
int src_port, u16 data);
int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip);
-int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip);
int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip);
void mv88e6xxx_g2_irq_free(struct mv88e6xxx_chip *chip);
int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip);
+int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip);
+
+int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target,
+ int port);
+
extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops;
extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops;
return -EOPNOTSUPP;
}
-static inline int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
-{
- return -EOPNOTSUPP;
-}
-
static inline int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
{
return -EOPNOTSUPP;
return -EOPNOTSUPP;
}
+static inline int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip,
+ int target, int port)
+{
+ return -EOPNOTSUPP;
+}
+
#endif /* CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */
#endif /* _MV88E6XXX_GLOBAL2_H */
#include <linux/bitfield.h>
#include <linux/if_bridge.h>
#include <linux/phy.h>
+#include <linux/phylink.h>
#include "chip.h"
#include "port.h"
return 0;
}
+int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_link_state *state)
+{
+ int err;
+ u16 reg;
+
+ err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®);
+ if (err)
+ return err;
+
+ switch (reg & MV88E6XXX_PORT_STS_SPEED_MASK) {
+ case MV88E6XXX_PORT_STS_SPEED_10:
+ state->speed = SPEED_10;
+ break;
+ case MV88E6XXX_PORT_STS_SPEED_100:
+ state->speed = SPEED_100;
+ break;
+ case MV88E6XXX_PORT_STS_SPEED_1000:
+ state->speed = SPEED_1000;
+ break;
+ case MV88E6XXX_PORT_STS_SPEED_10000:
+ if ((reg &MV88E6XXX_PORT_STS_CMODE_MASK) ==
+ MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+ state->speed = SPEED_2500;
+ else
+ state->speed = SPEED_10000;
+ break;
+ }
+
+ state->duplex = reg & MV88E6XXX_PORT_STS_DUPLEX ?
+ DUPLEX_FULL : DUPLEX_HALF;
+ state->link = !!(reg & MV88E6XXX_PORT_STS_LINK);
+ state->an_enabled = 1;
+ state->an_complete = state->link;
+
+ return 0;
+}
+
/* Offset 0x02: Jamming Control
*
* Do not limit the period of time that this port can be paused for by
#define MV88E6XXX_PORT_STS_SPEED_10 0x0000
#define MV88E6XXX_PORT_STS_SPEED_100 0x0100
#define MV88E6XXX_PORT_STS_SPEED_1000 0x0200
+#define MV88E6XXX_PORT_STS_SPEED_10000 0x0300
#define MV88E6352_PORT_STS_EEE 0x0040
#define MV88E6165_PORT_STS_AM_DIS 0x0040
#define MV88E6185_PORT_STS_MGMII 0x0040
int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
phy_interface_t mode);
int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
+int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_link_state *state);
int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
int upstream_port);
return 0;
}
+
+int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+{
+ int err;
+ u8 cmode;
+
+ if (port != 5)
+ return 0;
+
+ err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
+ if (err)
+ return err;
+
+ if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+ cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+ cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+ return mv88e6390_serdes_sgmii(chip, MV88E6341_ADDR_SERDES, on);
+
+ return 0;
+}
#define MV88E6352_ADDR_SERDES 0x0f
#define MV88E6352_SERDES_PAGE_FIBER 0x01
+#define MV88E6341_ADDR_SERDES 0x15
+
#define MV88E6390_PORT9_LANE0 0x09
#define MV88E6390_PORT9_LANE1 0x12
#define MV88E6390_PORT9_LANE2 0x13
#define MV88E6390_SGMII_CONTROL_LOOPBACK BIT(14)
#define MV88E6390_SGMII_CONTROL_PDOWN BIT(11)
+int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
}
static void
-qca8k_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data)
{
int i;
+ if (stringset != ETH_SS_STATS)
+ return;
+
for (i = 0; i < ARRAY_SIZE(ar8327_mib); i++)
strncpy(data + i * ETH_GSTRING_LEN, ar8327_mib[i].name,
ETH_GSTRING_LEN);
}
static int
-qca8k_get_sset_count(struct dsa_switch *ds, int port)
+qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
+ if (sset != ETH_SS_STATS)
+ return 0;
+
return ARRAY_SIZE(ar8327_mib);
}
struct net_device *dev);
static int vortex_rx(struct net_device *dev);
static int boomerang_rx(struct net_device *dev);
-static irqreturn_t vortex_interrupt(int irq, void *dev_id);
-static irqreturn_t boomerang_interrupt(int irq, void *dev_id);
+static irqreturn_t vortex_boomerang_interrupt(int irq, void *dev_id);
+static irqreturn_t _vortex_interrupt(int irq, struct net_device *dev);
+static irqreturn_t _boomerang_interrupt(int irq, struct net_device *dev);
static int vortex_close(struct net_device *dev);
static void dump_tx_ring(struct net_device *dev);
static void update_stats(void __iomem *ioaddr, struct net_device *dev);
#ifdef CONFIG_NET_POLL_CONTROLLER
static void poll_vortex(struct net_device *dev)
{
- struct vortex_private *vp = netdev_priv(dev);
- unsigned long flags;
- local_irq_save(flags);
- (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
- local_irq_restore(flags);
+ vortex_boomerang_interrupt(dev->irq, dev);
}
#endif
vp->mii.reg_num_mask = 0x1f;
/* Makes sure rings are at least 16 byte aligned. */
- vp->rx_ring = pci_alloc_consistent(pdev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
+ vp->rx_ring = dma_alloc_coherent(gendev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- &vp->rx_ring_dma);
+ &vp->rx_ring_dma, GFP_KERNEL);
retval = -ENOMEM;
if (!vp->rx_ring)
goto free_device;
return 0;
free_ring:
- pci_free_consistent(pdev,
- sizeof(struct boom_rx_desc) * RX_RING_SIZE
- + sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- vp->rx_ring,
- vp->rx_ring_dma);
+ dma_free_coherent(&pdev->dev,
+ sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+ vp->rx_ring, vp->rx_ring_dma);
free_device:
free_netdev(dev);
pr_err(PFX "vortex_probe1 fails. Returns %d\n", retval);
dma_addr_t dma;
/* Use the now-standard shared IRQ implementation. */
- if ((retval = request_irq(dev->irq, vp->full_bus_master_rx ?
- boomerang_interrupt : vortex_interrupt, IRQF_SHARED, dev->name, dev))) {
+ if ((retval = request_irq(dev->irq, vortex_boomerang_interrupt, IRQF_SHARED, dev->name, dev))) {
pr_err("%s: Could not reserve IRQ %d\n", dev->name, dev->irq);
goto err;
}
break; /* Bad news! */
skb_reserve(skb, NET_IP_ALIGN); /* Align IP on 16 byte boundaries */
- dma = pci_map_single(VORTEX_PCI(vp), skb->data,
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma))
+ dma = dma_map_single(vp->gendev, skb->data,
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma))
break;
vp->rx_ring[i].addr = cpu_to_le32(dma);
}
pr_err("%s: Interrupt posted but not delivered --"
" IRQ blocked by another device?\n", dev->name);
/* Bad idea here.. but we might as well handle a few events. */
- {
- /*
- * Block interrupts because vortex_interrupt does a bare spin_lock()
- */
- unsigned long flags;
- local_irq_save(flags);
- if (vp->full_bus_master_tx)
- boomerang_interrupt(dev->irq, dev);
- else
- vortex_interrupt(dev->irq, dev);
- local_irq_restore(flags);
- }
+ vortex_boomerang_interrupt(dev->irq, dev);
}
if (vortex_debug > 0)
if (vp->bus_master) {
/* Set the bus-master controller to transfer the packet. */
int len = (skb->len + 3) & ~3;
- vp->tx_skb_dma = pci_map_single(VORTEX_PCI(vp), skb->data, len,
- PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, vp->tx_skb_dma)) {
+ vp->tx_skb_dma = dma_map_single(vp->gendev, skb->data, len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, vp->tx_skb_dma)) {
dev_kfree_skb_any(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded | AddTCPChksum | AddUDPChksum);
if (!skb_shinfo(skb)->nr_frags) {
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len,
- PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data, skb->len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
} else {
int i;
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data,
- skb_headlen(skb), PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- dma_addr = skb_frag_dma_map(&VORTEX_PCI(vp)->dev, frag,
+ dma_addr = skb_frag_dma_map(vp->gendev, frag,
0,
frag->size,
DMA_TO_DEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr)) {
+ if (dma_mapping_error(vp->gendev, dma_addr)) {
for(i = i-1; i >= 0; i--)
- dma_unmap_page(&VORTEX_PCI(vp)->dev,
+ dma_unmap_page(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[i+1].addr),
le32_to_cpu(vp->tx_ring[entry].frag[i+1].length),
DMA_TO_DEVICE);
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
le32_to_cpu(vp->tx_ring[entry].frag[0].length),
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
goto out_dma_err;
}
}
}
#else
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len, PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data, skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].addr = cpu_to_le32(dma_addr);
vp->tx_ring[entry].length = cpu_to_le32(skb->len | LAST_FRAG);
out:
return NETDEV_TX_OK;
out_dma_err:
- dev_err(&VORTEX_PCI(vp)->dev, "Error mapping dma buffer\n");
+ dev_err(vp->gendev, "Error mapping dma buffer\n");
goto out;
}
*/
static irqreturn_t
-vortex_interrupt(int irq, void *dev_id)
+_vortex_interrupt(int irq, struct net_device *dev)
{
- struct net_device *dev = dev_id;
struct vortex_private *vp = netdev_priv(dev);
void __iomem *ioaddr;
int status;
unsigned int bytes_compl = 0, pkts_compl = 0;
ioaddr = vp->ioaddr;
- spin_lock(&vp->lock);
status = ioread16(ioaddr + EL3_STATUS);
if (status & DMADone) {
if (ioread16(ioaddr + Wn7_MasterStatus) & 0x1000) {
iowrite16(0x1000, ioaddr + Wn7_MasterStatus); /* Ack the event. */
- pci_unmap_single(VORTEX_PCI(vp), vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE);
pkts_compl++;
bytes_compl += vp->tx_skb->len;
dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */
pr_debug("%s: exiting interrupt, status %4.4x.\n",
dev->name, status);
handler_exit:
- spin_unlock(&vp->lock);
return IRQ_RETVAL(handled);
}
*/
static irqreturn_t
-boomerang_interrupt(int irq, void *dev_id)
+_boomerang_interrupt(int irq, struct net_device *dev)
{
- struct net_device *dev = dev_id;
struct vortex_private *vp = netdev_priv(dev);
void __iomem *ioaddr;
int status;
ioaddr = vp->ioaddr;
-
- /*
- * It seems dopey to put the spinlock this early, but we could race against vortex_tx_timeout
- * and boomerang_start_xmit
- */
- spin_lock(&vp->lock);
vp->handling_irq = 1;
status = ioread16(ioaddr + EL3_STATUS);
struct sk_buff *skb = vp->tx_skbuff[entry];
#if DO_ZEROCOPY
int i;
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
for (i=1; i<=skb_shinfo(skb)->nr_frags; i++)
- pci_unmap_page(VORTEX_PCI(vp),
+ dma_unmap_page(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[i].addr),
le32_to_cpu(vp->tx_ring[entry].frag[i].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
#else
- pci_unmap_single(VORTEX_PCI(vp),
- le32_to_cpu(vp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev,
+ le32_to_cpu(vp->tx_ring[entry].addr), skb->len, DMA_TO_DEVICE);
#endif
pkts_compl++;
bytes_compl += skb->len;
dev->name, status);
handler_exit:
vp->handling_irq = 0;
- spin_unlock(&vp->lock);
return IRQ_RETVAL(handled);
}
+static irqreturn_t
+vortex_boomerang_interrupt(int irq, void *dev_id)
+{
+ struct net_device *dev = dev_id;
+ struct vortex_private *vp = netdev_priv(dev);
+ unsigned long flags;
+ irqreturn_t ret;
+
+ spin_lock_irqsave(&vp->lock, flags);
+
+ if (vp->full_bus_master_rx)
+ ret = _boomerang_interrupt(dev->irq, dev);
+ else
+ ret = _vortex_interrupt(dev->irq, dev);
+
+ spin_unlock_irqrestore(&vp->lock, flags);
+
+ return ret;
+}
+
static int vortex_rx(struct net_device *dev)
{
struct vortex_private *vp = netdev_priv(dev);
/* 'skb_put()' points to the start of sk_buff data area. */
if (vp->bus_master &&
! (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)) {
- dma_addr_t dma = pci_map_single(VORTEX_PCI(vp), skb_put(skb, pkt_len),
- pkt_len, PCI_DMA_FROMDEVICE);
+ dma_addr_t dma = dma_map_single(vp->gendev, skb_put(skb, pkt_len),
+ pkt_len, DMA_FROM_DEVICE);
iowrite32(dma, ioaddr + Wn7_MasterAddr);
iowrite16((skb->len + 3) & ~3, ioaddr + Wn7_MasterLen);
iowrite16(StartDMAUp, ioaddr + EL3_CMD);
while (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)
;
- pci_unmap_single(VORTEX_PCI(vp), dma, pkt_len, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, dma, pkt_len, DMA_FROM_DEVICE);
} else {
ioread32_rep(ioaddr + RX_FIFO,
skb_put(skb, pkt_len),
if (pkt_len < rx_copybreak &&
(skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) {
skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */
- pci_dma_sync_single_for_cpu(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_cpu(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
/* 'skb_put()' points to the start of sk_buff data area. */
skb_put_data(skb, vp->rx_skbuff[entry]->data,
pkt_len);
- pci_dma_sync_single_for_device(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_device(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
vp->rx_copy++;
} else {
/* Pre-allocate the replacement skb. If it or its
dev->stats.rx_dropped++;
goto clear_complete;
}
- newdma = pci_map_single(VORTEX_PCI(vp), newskb->data,
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, newdma)) {
+ newdma = dma_map_single(vp->gendev, newskb->data,
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
+ if (dma_mapping_error(vp->gendev, newdma)) {
dev->stats.rx_dropped++;
consume_skb(newskb);
goto clear_complete;
vp->rx_skbuff[entry] = newskb;
vp->rx_ring[entry].addr = cpu_to_le32(newdma);
skb_put(skb, pkt_len);
- pci_unmap_single(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
vp->rx_nocopy++;
}
skb->protocol = eth_type_trans(skb, dev);
if (vp->full_bus_master_rx) { /* Free Boomerang bus master Rx buffers. */
for (i = 0; i < RX_RING_SIZE; i++)
if (vp->rx_skbuff[i]) {
- pci_unmap_single( VORTEX_PCI(vp), le32_to_cpu(vp->rx_ring[i].addr),
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, le32_to_cpu(vp->rx_ring[i].addr),
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
dev_kfree_skb(vp->rx_skbuff[i]);
vp->rx_skbuff[i] = NULL;
}
int k;
for (k=0; k<=skb_shinfo(skb)->nr_frags; k++)
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[i].frag[k].addr),
le32_to_cpu(vp->tx_ring[i].frag[k].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
#else
- pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[i].addr), skb->len, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev, le32_to_cpu(vp->tx_ring[i].addr), skb->len, DMA_TO_DEVICE);
#endif
dev_kfree_skb(skb);
vp->tx_skbuff[i] = NULL;
pci_iounmap(pdev, vp->ioaddr);
- pci_free_consistent(pdev,
- sizeof(struct boom_rx_desc) * RX_RING_SIZE
- + sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- vp->rx_ring,
- vp->rx_ring_dma);
+ dma_free_coherent(&pdev->dev,
+ sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+ vp->rx_ring, vp->rx_ring_dma);
pci_release_regions(pdev);
#define NESM_START_PG 0x40 /* First page of TX buffer */
#define NESM_STOP_PG 0x80 /* Last page +1 of RX ring */
-#if defined(CONFIG_ATARI) /* 8-bit mode on Atari, normal on Q40 */
+#if defined(CONFIG_MACH_TX49XX)
+# define DCR_VAL 0x48 /* 8-bit mode */
+#elif defined(CONFIG_ATARI) /* 8-bit mode on Atari, normal on Q40 */
# define DCR_VAL (MACH_IS_ATARI ? 0x48 : 0x49)
#else
# define DCR_VAL 0x49
source "drivers/net/ethernet/arc/Kconfig"
source "drivers/net/ethernet/atheros/Kconfig"
source "drivers/net/ethernet/aurora/Kconfig"
-source "drivers/net/ethernet/cadence/Kconfig"
source "drivers/net/ethernet/broadcom/Kconfig"
source "drivers/net/ethernet/brocade/Kconfig"
+source "drivers/net/ethernet/cadence/Kconfig"
source "drivers/net/ethernet/calxeda/Kconfig"
source "drivers/net/ethernet/cavium/Kconfig"
source "drivers/net/ethernet/chelsio/Kconfig"
source "drivers/net/ethernet/dlink/Kconfig"
source "drivers/net/ethernet/emulex/Kconfig"
source "drivers/net/ethernet/ezchip/Kconfig"
-source "drivers/net/ethernet/neterion/Kconfig"
source "drivers/net/ethernet/faraday/Kconfig"
source "drivers/net/ethernet/freescale/Kconfig"
source "drivers/net/ethernet/fujitsu/Kconfig"
source "drivers/net/ethernet/hisilicon/Kconfig"
source "drivers/net/ethernet/hp/Kconfig"
source "drivers/net/ethernet/huawei/Kconfig"
+source "drivers/net/ethernet/i825xx/Kconfig"
source "drivers/net/ethernet/ibm/Kconfig"
source "drivers/net/ethernet/intel/Kconfig"
-source "drivers/net/ethernet/i825xx/Kconfig"
+source "drivers/net/ethernet/neterion/Kconfig"
source "drivers/net/ethernet/xscale/Kconfig"
config JME
source "drivers/net/ethernet/micrel/Kconfig"
source "drivers/net/ethernet/microchip/Kconfig"
source "drivers/net/ethernet/moxa/Kconfig"
+source "drivers/net/ethernet/mscc/Kconfig"
source "drivers/net/ethernet/myricom/Kconfig"
config FEALNX
source "drivers/net/ethernet/pasemi/Kconfig"
source "drivers/net/ethernet/qlogic/Kconfig"
source "drivers/net/ethernet/qualcomm/Kconfig"
+source "drivers/net/ethernet/rdc/Kconfig"
source "drivers/net/ethernet/realtek/Kconfig"
source "drivers/net/ethernet/renesas/Kconfig"
-source "drivers/net/ethernet/rdc/Kconfig"
source "drivers/net/ethernet/rocker/Kconfig"
source "drivers/net/ethernet/samsung/Kconfig"
source "drivers/net/ethernet/seeq/Kconfig"
-source "drivers/net/ethernet/silan/Kconfig"
-source "drivers/net/ethernet/sis/Kconfig"
source "drivers/net/ethernet/sfc/Kconfig"
source "drivers/net/ethernet/sgi/Kconfig"
+source "drivers/net/ethernet/silan/Kconfig"
+source "drivers/net/ethernet/sis/Kconfig"
source "drivers/net/ethernet/smsc/Kconfig"
source "drivers/net/ethernet/socionext/Kconfig"
source "drivers/net/ethernet/stmicro/Kconfig"
source "drivers/net/ethernet/sun/Kconfig"
+source "drivers/net/ethernet/synopsys/Kconfig"
source "drivers/net/ethernet/tehuti/Kconfig"
source "drivers/net/ethernet/ti/Kconfig"
source "drivers/net/ethernet/toshiba/Kconfig"
source "drivers/net/ethernet/wiznet/Kconfig"
source "drivers/net/ethernet/xilinx/Kconfig"
source "drivers/net/ethernet/xircom/Kconfig"
-source "drivers/net/ethernet/synopsys/Kconfig"
endif # ETHERNET
obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/
obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/
obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/
+obj-$(CONFIG_NET_VENDOR_MICROSEMI) += mscc/
obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/
obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
obj-$(CONFIG_FEALNX) += fealnx.o
amd8111e_set_coalesce(dev,TX_INTR_COAL);
coal_conf->tx_coal_type = MEDIUM_COALESCE;
}
-
- }
- else if(tx_pkt_size >= 1024){
- if (tx_pkt_size >= 1024){
- if(coal_conf->tx_coal_type != HIGH_COALESCE){
- coal_conf->tx_timeout = 4;
- coal_conf->tx_event_count = 8;
- amd8111e_set_coalesce(dev,TX_INTR_COAL);
- coal_conf->tx_coal_type = HIGH_COALESCE;
- }
+ } else if (tx_pkt_size >= 1024) {
+ if (coal_conf->tx_coal_type != HIGH_COALESCE) {
+ coal_conf->tx_timeout = 4;
+ coal_conf->tx_event_count = 8;
+ amd8111e_set_coalesce(dev, TX_INTR_COAL);
+ coal_conf->tx_coal_type = HIGH_COALESCE;
}
}
}
#define MDIO_VEND2_AN_STAT 0x8002
#endif
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100
+#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON 0x01
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
"debugfs_create_file failed\n");
}
+ if (pdata->vdata->an_cdr_workaround) {
+ pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_workaround);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+
+ pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_track_early);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+ }
+
kfree(buf);
}
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
+ pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
ret = pdata->phy_if.phy_init(pdata);
if (ret)
return ret;
xgbe_an73_set(pdata, false, false);
xgbe_an73_disable_interrupts(pdata);
+ pdata->an_start = 0;
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
static void xgbe_an_restart(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_pre)
+ pdata->phy_if.phy_impl.an_pre(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
static void xgbe_an_disable(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- if (pdata->phy_if.phy_impl.kr_training_post)
- pdata->phy_if.phy_impl.kr_training_post(pdata);
-
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
+
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
}
return XGBE_AN_PAGE_RECEIVED;
return XGBE_AN_NO_LINK;
}
- xgbe_an73_disable(pdata);
+ xgbe_an_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_an73_restart(pdata);
+ xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
pdata->an_result = pdata->an_state;
pdata->an_state = XGBE_AN_READY;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct xgbe_version_data xgbe_v2b = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
/* Rate-change complete wait/retry count */
#define XGBE_RATECHANGE_COUNT 500
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT 10000
+#define XGBE_CDR_DELAY_INC 10000
+#define XGBE_CDR_DELAY_MAX 100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY 10
+
enum xgbe_port_mode {
XGBE_PORT_MODE_RSVD = 0,
XGBE_PORT_MODE_BACKPLANE,
#define XGBE_SFP_BASE_VENDOR_SN 4
#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+#define XGBE_SFP_EXTD_OPT1 1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3)
+
#define XGBE_SFP_EXTD_DIAG 28
#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
unsigned int sfp_gpio_address;
unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_inputs;
unsigned int sfp_gpio_rx_los;
unsigned int sfp_gpio_tx_fault;
unsigned int sfp_gpio_mod_absent;
unsigned int redrv_addr;
unsigned int redrv_lane;
unsigned int redrv_model;
+
+ /* KR AN support */
+ unsigned int phy_cdr_notrack;
+ unsigned int phy_cdr_delay;
};
/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
phy_data->sfp_phy_avail = 1;
}
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+ return true;
+
+ return false;
+}
+
static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
return;
+ /* Update transceiver signals (eeprom extd/options) */
+ phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+ phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
if (xgbe_phy_sfp_parse_quirks(pdata))
return;
static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
- unsigned int gpio_input;
u8 gpio_reg, gpio_ports[2];
int ret;
return;
}
- gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
- if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
- /* No GPIO, just assume the module is present for now */
- phy_data->sfp_mod_absent = 0;
- } else {
- if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
- phy_data->sfp_mod_absent = 0;
- }
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
- (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
- phy_data->sfp_rx_los = 1;
+ phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
- (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
- phy_data->sfp_tx_fault = 1;
+ phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
}
static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
return 1;
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++) {
+ if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
return true;
}
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (!phy_data->phy_cdr_notrack)
+ return;
+
+ usleep_range(phy_data->phy_cdr_delay,
+ phy_data->phy_cdr_delay + 500);
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_ON);
+
+ phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (phy_data->phy_cdr_notrack)
+ return;
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_OFF);
+
+ xgbe_phy_rrc(pdata);
+
+ phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ if (pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_track(pdata);
+
+ switch (pdata->an_result) {
+ case XGBE_AN_READY:
+ case XGBE_AN_COMPLETE:
+ break;
+ default:
+ if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+ phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+ else
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_notrack(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
xgbe_phy_sfp_reset(phy_data);
xgbe_phy_sfp_mod_absent(pdata);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* Power off the PHY */
xgbe_phy_power_off(pdata);
/* Start in highest supported mode */
xgbe_phy_set_mode(pdata, phy_data->start_mode);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* After starting the I2C controller, we can check for an SFP */
switch (phy_data->port_mode) {
case XGBE_PORT_MODE_SFP:
}
}
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
/* Register for driving external PHYs */
mii = devm_mdiobus_alloc(pdata->dev);
if (!mii) {
phy_impl->an_advertising = xgbe_phy_an_advertising;
phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->an_pre = xgbe_phy_an_pre;
+ phy_impl->an_post = xgbe_phy_an_post;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
}
/* This structure represents implementation specific routines for an
* implementation of a PHY. All routines are required unless noted below.
* Optional routines:
+ * an_pre, an_post
* kr_training_pre, kr_training_post
*/
struct xgbe_phy_impl_if {
/* Process results of auto-negotiation */
enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+ /* Pre/Post auto-negotiation support */
+ void (*an_pre)(struct xgbe_prv_data *);
+ void (*an_post)(struct xgbe_prv_data *);
+
/* Pre/Post KR training enablement support */
void (*kr_training_pre)(struct xgbe_prv_data *);
void (*kr_training_post)(struct xgbe_prv_data *);
unsigned int irq_reissue_support;
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
+ unsigned int an_cdr_workaround;
};
struct xgbe_vxlan_data {
unsigned int debugfs_xprop_reg;
unsigned int debugfs_xi2c_reg;
+
+ bool debugfs_an_cdr_workaround;
+ bool debugfs_an_cdr_track_early;
};
/* Function prototypes*/
/*rss rings */
cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
cfg->vecs = min(cfg->vecs, num_online_cpus());
+ cfg->vecs = min(cfg->vecs, self->irqvecs);
/* cfg->vecs should be power of 2 for RSS */
if (cfg->vecs >= 8U)
cfg->vecs = 8U;
self->ndev->hw_features |= aq_hw_caps->hw_features;
self->ndev->features = aq_hw_caps->hw_features;
+ self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+ NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO;
self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
struct pci_dev *pdev;
unsigned int msix_entry_mask;
+ u32 irqvecs;
};
static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
numvecs = min(numvecs, num_online_cpus());
/*enable interrupts */
#if !AQ_CFG_FORCE_LEGACY_INT
- err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs,
- PCI_IRQ_MSIX);
-
- if (err < 0) {
- err = pci_alloc_irq_vectors(self->pdev, 1, 1,
- PCI_IRQ_MSI | PCI_IRQ_LEGACY);
- if (err < 0)
- goto err_hwinit;
+ numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
+ PCI_IRQ_MSIX | PCI_IRQ_MSI |
+ PCI_IRQ_LEGACY);
+
+ if (numvecs < 0) {
+ err = numvecs;
+ goto err_hwinit;
}
#endif
+ self->irqvecs = numvecs;
/* net device init */
aq_nic_cfg_start(self);
kfree(self->aq_hw);
err_ioremap:
free_netdev(ndev);
-err_pci_func:
- pci_release_regions(pdev);
err_ndev:
+ pci_release_regions(pdev);
+err_pci_func:
pci_disable_device(pdev);
return err;
}
pkts = priv->rx_max_coalesced_frames;
if (ec->use_adaptive_rx_coalesce && !priv->dim.use_dim) {
- moder = net_dim_get_def_profile(priv->dim.dim.mode);
+ moder = net_dim_get_def_rx_moderation(priv->dim.dim.mode);
usecs = moder.usec;
pkts = moder.pkts;
}
struct bcm_sysport_priv *priv =
container_of(ndim, struct bcm_sysport_priv, dim);
struct net_dim_cq_moder cur_profile =
- net_dim_get_profile(dim->mode, dim->profile_ix);
+ net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
bcm_sysport_set_rx_coalesce(priv, cur_profile.usec, cur_profile.pkts);
dim->state = NET_DIM_START_MEASURE;
/* If DIM was enabled, re-apply default parameters */
if (dim->use_dim) {
- moder = net_dim_get_def_profile(dim->dim.mode);
+ moder = net_dim_get_def_rx_moderation(dim->dim.mode);
usecs = moder.usec;
pkts = moder.pkts;
}
.ndo_select_queue = bcm_sysport_select_queue,
};
-static int bcm_sysport_map_queues(struct net_device *dev,
+static int bcm_sysport_map_queues(struct notifier_block *nb,
struct dsa_notifier_register_info *info)
{
- struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_tx_ring *ring;
+ struct bcm_sysport_priv *priv;
struct net_device *slave_dev;
unsigned int num_tx_queues;
unsigned int q, start, port;
+ struct net_device *dev;
+
+ priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+ if (priv->netdev != info->master)
+ return 0;
+
+ dev = info->master;
/* We can't be setting up queue inspection for non directly attached
* switches
if (priv->is_lite)
netif_set_real_num_tx_queues(slave_dev,
slave_dev->num_tx_queues / 2);
+
num_tx_queues = slave_dev->real_num_tx_queues;
if (priv->per_port_num_tx_queues &&
priv->per_port_num_tx_queues != num_tx_queues)
- netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+ netdev_warn(slave_dev, "asymmetric number of per-port queues\n");
priv->per_port_num_tx_queues = num_tx_queues;
return 0;
}
-static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct dsa_notifier_register_info *info;
info = ptr;
- return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+ return notifier_from_errno(bcm_sysport_map_queues(nb, info));
}
#define REV_FMT "v%2x.%02x"
bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o
bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o
+bnxt_en-$(CONFIG_DEBUG_FS) += bnxt_debugfs.o
#include "bnxt_vfr.h"
#include "bnxt_tc.h"
#include "bnxt_devlink.h"
+#include "bnxt_debugfs.h"
#define BNXT_TX_TIMEOUT (5 * HZ)
for (i = 0, j = 0; i < bp->tx_nr_rings; i++) {
struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
struct bnxt_ring_struct *ring;
+ u8 qidx;
ring = &txr->tx_ring_struct;
memset(txr->tx_push, 0, sizeof(struct tx_push_bd));
}
- ring->queue_id = bp->q_info[j].queue_id;
+ qidx = bp->tc_to_qidx[j];
+ ring->queue_id = bp->q_info[qidx].queue_id;
if (i < bp->tx_nr_rings_xdp)
continue;
if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
if (!timeout)
timeout = DFLT_HWRM_CMD_TIMEOUT;
+ /* convert timeout to usec */
+ timeout *= 1000;
i = 0;
- tmo_count = timeout * 40;
+ /* Short timeout for the first few iterations:
+ * number of loops = number of loops for short timeout +
+ * number of loops for standard timeout.
+ */
+ tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
+ timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
+ tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
if (intr_process) {
/* Wait until hwrm response cmpl interrupt is processed */
while (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID &&
i++ < tmo_count) {
- usleep_range(25, 40);
+ /* on first few passes, just barely sleep */
+ if (i < HWRM_SHORT_TIMEOUT_COUNTER)
+ usleep_range(HWRM_SHORT_MIN_TIMEOUT,
+ HWRM_SHORT_MAX_TIMEOUT);
+ else
+ usleep_range(HWRM_MIN_TIMEOUT,
+ HWRM_MAX_TIMEOUT);
}
if (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID) {
HWRM_RESP_LEN_SFT;
valid = bp->hwrm_cmd_resp_addr + len - 1;
} else {
+ int j;
+
/* Check if response len is updated */
for (i = 0; i < tmo_count; i++) {
len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
HWRM_RESP_LEN_SFT;
if (len)
break;
- usleep_range(25, 40);
+ /* on first few passes, just barely sleep */
+ if (i < DFLT_HWRM_CMD_TIMEOUT)
+ usleep_range(HWRM_SHORT_MIN_TIMEOUT,
+ HWRM_SHORT_MAX_TIMEOUT);
+ else
+ usleep_range(HWRM_MIN_TIMEOUT,
+ HWRM_MAX_TIMEOUT);
}
if (i >= tmo_count) {
netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n",
- timeout, le16_to_cpu(req->req_type),
+ HWRM_TOTAL_TIMEOUT(i),
+ le16_to_cpu(req->req_type),
le16_to_cpu(req->seq_id), len);
return -1;
}
/* Last byte of resp contains valid bit */
valid = bp->hwrm_cmd_resp_addr + len - 1;
- for (i = 0; i < 5; i++) {
+ for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
/* make sure we read from updated DMA memory */
dma_rmb();
if (*valid)
udelay(1);
}
- if (i >= 5) {
+ if (j >= HWRM_VALID_BIT_DELAY_USEC) {
netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n",
- timeout, le16_to_cpu(req->req_type),
+ HWRM_TOTAL_TIMEOUT(i),
+ le16_to_cpu(req->req_type),
le16_to_cpu(req->seq_id), len, *valid);
return -1;
}
mutex_unlock(&bp->hwrm_cmd_lock);
if (rc || err) {
- switch (ring_type) {
- case RING_FREE_REQ_RING_TYPE_L2_CMPL:
- netdev_err(bp->dev, "hwrm_ring_alloc cp failed. rc:%x err:%x\n",
- rc, err);
- return -1;
-
- case RING_FREE_REQ_RING_TYPE_RX:
- netdev_err(bp->dev, "hwrm_ring_alloc rx failed. rc:%x err:%x\n",
- rc, err);
- return -1;
-
- case RING_FREE_REQ_RING_TYPE_TX:
- netdev_err(bp->dev, "hwrm_ring_alloc tx failed. rc:%x err:%x\n",
- rc, err);
- return -1;
-
- default:
- netdev_err(bp->dev, "Invalid ring\n");
- return -1;
- }
+ netdev_err(bp->dev, "hwrm_ring_alloc type %d failed. rc:%x err:%x\n",
+ ring_type, rc, err);
+ return -EIO;
}
ring->fw_ring_id = ring_id;
return rc;
mutex_unlock(&bp->hwrm_cmd_lock);
if (rc || error_code) {
- switch (ring_type) {
- case RING_FREE_REQ_RING_TYPE_L2_CMPL:
- netdev_err(bp->dev, "hwrm_ring_free cp failed. rc:%d\n",
- rc);
- return rc;
- case RING_FREE_REQ_RING_TYPE_RX:
- netdev_err(bp->dev, "hwrm_ring_free rx failed. rc:%d\n",
- rc);
- return rc;
- case RING_FREE_REQ_RING_TYPE_TX:
- netdev_err(bp->dev, "hwrm_ring_free tx failed. rc:%d\n",
- rc);
- return rc;
- default:
- netdev_err(bp->dev, "Invalid ring\n");
- return -1;
- }
+ netdev_err(bp->dev, "hwrm_ring_free type %d failed. rc:%x err:%x\n",
+ ring_type, rc, error_code);
+ return -EIO;
}
return 0;
}
__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
cp_rings, vnics);
+ req.enables |= cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS |
+ FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS);
+ req.num_rsscos_ctxs = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
+ req.num_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (rc)
return -ENOMEM;
for (i = 0; i < bp->max_tc; i++) {
bp->q_info[i].queue_id = *qptr++;
bp->q_info[i].queue_profile = *qptr++;
+ bp->tc_to_qidx[i] = i;
}
qportcfg_exit:
struct tm tm;
time64_t now = ktime_get_real_seconds();
- if (bp->hwrm_spec_code < 0x10400)
+ if ((BNXT_VF(bp) && bp->hwrm_spec_code < 0x10901) ||
+ bp->hwrm_spec_code < 0x10400)
return -EOPNOTSUPP;
time64_to_tm(now, 0, &tm);
if (total_vecs > max)
total_vecs = max;
+ if (!total_vecs)
+ return 0;
+
msix_ent = kcalloc(total_vecs, sizeof(struct msix_entry), GFP_KERNEL);
if (!msix_ent)
return -ENOMEM;
}
mutex_unlock(&bp->hwrm_cmd_lock);
+ if (!BNXT_SINGLE_PF(bp))
+ return 0;
+
diff = link_info->support_auto_speeds ^ link_info->advertising;
if ((link_info->support_auto_speeds | diff) !=
link_info->support_auto_speeds) {
}
}
+static int bnxt_init_dflt_ring_mode(struct bnxt *bp);
+
static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
{
int rc = 0;
bnxt_preset_reg_win(bp);
netif_carrier_off(bp->dev);
if (irq_re_init) {
+ /* Reserve rings now if none were reserved at driver probe. */
+ rc = bnxt_init_dflt_ring_mode(bp);
+ if (rc) {
+ netdev_err(bp->dev, "Failed to reserve default rings at open\n");
+ return rc;
+ }
rc = bnxt_reserve_rings(bp);
if (rc)
return rc;
}
bnxt_enable_napi(bp);
+ bnxt_debug_dev_init(bp);
rc = bnxt_init_nic(bp, irq_re_init);
if (rc) {
return 0;
open_err:
+ bnxt_debug_dev_exit(bp);
bnxt_disable_napi(bp);
bnxt_del_napi(bp);
/* TODO CHIMP_FW: Link/PHY related cleanup if (link_re_init) */
+ bnxt_debug_dev_exit(bp);
bnxt_disable_napi(bp);
del_timer_sync(&bp->timer);
bnxt_free_skbs(bp);
return rc;
}
+static bool bnxt_can_reserve_rings(struct bnxt *bp)
+{
+#ifdef CONFIG_BNXT_SRIOV
+ if ((bp->flags & BNXT_FLAG_NEW_RM) && BNXT_VF(bp)) {
+ struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+
+ /* No minimum rings were provisioned by the PF. Don't
+ * reserve rings by default when device is down.
+ */
+ if (hw_resc->min_tx_rings || hw_resc->resv_tx_rings)
+ return true;
+
+ if (!netif_running(bp->dev))
+ return false;
+ }
+#endif
+ return true;
+}
+
/* If the chip and firmware supports RFS */
static bool bnxt_rfs_supported(struct bnxt *bp)
{
#ifdef CONFIG_RFS_ACCEL
int vnics, max_vnics, max_rss_ctxs;
- if (!(bp->flags & BNXT_FLAG_MSIX_CAP))
+ if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp))
return false;
vnics = 1 + bp->rx_nr_rings;
coal->coal_bufs = 30;
coal->coal_ticks_irq = 1;
coal->coal_bufs_irq = 2;
- coal->idle_thresh = 25;
+ coal->idle_thresh = 50;
coal->bufs_per_record = 2;
coal->budget = 64; /* NAPI budget */
{
int dflt_rings, max_rx_rings, max_tx_rings, rc;
+ if (!bnxt_can_reserve_rings(bp))
+ return 0;
+
if (sh)
bp->flags |= BNXT_FLAG_SHARED_RINGS;
dflt_rings = netif_get_num_default_rss_queues();
return rc;
}
+static int bnxt_init_dflt_ring_mode(struct bnxt *bp)
+{
+ int rc;
+
+ if (bp->tx_nr_rings)
+ return 0;
+
+ rc = bnxt_set_dflt_rings(bp, true);
+ if (rc) {
+ netdev_err(bp->dev, "Not enough rings available.\n");
+ return rc;
+ }
+ rc = bnxt_init_int_mode(bp);
+ if (rc)
+ return rc;
+ bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+ if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) {
+ bp->flags |= BNXT_FLAG_RFS;
+ bp->dev->features |= NETIF_F_NTUPLE;
+ }
+ return 0;
+}
+
int bnxt_restore_pf_fw_resources(struct bnxt *bp)
{
int rc;
memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
} else {
eth_hw_addr_random(bp->dev);
- rc = bnxt_approve_mac(bp, bp->dev->dev_addr);
}
+ rc = bnxt_approve_mac(bp, bp->dev->dev_addr);
#endif
}
return rc;
static int __init bnxt_init(void)
{
+ bnxt_debug_init();
return pci_register_driver(&bnxt_pci_driver);
}
pci_unregister_driver(&bnxt_pci_driver);
if (bnxt_pf_wq)
destroy_workqueue(bnxt_pf_wq);
+ bnxt_debug_exit();
}
module_init(bnxt_init);
#define BNXT_HWRM_REQ_MAX_SIZE 128
#define BNXT_HWRM_REQS_PER_PAGE (BNXT_PAGE_SIZE / \
BNXT_HWRM_REQ_MAX_SIZE)
+#define HWRM_SHORT_MIN_TIMEOUT 3
+#define HWRM_SHORT_MAX_TIMEOUT 10
+#define HWRM_SHORT_TIMEOUT_COUNTER 5
+
+#define HWRM_MIN_TIMEOUT 25
+#define HWRM_MAX_TIMEOUT 40
+
+#define HWRM_TOTAL_TIMEOUT(n) (((n) <= HWRM_SHORT_TIMEOUT_COUNTER) ? \
+ ((n) * HWRM_SHORT_MIN_TIMEOUT) : \
+ (HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT + \
+ ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT))
+
+#define HWRM_VALID_BIT_DELAY_USEC 20
#define BNXT_RX_EVENT 1
#define BNXT_AGG_EVENT 2
u8 max_tc;
u8 max_lltc; /* lossless TCs */
struct bnxt_queue_info q_info[BNXT_MAX_QUEUE];
+ u8 tc_to_qidx[BNXT_MAX_QUEUE];
unsigned int current_interval;
#define BNXT_TIMER_INTERVAL HZ
u16 *cfa_code_map; /* cfa_code -> vf_idx map */
u8 switch_id[8];
struct bnxt_tc_info *tc_info;
+ struct dentry *debugfs_pdev;
+ struct dentry *debugfs_dim;
};
#define BNXT_RX_STATS_OFFSET(counter) \
#define I2C_DEV_ADDR_A0 0xa0
#define I2C_DEV_ADDR_A2 0xa2
-#define SFP_EEPROM_SFF_8472_COMP_ADDR 0x5e
-#define SFP_EEPROM_SFF_8472_COMP_SIZE 1
+#define SFF_DIAG_SUPPORT_OFFSET 0x5c
#define SFF_MODULE_ID_SFP 0x3
#define SFF_MODULE_ID_QSFP 0xc
#define SFF_MODULE_ID_QSFP_PLUS 0xd
#include "bnxt_dcb.h"
#ifdef CONFIG_BNXT_DCB
+static int bnxt_queue_to_tc(struct bnxt *bp, u8 queue_id)
+{
+ int i, j;
+
+ for (i = 0; i < bp->max_tc; i++) {
+ if (bp->q_info[i].queue_id == queue_id) {
+ for (j = 0; j < bp->max_tc; j++) {
+ if (bp->tc_to_qidx[j] == i)
+ return j;
+ }
+ }
+ }
+ return -EINVAL;
+}
+
static int bnxt_hwrm_queue_pri2cos_cfg(struct bnxt *bp, struct ieee_ets *ets)
{
struct hwrm_queue_pri2cos_cfg_input req = {0};
pri2cos = &req.pri0_cos_queue_id;
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+ u8 qidx;
+
req.enables |= cpu_to_le32(
QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID << i);
- pri2cos[i] = bp->q_info[ets->prio_tc[i]].queue_id;
+ qidx = bp->tc_to_qidx[ets->prio_tc[i]];
+ pri2cos[i] = bp->q_info[qidx].queue_id;
}
rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
return rc;
rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
if (!rc) {
u8 *pri2cos = &resp->pri0_cos_queue_id;
- int i, j;
+ int i;
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
u8 queue_id = pri2cos[i];
+ int tc;
- for (j = 0; j < bp->max_tc; j++) {
- if (bp->q_info[j].queue_id == queue_id) {
- ets->prio_tc[i] = j;
- break;
- }
- }
+ tc = bnxt_queue_to_tc(bp, queue_id);
+ if (tc >= 0)
+ ets->prio_tc[i] = tc;
}
}
mutex_unlock(&bp->hwrm_cmd_lock);
void *data;
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1);
- data = &req.unused_0;
- for (i = 0; i < max_tc; i++, data += sizeof(cos2bw) - 4) {
+ for (i = 0; i < max_tc; i++) {
+ u8 qidx;
+
req.enables |= cpu_to_le32(
QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << i);
memset(&cos2bw, 0, sizeof(cos2bw));
- cos2bw.queue_id = bp->q_info[i].queue_id;
+ qidx = bp->tc_to_qidx[i];
+ cos2bw.queue_id = bp->q_info[qidx].queue_id;
if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) {
cos2bw.tsa =
QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP;
cpu_to_le32((ets->tc_tx_bw[i] * 100) |
BW_VALUE_UNIT_PERCENT1_100);
}
+ data = &req.unused_0 + qidx * (sizeof(cos2bw) - 4);
memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4);
- if (i == 0) {
+ if (qidx == 0) {
req.queue_id0 = cos2bw.queue_id;
req.unused_0 = 0;
}
data = &resp->queue_id0 + offsetof(struct bnxt_cos2bw_cfg, queue_id);
for (i = 0; i < bp->max_tc; i++, data += sizeof(cos2bw) - 4) {
- int j;
+ int tc;
memcpy(&cos2bw.queue_id, data, sizeof(cos2bw) - 4);
if (i == 0)
cos2bw.queue_id = resp->queue_id0;
- for (j = 0; j < bp->max_tc; j++) {
- if (bp->q_info[j].queue_id != cos2bw.queue_id)
- continue;
- if (cos2bw.tsa ==
- QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP) {
- ets->tc_tsa[j] = IEEE_8021QAZ_TSA_STRICT;
- } else {
- ets->tc_tsa[j] = IEEE_8021QAZ_TSA_ETS;
- ets->tc_tx_bw[j] = cos2bw.bw_weight;
- }
+ tc = bnxt_queue_to_tc(bp, cos2bw.queue_id);
+ if (tc < 0)
+ continue;
+
+ if (cos2bw.tsa ==
+ QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP) {
+ ets->tc_tsa[tc] = IEEE_8021QAZ_TSA_STRICT;
+ } else {
+ ets->tc_tsa[tc] = IEEE_8021QAZ_TSA_ETS;
+ ets->tc_tx_bw[tc] = cos2bw.bw_weight;
}
}
mutex_unlock(&bp->hwrm_cmd_lock);
return 0;
}
-static int bnxt_hwrm_queue_cfg(struct bnxt *bp, unsigned int lltc_mask)
+static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask)
{
- struct hwrm_queue_cfg_input req = {0};
- int i;
+ unsigned long qmap = 0;
+ int max = bp->max_tc;
+ int i, j, rc;
- if (netif_running(bp->dev))
- bnxt_tx_disable(bp);
+ /* Assign lossless TCs first */
+ for (i = 0, j = 0; i < max; ) {
+ if (lltc_mask & (1 << i)) {
+ if (BNXT_LLQ(bp->q_info[j].queue_profile)) {
+ bp->tc_to_qidx[i] = j;
+ __set_bit(j, &qmap);
+ i++;
+ }
+ j++;
+ continue;
+ }
+ i++;
+ }
- bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_CFG, -1, -1);
- req.flags = cpu_to_le32(QUEUE_CFG_REQ_FLAGS_PATH_BIDIR);
- req.enables = cpu_to_le32(QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE);
+ for (i = 0, j = 0; i < max; i++) {
+ if (lltc_mask & (1 << i))
+ continue;
+ j = find_next_zero_bit(&qmap, max, j);
+ bp->tc_to_qidx[i] = j;
+ __set_bit(j, &qmap);
+ j++;
+ }
- /* Configure lossless queues to lossy first */
- req.service_profile = QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY;
- for (i = 0; i < bp->max_tc; i++) {
- if (BNXT_LLQ(bp->q_info[i].queue_profile)) {
- req.queue_id = cpu_to_le32(bp->q_info[i].queue_id);
- hwrm_send_message(bp, &req, sizeof(req),
- HWRM_CMD_TIMEOUT);
- bp->q_info[i].queue_profile =
- QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY;
+ if (netif_running(bp->dev)) {
+ bnxt_close_nic(bp, false, false);
+ rc = bnxt_open_nic(bp, false, false);
+ if (rc) {
+ netdev_warn(bp->dev, "failed to open NIC, rc = %d\n", rc);
+ return rc;
}
}
-
- /* Now configure desired queues to lossless */
- req.service_profile = QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS;
- for (i = 0; i < bp->max_tc; i++) {
- if (lltc_mask & (1 << i)) {
- req.queue_id = cpu_to_le32(bp->q_info[i].queue_id);
- hwrm_send_message(bp, &req, sizeof(req),
- HWRM_CMD_TIMEOUT);
- bp->q_info[i].queue_profile =
- QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS;
+ if (bp->ieee_ets) {
+ int tc = netdev_get_num_tc(bp->dev);
+
+ if (!tc)
+ tc = 1;
+ rc = bnxt_hwrm_queue_cos2bw_cfg(bp, bp->ieee_ets, tc);
+ if (rc) {
+ netdev_warn(bp->dev, "failed to config BW, rc = %d\n", rc);
+ return rc;
+ }
+ rc = bnxt_hwrm_queue_pri2cos_cfg(bp, bp->ieee_ets);
+ if (rc) {
+ netdev_warn(bp->dev, "failed to config prio, rc = %d\n", rc);
+ return rc;
}
}
- if (netif_running(bp->dev))
- bnxt_tx_enable(bp);
-
return 0;
}
struct ieee_ets *my_ets = bp->ieee_ets;
unsigned int tc_mask = 0, pri_mask = 0;
u8 i, pri, lltc_count = 0;
- bool need_q_recfg = false;
+ bool need_q_remap = false;
int rc;
if (!my_ets)
if (lltc_count > bp->max_lltc)
return -EINVAL;
- bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_CFG, -1, -1);
- req.flags = cpu_to_le32(pri_mask);
- rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
- if (rc)
- return rc;
-
for (i = 0; i < bp->max_tc; i++) {
if (tc_mask & (1 << i)) {
- if (!BNXT_LLQ(bp->q_info[i].queue_profile))
- need_q_recfg = true;
+ u8 qidx = bp->tc_to_qidx[i];
+
+ if (!BNXT_LLQ(bp->q_info[qidx].queue_profile)) {
+ need_q_remap = true;
+ break;
+ }
}
}
- if (need_q_recfg)
- rc = bnxt_hwrm_queue_cfg(bp, tc_mask);
+ if (need_q_remap)
+ rc = bnxt_queue_remap(bp, tc_mask);
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_CFG, -1, -1);
+ req.flags = cpu_to_le32(pri_mask);
+ rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (rc)
+ return rc;
return rc;
}
--- /dev/null
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017-2018 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include "bnxt_hsi.h"
+#include <linux/net_dim.h>
+#include "bnxt.h"
+#include "bnxt_debugfs.h"
+
+static struct dentry *bnxt_debug_mnt;
+
+static ssize_t debugfs_dim_read(struct file *filep,
+ char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct net_dim *dim = filep->private_data;
+ int len;
+ char *buf;
+
+ if (*ppos)
+ return 0;
+ if (!dim)
+ return -ENODEV;
+ buf = kasprintf(GFP_KERNEL,
+ "state = %d\n" \
+ "profile_ix = %d\n" \
+ "mode = %d\n" \
+ "tune_state = %d\n" \
+ "steps_right = %d\n" \
+ "steps_left = %d\n" \
+ "tired = %d\n",
+ dim->state,
+ dim->profile_ix,
+ dim->mode,
+ dim->tune_state,
+ dim->steps_right,
+ dim->steps_left,
+ dim->tired);
+ if (!buf)
+ return -ENOMEM;
+ if (count < strlen(buf)) {
+ kfree(buf);
+ return -ENOSPC;
+ }
+ len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+ kfree(buf);
+ return len;
+}
+
+static const struct file_operations debugfs_dim_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = debugfs_dim_read,
+};
+
+static struct dentry *debugfs_dim_ring_init(struct net_dim *dim, int ring_idx,
+ struct dentry *dd)
+{
+ static char qname[16];
+
+ snprintf(qname, 10, "%d", ring_idx);
+ return debugfs_create_file(qname, 0600, dd,
+ dim, &debugfs_dim_fops);
+}
+
+void bnxt_debug_dev_init(struct bnxt *bp)
+{
+ const char *pname = pci_name(bp->pdev);
+ struct dentry *pdevf;
+ int i;
+
+ bp->debugfs_pdev = debugfs_create_dir(pname, bnxt_debug_mnt);
+ if (bp->debugfs_pdev) {
+ pdevf = debugfs_create_dir("dim", bp->debugfs_pdev);
+ if (!pdevf) {
+ pr_err("failed to create debugfs entry %s/dim\n",
+ pname);
+ return;
+ }
+ bp->debugfs_dim = pdevf;
+ /* create files for each rx ring */
+ for (i = 0; i < bp->cp_nr_rings; i++) {
+ struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+
+ if (cpr && bp->bnapi[i]->rx_ring) {
+ pdevf = debugfs_dim_ring_init(&cpr->dim, i,
+ bp->debugfs_dim);
+ if (!pdevf)
+ pr_err("failed to create debugfs entry %s/dim/%d\n",
+ pname, i);
+ }
+ }
+ } else {
+ pr_err("failed to create debugfs entry %s\n", pname);
+ }
+}
+
+void bnxt_debug_dev_exit(struct bnxt *bp)
+{
+ if (bp) {
+ debugfs_remove_recursive(bp->debugfs_pdev);
+ bp->debugfs_pdev = NULL;
+ }
+}
+
+void bnxt_debug_init(void)
+{
+ bnxt_debug_mnt = debugfs_create_dir("bnxt_en", NULL);
+ if (!bnxt_debug_mnt)
+ pr_err("failed to init bnxt_en debugfs\n");
+}
+
+void bnxt_debug_exit(void)
+{
+ debugfs_remove_recursive(bnxt_debug_mnt);
+}
--- /dev/null
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017-2018 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+
+#ifdef CONFIG_DEBUG_FS
+void bnxt_debug_init(void);
+void bnxt_debug_exit(void);
+void bnxt_debug_dev_init(struct bnxt *bp);
+void bnxt_debug_dev_exit(struct bnxt *bp);
+#else
+static inline void bnxt_debug_init(void) {}
+static inline void bnxt_debug_exit(void) {}
+static inline void bnxt_debug_dev_init(struct bnxt *bp) {}
+static inline void bnxt_debug_dev_exit(struct bnxt *bp) {}
+#endif
struct bnxt_napi *bnapi = container_of(cpr,
struct bnxt_napi,
cp_ring);
- struct net_dim_cq_moder cur_profile = net_dim_get_profile(dim->mode,
- dim->profile_ix);
+ struct net_dim_cq_moder cur_moder =
+ net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
- cpr->rx_ring_coal.coal_ticks = cur_profile.usec;
- cpr->rx_ring_coal.coal_bufs = cur_profile.pkts;
+ cpr->rx_ring_coal.coal_ticks = cur_moder.usec;
+ cpr->rx_ring_coal.coal_bufs = cur_moder.pkts;
bnxt_hwrm_set_ring_coal(bnapi->bp, bnapi);
dim->state = NET_DIM_START_MEASURE;
#define BNXT_RX_STATS_EXT_ENTRY(counter) \
{ BNXT_RX_STATS_EXT_OFFSET(counter), __stringify(counter) }
+enum {
+ RX_TOTAL_DISCARDS,
+ TX_TOTAL_DISCARDS,
+};
+
+static struct {
+ u64 counter;
+ char string[ETH_GSTRING_LEN];
+} bnxt_sw_func_stats[] = {
+ {0, "rx_total_discard_pkts"},
+ {0, "tx_total_discard_pkts"},
+};
+
static const struct {
long offset;
char string[ETH_GSTRING_LEN];
BNXT_RX_STATS_EXT_ENTRY(resume_roce_pause_events),
};
+#define BNXT_NUM_SW_FUNC_STATS ARRAY_SIZE(bnxt_sw_func_stats)
#define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
#define BNXT_NUM_PORT_STATS_EXT ARRAY_SIZE(bnxt_port_stats_ext_arr)
{
int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
+ num_stats += BNXT_NUM_SW_FUNC_STATS;
+
if (bp->flags & BNXT_FLAG_PORT_STATS)
num_stats += BNXT_NUM_PORT_STATS;
if (!bp->bnapi)
return;
+ for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
+ bnxt_sw_func_stats[i].counter = 0;
+
for (i = 0; i < bp->cp_nr_rings; i++) {
struct bnxt_napi *bnapi = bp->bnapi[i];
struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
for (k = 0; k < stat_fields; j++, k++)
buf[j] = le64_to_cpu(hw_stats[k]);
buf[j++] = cpr->rx_l4_csum_errors;
+
+ bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter +=
+ le64_to_cpu(cpr->hw_stats->rx_discard_pkts);
+ bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter +=
+ le64_to_cpu(cpr->hw_stats->tx_discard_pkts);
}
+
+ for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
+ buf[j] = bnxt_sw_func_stats[i].counter;
+
if (bp->flags & BNXT_FLAG_PORT_STATS) {
__le64 *port_stats = (__le64 *)bp->hw_rx_port_stats;
sprintf(buf, "[%d]: rx_l4_csum_errors", i);
buf += ETH_GSTRING_LEN;
}
+ for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) {
+ strcpy(buf, bnxt_sw_func_stats[i].string);
+ buf += ETH_GSTRING_LEN;
+ }
+
if (bp->flags & BNXT_FLAG_PORT_STATS) {
for (i = 0; i < BNXT_NUM_PORT_STATS; i++) {
strcpy(buf, bnxt_port_stats_arr[i].string);
* to renable
*/
}
+ } else {
+ rc = bnxt_reserve_rings(bp);
}
return rc;
static int bnxt_get_eeprom_len(struct net_device *dev)
{
+ struct bnxt *bp = netdev_priv(dev);
+
+ if (BNXT_VF(bp))
+ return 0;
+
/* The -1 return value allows the entire 32-bit range of offsets to be
* passed via the ethtool command-line utility.
*/
static int bnxt_get_module_info(struct net_device *dev,
struct ethtool_modinfo *modinfo)
{
+ u8 data[SFF_DIAG_SUPPORT_OFFSET + 1];
struct bnxt *bp = netdev_priv(dev);
- struct hwrm_port_phy_i2c_read_input req = {0};
- struct hwrm_port_phy_i2c_read_output *output = bp->hwrm_cmd_resp_addr;
int rc;
/* No point in going further if phy status indicates
if (bp->hwrm_spec_code < 0x10202)
return -EOPNOTSUPP;
- bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_I2C_READ, -1, -1);
- req.i2c_slave_addr = I2C_DEV_ADDR_A0;
- req.page_number = 0;
- req.page_offset = cpu_to_le16(SFP_EEPROM_SFF_8472_COMP_ADDR);
- req.data_length = SFP_EEPROM_SFF_8472_COMP_SIZE;
- req.port_id = cpu_to_le16(bp->pf.port_id);
- mutex_lock(&bp->hwrm_cmd_lock);
- rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, 0,
+ SFF_DIAG_SUPPORT_OFFSET + 1,
+ data);
if (!rc) {
- u32 module_id = le32_to_cpu(output->data[0]);
+ u8 module_id = data[0];
+ u8 diag_supported = data[SFF_DIAG_SUPPORT_OFFSET];
switch (module_id) {
case SFF_MODULE_ID_SFP:
modinfo->type = ETH_MODULE_SFF_8472;
modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+ if (!diag_supported)
+ modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
break;
case SFF_MODULE_ID_QSFP:
case SFF_MODULE_ID_QSFP_PLUS:
break;
}
}
- mutex_unlock(&bp->hwrm_cmd_lock);
return rc;
}
vf_vnics = hw_resc->max_vnics - bp->nr_vnics;
vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
- req.min_rsscos_ctx = cpu_to_le16(1);
- req.max_rsscos_ctx = cpu_to_le16(1);
+ req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX);
+ req.max_rsscos_ctx = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL) {
req.min_cmpl_rings = cpu_to_le16(1);
req.min_tx_rings = cpu_to_le16(1);
req.min_rx_rings = cpu_to_le16(1);
- req.min_l2_ctxs = cpu_to_le16(1);
+ req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MIN_L2_CTX);
req.min_vnics = cpu_to_le16(1);
req.min_stat_ctx = cpu_to_le16(1);
req.min_hw_ring_grps = cpu_to_le16(1);
req.min_cmpl_rings = cpu_to_le16(vf_cp_rings);
req.min_tx_rings = cpu_to_le16(vf_tx_rings);
req.min_rx_rings = cpu_to_le16(vf_rx_rings);
- req.min_l2_ctxs = cpu_to_le16(4);
+ req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
req.min_vnics = cpu_to_le16(vf_vnics);
req.min_stat_ctx = cpu_to_le16(vf_stat_ctx);
req.min_hw_ring_grps = cpu_to_le16(vf_ring_grps);
req.max_cmpl_rings = cpu_to_le16(vf_cp_rings);
req.max_tx_rings = cpu_to_le16(vf_tx_rings);
req.max_rx_rings = cpu_to_le16(vf_rx_rings);
- req.max_l2_ctxs = cpu_to_le16(4);
+ req.max_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX);
req.max_vnics = cpu_to_le16(vf_vnics);
req.max_stat_ctx = cpu_to_le16(vf_stat_ctx);
req.max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
struct hwrm_fwd_resp_input req = {0};
struct hwrm_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
+ if (BNXT_FWD_RESP_SIZE_ERR(msg_size))
+ return -EINVAL;
+
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FWD_RESP, -1, -1);
/* Set the new target id */
struct hwrm_reject_fwd_resp_input req = {0};
struct hwrm_reject_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
+ if (BNXT_REJ_FWD_RESP_SIZE_ERR(msg_size))
+ return -EINVAL;
+
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_REJECT_FWD_RESP, -1, -1);
/* Set the new target id */
req.target_id = cpu_to_le16(vf->fw_fid);
struct hwrm_exec_fwd_resp_input req = {0};
struct hwrm_exec_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr;
+ if (BNXT_EXEC_FWD_RESP_SIZE_ERR(msg_size))
+ return -EINVAL;
+
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_EXEC_FWD_RESP, -1, -1);
/* Set the new target id */
req.target_id = cpu_to_le16(vf->fw_fid);
if (req->enables & cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR)) {
if (is_valid_ether_addr(req->dflt_mac_addr) &&
((vf->flags & BNXT_VF_TRUST) ||
- (!is_valid_ether_addr(vf->mac_addr)))) {
+ !is_valid_ether_addr(vf->mac_addr) ||
+ ether_addr_equal(req->dflt_mac_addr, vf->mac_addr))) {
ether_addr_copy(vf->vf_mac_addr, req->dflt_mac_addr);
return bnxt_hwrm_exec_fwd_resp(bp, vf, msg_size);
}
#ifndef BNXT_SRIOV_H
#define BNXT_SRIOV_H
+#define BNXT_FWD_RESP_SIZE_ERR(n) \
+ ((offsetof(struct hwrm_fwd_resp_input, encap_resp) + n) > \
+ sizeof(struct hwrm_fwd_resp_input))
+
+#define BNXT_EXEC_FWD_RESP_SIZE_ERR(n) \
+ ((offsetof(struct hwrm_exec_fwd_resp_input, encap_request) + n) >\
+ offsetof(struct hwrm_exec_fwd_resp_input, encap_resp_target_id))
+
+#define BNXT_REJ_FWD_RESP_SIZE_ERR(n) \
+ ((offsetof(struct hwrm_reject_fwd_resp_input, encap_request) + n) >\
+ offsetof(struct hwrm_reject_fwd_resp_input, encap_resp_target_id))
+
+#define BNXT_VF_MIN_RSS_CTX 1
+#define BNXT_VF_MAX_RSS_CTX 1
+#define BNXT_VF_MIN_L2_CTX 1
+#define BNXT_VF_MAX_L2_CTX 4
+
int bnxt_get_vf_config(struct net_device *, int, struct ifla_vf_info *);
int bnxt_set_vf_mac(struct net_device *, int, u8 *);
int bnxt_set_vf_vlan(struct net_device *, int, u16, u8, __be16);
pkts = ring->rx_max_coalesced_frames;
if (ec->use_adaptive_rx_coalesce && !ring->dim.use_dim) {
- moder = net_dim_get_def_profile(ring->dim.dim.mode);
+ moder = net_dim_get_def_rx_moderation(ring->dim.dim.mode);
usecs = moder.usec;
pkts = moder.pkts;
}
struct bcmgenet_rx_ring *ring =
container_of(ndim, struct bcmgenet_rx_ring, dim);
struct net_dim_cq_moder cur_profile =
- net_dim_get_profile(dim->mode, dim->profile_ix);
+ net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
bcmgenet_set_rx_coalesce(ring, cur_profile.usec, cur_profile.pkts);
dim->state = NET_DIM_START_MEASURE;
/* If DIM was enabled, re-apply default parameters */
if (dim->use_dim) {
- moder = net_dim_get_def_profile(dim->dim.mode);
+ moder = net_dim_get_def_rx_moderation(dim->dim.mode);
usecs = moder.usec;
pkts = moder.pkts;
}
tg3_mem_rx_release(tp);
tg3_mem_tx_release(tp);
- /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
- tg3_full_lock(tp, 0);
+ /* tp->hw_stats can be referenced safely:
+ * 1. under rtnl_lock
+ * 2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set.
+ */
if (tp->hw_stats) {
dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
tp->hw_stats, tp->stats_mapping);
tp->hw_stats = NULL;
}
- tg3_full_unlock(tp);
}
/*
struct tg3 *tp = netdev_priv(dev);
spin_lock_bh(&tp->lock);
- if (!tp->hw_stats) {
+ if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) {
*stats = tp->net_stats_prev;
spin_unlock_bh(&tp->lock);
return;
dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
np = bp->pdev->dev.of_node;
+ if (pdata)
+ bp->mii_bus->phy_mask = pdata->phy_mask;
- if (np) {
- err = of_mdiobus_register(bp->mii_bus, np);
- } else {
- if (pdata)
- bp->mii_bus->phy_mask = pdata->phy_mask;
-
- err = mdiobus_register(bp->mii_bus);
- }
-
+ err = of_mdiobus_register(bp->mii_bus, np);
if (err)
goto err_out_free_mdiobus;
CN23XX_SLI_MAC_PF_INT_ENB64(oct->pcie_port, oct->pf_num);
}
-static int cn23xx_sriov_config(struct octeon_device *oct)
+int cn23xx_sriov_config(struct octeon_device *oct)
{
struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
u32 max_rings, total_rings, max_vfs, rings_per_vf;
break;
}
- if (max_rings <= num_present_cpus())
- num_pf_rings = 1;
+ if (oct->sriov_info.num_pf_rings)
+ num_pf_rings = oct->sriov_info.num_pf_rings;
else
num_pf_rings = num_present_cpus();
void cn23xx_dump_pf_initialized_regs(struct octeon_device *oct);
+int cn23xx_sriov_config(struct octeon_device *oct);
+
int cn23xx_fw_loaded(struct octeon_device *oct);
void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx,
/* OOM task polling interval */
#define LIO_OOM_POLL_INTERVAL_MS 250
+#define OCTNIC_MAX_SG MAX_SKB_FRAGS
+
+/**
+ * \brief Callback for getting interface configuration
+ * @param status status of request
+ * @param buf pointer to resp structure
+ */
+void lio_if_cfg_callback(struct octeon_device *oct,
+ u32 status __attribute__((unused)), void *buf)
+{
+ struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
+ struct liquidio_if_cfg_context *ctx;
+ struct liquidio_if_cfg_resp *resp;
+
+ resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
+ ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
+
+ oct = lio_get_device(ctx->octeon_id);
+ if (resp->status)
+ dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
+ CVM_CAST64(resp->status));
+ WRITE_ONCE(ctx->cond, 1);
+
+ snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
+ resp->cfg_info.liquidio_firmware_version);
+
+ /* This barrier is required to be sure that the response has been
+ * written fully before waking up the handler
+ */
+ wmb();
+
+ wake_up_interruptible(&ctx->wc);
+}
+
+/**
+ * \brief Delete gather lists
+ * @param lio per-network private data
+ */
+void lio_delete_glists(struct lio *lio)
+{
+ struct octnic_gather *g;
+ int i;
+
+ kfree(lio->glist_lock);
+ lio->glist_lock = NULL;
+
+ if (!lio->glist)
+ return;
+
+ for (i = 0; i < lio->oct_dev->num_iqs; i++) {
+ do {
+ g = (struct octnic_gather *)
+ lio_list_delete_head(&lio->glist[i]);
+ kfree(g);
+ } while (g);
+
+ if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+ lio->glists_dma_base && lio->glists_dma_base[i]) {
+ lio_dma_free(lio->oct_dev,
+ lio->glist_entry_size * lio->tx_qsize,
+ lio->glists_virt_base[i],
+ lio->glists_dma_base[i]);
+ }
+ }
+
+ kfree(lio->glists_virt_base);
+ lio->glists_virt_base = NULL;
+
+ kfree(lio->glists_dma_base);
+ lio->glists_dma_base = NULL;
+
+ kfree(lio->glist);
+ lio->glist = NULL;
+}
+
+/**
+ * \brief Setup gather lists
+ * @param lio per-network private data
+ */
+int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
+{
+ struct octnic_gather *g;
+ int i, j;
+
+ lio->glist_lock =
+ kcalloc(num_iqs, sizeof(*lio->glist_lock), GFP_KERNEL);
+ if (!lio->glist_lock)
+ return -ENOMEM;
+
+ lio->glist =
+ kcalloc(num_iqs, sizeof(*lio->glist), GFP_KERNEL);
+ if (!lio->glist) {
+ kfree(lio->glist_lock);
+ lio->glist_lock = NULL;
+ return -ENOMEM;
+ }
+
+ lio->glist_entry_size =
+ ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+ /* allocate memory to store virtual and dma base address of
+ * per glist consistent memory
+ */
+ lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+ GFP_KERNEL);
+ lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+ GFP_KERNEL);
+
+ if (!lio->glists_virt_base || !lio->glists_dma_base) {
+ lio_delete_glists(lio);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < num_iqs; i++) {
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
+
+ spin_lock_init(&lio->glist_lock[i]);
+
+ INIT_LIST_HEAD(&lio->glist[i]);
+
+ lio->glists_virt_base[i] =
+ lio_dma_alloc(oct,
+ lio->glist_entry_size * lio->tx_qsize,
+ &lio->glists_dma_base[i]);
+
+ if (!lio->glists_virt_base[i]) {
+ lio_delete_glists(lio);
+ return -ENOMEM;
+ }
+
+ for (j = 0; j < lio->tx_qsize; j++) {
+ g = kzalloc_node(sizeof(*g), GFP_KERNEL,
+ numa_node);
+ if (!g)
+ g = kzalloc(sizeof(*g), GFP_KERNEL);
+ if (!g)
+ break;
+
+ g->sg = lio->glists_virt_base[i] +
+ (j * lio->glist_entry_size);
+
+ g->sg_dma_ptr = lio->glists_dma_base[i] +
+ (j * lio->glist_entry_size);
+
+ list_add_tail(&g->list, &lio->glist[i]);
+ }
+
+ if (j != lio->tx_qsize) {
+ lio_delete_glists(lio);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
{
struct lio *lio = GET_LIO(netdev);
int num_ioq_vectors;
int irqret, err;
- oct->num_msix_irqs = num_ioqs;
if (oct->msix_on) {
+ oct->num_msix_irqs = num_ioqs;
if (OCTEON_CN23XX_PF(oct)) {
num_interrupts = MAX_IOQ_INTERRUPTS_PER_PF + 1;
return pending_pkts;
}
+
+static void
+octnet_nic_stats_callback(struct octeon_device *oct_dev,
+ u32 status, void *ptr)
+{
+ struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
+ struct oct_nic_stats_resp *resp =
+ (struct oct_nic_stats_resp *)sc->virtrptr;
+ struct oct_nic_stats_ctrl *ctrl =
+ (struct oct_nic_stats_ctrl *)sc->ctxptr;
+ struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire;
+ struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost;
+ struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire;
+ struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost;
+
+ if (status != OCTEON_REQUEST_TIMEOUT && !resp->status) {
+ octeon_swap_8B_data((u64 *)&resp->stats,
+ (sizeof(struct oct_link_stats)) >> 3);
+
+ /* RX link-level stats */
+ rstats->total_rcvd = rsp_rstats->total_rcvd;
+ rstats->bytes_rcvd = rsp_rstats->bytes_rcvd;
+ rstats->total_bcst = rsp_rstats->total_bcst;
+ rstats->total_mcst = rsp_rstats->total_mcst;
+ rstats->runts = rsp_rstats->runts;
+ rstats->ctl_rcvd = rsp_rstats->ctl_rcvd;
+ /* Accounts for over/under-run of buffers */
+ rstats->fifo_err = rsp_rstats->fifo_err;
+ rstats->dmac_drop = rsp_rstats->dmac_drop;
+ rstats->fcs_err = rsp_rstats->fcs_err;
+ rstats->jabber_err = rsp_rstats->jabber_err;
+ rstats->l2_err = rsp_rstats->l2_err;
+ rstats->frame_err = rsp_rstats->frame_err;
+ rstats->red_drops = rsp_rstats->red_drops;
+
+ /* RX firmware stats */
+ rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd;
+ rstats->fw_total_fwd = rsp_rstats->fw_total_fwd;
+ rstats->fw_total_mcast = rsp_rstats->fw_total_mcast;
+ rstats->fw_total_bcast = rsp_rstats->fw_total_bcast;
+ rstats->fw_err_pko = rsp_rstats->fw_err_pko;
+ rstats->fw_err_link = rsp_rstats->fw_err_link;
+ rstats->fw_err_drop = rsp_rstats->fw_err_drop;
+ rstats->fw_rx_vxlan = rsp_rstats->fw_rx_vxlan;
+ rstats->fw_rx_vxlan_err = rsp_rstats->fw_rx_vxlan_err;
+
+ /* Number of packets that are LROed */
+ rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts;
+ /* Number of octets that are LROed */
+ rstats->fw_lro_octs = rsp_rstats->fw_lro_octs;
+ /* Number of LRO packets formed */
+ rstats->fw_total_lro = rsp_rstats->fw_total_lro;
+ /* Number of times lRO of packet aborted */
+ rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts;
+ rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port;
+ rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq;
+ rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval;
+ rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer;
+ /* intrmod: packet forward rate */
+ rstats->fwd_rate = rsp_rstats->fwd_rate;
+
+ /* TX link-level stats */
+ tstats->total_pkts_sent = rsp_tstats->total_pkts_sent;
+ tstats->total_bytes_sent = rsp_tstats->total_bytes_sent;
+ tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent;
+ tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent;
+ tstats->ctl_sent = rsp_tstats->ctl_sent;
+ /* Packets sent after one collision*/
+ tstats->one_collision_sent = rsp_tstats->one_collision_sent;
+ /* Packets sent after multiple collision*/
+ tstats->multi_collision_sent = rsp_tstats->multi_collision_sent;
+ /* Packets not sent due to max collisions */
+ tstats->max_collision_fail = rsp_tstats->max_collision_fail;
+ /* Packets not sent due to max deferrals */
+ tstats->max_deferral_fail = rsp_tstats->max_deferral_fail;
+ /* Accounts for over/under-run of buffers */
+ tstats->fifo_err = rsp_tstats->fifo_err;
+ tstats->runts = rsp_tstats->runts;
+ /* Total number of collisions detected */
+ tstats->total_collisions = rsp_tstats->total_collisions;
+
+ /* firmware stats */
+ tstats->fw_total_sent = rsp_tstats->fw_total_sent;
+ tstats->fw_total_fwd = rsp_tstats->fw_total_fwd;
+ tstats->fw_total_mcast_sent = rsp_tstats->fw_total_mcast_sent;
+ tstats->fw_total_bcast_sent = rsp_tstats->fw_total_bcast_sent;
+ tstats->fw_err_pko = rsp_tstats->fw_err_pko;
+ tstats->fw_err_pki = rsp_tstats->fw_err_pki;
+ tstats->fw_err_link = rsp_tstats->fw_err_link;
+ tstats->fw_err_drop = rsp_tstats->fw_err_drop;
+ tstats->fw_tso = rsp_tstats->fw_tso;
+ tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd;
+ tstats->fw_err_tso = rsp_tstats->fw_err_tso;
+ tstats->fw_tx_vxlan = rsp_tstats->fw_tx_vxlan;
+
+ resp->status = 1;
+ } else {
+ resp->status = -1;
+ }
+ complete(&ctrl->complete);
+}
+
+int octnet_get_link_stats(struct net_device *netdev)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct_dev = lio->oct_dev;
+ struct octeon_soft_command *sc;
+ struct oct_nic_stats_ctrl *ctrl;
+ struct oct_nic_stats_resp *resp;
+ int retval;
+
+ /* Alloc soft command */
+ sc = (struct octeon_soft_command *)
+ octeon_alloc_soft_command(oct_dev,
+ 0,
+ sizeof(struct oct_nic_stats_resp),
+ sizeof(struct octnic_ctrl_pkt));
+
+ if (!sc)
+ return -ENOMEM;
+
+ resp = (struct oct_nic_stats_resp *)sc->virtrptr;
+ memset(resp, 0, sizeof(struct oct_nic_stats_resp));
+
+ ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr;
+ memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl));
+ ctrl->netdev = netdev;
+ init_completion(&ctrl->complete);
+
+ sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+ octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+ OPCODE_NIC_PORT_STATS, 0, 0, 0);
+
+ sc->callback = octnet_nic_stats_callback;
+ sc->callback_arg = sc;
+ sc->wait_time = 500; /*in milli seconds*/
+
+ retval = octeon_send_soft_command(oct_dev, sc);
+ if (retval == IQ_SEND_FAILED) {
+ octeon_free_soft_command(oct_dev, sc);
+ return -EINVAL;
+ }
+
+ wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000));
+
+ if (resp->status != 1) {
+ octeon_free_soft_command(oct_dev, sc);
+
+ return -EINVAL;
+ }
+
+ octeon_free_soft_command(oct_dev, sc);
+
+ return 0;
+}
+
+static void liquidio_nic_seapi_ctl_callback(struct octeon_device *oct,
+ u32 status,
+ void *buf)
+{
+ struct liquidio_nic_seapi_ctl_context *ctx;
+ struct octeon_soft_command *sc = buf;
+
+ ctx = sc->ctxptr;
+
+ oct = lio_get_device(ctx->octeon_id);
+ if (status) {
+ dev_err(&oct->pci_dev->dev, "%s: instruction failed. Status: %llx\n",
+ __func__,
+ CVM_CAST64(status));
+ }
+ ctx->status = status;
+ complete(&ctx->complete);
+}
+
+int liquidio_set_speed(struct lio *lio, int speed)
+{
+ struct liquidio_nic_seapi_ctl_context *ctx;
+ struct octeon_device *oct = lio->oct_dev;
+ struct oct_nic_seapi_resp *resp;
+ struct octeon_soft_command *sc;
+ union octnet_cmd *ncmd;
+ u32 ctx_size;
+ int retval;
+ u32 var;
+
+ if (oct->speed_setting == speed)
+ return 0;
+
+ if (!OCTEON_CN23XX_PF(oct)) {
+ dev_err(&oct->pci_dev->dev, "%s: SET SPEED only for PF\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+
+ ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context);
+ sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
+ sizeof(struct oct_nic_seapi_resp),
+ ctx_size);
+ if (!sc)
+ return -ENOMEM;
+
+ ncmd = sc->virtdptr;
+ ctx = sc->ctxptr;
+ resp = sc->virtrptr;
+ memset(resp, 0, sizeof(struct oct_nic_seapi_resp));
+
+ ctx->octeon_id = lio_get_device_id(oct);
+ ctx->status = 0;
+ init_completion(&ctx->complete);
+
+ ncmd->u64 = 0;
+ ncmd->s.cmd = SEAPI_CMD_SPEED_SET;
+ ncmd->s.param1 = speed;
+
+ octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3));
+
+ sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+ octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
+ OPCODE_NIC_UBOOT_CTL, 0, 0, 0);
+
+ sc->callback = liquidio_nic_seapi_ctl_callback;
+ sc->callback_arg = sc;
+ sc->wait_time = 5000;
+
+ retval = octeon_send_soft_command(oct, sc);
+ if (retval == IQ_SEND_FAILED) {
+ dev_info(&oct->pci_dev->dev, "Failed to send soft command\n");
+ retval = -EBUSY;
+ } else {
+ /* Wait for response or timeout */
+ if (wait_for_completion_timeout(&ctx->complete,
+ msecs_to_jiffies(10000)) == 0) {
+ dev_err(&oct->pci_dev->dev, "%s: sc timeout\n",
+ __func__);
+ octeon_free_soft_command(oct, sc);
+ return -EINTR;
+ }
+
+ retval = resp->status;
+
+ if (retval) {
+ dev_err(&oct->pci_dev->dev, "%s failed, retval=%d\n",
+ __func__, retval);
+ octeon_free_soft_command(oct, sc);
+ return -EIO;
+ }
+
+ var = be32_to_cpu((__force __be32)resp->speed);
+ if (var != speed) {
+ dev_err(&oct->pci_dev->dev,
+ "%s: setting failed speed= %x, expect %x\n",
+ __func__, var, speed);
+ }
+
+ oct->speed_setting = var;
+ }
+
+ octeon_free_soft_command(oct, sc);
+
+ return retval;
+}
+
+int liquidio_get_speed(struct lio *lio)
+{
+ struct liquidio_nic_seapi_ctl_context *ctx;
+ struct octeon_device *oct = lio->oct_dev;
+ struct oct_nic_seapi_resp *resp;
+ struct octeon_soft_command *sc;
+ union octnet_cmd *ncmd;
+ u32 ctx_size;
+ int retval;
+
+ ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context);
+ sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
+ sizeof(struct oct_nic_seapi_resp),
+ ctx_size);
+ if (!sc)
+ return -ENOMEM;
+
+ ncmd = sc->virtdptr;
+ ctx = sc->ctxptr;
+ resp = sc->virtrptr;
+ memset(resp, 0, sizeof(struct oct_nic_seapi_resp));
+
+ ctx->octeon_id = lio_get_device_id(oct);
+ ctx->status = 0;
+ init_completion(&ctx->complete);
+
+ ncmd->u64 = 0;
+ ncmd->s.cmd = SEAPI_CMD_SPEED_GET;
+
+ octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3));
+
+ sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+ octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
+ OPCODE_NIC_UBOOT_CTL, 0, 0, 0);
+
+ sc->callback = liquidio_nic_seapi_ctl_callback;
+ sc->callback_arg = sc;
+ sc->wait_time = 5000;
+
+ retval = octeon_send_soft_command(oct, sc);
+ if (retval == IQ_SEND_FAILED) {
+ dev_info(&oct->pci_dev->dev, "Failed to send soft command\n");
+ oct->no_speed_setting = 1;
+ oct->speed_setting = 25;
+
+ retval = -EBUSY;
+ } else {
+ if (wait_for_completion_timeout(&ctx->complete,
+ msecs_to_jiffies(10000)) == 0) {
+ dev_err(&oct->pci_dev->dev, "%s: sc timeout\n",
+ __func__);
+
+ oct->speed_setting = 25;
+ oct->no_speed_setting = 1;
+
+ octeon_free_soft_command(oct, sc);
+
+ return -EINTR;
+ }
+ retval = resp->status;
+ if (retval) {
+ dev_err(&oct->pci_dev->dev,
+ "%s failed retval=%d\n", __func__, retval);
+ oct->no_speed_setting = 1;
+ oct->speed_setting = 25;
+ octeon_free_soft_command(oct, sc);
+ retval = -EIO;
+ } else {
+ u32 var;
+
+ var = be32_to_cpu((__force __be32)resp->speed);
+ oct->speed_setting = var;
+ if (var == 0xffff) {
+ oct->no_speed_setting = 1;
+ /* unable to access boot variables
+ * get the default value based on the NIC type
+ */
+ oct->speed_setting = 25;
+ }
+ }
+ }
+
+ octeon_free_soft_command(oct, sc);
+
+ return retval;
+}
#include "cn23xx_vf_device.h"
static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs);
-static int octnet_get_link_stats(struct net_device *netdev);
struct oct_intrmod_context {
int octeon_id;
"tx_tso_err",
"tx_vxlan",
+ "tx_mcast",
+ "tx_bcast",
+
"mac_tx_total_pkts",
"mac_tx_total_bytes",
"mac_tx_mcast_pkts",
"mac_tx_ctl_packets",
"mac_tx_total_collisions",
"mac_tx_one_collision",
- "mac_tx_multi_collison",
+ "mac_tx_multi_collision",
"mac_tx_max_collision_fail",
"mac_tx_max_deferal_fail",
"mac_tx_fifo_err",
"rx_total_rcvd",
"rx_total_fwd",
+ "rx_mcast",
+ "rx_bcast",
"rx_jabber_err",
"rx_l2_err",
"rx_frame_err",
"tx_errors",
"rx_dropped",
"tx_dropped",
+ "rx_mcast",
+ "tx_mcast",
+ "rx_bcast",
+ "tx_bcast",
"link_state_changes",
};
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct oct_link_info *linfo;
- u32 supported = 0, advertising = 0;
linfo = &lio->linfo;
+ ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+ ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+
switch (linfo->link.s.phy_type) {
case LIO_PHY_PORT_TP:
ecmd->base.port = PORT_TP;
- supported = (SUPPORTED_10000baseT_Full |
- SUPPORTED_TP | SUPPORTED_Pause);
- advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause);
ecmd->base.autoneg = AUTONEG_DISABLE;
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, Pause);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported,
+ 10000baseT_Full);
+
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising, Pause);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+ 10000baseT_Full);
+
break;
case LIO_PHY_PORT_FIBRE:
- ecmd->base.port = PORT_FIBRE;
-
- if (linfo->link.s.speed == SPEED_10000) {
- supported = SUPPORTED_10000baseT_Full;
- advertising = ADVERTISED_10000baseT_Full;
+ if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
+ linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+ linfo->link.s.if_mode == INTERFACE_MODE_XLAUI ||
+ linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
+ dev_dbg(&oct->pci_dev->dev, "ecmd->base.transceiver is XCVR_EXTERNAL\n");
+ } else {
+ dev_err(&oct->pci_dev->dev, "Unknown link interface mode: %d\n",
+ linfo->link.s.if_mode);
}
- supported |= SUPPORTED_FIBRE | SUPPORTED_Pause;
- advertising |= ADVERTISED_Pause;
+ ecmd->base.port = PORT_FIBRE;
ecmd->base.autoneg = AUTONEG_DISABLE;
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, Pause);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising, Pause);
+ if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
+ oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) {
+ if (OCTEON_CN23XX_PF(oct)) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported, 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported, 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported, 25000baseCR_Full);
+
+ if (oct->no_speed_setting == 0) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseCR_Full);
+ }
+
+ if (oct->no_speed_setting == 0)
+ liquidio_get_speed(lio);
+ else
+ oct->speed_setting = 25;
+
+ if (oct->speed_setting == 10) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseCR_Full);
+ }
+ if (oct->speed_setting == 25) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseCR_Full);
+ }
+ } else { /* VF */
+ if (linfo->link.s.speed == 10000) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 10000baseCR_Full);
+
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 10000baseCR_Full);
+ }
+
+ if (linfo->link.s.speed == 25000) {
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, supported,
+ 25000baseCR_Full);
+
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode
+ (ecmd, advertising,
+ 25000baseCR_Full);
+ }
+ }
+ } else {
+ ethtool_link_ksettings_add_link_mode(ecmd, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+ 10000baseT_Full);
+ }
break;
}
- if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
- linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
- linfo->link.s.if_mode == INTERFACE_MODE_XLAUI ||
- linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
- ethtool_convert_legacy_u32_to_link_mode(
- ecmd->link_modes.supported, supported);
- ethtool_convert_legacy_u32_to_link_mode(
- ecmd->link_modes.advertising, advertising);
- } else {
- dev_err(&oct->pci_dev->dev, "Unknown link interface reported %d\n",
- linfo->link.s.if_mode);
- }
-
if (linfo->link.s.link_up) {
ecmd->base.speed = linfo->link.s.speed;
ecmd->base.duplex = linfo->link.s.duplex;
return 0;
}
+static int lio_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *ecmd)
+{
+ const int speed = ecmd->base.speed;
+ struct lio *lio = GET_LIO(netdev);
+ struct oct_link_info *linfo;
+ struct octeon_device *oct;
+ u32 is25G = 0;
+
+ oct = lio->oct_dev;
+
+ linfo = &lio->linfo;
+
+ if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
+ oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) {
+ is25G = 1;
+ } else {
+ return -EOPNOTSUPP;
+ }
+
+ if (oct->no_speed_setting) {
+ dev_err(&oct->pci_dev->dev, "%s: Changing speed is not supported\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+
+ if ((ecmd->base.duplex != DUPLEX_UNKNOWN &&
+ ecmd->base.duplex != linfo->link.s.duplex) ||
+ ecmd->base.autoneg != AUTONEG_DISABLE ||
+ (ecmd->base.speed != 10000 && ecmd->base.speed != 25000 &&
+ ecmd->base.speed != SPEED_UNKNOWN))
+ return -EOPNOTSUPP;
+
+ if ((oct->speed_boot == speed / 1000) &&
+ oct->speed_boot == oct->speed_setting)
+ return 0;
+
+ liquidio_set_speed(lio, speed / 1000);
+
+ dev_dbg(&oct->pci_dev->dev, "Port speed is set to %dG\n",
+ oct->speed_setting);
+
+ return 0;
+}
+
static void
lio_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
{
rx_count = CFG_GET_NUM_RXQS_NIC_IF(conf6x, lio->ifidx);
tx_count = CFG_GET_NUM_TXQS_NIC_IF(conf6x, lio->ifidx);
} else if (OCTEON_CN23XX_PF(oct)) {
- max_combined = lio->linfo.num_txpciq;
+ if (oct->sriov_info.sriov_enabled) {
+ max_combined = lio->linfo.num_txpciq;
+ } else {
+ struct octeon_config *conf23_pf =
+ CHIP_CONF(oct, cn23xx_pf);
+
+ max_combined = CFG_GET_IQ_MAX_Q(conf23_pf);
+ }
combined_count = oct->num_iqs;
} else if (OCTEON_CN23XX_VF(oct)) {
u64 reg_val = 0ULL;
kfree(oct->irq_name_storage);
oct->irq_name_storage = NULL;
+
+ if (octeon_allocate_ioq_vector(oct, num_ioqs)) {
+ dev_err(&oct->pci_dev->dev, "OCTEON: ioq vector allocation failed\n");
+ return -1;
+ }
+
if (octeon_setup_interrupt(oct, num_ioqs)) {
dev_info(&oct->pci_dev->dev, "Setup interrupt failed\n");
- return 1;
+ return -1;
}
/* Enable Octeon device interrupts */
combined_count = channel->combined_count;
if (OCTEON_CN23XX_PF(oct)) {
- max_combined = channel->max_combined;
+ if (oct->sriov_info.sriov_enabled) {
+ max_combined = lio->linfo.num_txpciq;
+ } else {
+ struct octeon_config *conf23_pf =
+ CHIP_CONF(oct,
+ cn23xx_pf);
+
+ max_combined =
+ CFG_GET_IQ_MAX_Q(conf23_pf);
+ }
} else if (OCTEON_CN23XX_VF(oct)) {
u64 reg_val = 0ULL;
u64 ctrl = CN23XX_VF_SLI_IQ_PKT_CONTROL64(0);
if (lio_reset_queues(dev, combined_count))
return -EINVAL;
- lio_irq_reallocate_irqs(oct, combined_count);
if (stopped)
dev->netdev_ops->ndo_open(dev);
ering->rx_jumbo_max_pending = 0;
}
+static int lio_23xx_reconfigure_queue_count(struct lio *lio)
+{
+ struct octeon_device *oct = lio->oct_dev;
+ struct liquidio_if_cfg_context *ctx;
+ u32 resp_size, ctx_size, data_size;
+ struct liquidio_if_cfg_resp *resp;
+ struct octeon_soft_command *sc;
+ union oct_nic_if_cfg if_cfg;
+ struct lio_version *vdata;
+ u32 ifidx_or_pfnum;
+ int retval;
+ int j;
+
+ resp_size = sizeof(struct liquidio_if_cfg_resp);
+ ctx_size = sizeof(struct liquidio_if_cfg_context);
+ data_size = sizeof(struct lio_version);
+ sc = (struct octeon_soft_command *)
+ octeon_alloc_soft_command(oct, data_size,
+ resp_size, ctx_size);
+ if (!sc) {
+ dev_err(&oct->pci_dev->dev, "%s: Failed to allocate soft command\n",
+ __func__);
+ return -1;
+ }
+
+ resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
+ ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
+ vdata = (struct lio_version *)sc->virtdptr;
+
+ vdata->major = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MAJOR_VERSION);
+ vdata->minor = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MINOR_VERSION);
+ vdata->micro = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION);
+
+ ifidx_or_pfnum = oct->pf_num;
+ WRITE_ONCE(ctx->cond, 0);
+ ctx->octeon_id = lio_get_device_id(oct);
+ init_waitqueue_head(&ctx->wc);
+
+ if_cfg.u64 = 0;
+ if_cfg.s.num_iqueues = oct->sriov_info.num_pf_rings;
+ if_cfg.s.num_oqueues = oct->sriov_info.num_pf_rings;
+ if_cfg.s.base_queue = oct->sriov_info.pf_srn;
+ if_cfg.s.gmx_port_id = oct->pf_num;
+
+ sc->iq_no = 0;
+ octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
+ OPCODE_NIC_QCOUNT_UPDATE, 0,
+ if_cfg.u64, 0);
+ sc->callback = lio_if_cfg_callback;
+ sc->callback_arg = sc;
+ sc->wait_time = LIO_IFCFG_WAIT_TIME;
+
+ retval = octeon_send_soft_command(oct, sc);
+ if (retval == IQ_SEND_FAILED) {
+ dev_err(&oct->pci_dev->dev,
+ "iq/oq config failed status: %x\n",
+ retval);
+ goto qcount_update_fail;
+ }
+
+ if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
+ dev_err(&oct->pci_dev->dev, "Wait interrupted\n");
+ return -1;
+ }
+
+ retval = resp->status;
+ if (retval) {
+ dev_err(&oct->pci_dev->dev, "iq/oq config failed\n");
+ goto qcount_update_fail;
+ }
+
+ octeon_swap_8B_data((u64 *)(&resp->cfg_info),
+ (sizeof(struct liquidio_if_cfg_info)) >> 3);
+
+ lio->ifidx = ifidx_or_pfnum;
+ lio->linfo.num_rxpciq = hweight64(resp->cfg_info.iqmask);
+ lio->linfo.num_txpciq = hweight64(resp->cfg_info.iqmask);
+ for (j = 0; j < lio->linfo.num_rxpciq; j++) {
+ lio->linfo.rxpciq[j].u64 =
+ resp->cfg_info.linfo.rxpciq[j].u64;
+ }
+
+ for (j = 0; j < lio->linfo.num_txpciq; j++) {
+ lio->linfo.txpciq[j].u64 =
+ resp->cfg_info.linfo.txpciq[j].u64;
+ }
+
+ lio->linfo.hw_addr = resp->cfg_info.linfo.hw_addr;
+ lio->linfo.gmxport = resp->cfg_info.linfo.gmxport;
+ lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64;
+ lio->txq = lio->linfo.txpciq[0].s.q_no;
+ lio->rxq = lio->linfo.rxpciq[0].s.q_no;
+
+ octeon_free_soft_command(oct, sc);
+ dev_info(&oct->pci_dev->dev, "Queue count updated to %d\n",
+ lio->linfo.num_rxpciq);
+
+ return 0;
+
+qcount_update_fail:
+ octeon_free_soft_command(oct, sc);
+
+ return -1;
+}
+
static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs)
{
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
+ int i, queue_count_update = 0;
struct napi_struct *napi, *n;
- int i, update = 0;
+ int ret;
+
+ schedule_timeout_uninterruptible(msecs_to_jiffies(100));
if (wait_for_pending_requests(oct))
dev_err(&oct->pci_dev->dev, "There were pending requests\n");
dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
if (octeon_set_io_queues_off(oct)) {
- dev_err(&oct->pci_dev->dev, "setting io queues off failed\n");
+ dev_err(&oct->pci_dev->dev, "Setting io queues off failed\n");
return -1;
}
netif_napi_del(napi);
if (num_qs != oct->num_iqs) {
- netif_set_real_num_rx_queues(netdev, num_qs);
- netif_set_real_num_tx_queues(netdev, num_qs);
- update = 1;
+ ret = netif_set_real_num_rx_queues(netdev, num_qs);
+ if (ret) {
+ dev_err(&oct->pci_dev->dev,
+ "Setting real number rx failed\n");
+ return ret;
+ }
+
+ ret = netif_set_real_num_tx_queues(netdev, num_qs);
+ if (ret) {
+ dev_err(&oct->pci_dev->dev,
+ "Setting real number tx failed\n");
+ return ret;
+ }
+
+ /* The value of queue_count_update decides whether it is the
+ * queue count or the descriptor count that is being
+ * re-configured.
+ */
+ queue_count_update = 1;
+ }
+
+ /* Re-configuration of queues can happen in two scenarios, SRIOV enabled
+ * and SRIOV disabled. Few things like recreating queue zero, resetting
+ * glists and IRQs are required for both. For the latter, some more
+ * steps like updating sriov_info for the octeon device need to be done.
+ */
+ if (queue_count_update) {
+ lio_delete_glists(lio);
+
+ /* Delete mbox for PF which is SRIOV disabled because sriov_info
+ * will be now changed.
+ */
+ if ((OCTEON_CN23XX_PF(oct)) && !oct->sriov_info.sriov_enabled)
+ oct->fn_list.free_mbox(oct);
}
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
octeon_delete_instr_queue(oct, i);
}
+ if (queue_count_update) {
+ /* For PF re-configure sriov related information */
+ if ((OCTEON_CN23XX_PF(oct)) &&
+ !oct->sriov_info.sriov_enabled) {
+ oct->sriov_info.num_pf_rings = num_qs;
+ if (cn23xx_sriov_config(oct)) {
+ dev_err(&oct->pci_dev->dev,
+ "Queue reset aborted: SRIOV config failed\n");
+ return -1;
+ }
+
+ num_qs = oct->sriov_info.num_pf_rings;
+ }
+ }
+
if (oct->fn_list.setup_device_regs(oct)) {
dev_err(&oct->pci_dev->dev, "Failed to configure device registers\n");
return -1;
}
- if (liquidio_setup_io_queues(oct, 0, num_qs, num_qs)) {
- dev_err(&oct->pci_dev->dev, "IO queues initialization failed\n");
- return -1;
+ /* The following are needed in case of queue count re-configuration and
+ * not for descriptor count re-configuration.
+ */
+ if (queue_count_update) {
+ if (octeon_setup_instr_queues(oct))
+ return -1;
+
+ if (octeon_setup_output_queues(oct))
+ return -1;
+
+ /* Recreating mbox for PF that is SRIOV disabled */
+ if (OCTEON_CN23XX_PF(oct) && !oct->sriov_info.sriov_enabled) {
+ if (oct->fn_list.setup_mbox(oct)) {
+ dev_err(&oct->pci_dev->dev, "Mailbox setup failed\n");
+ return -1;
+ }
+ }
+
+ /* Deleting and recreating IRQs whether the interface is SRIOV
+ * enabled or disabled.
+ */
+ if (lio_irq_reallocate_irqs(oct, num_qs)) {
+ dev_err(&oct->pci_dev->dev, "IRQs could not be allocated\n");
+ return -1;
+ }
+
+ /* Enable the input and output queues for this Octeon device */
+ if (oct->fn_list.enable_io_queues(oct)) {
+ dev_err(&oct->pci_dev->dev, "Failed to enable input/output queues\n");
+ return -1;
+ }
+
+ for (i = 0; i < oct->num_oqs; i++)
+ writel(oct->droq[i]->max_count,
+ oct->droq[i]->pkts_credit_reg);
+
+ /* Informing firmware about the new queue count. It is required
+ * for firmware to allocate more number of queues than those at
+ * load time.
+ */
+ if (OCTEON_CN23XX_PF(oct) && !oct->sriov_info.sriov_enabled) {
+ if (lio_23xx_reconfigure_queue_count(lio))
+ return -1;
+ }
}
- /* Enable the input and output queues for this Octeon device */
- if (oct->fn_list.enable_io_queues(oct)) {
- dev_err(&oct->pci_dev->dev, "Failed to enable input/output queues");
+ /* Once firmware is aware of the new value, queues can be recreated */
+ if (liquidio_setup_io_queues(oct, 0, num_qs, num_qs)) {
+ dev_err(&oct->pci_dev->dev, "I/O queues creation failed\n");
return -1;
}
- if (update && lio_send_queue_count_update(netdev, num_qs))
- return -1;
+ if (queue_count_update) {
+ if (lio_setup_glists(oct, lio, num_qs)) {
+ dev_err(&oct->pci_dev->dev, "Gather list allocation failed\n");
+ return -1;
+ }
+
+ /* Send firmware the information about new number of queues
+ * if the interface is a VF or a PF that is SRIOV enabled.
+ */
+ if (oct->sriov_info.sriov_enabled || OCTEON_CN23XX_VF(oct))
+ if (lio_send_queue_count_update(netdev, num_qs))
+ return -1;
+ }
return 0;
}
CFG_SET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx,
rx_count);
- if (lio_reset_queues(netdev, lio->linfo.num_txpciq))
+ if (lio_reset_queues(netdev, oct->num_iqs))
goto err_lio_reset_queues;
if (stopped)
{
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct_dev = lio->oct_dev;
- struct net_device_stats *netstats = &netdev->stats;
+ struct rtnl_link_stats64 lstats;
int i = 0, j;
if (ifstate_check(lio, LIO_IFSTATE_RESETTING))
return;
- netdev->netdev_ops->ndo_get_stats(netdev);
- octnet_get_link_stats(netdev);
-
+ netdev->netdev_ops->ndo_get_stats64(netdev, &lstats);
/*sum of oct->droq[oq_no]->stats->rx_pkts_received */
- data[i++] = CVM_CAST64(netstats->rx_packets);
+ data[i++] = lstats.rx_packets;
/*sum of oct->instr_queue[iq_no]->stats.tx_done */
- data[i++] = CVM_CAST64(netstats->tx_packets);
+ data[i++] = lstats.tx_packets;
/*sum of oct->droq[oq_no]->stats->rx_bytes_received */
- data[i++] = CVM_CAST64(netstats->rx_bytes);
+ data[i++] = lstats.rx_bytes;
/*sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */
- data[i++] = CVM_CAST64(netstats->tx_bytes);
- data[i++] = CVM_CAST64(netstats->rx_errors +
- oct_dev->link_stats.fromwire.fcs_err +
- oct_dev->link_stats.fromwire.jabber_err +
- oct_dev->link_stats.fromwire.l2_err +
- oct_dev->link_stats.fromwire.frame_err);
- data[i++] = CVM_CAST64(netstats->tx_errors);
+ data[i++] = lstats.tx_bytes;
+ data[i++] = lstats.rx_errors +
+ oct_dev->link_stats.fromwire.fcs_err +
+ oct_dev->link_stats.fromwire.jabber_err +
+ oct_dev->link_stats.fromwire.l2_err +
+ oct_dev->link_stats.fromwire.frame_err;
+ data[i++] = lstats.tx_errors;
/*sum of oct->droq[oq_no]->stats->rx_dropped +
*oct->droq[oq_no]->stats->dropped_nodispatch +
*oct->droq[oq_no]->stats->dropped_toomany +
*oct->droq[oq_no]->stats->dropped_nomem
*/
- data[i++] = CVM_CAST64(netstats->rx_dropped +
- oct_dev->link_stats.fromwire.fifo_err +
- oct_dev->link_stats.fromwire.dmac_drop +
- oct_dev->link_stats.fromwire.red_drops +
- oct_dev->link_stats.fromwire.fw_err_pko +
- oct_dev->link_stats.fromwire.fw_err_link +
- oct_dev->link_stats.fromwire.fw_err_drop);
+ data[i++] = lstats.rx_dropped +
+ oct_dev->link_stats.fromwire.fifo_err +
+ oct_dev->link_stats.fromwire.dmac_drop +
+ oct_dev->link_stats.fromwire.red_drops +
+ oct_dev->link_stats.fromwire.fw_err_pko +
+ oct_dev->link_stats.fromwire.fw_err_link +
+ oct_dev->link_stats.fromwire.fw_err_drop;
/*sum of oct->instr_queue[iq_no]->stats.tx_dropped */
- data[i++] = CVM_CAST64(netstats->tx_dropped +
- oct_dev->link_stats.fromhost.max_collision_fail +
- oct_dev->link_stats.fromhost.max_deferral_fail +
- oct_dev->link_stats.fromhost.total_collisions +
- oct_dev->link_stats.fromhost.fw_err_pko +
- oct_dev->link_stats.fromhost.fw_err_link +
- oct_dev->link_stats.fromhost.fw_err_drop +
- oct_dev->link_stats.fromhost.fw_err_pki);
+ data[i++] = lstats.tx_dropped +
+ oct_dev->link_stats.fromhost.max_collision_fail +
+ oct_dev->link_stats.fromhost.max_deferral_fail +
+ oct_dev->link_stats.fromhost.total_collisions +
+ oct_dev->link_stats.fromhost.fw_err_pko +
+ oct_dev->link_stats.fromhost.fw_err_link +
+ oct_dev->link_stats.fromhost.fw_err_drop +
+ oct_dev->link_stats.fromhost.fw_err_pki;
/* firmware tx stats */
/*per_core_stats[cvmx_get_core_num()].link_stats[mdata->from_ifidx].
*/
data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tx_vxlan);
+ /* Multicast packets sent by this port */
+ data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent;
+ data[i++] = oct_dev->link_stats.fromhost.fw_total_bcast_sent;
+
/* mac tx statistics */
/*CVMX_BGXX_CMRX_TX_STAT5 */
data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_pkts_sent);
*fw_total_fwd
*/
data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_fwd);
+ /* Multicast packets received on this port */
+ data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast;
+ data[i++] = oct_dev->link_stats.fromwire.fw_total_bcast;
/*per_core_stats[core_id].link_stats[ifidx].fromwire.jabber_err */
data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.jabber_err);
/*per_core_stats[core_id].link_stats[ifidx].fromwire.l2_err */
__attribute__((unused)),
u64 *data)
{
- struct net_device_stats *netstats = &netdev->stats;
+ struct rtnl_link_stats64 lstats;
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct_dev = lio->oct_dev;
int i = 0, j, vj;
if (ifstate_check(lio, LIO_IFSTATE_RESETTING))
return;
- netdev->netdev_ops->ndo_get_stats(netdev);
+ netdev->netdev_ops->ndo_get_stats64(netdev, &lstats);
/* sum of oct->droq[oq_no]->stats->rx_pkts_received */
- data[i++] = CVM_CAST64(netstats->rx_packets);
+ data[i++] = lstats.rx_packets;
/* sum of oct->instr_queue[iq_no]->stats.tx_done */
- data[i++] = CVM_CAST64(netstats->tx_packets);
+ data[i++] = lstats.tx_packets;
/* sum of oct->droq[oq_no]->stats->rx_bytes_received */
- data[i++] = CVM_CAST64(netstats->rx_bytes);
+ data[i++] = lstats.rx_bytes;
/* sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */
- data[i++] = CVM_CAST64(netstats->tx_bytes);
- data[i++] = CVM_CAST64(netstats->rx_errors);
- data[i++] = CVM_CAST64(netstats->tx_errors);
+ data[i++] = lstats.tx_bytes;
+ data[i++] = lstats.rx_errors;
+ data[i++] = lstats.tx_errors;
/* sum of oct->droq[oq_no]->stats->rx_dropped +
* oct->droq[oq_no]->stats->dropped_nodispatch +
* oct->droq[oq_no]->stats->dropped_toomany +
* oct->droq[oq_no]->stats->dropped_nomem
*/
- data[i++] = CVM_CAST64(netstats->rx_dropped);
+ data[i++] = lstats.rx_dropped;
/* sum of oct->instr_queue[iq_no]->stats.tx_dropped */
- data[i++] = CVM_CAST64(netstats->tx_dropped);
+ data[i++] = lstats.tx_dropped;
+
+ data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast;
+ data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent;
+ data[i++] = oct_dev->link_stats.fromwire.fw_total_bcast;
+ data[i++] = oct_dev->link_stats.fromhost.fw_total_bcast_sent;
+
/* lio->link_changes */
data[i++] = CVM_CAST64(lio->link_changes);
return -EINTR;
}
-static void
-octnet_nic_stats_callback(struct octeon_device *oct_dev,
- u32 status, void *ptr)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
- struct oct_nic_stats_resp *resp =
- (struct oct_nic_stats_resp *)sc->virtrptr;
- struct oct_nic_stats_ctrl *ctrl =
- (struct oct_nic_stats_ctrl *)sc->ctxptr;
- struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire;
- struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost;
-
- struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire;
- struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost;
-
- if ((status != OCTEON_REQUEST_TIMEOUT) && !resp->status) {
- octeon_swap_8B_data((u64 *)&resp->stats,
- (sizeof(struct oct_link_stats)) >> 3);
-
- /* RX link-level stats */
- rstats->total_rcvd = rsp_rstats->total_rcvd;
- rstats->bytes_rcvd = rsp_rstats->bytes_rcvd;
- rstats->total_bcst = rsp_rstats->total_bcst;
- rstats->total_mcst = rsp_rstats->total_mcst;
- rstats->runts = rsp_rstats->runts;
- rstats->ctl_rcvd = rsp_rstats->ctl_rcvd;
- /* Accounts for over/under-run of buffers */
- rstats->fifo_err = rsp_rstats->fifo_err;
- rstats->dmac_drop = rsp_rstats->dmac_drop;
- rstats->fcs_err = rsp_rstats->fcs_err;
- rstats->jabber_err = rsp_rstats->jabber_err;
- rstats->l2_err = rsp_rstats->l2_err;
- rstats->frame_err = rsp_rstats->frame_err;
- rstats->red_drops = rsp_rstats->red_drops;
-
- /* RX firmware stats */
- rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd;
- rstats->fw_total_fwd = rsp_rstats->fw_total_fwd;
- rstats->fw_err_pko = rsp_rstats->fw_err_pko;
- rstats->fw_err_link = rsp_rstats->fw_err_link;
- rstats->fw_err_drop = rsp_rstats->fw_err_drop;
- rstats->fw_rx_vxlan = rsp_rstats->fw_rx_vxlan;
- rstats->fw_rx_vxlan_err = rsp_rstats->fw_rx_vxlan_err;
-
- /* Number of packets that are LROed */
- rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts;
- /* Number of octets that are LROed */
- rstats->fw_lro_octs = rsp_rstats->fw_lro_octs;
- /* Number of LRO packets formed */
- rstats->fw_total_lro = rsp_rstats->fw_total_lro;
- /* Number of times lRO of packet aborted */
- rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts;
- rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port;
- rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq;
- rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval;
- rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer;
- /* intrmod: packet forward rate */
- rstats->fwd_rate = rsp_rstats->fwd_rate;
-
- /* TX link-level stats */
- tstats->total_pkts_sent = rsp_tstats->total_pkts_sent;
- tstats->total_bytes_sent = rsp_tstats->total_bytes_sent;
- tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent;
- tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent;
- tstats->ctl_sent = rsp_tstats->ctl_sent;
- /* Packets sent after one collision*/
- tstats->one_collision_sent = rsp_tstats->one_collision_sent;
- /* Packets sent after multiple collision*/
- tstats->multi_collision_sent = rsp_tstats->multi_collision_sent;
- /* Packets not sent due to max collisions */
- tstats->max_collision_fail = rsp_tstats->max_collision_fail;
- /* Packets not sent due to max deferrals */
- tstats->max_deferral_fail = rsp_tstats->max_deferral_fail;
- /* Accounts for over/under-run of buffers */
- tstats->fifo_err = rsp_tstats->fifo_err;
- tstats->runts = rsp_tstats->runts;
- /* Total number of collisions detected */
- tstats->total_collisions = rsp_tstats->total_collisions;
-
- /* firmware stats */
- tstats->fw_total_sent = rsp_tstats->fw_total_sent;
- tstats->fw_total_fwd = rsp_tstats->fw_total_fwd;
- tstats->fw_err_pko = rsp_tstats->fw_err_pko;
- tstats->fw_err_pki = rsp_tstats->fw_err_pki;
- tstats->fw_err_link = rsp_tstats->fw_err_link;
- tstats->fw_err_drop = rsp_tstats->fw_err_drop;
- tstats->fw_tso = rsp_tstats->fw_tso;
- tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd;
- tstats->fw_err_tso = rsp_tstats->fw_err_tso;
- tstats->fw_tx_vxlan = rsp_tstats->fw_tx_vxlan;
-
- resp->status = 1;
- } else {
- resp->status = -1;
- }
- complete(&ctrl->complete);
-}
-
-/* Configure interrupt moderation parameters */
-static int octnet_get_link_stats(struct net_device *netdev)
-{
- struct lio *lio = GET_LIO(netdev);
- struct octeon_device *oct_dev = lio->oct_dev;
-
- struct octeon_soft_command *sc;
- struct oct_nic_stats_ctrl *ctrl;
- struct oct_nic_stats_resp *resp;
-
- int retval;
-
- /* Alloc soft command */
- sc = (struct octeon_soft_command *)
- octeon_alloc_soft_command(oct_dev,
- 0,
- sizeof(struct oct_nic_stats_resp),
- sizeof(struct octnic_ctrl_pkt));
-
- if (!sc)
- return -ENOMEM;
-
- resp = (struct oct_nic_stats_resp *)sc->virtrptr;
- memset(resp, 0, sizeof(struct oct_nic_stats_resp));
-
- ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr;
- memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl));
- ctrl->netdev = netdev;
- init_completion(&ctrl->complete);
-
- sc->iq_no = lio->linfo.txpciq[0].s.q_no;
-
- octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
- OPCODE_NIC_PORT_STATS, 0, 0, 0);
-
- sc->callback = octnet_nic_stats_callback;
- sc->callback_arg = sc;
- sc->wait_time = 500; /*in milli seconds*/
-
- retval = octeon_send_soft_command(oct_dev, sc);
- if (retval == IQ_SEND_FAILED) {
- octeon_free_soft_command(oct_dev, sc);
- return -EINVAL;
- }
-
- wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000));
-
- if (resp->status != 1) {
- octeon_free_soft_command(oct_dev, sc);
-
- return -EINVAL;
- }
-
- octeon_free_soft_command(oct_dev, sc);
-
- return 0;
-}
-
static int lio_get_intr_coalesce(struct net_device *netdev,
struct ethtool_coalesce *intr_coal)
{
static const struct ethtool_ops lio_ethtool_ops = {
.get_link_ksettings = lio_get_link_ksettings,
+ .set_link_ksettings = lio_set_link_ksettings,
.get_link = ethtool_op_get_link,
.get_drvinfo = lio_get_drvinfo,
.get_ringparam = lio_ethtool_get_ringparam,
* by this structure in the NIC module.
*/
-#define OCTNIC_MAX_SG (MAX_SKB_FRAGS)
-
#define OCTNIC_GSO_MAX_HEADER_SIZE 128
#define OCTNIC_GSO_MAX_SIZE \
(CN23XX_DEFAULT_INPUT_JABBER - OCTNIC_GSO_MAX_HEADER_SIZE)
-/** Structure of a node in list of gather components maintained by
- * NIC driver for each network device.
- */
-struct octnic_gather {
- /** List manipulation. Next and prev pointers. */
- struct list_head list;
-
- /** Size of the gather component at sg in bytes. */
- int sg_size;
-
- /** Number of bytes that sg was adjusted to make it 8B-aligned. */
- int adjust;
-
- /** Gather component that can accommodate max sized fragment list
- * received from the IP layer.
- */
- struct octeon_sg_entry *sg;
-
- dma_addr_t sg_dma_ptr;
-};
-
struct handshake {
struct completion init;
struct completion started;
*/
static inline int check_txq_status(struct lio *lio)
{
- int numqs = lio->netdev->num_tx_queues;
+ int numqs = lio->netdev->real_num_tx_queues;
int ret_val = 0;
int q, iq;
return ret_val;
}
-/**
- * Remove the node at the head of the list. The list would be empty at
- * the end of this call if there are no more nodes in the list.
- */
-static inline struct list_head *list_delete_head(struct list_head *root)
-{
- struct list_head *node;
-
- if ((root->prev == root) && (root->next == root))
- node = NULL;
- else
- node = root->next;
-
- if (node)
- list_del(node);
-
- return node;
-}
-
-/**
- * \brief Delete gather lists
- * @param lio per-network private data
- */
-static void delete_glists(struct lio *lio)
-{
- struct octnic_gather *g;
- int i;
-
- kfree(lio->glist_lock);
- lio->glist_lock = NULL;
-
- if (!lio->glist)
- return;
-
- for (i = 0; i < lio->linfo.num_txpciq; i++) {
- do {
- g = (struct octnic_gather *)
- list_delete_head(&lio->glist[i]);
- if (g)
- kfree(g);
- } while (g);
-
- if (lio->glists_virt_base && lio->glists_virt_base[i] &&
- lio->glists_dma_base && lio->glists_dma_base[i]) {
- lio_dma_free(lio->oct_dev,
- lio->glist_entry_size * lio->tx_qsize,
- lio->glists_virt_base[i],
- lio->glists_dma_base[i]);
- }
- }
-
- kfree(lio->glists_virt_base);
- lio->glists_virt_base = NULL;
-
- kfree(lio->glists_dma_base);
- lio->glists_dma_base = NULL;
-
- kfree(lio->glist);
- lio->glist = NULL;
-}
-
-/**
- * \brief Setup gather lists
- * @param lio per-network private data
- */
-static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
-{
- int i, j;
- struct octnic_gather *g;
-
- lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
- GFP_KERNEL);
- if (!lio->glist_lock)
- return -ENOMEM;
-
- lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
- GFP_KERNEL);
- if (!lio->glist) {
- kfree(lio->glist_lock);
- lio->glist_lock = NULL;
- return -ENOMEM;
- }
-
- lio->glist_entry_size =
- ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
-
- /* allocate memory to store virtual and dma base address of
- * per glist consistent memory
- */
- lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
- GFP_KERNEL);
- lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
- GFP_KERNEL);
-
- if (!lio->glists_virt_base || !lio->glists_dma_base) {
- delete_glists(lio);
- return -ENOMEM;
- }
-
- for (i = 0; i < num_iqs; i++) {
- int numa_node = dev_to_node(&oct->pci_dev->dev);
-
- spin_lock_init(&lio->glist_lock[i]);
-
- INIT_LIST_HEAD(&lio->glist[i]);
-
- lio->glists_virt_base[i] =
- lio_dma_alloc(oct,
- lio->glist_entry_size * lio->tx_qsize,
- &lio->glists_dma_base[i]);
-
- if (!lio->glists_virt_base[i]) {
- delete_glists(lio);
- return -ENOMEM;
- }
-
- for (j = 0; j < lio->tx_qsize; j++) {
- g = kzalloc_node(sizeof(*g), GFP_KERNEL,
- numa_node);
- if (!g)
- g = kzalloc(sizeof(*g), GFP_KERNEL);
- if (!g)
- break;
-
- g->sg = lio->glists_virt_base[i] +
- (j * lio->glist_entry_size);
-
- g->sg_dma_ptr = lio->glists_dma_base[i] +
- (j * lio->glist_entry_size);
-
- list_add_tail(&g->list, &lio->glist[i]);
- }
-
- if (j != lio->tx_qsize) {
- delete_glists(lio);
- return -ENOMEM;
- }
- }
-
- return 0;
-}
-
/**
* \brief Print link information
* @param netdev network device
/* set linux specific device pointer */
oct_dev->pci_dev = (void *)pdev;
+ oct_dev->subsystem_id = pdev->subsystem_vendor |
+ (pdev->subsystem_device << 16);
+
hs = &handshake[oct_dev->octeon_id];
init_completion(&hs->init);
init_completion(&hs->started);
cleanup_rx_oom_poll_fn(netdev);
- delete_glists(lio);
+ lio_delete_glists(lio);
free_netdev(netdev);
i++;
}
- iq = skb_iq(lio, skb);
+ iq = skb_iq(lio->oct_dev, skb);
spin_lock(&lio->glist_lock[iq]);
list_add_tail(&g->list, &lio->glist[iq]);
spin_unlock(&lio->glist_lock[iq]);
i++;
}
- iq = skb_iq(lio, skb);
+ iq = skb_iq(lio->oct_dev, skb);
spin_lock(&lio->glist_lock[iq]);
list_add_tail(&g->list, &lio->glist[iq]);
return ret;
}
-/**
- * \brief Callback for getting interface configuration
- * @param status status of request
- * @param buf pointer to resp structure
- */
-static void if_cfg_callback(struct octeon_device *oct,
- u32 status __attribute__((unused)),
- void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_if_cfg_resp *resp;
- struct liquidio_if_cfg_context *ctx;
-
- resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (resp->status)
- dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n",
- CVM_CAST64(resp->status), status);
- WRITE_ONCE(ctx->cond, 1);
-
- snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
- resp->cfg_info.liquidio_firmware_version);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
/**
* \brief Poll routine for checking transmit queue status
* @param work work_struct data structure
ifstate_set(lio, LIO_IFSTATE_RUNNING);
- /* Ready for link status updates */
- lio->intf_open = 1;
-
- netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n");
-
if (OCTEON_CN23XX_PF(oct)) {
if (!oct->msix_on)
if (setup_tx_poll_fn(netdev))
return -1;
}
- start_txqs(netdev);
+ netif_tx_start_all_queues(netdev);
+
+ /* Ready for link status updates */
+ lio->intf_open = 1;
+
+ netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n");
/* tell Octeon to start forwarding packets to host */
send_rx_ctrl_cmd(lio, 1);
ifstate_reset(lio, LIO_IFSTATE_RUNNING);
- netif_tx_disable(netdev);
+ /* Stop any link updates */
+ lio->intf_open = 0;
+
+ stop_txqs(netdev);
/* Inform that netif carrier is down */
netif_carrier_off(netdev);
- lio->intf_open = 0;
+ netif_tx_disable(netdev);
+
lio->linfo.link.s.link_up = 0;
lio->link_changes++;
return 0;
}
-/**
- * \brief Net device get_stats
- * @param netdev network device
- */
-static struct net_device_stats *liquidio_get_stats(struct net_device *netdev)
+static void
+liquidio_get_stats64(struct net_device *netdev,
+ struct rtnl_link_stats64 *lstats)
{
struct lio *lio = GET_LIO(netdev);
- struct net_device_stats *stats = &netdev->stats;
struct octeon_device *oct;
u64 pkts = 0, drop = 0, bytes = 0;
struct oct_droq_stats *oq_stats;
oct = lio->oct_dev;
if (ifstate_check(lio, LIO_IFSTATE_RESETTING))
- return stats;
+ return;
for (i = 0; i < oct->num_iqs; i++) {
iq_no = lio->linfo.txpciq[i].s.q_no;
bytes += iq_stats->tx_tot_bytes;
}
- stats->tx_packets = pkts;
- stats->tx_bytes = bytes;
- stats->tx_dropped = drop;
+ lstats->tx_packets = pkts;
+ lstats->tx_bytes = bytes;
+ lstats->tx_dropped = drop;
pkts = 0;
drop = 0;
bytes += oq_stats->rx_bytes_received;
}
- stats->rx_bytes = bytes;
- stats->rx_packets = pkts;
- stats->rx_dropped = drop;
-
- return stats;
+ lstats->rx_bytes = bytes;
+ lstats->rx_packets = pkts;
+ lstats->rx_dropped = drop;
+
+ octnet_get_link_stats(netdev);
+ lstats->multicast = oct->link_stats.fromwire.fw_total_mcast;
+ lstats->collisions = oct->link_stats.fromhost.total_collisions;
+
+ /* detailed rx_errors: */
+ lstats->rx_length_errors = oct->link_stats.fromwire.l2_err;
+ /* recved pkt with crc error */
+ lstats->rx_crc_errors = oct->link_stats.fromwire.fcs_err;
+ /* recv'd frame alignment error */
+ lstats->rx_frame_errors = oct->link_stats.fromwire.frame_err;
+ /* recv'r fifo overrun */
+ lstats->rx_fifo_errors = oct->link_stats.fromwire.fifo_err;
+
+ lstats->rx_errors = lstats->rx_length_errors + lstats->rx_crc_errors +
+ lstats->rx_frame_errors + lstats->rx_fifo_errors;
+
+ /* detailed tx_errors */
+ lstats->tx_aborted_errors = oct->link_stats.fromhost.fw_err_pko;
+ lstats->tx_carrier_errors = oct->link_stats.fromhost.fw_err_link;
+ lstats->tx_fifo_errors = oct->link_stats.fromhost.fifo_err;
+
+ lstats->tx_errors = lstats->tx_aborted_errors +
+ lstats->tx_carrier_errors +
+ lstats->tx_fifo_errors;
}
/**
lio = GET_LIO(netdev);
oct = lio->oct_dev;
- q_idx = skb_iq(lio, skb);
+ q_idx = skb_iq(oct, skb);
tag = q_idx;
iq_no = lio->linfo.txpciq[q_idx].s.q_no;
spin_lock(&lio->glist_lock[q_idx]);
g = (struct octnic_gather *)
- list_delete_head(&lio->glist[q_idx]);
+ lio_list_delete_head(&lio->glist[q_idx]);
spin_unlock(&lio->glist_lock[q_idx]);
if (!g) {
.ndo_open = liquidio_open,
.ndo_stop = liquidio_stop,
.ndo_start_xmit = liquidio_xmit,
- .ndo_get_stats = liquidio_get_stats,
+ .ndo_get_stats64 = liquidio_get_stats64,
.ndo_set_mac_address = liquidio_set_mac,
.ndo_set_rx_mode = liquidio_set_mcast_list,
.ndo_tx_timeout = liquidio_tx_timeout,
struct liquidio_if_cfg_resp *resp;
struct octdev_props *props;
int retval, num_iqueues, num_oqueues;
+ int max_num_queues = 0;
union oct_nic_if_cfg if_cfg;
unsigned int base_queue;
unsigned int gmx_port_id;
OPCODE_NIC_IF_CFG, 0,
if_cfg.u64, 0);
- sc->callback = if_cfg_callback;
+ sc->callback = lio_if_cfg_callback;
sc->callback_arg = sc;
- sc->wait_time = 3000;
+ sc->wait_time = LIO_IFCFG_WAIT_TIME;
retval = octeon_send_soft_command(octeon_dev, sc);
if (retval == IQ_SEND_FAILED) {
resp->cfg_info.oqmask);
goto setup_nic_dev_fail;
}
+
+ if (OCTEON_CN6XXX(octeon_dev)) {
+ max_num_queues = CFG_GET_IQ_MAX_Q(CHIP_CONF(octeon_dev,
+ cn6xxx));
+ } else if (OCTEON_CN23XX_PF(octeon_dev)) {
+ max_num_queues = CFG_GET_IQ_MAX_Q(CHIP_CONF(octeon_dev,
+ cn23xx_pf));
+ }
+
dev_dbg(&octeon_dev->pci_dev->dev,
- "interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d\n",
+ "interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d max_num_queues: %d\n",
i, resp->cfg_info.iqmask, resp->cfg_info.oqmask,
- num_iqueues, num_oqueues);
- netdev = alloc_etherdev_mq(LIO_SIZE, num_iqueues);
+ num_iqueues, num_oqueues, max_num_queues);
+ netdev = alloc_etherdev_mq(LIO_SIZE, max_num_queues);
if (!netdev) {
dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n");
netdev->netdev_ops = &lionetdevops;
SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops);
+ retval = netif_set_real_num_rx_queues(netdev, num_oqueues);
+ if (retval) {
+ dev_err(&octeon_dev->pci_dev->dev,
+ "setting real number rx failed\n");
+ goto setup_nic_dev_fail;
+ }
+
+ retval = netif_set_real_num_tx_queues(netdev, num_iqueues);
+ if (retval) {
+ dev_err(&octeon_dev->pci_dev->dev,
+ "setting real number tx failed\n");
+ goto setup_nic_dev_fail;
+ }
+
lio = GET_LIO(netdev);
memset(lio, 0, sizeof(struct lio));
lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq);
lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq);
- if (setup_glists(octeon_dev, lio, num_iqueues)) {
+ if (lio_setup_glists(octeon_dev, lio, num_iqueues)) {
dev_err(&octeon_dev->pci_dev->dev,
"Gather list allocation failed\n");
goto setup_nic_dev_fail;
"NIC ifidx:%d Setup successful\n", i);
octeon_free_soft_command(octeon_dev, sc);
+
+ if (octeon_dev->subsystem_id ==
+ OCTEON_CN2350_25GB_SUBSYS_ID ||
+ octeon_dev->subsystem_id ==
+ OCTEON_CN2360_25GB_SUBSYS_ID) {
+ liquidio_get_speed(lio);
+
+ if (octeon_dev->speed_setting == 0) {
+ octeon_dev->speed_setting = 25;
+ octeon_dev->no_speed_setting = 1;
+ }
+ } else {
+ octeon_dev->no_speed_setting = 1;
+ octeon_dev->speed_setting = 10;
+ }
+ octeon_dev->speed_boot = octeon_dev->speed_setting;
+
}
devlink = devlink_alloc(&liquidio_devlink_ops,
}
atomic_set(&octeon_dev->status, OCT_DEV_MBOX_SETUP_DONE);
- if (octeon_allocate_ioq_vector(octeon_dev)) {
+ if (octeon_allocate_ioq_vector
+ (octeon_dev,
+ octeon_dev->sriov_info.num_pf_rings)) {
dev_err(&octeon_dev->pci_dev->dev, "OCTEON: ioq vector allocation failed\n");
return 1;
}
} s;
};
-#define OCTNIC_MAX_SG (MAX_SKB_FRAGS)
-
#define OCTNIC_GSO_MAX_HEADER_SIZE 128
#define OCTNIC_GSO_MAX_SIZE \
(CN23XX_DEFAULT_INPUT_JABBER - OCTNIC_GSO_MAX_HEADER_SIZE)
-struct octnic_gather {
- /* List manipulation. Next and prev pointers. */
- struct list_head list;
-
- /* Size of the gather component at sg in bytes. */
- int sg_size;
-
- /* Number of bytes that sg was adjusted to make it 8B-aligned. */
- int adjust;
-
- /* Gather component that can accommodate max sized fragment list
- * received from the IP layer.
- */
- struct octeon_sg_entry *sg;
-
- dma_addr_t sg_dma_ptr;
-};
-
static int
liquidio_vf_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
static void liquidio_vf_remove(struct pci_dev *pdev);
.err_handler = &liquidio_vf_err_handler, /* For AER */
};
-/**
- * Remove the node at the head of the list. The list would be empty at
- * the end of this call if there are no more nodes in the list.
- */
-static struct list_head *list_delete_head(struct list_head *root)
-{
- struct list_head *node;
-
- if ((root->prev == root) && (root->next == root))
- node = NULL;
- else
- node = root->next;
-
- if (node)
- list_del(node);
-
- return node;
-}
-
-/**
- * \brief Delete gather lists
- * @param lio per-network private data
- */
-static void delete_glists(struct lio *lio)
-{
- struct octnic_gather *g;
- int i;
-
- kfree(lio->glist_lock);
- lio->glist_lock = NULL;
-
- if (!lio->glist)
- return;
-
- for (i = 0; i < lio->linfo.num_txpciq; i++) {
- do {
- g = (struct octnic_gather *)
- list_delete_head(&lio->glist[i]);
- kfree(g);
- } while (g);
-
- if (lio->glists_virt_base && lio->glists_virt_base[i] &&
- lio->glists_dma_base && lio->glists_dma_base[i]) {
- lio_dma_free(lio->oct_dev,
- lio->glist_entry_size * lio->tx_qsize,
- lio->glists_virt_base[i],
- lio->glists_dma_base[i]);
- }
- }
-
- kfree(lio->glists_virt_base);
- lio->glists_virt_base = NULL;
-
- kfree(lio->glists_dma_base);
- lio->glists_dma_base = NULL;
-
- kfree(lio->glist);
- lio->glist = NULL;
-}
-
-/**
- * \brief Setup gather lists
- * @param lio per-network private data
- */
-static int setup_glists(struct lio *lio, int num_iqs)
-{
- struct octnic_gather *g;
- int i, j;
-
- lio->glist_lock =
- kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL);
- if (!lio->glist_lock)
- return -ENOMEM;
-
- lio->glist =
- kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL);
- if (!lio->glist) {
- kfree(lio->glist_lock);
- lio->glist_lock = NULL;
- return -ENOMEM;
- }
-
- lio->glist_entry_size =
- ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
-
- /* allocate memory to store virtual and dma base address of
- * per glist consistent memory
- */
- lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
- GFP_KERNEL);
- lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
- GFP_KERNEL);
-
- if (!lio->glists_virt_base || !lio->glists_dma_base) {
- delete_glists(lio);
- return -ENOMEM;
- }
-
- for (i = 0; i < num_iqs; i++) {
- spin_lock_init(&lio->glist_lock[i]);
-
- INIT_LIST_HEAD(&lio->glist[i]);
-
- lio->glists_virt_base[i] =
- lio_dma_alloc(lio->oct_dev,
- lio->glist_entry_size * lio->tx_qsize,
- &lio->glists_dma_base[i]);
-
- if (!lio->glists_virt_base[i]) {
- delete_glists(lio);
- return -ENOMEM;
- }
-
- for (j = 0; j < lio->tx_qsize; j++) {
- g = kzalloc(sizeof(*g), GFP_KERNEL);
- if (!g)
- break;
-
- g->sg = lio->glists_virt_base[i] +
- (j * lio->glist_entry_size);
-
- g->sg_dma_ptr = lio->glists_dma_base[i] +
- (j * lio->glist_entry_size);
-
- list_add_tail(&g->list, &lio->glist[i]);
- }
-
- if (j != lio->tx_qsize) {
- delete_glists(lio);
- return -ENOMEM;
- }
- }
-
- return 0;
-}
-
/**
* \brief Print link information
* @param netdev network device
/* set linux specific device pointer */
oct_dev->pci_dev = pdev;
+ oct_dev->subsystem_id = pdev->subsystem_vendor |
+ (pdev->subsystem_device << 16);
+
if (octeon_device_init(oct_dev)) {
liquidio_vf_remove(pdev);
return -ENOMEM;
cleanup_link_status_change_wq(netdev);
- delete_glists(lio);
+ lio_delete_glists(lio);
free_netdev(netdev);
i++;
}
- iq = skb_iq(lio, skb);
+ iq = skb_iq(lio->oct_dev, skb);
spin_lock(&lio->glist_lock[iq]);
list_add_tail(&g->list, &lio->glist[iq]);
i++;
}
- iq = skb_iq(lio, skb);
+ iq = skb_iq(lio->oct_dev, skb);
spin_lock(&lio->glist_lock[iq]);
list_add_tail(&g->list, &lio->glist[iq]);
/* Don't free the skb yet */
}
-/**
- * \brief Callback for getting interface configuration
- * @param status status of request
- * @param buf pointer to resp structure
- */
-static void if_cfg_callback(struct octeon_device *oct,
- u32 status __attribute__((unused)), void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_if_cfg_context *ctx;
- struct liquidio_if_cfg_resp *resp;
-
- resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (resp->status)
- dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
- CVM_CAST64(resp->status));
- WRITE_ONCE(ctx->cond, 1);
-
- snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
- resp->cfg_info.liquidio_firmware_version);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
/**
* \brief Net device open for LiquidIO
* @param netdev network device
return 0;
}
-/**
- * \brief Net device get_stats
- * @param netdev network device
- */
-static struct net_device_stats *liquidio_get_stats(struct net_device *netdev)
+static void
+liquidio_get_stats64(struct net_device *netdev,
+ struct rtnl_link_stats64 *lstats)
{
struct lio *lio = GET_LIO(netdev);
- struct net_device_stats *stats = &netdev->stats;
+ struct octeon_device *oct;
u64 pkts = 0, drop = 0, bytes = 0;
struct oct_droq_stats *oq_stats;
struct oct_iq_stats *iq_stats;
- struct octeon_device *oct;
int i, iq_no, oq_no;
oct = lio->oct_dev;
if (ifstate_check(lio, LIO_IFSTATE_RESETTING))
- return stats;
+ return;
for (i = 0; i < oct->num_iqs; i++) {
iq_no = lio->linfo.txpciq[i].s.q_no;
bytes += iq_stats->tx_tot_bytes;
}
- stats->tx_packets = pkts;
- stats->tx_bytes = bytes;
- stats->tx_dropped = drop;
+ lstats->tx_packets = pkts;
+ lstats->tx_bytes = bytes;
+ lstats->tx_dropped = drop;
pkts = 0;
drop = 0;
bytes += oq_stats->rx_bytes_received;
}
- stats->rx_bytes = bytes;
- stats->rx_packets = pkts;
- stats->rx_dropped = drop;
+ lstats->rx_bytes = bytes;
+ lstats->rx_packets = pkts;
+ lstats->rx_dropped = drop;
+
+ octnet_get_link_stats(netdev);
+ lstats->multicast = oct->link_stats.fromwire.fw_total_mcast;
+
+ /* detailed rx_errors: */
+ lstats->rx_length_errors = oct->link_stats.fromwire.l2_err;
+ /* recved pkt with crc error */
+ lstats->rx_crc_errors = oct->link_stats.fromwire.fcs_err;
+ /* recv'd frame alignment error */
+ lstats->rx_frame_errors = oct->link_stats.fromwire.frame_err;
- return stats;
+ lstats->rx_errors = lstats->rx_length_errors + lstats->rx_crc_errors +
+ lstats->rx_frame_errors;
+
+ /* detailed tx_errors */
+ lstats->tx_aborted_errors = oct->link_stats.fromhost.fw_err_pko;
+ lstats->tx_carrier_errors = oct->link_stats.fromhost.fw_err_link;
+
+ lstats->tx_errors = lstats->tx_aborted_errors +
+ lstats->tx_carrier_errors;
}
/**
lio = GET_LIO(netdev);
oct = lio->oct_dev;
- q_idx = skb_iq(lio, skb);
+ q_idx = skb_iq(lio->oct_dev, skb);
tag = q_idx;
iq_no = lio->linfo.txpciq[q_idx].s.q_no;
int i, frags;
spin_lock(&lio->glist_lock[q_idx]);
- g = (struct octnic_gather *)list_delete_head(
- &lio->glist[q_idx]);
+ g = (struct octnic_gather *)
+ lio_list_delete_head(&lio->glist[q_idx]);
spin_unlock(&lio->glist_lock[q_idx]);
if (!g) {
.ndo_open = liquidio_open,
.ndo_stop = liquidio_stop,
.ndo_start_xmit = liquidio_xmit,
- .ndo_get_stats = liquidio_get_stats,
+ .ndo_get_stats64 = liquidio_get_stats64,
.ndo_set_mac_address = liquidio_set_mac,
.ndo_set_rx_mode = liquidio_set_mcast_list,
.ndo_tx_timeout = liquidio_tx_timeout,
OPCODE_NIC_IF_CFG, 0, if_cfg.u64,
0);
- sc->callback = if_cfg_callback;
+ sc->callback = lio_if_cfg_callback;
sc->callback_arg = sc;
sc->wait_time = 5000;
netdev->features = (lio->dev_capability & ~NETIF_F_LRO);
netdev->hw_features = lio->dev_capability;
+ netdev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
/* MTU range: 68 - 16000 */
netdev->min_mtu = LIO_MIN_MTU_SIZE;
lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq);
lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq);
- if (setup_glists(lio, num_iqueues)) {
+ if (lio_setup_glists(octeon_dev, lio, num_iqueues)) {
dev_err(&octeon_dev->pci_dev->dev,
"Gather list allocation failed\n");
goto setup_nic_dev_fail;
"NIC ifidx:%d Setup successful\n", i);
octeon_free_soft_command(octeon_dev, sc);
+
+ octeon_dev->no_speed_setting = 1;
}
return 0;
}
atomic_set(&oct->status, OCT_DEV_MBOX_SETUP_DONE);
- if (octeon_allocate_ioq_vector(oct)) {
+ if (octeon_allocate_ioq_vector(oct, oct->sriov_info.rings_per_vf)) {
dev_err(&oct->pci_dev->dev, "ioq vector allocation failed\n");
return 1;
}
{
struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
- stats64->tx_packets = vf_rep->stats.tx_packets;
- stats64->tx_bytes = vf_rep->stats.tx_bytes;
- stats64->tx_dropped = vf_rep->stats.tx_dropped;
-
- stats64->rx_packets = vf_rep->stats.rx_packets;
- stats64->rx_bytes = vf_rep->stats.rx_bytes;
- stats64->rx_dropped = vf_rep->stats.rx_dropped;
+ /* Swap tx and rx stats as VF rep is a switch port */
+ stats64->tx_packets = vf_rep->stats.rx_packets;
+ stats64->tx_bytes = vf_rep->stats.rx_bytes;
+ stats64->tx_dropped = vf_rep->stats.rx_dropped;
+
+ stats64->rx_packets = vf_rep->stats.tx_packets;
+ stats64->rx_bytes = vf_rep->stats.tx_bytes;
+ stats64->rx_dropped = vf_rep->stats.tx_dropped;
}
static int
#define LIQUIDIO_PACKAGE ""
#define LIQUIDIO_BASE_MAJOR_VERSION 1
#define LIQUIDIO_BASE_MINOR_VERSION 7
-#define LIQUIDIO_BASE_MICRO_VERSION 0
+#define LIQUIDIO_BASE_MICRO_VERSION 2
#define LIQUIDIO_BASE_VERSION __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \
__stringify(LIQUIDIO_BASE_MINOR_VERSION)
#define LIQUIDIO_MICRO_VERSION "." __stringify(LIQUIDIO_BASE_MICRO_VERSION)
#define OPCODE_NIC_IF_CFG 0x09
#define OPCODE_NIC_VF_DRV_NOTICE 0x0A
#define OPCODE_NIC_INTRMOD_PARAMS 0x0B
+#define OPCODE_NIC_QCOUNT_UPDATE 0x12
#define OPCODE_NIC_SET_TRUSTED_VF 0x13
#define OPCODE_NIC_SYNC_OCTEON_TIME 0x14
#define VF_DRV_LOADED 1
#define OPCODE_NIC_VF_REP_PKT 0x15
#define OPCODE_NIC_VF_REP_CMD 0x16
+#define OPCODE_NIC_UBOOT_CTL 0x17
#define CORE_DRV_TEST_SCATTER_OP 0xFFF5
#define OCTNET_CMD_VLAN_FILTER_ENABLE 0x1
#define OCTNET_CMD_VLAN_FILTER_DISABLE 0x0
+#define SEAPI_CMD_SPEED_SET 0x2
+#define SEAPI_CMD_SPEED_GET 0x3
+
#define LIO_CMD_WAIT_TM 100
/* RX(packets coming from wire) Checksum verification flags */
u64 fw_total_rcvd;
u64 fw_total_fwd;
u64 fw_total_fwd_bytes;
+ u64 fw_total_mcast;
+ u64 fw_total_bcast;
+
u64 fw_err_pko;
u64 fw_err_link;
u64 fw_err_drop;
u64 fw_total_sent;
u64 fw_total_fwd;
u64 fw_total_fwd_bytes;
+ u64 fw_total_mcast_sent;
+ u64 fw_total_bcast_sent;
u64 fw_err_pko;
u64 fw_err_link;
u64 fw_err_drop;
}
int
-octeon_allocate_ioq_vector(struct octeon_device *oct)
+octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs)
{
- int i, num_ioqs = 0;
struct octeon_ioq_vector *ioq_vector;
int cpu_num;
int size;
-
- if (OCTEON_CN23XX_PF(oct))
- num_ioqs = oct->sriov_info.num_pf_rings;
- else if (OCTEON_CN23XX_VF(oct))
- num_ioqs = oct->sriov_info.rings_per_vf;
+ int i;
size = sizeof(struct octeon_ioq_vector) * num_ioqs;
oct->ioq_vector = vzalloc(size);
if (!oct->ioq_vector)
- return 1;
+ return -1;
for (i = 0; i < num_ioqs; i++) {
ioq_vector = &oct->ioq_vector[i];
ioq_vector->oct_dev = oct;
else
ioq_vector->ioq_num = i;
}
+
return 0;
}
#define OCTEON_CN23XX_REV_1_1 0x01
#define OCTEON_CN23XX_REV_2_0 0x80
+/**SubsystemId for the chips */
+#define OCTEON_CN2350_10GB_SUBSYS_ID_1 0X3177d
+#define OCTEON_CN2350_10GB_SUBSYS_ID_2 0X4177d
+#define OCTEON_CN2360_10GB_SUBSYS_ID 0X5177d
+#define OCTEON_CN2350_25GB_SUBSYS_ID 0X7177d
+#define OCTEON_CN2360_25GB_SUBSYS_ID 0X6177d
+
/** Endian-swap modes supported by Octeon. */
enum octeon_pci_swap_mode {
OCTEON_PCI_PASSTHROUGH = 0,
u16 rev_id;
+ u32 subsystem_id;
+
u16 pf_num;
u16 vf_num;
struct lio_vf_rep_list vf_rep_list;
struct devlink *devlink;
enum devlink_eswitch_mode eswitch_mode;
+
+ /* for 25G NIC speed change */
+ u8 speed_boot;
+ u8 speed_setting;
+ u8 no_speed_setting;
};
#define OCT_DRV_ONLINE 1
struct octeon_config *octeon_get_conf(struct octeon_device *oct);
void octeon_free_ioq_vector(struct octeon_device *oct);
-int octeon_allocate_ioq_vector(struct octeon_device *oct);
+int octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs);
void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq);
/* LiquidIO driver pivate flags */
u64 status;
};
+#define LIO_IFCFG_WAIT_TIME 3000 /* In milli seconds */
+
+/* Structure of a node in list of gather components maintained by
+ * NIC driver for each network device.
+ */
+struct octnic_gather {
+ /* List manipulation. Next and prev pointers. */
+ struct list_head list;
+
+ /* Size of the gather component at sg in bytes. */
+ int sg_size;
+
+ /* Number of bytes that sg was adjusted to make it 8B-aligned. */
+ int adjust;
+
+ /* Gather component that can accommodate max sized fragment list
+ * received from the IP layer.
+ */
+ struct octeon_sg_entry *sg;
+
+ dma_addr_t sg_dma_ptr;
+};
+
struct oct_nic_stats_resp {
u64 rh;
struct oct_link_stats stats;
struct net_device *netdev;
};
+struct oct_nic_seapi_resp {
+ u64 rh;
+ u32 speed;
+ u64 status;
+};
+
+struct liquidio_nic_seapi_ctl_context {
+ int octeon_id;
+ u32 status;
+ struct completion complete;
+};
+
/** LiquidIO per-interface network private data */
struct lio {
/** State of the interface. Rx/Tx happens only in the RUNNING state. */
#define LIO_SIZE (sizeof(struct lio))
#define GET_LIO(netdev) ((struct lio *)netdev_priv(netdev))
-#define LIO_MAX_CORES 12
+#define LIO_MAX_CORES 16
/**
* \brief Enable or disable feature
int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs);
+int octnet_get_link_stats(struct net_device *netdev);
+
int lio_wait_for_clean_oq(struct octeon_device *oct);
/**
* \brief Register ethtool operations
*/
void liquidio_set_ethtool_ops(struct net_device *netdev);
+void lio_if_cfg_callback(struct octeon_device *oct,
+ u32 status __attribute__((unused)),
+ void *buf);
+
+void lio_delete_glists(struct lio *lio);
+
+int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_qs);
+
+int liquidio_get_speed(struct lio *lio);
+int liquidio_set_speed(struct lio *lio, int speed);
+
/**
* \brief Net device change_mtu
* @param netdev network device
{
int i;
- for (i = 0; i < netdev->num_tx_queues; i++)
+ for (i = 0; i < netdev->real_num_tx_queues; i++)
netif_stop_subqueue(netdev, i);
}
struct lio *lio = GET_LIO(netdev);
int i, qno;
- for (i = 0; i < netdev->num_tx_queues; i++) {
+ for (i = 0; i < netdev->real_num_tx_queues; i++) {
qno = lio->linfo.txpciq[i % lio->oct_dev->num_iqs].s.q_no;
if (__netif_subqueue_stopped(netdev, i)) {
int i;
if (lio->linfo.link.s.link_up) {
- for (i = 0; i < netdev->num_tx_queues; i++)
+ for (i = 0; i < netdev->real_num_tx_queues; i++)
netif_start_subqueue(netdev, i);
}
}
-static inline int skb_iq(struct lio *lio, struct sk_buff *skb)
+static inline int skb_iq(struct octeon_device *oct, struct sk_buff *skb)
{
- return skb->queue_mapping % lio->linfo.num_txpciq;
+ return skb->queue_mapping % oct->num_iqs;
+}
+
+/**
+ * Remove the node at the head of the list. The list would be empty at
+ * the end of this call if there are no more nodes in the list.
+ */
+static inline struct list_head *lio_list_delete_head(struct list_head *root)
+{
+ struct list_head *node;
+
+ if (root->prev == root && root->next == root)
+ node = NULL;
+ else
+ node = root->next;
+
+ if (node)
+ list_del(node);
+
+ return node;
}
#endif
u32 map;
};
+#define SGE_QBASE_DATA_REG_NUM 4
+
+struct sge_qbase_reg_field {
+ u32 reg_addr;
+ u32 reg_data[SGE_QBASE_DATA_REG_NUM];
+ /* Max supported PFs */
+ u32 pf_data_value[PCIE_FW_MASTER_M + 1][SGE_QBASE_DATA_REG_NUM];
+ /* Max supported VFs */
+ u32 vf_data_value[T6_VF_M + 1][SGE_QBASE_DATA_REG_NUM];
+ u32 vfcount; /* Actual number of max vfs in current configuration */
+};
+
struct ireg_field {
u32 ireg_addr;
u32 ireg_data;
};
#define CUDBG_MAX_TCAM_TID 0x800
+#define CUDBG_T6_CLIP 1536
+#define CUDBG_MAX_TID_COMP_EN 6144
+#define CUDBG_MAX_TID_COMP_DIS 3072
enum cudbg_le_entry_types {
LE_ET_UNKNOWN = 0,
{0x10cc, 0x10d4, 0x0, 16},
};
+static const u32 t6_sge_qbase_index_array[] = {
+ /* 1 addr reg SGE_QBASE_INDEX and 4 data reg SGE_QBASE_MAP[0-3] */
+ 0x1250, 0x1240, 0x1244, 0x1248, 0x124c,
+};
+
static const u32 t5_pcie_pdbg_array[][IREG_NUM_ELEM] = {
{0x5a04, 0x5a0c, 0x00, 0x20}, /* t5_pcie_pdbg_regs_00_to_20 */
{0x5a04, 0x5a0c, 0x21, 0x20}, /* t5_pcie_pdbg_regs_21_to_40 */
{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
- {0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
- {0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
- {0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
- {0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
- {0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
- {0x7b50, 0x7b54, 0x2920, 0x10, 0x10}, /* up_cim_2920_to_2a10 */
- {0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2a14 */
- {0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
- {0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
+ {0x7b50, 0x7b54, 0x4900, 0x4, 0x4}, /* up_cim_4900_to_4c60 */
+ {0x7b50, 0x7b54, 0x4904, 0x4, 0x4}, /* up_cim_4904_to_4c64 */
+ {0x7b50, 0x7b54, 0x4908, 0x4, 0x4}, /* up_cim_4908_to_4c68 */
+ {0x7b50, 0x7b54, 0x4910, 0x4, 0x4}, /* up_cim_4910_to_4c70 */
+ {0x7b50, 0x7b54, 0x4914, 0x4, 0x4}, /* up_cim_4914_to_4c74 */
+ {0x7b50, 0x7b54, 0x4920, 0x10, 0x10}, /* up_cim_4920_to_4a10 */
+ {0x7b50, 0x7b54, 0x4924, 0x10, 0x10}, /* up_cim_4924_to_4a14 */
+ {0x7b50, 0x7b54, 0x4928, 0x10, 0x10}, /* up_cim_4928_to_4a18 */
+ {0x7b50, 0x7b54, 0x492c, 0x10, 0x10}, /* up_cim_492c_to_4a1c */
};
static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
- {0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
- {0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
- {0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
- {0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
- {0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
- {0x7b50, 0x7b54, 0x2918, 0x4, 0x4}, /* up_cim_2918_to_3d54 */
- {0x7b50, 0x7b54, 0x291c, 0x4, 0x4}, /* up_cim_291c_to_3d58 */
- {0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2914 */
- {0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
- {0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
};
static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = {
#define CUDBG_STATUS_NOT_IMPLEMENTED -28
#define CUDBG_SYSTEM_ERROR -29
#define CUDBG_STATUS_CCLK_NOT_DEFINED -32
+#define CUDBG_STATUS_PARTIAL_DATA -41
#define CUDBG_MAJOR_VERSION 1
#define CUDBG_MINOR_VERSION 14
return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
}
+static void cudbg_read_sge_qbase_indirect_reg(struct adapter *padap,
+ struct sge_qbase_reg_field *qbase,
+ u32 func, bool is_pf)
+{
+ u32 *buff, i;
+
+ if (is_pf) {
+ buff = qbase->pf_data_value[func];
+ } else {
+ buff = qbase->vf_data_value[func];
+ /* In SGE_QBASE_INDEX,
+ * Entries 0->7 are PF0->7, Entries 8->263 are VFID0->256.
+ */
+ func += 8;
+ }
+
+ t4_write_reg(padap, qbase->reg_addr, func);
+ for (i = 0; i < SGE_QBASE_DATA_REG_NUM; i++, buff++)
+ *buff = t4_read_reg(padap, qbase->reg_data[i]);
+}
+
int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init,
struct cudbg_buffer *dbg_buff,
struct cudbg_error *cudbg_err)
{
struct adapter *padap = pdbg_init->adap;
struct cudbg_buffer temp_buff = { 0 };
+ struct sge_qbase_reg_field *sge_qbase;
struct ireg_buf *ch_sge_dbg;
int i, rc;
- rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(*ch_sge_dbg) * 2,
+ rc = cudbg_get_buff(pdbg_init, dbg_buff,
+ sizeof(*ch_sge_dbg) * 2 + sizeof(*sge_qbase),
&temp_buff);
if (rc)
return rc;
sge_pio->ireg_local_offset);
ch_sge_dbg++;
}
+
+ if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5) {
+ sge_qbase = (struct sge_qbase_reg_field *)ch_sge_dbg;
+ /* 1 addr reg SGE_QBASE_INDEX and 4 data reg
+ * SGE_QBASE_MAP[0-3]
+ */
+ sge_qbase->reg_addr = t6_sge_qbase_index_array[0];
+ for (i = 0; i < SGE_QBASE_DATA_REG_NUM; i++)
+ sge_qbase->reg_data[i] =
+ t6_sge_qbase_index_array[i + 1];
+
+ for (i = 0; i <= PCIE_FW_MASTER_M; i++)
+ cudbg_read_sge_qbase_indirect_reg(padap, sge_qbase,
+ i, true);
+
+ for (i = 0; i < padap->params.arch.vfcount; i++)
+ cudbg_read_sge_qbase_indirect_reg(padap, sge_qbase,
+ i, false);
+
+ sge_qbase->vfcount = padap->params.arch.vfcount;
+ }
+
return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
}
value = t4_read_reg(padap, LE_DB_ROUTING_TABLE_INDEX_A);
tcam_region->routing_start = value;
- /*Get clip table index */
- value = t4_read_reg(padap, LE_DB_CLIP_TABLE_INDEX_A);
+ /* Get clip table index. For T6 there is separate CLIP TCAM */
+ if (is_t6(padap->params.chip))
+ value = t4_read_reg(padap, LE_DB_CLCAM_TID_BASE_A);
+ else
+ value = t4_read_reg(padap, LE_DB_CLIP_TABLE_INDEX_A);
tcam_region->clip_start = value;
/* Get filter table index */
tcam_region->tid_hash_base;
}
} else { /* hash not enabled */
- tcam_region->max_tid = CUDBG_MAX_TCAM_TID;
+ if (is_t6(padap->params.chip))
+ tcam_region->max_tid = (value & ASLIPCOMPEN_F) ?
+ CUDBG_MAX_TID_COMP_EN :
+ CUDBG_MAX_TID_COMP_DIS;
+ else
+ tcam_region->max_tid = CUDBG_MAX_TCAM_TID;
}
+
+ if (is_t6(padap->params.chip))
+ tcam_region->max_tid += CUDBG_T6_CLIP;
}
int cudbg_collect_le_tcam(struct cudbg_init *pdbg_init,
for (i = 0; i < tcam_region.max_tid; ) {
rc = cudbg_read_tid(pdbg_init, i, tid_data);
if (rc) {
- cudbg_err->sys_err = rc;
- cudbg_put_buff(pdbg_init, &temp_buff);
- return rc;
+ cudbg_err->sys_warn = CUDBG_STATUS_PARTIAL_DATA;
+ /* Update tcam header and exit */
+ tcam_region.max_tid = i;
+ memcpy(temp_buff.data, &tcam_region,
+ sizeof(struct cudbg_tcam));
+ goto out;
}
- /* ipv6 takes two tids */
- cudbg_is_ipv6_entry(tid_data, tcam_region) ? i += 2 : i++;
+ if (cudbg_is_ipv6_entry(tid_data, tcam_region)) {
+ /* T6 CLIP TCAM: ipv6 takes 4 entries */
+ if (is_t6(padap->params.chip) &&
+ i >= tcam_region.clip_start &&
+ i < tcam_region.clip_start + CUDBG_T6_CLIP)
+ i += 4;
+ else /* Main TCAM: ipv6 takes two tids */
+ i += 2;
+ } else {
+ i++;
+ }
tid_data++;
bytes += sizeof(struct cudbg_tid_data);
}
+out:
return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
}
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/ptp_classify.h>
+#include <linux/crash_dump.h>
#include <asm/io.h>
#include "t4_chip_type.h"
#include "cxgb4_uld.h"
struct hma_data hma;
struct srq_data *srq;
+
+ /* Dump buffer for collecting logs in kdump kernel */
+ struct vmcoredd_data vmcoredd;
};
/* Support for "sched-class" command to allow a TX Scheduling Class to be
#define VF_BITWIDTH 8
#define IVLAN_BITWIDTH 16
#define OVLAN_BITWIDTH 16
+#define ENCAP_VNI_BITWIDTH 24
/* Filter matching rules. These consist of a set of ingress packet field
* (value, mask) tuples. The associated ingress packet field matches the
uint32_t ivlan_vld:1; /* inner VLAN valid */
uint32_t ovlan_vld:1; /* outer VLAN valid */
uint32_t pfvf_vld:1; /* PF/VF valid */
+ uint32_t encap_vld:1; /* Encapsulation valid */
uint32_t macidx:MACIDX_BITWIDTH; /* exact match MAC index */
uint32_t fcoe:FCOE_BITWIDTH; /* FCoE packet */
uint32_t iport:IPORT_BITWIDTH; /* ingress port */
uint32_t vf:VF_BITWIDTH; /* PCI-E VF ID */
uint32_t ivlan:IVLAN_BITWIDTH; /* inner VLAN */
uint32_t ovlan:OVLAN_BITWIDTH; /* outer VLAN */
+ uint32_t vni:ENCAP_VNI_BITWIDTH; /* VNI of tunnel */
/* Uncompressed header matching field rules. These are always
* available for field rules.
int t4_free_raw_mac_filt(struct adapter *adap, unsigned int viid,
const u8 *addr, const u8 *mask, unsigned int idx,
u8 lookup_type, u8 port_id, bool sleep_ok);
+int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid, int idx,
+ bool sleep_ok);
+int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ const u8 *addr, const u8 *mask, unsigned int vni,
+ unsigned int vni_mask, u8 dip_hit, u8 lookup_type,
+ bool sleep_ok);
int t4_alloc_raw_mac_filt(struct adapter *adap, unsigned int viid,
const u8 *addr, const u8 *mask, unsigned int idx,
u8 lookup_type, u8 port_id, bool sleep_ok);
len = sizeof(struct ireg_buf) * n;
break;
case CUDBG_SGE_INDIRECT:
- len = sizeof(struct ireg_buf) * 2;
+ len = sizeof(struct ireg_buf) * 2 +
+ sizeof(struct sge_qbase_reg_field);
break;
case CUDBG_ULPRX_LA:
len = sizeof(struct cudbg_ulprx_la);
adapter->eth_dump.version = adapter->params.fw_vers;
adapter->eth_dump.len = 0;
}
+
+static int cxgb4_cudbg_vmcoredd_collect(struct vmcoredd_data *data, void *buf)
+{
+ struct adapter *adap = container_of(data, struct adapter, vmcoredd);
+ u32 len = data->size;
+
+ return cxgb4_cudbg_collect(adap, buf, &len, CXGB4_ETH_DUMP_ALL);
+}
+
+int cxgb4_cudbg_vmcore_add_dump(struct adapter *adap)
+{
+ struct vmcoredd_data *data = &adap->vmcoredd;
+ u32 len;
+
+ len = sizeof(struct cudbg_hdr) +
+ sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY;
+ len += CUDBG_DUMP_BUFF_SIZE;
+
+ data->size = len;
+ snprintf(data->dump_name, sizeof(data->dump_name), "%s_%s",
+ cxgb4_driver_name, adap->name);
+ data->vmcoredd_callback = cxgb4_cudbg_vmcoredd_collect;
+
+ return vmcore_add_device_dump(data);
+}
CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */
};
+#define CXGB4_ETH_DUMP_ALL (CXGB4_ETH_DUMP_MEM | CXGB4_ETH_DUMP_HW)
+
u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag);
int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size,
u32 flag);
void cxgb4_init_ethtool_dump(struct adapter *adapter);
+int cxgb4_cudbg_vmcore_add_dump(struct adapter *adap);
#endif /* __CXGB4_CUDBG_H__ */
if (!skb)
return -ENOMEM;
- req = (struct cpl_set_tcb_field *)__skb_put(skb, sizeof(*req));
- memset(req, 0, sizeof(*req));
+ req = (struct cpl_set_tcb_field *)__skb_put_zero(skb, sizeof(*req));
INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, ftid);
req->reply_ctrl = htons(REPLY_CHAN_V(0) |
QUEUENO_V(adap->sge.fw_evtq.abs_id) |
fs->mask.pfvf_vld) ||
unsupported(fconf, VNIC_ID_F, fs->val.ovlan_vld,
fs->mask.ovlan_vld) ||
+ unsupported(fconf, VNIC_ID_F, fs->val.encap_vld,
+ fs->mask.encap_vld) ||
unsupported(fconf, VLAN_F, fs->val.ivlan_vld, fs->mask.ivlan_vld))
return -EOPNOTSUPP;
* carries that overlap, we need to translate any PF/VF
* specification into that internal format below.
*/
- if (is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
- is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld))
+ if ((is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
+ is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld)) ||
+ (is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
+ is_field_set(fs->val.encap_vld, fs->mask.encap_vld)) ||
+ (is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld) &&
+ is_field_set(fs->val.encap_vld, fs->mask.encap_vld)))
return -EOPNOTSUPP;
if (unsupported(iconf, VNIC_F, fs->val.pfvf_vld, fs->mask.pfvf_vld) ||
(is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld) &&
fs->newvlan == VLAN_REWRITE))
return -EOPNOTSUPP;
+ if (fs->val.encap_vld &&
+ CHELSIO_CHIP_VERSION(adapter->params.chip) < CHELSIO_T6)
+ return -EOPNOTSUPP;
return 0;
}
*/
void clear_filter(struct adapter *adap, struct filter_entry *f)
{
+ struct port_info *pi = netdev_priv(f->dev);
+
/* If the new or old filter have loopback rewriteing rules then we'll
* need to free any existing L2T, SMT, CLIP entries of filter
* rule.
if (f->smt)
cxgb4_smt_release(f->smt);
+ if (f->fs.val.encap_vld && f->fs.val.ovlan_vld)
+ if (atomic_dec_and_test(&adap->mps_encap[f->fs.val.ovlan &
+ 0x1ff].refcnt))
+ t4_free_encap_mac_filt(adap, pi->viid,
+ f->fs.val.ovlan & 0x1ff, 0);
+
if ((f->fs.hash || is_t6(adap->params.chip)) && f->fs.type)
cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
{
struct tp_params *tp = &adap->params.tp;
u64 hash_filter_mask = tp->hash_filter_mask;
- u32 mask;
+ u64 ntuple_mask = 0;
if (!is_hashfilter(adap))
return false;
+ /* Keep tunnel VNI match disabled for hash-filters for now */
+ if (fs->mask.encap_vld)
+ return false;
+
if (fs->type) {
if (is_inaddr_any(fs->val.fip, AF_INET6) ||
!is_addr_all_mask(fs->mask.fip, AF_INET6))
if (!fs->val.fport || fs->mask.fport != 0xffff)
return false;
- if (tp->fcoe_shift >= 0) {
- mask = (hash_filter_mask >> tp->fcoe_shift) & FT_FCOE_W;
- if (mask && !fs->mask.fcoe)
- return false;
- }
+ /* calculate tuple mask and compare with mask configured in hw */
+ if (tp->fcoe_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.fcoe << tp->fcoe_shift;
- if (tp->port_shift >= 0) {
- mask = (hash_filter_mask >> tp->port_shift) & FT_PORT_W;
- if (mask && !fs->mask.iport)
- return false;
- }
+ if (tp->port_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.iport << tp->port_shift;
if (tp->vnic_shift >= 0) {
- mask = (hash_filter_mask >> tp->vnic_shift) & FT_VNIC_ID_W;
-
- if ((adap->params.tp.ingress_config & VNIC_F)) {
- if (mask && !fs->mask.pfvf_vld)
- return false;
- } else {
- if (mask && !fs->mask.ovlan_vld)
- return false;
- }
+ if ((adap->params.tp.ingress_config & VNIC_F))
+ ntuple_mask |= (u64)fs->mask.pfvf_vld << tp->vnic_shift;
+ else
+ ntuple_mask |= (u64)fs->mask.ovlan_vld <<
+ tp->vnic_shift;
}
- if (tp->vlan_shift >= 0) {
- mask = (hash_filter_mask >> tp->vlan_shift) & FT_VLAN_W;
- if (mask && !fs->mask.ivlan)
- return false;
- }
+ if (tp->vlan_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.ivlan << tp->vlan_shift;
- if (tp->tos_shift >= 0) {
- mask = (hash_filter_mask >> tp->tos_shift) & FT_TOS_W;
- if (mask && !fs->mask.tos)
- return false;
- }
+ if (tp->tos_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.tos << tp->tos_shift;
- if (tp->protocol_shift >= 0) {
- mask = (hash_filter_mask >> tp->protocol_shift) & FT_PROTOCOL_W;
- if (mask && !fs->mask.proto)
- return false;
- }
+ if (tp->protocol_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.proto << tp->protocol_shift;
- if (tp->ethertype_shift >= 0) {
- mask = (hash_filter_mask >> tp->ethertype_shift) &
- FT_ETHERTYPE_W;
- if (mask && !fs->mask.ethtype)
- return false;
- }
+ if (tp->ethertype_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.ethtype << tp->ethertype_shift;
- if (tp->macmatch_shift >= 0) {
- mask = (hash_filter_mask >> tp->macmatch_shift) & FT_MACMATCH_W;
- if (mask && !fs->mask.macidx)
- return false;
- }
+ if (tp->macmatch_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.macidx << tp->macmatch_shift;
+
+ if (tp->matchtype_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.matchtype << tp->matchtype_shift;
+
+ if (tp->frag_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.frag << tp->frag_shift;
+
+ if (ntuple_mask != hash_filter_mask)
+ return false;
- if (tp->matchtype_shift >= 0) {
- mask = (hash_filter_mask >> tp->matchtype_shift) &
- FT_MPSHITTYPE_W;
- if (mask && !fs->mask.matchtype)
- return false;
- }
- if (tp->frag_shift >= 0) {
- mask = (hash_filter_mask >> tp->frag_shift) &
- FT_FRAGMENTATION_W;
- if (mask && !fs->mask.frag)
- return false;
- }
return true;
}
ntuple |= (u64)(fs->val.tos) << tp->tos_shift;
if (tp->vnic_shift >= 0) {
- if ((adap->params.tp.ingress_config & VNIC_F) &&
- fs->mask.pfvf_vld)
+ if ((adap->params.tp.ingress_config & USE_ENC_IDX_F) &&
+ fs->mask.encap_vld)
+ ntuple |= (u64)((fs->val.encap_vld << 16) |
+ (fs->val.ovlan)) << tp->vnic_shift;
+ else if ((adap->params.tp.ingress_config & VNIC_F) &&
+ fs->mask.pfvf_vld)
ntuple |= (u64)((fs->val.pfvf_vld << 16) |
(fs->val.pf << 13) |
(fs->val.vf)) << tp->vnic_shift;
struct filter_ctx *ctx)
{
struct adapter *adapter = netdev2adap(dev);
+ struct port_info *pi = netdev_priv(dev);
struct tid_info *t = &adapter->tids;
struct filter_entry *f;
struct sk_buff *skb;
f->fs.mask.ovlan = (fs->mask.pf << 13) | fs->mask.vf;
f->fs.val.ovlan_vld = fs->val.pfvf_vld;
f->fs.mask.ovlan_vld = fs->mask.pfvf_vld;
+ } else if (iconf & USE_ENC_IDX_F) {
+ if (f->fs.val.encap_vld) {
+ struct port_info *pi = netdev_priv(f->dev);
+ u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+
+ /* allocate MPS TCAM entry */
+ ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
+ match_all_mac,
+ match_all_mac,
+ f->fs.val.vni,
+ f->fs.mask.vni,
+ 0, 1, 1);
+ if (ret < 0)
+ goto free_atid;
+
+ atomic_inc(&adapter->mps_encap[ret].refcnt);
+ f->fs.val.ovlan = ret;
+ f->fs.mask.ovlan = 0xffff;
+ f->fs.val.ovlan_vld = 1;
+ f->fs.mask.ovlan_vld = 1;
+ }
}
size = sizeof(struct cpl_t6_act_open_req);
if (f->fs.type) {
ret = cxgb4_clip_get(f->dev, (const u32 *)&f->fs.val.lip, 1);
if (ret)
- goto free_atid;
+ goto free_mps;
skb = alloc_skb(size, GFP_KERNEL);
if (!skb) {
skb = alloc_skb(size, GFP_KERNEL);
if (!skb) {
ret = -ENOMEM;
- goto free_atid;
+ goto free_mps;
}
mk_act_open_req(f, skb,
free_clip:
cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+free_mps:
+ if (f->fs.val.encap_vld && f->fs.val.ovlan_vld)
+ t4_free_encap_mac_filt(adapter, pi->viid, f->fs.val.ovlan, 1);
+
free_atid:
cxgb4_free_atid(t, atid);
f->fs.mask.ovlan = (fs->mask.pf << 13) | fs->mask.vf;
f->fs.val.ovlan_vld = fs->val.pfvf_vld;
f->fs.mask.ovlan_vld = fs->mask.pfvf_vld;
+ } else if (iconf & USE_ENC_IDX_F) {
+ if (f->fs.val.encap_vld) {
+ struct port_info *pi = netdev_priv(f->dev);
+ u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+
+ /* allocate MPS TCAM entry */
+ ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
+ match_all_mac,
+ match_all_mac,
+ f->fs.val.vni,
+ f->fs.mask.vni,
+ 0, 1, 1);
+ if (ret < 0)
+ goto free_clip;
+
+ atomic_inc(&adapter->mps_encap[ret].refcnt);
+ f->fs.val.ovlan = ret;
+ f->fs.mask.ovlan = 0x1ff;
+ f->fs.val.ovlan_vld = 1;
+ f->fs.mask.ovlan_vld = 1;
+ }
}
/* Attempt to set the filter. If we don't succeed, we clear
}
return ret;
+
+free_clip:
+ if (is_t6(adapter->params.chip) && f->fs.type)
+ cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+ cxgb4_clear_ftid(&adapter->tids, filter_id,
+ fs->type ? PF_INET6 : PF_INET, chip_ver);
+ return ret;
}
static int cxgb4_del_hash_filter(struct net_device *dev, int filter_id,
}
/* Convert from Mbps to Kbps */
- req_rate = rate << 10;
+ req_rate = rate * 1000;
/* Max rate is 100 Gbps */
- if (req_rate >= SCHED_MAX_RATE_KBPS) {
+ if (req_rate > SCHED_MAX_RATE_KBPS) {
dev_err(adap->pdev_dev,
"Invalid rate %u Mbps, Max rate is %u Mbps\n",
- rate, SCHED_MAX_RATE_KBPS >> 10);
+ rate, SCHED_MAX_RATE_KBPS / 1000);
return -ERANGE;
}
match_all_mac, match_all_mac,
adapter->rawf_start +
pi->port_id,
- 1, pi->port_id, true);
+ 1, pi->port_id, false);
if (ret < 0) {
netdev_info(netdev, "Failed to free mac filter entry, for port %d\n",
i);
match_all_mac,
adapter->rawf_start +
pi->port_id,
- 1, pi->port_id, true);
+ 1, pi->port_id, false);
if (ret < 0) {
netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n",
be16_to_cpu(ti->port));
sgl = adapter->hma.sgt->sgl;
node = dev_to_node(adapter->pdev_dev);
for_each_sg(sgl, iter, sgt->orig_nents, i) {
- newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL,
- page_order);
+ newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL |
+ __GFP_ZERO, page_order);
if (!newpage) {
dev_err(adapter->pdev_dev,
"Not enough memory for HMA page allocation\n");
adap->tids.nftids = val[4] - val[3] + 1;
adap->sge.ingr_start = val[5];
+ if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
+ /* Read the raw mps entries. In T6, the last 2 tcam entries
+ * are reserved for raw mac addresses (rawf = 2, one per port).
+ */
+ params[0] = FW_PARAM_PFVF(RAWF_START);
+ params[1] = FW_PARAM_PFVF(RAWF_END);
+ ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
+ params, val);
+ if (ret == 0) {
+ adap->rawf_start = val[0];
+ adap->rawf_cnt = val[1] - val[0] + 1;
+ }
+ }
+
/* qids (ingress/egress) returned from firmware can be anywhere
* in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END.
* Hence driver needs to allocate memory for this range to
{
unsigned int i;
+ kvfree(adapter->mps_encap);
kvfree(adapter->smt);
kvfree(adapter->l2t);
kvfree(adapter->srq);
u32 pcie_fw;
pcie_fw = readl(adap->regs + PCIE_FW_A);
- /* Check if cxgb4 is the MASTER and fw is initialized */
- if (num_vfs &&
- (!(pcie_fw & PCIE_FW_INIT_F) ||
- !(pcie_fw & PCIE_FW_MASTER_VLD_F) ||
- PCIE_FW_MASTER_G(pcie_fw) != CXGB4_UNIFIED_PF)) {
- dev_warn(&pdev->dev,
- "cxgb4 driver needs to be MASTER to support SRIOV\n");
+ /* Check if fw is initialized */
+ if (!(pcie_fw & PCIE_FW_INIT_F)) {
+ dev_warn(&pdev->dev, "Device not initialized\n");
return -EOPNOTSUPP;
}
}
spin_lock_init(&adapter->mbox_lock);
INIT_LIST_HEAD(&adapter->mlist.list);
+ adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
pci_set_drvdata(pdev, adapter);
if (func != ent->driver_data) {
goto out_free_adapter;
}
- adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
-
/* PCI device has been enabled */
adapter->flags |= DEV_ENABLED;
memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
if (err)
goto out_free_adapter;
+ if (is_kdump_kernel()) {
+ /* Collect hardware state and append to /proc/vmcore */
+ err = cxgb4_cudbg_vmcore_add_dump(adapter);
+ if (err) {
+ dev_warn(adapter->pdev_dev,
+ "Fail collecting vmcore device dump, err: %d. Continuing\n",
+ err);
+ err = 0;
+ }
+ }
if (!is_t4(adapter->params.chip)) {
s_qpp = (QUEUESPERPAGEPF0_S +
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_TC;
- if (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5)
+ if (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5) {
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_RXCSUM |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_TSO | NETIF_F_TSO6;
+
netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+ }
if (highdma)
netdev->hw_features |= NETIF_F_HIGHDMA;
adapter->params.offload = 0;
}
+ adapter->mps_encap = kvzalloc(sizeof(struct mps_encap_entry) *
+ adapter->params.arch.mps_tcam_size,
+ GFP_KERNEL);
+ if (!adapter->mps_encap)
+ dev_warn(&pdev->dev, "could not allocate MPS Encap entries, continuing\n");
+
#if IS_ENABLED(CONFIG_IPV6)
if ((CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) &&
(!(t4_read_reg(adapter, LE_DB_CONFIG_A) & ASLIPCOMPEN_F))) {
fs->mask.tos = mask->tos;
}
+ if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *key, *mask;
+
+ key = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ cls->key);
+ mask = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ cls->mask);
+ fs->val.vni = be32_to_cpu(key->keyid);
+ fs->mask.vni = be32_to_cpu(mask->keyid);
+ if (fs->mask.vni) {
+ fs->val.encap_vld = 1;
+ fs->mask.encap_vld = 1;
+ }
+ }
+
if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
struct flow_dissector_key_vlan *key, *mask;
u16 vlan_tci, vlan_tci_mask;
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
BIT(FLOW_DISSECTOR_KEY_VLAN) |
BIT(FLOW_DISSECTOR_KEY_IP))) {
netdev_warn(dev, "Unsupported key used: 0x%x\n",
if (tp->protocol_shift >= 0)
ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
- if (tp->vnic_shift >= 0) {
+ if (tp->vnic_shift >= 0 && (tp->ingress_config & VNIC_F)) {
u32 viid = cxgb4_port_viid(dev);
u32 vf = FW_VIID_VIN_G(viid);
u32 pf = FW_VIID_PFN_G(viid);
static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb)
{
int csum_type;
- const struct iphdr *iph = ip_hdr(skb);
+ bool inner_hdr_csum = false;
+ u16 proto, ver;
- if (iph->version == 4) {
- if (iph->protocol == IPPROTO_TCP)
+ if (skb->encapsulation &&
+ (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5))
+ inner_hdr_csum = true;
+
+ if (inner_hdr_csum) {
+ ver = inner_ip_hdr(skb)->version;
+ proto = (ver == 4) ? inner_ip_hdr(skb)->protocol :
+ inner_ipv6_hdr(skb)->nexthdr;
+ } else {
+ ver = ip_hdr(skb)->version;
+ proto = (ver == 4) ? ip_hdr(skb)->protocol :
+ ipv6_hdr(skb)->nexthdr;
+ }
+
+ if (ver == 4) {
+ if (proto == IPPROTO_TCP)
csum_type = TX_CSUM_TCPIP;
- else if (iph->protocol == IPPROTO_UDP)
+ else if (proto == IPPROTO_UDP)
csum_type = TX_CSUM_UDPIP;
else {
nocsum: /*
/*
* this doesn't work with extension headers
*/
- const struct ipv6hdr *ip6h = (const struct ipv6hdr *)iph;
-
- if (ip6h->nexthdr == IPPROTO_TCP)
+ if (proto == IPPROTO_TCP)
csum_type = TX_CSUM_TCPIP6;
- else if (ip6h->nexthdr == IPPROTO_UDP)
+ else if (proto == IPPROTO_UDP)
csum_type = TX_CSUM_UDPIP6;
else
goto nocsum;
}
if (likely(csum_type >= TX_CSUM_TCPIP)) {
- u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb));
- int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN;
+ int eth_hdr_len, l4_len;
+ u64 hdr_len;
+
+ if (inner_hdr_csum) {
+ /* This allows checksum offload for all encapsulated
+ * packets like GRE etc..
+ */
+ l4_len = skb_inner_network_header_len(skb);
+ eth_hdr_len = skb_inner_network_offset(skb) - ETH_HLEN;
+ } else {
+ l4_len = skb_network_header_len(skb);
+ eth_hdr_len = skb_network_offset(skb) - ETH_HLEN;
+ }
+ hdr_len = TXPKT_IPHDR_LEN_V(l4_len);
if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5)
hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len);
netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
{
u32 wr_mid, ctrl0, op;
- u64 cntrl, *end;
+ u64 cntrl, *end, *sgl;
int qidx, credits;
unsigned int flits, ndesc;
struct adapter *adap;
end = (u64 *)wr + flits;
len = immediate ? skb->len : 0;
+ len += sizeof(*cpl);
if (ssi->gso_size) {
- struct cpl_tx_pkt_lso *lso = (void *)wr;
+ struct cpl_tx_pkt_lso_core *lso = (void *)(wr + 1);
bool v6 = (ssi->gso_type & SKB_GSO_TCPV6) != 0;
int l3hdr_len = skb_network_header_len(skb);
int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN;
if (skb->ip_summed == CHECKSUM_PARTIAL)
cntrl = hwcsum(adap->params.chip, skb);
} else {
- lso->c.lso_ctrl = htonl(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
- LSO_FIRST_SLICE_F | LSO_LAST_SLICE_F |
- LSO_IPV6_V(v6) |
- LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
- LSO_IPHDR_LEN_V(l3hdr_len / 4) |
- LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
- lso->c.ipid_ofst = htons(0);
- lso->c.mss = htons(ssi->gso_size);
- lso->c.seqno_offset = htonl(0);
+ lso->lso_ctrl = htonl(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+ LSO_FIRST_SLICE_F | LSO_LAST_SLICE_F |
+ LSO_IPV6_V(v6) |
+ LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+ LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+ LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
+ lso->ipid_ofst = htons(0);
+ lso->mss = htons(ssi->gso_size);
+ lso->seqno_offset = htonl(0);
if (is_t4(adap->params.chip))
- lso->c.len = htonl(skb->len);
+ lso->len = htonl(skb->len);
else
- lso->c.len =
- htonl(LSO_T5_XFER_SIZE_V(skb->len));
+ lso->len = htonl(LSO_T5_XFER_SIZE_V(skb->len));
cpl = (void *)(lso + 1);
if (CHELSIO_CHIP_VERSION(adap->params.chip)
TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
TXPKT_IPHDR_LEN_V(l3hdr_len);
}
+ sgl = (u64 *)(cpl + 1); /* sgl start here */
+ if (unlikely((u8 *)sgl >= (u8 *)q->q.stat)) {
+ /* If current position is already at the end of the
+ * txq, reset the current to point to start of the queue
+ * and update the end ptr as well.
+ */
+ if (sgl == (u64 *)q->q.stat) {
+ int left = (u8 *)end - (u8 *)q->q.stat;
+
+ end = (void *)q->q.desc + left;
+ sgl = (void *)q->q.desc;
+ }
+ }
q->tso++;
q->tx_cso += ssi->gso_segs;
} else {
- len += sizeof(*cpl);
if (ptp_enabled)
op = FW_PTP_TX_PKT_WR;
else
wr->op_immdlen = htonl(FW_WR_OP_V(op) |
FW_WR_IMMDLEN_V(len));
cpl = (void *)(wr + 1);
+ sgl = (u64 *)(cpl + 1);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
cntrl = hwcsum(adap->params.chip, skb) |
TXPKT_IPCSUM_DIS_F;
cpl->ctrl1 = cpu_to_be64(cntrl);
if (immediate) {
- cxgb4_inline_tx_skb(skb, &q->q, cpl + 1);
+ cxgb4_inline_tx_skb(skb, &q->q, sgl);
dev_consume_skb_any(skb);
} else {
int last_desc;
- cxgb4_write_sgl(skb, &q->q, (struct ulptx_sgl *)(cpl + 1),
- end, 0, addr);
+ cxgb4_write_sgl(skb, &q->q, (void *)sgl, end, 0, addr);
skb_orphan(skb);
last_desc = q->q.pidx + ndesc - 1;
if (last_desc >= q->q.size)
last_desc -= q->q.size;
q->q.sdesc[last_desc].skb = skb;
- q->q.sdesc[last_desc].sgl = (struct ulptx_sgl *)(cpl + 1);
+ q->q.sdesc[last_desc].sgl = (struct ulptx_sgl *)sgl;
}
txq_advance(&q->q, ndesc);
}
static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl,
- const struct cpl_rx_pkt *pkt)
+ const struct cpl_rx_pkt *pkt, unsigned long tnl_hdr_len)
{
struct adapter *adapter = rxq->rspq.adap;
struct sge *s = &adapter->sge;
}
copy_frags(skb, gl, s->pktshift);
+ if (tnl_hdr_len)
+ skb->csum_level = 1;
skb->len = gl->tot_len - s->pktshift;
skb->data_len = skb->len;
skb->truesize += skb->data_len;
struct sge *s = &q->adap->sge;
int cpl_trace_pkt = is_t4(q->adap->params.chip) ?
CPL_TRACE_PKT : CPL_TRACE_PKT_T5;
- u16 err_vec;
+ u16 err_vec, tnl_hdr_len = 0;
struct port_info *pi;
int ret = 0;
pkt = (const struct cpl_rx_pkt *)rsp;
/* Compressed error vector is enabled for T6 only */
- if (q->adap->params.tp.rx_pkt_encap)
+ if (q->adap->params.tp.rx_pkt_encap) {
err_vec = T6_COMPR_RXERR_VEC_G(be16_to_cpu(pkt->err_vec));
- else
+ tnl_hdr_len = T6_RX_TNLHDR_LEN_G(ntohs(pkt->err_vec));
+ } else {
err_vec = be16_to_cpu(pkt->err_vec);
+ }
csum_ok = pkt->csum_calc && !err_vec &&
(q->netdev->features & NETIF_F_RXCSUM);
- if ((pkt->l2info & htonl(RXF_TCP_F)) &&
+ if (((pkt->l2info & htonl(RXF_TCP_F)) ||
+ tnl_hdr_len) &&
(q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) {
- do_gro(rxq, si, pkt);
+ do_gro(rxq, si, pkt, tnl_hdr_len);
return 0;
}
} else if (pkt->l2info & htonl(RXF_IP_F)) {
__sum16 c = (__force __sum16)pkt->csum;
skb->csum = csum_unfold(c);
- skb->ip_summed = CHECKSUM_COMPLETE;
+
+ if (tnl_hdr_len) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->csum_level = 1;
+ } else {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ }
rxq->stats.rx_cso++;
}
} else {
if (!skb)
return -ENOMEM;
req = (struct cpl_srq_table_req *)
- __skb_put(skb, sizeof(*req));
- memset(req, 0, sizeof(*req));
+ __skb_put_zero(skb, sizeof(*req));
INIT_TP_WR(req, 0);
OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SRQ_TABLE_REQ,
TID_TID_V(srq_idx) |
return t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), NULL, sleep_ok);
}
+/**
+ * t4_free_encap_mac_filt - frees MPS entry at given index
+ * @adap: the adapter
+ * @viid: the VI id
+ * @idx: index of MPS entry to be freed
+ * @sleep_ok: call is allowed to sleep
+ *
+ * Frees the MPS entry at supplied index
+ *
+ * Returns a negative error number or zero on success
+ */
+int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ int idx, bool sleep_ok)
+{
+ struct fw_vi_mac_exact *p;
+ u8 addr[] = {0, 0, 0, 0, 0, 0};
+ struct fw_vi_mac_cmd c;
+ int ret = 0;
+ u32 exact;
+
+ memset(&c, 0, sizeof(c));
+ c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+ FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+ FW_CMD_EXEC_V(0) |
+ FW_VI_MAC_CMD_VIID_V(viid));
+ exact = FW_VI_MAC_CMD_ENTRY_TYPE_V(FW_VI_MAC_TYPE_EXACTMAC);
+ c.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS_V(0) |
+ exact |
+ FW_CMD_LEN16_V(1));
+ p = c.u.exact;
+ p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+ FW_VI_MAC_CMD_IDX_V(idx));
+ memcpy(p->macaddr, addr, sizeof(p->macaddr));
+ ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
+ return ret;
+}
+
/**
* t4_free_raw_mac_filt - Frees a raw mac entry in mps tcam
* @adap: the adapter
return t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
}
+/**
+ * t4_alloc_encap_mac_filt - Adds a mac entry in mps tcam with VNI support
+ * @adap: the adapter
+ * @viid: the VI id
+ * @mac: the MAC address
+ * @mask: the mask
+ * @vni: the VNI id for the tunnel protocol
+ * @vni_mask: mask for the VNI id
+ * @dip_hit: to enable DIP match for the MPS entry
+ * @lookup_type: MAC address for inner (1) or outer (0) header
+ * @sleep_ok: call is allowed to sleep
+ *
+ * Allocates an MPS entry with specified MAC address and VNI value.
+ *
+ * Returns a negative error number or the allocated index for this mac.
+ */
+int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ const u8 *addr, const u8 *mask, unsigned int vni,
+ unsigned int vni_mask, u8 dip_hit, u8 lookup_type,
+ bool sleep_ok)
+{
+ struct fw_vi_mac_cmd c;
+ struct fw_vi_mac_vni *p = c.u.exact_vni;
+ int ret = 0;
+ u32 val;
+
+ memset(&c, 0, sizeof(c));
+ c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+ FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+ FW_VI_MAC_CMD_VIID_V(viid));
+ val = FW_CMD_LEN16_V(1) |
+ FW_VI_MAC_CMD_ENTRY_TYPE_V(FW_VI_MAC_TYPE_EXACTMAC_VNI);
+ c.freemacs_to_len16 = cpu_to_be32(val);
+ p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+ FW_VI_MAC_CMD_IDX_V(FW_VI_MAC_ADD_MAC));
+ memcpy(p->macaddr, addr, sizeof(p->macaddr));
+ memcpy(p->macaddr_mask, mask, sizeof(p->macaddr_mask));
+
+ p->lookup_type_to_vni =
+ cpu_to_be32(FW_VI_MAC_CMD_VNI_V(vni) |
+ FW_VI_MAC_CMD_DIP_HIT_V(dip_hit) |
+ FW_VI_MAC_CMD_LOOKUP_TYPE_V(lookup_type));
+ p->vni_mask_pkd = cpu_to_be32(FW_VI_MAC_CMD_VNI_MASK_V(vni_mask));
+ ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
+ if (ret == 0)
+ ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
+ return ret;
+}
+
/**
* t4_alloc_raw_mac_filt - Adds a mac entry in mps tcam
* @adap: the adapter
#define T6_COMPR_RXERR_SUM_V(x) ((x) << T6_COMPR_RXERR_SUM_S)
#define T6_COMPR_RXERR_SUM_F T6_COMPR_RXERR_SUM_V(1U)
+#define T6_RX_TNLHDR_LEN_S 8
+#define T6_RX_TNLHDR_LEN_M 0xFF
+#define T6_RX_TNLHDR_LEN_V(x) ((x) << T6_RX_TNLHDR_LEN_S)
+#define T6_RX_TNLHDR_LEN_G(x) (((x) >> T6_RX_TNLHDR_LEN_S) & T6_RX_TNLHDR_LEN_M)
+
struct cpl_trace_pkt {
u8 opcode;
u8 intf;
CH_PCI_ID_TABLE_FENTRY(0x5016), /* T580-OCP-SO */
CH_PCI_ID_TABLE_FENTRY(0x5017), /* T520-OCP-SO */
CH_PCI_ID_TABLE_FENTRY(0x5018), /* T540-BT */
+ CH_PCI_ID_TABLE_FENTRY(0x5019), /* T540-LP-BT */
+ CH_PCI_ID_TABLE_FENTRY(0x501a), /* T540-SO-BT */
+ CH_PCI_ID_TABLE_FENTRY(0x501b), /* T540-SO-CR */
CH_PCI_ID_TABLE_FENTRY(0x5080), /* Custom T540-cr */
CH_PCI_ID_TABLE_FENTRY(0x5081), /* Custom T540-LL-cr */
CH_PCI_ID_TABLE_FENTRY(0x5082), /* Custom T504-cr */
CH_PCI_ID_TABLE_FENTRY(0x50aa), /* Custom T580-CR */
CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */
CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */
+ CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */
/* T6 adapters:
*/
#define VNIC_V(x) ((x) << VNIC_S)
#define VNIC_F VNIC_V(1U)
+#define USE_ENC_IDX_S 13
+#define USE_ENC_IDX_V(x) ((x) << USE_ENC_IDX_S)
+#define USE_ENC_IDX_F USE_ENC_IDX_V(1U)
+
#define CSUM_HAS_PSEUDO_HDR_S 10
#define CSUM_HAS_PSEUDO_HDR_V(x) ((x) << CSUM_HAS_PSEUDO_HDR_S)
#define CSUM_HAS_PSEUDO_HDR_F CSUM_HAS_PSEUDO_HDR_V(1U)
#define LE_DB_HASH_TID_BASE_A 0x19c30
#define LE_DB_HASH_TBL_BASE_ADDR_A 0x19c30
#define LE_DB_INT_CAUSE_A 0x19c3c
+#define LE_DB_CLCAM_TID_BASE_A 0x19df4
#define LE_DB_TID_HASHBASE_A 0x19df8
#define T6_LE_DB_HASH_TID_BASE_A 0x19df8
FW_PARAMS_PARAM_PFVF_HPFILTER_END = 0x33,
FW_PARAMS_PARAM_PFVF_TLS_START = 0x34,
FW_PARAMS_PARAM_PFVF_TLS_END = 0x35,
+ FW_PARAMS_PARAM_PFVF_RAWF_START = 0x36,
+ FW_PARAMS_PARAM_PFVF_RAWF_END = 0x37,
FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x39,
FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A,
};
__be64 data0m_pkd;
__be32 data1m[2];
} raw;
+ struct fw_vi_mac_vni {
+ __be16 valid_to_idx;
+ __u8 macaddr[6];
+ __be16 r7;
+ __u8 macaddr_mask[6];
+ __be32 lookup_type_to_vni;
+ __be32 vni_mask_pkd;
+ } exact_vni[2];
} u;
};
#define FW_VI_MAC_CMD_RAW_IDX_G(x) \
(((x) >> FW_VI_MAC_CMD_RAW_IDX_S) & FW_VI_MAC_CMD_RAW_IDX_M)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_S 31
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_M 0x1
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_V(x) ((x) << FW_VI_MAC_CMD_LOOKUP_TYPE_S)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_G(x) \
+ (((x) >> FW_VI_MAC_CMD_LOOKUP_TYPE_S) & FW_VI_MAC_CMD_LOOKUP_TYPE_M)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_F FW_VI_MAC_CMD_LOOKUP_TYPE_V(1U)
+
+#define FW_VI_MAC_CMD_DIP_HIT_S 30
+#define FW_VI_MAC_CMD_DIP_HIT_M 0x1
+#define FW_VI_MAC_CMD_DIP_HIT_V(x) ((x) << FW_VI_MAC_CMD_DIP_HIT_S)
+#define FW_VI_MAC_CMD_DIP_HIT_G(x) \
+ (((x) >> FW_VI_MAC_CMD_DIP_HIT_S) & FW_VI_MAC_CMD_DIP_HIT_M)
+#define FW_VI_MAC_CMD_DIP_HIT_F FW_VI_MAC_CMD_DIP_HIT_V(1U)
+
+#define FW_VI_MAC_CMD_VNI_S 0
+#define FW_VI_MAC_CMD_VNI_M 0xffffff
+#define FW_VI_MAC_CMD_VNI_V(x) ((x) << FW_VI_MAC_CMD_VNI_S)
+#define FW_VI_MAC_CMD_VNI_G(x) \
+ (((x) >> FW_VI_MAC_CMD_VNI_S) & FW_VI_MAC_CMD_VNI_M)
+
+#define FW_VI_MAC_CMD_VNI_MASK_S 0
+#define FW_VI_MAC_CMD_VNI_MASK_M 0xffffff
+#define FW_VI_MAC_CMD_VNI_MASK_V(x) ((x) << FW_VI_MAC_CMD_VNI_MASK_S)
+#define FW_VI_MAC_CMD_VNI_MASK_G(x) \
+ (((x) >> FW_VI_MAC_CMD_VNI_MASK_S) & FW_VI_MAC_CMD_VNI_MASK_M)
+
#define FW_RXMODE_MTU_NO_CHG 65535
struct fw_vi_rxmode_cmd {
#define __T4FW_VERSION_H__
#define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x10
-#define T4FW_VERSION_MICRO 0x3F
+#define T4FW_VERSION_MINOR 0x13
+#define T4FW_VERSION_MICRO 0x01
#define T4FW_VERSION_BUILD 0x00
#define T4FW_MIN_VERSION_MAJOR 0x01
#define T4FW_MIN_VERSION_MICRO 0x00
#define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x10
-#define T5FW_VERSION_MICRO 0x3F
+#define T5FW_VERSION_MINOR 0x13
+#define T5FW_VERSION_MICRO 0x01
#define T5FW_VERSION_BUILD 0x00
#define T5FW_MIN_VERSION_MAJOR 0x00
#define T5FW_MIN_VERSION_MICRO 0x00
#define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x10
-#define T6FW_VERSION_MICRO 0x3F
+#define T6FW_VERSION_MINOR 0x13
+#define T6FW_VERSION_MICRO 0x01
#define T6FW_VERSION_BUILD 0x00
#define T6FW_MIN_VERSION_MAJOR 0x00
{
struct cpl_tid_release *req;
- req = __skb_put(skb, len);
- memset(req, 0, len);
+ req = __skb_put_zero(skb, len);
INIT_TP_WR(req, tid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_TID_RELEASE, tid));
{
struct cpl_close_con_req *req;
- req = __skb_put(skb, len);
- memset(req, 0, len);
+ req = __skb_put_zero(skb, len);
INIT_TP_WR(req, tid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid));
{
struct cpl_abort_req *req;
- req = __skb_put(skb, len);
- memset(req, 0, len);
+ req = __skb_put_zero(skb, len);
INIT_TP_WR(req, tid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, tid));
{
struct cpl_abort_rpl *rpl;
- rpl = __skb_put(skb, len);
- memset(rpl, 0, len);
+ rpl = __skb_put_zero(skb, len);
INIT_TP_WR(rpl, tid);
OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, tid));
{
struct cpl_rx_data_ack *req;
- req = __skb_put(skb, len);
- memset(req, 0, len);
+ req = __skb_put_zero(skb, len);
INIT_TP_WR(req, tid);
OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, tid));
mdiobus_unregister(priv->mdio);
mdiobus_free(priv->mdio);
free2:
- if (priv->clk)
- clk_disable_unprepare(priv->clk);
+ clk_disable_unprepare(priv->clk);
free:
free_netdev(netdev);
out:
mdiobus_unregister(priv->mdio);
mdiobus_free(priv->mdio);
}
- if (priv->clk)
- clk_disable_unprepare(priv->clk);
+ clk_disable_unprepare(priv->clk);
unregister_netdev(netdev);
free_netdev(netdev);
}
config FEC
tristate "FEC ethernet controller (of ColdFire and some i.MX CPUs)"
depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \
- ARCH_MXC || SOC_IMX28)
+ ARCH_MXC || SOC_IMX28 || COMPILE_TEST)
default ARCH_MXC || SOC_IMX28 if ARM
select PHYLIB
imply PTP_1588_CLOCK
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
- defined(CONFIG_ARM64)
+ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
/*
* Just figures, Motorola would have to change the offsets for
* registers in the same peripheral device on different models
fep->mii_bus->parent = &pdev->dev;
node = of_get_child_by_name(pdev->dev.of_node, "mdio");
- if (node) {
- err = of_mdiobus_register(fep->mii_bus, node);
+ err = of_mdiobus_register(fep->mii_bus, node);
+ if (node)
of_node_put(node);
- } else {
- err = mdiobus_register(fep->mii_bus);
- }
-
if (err)
goto err_out_free_mdiobus;
/* List of registers that can be safety be read to dump them with ethtool */
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
- defined(CONFIG_ARM64)
+ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
static u32 fec_enet_register_offset[] = {
FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
/* FM_WRONG_RESET_VALUES_ERRATA_FMAN_A005127 Errata
* workaround
*/
- if (port->rev_info.major >= 6) {
- u32 reg;
+ u32 reg;
- reg = 0x00001013;
- iowrite32be(reg, &port->bmi_regs->tx.fmbm_tfp);
- }
+ reg = 0x00001013;
+ iowrite32be(reg, &port->bmi_regs->tx.fmbm_tfp);
}
return 0;
static const char tx_fw_stat_gstrings[][ETH_GSTRING_LEN] = {
"tx-single-collision",
"tx-multiple-collision",
- "tx-late-collsion",
+ "tx-late-collision",
"tx-aborted-frames",
"tx-lost-frames",
"tx-carrier-sense-errors",
/* now, (un-)instantiate client by calling lower layer */
if (is_reg) {
ret = ae_dev->ops->init_client_instance(client, ae_dev);
- if (ret)
+ if (ret) {
dev_err(&ae_dev->pdev->dev,
"fail to instantiate client\n");
- return ret;
+ return ret;
+ }
+
+ hnae_set_bit(ae_dev->flag, HNAE3_CLIENT_INITED_B, 1);
+ return 0;
+ }
+
+ if (hnae_get_bit(ae_dev->flag, HNAE3_CLIENT_INITED_B)) {
+ ae_dev->ops->uninit_client_instance(client, ae_dev);
+
+ hnae_set_bit(ae_dev->flag, HNAE3_CLIENT_INITED_B, 0);
}
- ae_dev->ops->uninit_client_instance(client, ae_dev);
return 0;
}
exit:
mutex_unlock(&hnae3_common_lock);
- return ret;
+ return 0;
}
EXPORT_SYMBOL(hnae3_register_client);
* @ae_algo: AE algorithm
* NOTE: the duplicated name will not be checked
*/
-int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
+void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
{
const struct pci_device_id *id;
struct hnae3_ae_dev *ae_dev;
}
mutex_unlock(&hnae3_common_lock);
-
- return ret;
}
EXPORT_SYMBOL(hnae3_register_ae_algo);
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_dev */
list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
+ if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+ continue;
+
id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
if (!id)
continue;
* @ae_dev: the AE device
* NOTE: the duplicated name will not be checked
*/
-int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
+void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
{
const struct pci_device_id *id;
struct hnae3_ae_algo *ae_algo;
struct hnae3_client *client;
- int ret = 0, lock_acquired;
+ int ret = 0;
- /* we can get deadlocked if SRIOV is being enabled in context to probe
- * and probe gets called again in same context. This can happen when
- * pci_enable_sriov() is called to create VFs from PF probes context.
- * Therefore, for simplicity uniformly defering further probing in all
- * cases where we detect contention.
- */
- lock_acquired = mutex_trylock(&hnae3_common_lock);
- if (!lock_acquired)
- return -EPROBE_DEFER;
+ mutex_lock(&hnae3_common_lock);
list_add_tail(&ae_dev->node, &hnae3_ae_dev_list);
if (!ae_dev->ops) {
dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n");
- ret = -EOPNOTSUPP;
goto out_err;
}
out_err:
mutex_unlock(&hnae3_common_lock);
-
- return ret;
}
EXPORT_SYMBOL(hnae3_register_ae_dev);
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_algo */
list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
+ if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+ continue;
+
id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
if (!id)
continue;
MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("HNAE3(Hisilicon Network Acceleration Engine) Framework");
+MODULE_VERSION(HNAE3_MOD_VERSION);
#include <linux/pci.h>
#include <linux/types.h>
+#define HNAE3_MOD_VERSION "1.0"
+
/* Device IDs */
#define HNAE3_DEV_ID_GE 0xA220
#define HNAE3_DEV_ID_25GE 0xA221
#define HNAE3_DEV_INITED_B 0x0
#define HNAE3_DEV_SUPPORT_ROCE_B 0x1
#define HNAE3_DEV_SUPPORT_DCB_B 0x2
+#define HNAE3_CLIENT_INITED_B 0x3
#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
BIT(HNAE3_DEV_SUPPORT_ROCE_B))
* Map rings to vector
* unmap_ring_from_vector()
* Unmap rings from vector
- * add_tunnel_udp()
- * Add tunnel information to hardware
- * del_tunnel_udp()
- * Delete tunnel information from hardware
* reset_queue()
* Reset queue
* get_fw_version()
int vector_num,
struct hnae3_ring_chain_node *vr_chain);
- int (*add_tunnel_udp)(struct hnae3_handle *handle, u16 port_num);
- int (*del_tunnel_udp)(struct hnae3_handle *handle, u16 port_num);
-
void (*reset_queue)(struct hnae3_handle *handle, u16 queue_id);
u32 (*get_fw_version)(struct hnae3_handle *handle);
void (*get_mdix_mode)(struct hnae3_handle *handle,
#define hnae_get_bit(origin, shift) \
hnae_get_field((origin), (0x1 << (shift)), (shift))
-int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
+void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo);
-int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo);
+void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo);
void hnae3_unregister_client(struct hnae3_client *client);
int hnae3_register_client(struct hnae3_client *client);
/* find outer header point */
l3.hdr = skb_network_header(skb);
- l4_hdr = skb_inner_transport_header(skb);
+ l4_hdr = skb_transport_header(skb);
if (skb->protocol == htons(ETH_P_IPV6)) {
exthdr = l3.hdr + sizeof(*l3.v6);
stats->tx_compressed = netdev->stats.tx_compressed;
}
-static void hns3_add_tunnel_port(struct net_device *netdev, u16 port,
- enum hns3_udp_tnl_type type)
-{
- struct hns3_nic_priv *priv = netdev_priv(netdev);
- struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type];
- struct hnae3_handle *h = priv->ae_handle;
-
- if (udp_tnl->used && udp_tnl->dst_port == port) {
- udp_tnl->used++;
- return;
- }
-
- if (udp_tnl->used) {
- netdev_warn(netdev,
- "UDP tunnel [%d], port [%d] offload\n", type, port);
- return;
- }
-
- udp_tnl->dst_port = port;
- udp_tnl->used = 1;
- /* TBD send command to hardware to add port */
- if (h->ae_algo->ops->add_tunnel_udp)
- h->ae_algo->ops->add_tunnel_udp(h, port);
-}
-
-static void hns3_del_tunnel_port(struct net_device *netdev, u16 port,
- enum hns3_udp_tnl_type type)
-{
- struct hns3_nic_priv *priv = netdev_priv(netdev);
- struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type];
- struct hnae3_handle *h = priv->ae_handle;
-
- if (!udp_tnl->used || udp_tnl->dst_port != port) {
- netdev_warn(netdev,
- "Invalid UDP tunnel port %d\n", port);
- return;
- }
-
- udp_tnl->used--;
- if (udp_tnl->used)
- return;
-
- udp_tnl->dst_port = 0;
- /* TBD send command to hardware to del port */
- if (h->ae_algo->ops->del_tunnel_udp)
- h->ae_algo->ops->del_tunnel_udp(h, port);
-}
-
-/* hns3_nic_udp_tunnel_add - Get notifiacetion about UDP tunnel ports
- * @netdev: This physical ports's netdev
- * @ti: Tunnel information
- */
-static void hns3_nic_udp_tunnel_add(struct net_device *netdev,
- struct udp_tunnel_info *ti)
-{
- u16 port_n = ntohs(ti->port);
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN);
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE);
- break;
- default:
- netdev_err(netdev, "unsupported tunnel type %d\n", ti->type);
- break;
- }
-}
-
-static void hns3_nic_udp_tunnel_del(struct net_device *netdev,
- struct udp_tunnel_info *ti)
-{
- u16 port_n = ntohs(ti->port);
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN);
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE);
- break;
- default:
- break;
- }
-}
-
static int hns3_setup_tc(struct net_device *netdev, void *type_data)
{
struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
.ndo_get_stats64 = hns3_nic_get_stats64,
.ndo_setup_tc = hns3_nic_setup_tc,
.ndo_set_rx_mode = hns3_nic_set_rx_mode,
- .ndo_udp_tunnel_add = hns3_nic_udp_tunnel_add,
- .ndo_udp_tunnel_del = hns3_nic_udp_tunnel_del,
.ndo_vlan_rx_add_vid = hns3_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = hns3_vlan_rx_kill_vid,
.ndo_set_vf_vlan = hns3_ndo_set_vf_vlan,
};
+static bool hns3_is_phys_func(struct pci_dev *pdev)
+{
+ u32 dev_id = pdev->device;
+
+ switch (dev_id) {
+ case HNAE3_DEV_ID_GE:
+ case HNAE3_DEV_ID_25GE:
+ case HNAE3_DEV_ID_25GE_RDMA:
+ case HNAE3_DEV_ID_25GE_RDMA_MACSEC:
+ case HNAE3_DEV_ID_50GE_RDMA:
+ case HNAE3_DEV_ID_50GE_RDMA_MACSEC:
+ case HNAE3_DEV_ID_100G_RDMA_MACSEC:
+ return true;
+ case HNAE3_DEV_ID_100G_VF:
+ case HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF:
+ return false;
+ default:
+ dev_warn(&pdev->dev, "un-recognized pci device-id %d",
+ dev_id);
+ }
+
+ return false;
+}
+
+static void hns3_disable_sriov(struct pci_dev *pdev)
+{
+ /* If our VFs are assigned we cannot shut down SR-IOV
+ * without causing issues, so just leave the hardware
+ * available but disabled
+ */
+ if (pci_vfs_assigned(pdev)) {
+ dev_warn(&pdev->dev,
+ "disabling driver while VFs are assigned\n");
+ return;
+ }
+
+ pci_disable_sriov(pdev);
+}
+
/* hns3_probe - Device initialization routine
* @pdev: PCI device information struct
* @ent: entry in hns3_pci_tbl
ae_dev->dev_type = HNAE3_DEV_KNIC;
pci_set_drvdata(pdev, ae_dev);
- return hnae3_register_ae_dev(ae_dev);
+ hnae3_register_ae_dev(ae_dev);
+
+ return 0;
}
/* hns3_remove - Device removal routine
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+ if (hns3_is_phys_func(pdev) && IS_ENABLED(CONFIG_PCI_IOV))
+ hns3_disable_sriov(pdev);
+
hnae3_unregister_ae_dev(ae_dev);
}
+/**
+ * hns3_pci_sriov_configure
+ * @pdev: pointer to a pci_dev structure
+ * @num_vfs: number of VFs to allocate
+ *
+ * Enable or change the number of VFs. Called when the user updates the number
+ * of VFs in sysfs.
+ **/
+static int hns3_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+ int ret;
+
+ if (!(hns3_is_phys_func(pdev) && IS_ENABLED(CONFIG_PCI_IOV))) {
+ dev_warn(&pdev->dev, "Can not config SRIOV\n");
+ return -EINVAL;
+ }
+
+ if (num_vfs) {
+ ret = pci_enable_sriov(pdev, num_vfs);
+ if (ret)
+ dev_err(&pdev->dev, "SRIOV enable failed %d\n", ret);
+ else
+ return num_vfs;
+ } else if (!pci_vfs_assigned(pdev)) {
+ pci_disable_sriov(pdev);
+ } else {
+ dev_warn(&pdev->dev,
+ "Unable to free VFs because some are assigned to VMs.\n");
+ }
+
+ return 0;
+}
+
static struct pci_driver hns3_driver = {
.name = hns3_driver_name,
.id_table = hns3_pci_tbl,
.probe = hns3_probe,
.remove = hns3_remove,
+ .sriov_configure = hns3_pci_sriov_configure,
};
/* set default feature to hns3 */
static void hns3_set_default_feature(struct net_device *netdev)
{
- struct hnae3_handle *h = hns3_get_handle(netdev);
-
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_GSO_UDP_TUNNEL_CSUM;
netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM;
-
- if (!(h->flags & HNAE3_SUPPORT_VF))
- netdev->hw_features |=
- NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
}
static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
writel_relaxed(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG);
}
-/* hns3_nic_get_headlen - determine size of header for LRO/GRO
- * @data: pointer to the start of the headers
- * @max: total length of section to find headers in
- *
- * This function is meant to determine the length of headers that will
- * be recognized by hardware for LRO, GRO, and RSC offloads. The main
- * motivation of doing this is to only perform one pull for IPv4 TCP
- * packets so that we can do basic things like calculating the gso_size
- * based on the average data per packet.
- */
-static unsigned int hns3_nic_get_headlen(unsigned char *data, u32 flag,
- unsigned int max_size)
-{
- unsigned char *network;
- u8 hlen;
-
- /* This should never happen, but better safe than sorry */
- if (max_size < ETH_HLEN)
- return max_size;
-
- /* Initialize network frame pointer */
- network = data;
-
- /* Set first protocol and move network header forward */
- network += ETH_HLEN;
-
- /* Handle any vlan tag if present */
- if (hnae_get_field(flag, HNS3_RXD_VLAN_M, HNS3_RXD_VLAN_S)
- == HNS3_RX_FLAG_VLAN_PRESENT) {
- if ((typeof(max_size))(network - data) > (max_size - VLAN_HLEN))
- return max_size;
-
- network += VLAN_HLEN;
- }
-
- /* Handle L3 protocols */
- if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S)
- == HNS3_RX_FLAG_L3ID_IPV4) {
- if ((typeof(max_size))(network - data) >
- (max_size - sizeof(struct iphdr)))
- return max_size;
-
- /* Access ihl as a u8 to avoid unaligned access on ia64 */
- hlen = (network[0] & 0x0F) << 2;
-
- /* Verify hlen meets minimum size requirements */
- if (hlen < sizeof(struct iphdr))
- return network - data;
-
- /* Record next protocol if header is present */
- } else if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S)
- == HNS3_RX_FLAG_L3ID_IPV6) {
- if ((typeof(max_size))(network - data) >
- (max_size - sizeof(struct ipv6hdr)))
- return max_size;
-
- /* Record next protocol */
- hlen = sizeof(struct ipv6hdr);
- } else {
- return network - data;
- }
-
- /* Relocate pointer to start of L4 header */
- network += hlen;
-
- /* Finally sort out TCP/UDP */
- if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S)
- == HNS3_RX_FLAG_L4ID_TCP) {
- if ((typeof(max_size))(network - data) >
- (max_size - sizeof(struct tcphdr)))
- return max_size;
-
- /* Access doff as a u8 to avoid unaligned access on ia64 */
- hlen = (network[12] & 0xF0) >> 2;
-
- /* Verify hlen meets minimum size requirements */
- if (hlen < sizeof(struct tcphdr))
- return network - data;
-
- network += hlen;
- } else if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S)
- == HNS3_RX_FLAG_L4ID_UDP) {
- if ((typeof(max_size))(network - data) >
- (max_size - sizeof(struct udphdr)))
- return max_size;
-
- network += sizeof(struct udphdr);
- }
-
- /* If everything has gone correctly network should be the
- * data section of the packet and will be the end of the header.
- * If not then it probably represents the end of the last recognized
- * header.
- */
- if ((typeof(max_size))(network - data) < max_size)
- return network - data;
- else
- return max_size;
-}
-
static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
struct hns3_enet_ring *ring, int pull_len,
struct hns3_desc_cb *desc_cb)
ring->stats.seg_pkt_cnt++;
u64_stats_update_end(&ring->syncp);
- pull_len = hns3_nic_get_headlen(va, l234info,
- HNS3_RX_HEAD_SIZE);
+ pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+
memcpy(__skb_put(skb, pull_len), va,
ALIGN(pull_len, sizeof(long)));
}
/* Set mac addr if it is configured. or leave it to the AE driver */
-static void hns3_init_mac_addr(struct net_device *netdev)
+static void hns3_init_mac_addr(struct net_device *netdev, bool init)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
u8 mac_addr_temp[ETH_ALEN];
- if (h->ae_algo->ops->get_mac_addr) {
+ if (h->ae_algo->ops->get_mac_addr && init) {
h->ae_algo->ops->get_mac_addr(h, mac_addr_temp);
ether_addr_copy(netdev->dev_addr, mac_addr_temp);
}
handle->kinfo.netdev = netdev;
handle->priv = (void *)priv;
- hns3_init_mac_addr(netdev);
+ hns3_init_mac_addr(netdev, true);
hns3_set_default_feature(netdev);
hns3_nic_mc_sync(ndev, ha->addr);
}
-static void hns3_drop_skb_data(struct hns3_enet_ring *ring, struct sk_buff *skb)
+static void hns3_clear_tx_ring(struct hns3_enet_ring *ring)
{
- dev_kfree_skb_any(skb);
+ if (!HNAE3_IS_TX_RING(ring))
+ return;
+
+ while (ring->next_to_clean != ring->next_to_use) {
+ hns3_free_buffer_detach(ring, ring->next_to_clean);
+ ring_ptr_move_fw(ring, next_to_clean);
+ }
+}
+
+static void hns3_clear_rx_ring(struct hns3_enet_ring *ring)
+{
+ if (HNAE3_IS_TX_RING(ring))
+ return;
+
+ while (ring->next_to_use != ring->next_to_clean) {
+ /* When a buffer is not reused, it's memory has been
+ * freed in hns3_handle_rx_bd or will be freed by
+ * stack, so only need to unmap the buffer here.
+ */
+ if (!ring->desc_cb[ring->next_to_use].reuse_flag) {
+ hns3_unmap_buffer(ring,
+ &ring->desc_cb[ring->next_to_use]);
+ ring->desc_cb[ring->next_to_use].dma = 0;
+ }
+
+ ring_ptr_move_fw(ring, next_to_use);
+ }
}
static void hns3_clear_all_ring(struct hnae3_handle *h)
struct hns3_enet_ring *ring;
ring = priv->ring_data[i].ring;
- hns3_clean_tx_ring(ring, ring->desc_num);
+ hns3_clear_tx_ring(ring);
dev_queue = netdev_get_tx_queue(ndev,
priv->ring_data[i].queue_index);
netdev_tx_reset_queue(dev_queue);
ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
- hns3_clean_rx_ring(ring, ring->desc_num, hns3_drop_skb_data);
+ hns3_clear_rx_ring(ring);
}
}
struct hns3_nic_priv *priv = netdev_priv(netdev);
int ret;
- hns3_init_mac_addr(netdev);
+ hns3_init_mac_addr(netdev, false);
hns3_nic_set_rx_mode(netdev);
hns3_recover_hw_addr(netdev);
client.ops = &client_ops;
+ INIT_LIST_HEAD(&client.node);
+
ret = hnae3_register_client(&client);
if (ret)
return ret;
MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
MODULE_LICENSE("GPL");
MODULE_ALIAS("pci:hns-nic");
+MODULE_VERSION(HNS3_MOD_VERSION);
#include "hnae3.h"
+#define HNS3_MOD_VERSION "1.0"
+
extern const char hns3_driver_version[];
enum hns3_nic_state {
u32 ethtool_link_mode;
};
-static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop)
+static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
int ret;
switch (loop) {
case HNAE3_MAC_INTER_LOOP_MAC:
- ret = h->ae_algo->ops->set_loopback(h, loop, true);
- break;
- case HNAE3_MAC_LOOP_NONE:
- ret = h->ae_algo->ops->set_loopback(h,
- HNAE3_MAC_INTER_LOOP_MAC, false);
+ ret = h->ae_algo->ops->set_loopback(h, loop, en);
break;
default:
ret = -ENOTSUPP;
if (ret)
return ret;
- if (loop == HNAE3_MAC_LOOP_NONE)
- h->ae_algo->ops->set_promisc_mode(h, ndev->flags & IFF_PROMISC);
- else
- h->ae_algo->ops->set_promisc_mode(h, 1);
+ h->ae_algo->ops->set_promisc_mode(h, en);
return ret;
}
return ret;
}
- ret = hns3_lp_setup(ndev, loop_mode);
+ ret = hns3_lp_setup(ndev, loop_mode, true);
usleep_range(10000, 20000);
return ret;
}
-static int hns3_lp_down(struct net_device *ndev)
+static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
int ret;
if (!h->ae_algo->ops->stop)
return -EOPNOTSUPP;
- ret = hns3_lp_setup(ndev, HNAE3_MAC_LOOP_NONE);
+ ret = hns3_lp_setup(ndev, loop_mode, false);
if (ret) {
netdev_err(ndev, "lb_setup return error: %d\n", ret);
return ret;
data[test_index] = hns3_lp_up(ndev, loop_type);
if (!data[test_index]) {
data[test_index] = hns3_lp_run_test(ndev, loop_type);
- hns3_lp_down(ndev);
+ hns3_lp_down(ndev, loop_type);
}
if (data[test_index])
return ring->desc_num - used - 1;
}
+static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int h)
+{
+ int u = ring->next_to_use;
+ int c = ring->next_to_clean;
+
+ if (unlikely(h >= ring->desc_num))
+ return 0;
+
+ return u > c ? (h > c && h <= u) : (h > c || h <= u);
+}
+
static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring)
{
int size = ring->desc_num * sizeof(struct hclge_desc);
static int hclge_cmd_csq_clean(struct hclge_hw *hw)
{
+ struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
struct hclge_cmq_ring *csq = &hw->cmq.csq;
u16 ntc = csq->next_to_clean;
struct hclge_desc *desc;
desc = &csq->desc[ntc];
head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG);
+ rmb(); /* Make sure head is ready before touch any data */
+
+ if (!is_valid_csq_clean_head(csq, head)) {
+ dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head,
+ csq->next_to_use, csq->next_to_clean);
+ return 0;
+ }
while (head != ntc) {
memset(desc, 0, sizeof(*desc));
static bool hclge_is_special_opcode(u16 opcode)
{
- u16 spec_opcode[3] = {0x0030, 0x0031, 0x0032};
+ /* these commands have several descriptors,
+ * and use the first one to save opcode and return value
+ */
+ u16 spec_opcode[3] = {HCLGE_OPC_STATS_64_BIT,
+ HCLGE_OPC_STATS_32_BIT, HCLGE_OPC_STATS_MAC};
int i;
for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
static void hclge_destroy_queue(struct hclge_cmq_ring *ring)
{
- spin_lock_bh(&ring->lock);
+ spin_lock(&ring->lock);
hclge_free_cmd_desc(ring);
- spin_unlock_bh(&ring->lock);
+ spin_unlock(&ring->lock);
}
void hclge_destroy_cmd_queue(struct hclge_hw *hw)
HCLGE_MAC_STATS_FIELD_OFF(mac_tx_2048_4095_oct_pkt_num)},
{"mac_tx_4096_8191_oct_pkt_num",
HCLGE_MAC_STATS_FIELD_OFF(mac_tx_4096_8191_oct_pkt_num)},
- {"mac_tx_8192_12287_oct_pkt_num",
- HCLGE_MAC_STATS_FIELD_OFF(mac_tx_8192_12287_oct_pkt_num)},
{"mac_tx_8192_9216_oct_pkt_num",
HCLGE_MAC_STATS_FIELD_OFF(mac_tx_8192_9216_oct_pkt_num)},
{"mac_tx_9217_12287_oct_pkt_num",
HCLGE_MAC_STATS_FIELD_OFF(mac_rx_2048_4095_oct_pkt_num)},
{"mac_rx_4096_8191_oct_pkt_num",
HCLGE_MAC_STATS_FIELD_OFF(mac_rx_4096_8191_oct_pkt_num)},
- {"mac_rx_8192_12287_oct_pkt_num",
- HCLGE_MAC_STATS_FIELD_OFF(mac_rx_8192_12287_oct_pkt_num)},
{"mac_rx_8192_9216_oct_pkt_num",
HCLGE_MAC_STATS_FIELD_OFF(mac_rx_8192_9216_oct_pkt_num)},
{"mac_rx_9217_12287_oct_pkt_num",
/* We need to alloc a vport for main NIC of PF */
num_vport = hdev->num_vmdq_vport + hdev->num_req_vfs + 1;
- if (hdev->num_tqps < num_vport)
- num_vport = hdev->num_tqps;
+ if (hdev->num_tqps < num_vport) {
+ dev_err(&hdev->pdev->dev, "tqps(%d) is less than vports(%d)",
+ hdev->num_tqps, num_vport);
+ return -EINVAL;
+ }
/* Alloc the same number of TQPs for every vport */
tqp_per_vport = hdev->num_tqps / num_vport;
hdev->vport = vport;
hdev->num_alloc_vport = num_vport;
-#ifdef CONFIG_PCI_IOV
- /* Enable SRIOV */
- if (hdev->num_req_vfs) {
- dev_info(&pdev->dev, "active VFs(%d) found, enabling SRIOV\n",
- hdev->num_req_vfs);
- ret = pci_enable_sriov(hdev->pdev, hdev->num_req_vfs);
- if (ret) {
- hdev->num_alloc_vfs = 0;
- dev_err(&pdev->dev, "SRIOV enable failed %d\n",
- ret);
- return ret;
- }
- }
- hdev->num_alloc_vfs = hdev->num_req_vfs;
-#endif
+ if (IS_ENABLED(CONFIG_PCI_IOV))
+ hdev->num_alloc_vfs = hdev->num_req_vfs;
for (i = 0; i < num_vport; i++) {
vport->back = hdev;
hclge_service_complete(hdev);
}
-static void hclge_disable_sriov(struct hclge_dev *hdev)
-{
- /* If our VFs are assigned we cannot shut down SR-IOV
- * without causing issues, so just leave the hardware
- * available but disabled
- */
- if (pci_vfs_assigned(hdev->pdev)) {
- dev_warn(&hdev->pdev->dev,
- "disabling driver while VFs are assigned\n");
- return;
- }
-
- pci_disable_sriov(hdev->pdev);
-}
-
struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle)
{
/* VF handle has no client */
"mac enable fail, ret =%d.\n", ret);
}
-static int hclge_set_loopback(struct hnae3_handle *handle,
- enum hnae3_loop loop_mode, bool en)
+static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en)
{
- struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_config_mac_mode_cmd *req;
- struct hclge_dev *hdev = vport->back;
struct hclge_desc desc;
u32 loop_en;
int ret;
- switch (loop_mode) {
- case HNAE3_MAC_INTER_LOOP_MAC:
- req = (struct hclge_config_mac_mode_cmd *)&desc.data[0];
- /* 1 Read out the MAC mode config at first */
- hclge_cmd_setup_basic_desc(&desc,
- HCLGE_OPC_CONFIG_MAC_MODE,
- true);
- ret = hclge_cmd_send(&hdev->hw, &desc, 1);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "mac loopback get fail, ret =%d.\n",
- ret);
- return ret;
- }
+ req = (struct hclge_config_mac_mode_cmd *)&desc.data[0];
+ /* 1 Read out the MAC mode config at first */
+ hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true);
+ ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "mac loopback get fail, ret =%d.\n", ret);
+ return ret;
+ }
- /* 2 Then setup the loopback flag */
- loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
- if (en)
- hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 1);
- else
- hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+ /* 2 Then setup the loopback flag */
+ loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
+ hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
- req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
+ req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
- /* 3 Config mac work mode with loopback flag
- * and its original configure parameters
- */
- hclge_cmd_reuse_desc(&desc, false);
- ret = hclge_cmd_send(&hdev->hw, &desc, 1);
- if (ret)
- dev_err(&hdev->pdev->dev,
- "mac loopback set fail, ret =%d.\n", ret);
+ /* 3 Config mac work mode with loopback flag
+ * and its original configure parameters
+ */
+ hclge_cmd_reuse_desc(&desc, false);
+ ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+ if (ret)
+ dev_err(&hdev->pdev->dev,
+ "mac loopback set fail, ret =%d.\n", ret);
+ return ret;
+}
+
+static int hclge_set_loopback(struct hnae3_handle *handle,
+ enum hnae3_loop loop_mode, bool en)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ switch (loop_mode) {
+ case HNAE3_MAC_INTER_LOOP_MAC:
+ ret = hclge_set_mac_loopback(hdev, en);
break;
default:
ret = -ENOTSUPP;
hclge_cfg_mac_mode(hdev, true);
clear_bit(HCLGE_STATE_DOWN, &hdev->state);
mod_timer(&hdev->service_timer, jiffies + HZ);
+ hdev->hw.mac.link = 0;
/* reset tqp stats */
hclge_reset_tqp_stats(handle);
/* reset tqp stats */
hclge_reset_tqp_stats(handle);
+ del_timer_sync(&hdev->service_timer);
+ cancel_work_sync(&hdev->service_task);
hclge_update_link_status(hdev);
}
hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, enable);
}
-int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
- bool is_kill, u16 vlan, u8 qos, __be16 proto)
+static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
+ bool is_kill, u16 vlan, u8 qos,
+ __be16 proto)
{
#define HCLGE_MAX_VF_BYTES 16
struct hclge_vlan_filter_vf_cfg_cmd *req0;
return -EIO;
}
-static int hclge_set_port_vlan_filter(struct hnae3_handle *handle,
- __be16 proto, u16 vlan_id,
- bool is_kill)
+static int hclge_set_port_vlan_filter(struct hclge_dev *hdev, __be16 proto,
+ u16 vlan_id, bool is_kill)
{
- struct hclge_vport *vport = hclge_get_vport(handle);
- struct hclge_dev *hdev = vport->back;
struct hclge_vlan_filter_pf_cfg_cmd *req;
struct hclge_desc desc;
u8 vlan_offset_byte_val;
req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val;
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+ if (ret)
+ dev_err(&hdev->pdev->dev,
+ "port vlan command, send fail, ret =%d.\n", ret);
+ return ret;
+}
+
+static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto,
+ u16 vport_id, u16 vlan_id, u8 qos,
+ bool is_kill)
+{
+ u16 vport_idx, vport_num = 0;
+ int ret;
+
+ ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id,
+ 0, proto);
if (ret) {
dev_err(&hdev->pdev->dev,
- "port vlan command, send fail, ret =%d.\n",
- ret);
+ "Set %d vport vlan filter config fail, ret =%d.\n",
+ vport_id, ret);
return ret;
}
- ret = hclge_set_vf_vlan_common(hdev, 0, is_kill, vlan_id, 0, proto);
- if (ret) {
+ /* vlan 0 may be added twice when 8021q module is enabled */
+ if (!is_kill && !vlan_id &&
+ test_bit(vport_id, hdev->vlan_table[vlan_id]))
+ return 0;
+
+ if (!is_kill && test_and_set_bit(vport_id, hdev->vlan_table[vlan_id])) {
dev_err(&hdev->pdev->dev,
- "Set pf vlan filter config fail, ret =%d.\n",
- ret);
- return -EIO;
+ "Add port vlan failed, vport %d is already in vlan %d\n",
+ vport_id, vlan_id);
+ return -EINVAL;
}
- return 0;
+ if (is_kill &&
+ !test_and_clear_bit(vport_id, hdev->vlan_table[vlan_id])) {
+ dev_err(&hdev->pdev->dev,
+ "Delete port vlan failed, vport %d is not in vlan %d\n",
+ vport_id, vlan_id);
+ return -EINVAL;
+ }
+
+ for_each_set_bit(vport_idx, hdev->vlan_table[vlan_id], VLAN_N_VID)
+ vport_num++;
+
+ if ((is_kill && vport_num == 0) || (!is_kill && vport_num == 1))
+ ret = hclge_set_port_vlan_filter(hdev, proto, vlan_id,
+ is_kill);
+
+ return ret;
+}
+
+int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
+ u16 vlan_id, bool is_kill)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+
+ return hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id, vlan_id,
+ 0, is_kill);
}
static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
if (proto != htons(ETH_P_8021Q))
return -EPROTONOSUPPORT;
- return hclge_set_vf_vlan_common(hdev, vfid, false, vlan, qos, proto);
+ return hclge_set_vlan_filter_hw(hdev, proto, vfid, vlan, qos, false);
}
static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport)
}
handle = &hdev->vport[0].nic;
- return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
+ return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
}
-static int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct phy_device *phydev = hdev->hw.mac.phydev;
u32 fc_autoneg;
- /* Only support flow control negotiation for netdev with
- * phy attached for now.
- */
- if (!phydev)
- return -EOPNOTSUPP;
-
fc_autoneg = hclge_get_autoneg(handle);
if (auto_neg != fc_autoneg) {
dev_info(&hdev->pdev->dev,
if (!fc_autoneg)
return hclge_cfg_pauseparam(hdev, rx_en, tx_en);
+ /* Only support flow control negotiation for netdev with
+ * phy attached for now.
+ */
+ if (!phydev)
+ return -EOPNOTSUPP;
+
return phy_start_aneg(phydev);
}
vport->nic.client = client;
ret = client->ops->init_instance(&vport->nic);
if (ret)
- goto err;
+ return ret;
if (hdev->roce_client &&
hnae3_dev_roce_supported(hdev)) {
ret = hclge_init_roce_base_info(vport);
if (ret)
- goto err;
+ return ret;
ret = rc->ops->init_instance(&vport->roce);
if (ret)
- goto err;
+ return ret;
}
break;
ret = client->ops->init_instance(&vport->nic);
if (ret)
- goto err;
+ return ret;
break;
case HNAE3_CLIENT_ROCE:
if (hdev->roce_client && hdev->nic_client) {
ret = hclge_init_roce_base_info(vport);
if (ret)
- goto err;
+ return ret;
ret = client->ops->init_instance(&vport->roce);
if (ret)
- goto err;
+ return ret;
}
}
}
return 0;
-err:
- return ret;
}
static void hclge_uninit_client_instance(struct hnae3_client *client,
ret = pci_enable_device(pdev);
if (ret) {
dev_err(&pdev->dev, "failed to enable PCI device\n");
- goto err_no_drvdata;
+ return ret;
}
ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
pci_release_regions(pdev);
err_disable_device:
pci_disable_device(pdev);
-err_no_drvdata:
- pci_set_drvdata(pdev, NULL);
return ret;
}
{
struct pci_dev *pdev = hdev->pdev;
+ pcim_iounmap(pdev, hdev->hw.io_base);
pci_free_irq_vectors(pdev);
pci_clear_master(pdev);
pci_release_mem_regions(pdev);
hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL);
if (!hdev) {
ret = -ENOMEM;
- goto err_hclge_dev;
+ goto out;
}
hdev->pdev = pdev;
ret = hclge_pci_init(hdev);
if (ret) {
dev_err(&pdev->dev, "PCI init failed\n");
- goto err_pci_init;
+ goto out;
}
/* Firmware command queue initialize */
ret = hclge_cmd_queue_init(hdev);
if (ret) {
dev_err(&pdev->dev, "Cmd queue init failed, ret = %d.\n", ret);
- return ret;
+ goto err_pci_uninit;
}
/* Firmware command initialize */
ret = hclge_cmd_init(hdev);
if (ret)
- goto err_cmd_init;
+ goto err_cmd_uninit;
ret = hclge_get_cap(hdev);
if (ret) {
dev_err(&pdev->dev, "get hw capability error, ret = %d.\n",
ret);
- return ret;
+ goto err_cmd_uninit;
}
ret = hclge_configure(hdev);
if (ret) {
dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret);
- return ret;
+ goto err_cmd_uninit;
}
ret = hclge_init_msi(hdev);
if (ret) {
dev_err(&pdev->dev, "Init MSI/MSI-X error, ret = %d.\n", ret);
- return ret;
+ goto err_cmd_uninit;
}
ret = hclge_misc_irq_init(hdev);
dev_err(&pdev->dev,
"Misc IRQ(vector0) init error, ret = %d.\n",
ret);
- return ret;
+ goto err_msi_uninit;
}
ret = hclge_alloc_tqps(hdev);
if (ret) {
dev_err(&pdev->dev, "Allocate TQPs error, ret = %d.\n", ret);
- return ret;
+ goto err_msi_irq_uninit;
}
ret = hclge_alloc_vport(hdev);
if (ret) {
dev_err(&pdev->dev, "Allocate vport error, ret = %d.\n", ret);
- return ret;
+ goto err_msi_irq_uninit;
}
ret = hclge_map_tqp(hdev);
if (ret) {
dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
- return ret;
+ goto err_msi_irq_uninit;
}
- ret = hclge_mac_mdio_config(hdev);
- if (ret) {
- dev_warn(&hdev->pdev->dev,
- "mdio config fail ret=%d\n", ret);
- return ret;
+ if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) {
+ ret = hclge_mac_mdio_config(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "mdio config fail ret=%d\n", ret);
+ goto err_msi_irq_uninit;
+ }
}
ret = hclge_mac_init(hdev);
if (ret) {
dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
ret = hclge_config_tso(hdev, HCLGE_TSO_MSS_MIN, HCLGE_TSO_MSS_MAX);
if (ret) {
dev_err(&pdev->dev, "Enable tso fail, ret =%d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
ret = hclge_init_vlan_config(hdev);
if (ret) {
dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
ret = hclge_tm_schd_init(hdev);
if (ret) {
dev_err(&pdev->dev, "tm schd init fail, ret =%d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
hclge_rss_init_cfg(hdev);
ret = hclge_rss_init_hw(hdev);
if (ret) {
dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
ret = init_mgr_tbl(hdev);
if (ret) {
dev_err(&pdev->dev, "manager table init fail, ret =%d\n", ret);
- return ret;
+ goto err_mdiobus_unreg;
}
hclge_dcb_ops_set(hdev);
pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
return 0;
-err_cmd_init:
+err_mdiobus_unreg:
+ if (hdev->hw.mac.phydev)
+ mdiobus_unregister(hdev->hw.mac.mdio_bus);
+err_msi_irq_uninit:
+ hclge_misc_irq_uninit(hdev);
+err_msi_uninit:
+ pci_free_irq_vectors(pdev);
+err_cmd_uninit:
+ hclge_destroy_cmd_queue(&hdev->hw);
+err_pci_uninit:
+ pcim_iounmap(pdev, hdev->hw.io_base);
+ pci_clear_master(pdev);
pci_release_regions(pdev);
-err_pci_init:
- pci_set_drvdata(pdev, NULL);
-err_hclge_dev:
+ pci_disable_device(pdev);
+out:
return ret;
}
set_bit(HCLGE_STATE_DOWN, &hdev->state);
hclge_stats_clear(hdev);
+ memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table));
ret = hclge_cmd_init(hdev);
if (ret) {
set_bit(HCLGE_STATE_DOWN, &hdev->state);
- if (IS_ENABLED(CONFIG_PCI_IOV))
- hclge_disable_sriov(hdev);
-
if (hdev->service_timer.function)
del_timer_sync(&hdev->service_timer);
if (hdev->service_task.func)
.get_fw_version = hclge_get_fw_version,
.get_mdix_mode = hclge_get_mdix_mode,
.enable_vlan_filter = hclge_enable_vlan_filter,
- .set_vlan_filter = hclge_set_port_vlan_filter,
+ .set_vlan_filter = hclge_set_vlan_filter,
.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
.enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag,
.reset_event = hclge_reset_event,
{
pr_info("%s is initializing\n", HCLGE_NAME);
- return hnae3_register_ae_algo(&ae_algo);
+ hnae3_register_ae_algo(&ae_algo);
+
+ return 0;
}
static void hclge_exit(void)
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/phy.h>
+#include <linux/if_vlan.h>
+
#include "hclge_cmd.h"
#include "hnae3.h"
-#define HCLGE_MOD_VERSION "v1.0"
+#define HCLGE_MOD_VERSION "1.0"
#define HCLGE_DRIVER_NAME "hclge"
#define HCLGE_INVALID_VPORT 0xffff
u64 mac_tx_1519_2047_oct_pkt_num;
u64 mac_tx_2048_4095_oct_pkt_num;
u64 mac_tx_4096_8191_oct_pkt_num;
- u64 mac_tx_8192_12287_oct_pkt_num; /* valid for GE MAC only */
- u64 mac_tx_8192_9216_oct_pkt_num; /* valid for LGE & CGE MAC only */
- u64 mac_tx_9217_12287_oct_pkt_num; /* valid for LGE & CGE MAC */
+ u64 rsv0;
+ u64 mac_tx_8192_9216_oct_pkt_num;
+ u64 mac_tx_9217_12287_oct_pkt_num;
u64 mac_tx_12288_16383_oct_pkt_num;
u64 mac_tx_1519_max_good_oct_pkt_num;
u64 mac_tx_1519_max_bad_oct_pkt_num;
u64 mac_rx_1519_2047_oct_pkt_num;
u64 mac_rx_2048_4095_oct_pkt_num;
u64 mac_rx_4096_8191_oct_pkt_num;
- u64 mac_rx_8192_12287_oct_pkt_num;/* valid for GE MAC only */
- u64 mac_rx_8192_9216_oct_pkt_num; /* valid for LGE & CGE MAC only */
- u64 mac_rx_9217_12287_oct_pkt_num; /* valid for LGE & CGE MAC only */
+ u64 rsv1;
+ u64 mac_rx_8192_9216_oct_pkt_num;
+ u64 mac_rx_9217_12287_oct_pkt_num;
u64 mac_rx_12288_16383_oct_pkt_num;
u64 mac_rx_1519_max_good_oct_pkt_num;
u64 mac_rx_1519_max_bad_oct_pkt_num;
u16 tx_in_vlan_type;
};
+#define HCLGE_VPORT_NUM 256
struct hclge_dev {
struct pci_dev *pdev;
struct hnae3_ae_dev *ae_dev;
u64 rx_pkts_for_led;
u64 tx_pkts_for_led;
+ unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)];
};
/* VPort level vlan tag configuration for TX direction */
}
int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
-int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid,
- bool is_kill, u16 vlan, u8 qos, __be16 proto);
+int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
+ u16 vlan_id, bool is_kill);
+int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable);
int hclge_buffer_alloc(struct hclge_dev *hdev);
int hclge_rss_init_hw(struct hclge_dev *hdev);
struct hclge_mbx_vf_to_pf_cmd *mbx_req,
bool gen_resp)
{
- struct hclge_dev *hdev = vport->back;
int status = 0;
if (mbx_req->msg[1] == HCLGE_MBX_VLAN_FILTER) {
+ struct hnae3_handle *handle = &vport->nic;
u16 vlan, proto;
bool is_kill;
is_kill = !!mbx_req->msg[2];
memcpy(&vlan, &mbx_req->msg[3], sizeof(vlan));
memcpy(&proto, &mbx_req->msg[5], sizeof(proto));
- status = hclge_set_vf_vlan_common(hdev, vport->vport_id,
- is_kill, vlan, 0,
- cpu_to_be16(proto));
+ status = hclge_set_vlan_filter(handle, cpu_to_be16(proto),
+ vlan, is_kill);
+ } else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) {
+ struct hnae3_handle *handle = &vport->nic;
+ bool en = mbx_req->msg[2] ? true : false;
+
+ status = hclge_en_hw_strip_rxvtag(handle, en);
}
if (gen_resp)
struct mii_bus *mdio_bus;
int ret;
- if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR)
- return 0;
+ if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) {
+ dev_err(&hdev->pdev->dev, "phy_addr(%d) is too large.\n",
+ hdev->hw.mac.phy_addr);
+ return -EINVAL;
+ }
mdio_bus = devm_mdiobus_alloc(&hdev->pdev->dev);
if (!mdio_bus)
}
ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_TM_PFC_PKT_GET_CMD_NUM);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "Get pfc pause stats fail, ret = %d.\n", ret);
+ if (ret)
return ret;
- }
for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM; i++) {
struct hclge_pfc_stats_cmd *pfc_stats =
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
-static int hclge_tm_qs_bp_cfg(struct hclge_dev *hdev, u8 tc)
+static int hclge_tm_qs_bp_cfg(struct hclge_dev *hdev, u8 tc, u8 grp_id,
+ u32 bit_map)
{
struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
struct hclge_desc desc;
bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
bp_to_qs_map_cmd->tc_id = tc;
-
- /* Qset and tc is one by one mapping */
- bp_to_qs_map_cmd->qs_bit_map = cpu_to_le32(1 << tc);
+ bp_to_qs_map_cmd->qs_group_id = grp_id;
+ bp_to_qs_map_cmd->qs_bit_map = cpu_to_le32(bit_map);
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
hdev->tm_info.hw_pfc_map);
}
+/* Each Tc has a 1024 queue sets to backpress, it divides to
+ * 32 group, each group contains 32 queue sets, which can be
+ * represented by u32 bitmap.
+ */
+static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc)
+{
+ struct hclge_vport *vport = hdev->vport;
+ u32 i, k, qs_bitmap;
+ int ret;
+
+ for (i = 0; i < HCLGE_BP_GRP_NUM; i++) {
+ qs_bitmap = 0;
+
+ for (k = 0; k < hdev->num_alloc_vport; k++) {
+ u16 qs_id = vport->qs_offset + tc;
+ u8 grp, sub_grp;
+
+ grp = hnae_get_field(qs_id, HCLGE_BP_GRP_ID_M,
+ HCLGE_BP_GRP_ID_S);
+ sub_grp = hnae_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
+ HCLGE_BP_SUB_GRP_ID_S);
+ if (i == grp)
+ qs_bitmap |= (1 << sub_grp);
+
+ vport++;
+ }
+
+ ret = hclge_tm_qs_bp_cfg(hdev, tc, i, qs_bitmap);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
{
bool tx_en, rx_en;
dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
for (i = 0; i < hdev->tm_info.num_tc; i++) {
- ret = hclge_tm_qs_bp_cfg(hdev, i);
+ ret = hclge_bp_setup_hw(hdev, i);
if (ret)
return ret;
}
__le32 pg_shapping_para;
};
+#define HCLGE_BP_GRP_NUM 32
+#define HCLGE_BP_SUB_GRP_ID_S 0
+#define HCLGE_BP_SUB_GRP_ID_M GENMASK(4, 0)
+#define HCLGE_BP_GRP_ID_S 5
+#define HCLGE_BP_GRP_ID_M GENMASK(9, 5)
struct hclge_bp_to_qs_map_cmd {
u8 tc_id;
u8 rsvd[2];
HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0);
}
+static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ u8 msg_data;
+
+ msg_data = enable ? 1 : 0;
+ return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+ HCLGE_MBX_VLAN_RX_OFF_CFG, &msg_data,
+ 1, false, NULL, 0);
+}
+
static void hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
ret = pci_enable_device(pdev);
if (ret) {
dev_err(&pdev->dev, "failed to enable PCI device\n");
- goto err_no_drvdata;
+ return ret;
}
ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
pci_release_regions(pdev);
err_disable_device:
pci_disable_device(pdev);
-err_no_drvdata:
- pci_set_drvdata(pdev, NULL);
+
return ret;
}
pci_clear_master(pdev);
pci_release_regions(pdev);
pci_disable_device(pdev);
- pci_set_drvdata(pdev, NULL);
}
static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
hclgevf_state_init(hdev);
+ ret = hclgevf_cmd_init(hdev);
+ if (ret)
+ goto err_cmd_init;
+
ret = hclgevf_misc_irq_init(hdev);
if (ret) {
dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
goto err_misc_irq_init;
}
- ret = hclgevf_cmd_init(hdev);
- if (ret)
- goto err_cmd_init;
-
ret = hclgevf_configure(hdev);
if (ret) {
dev_err(&pdev->dev, "failed(%d) to fetch configuration\n", ret);
return 0;
err_config:
- hclgevf_cmd_uninit(hdev);
-err_cmd_init:
hclgevf_misc_irq_uninit(hdev);
err_misc_irq_init:
+ hclgevf_cmd_uninit(hdev);
+err_cmd_init:
hclgevf_state_uninit(hdev);
hclgevf_uninit_msi(hdev);
err_irq_init:
static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
{
- hclgevf_cmd_uninit(hdev);
- hclgevf_misc_irq_uninit(hdev);
hclgevf_state_uninit(hdev);
+ hclgevf_misc_irq_uninit(hdev);
+ hclgevf_cmd_uninit(hdev);
hclgevf_uninit_msi(hdev);
hclgevf_pci_uninit(hdev);
}
.get_tc_size = hclgevf_get_tc_size,
.get_fw_version = hclgevf_get_fw_version,
.set_vlan_filter = hclgevf_set_vlan_filter,
+ .enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag,
.reset_event = hclgevf_reset_event,
.get_channels = hclgevf_get_channels,
.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
{
pr_info("%s is initializing\n", HCLGEVF_NAME);
- return hnae3_register_ae_algo(&ae_algovf);
+ hnae3_register_ae_algo(&ae_algovf);
+
+ return 0;
}
static void hclgevf_exit(void)
#include "hclgevf_cmd.h"
#include "hnae3.h"
-#define HCLGEVF_MOD_VERSION "v1.0"
+#define HCLGEVF_MOD_VERSION "1.0"
#define HCLGEVF_DRIVER_NAME "hclgevf"
#define HCLGEVF_ROCEE_VECTOR_NUM 0
module_param(rx_weight, uint, 0644);
MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
-#define PCI_DEVICE_ID_HI1822_PF 0x1822
+#define HINIC_DEV_ID_QUAD_PORT_25GE 0x1822
+#define HINIC_DEV_ID_DUAL_PORT_25GE 0x0200
+#define HINIC_DEV_ID_DUAL_PORT_100GE 0x0201
#define HINIC_WQ_NAME "hinic_dev"
}
static const struct pci_device_id hinic_pci_table[] = {
- { PCI_VDEVICE(HUAWEI, PCI_DEVICE_ID_HI1822_PF), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0},
{ 0, 0}
};
MODULE_DEVICE_TABLE(pci, hinic_pci_table);
if (adapter->fw_done_rc) {
dev_err(dev, "Couldn't map long term buffer,rc = %d\n",
adapter->fw_done_rc);
+ dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
return -1;
}
return 0;
if (!adapter->rx_pool)
return;
- rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+ rx_scrqs = adapter->num_active_rx_pools;
rx_entries = adapter->req_rx_add_entries_per_subcrq;
/* Free any remaining skbs in the rx buffer pools */
if (!adapter->tx_pool || !adapter->tso_pool)
return;
- tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+ tx_scrqs = adapter->num_active_tx_pools;
/* Free any remaining skbs in the tx buffer pools */
for (i = 0; i < tx_scrqs; i++) {
if (rc)
return rc;
}
+ ibmvnic_disable_irqs(adapter);
}
-
- ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
release_crq_queue(adapter);
}
- rc = init_stats_buffers(adapter);
- if (rc)
- return rc;
-
- rc = init_stats_token(adapter);
- if (rc)
- return rc;
-
return rc;
}
goto ibmvnic_init_fail;
} while (rc == EAGAIN);
+ rc = init_stats_buffers(adapter);
+ if (rc)
+ goto ibmvnic_init_fail;
+
+ rc = init_stats_token(adapter);
+ if (rc)
+ goto ibmvnic_stats_fail;
+
netdev->mtu = adapter->req_mtu - ETH_HLEN;
netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
rc = device_create_file(&dev->dev, &dev_attr_failover);
if (rc)
- goto ibmvnic_init_fail;
+ goto ibmvnic_dev_file_err;
netif_carrier_off(netdev);
rc = register_netdev(netdev);
ibmvnic_register_fail:
device_remove_file(&dev->dev, &dev_attr_failover);
+ibmvnic_dev_file_err:
+ release_stats_token(adapter);
+
+ibmvnic_stats_fail:
+ release_stats_buffers(adapter);
+
ibmvnic_init_fail:
release_sub_crqs(adapter, 1);
release_crq_queue(adapter);
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel PRO/100 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/*
* e100.c: Intel(R) PRO/100 ethernet driver
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel PRO/1000 Linux driver
# Copyright(c) 1999 - 2006 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# Linux NICS <linux.nics@intel.com>
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
#
# Makefile for the Intel(R) PRO/1000 ethernet driver
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
-
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/* Linux PRO/1000 Ethernet Driver main header file */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- * Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2006 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/* ethtool support for e1000 */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-*
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
- */
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/* e1000_hw.c
* Shared functions for accessing and configuring the MAC
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/* e1000_hw.h
* Structures, enums, and macros for the MAC
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
#include "e1000.h"
#include <net/ip6_checksum.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
-
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
/* glue for the OS independent part of e1000
* includes register access macros
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2006 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2006 Intel Corporation. */
#include "e1000.h"
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* 80003ES2LAN Gigabit Ethernet Controller (Copper)
* 80003ES2LAN Gigabit Ethernet Controller (Serdes)
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_80003ES2LAN_H_
#define _E1000E_80003ES2LAN_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* 82571EB Gigabit Ethernet Controller
* 82571EB Gigabit Ethernet Controller (Copper)
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_82571_H_
#define _E1000E_82571_H_
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel PRO/1000 Linux driver
-# Copyright(c) 1999 - 2014 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, see <http://www.gnu.org/licenses/>.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# Linux NICS <linux.nics@intel.com>
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
+# Copyright(c) 1999 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) PRO/1000 ethernet driver
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000_DEFINES_H_
#define _E1000_DEFINES_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* Linux PRO/1000 Ethernet Driver main header file */
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* ethtool support for e1000 */
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000_HW_H_
#define _E1000_HW_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* 82562G 10/100 Network Connection
* 82562G-2 10/100 Network Connection
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_ICH8LAN_H_
#define _E1000E_ICH8LAN_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "e1000.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_MAC_H_
#define _E1000E_MAC_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "e1000.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_MANAGE_H_
#define _E1000E_MANAGE_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "e1000.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_NVM_H_
#define _E1000E_NVM_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/netdevice.h>
#include <linux/module.h>
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "e1000.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_PHY_H_
#define _E1000E_PHY_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* PTP 1588 Hardware Clock (PHC)
* Derived from PTP Hardware Clock driver for Intel 82576 and 82580 (igb)
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000E_REGS_H_
#define _E1000E_REGS_H_
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel(R) Ethernet Switch Host Interface Driver
-# Copyright(c) 2013 - 2016 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
+# Copyright(c) 2013 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) Ethernet Switch Host Interface Driver
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_H_
#define _FM10K_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2018 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k_common.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_COMMON_H_
#define _FM10K_COMMON_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k.h"
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k.h"
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/vmalloc.h>
#include "fm10k.h"
struct fm10k_stats {
+ /* The stat_string is expected to be a format string formatted using
+ * vsnprintf by fm10k_add_stat_strings. Every member of a stats array
+ * should use the same format specifiers as they will be formatted
+ * using the same variadic arguments.
+ */
char stat_string[ETH_GSTRING_LEN];
int sizeof_stat;
int stat_offset;
};
-#define FM10K_NETDEV_STAT(_net_stat) { \
- .stat_string = #_net_stat, \
- .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \
- .stat_offset = offsetof(struct net_device_stats, _net_stat) \
+#define FM10K_STAT_FIELDS(_type, _name, _stat) { \
+ .stat_string = _name, \
+ .sizeof_stat = FIELD_SIZEOF(_type, _stat), \
+ .stat_offset = offsetof(_type, _stat) \
}
+/* netdevice statistics */
+#define FM10K_NETDEV_STAT(_net_stat) \
+ FM10K_STAT_FIELDS(struct net_device_stats, __stringify(_net_stat), \
+ _net_stat)
+
static const struct fm10k_stats fm10k_gstrings_net_stats[] = {
FM10K_NETDEV_STAT(tx_packets),
FM10K_NETDEV_STAT(tx_bytes),
#define FM10K_NETDEV_STATS_LEN ARRAY_SIZE(fm10k_gstrings_net_stats)
-#define FM10K_STAT(_name, _stat) { \
- .stat_string = _name, \
- .sizeof_stat = FIELD_SIZEOF(struct fm10k_intfc, _stat), \
- .stat_offset = offsetof(struct fm10k_intfc, _stat) \
-}
+/* General interface statistics */
+#define FM10K_STAT(_name, _stat) \
+ FM10K_STAT_FIELDS(struct fm10k_intfc, _name, _stat)
static const struct fm10k_stats fm10k_gstrings_global_stats[] = {
FM10K_STAT("tx_restart_queue", restart_queue),
FM10K_STAT("nodesc_drop", stats.nodesc_drop.count),
};
-#define FM10K_MBX_STAT(_name, _stat) { \
- .stat_string = _name, \
- .sizeof_stat = FIELD_SIZEOF(struct fm10k_mbx_info, _stat), \
- .stat_offset = offsetof(struct fm10k_mbx_info, _stat) \
-}
+/* mailbox statistics */
+#define FM10K_MBX_STAT(_name, _stat) \
+ FM10K_STAT_FIELDS(struct fm10k_mbx_info, _name, _stat)
static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = {
FM10K_MBX_STAT("mbx_tx_busy", tx_busy),
FM10K_MBX_STAT("mbx_rx_mbmem_pushed", rx_mbmem_pushed),
};
-#define FM10K_QUEUE_STAT(_name, _stat) { \
- .stat_string = _name, \
- .sizeof_stat = FIELD_SIZEOF(struct fm10k_ring, _stat), \
- .stat_offset = offsetof(struct fm10k_ring, _stat) \
-}
+/* per-queue ring statistics */
+#define FM10K_QUEUE_STAT(_name, _stat) \
+ FM10K_STAT_FIELDS(struct fm10k_ring, _name, _stat)
static const struct fm10k_stats fm10k_gstrings_queue_stats[] = {
- FM10K_QUEUE_STAT("packets", stats.packets),
- FM10K_QUEUE_STAT("bytes", stats.bytes),
+ FM10K_QUEUE_STAT("%s_queue_%u_packets", stats.packets),
+ FM10K_QUEUE_STAT("%s_queue_%u_bytes", stats.bytes),
};
#define FM10K_GLOBAL_STATS_LEN ARRAY_SIZE(fm10k_gstrings_global_stats)
static const char fm10k_prv_flags[FM10K_PRV_FLAG_LEN][ETH_GSTRING_LEN] = {
};
-static void fm10k_add_stat_strings(u8 **p, const char *prefix,
- const struct fm10k_stats stats[],
- const unsigned int size)
+static void __fm10k_add_stat_strings(u8 **p, const struct fm10k_stats stats[],
+ const unsigned int size, ...)
{
unsigned int i;
for (i = 0; i < size; i++) {
- snprintf(*p, ETH_GSTRING_LEN, "%s%s",
- prefix, stats[i].stat_string);
+ va_list args;
+
+ va_start(args, size);
+ vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
*p += ETH_GSTRING_LEN;
+ va_end(args);
}
}
+#define fm10k_add_stat_strings(p, stats, ...) \
+ __fm10k_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
+
static void fm10k_get_stat_strings(struct net_device *dev, u8 *data)
{
struct fm10k_intfc *interface = netdev_priv(dev);
unsigned int i;
- fm10k_add_stat_strings(&data, "", fm10k_gstrings_net_stats,
- FM10K_NETDEV_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_net_stats);
- fm10k_add_stat_strings(&data, "", fm10k_gstrings_global_stats,
- FM10K_GLOBAL_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_global_stats);
- fm10k_add_stat_strings(&data, "", fm10k_gstrings_mbx_stats,
- FM10K_MBX_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_mbx_stats);
if (interface->hw.mac.type != fm10k_mac_vf)
- fm10k_add_stat_strings(&data, "", fm10k_gstrings_pf_stats,
- FM10K_PF_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_pf_stats);
for (i = 0; i < interface->hw.mac.max_queues; i++) {
- char prefix[ETH_GSTRING_LEN];
-
- snprintf(prefix, ETH_GSTRING_LEN, "tx_queue_%u_", i);
- fm10k_add_stat_strings(&data, prefix,
- fm10k_gstrings_queue_stats,
- FM10K_QUEUE_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats,
+ "tx", i);
- snprintf(prefix, ETH_GSTRING_LEN, "rx_queue_%u_", i);
- fm10k_add_stat_strings(&data, prefix,
- fm10k_gstrings_queue_stats,
- FM10K_QUEUE_STATS_LEN);
+ fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats,
+ "rx", i);
}
}
}
}
-static void fm10k_add_ethtool_stats(u64 **data, void *pointer,
- const struct fm10k_stats stats[],
- const unsigned int size)
+static void __fm10k_add_ethtool_stats(u64 **data, void *pointer,
+ const struct fm10k_stats stats[],
+ const unsigned int size)
{
unsigned int i;
char *p;
*((*data)++) = *(u8 *)p;
break;
default:
+ WARN_ONCE(1, "unexpected stat size for %s",
+ stats[i].stat_string);
*((*data)++) = 0;
}
}
}
+#define fm10k_add_ethtool_stats(data, pointer, stats) \
+ __fm10k_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
static void fm10k_get_ethtool_stats(struct net_device *netdev,
struct ethtool_stats __always_unused *stats,
u64 *data)
fm10k_update_stats(interface);
- fm10k_add_ethtool_stats(&data, net_stats, fm10k_gstrings_net_stats,
- FM10K_NETDEV_STATS_LEN);
+ fm10k_add_ethtool_stats(&data, net_stats, fm10k_gstrings_net_stats);
- fm10k_add_ethtool_stats(&data, interface, fm10k_gstrings_global_stats,
- FM10K_GLOBAL_STATS_LEN);
+ fm10k_add_ethtool_stats(&data, interface, fm10k_gstrings_global_stats);
fm10k_add_ethtool_stats(&data, &interface->hw.mbx,
- fm10k_gstrings_mbx_stats,
- FM10K_MBX_STATS_LEN);
+ fm10k_gstrings_mbx_stats);
if (interface->hw.mac.type != fm10k_mac_vf) {
fm10k_add_ethtool_stats(&data, interface,
- fm10k_gstrings_pf_stats,
- FM10K_PF_STATS_LEN);
+ fm10k_gstrings_pf_stats);
}
for (i = 0; i < interface->hw.mac.max_queues; i++) {
ring = interface->tx_ring[i];
fm10k_add_ethtool_stats(&data, ring,
- fm10k_gstrings_queue_stats,
- FM10K_QUEUE_STATS_LEN);
+ fm10k_gstrings_queue_stats);
ring = interface->rx_ring[i];
fm10k_add_ethtool_stats(&data, ring,
- fm10k_gstrings_queue_stats,
- FM10K_QUEUE_STATS_LEN);
+ fm10k_gstrings_queue_stats);
}
}
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k.h"
#include "fm10k_vf.h"
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/types.h>
#include <linux/module.h>
l2_accel = NULL;
}
- skb->protocol = eth_type_trans(skb, dev);
-
/* Record Rx queue, or update macvlan statistics */
if (!l2_accel)
skb_record_rx_queue(skb, rx_ring->queue_index);
else
macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true,
- (skb->pkt_type == PACKET_BROADCAST) ||
- (skb->pkt_type == PACKET_MULTICAST));
+ false);
+
+ skb->protocol = eth_type_trans(skb, dev);
}
/**
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k_common.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_MBX_H_
#define _FM10K_MBX_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2018 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k.h"
#include <linux/vmalloc.h>
#include <net/udp_tunnel.h>
+#include <linux/if_macvlan.h>
/**
* fm10k_setup_tx_resources - allocate Tx resources (Descriptors)
static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
{
struct fm10k_intfc *interface = netdev_priv(netdev);
+ struct fm10k_l2_accel *l2_accel = interface->l2_accel;
struct fm10k_hw *hw = &interface->hw;
+ u16 glort;
s32 err;
int i;
if (err)
goto err_out;
+ /* Update L2 accelerated macvlan addresses */
+ if (l2_accel) {
+ for (i = 0; i < l2_accel->size; i++) {
+ struct net_device *sdev = l2_accel->macvlan[i];
+
+ if (!sdev)
+ continue;
+
+ glort = l2_accel->dglort + 1 + i;
+
+ fm10k_queue_mac_request(interface, glort,
+ sdev->dev_addr,
+ vid, set);
+ }
+ }
+
/* set VLAN ID prior to syncing/unsyncing the VLAN */
interface->vid = vid + (set ? VLAN_N_VID : 0);
fm10k_queue_mac_request(interface, glort,
hw->mac.addr, vid, true);
+
+ /* synchronize macvlan addresses */
+ if (l2_accel) {
+ for (i = 0; i < l2_accel->size; i++) {
+ struct net_device *sdev = l2_accel->macvlan[i];
+
+ if (!sdev)
+ continue;
+
+ glort = l2_accel->dglort + 1 + i;
+
+ fm10k_queue_mac_request(interface, glort,
+ sdev->dev_addr,
+ vid, true);
+ }
+ }
}
/* update xcast mode before synchronizing addresses if host's mailbox
glort = l2_accel->dglort + 1 + i;
hw->mac.ops.update_xcast_mode(hw, glort,
- FM10K_XCAST_MODE_MULTI);
+ FM10K_XCAST_MODE_NONE);
fm10k_queue_mac_request(interface, glort,
sdev->dev_addr,
hw->mac.default_vid, true);
struct fm10k_dglort_cfg dglort = { 0 };
struct fm10k_hw *hw = &interface->hw;
int size = 0, i;
- u16 glort;
+ u16 vid, glort;
+
+ /* The hardware supported by fm10k only filters on the destination MAC
+ * address. In order to avoid issues we only support offloading modes
+ * where the hardware can actually provide the functionality.
+ */
+ if (!macvlan_supports_dest_filter(sdev))
+ return ERR_PTR(-EMEDIUMTYPE);
/* allocate l2 accel structure if it is not available */
if (!l2_accel) {
glort = l2_accel->dglort + 1 + i;
- if (fm10k_host_mbx_ready(interface)) {
+ if (fm10k_host_mbx_ready(interface))
hw->mac.ops.update_xcast_mode(hw, glort,
- FM10K_XCAST_MODE_MULTI);
+ FM10K_XCAST_MODE_NONE);
+
+ fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+ hw->mac.default_vid, true);
+
+ for (vid = fm10k_find_next_vlan(interface, 0);
+ vid < VLAN_N_VID;
+ vid = fm10k_find_next_vlan(interface, vid))
fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
- hw->mac.default_vid, true);
- }
+ vid, true);
fm10k_mbx_unlock(interface);
struct fm10k_dglort_cfg dglort = { 0 };
struct fm10k_hw *hw = &interface->hw;
struct net_device *sdev = priv;
+ u16 vid, glort;
int i;
- u16 glort;
if (!l2_accel)
return;
glort = l2_accel->dglort + 1 + i;
- if (fm10k_host_mbx_ready(interface)) {
+ if (fm10k_host_mbx_ready(interface))
hw->mac.ops.update_xcast_mode(hw, glort,
FM10K_XCAST_MODE_NONE);
+
+ fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
+ hw->mac.default_vid, false);
+
+ for (vid = fm10k_find_next_vlan(interface, 0);
+ vid < VLAN_N_VID;
+ vid = fm10k_find_next_vlan(interface, vid))
fm10k_queue_mac_request(interface, glort, sdev->dev_addr,
- hw->mac.default_vid, false);
- }
+ vid, false);
fm10k_mbx_unlock(interface);
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2018 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/module.h>
#include <linux/interrupt.h>
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2018 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k_pf.h"
#include "fm10k_vf.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_PF_H_
#define _FM10K_PF_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2018 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k_tlv.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_TLV_H_
#define _FM10K_TLV_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_TYPE_H_
#define _FM10K_TYPE_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "fm10k_vf.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _FM10K_VF_H_
#define _FM10K_VF_H_
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel Ethernet Controller XL710 Family Linux Driver
-# Copyright(c) 2013 - 2015 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program. If not, see <http://www.gnu.org/licenses/>.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
+# Copyright(c) 2013 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_H_
#define _I40E_H_
struct i40e_tc_info tc_info[I40E_MAX_TRAFFIC_CLASS];
};
+#define I40E_UDP_PORT_INDEX_UNUSED 255
struct i40e_udp_port_config {
/* AdminQ command interface expects port number in Host byte order */
u16 port;
u8 type;
+ u8 filter_index;
};
/* macros related to FLX_PIT */
unsigned long ptp_tx_start;
struct hwtstamp_config tstamp_config;
struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
- u64 ptp_base_adj;
+ u32 ptp_adj_mult;
u32 tx_hwtstamp_timeouts;
u32 tx_hwtstamp_skipped;
u32 rx_hwtstamp_cleared;
void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id,
u8 *msg, u16 len);
+int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, bool is_xdp,
+ bool enable);
+int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable);
int i40e_vsi_start_rings(struct i40e_vsi *vsi);
void i40e_vsi_stop_rings(struct i40e_vsi *vsi);
void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi);
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_status.h"
#include "i40e_type.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ADMINQ_H_
#define _I40E_ADMINQ_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ADMINQ_CMD_H_
#define _I40E_ADMINQ_CMD_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ALLOC_H_
#define _I40E_ALLOC_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/list.h>
#include <linux/errno.h>
/**
* i40e_client_get_params - Get the params that can change at runtime
* @vsi: the VSI with the message
- * @param: clinet param struct
+ * @params: client param struct
*
**/
static
* i40e_client_setup_qvlist
* @ldev: pointer to L2 context.
* @client: Client pointer.
- * @qv_info: queue and vector list
+ * @qvlist_info: queue and vector list
*
* Return 0 on success or < 0 on error
**/
* i40e_client_request_reset
* @ldev: pointer to L2 context.
* @client: Client pointer.
- * @level: reset level
+ * @reset_level: reset level
**/
static void i40e_client_request_reset(struct i40e_info *ldev,
struct i40e_client *client,
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_CLIENT_H_
#define _I40E_CLIENT_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_type.h"
#include "i40e_adminq.h"
/**
* i40e_set_fc
* @hw: pointer to the hw struct
+ * @aq_failures: buffer to return AdminQ failure information
+ * @atomic_restart: whether to enable atomic link restart
*
* Set the requested flow control mode using set_phy_config.
**/
* @mr_list: list of mirrored VSI SEIDs or VLAN IDs
* @cmd_details: pointer to command details structure or NULL
* @rule_id: Rule ID returned from FW
- * @rule_used: Number of rules used in internal switch
- * @rule_free: Number of rules free in internal switch
+ * @rules_used: Number of rules used in internal switch
+ * @rules_free: Number of rules free in internal switch
*
* Add/Delete a mirror rule to a specific switch. Mirror rules are supported for
* VEBs/VEPA elements only
* @mr_list: list of mirrored VSI SEIDs or VLAN IDs
* @cmd_details: pointer to command details structure or NULL
* @rule_id: Rule ID returned from FW
- * @rule_used: Number of rules used in internal switch
- * @rule_free: Number of rules free in internal switch
+ * @rules_used: Number of rules used in internal switch
+ * @rules_free: Number of rules free in internal switch
*
* Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only
**/
* add_mirrorrule.
* @mr_list: list of mirrored VLAN IDs to be removed
* @cmd_details: pointer to command details structure or NULL
- * @rule_used: Number of rules used in internal switch
- * @rule_free: Number of rules free in internal switch
+ * @rules_used: Number of rules used in internal switch
+ * @rules_free: Number of rules free in internal switch
*
* Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only
**/
/**
* i40e_aq_start_lldp
* @hw: pointer to the hw struct
+ * @buff: buffer for result
+ * @buff_size: buffer size
* @cmd_details: pointer to command details structure or NULL
*
* Start the embedded LLDP Agent on all ports.
* i40e_aq_add_udp_tunnel
* @hw: pointer to the hw struct
* @udp_port: the UDP port to add in Host byte order
- * @header_len: length of the tunneling header length in DWords
* @protocol_index: protocol index type
* @filter_index: pointer to filter index
* @cmd_details: pointer to command details structure or NULL
* @hw: pointer to the hw struct
* @seid: seid of the switching component connected to Physical Port
* @ets_data: Buffer holding ETS parameters
+ * @opcode: Tx scheduler AQ command opcode
* @cmd_details: pointer to command details structure or NULL
**/
i40e_status i40e_aq_config_switch_comp_ets(struct i40e_hw *hw,
* @hw: pointer to the hw struct
* @seid: VSI seid to add ethertype filter from
**/
-#define I40E_FLOW_CONTROL_ETHTYPE 0x8808
void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw,
u16 seid)
{
+#define I40E_FLOW_CONTROL_ETHTYPE 0x8808
u16 flag = I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC |
I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP |
I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX;
* @ret_buff_size: actual buffer size returned
* @ret_next_table: next block to read
* @ret_next_index: next index to read
+ * @cmd_details: pointer to command details structure or NULL
*
* Dump internal FW/HW data for debug purposes.
*
* i40e_read_phy_register_clause22
* @hw: pointer to the HW structure
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Reads specified PHY register value
* i40e_write_phy_register_clause22
* @hw: pointer to the HW structure
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Writes specified PHY register value
* @hw: pointer to the HW structure
* @page: registers page number
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Reads specified PHY register value
* @hw: pointer to the HW structure
* @page: registers page number
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Writes value to specified PHY register
* @hw: pointer to the HW structure
* @page: registers page number
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Writes value to specified PHY register
* @hw: pointer to the HW structure
* @page: registers page number
* @reg: register address in the page
- * @phy_adr: PHY address on MDIO interface
+ * @phy_addr: PHY address on MDIO interface
* @value: PHY register value
*
* Reads specified PHY register value
* i40e_get_phy_address
* @hw: pointer to the HW structure
* @dev_num: PHY port num that address we want
- * @phy_addr: Returned PHY address
*
* Gets PHY address for current port
**/
* i40e_led_set_phy
* @hw: pointer to the HW structure
* @on: true or false
+ * @led_addr: address of led register to use
* @mode: original val plus bit for set or ignore
+ *
* Set led's on or off when controlled by the PHY
*
**/
* @hw: pointer to the hw struct
* @buff: command buffer (size in bytes = buff_size)
* @buff_size: buffer size in bytes
+ * @flags: AdminQ command flags
* @cmd_details: pointer to command details structure or NULL
**/
enum
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_adminq.h"
#include "i40e_prototype.h"
return ret;
}
+/**
+ * _i40e_read_lldp_cfg - generic read of LLDP Configuration data from NVM
+ * @hw: pointer to the HW structure
+ * @lldp_cfg: pointer to hold lldp configuration variables
+ * @module: address of the module pointer
+ * @word_offset: offset of LLDP configuration
+ *
+ * Reads the LLDP configuration data from NVM using passed addresses
+ **/
+static i40e_status _i40e_read_lldp_cfg(struct i40e_hw *hw,
+ struct i40e_lldp_variables *lldp_cfg,
+ u8 module, u32 word_offset)
+{
+ u32 address, offset = (2 * word_offset);
+ i40e_status ret;
+ __le16 raw_mem;
+ u16 mem;
+
+ ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (ret)
+ return ret;
+
+ ret = i40e_aq_read_nvm(hw, 0x0, module * 2, sizeof(raw_mem), &raw_mem,
+ true, NULL);
+ i40e_release_nvm(hw);
+ if (ret)
+ return ret;
+
+ mem = le16_to_cpu(raw_mem);
+ /* Check if this pointer needs to be read in word size or 4K sector
+ * units.
+ */
+ if (mem & I40E_PTR_TYPE)
+ address = (0x7FFF & mem) * 4096;
+ else
+ address = (0x7FFF & mem) * 2;
+
+ ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (ret)
+ goto err_lldp_cfg;
+
+ ret = i40e_aq_read_nvm(hw, module, offset, sizeof(raw_mem), &raw_mem,
+ true, NULL);
+ i40e_release_nvm(hw);
+ if (ret)
+ return ret;
+
+ mem = le16_to_cpu(raw_mem);
+ offset = mem + word_offset;
+ offset *= 2;
+
+ ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (ret)
+ goto err_lldp_cfg;
+
+ ret = i40e_aq_read_nvm(hw, 0, address + offset,
+ sizeof(struct i40e_lldp_variables), lldp_cfg,
+ true, NULL);
+ i40e_release_nvm(hw);
+
+err_lldp_cfg:
+ return ret;
+}
+
/**
* i40e_read_lldp_cfg - read LLDP Configuration data from NVM
* @hw: pointer to the HW structure
struct i40e_lldp_variables *lldp_cfg)
{
i40e_status ret = 0;
- u32 offset = (2 * I40E_NVM_LLDP_CFG_PTR);
+ u32 mem;
if (!lldp_cfg)
return I40E_ERR_PARAM;
ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
if (ret)
- goto err_lldp_cfg;
+ return ret;
- ret = i40e_aq_read_nvm(hw, I40E_SR_EMP_MODULE_PTR, offset,
- sizeof(struct i40e_lldp_variables),
- (u8 *)lldp_cfg,
- true, NULL);
+ ret = i40e_aq_read_nvm(hw, I40E_SR_NVM_CONTROL_WORD, 0, sizeof(mem),
+ &mem, true, NULL);
i40e_release_nvm(hw);
+ if (ret)
+ return ret;
+
+ /* Read a bit that holds information whether we are running flat or
+ * structured NVM image. Flat image has LLDP configuration in shadow
+ * ram, so there is a need to pass different addresses for both cases.
+ */
+ if (mem & I40E_SR_NVM_MAP_STRUCTURE_TYPE) {
+ /* Flat NVM case */
+ ret = _i40e_read_lldp_cfg(hw, lldp_cfg, I40E_SR_EMP_MODULE_PTR,
+ I40E_SR_LLDP_CFG_PTR);
+ } else {
+ /* Good old structured NVM image */
+ ret = _i40e_read_lldp_cfg(hw, lldp_cfg, I40E_EMP_MODULE_PTR,
+ I40E_NVM_LLDP_CFG_PTR);
+ }
-err_lldp_cfg:
return ret;
}
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_DCB_H_
#define _I40E_DCB_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifdef CONFIG_I40E_DCB
#include "i40e.h"
/**
* i40e_dcbnl_ieee_getets - retrieve local IEEE ETS configuration
- * @netdev: the corresponding netdev
+ * @dev: the corresponding netdev
* @ets: structure to hold the ETS information
*
* Returns local IEEE ETS configuration
/**
* i40e_dcbnl_ieee_getpfc - retrieve local IEEE PFC configuration
- * @netdev: the corresponding netdev
- * @ets: structure to hold the PFC information
+ * @dev: the corresponding netdev
+ * @pfc: structure to hold the PFC information
*
* Returns local IEEE PFC configuration
**/
/**
* i40e_dcbnl_getdcbx - retrieve current DCBx capability
- * @netdev: the corresponding netdev
+ * @dev: the corresponding netdev
*
* Returns DCBx capability features
**/
/**
* i40e_dcbnl_get_perm_hw_addr - MAC address used by DCBx
- * @netdev: the corresponding netdev
+ * @dev: the corresponding netdev
+ * @perm_addr: buffer to store the MAC address
*
* Returns the SAN MAC address used for LLDP exchange
**/
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifdef CONFIG_DEBUG_FS
/**
* i40e_dbg_find_vsi - searches for the vsi with the given seid
- * @pf - the PF structure to search for the vsi
- * @seid - seid of the vsi it is searching for
+ * @pf: the PF structure to search for the vsi
+ * @seid: seid of the vsi it is searching for
**/
static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid)
{
/**
* i40e_dbg_find_veb - searches for the veb with the given seid
- * @pf - the PF structure to search for the veb
- * @seid - seid of the veb it is searching for
+ * @pf: the PF structure to search for the veb
+ * @seid: seid of the veb it is searching for
**/
static struct i40e_veb *i40e_dbg_find_veb(struct i40e_pf *pf, int seid)
{
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_DEVIDS_H_
#define _I40E_DEVIDS_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_diag.h"
#include "i40e_prototype.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_DIAG_H_
#define _I40E_DIAG_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
/* ethtool support for i40e */
}
#define I40E_NETDEV_STAT(_net_stat) \
- I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat)
+ I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat)
#define I40E_PF_STAT(_name, _stat) \
- I40E_STAT(struct i40e_pf, _name, _stat)
+ I40E_STAT(struct i40e_pf, _name, _stat)
#define I40E_VSI_STAT(_name, _stat) \
- I40E_STAT(struct i40e_vsi, _name, _stat)
+ I40E_STAT(struct i40e_vsi, _name, _stat)
#define I40E_VEB_STAT(_name, _stat) \
- I40E_STAT(struct i40e_veb, _name, _stat)
+ I40E_STAT(struct i40e_veb, _name, _stat)
static const struct i40e_stats i40e_gstrings_net_stats[] = {
I40E_NETDEV_STAT(rx_packets),
I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
I40E_VSI_STAT("tx_linearize", tx_linearize),
I40E_VSI_STAT("tx_force_wb", tx_force_wb),
+ I40E_VSI_STAT("tx_busy", tx_busy),
I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed),
I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
};
I40E_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
I40E_PF_STAT("link_xon_tx", stats.link_xon_tx),
I40E_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
- I40E_PF_STAT("priority_xon_rx", stats.priority_xon_rx),
- I40E_PF_STAT("priority_xoff_rx", stats.priority_xoff_rx),
- I40E_PF_STAT("priority_xon_tx", stats.priority_xon_tx),
- I40E_PF_STAT("priority_xoff_tx", stats.priority_xoff_tx),
I40E_PF_STAT("rx_size_64", stats.rx_size_64),
I40E_PF_STAT("rx_size_127", stats.rx_size_127),
I40E_PF_STAT("rx_size_255", stats.rx_size_255),
* 2 /* Tx and Rx together */ \
* (sizeof(struct i40e_queue_stats) / sizeof(u64)))
#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats)
-#define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats)
+#define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats)
#define I40E_MISC_STATS_LEN ARRAY_SIZE(i40e_gstrings_misc_stats)
-#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
+#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
I40E_MISC_STATS_LEN + \
I40E_QUEUE_STATS_LEN((n)))
#define I40E_PFC_STATS_LEN ( \
ethtool_link_ksettings_test_link_mode(ks, advertising,
10000baseCR_Full) ||
ethtool_link_ksettings_test_link_mode(ks, advertising,
- 10000baseSR_Full))
+ 10000baseSR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseLR_Full))
config.link_speed |= I40E_LINK_SPEED_10GB;
if (ethtool_link_ksettings_test_link_mode(ks, advertising,
20000baseKR2_Full))
/**
* i40e_get_pauseparam - Get Flow Control status
+ * @netdev: netdevice structure
+ * @pause: buffer to return pause parameters
+ *
* Return tx/rx-pause status
**/
static void i40e_get_pauseparam(struct net_device *netdev,
return err;
}
+static int i40e_get_stats_count(struct net_device *netdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+
+ if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1) {
+ if (pf->lan_veb != I40E_NO_VEB &&
+ pf->flags & I40E_FLAG_VEB_STATS_ENABLED)
+ return I40E_PF_STATS_LEN(netdev) + I40E_VEB_STATS_TOTAL;
+ else
+ return I40E_PF_STATS_LEN(netdev);
+ } else {
+ return I40E_VSI_STATS_LEN(netdev);
+ }
+}
+
static int i40e_get_sset_count(struct net_device *netdev, int sset)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
case ETH_SS_TEST:
return I40E_TEST_LEN;
case ETH_SS_STATS:
- if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1) {
- int len = I40E_PF_STATS_LEN(netdev);
-
- if ((pf->lan_veb != I40E_NO_VEB) &&
- (pf->flags & I40E_FLAG_VEB_STATS_ENABLED))
- len += I40E_VEB_STATS_TOTAL;
- return len;
- } else {
- return I40E_VSI_STATS_LEN(netdev);
- }
+ return i40e_get_stats_count(netdev);
case ETH_SS_PRIV_FLAGS:
return I40E_PRIV_FLAGS_STR_LEN +
(pf->hw.pf_id == 0 ? I40E_GL_PRIV_FLAGS_STR_LEN : 0);
/**
* i40e_check_mask - Check whether a mask field is set
* @mask: the full mask value
- * @field; mask of the field to check
+ * @field: mask of the field to check
*
* If the given mask is fully set, return positive value. If the mask for the
* field is fully unset, return zero. Otherwise return a negative error code.
/**
* i40e_fill_rx_flow_user_data - Fill in user-defined data field
* @fsp: pointer to rx_flow specification
+ * @data: pointer to return userdef data
*
* Reads the userdef data structure and properly fills in the user defined
* fields of the rx_flow_spec.
* i40e_get_rxnfc - command to get RX flow classification rules
* @netdev: network interface device structure
* @cmd: ethtool rxnfc command
+ * @rule_locs: pointer to store rule data
*
* Returns Success if the command is supported.
**/
/**
* i40e_get_rss_hash_bits - Read RSS Hash bits from register
* @nfc: pointer to user request
- * @i_setc bits currently set
+ * @i_setc: bits currently set
*
* Returns value of bits to be set per user request
**/
/**
* i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash
* @pf: pointer to the physical function struct
- * @cmd: ethtool rxnfc command
+ * @nfc: ethtool rxnfc command
*
* Returns Success if the flow input set is supported.
**/
* __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table
* @pf: Pointer to the PF structure
* @flex_pit_list: list of flexible src offsets in use
- * #flex_pit_start: index to first entry for this section of the table
+ * @flex_pit_start: index to first entry for this section of the table
*
* In order to handle flexible data, the hardware uses a table of values
* called the FLX_PIT table. This table is used to indicate which sections of
/**
* i40e_flow_str - Converts a flow_type into a human readable string
- * @flow_type: the flow type from a flow specification
+ * @fsp: the flow specification
*
* Currently only flow types we support are included here, and the string
* value attempts to match what ethtool would use to configure this flow type.
/**
* i40e_get_channels - Get the current channels enabled and max supported etc.
- * @netdev: network interface device structure
+ * @dev: network interface device structure
* @ch: ethtool channels structure
*
* We don't support separate tx and rx queues as channels. The other count
* q_vectors since we support a lot more queue pairs than q_vectors.
**/
static void i40e_get_channels(struct net_device *dev,
- struct ethtool_channels *ch)
+ struct ethtool_channels *ch)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
/**
* i40e_set_channels - Set the new channels count.
- * @netdev: network interface device structure
+ * @dev: network interface device structure
* @ch: ethtool channels structure
*
* The new channels count may not be the same as requested by the user
* since it gets rounded down to a power of 2 value.
**/
static int i40e_set_channels(struct net_device *dev,
- struct ethtool_channels *ch)
+ struct ethtool_channels *ch)
{
const u8 drop = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
struct i40e_netdev_priv *np = netdev_priv(dev);
* @netdev: network interface device structure
* @indir: indirection table
* @key: hash key
+ * @hfunc: hash function to use
*
* Returns -EINVAL if the table specifies an invalid queue id, otherwise
* returns 0 after programming the table.
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_osdep.h"
#include "i40e_register.h"
* @hw: pointer to our HW structure
* @hmc_info: pointer to the HMC configuration information structure
* @idx: the page index
- * @is_pf: distinguishes a VF from a PF
*
* This function:
* 1. Marks the entry in pd tabe (for paged address mode) or in sd table
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_HMC_H_
#define _I40E_HMC_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_osdep.h"
#include "i40e_register.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_LAN_HMC_H_
#define _I40E_LAN_HMC_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/etherdevice.h>
#include <linux/of_net.h>
/**
* i40e_find_vsi_from_id - searches for the vsi with the given id
- * @pf - the pf structure to search for the vsi
- * @id - id of the vsi it is searching for
+ * @pf: the pf structure to search for the vsi
+ * @id: id of the vsi it is searching for
**/
struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
{
/**
* i40e_get_netdev_stats_struct - Get statistics for netdev interface
* @netdev: network interface device structure
+ * @stats: data structure to store statistics
*
* Returns the address of the device statistics structure.
* The statistics are actually updated from the service task.
* from firmware
* @count: Number of filters added
* @add_list: return data from fw
- * @head: pointer to first filter in current batch
+ * @add_head: pointer to first filter in current batch
*
* MAC filter entries from list were slated to be added to device. Returns
* number of successful filters. Note that 0 does NOT mean success!
/**
* i40e_aqc_broadcast_filter - Set promiscuous broadcast flags
* @vsi: pointer to the VSI
+ * @vsi_name: the VSI name
* @f: filter data
*
* This function sets or clears the promiscuous broadcast flags for VLAN
/**
* i40e_vlan_rx_add_vid - Add a vlan id filter to HW offload
* @netdev: network interface to be adjusted
+ * @proto: unused protocol value
* @vid: vlan id to be added
*
* net_device_ops implementation for adding vlan ids
return ret;
}
+/**
+ * i40e_vlan_rx_add_vid_up - Add a vlan id filter to HW offload in UP path
+ * @netdev: network interface to be adjusted
+ * @proto: unused protocol value
+ * @vid: vlan id to be added
+ **/
+static void i40e_vlan_rx_add_vid_up(struct net_device *netdev,
+ __always_unused __be16 proto, u16 vid)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (vid >= VLAN_N_VID)
+ return;
+ set_bit(vid, vsi->active_vlans);
+}
+
/**
* i40e_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
* @netdev: network interface to be adjusted
+ * @proto: unused protocol value
* @vid: vlan id to be removed
*
* net_device_ops implementation for removing vlan ids
i40e_vlan_stripping_disable(vsi);
for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID)
- i40e_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q),
- vid);
+ i40e_vlan_rx_add_vid_up(vsi->netdev, htons(ETH_P_8021Q),
+ vid);
}
/**
/**
* i40e_enable_misc_int_causes - enable the non-queue interrupts
- * @hw: ptr to the hardware info
+ * @pf: pointer to private device data structure
**/
static void i40e_enable_misc_int_causes(struct i40e_pf *pf)
{
* @is_xdp: true if the queue is used for XDP
* @enable: start or stop the queue
**/
-static int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q,
- bool is_xdp, bool enable)
+int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q,
+ bool is_xdp, bool enable)
{
int ret;
if (ret)
break;
}
-
return ret;
}
* @pf_q: the PF queue to configure
* @enable: start or stop the queue
*
- * This function enables or disables a single queue. Note that any delay
- * required after the operation is expected to be handled by the caller of
- * this function.
+ * This function enables or disables a single queue. Note that
+ * any delay required after the operation is expected to be
+ * handled by the caller of this function.
**/
static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable)
{
wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
}
+/**
+ * i40e_control_wait_rx_q
+ * @pf: the PF structure
+ * @pf_q: queue being configured
+ * @enable: start or stop the rings
+ *
+ * This function enables or disables a single queue along with waiting
+ * for the change to finish. The caller of this function should handle
+ * the delays needed in the case of disabling queues.
+ **/
+int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable)
+{
+ int ret = 0;
+
+ i40e_control_rx_q(pf, pf_q, enable);
+
+ /* wait for the change to finish */
+ ret = i40e_pf_rxq_wait(pf, pf_q, enable);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
/**
* i40e_vsi_control_rx - Start or stop a VSI's rings
* @vsi: the VSI being configured
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- i40e_control_rx_q(pf, pf_q, enable);
-
- /* wait for the change to finish */
- ret = i40e_pf_rxq_wait(pf, pf_q, enable);
+ ret = i40e_control_wait_rx_q(pf, pf_q, enable);
if (ret) {
dev_info(&pf->pdev->dev,
"VSI seid %d Rx ring %d %sable timeout\n",
* i40e_vsi_configure_bw_alloc - Configure VSI BW allocation per TC
* @vsi: the VSI being configured
* @enabled_tc: TC bitmap
- * @bw_credits: BW shared credits per TC
+ * @bw_share: BW shared credits per TC
*
* Returns 0 on success, negative value on failure
**/
/**
* i40e_print_link_message - print link up or down
* @vsi: the VSI for which link needs a message
+ * @isup: true of link is up, false otherwise
*/
void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
{
if (mask->dst == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
- mask->dst = be32_to_cpu(mask->dst);
- dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4\n",
+ dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
&mask->dst);
return I40E_ERR_CONFIG;
}
if (mask->src == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
- mask->src = be32_to_cpu(mask->src);
- dev_err(&pf->pdev->dev, "Bad ip src mask %pI4\n",
+ dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
&mask->src);
return I40E_ERR_CONFIG;
}
i40e_flush(hw);
}
-static const char *i40e_tunnel_name(struct i40e_udp_port_config *port)
+static const char *i40e_tunnel_name(u8 type)
{
- switch (port->type) {
+ switch (type) {
case UDP_TUNNEL_TYPE_VXLAN:
return "vxlan";
case UDP_TUNNEL_TYPE_GENEVE:
static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
{
struct i40e_hw *hw = &pf->hw;
- i40e_status ret;
+ u8 filter_index, type;
u16 port;
int i;
if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state))
return;
+ /* acquire RTNL to maintain state of flags and port requests */
+ rtnl_lock();
+
for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
if (pf->pending_udp_bitmap & BIT_ULL(i)) {
+ struct i40e_udp_port_config *udp_port;
+ i40e_status ret = 0;
+
+ udp_port = &pf->udp_ports[i];
pf->pending_udp_bitmap &= ~BIT_ULL(i);
- port = pf->udp_ports[i].port;
+
+ port = READ_ONCE(udp_port->port);
+ type = READ_ONCE(udp_port->type);
+ filter_index = READ_ONCE(udp_port->filter_index);
+
+ /* release RTNL while we wait on AQ command */
+ rtnl_unlock();
+
if (port)
ret = i40e_aq_add_udp_tunnel(hw, port,
- pf->udp_ports[i].type,
- NULL, NULL);
- else
- ret = i40e_aq_del_udp_tunnel(hw, i, NULL);
+ type,
+ &filter_index,
+ NULL);
+ else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED)
+ ret = i40e_aq_del_udp_tunnel(hw, filter_index,
+ NULL);
+
+ /* reacquire RTNL so we can update filter_index */
+ rtnl_lock();
if (ret) {
dev_info(&pf->pdev->dev,
"%s %s port %d, index %d failed, err %s aq_err %s\n",
- i40e_tunnel_name(&pf->udp_ports[i]),
+ i40e_tunnel_name(type),
port ? "add" : "delete",
- port, i,
+ port,
+ filter_index,
i40e_stat_str(&pf->hw, ret),
i40e_aq_str(&pf->hw,
pf->hw.aq.asq_last_status));
- pf->udp_ports[i].port = 0;
+ if (port) {
+ /* failed to add, just reset port,
+ * drop pending bit for any deletion
+ */
+ udp_port->port = 0;
+ pf->pending_udp_bitmap &= ~BIT_ULL(i);
+ }
+ } else if (port) {
+ /* record filter index on success */
+ udp_port->filter_index = filter_index;
}
}
}
+
+ rtnl_unlock();
}
/**
/**
* i40e_vsi_free_arrays - Free queue and vector pointer arrays for the VSI
- * @type: VSI pointer
+ * @vsi: VSI pointer
* @free_qvectors: a bool to specify if q_vectors need to be freed.
*
* On error: returns error code (negative)
/* any vectors left over go for VMDq support */
if (pf->flags & I40E_FLAG_VMDQ_ENABLED) {
- int vmdq_vecs_wanted = pf->num_vmdq_vsis * pf->num_vmdq_qps;
- int vmdq_vecs = min_t(int, vectors_left, vmdq_vecs_wanted);
-
if (!vectors_left) {
pf->num_vmdq_msix = 0;
pf->num_vmdq_qps = 0;
} else {
+ int vmdq_vecs_wanted =
+ pf->num_vmdq_vsis * pf->num_vmdq_qps;
+ int vmdq_vecs =
+ min_t(int, vectors_left, vmdq_vecs_wanted);
+
/* if we're short on vectors for what's desired, we limit
* the queues per vmdq. If this is still more than are
* available, the user will need to change the number of
* queues/vectors used by the PF later with the ethtool
* channels command
*/
- if (vmdq_vecs < vmdq_vecs_wanted)
+ if (vectors_left < vmdq_vecs_wanted) {
pf->num_vmdq_qps = 1;
+ vmdq_vecs_wanted = pf->num_vmdq_vsis;
+ vmdq_vecs = min_t(int,
+ vectors_left,
+ vmdq_vecs_wanted);
+ }
pf->num_vmdq_msix = pf->num_vmdq_qps;
v_budget += vmdq_vecs;
* @vsi: Pointer to VSI structure
* @seed: Buffer to store the keys
* @lut: Buffer to store the lookup table entries
- * lut_size: Size of buffer to store the lookup table entries
+ * @lut_size: Size of buffer to store the lookup table entries
*
* Returns 0 on success, negative on failure
*/
u8 i;
for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
+ /* Do not report ports with pending deletions as
+ * being available.
+ */
+ if (!port && (pf->pending_udp_bitmap & BIT_ULL(i)))
+ continue;
if (pf->udp_ports[i].port == port)
return i;
}
/* New port: add it and mark its index in the bitmap */
pf->udp_ports[next_idx].port = port;
+ pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED;
pf->pending_udp_bitmap |= BIT_ULL(next_idx);
set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
}
* and make it pending
*/
pf->udp_ports[idx].port = 0;
- pf->pending_udp_bitmap |= BIT_ULL(idx);
+
+ /* Toggle pending bit instead of setting it. This way if we are
+ * deleting a port that has yet to be added we just clear the pending
+ * bit and don't have to worry about it.
+ */
+ pf->pending_udp_bitmap ^= BIT_ULL(idx);
set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
return;
* @tb: pointer to array of nladdr (unused)
* @dev: the net device pointer
* @addr: the MAC address entry being added
+ * @vid: VLAN ID
* @flags: instructions from stack about fdb operation
*/
static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
* i40e_ndo_bridge_setlink - Set the hardware bridge mode
* @dev: the netdev being configured
* @nlh: RTNL message
+ * @flags: bridge flags
*
* Inserts a new hardware bridge if not already created and
* enables the bridging mode requested (VEB or VEPA). If the
/**
* i40e_pci_error_detected - warning that something funky happened in PCI land
* @pdev: PCI device information struct
+ * @error: the type of PCI error
*
* Called to warn that something happened and the error handling steps
* are in progress. Allows the driver to quiesce things, be ready for
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_prototype.h"
* i40e_nvmupd_check_wait_event - handle NVM update operation events
* @hw: pointer to the hardware structure
* @opcode: the event that just happened
+ * @desc: AdminQ descriptor
**/
void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
struct i40e_aq_desc *desc)
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_OSDEP_H_
#define _I40E_OSDEP_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_PROTOTYPE_H_
#define _I40E_PROTOTYPE_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e.h"
#include <linux/ptp_classify.h>
* At 1Gb link, the period is multiplied by 20. (32ns)
* 1588 functionality is not supported at 100Mbps.
*/
-#define I40E_PTP_40GB_INCVAL 0x0199999999ULL
-#define I40E_PTP_10GB_INCVAL 0x0333333333ULL
-#define I40E_PTP_1GB_INCVAL 0x2000000000ULL
+#define I40E_PTP_40GB_INCVAL 0x0199999999ULL
+#define I40E_PTP_10GB_INCVAL_MULT 2
+#define I40E_PTP_1GB_INCVAL_MULT 20
#define I40E_PRTTSYN_CTL1_TSYNTYPE_V1 BIT(I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
#define I40E_PRTTSYN_CTL1_TSYNTYPE_V2 (2 << \
ppb = -ppb;
}
- smp_mb(); /* Force any pending update before accessing. */
- adj = READ_ONCE(pf->ptp_base_adj);
-
- freq = adj;
+ freq = I40E_PTP_40GB_INCVAL;
freq *= ppb;
diff = div_u64(freq, 1000000000ULL);
if (neg_adj)
- adj -= diff;
+ adj = I40E_PTP_40GB_INCVAL - diff;
else
- adj += diff;
+ adj = I40E_PTP_40GB_INCVAL + diff;
+
+ /* At some link speeds, the base incval is so large that directly
+ * multiplying by ppb would result in arithmetic overflow even when
+ * using a u64. Avoid this by instead calculating the new incval
+ * always in terms of the 40GbE clock rate and then multiplying by the
+ * link speed factor afterwards. This does result in slightly lower
+ * precision at lower link speeds, but it is fairly minor.
+ */
+ smp_mb(); /* Force any pending update before accessing. */
+ adj *= READ_ONCE(pf->ptp_adj_mult);
wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF);
wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32);
* This watchdog task is run periodically to make sure that we clear the Tx
* timestamp logic if we don't obtain a timestamp in a reasonable amount of
* time. It is unexpected in the normal case but if it occurs it results in
- * permanently prevent timestamps of future packets
+ * permanently preventing timestamps of future packets.
**/
void i40e_ptp_tx_hang(struct i40e_pf *pf)
{
+ struct sk_buff *skb;
+
if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_tx)
return;
* within a second it is reasonable to assume that we never will.
*/
if (time_is_before_jiffies(pf->ptp_tx_start + HZ)) {
- dev_kfree_skb_any(pf->ptp_tx_skb);
+ skb = pf->ptp_tx_skb;
pf->ptp_tx_skb = NULL;
clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state);
+
+ /* Free the skb after we clear the bitlock */
+ dev_kfree_skb_any(skb);
pf->tx_hwtstamp_timeouts++;
}
}
struct i40e_link_status *hw_link_info;
struct i40e_hw *hw = &pf->hw;
u64 incval;
+ u32 mult;
hw_link_info = &hw->phy.link_info;
switch (hw_link_info->link_speed) {
case I40E_LINK_SPEED_10GB:
- incval = I40E_PTP_10GB_INCVAL;
+ mult = I40E_PTP_10GB_INCVAL_MULT;
break;
case I40E_LINK_SPEED_1GB:
- incval = I40E_PTP_1GB_INCVAL;
+ mult = I40E_PTP_1GB_INCVAL_MULT;
break;
case I40E_LINK_SPEED_100MB:
{
"1588 functionality is not supported at 100 Mbps. Stopping the PHC.\n");
warn_once++;
}
- incval = 0;
+ mult = 0;
break;
}
case I40E_LINK_SPEED_40GB:
default:
- incval = I40E_PTP_40GB_INCVAL;
+ mult = 1;
break;
}
+ /* The increment value is calculated by taking the base 40GbE incvalue
+ * and multiplying it by a factor based on the link speed.
+ */
+ incval = I40E_PTP_40GB_INCVAL * mult;
+
/* Write the new increment value into the increment register. The
* hardware will not update the clock until both registers have been
* written.
wr32(hw, I40E_PRTTSYN_INC_H, incval >> 32);
/* Update the base adjustement value. */
- WRITE_ONCE(pf->ptp_base_adj, incval);
+ WRITE_ONCE(pf->ptp_adj_mult, mult);
smp_mb(); /* Force the above update. */
}
/**
* i40e_ptp_get_ts_config - ioctl interface to read the HW timestamping
* @pf: Board private structure
- * @ifreq: ioctl data
+ * @ifr: ioctl data
*
* Obtain the current hardware timestamping settigs as requested. To do this,
* keep a shadow copy of the timestamp settings rather than attempting to
/**
* i40e_ptp_set_ts_config - ioctl interface to control the HW timestamping
* @pf: Board private structure
- * @ifreq: ioctl data
+ * @ifr: ioctl data
*
* Respond to the user filter requests and make the appropriate hardware
* changes here. The XL710 cannot support splitting of the Tx/Rx timestamping
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_REGISTER_H_
#define _I40E_REGISTER_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_STATUS_H_
#define _I40E_STATUS_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel(R) 40-10 Gigabit Ethernet Connection Network Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
/* Modeled on trace-events-sample.h */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/prefetch.h>
#include <net/busy_poll.h>
/**
* i40e_add_del_fdir - Build raw packets to add/del fdir filter
* @vsi: pointer to the targeted VSI
- * @cmd: command to get or set RX flow classification rules
+ * @input: filter to add or delete
* @add: true adds a filter, false removes it
*
**/
/**
* i40e_get_tx_pending - how many tx descriptors not processed
- * @tx_ring: the ring of descriptors
+ * @ring: the ring of descriptors
* @in_sw: use SW variables
*
* Since there is no access to the ring head register
* i40e_rx_hash - set the hash value in the skb
* @ring: descriptor ring
* @rx_desc: specific descriptor
+ * @skb: skb currently being received and modified
+ * @rx_ptype: Rx packet type
**/
static inline void i40e_rx_hash(struct i40e_ring *ring,
union i40e_rx_desc *rx_desc,
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_TXRX_H_
#define _I40E_TXRX_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_TYPE_H_
#define _I40E_TYPE_H_
/* Checksum and Shadow RAM pointers */
#define I40E_SR_NVM_CONTROL_WORD 0x00
-#define I40E_SR_EMP_MODULE_PTR 0x0F
+#define I40E_EMP_MODULE_PTR 0x0F
+#define I40E_SR_EMP_MODULE_PTR 0x48
#define I40E_SR_PBA_FLAGS 0x15
#define I40E_SR_PBA_BLOCK_PTR 0x16
#define I40E_SR_BOOT_CONFIG_PTR 0x17
#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024
#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06
#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT)
+#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5)
+#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12)
#define I40E_PTR_TYPE BIT(15)
#define I40E_SR_OCP_CFG_WORD0 0x2B
#define I40E_SR_OCP_ENABLED BIT(15)
};
/* IEEE 802.1AB LLDP Agent Variables from NVM */
-#define I40E_NVM_LLDP_CFG_PTR 0xD
+#define I40E_NVM_LLDP_CFG_PTR 0x06
+#define I40E_SR_LLDP_CFG_PTR 0x31
struct i40e_lldp_variables {
u16 length;
u16 adminstatus;
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e.h"
/**
* i40e_vc_vf_broadcast
* @pf: pointer to the PF structure
- * @opcode: operation code
- * @retval: return value
+ * @v_opcode: operation code
+ * @v_retval: return value
* @msg: pointer to the msg buffer
* @msglen: msg length
*
/**
* i40e_vc_get_version_msg
* @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
*
* called from the VF to request the API version used by the PF
**/
* i40e_vc_get_vf_resources_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to request its resources
**/
/**
* i40e_vc_reset_vf_msg
* @vf: pointer to the VF info
- * @msg: pointer to the msg buffer
- * @msglen: msg length
*
* called from the VF to reset itself,
* unlike other virtchnl messages, PF driver
aq_ret);
}
+/**
+ * i40e_ctrl_vf_tx_rings
+ * @vsi: the SRIOV VSI being configured
+ * @q_map: bit map of the queues to be enabled
+ * @enable: start or stop the queue
+ **/
+static int i40e_ctrl_vf_tx_rings(struct i40e_vsi *vsi, unsigned long q_map,
+ bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ int ret = 0;
+ u16 q_id;
+
+ for_each_set_bit(q_id, &q_map, I40E_MAX_VF_QUEUES) {
+ ret = i40e_control_wait_tx_q(vsi->seid, pf,
+ vsi->base_queue + q_id,
+ false /*is xdp*/, enable);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
+/**
+ * i40e_ctrl_vf_rx_rings
+ * @vsi: the SRIOV VSI being configured
+ * @q_map: bit map of the queues to be enabled
+ * @enable: start or stop the queue
+ **/
+static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map,
+ bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ int ret = 0;
+ u16 q_id;
+
+ for_each_set_bit(q_id, &q_map, I40E_MAX_VF_QUEUES) {
+ ret = i40e_control_wait_rx_q(pf, vsi->base_queue + q_id,
+ enable);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
/**
* i40e_vc_enable_queues_msg
* @vf: pointer to the VF info
goto error_param;
}
- if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
+ /* Use the queue bit map sent by the VF */
+ if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues,
+ true)) {
aq_ret = I40E_ERR_TIMEOUT;
+ goto error_param;
+ }
+ if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues,
+ true)) {
+ aq_ret = I40E_ERR_TIMEOUT;
+ goto error_param;
+ }
/* need to start the rings for additional ADq VSI's as well */
if (vf->adq_enabled) {
goto error_param;
}
- i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
-
+ /* Use the queue bit map sent by the VF */
+ if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues,
+ false)) {
+ aq_ret = I40E_ERR_TIMEOUT;
+ goto error_param;
+ }
+ if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues,
+ false)) {
+ aq_ret = I40E_ERR_TIMEOUT;
+ goto error_param;
+ }
error_param:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES,
* i40e_vc_process_vf_msg
* @pf: pointer to the PF structure
* @vf_id: source VF id
+ * @v_opcode: operation code
+ * @v_retval: unused return value code
* @msg: pointer to the msg buffer
* @msglen: msg length
- * @msghndl: msg handle
*
* called from the common aeq/arq handler to
* process request from VF
**/
int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
- u32 v_retval, u8 *msg, u16 msglen)
+ u32 __always_unused v_retval, u8 *msg, u16 msglen)
{
struct i40e_hw *hw = &pf->hw;
int local_vf_id = vf_id - (s16)hw->func_caps.vf_base_id;
* i40e_ndo_set_vf_bw
* @netdev: network interface device structure
* @vf_id: VF identifier
- * @tx_rate: Tx rate
+ * @min_tx_rate: Minimum Tx rate
+ * @max_tx_rate: Maximum Tx rate
*
* configure VF Tx rate
**/
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_VIRTCHNL_PF_H_
#define _I40E_VIRTCHNL_PF_H_
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
-# Copyright(c) 2013 - 2014 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program. If not, see <http://www.gnu.org/licenses/>.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
+# Copyright(c) 2013 - 2018 Intel Corporation.
#
## Makefile for the Intel(R) 40GbE VF driver
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_status.h"
#include "i40e_type.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ADMINQ_H_
#define _I40E_ADMINQ_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ADMINQ_CMD_H_
#define _I40E_ADMINQ_CMD_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_ALLOC_H_
#define _I40E_ALLOC_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40e_type.h"
#include "i40e_adminq.h"
* @hw: pointer to the hw struct
* @buff: command buffer (size in bytes = buff_size)
* @buff_size: buffer size in bytes
+ * @flags: AdminQ command flags
* @cmd_details: pointer to command details structure or NULL
**/
enum
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_DEVIDS_H_
#define _I40E_DEVIDS_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_HMC_H_
#define _I40E_HMC_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_LAN_HMC_H_
#define _I40E_LAN_HMC_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_OSDEP_H_
#define _I40E_OSDEP_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_PROTOTYPE_H_
#define _I40E_PROTOTYPE_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_REGISTER_H_
#define _I40E_REGISTER_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_STATUS_H_
#define _I40E_STATUS_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel(R) 40-10 Gigabit Ethernet Virtual Function Driver
- * Copyright(c) 2013 - 2017 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
/* Modeled on trace-events-sample.h */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/prefetch.h>
#include <net/busy_poll.h>
/**
* i40evf_get_tx_pending - how many Tx descriptors not processed
- * @tx_ring: the ring of descriptors
+ * @ring: the ring of descriptors
* @in_sw: is tx_pending being checked in SW or HW
*
* Since there is no access to the ring head register
* i40e_rx_hash - set the hash value in the skb
* @ring: descriptor ring
* @rx_desc: specific descriptor
+ * @skb: skb currently being received and modified
+ * @rx_ptype: Rx packet type
**/
static inline void i40e_rx_hash(struct i40e_ring *ring,
union i40e_rx_desc *rx_desc,
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_TXRX_H_
#define _I40E_TXRX_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40E_TYPE_H_
#define _I40E_TYPE_H_
/* Checksum and Shadow RAM pointers */
#define I40E_SR_NVM_CONTROL_WORD 0x00
-#define I40E_SR_EMP_MODULE_PTR 0x0F
+#define I40E_EMP_MODULE_PTR 0x0F
+#define I40E_SR_EMP_MODULE_PTR 0x48
#define I40E_NVM_OEM_VER_OFF 0x83
#define I40E_SR_NVM_DEV_STARTER_VERSION 0x18
#define I40E_SR_NVM_WAKE_ON_LAN 0x19
#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024
#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06
#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT)
+#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5)
+#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12)
+#define I40E_PTR_TYPE BIT(15)
/* Shadow RAM related */
#define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800
I40E_RESET_EMPR = 3,
};
+/* IEEE 802.1AB LLDP Agent Variables from NVM */
+#define I40E_NVM_LLDP_CFG_PTR 0x06
+#define I40E_SR_LLDP_CFG_PTR 0x31
+
/* RSS Hash Table Size */
#define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#ifndef _I40EVF_H_
#define _I40EVF_H_
#define I40E_TX_DESC(R, i) (&(((struct i40e_tx_desc *)((R)->desc))[i]))
#define I40E_TX_CTXTDESC(R, i) \
(&(((struct i40e_tx_context_desc *)((R)->desc))[i]))
-#define MAX_QUEUES 16
#define I40EVF_MAX_REQ_QUEUES 4
#define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4)
// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
#include <linux/list.h>
#include <linux/errno.h>
/**
* i40evf_client_add_instance - add a client instance to the instance list
* @adapter: pointer to the board struct
- * @client: pointer to a client struct in the client list.
*
* Returns cinst ptr on success, NULL on failure
**/
/**
* i40evf_client_del_instance - removes a client instance from the list
* @adapter: pointer to the board struct
- * @client: pointer to the client struct
*
**/
static
* i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
* @ldev: pointer to L2 context.
* @client: Client pointer.
- * @qv_info: queue and vector list
+ * @qvlist_info: queue and vector list
*
* Return 0 on success or < 0 on error
**/
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _I40E_CLIENT_H_
-#define _I40E_CLIENT_H_
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _I40EVF_CLIENT_H_
+#define _I40EVF_CLIENT_H_
#define I40EVF_CLIENT_STR_LENGTH 10
/* used by clients */
int i40evf_register_client(struct i40e_client *client);
int i40evf_unregister_client(struct i40e_client *client);
-#endif /* _I40E_CLIENT_H_ */
+#endif /* _I40EVF_CLIENT_H_ */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
/* ethtool support for i40evf */
#include "i40evf.h"
/**
* i40evf_get_priv_flags - report device private flags
- * @dev: network interface device structure
+ * @netdev: network interface device structure
*
* The get string set count and the string set should be matched for each
* flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags
/**
* i40evf_set_priv_flags - set private flags
- * @dev: network interface device structure
+ * @netdev: network interface device structure
* @flags: bit flags to be set
**/
static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
* i40evf_get_rxnfc - command to get RX flow classification rules
* @netdev: network interface device structure
* @cmd: ethtool rxnfc command
+ * @rule_locs: pointer to store rule locations
*
* Returns Success if the command is supported.
**/
* @netdev: network interface device structure
* @indir: indirection table
* @key: hash key
+ * @hfunc: hash function in use
*
* Reads the indirection table directly from the hardware. Always returns 0.
**/
* @netdev: network interface device structure
* @indir: indirection table
* @key: hash key
+ * @hfunc: hash function to use
*
* Returns -EINVAL if the table specifies an inavlid queue id, otherwise
* returns 0 after programming the table.
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40evf.h"
#include "i40e_prototype.h"
/**
* i40evf_request_traffic_irqs - Initialize MSI-X interrupts
* @adapter: board private structure
+ * @basename: device basename
*
* Allocates MSI-X vectors for tx and rx handling, and requests
* interrupts from the kernel.
f = i40evf_find_vlan(adapter, vlan);
if (!f) {
- f = kzalloc(sizeof(*f), GFP_ATOMIC);
+ f = kzalloc(sizeof(*f), GFP_KERNEL);
if (!f)
goto clearout;
/**
* i40evf_vlan_rx_add_vid - Add a VLAN filter to a device
* @netdev: network device struct
+ * @proto: unused protocol data
* @vid: VLAN tag
**/
static int i40evf_vlan_rx_add_vid(struct net_device *netdev,
/**
* i40evf_vlan_rx_kill_vid - Remove a VLAN filter from a device
* @netdev: network device struct
+ * @proto: unused protocol data
* @vid: VLAN tag
**/
static int i40evf_vlan_rx_kill_vid(struct net_device *netdev,
* ndo_open() returning, so we can't assume it means all our open
* tasks have finished, since we're not holding the rtnl_lock here.
*/
- running = (adapter->state == __I40EVF_RUNNING);
+ running = ((adapter->state == __I40EVF_RUNNING) ||
+ (adapter->state == __I40EVF_RESETTING));
if (running) {
netif_carrier_off(netdev);
total_max_rate += tx_rate;
num_qps += mqprio_qopt->qopt.count[i];
}
- if (num_qps > MAX_QUEUES)
+ if (num_qps > I40EVF_MAX_REQ_QUEUES)
return -EINVAL;
ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate);
/**
* i40evf_features_check - Validate encapsulated packet conforms to limits
* @skb: skb buff
- * @netdev: This physical port's netdev
+ * @dev: This physical port's netdev
* @features: Offload features that the stack believes apply
**/
static netdev_features_t i40evf_features_check(struct sk_buff *skb,
if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ /* Do not turn on offloads when they are requested to be turned off.
+ * TSO needs minimum 576 bytes to work correctly.
+ */
+ if (netdev->wanted_features) {
+ if (!(netdev->wanted_features & NETIF_F_TSO) ||
+ netdev->mtu < 576)
+ netdev->features &= ~NETIF_F_TSO;
+ if (!(netdev->wanted_features & NETIF_F_TSO6) ||
+ netdev->mtu < 576)
+ netdev->features &= ~NETIF_F_TSO6;
+ if (!(netdev->wanted_features & NETIF_F_TSO_ECN))
+ netdev->features &= ~NETIF_F_TSO_ECN;
+ if (!(netdev->wanted_features & NETIF_F_GRO))
+ netdev->features &= ~NETIF_F_GRO;
+ if (!(netdev->wanted_features & NETIF_F_GSO))
+ netdev->features &= ~NETIF_F_GSO;
+ }
+
adapter->vsi.id = adapter->vsi_res->vsi_id;
adapter->vsi.back = adapter;
pci_set_master(pdev);
- netdev = alloc_etherdev_mq(sizeof(struct i40evf_adapter), MAX_QUEUES);
+ netdev = alloc_etherdev_mq(sizeof(struct i40evf_adapter),
+ I40EVF_MAX_REQ_QUEUES);
if (!netdev) {
err = -ENOMEM;
goto err_alloc_etherdev;
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
- *
- * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include "i40evf.h"
#include "i40e_prototype.h"
/**
* i40evf_get_vf_config
- * @hw: pointer to the hardware structure
- * @len: length of buffer
+ * @adapter: private adapter structure
*
* Get VF configuration from PF and populate hw structure. Must be called after
* admin queue is initialized. Busy waits until response is received from PF,
/**
* i40evf_add_ether_addrs
* @adapter: adapter structure
- * @addrs: the MAC address filters to add (contiguous)
- * @count: number of filters
*
* Request that the PF add one or more addresses to our filters.
**/
/**
* i40evf_del_ether_addrs
* @adapter: adapter structure
- * @addrs: the MAC address filters to remove (contiguous)
- * @count: number of filtes
*
* Request that the PF remove one or more addresses from our filters.
**/
/**
* i40evf_add_vlans
* @adapter: adapter structure
- * @vlans: the VLANs to add
- * @count: number of VLANs
*
* Request that the PF add one or more VLAN filters to our VSI.
**/
/**
* i40evf_del_vlans
* @adapter: adapter structure
- * @vlans: the VLANs to remove
- * @count: number of VLANs
*
* Request that the PF remove one or more VLAN filters from our VSI.
**/
#define ICE_LG_ACT_MIRROR_VSI_ID_S 3
#define ICE_LG_ACT_MIRROR_VSI_ID_M (0x3FF << ICE_LG_ACT_MIRROR_VSI_ID_S)
- /* Action type = 5 - Large Action */
+ /* Action type = 5 - Generic Value */
#define ICE_LG_ACT_GENERIC 0x5
#define ICE_LG_ACT_GENERIC_VALUE_S 3
#define ICE_LG_ACT_GENERIC_VALUE_M (0xFFFF << ICE_LG_ACT_GENERIC_VALUE_S)
* NVM Update commands (indirect 0x0703)
*/
struct ice_aqc_nvm {
- u8 cmd_flags;
+ __le16 offset_low;
+ u8 offset_high;
+ u8 cmd_flags;
#define ICE_AQC_NVM_LAST_CMD BIT(0)
#define ICE_AQC_NVM_PCIR_REQ BIT(0) /* Used by NVM Update reply */
#define ICE_AQC_NVM_PRESERVATION_S 1
#define ICE_AQC_NVM_PRESERVE_ALL BIT(1)
#define ICE_AQC_NVM_PRESERVE_SELECTED (3 << CSR_AQ_NVM_PRESERVATION_S)
#define ICE_AQC_NVM_FLASH_ONLY BIT(7)
- u8 module_typeid;
- __le16 length;
+ __le16 module_typeid;
+ __le16 length;
#define ICE_AQC_NVM_ERASE_LEN 0xFFFF
- __le32 offset;
- __le32 addr_high;
- __le32 addr_low;
+ __le32 addr_high;
+ __le32 addr_low;
};
/* Get/Set RSS key (indirect 0x0B04/0x0B02) */
struct ice_aq_desc desc;
enum ice_status status;
u16 flags;
+ u8 i;
cmd = &desc.params.mac_read;
return ICE_ERR_CFG;
}
- ether_addr_copy(hw->port_info->mac.lan_addr, resp->mac_addr);
- ether_addr_copy(hw->port_info->mac.perm_addr, resp->mac_addr);
+ /* A single port can report up to two (LAN and WoL) addresses */
+ for (i = 0; i < cmd->num_addr; i++)
+ if (resp[i].addr_type == ICE_AQC_MAN_MAC_ADDR_TYPE_LAN) {
+ ether_addr_copy(hw->port_info->mac.lan_addr,
+ resp[i].mac_addr);
+ ether_addr_copy(hw->port_info->mac.perm_addr,
+ resp[i].mac_addr);
+ break;
+ }
+
return 0;
}
if (status)
goto err_unroll_sched;
- /* Get port MAC information */
- mac_buf_len = sizeof(struct ice_aqc_manage_mac_read_resp);
- mac_buf = devm_kzalloc(ice_hw_to_dev(hw), mac_buf_len, GFP_KERNEL);
+ /* Get MAC information */
+ /* A single port can report up to two (LAN and WoL) addresses */
+ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
+ sizeof(struct ice_aqc_manage_mac_read_resp),
+ GFP_KERNEL);
+ mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp);
if (!mac_buf) {
status = ICE_ERR_NO_MEMORY;
desc = ICE_CTL_Q_DESC(cq->rq, ntc);
desc_idx = ntc;
+ cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
flags = le16_to_cpu(desc->flags);
if (flags & ICE_AQ_FLAG_ERR) {
ret_code = ICE_ERR_AQ_ERROR;
- cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
ice_debug(hw, ICE_DBG_AQ_MSG,
"Control Receive Queue Event received with error 0x%x\n",
cq->rq_last_status);
#define PFINT_FW_CTL_CAUSE_ENA_S 30
#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S)
#define PFINT_OICR 0x0016CA00
-#define PFINT_OICR_INTEVENT_S 0
-#define PFINT_OICR_INTEVENT_M BIT(PFINT_OICR_INTEVENT_S)
#define PFINT_OICR_HLP_RDY_S 14
#define PFINT_OICR_HLP_RDY_M BIT(PFINT_OICR_HLP_RDY_S)
#define PFINT_OICR_CPM_RDY_S 15
oicr = rd32(hw, PFINT_OICR);
ena_mask = rd32(hw, PFINT_OICR_ENA);
- if (!(oicr & PFINT_OICR_INTEVENT_M))
- goto ena_intr;
-
if (oicr & PFINT_OICR_GRST_M) {
u32 reset;
/* we have a reset warning */
}
ret = IRQ_HANDLED;
-ena_intr:
/* re-enable interrupt causes that are not handled during this pass */
wr32(hw, PFINT_OICR_ENA, ena_mask);
if (!test_bit(__ICE_DOWN, pf->state)) {
* Read the NVM using the admin queue commands (0x0701)
*/
static enum ice_status
-ice_aq_read_nvm(struct ice_hw *hw, u8 module_typeid, u32 offset, u16 length,
+ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length,
void *data, bool last_command, struct ice_sq_cd *cd)
{
struct ice_aq_desc desc;
/* If this is the last command in a series, set the proper flag. */
if (last_command)
cmd->cmd_flags |= ICE_AQC_NVM_LAST_CMD;
- cmd->module_typeid = module_typeid;
- cmd->offset = cpu_to_le32(offset);
+ cmd->module_typeid = cpu_to_le16(module_typeid);
+ cmd->offset_low = cpu_to_le16(offset & 0xFFFF);
+ cmd->offset_high = (offset >> 16) & 0xFF;
cmd->length = cpu_to_le16(length);
return ice_aq_send_cmd(hw, &desc, data, length, cd);
u16 num_added = 0;
u32 temp;
+ *num_nodes_added = 0;
+
if (!num_nodes)
return status;
if (!parent || layer < hw->sw_entry_point_layer)
return ICE_ERR_PARAM;
- *num_nodes_added = 0;
-
/* max children per node per layer */
max_child_nodes =
le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel 82575 PCI-Express Ethernet Linux driver
-# Copyright(c) 1999 - 2014 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, see <http://www.gnu.org/licenses/>.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# Linux NICS <linux.nics@intel.com>
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
-
+# Copyright(c) 1999 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) 82575 PCI-Express ethernet driver
#
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
/* e1000_82575
* e1000_82576
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_82575_H_
#define _E1000_82575_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_DEFINES_H_
#define _E1000_DEFINES_H_
* manageability enabled, allowing us room for 15 multicast addresses.
*/
#define E1000_RAH_AV 0x80000000 /* Receive descriptor valid */
+#define E1000_RAH_ASEL_SRC_ADDR 0x00010000
+#define E1000_RAH_QSEL_ENABLE 0x10000000
#define E1000_RAL_MAC_ADDR_LEN 4
#define E1000_RAH_MAC_ADDR_LEN 2
#define E1000_RAH_POOL_MASK 0x03FC0000
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_HW_H_
#define _E1000_HW_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
/* e1000_i210
* e1000_i211
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_I210_H_
#define _E1000_I210_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#include <linux/if_ether.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_MAC_H_
#define _E1000_MAC_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#include "e1000_mbx.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_MBX_H_
#define _E1000_MBX_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#include <linux/if_ether.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_NVM_H_
#define _E1000_NVM_H_
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#include <linux/if_ether.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_PHY_H_
#define _E1000_PHY_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#ifndef _E1000_REGS_H_
#define _E1000_REGS_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
/* Linux PRO/1000 Ethernet Driver main header file */
enum igb_filter_match_flags {
IGB_FILTER_FLAG_ETHER_TYPE = 0x1,
IGB_FILTER_FLAG_VLAN_TCI = 0x2,
+ IGB_FILTER_FLAG_SRC_MAC_ADDR = 0x4,
+ IGB_FILTER_FLAG_DST_MAC_ADDR = 0x8,
};
#define IGB_MAX_RXNFC_FILTERS 16
u8 match_flags;
__be16 etype;
__be16 vlan_tci;
+ u8 src_addr[ETH_ALEN];
+ u8 dst_addr[ETH_ALEN];
};
struct igb_nfc_filter {
struct hlist_node nfc_node;
struct igb_nfc_input filter;
+ unsigned long cookie;
u16 etype_reg_index;
u16 sw_idx;
u16 action;
#define IGB_MAC_STATE_DEFAULT 0x1
#define IGB_MAC_STATE_IN_USE 0x2
+#define IGB_MAC_STATE_SRC_ADDR 0x4
+#define IGB_MAC_STATE_QUEUE_STEERING 0x8
/* board specific private data structure */
struct igb_adapter {
/* RX network flow classification support */
struct hlist_head nfc_filter_list;
+ struct hlist_head cls_flower_list;
unsigned int nfc_filter_count;
/* lock for RX network flow classification filter */
spinlock_t nfc_lock;
int igb_erase_filter(struct igb_adapter *adapter,
struct igb_nfc_filter *input);
+int igb_add_mac_steering_filter(struct igb_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags);
+int igb_del_mac_steering_filter(struct igb_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags);
+
#endif /* _IGB_H_ */
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
/* ethtool support for igb */
fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
}
+ if (rule->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) {
+ ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+ rule->filter.dst_addr);
+ /* As we only support matching by the full
+ * mask, return the mask to userspace
+ */
+ eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+ }
+ if (rule->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) {
+ ether_addr_copy(fsp->h_u.ether_spec.h_source,
+ rule->filter.src_addr);
+ /* As we only support matching by the full
+ * mask, return the mask to userspace
+ */
+ eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
+ }
+
return 0;
}
return -EINVAL;
int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input)
{
+ struct e1000_hw *hw = &adapter->hw;
int err = -EINVAL;
+ if (hw->mac.type == e1000_i210 &&
+ !(input->filter.match_flags & ~IGB_FILTER_FLAG_SRC_MAC_ADDR)) {
+ dev_err(&adapter->pdev->dev,
+ "i210 doesn't support flow classification rules specifying only source addresses.\n");
+ return -EOPNOTSUPP;
+ }
+
if (input->filter.match_flags & IGB_FILTER_FLAG_ETHER_TYPE) {
err = igb_rxnfc_write_etype_filter(adapter, input);
if (err)
return err;
}
+ if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) {
+ err = igb_add_mac_steering_filter(adapter,
+ input->filter.dst_addr,
+ input->action, 0);
+ err = min_t(int, err, 0);
+ if (err)
+ return err;
+ }
+
+ if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) {
+ err = igb_add_mac_steering_filter(adapter,
+ input->filter.src_addr,
+ input->action,
+ IGB_MAC_STATE_SRC_ADDR);
+ err = min_t(int, err, 0);
+ if (err)
+ return err;
+ }
+
if (input->filter.match_flags & IGB_FILTER_FLAG_VLAN_TCI)
err = igb_rxnfc_write_vlan_prio_filter(adapter, input);
igb_clear_vlan_prio_filter(adapter,
ntohs(input->filter.vlan_tci));
+ if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR)
+ igb_del_mac_steering_filter(adapter, input->filter.src_addr,
+ input->action,
+ IGB_MAC_STATE_SRC_ADDR);
+
+ if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR)
+ igb_del_mac_steering_filter(adapter, input->filter.dst_addr,
+ input->action, 0);
+
return 0;
}
/* add filter to the list */
if (parent)
- hlist_add_behind(&parent->nfc_node, &input->nfc_node);
+ hlist_add_behind(&input->nfc_node, &parent->nfc_node);
else
hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list);
if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
return -EINVAL;
- if (fsp->m_u.ether_spec.h_proto != ETHER_TYPE_FULL_MASK &&
- fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK))
- return -EINVAL;
-
input = kzalloc(sizeof(*input), GFP_KERNEL);
if (!input)
return -ENOMEM;
input->filter.match_flags = IGB_FILTER_FLAG_ETHER_TYPE;
}
+ /* Only support matching addresses by the full mask */
+ if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) {
+ input->filter.match_flags |= IGB_FILTER_FLAG_SRC_MAC_ADDR;
+ ether_addr_copy(input->filter.src_addr,
+ fsp->h_u.ether_spec.h_source);
+ }
+
+ /* Only support matching addresses by the full mask */
+ if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+ input->filter.match_flags |= IGB_FILTER_FLAG_DST_MAC_ADDR;
+ ether_addr_copy(input->filter.dst_addr,
+ fsp->h_u.ether_spec.h_dest);
+ }
+
if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
err = -EINVAL;
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#include "igb.h"
#include "e1000_82575.h"
// SPDX-License-Identifier: GPL-2.0
-/* Intel(R) Gigabit Ethernet Linux driver
- * Copyright(c) 2007-2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- */
+/* Copyright(c) 2007 - 2018 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
#include <linux/net_tstamp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
- if (enable) {
+ if (enable || queue == 0) {
+ /* i210 does not allow the queue 0 to be in the Strict
+ * Priority mode while the Qav mode is enabled, so,
+ * instead of disabling strict priority mode, we give
+ * queue 0 the maximum of credits possible.
+ *
+ * See section 8.12.19 of the i210 datasheet, "Note:
+ * Queue0 QueueMode must be set to 1b when
+ * TransmitMode is set to Qav."
+ */
+ if (queue == 0 && !enable) {
+ /* max "linkspeed" idleslope in kbps */
+ idleslope = 1000000;
+ hicredit = ETH_FRAME_LEN;
+ }
+
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
return 0;
}
+#define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+#define VLAN_PRIO_FULL_MASK (0x07)
+
+static int igb_parse_cls_flower(struct igb_adapter *adapter,
+ struct tc_cls_flower_offload *f,
+ int traffic_class,
+ struct igb_nfc_filter *input)
+{
+ struct netlink_ext_ack *extack = f->common.extack;
+
+ if (f->dissector->used_keys &
+ ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
+ BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_VLAN))) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported");
+ return -EOPNOTSUPP;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_dissector_key_eth_addrs *key, *mask;
+
+ key = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS,
+ f->key);
+ mask = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS,
+ f->mask);
+
+ if (!is_zero_ether_addr(mask->dst)) {
+ if (!is_broadcast_ether_addr(mask->dst)) {
+ NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address");
+ return -EINVAL;
+ }
+
+ input->filter.match_flags |=
+ IGB_FILTER_FLAG_DST_MAC_ADDR;
+ ether_addr_copy(input->filter.dst_addr, key->dst);
+ }
+
+ if (!is_zero_ether_addr(mask->src)) {
+ if (!is_broadcast_ether_addr(mask->src)) {
+ NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address");
+ return -EINVAL;
+ }
+
+ input->filter.match_flags |=
+ IGB_FILTER_FLAG_SRC_MAC_ADDR;
+ ether_addr_copy(input->filter.src_addr, key->src);
+ }
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key, *mask;
+
+ key = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+ mask = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->mask);
+
+ if (mask->n_proto) {
+ if (mask->n_proto != ETHER_TYPE_FULL_MASK) {
+ NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter");
+ return -EINVAL;
+ }
+
+ input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE;
+ input->filter.etype = key->n_proto;
+ }
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_dissector_key_vlan *key, *mask;
+
+ key = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->key);
+ mask = skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->mask);
+
+ if (mask->vlan_priority) {
+ if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
+ NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority");
+ return -EINVAL;
+ }
+
+ input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI;
+ input->filter.vlan_tci = key->vlan_priority;
+ }
+ }
+
+ input->action = traffic_class;
+ input->cookie = f->cookie;
+
+ return 0;
+}
+
+static int igb_configure_clsflower(struct igb_adapter *adapter,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ struct netlink_ext_ack *extack = cls_flower->common.extack;
+ struct igb_nfc_filter *filter, *f;
+ int err, tc;
+
+ tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
+ if (tc < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid traffic class");
+ return -EINVAL;
+ }
+
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return -ENOMEM;
+
+ err = igb_parse_cls_flower(adapter, cls_flower, tc, filter);
+ if (err < 0)
+ goto err_parse;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(f, &adapter->nfc_filter_list, nfc_node) {
+ if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) {
+ err = -EEXIST;
+ NL_SET_ERR_MSG_MOD(extack,
+ "This filter is already set in ethtool");
+ goto err_locked;
+ }
+ }
+
+ hlist_for_each_entry(f, &adapter->cls_flower_list, nfc_node) {
+ if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) {
+ err = -EEXIST;
+ NL_SET_ERR_MSG_MOD(extack,
+ "This filter is already set in cls_flower");
+ goto err_locked;
+ }
+ }
+
+ err = igb_add_filter(adapter, filter);
+ if (err < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Could not add filter to the adapter");
+ goto err_locked;
+ }
+
+ hlist_add_head(&filter->nfc_node, &adapter->cls_flower_list);
+
+ spin_unlock(&adapter->nfc_lock);
+
+ return 0;
+
+err_locked:
+ spin_unlock(&adapter->nfc_lock);
+
+err_parse:
+ kfree(filter);
+
+ return err;
+}
+
+static int igb_delete_clsflower(struct igb_adapter *adapter,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ struct igb_nfc_filter *filter;
+ int err;
+
+ spin_lock(&adapter->nfc_lock);
+
+ hlist_for_each_entry(filter, &adapter->cls_flower_list, nfc_node)
+ if (filter->cookie == cls_flower->cookie)
+ break;
+
+ if (!filter) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ err = igb_erase_filter(adapter, filter);
+ if (err < 0)
+ goto out;
+
+ hlist_del(&filter->nfc_node);
+ kfree(filter);
+
+out:
+ spin_unlock(&adapter->nfc_lock);
+
+ return err;
+}
+
+static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
+ struct tc_cls_flower_offload *cls_flower)
+{
+ switch (cls_flower->command) {
+ case TC_CLSFLOWER_REPLACE:
+ return igb_configure_clsflower(adapter, cls_flower);
+ case TC_CLSFLOWER_DESTROY:
+ return igb_delete_clsflower(adapter, cls_flower);
+ case TC_CLSFLOWER_STATS:
+ return -EOPNOTSUPP;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+ void *cb_priv)
+{
+ struct igb_adapter *adapter = cb_priv;
+
+ if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data))
+ return -EOPNOTSUPP;
+
+ switch (type) {
+ case TC_SETUP_CLSFLOWER:
+ return igb_setup_tc_cls_flower(adapter, type_data);
+
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int igb_setup_tc_block(struct igb_adapter *adapter,
+ struct tc_block_offload *f)
+{
+ if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ return -EOPNOTSUPP;
+
+ switch (f->command) {
+ case TC_BLOCK_BIND:
+ return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
+ adapter, adapter);
+ case TC_BLOCK_UNBIND:
+ tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
+ adapter);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
switch (type) {
case TC_SETUP_QDISC_CBS:
return igb_offload_cbs(adapter, type_data);
+ case TC_SETUP_BLOCK:
+ return igb_setup_tc_block(adapter, type_data);
default:
return -EOPNOTSUPP;
if (hw->mac.type >= e1000_82576)
netdev->features |= NETIF_F_SCTP_CRC;
+ if (hw->mac.type >= e1000_i350)
+ netdev->features |= NETIF_F_HW_TC;
+
#define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
NETIF_F_GSO_GRE_CSUM | \
NETIF_F_GSO_IPXIP4 | \
igb_rar_set_index(adapter, 0);
}
-static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr,
- const u8 queue)
+/* If the filter to be added and an already existing filter express
+ * the same address and address type, it should be possible to only
+ * override the other configurations, for example the queue to steer
+ * traffic.
+ */
+static bool igb_mac_entry_can_be_used(const struct igb_mac_addr *entry,
+ const u8 *addr, const u8 flags)
+{
+ if (!(entry->state & IGB_MAC_STATE_IN_USE))
+ return true;
+
+ if ((entry->state & IGB_MAC_STATE_SRC_ADDR) !=
+ (flags & IGB_MAC_STATE_SRC_ADDR))
+ return false;
+
+ if (!ether_addr_equal(addr, entry->addr))
+ return false;
+
+ return true;
+}
+
+/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
+ * 'flags' is used to indicate what kind of match is made, match is by
+ * default for the destination address, if matching by source address
+ * is desired the flag IGB_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igb_add_mac_filter_flags(struct igb_adapter *adapter,
+ const u8 *addr, const u8 queue,
+ const u8 flags)
{
struct e1000_hw *hw = &adapter->hw;
int rar_entries = hw->mac.rar_entry_count -
* addresses.
*/
for (i = 0; i < rar_entries; i++) {
- if (adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE)
+ if (!igb_mac_entry_can_be_used(&adapter->mac_table[i],
+ addr, flags))
continue;
ether_addr_copy(adapter->mac_table[i].addr, addr);
adapter->mac_table[i].queue = queue;
- adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE;
+ adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE | flags;
igb_rar_set_index(adapter, i);
return i;
return -ENOSPC;
}
-static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr,
+static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr,
const u8 queue)
+{
+ return igb_add_mac_filter_flags(adapter, addr, queue, 0);
+}
+
+/* Remove a MAC filter for 'addr' directing matching traffic to
+ * 'queue', 'flags' is used to indicate what kind of match need to be
+ * removed, match is by default for the destination address, if
+ * matching by source address is to be removed the flag
+ * IGB_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igb_del_mac_filter_flags(struct igb_adapter *adapter,
+ const u8 *addr, const u8 queue,
+ const u8 flags)
{
struct e1000_hw *hw = &adapter->hw;
int rar_entries = hw->mac.rar_entry_count -
for (i = 0; i < rar_entries; i++) {
if (!(adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE))
continue;
+ if ((adapter->mac_table[i].state & flags) != flags)
+ continue;
if (adapter->mac_table[i].queue != queue)
continue;
if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
continue;
- adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE;
- memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
- adapter->mac_table[i].queue = 0;
+ /* When a filter for the default address is "deleted",
+ * we return it to its initial configuration
+ */
+ if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT) {
+ adapter->mac_table[i].state =
+ IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE;
+ adapter->mac_table[i].queue =
+ adapter->vfs_allocated_count;
+ } else {
+ adapter->mac_table[i].state = 0;
+ adapter->mac_table[i].queue = 0;
+ memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+ }
igb_rar_set_index(adapter, i);
return 0;
return -ENOENT;
}
+static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr,
+ const u8 queue)
+{
+ return igb_del_mac_filter_flags(adapter, addr, queue, 0);
+}
+
+int igb_add_mac_steering_filter(struct igb_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags)
+{
+ struct e1000_hw *hw = &adapter->hw;
+
+ /* In theory, this should be supported on 82575 as well, but
+ * that part wasn't easily accessible during development.
+ */
+ if (hw->mac.type != e1000_i210)
+ return -EOPNOTSUPP;
+
+ return igb_add_mac_filter_flags(adapter, addr, queue,
+ IGB_MAC_STATE_QUEUE_STEERING | flags);
+}
+
+int igb_del_mac_steering_filter(struct igb_adapter *adapter,
+ const u8 *addr, u8 queue, u8 flags)
+{
+ return igb_del_mac_filter_flags(adapter, addr, queue,
+ IGB_MAC_STATE_QUEUE_STEERING | flags);
+}
+
static int igb_uc_sync(struct net_device *netdev, const unsigned char *addr)
{
struct igb_adapter *adapter = netdev_priv(netdev);
if (is_valid_ether_addr(addr))
rar_high |= E1000_RAH_AV;
- if (hw->mac.type == e1000_82575)
+ if (adapter->mac_table[index].state & IGB_MAC_STATE_SRC_ADDR)
+ rar_high |= E1000_RAH_ASEL_SRC_ADDR;
+
+ switch (hw->mac.type) {
+ case e1000_82575:
+ case e1000_i210:
+ if (adapter->mac_table[index].state &
+ IGB_MAC_STATE_QUEUE_STEERING)
+ rar_high |= E1000_RAH_QSEL_ENABLE;
+
rar_high |= E1000_RAH_POOL_1 *
adapter->mac_table[index].queue;
- else
+ break;
+ default:
rar_high |= E1000_RAH_POOL_1 <<
adapter->mac_table[index].queue;
+ break;
+ }
}
wr32(E1000_RAL(index), rar_low);
hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
igb_erase_filter(adapter, rule);
+ hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node)
+ igb_erase_filter(adapter, rule);
+
spin_unlock(&adapter->nfc_lock);
}
// SPDX-License-Identifier: GPL-2.0+
-/* PTP Hardware Clock (PHC) driver for the Intel 82576 and 82580
- *
- * Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- */
+/* Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com> */
+
#include <linux/module.h>
#include <linux/device.h>
#include <linux/pci.h>
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel(R) 82576 Virtual Function Linux driver
-# Copyright(c) 2009 - 2012 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
-
+# Copyright(c) 2009 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) 82576 VF ethernet driver
#
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 1999 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000_DEFINES_H_
#define _E1000_DEFINES_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
/* ethtool support for igbvf */
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
/* Linux PRO/1000 Ethernet Driver main header file */
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
#include "mbx.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 1999 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _E1000_MBX_H_
#define _E1000_MBX_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
#ifndef _E1000_REGS_H_
#define _E1000_REGS_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
#include "vf.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 - 2012 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2009 - 2018 Intel Corporation. */
#ifndef _E1000_VF_H_
#define _E1000_VF_H_
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel PRO/10GbE Linux driver
# Copyright(c) 1999 - 2008 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# Linux NICS <linux.nics@intel.com>
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
-
#
# Makefile for the Intel(R) PRO/10GbE ethernet driver
#
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#ifndef _IXGB_H_
#define _IXGB_H_
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#ifndef _IXGB_EE_H_
#define _IXGB_EE_H_
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
/* ethtool support for ixgb */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
/* ixgb_hw.c
* Shared functions for accessing and configuring the adapter
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#ifndef _IXGB_HW_H_
#define _IXGB_HW_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#ifndef _IXGB_IDS_H_
#define _IXGB_IDS_H_
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
/* glue for the OS independent part of ixgb
* includes register access macros
-/*******************************************************************************
-
- Intel PRO/10GbE Linux driver
- Copyright(c) 1999 - 2008 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2008 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel 10 Gigabit PCI Express Linux driver
-# Copyright(c) 1999 - 2013 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# Linux NICS <linux.nics@intel.com>
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
-
+# Copyright(c) 1999 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) 10GbE PCI Express ethernet driver
#
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_H_
#define _IXGBE_H_
struct ixgbe_fwd_adapter {
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
struct net_device *netdev;
- struct ixgbe_adapter *real_adapter;
unsigned int tx_base_queue;
unsigned int rx_base_queue;
int pool;
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
{
u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan;
- u32 bucket_hash = 0, hi_dword = 0;
+ u32 bucket_hash = 0;
+ __be32 hi_dword = 0;
int i;
/* Apply masks to input data */
* Limit hash to 13 bits since max bucket count is 8K.
* Store result at the end of the input stream.
*/
- input->formatted.bkt_hash = bucket_hash & 0x1FFF;
+ input->formatted.bkt_hash = (__force __be16)(bucket_hash & 0x1FFF);
}
/**
return IXGBE_ERR_CONFIG;
}
- switch (input_mask->formatted.flex_bytes & 0xFFFF) {
+ switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) {
case 0x0000:
/* Mask Flex Bytes */
fdirm |= IXGBE_FDIRM_FLEX;
IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, fdirport);
/* record vlan (little-endian) and flex_bytes(big-endian) */
- fdirvlan = IXGBE_STORE_AS_BE16(input->formatted.flex_bytes);
+ fdirvlan = IXGBE_STORE_AS_BE16((__force u16)input->formatted.flex_bytes);
fdirvlan <<= IXGBE_FDIRVLAN_FLEX_SHIFT;
fdirvlan |= ntohs(input->formatted.vlan_id);
IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, fdirvlan);
/* configure FDIRHASH register */
- fdirhash = input->formatted.bkt_hash;
+ fdirhash = (__force u32)input->formatted.bkt_hash;
fdirhash |= soft_id << IXGBE_FDIRHASH_SIG_SW_INDEX_SHIFT;
IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, fdirhash);
s32 err;
/* configure FDIRHASH register */
- fdirhash = input->formatted.bkt_hash;
+ fdirhash = (__force u32)input->formatted.bkt_hash;
fdirhash |= soft_id << IXGBE_FDIRHASH_SIG_SW_INDEX_SHIFT;
IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, fdirhash);
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
*/
for (i = 0; i < dword_len; i++)
IXGBE_WRITE_REG_ARRAY(hw, IXGBE_FLEX_MNG,
- i, cpu_to_le32(buffer[i]));
+ i, (__force u32)cpu_to_le32(buffer[i]));
/* Setting this bit tells the ARC that a new command is pending. */
IXGBE_WRITE_REG(hw, IXGBE_HICR, hicr | IXGBE_HICR_C);
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_COMMON_H_
#define _IXGBE_COMMON_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
-
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include "ixgbe_type.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _DCB_CONFIG_H_
#define _DCB_CONFIG_H_
// SPDX-License-Identifier: GPL-2.0
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include "ixgbe_type.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _DCB_82598_CONFIG_H_
#define _DCB_82598_CONFIG_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include "ixgbe_type.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _DCB_82599_CONFIG_H_
#define _DCB_82599_CONFIG_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2014 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include <linux/dcbnl.h>
-/*******************************************************************************
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
#include <linux/debugfs.h>
#include <linux/module.h>
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* ethtool support for ixgbe */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2014 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include <linux/if_ether.h>
case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP):
dma_unmap_sg(&adapter->pdev->dev, ddp->sgl,
ddp->sgc, DMA_FROM_DEVICE);
- ddp->err = ddp_err;
+ ddp->err = (__force u32)ddp_err;
ddp->sgl = NULL;
ddp->sgc = 0;
/* fall through */
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_FCOE_H
#define _IXGBE_FCOE_H
-/*******************************************************************************
- *
- * Intel 10 Gigabit PCI Express Linux driver
- * Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */
#include "ixgbe.h"
#include <net/xfrm.h>
int i;
for (i = 0; i < 4; i++)
- IXGBE_WRITE_REG(hw, IXGBE_IPSTXKEY(i), cpu_to_be32(key[3 - i]));
- IXGBE_WRITE_REG(hw, IXGBE_IPSTXSALT, cpu_to_be32(salt));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSTXKEY(i),
+ (__force u32)cpu_to_be32(key[3 - i]));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSTXSALT, (__force u32)cpu_to_be32(salt));
IXGBE_WRITE_FLUSH(hw);
reg = IXGBE_READ_REG(hw, IXGBE_IPSTXIDX);
int i;
/* store the SPI (in bigendian) and IPidx */
- IXGBE_WRITE_REG(hw, IXGBE_IPSRXSPI, cpu_to_le32(spi));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSRXSPI,
+ (__force u32)cpu_to_le32((__force u32)spi));
IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPIDX, ip_idx);
IXGBE_WRITE_FLUSH(hw);
/* store the key, salt, and mode */
for (i = 0; i < 4; i++)
- IXGBE_WRITE_REG(hw, IXGBE_IPSRXKEY(i), cpu_to_be32(key[3 - i]));
- IXGBE_WRITE_REG(hw, IXGBE_IPSRXSALT, cpu_to_be32(salt));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSRXKEY(i),
+ (__force u32)cpu_to_be32(key[3 - i]));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSRXSALT, (__force u32)cpu_to_be32(salt));
IXGBE_WRITE_REG(hw, IXGBE_IPSRXMOD, mode);
IXGBE_WRITE_FLUSH(hw);
/* store the ip address */
for (i = 0; i < 4; i++)
- IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPADDR(i), cpu_to_le32(addr[i]));
+ IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPADDR(i),
+ (__force u32)cpu_to_le32((__force u32)addr[i]));
IXGBE_WRITE_FLUSH(hw);
ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_ip_tbl);
struct xfrm_state *ret = NULL;
rcu_read_lock();
- hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, spi)
+ hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist,
+ (__force u32)spi) {
if (spi == rsa->xs->id.spi &&
((ip4 && *daddr == rsa->xs->id.daddr.a4) ||
(!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6,
xfrm_state_hold(ret);
break;
}
+ }
rcu_read_unlock();
return ret;
}
/* hash the new entry for faster search in Rx path */
hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist,
- rsa.xs->id.spi);
+ (__force u64)rsa.xs->id.spi);
} else {
struct tx_sa tsa;
if (!ipsec->ip_tbl[ipi].ref_cnt) {
memset(&ipsec->ip_tbl[ipi], 0,
sizeof(struct rx_ip_sa));
- ixgbe_ipsec_set_rx_ip(hw, ipi, zerobuf);
+ ixgbe_ipsec_set_rx_ip(hw, ipi,
+ (__force __be32 *)zerobuf);
}
}
kfree(ipsec->ip_tbl);
kfree(ipsec->rx_tbl);
kfree(ipsec->tx_tbl);
+ kfree(ipsec);
err1:
- kfree(adapter->ipsec);
netdev_err(adapter->netdev, "Unable to allocate memory for SA tables");
}
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program. If not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */
#ifndef _IXGBE_IPSEC_H_
#define _IXGBE_IPSEC_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include "ixgbe_sriov.h"
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/types.h>
#include <linux/module.h>
ring_desc = "";
pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p%s",
i,
- le64_to_cpu(u0->a),
- le64_to_cpu(u0->b),
+ le64_to_cpu((__force __le64)u0->a),
+ le64_to_cpu((__force __le64)u0->b),
(u64)dma_unmap_addr(tx_buffer, dma),
dma_unmap_len(tx_buffer, len),
tx_buffer->next_to_watch,
/* Descriptor Done */
pr_info("RWB[0x%03X] %016llX %016llX ---------------- %p%s\n",
i,
- le64_to_cpu(u0->a),
- le64_to_cpu(u0->b),
+ le64_to_cpu((__force __le64)u0->a),
+ le64_to_cpu((__force __le64)u0->b),
rx_buffer_info->skb,
ring_desc);
} else {
pr_info("R [0x%03X] %016llX %016llX %016llX %p%s\n",
i,
- le64_to_cpu(u0->a),
- le64_to_cpu(u0->b),
+ le64_to_cpu((__force __le64)u0->a),
+ le64_to_cpu((__force __le64)u0->b),
(u64)rx_buffer_info->dma,
rx_buffer_info->skb,
ring_desc);
if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP))
ixgbe_ipsec_rx(rx_ring, rx_desc, skb);
- skb->protocol = eth_type_trans(skb, dev);
-
/* record Rx queue, or update MACVLAN statistics */
if (netif_is_ixgbe(dev))
skb_record_rx_queue(skb, rx_ring->queue_index);
else
macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true,
- (skb->pkt_type == PACKET_BROADCAST) ||
- (skb->pkt_type == PACKET_MULTICAST));
+ false);
+
+ skb->protocol = eth_type_trans(skb, dev);
}
static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
- u32 reg_offset, vf_shift;
+ u16 pool = adapter->num_rx_pools;
+ u32 reg_offset, vf_shift, vmolr;
u32 gcr_ext, vmdctl;
int i;
vmdctl |= IXGBE_VT_CTL_REPLEN;
IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
+ /* accept untagged packets until a vlan tag is
+ * specifically set for the VMDQ queue/pool
+ */
+ vmolr = IXGBE_VMOLR_AUPE;
+ while (pool--)
+ IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr);
+
vf_shift = VMDQ_P(0) % 32;
reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0;
return -ENOMEM;
}
-/**
- * ixgbe_write_uc_addr_list - write unicast addresses to RAR table
- * @netdev: network interface device structure
- * @vfn: pool to associate with unicast addresses
- *
- * Writes unicast address list to the RAR table.
- * Returns: -ENOMEM on failure/insufficient address space
- * 0 on no addresses written
- * X on writing X addresses to the RAR table
- **/
-static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn)
-{
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
- int count = 0;
-
- /* return ENOMEM indicating insufficient memory for addresses */
- if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter, vfn))
- return -ENOMEM;
-
- if (!netdev_uc_empty(netdev)) {
- struct netdev_hw_addr *ha;
- netdev_for_each_uc_addr(ha, netdev) {
- ixgbe_del_mac_filter(adapter, ha->addr, vfn);
- ixgbe_add_mac_filter(adapter, ha->addr, vfn);
- count++;
- }
- }
- return count;
-}
-
static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
spin_unlock(&adapter->fdir_perfect_lock);
}
-static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool,
- struct ixgbe_adapter *adapter)
-{
- struct ixgbe_hw *hw = &adapter->hw;
- u32 vmolr;
-
- /* No unicast promiscuous support for VMDQ devices. */
- vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool));
- vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE);
-
- /* clear the affected bit */
- vmolr &= ~IXGBE_VMOLR_MPE;
-
- if (dev->flags & IFF_ALLMULTI) {
- vmolr |= IXGBE_VMOLR_MPE;
- } else {
- vmolr |= IXGBE_VMOLR_ROMPE;
- hw->mac.ops.update_mc_addr_list(hw, dev);
- }
- ixgbe_write_uc_addr_list(adapter->netdev, pool);
- IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr);
-}
-
/**
* ixgbe_clean_rx_ring - Free Rx Buffers per Queue
* @rx_ring: ring to free buffers from
rx_ring->next_to_use = 0;
}
-static int ixgbe_fwd_ring_up(struct net_device *vdev,
+static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
struct ixgbe_fwd_adapter *accel)
{
- struct ixgbe_adapter *adapter = accel->real_adapter;
+ struct net_device *vdev = accel->netdev;
int i, baseq, err;
- if (!test_bit(accel->pool, adapter->fwd_bitmask))
- return 0;
-
baseq = accel->pool * adapter->num_rx_queues_per_pool;
netdev_dbg(vdev, "pool %i:%i queues %i:%i\n",
accel->pool, adapter->num_rx_pools,
baseq, baseq + adapter->num_rx_queues_per_pool);
- accel->netdev = vdev;
accel->rx_base_queue = baseq;
accel->tx_base_queue = baseq;
*/
err = ixgbe_add_mac_filter(adapter, vdev->dev_addr,
VMDQ_P(accel->pool));
- if (err >= 0) {
- ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter);
+ if (err >= 0)
return 0;
- }
+
+ /* if we cannot add the MAC rule then disable the offload */
+ macvlan_release_l2fw_offload(vdev);
for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
adapter->rx_ring[baseq + i]->netdev = NULL;
+ netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
+
+ clear_bit(accel->pool, adapter->fwd_bitmask);
+ kfree(accel);
+
return err;
}
-static int ixgbe_upper_dev_walk(struct net_device *upper, void *data)
+static int ixgbe_macvlan_up(struct net_device *vdev, void *data)
{
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ struct ixgbe_adapter *adapter = data;
+ struct ixgbe_fwd_adapter *accel;
- if (dfwd->fwd_priv)
- ixgbe_fwd_ring_up(upper, vadapter);
- }
+ if (!netif_is_macvlan(vdev))
+ return 0;
+
+ accel = macvlan_accel_priv(vdev);
+ if (!accel)
+ return 0;
+
+ ixgbe_fwd_ring_up(adapter, accel);
return 0;
}
static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
{
netdev_walk_all_upper_dev_rcu(adapter->netdev,
- ixgbe_upper_dev_walk, NULL);
+ ixgbe_macvlan_up, adapter);
}
static void ixgbe_configure(struct ixgbe_adapter *adapter)
/* remove payload length from inner checksum */
paylen = skb->len - l4_offset;
- csum_replace_by_diff(&l4.tcp->check, htonl(paylen));
+ csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));
/* update gso size and bytecount with header size */
first->gso_segs = skb_shinfo(skb)->gso_segs;
}
#endif /* CONFIG_IXGBE_DCB */
+static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
+{
+ struct ixgbe_adapter *adapter = data;
+ struct ixgbe_fwd_adapter *accel;
+ int pool;
+
+ /* we only care about macvlans... */
+ if (!netif_is_macvlan(vdev))
+ return 0;
+
+ /* that have hardware offload enabled... */
+ accel = macvlan_accel_priv(vdev);
+ if (!accel)
+ return 0;
+
+ /* If we can relocate to a different bit do so */
+ pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
+ if (pool < adapter->num_rx_pools) {
+ set_bit(pool, adapter->fwd_bitmask);
+ accel->pool = pool;
+ return 0;
+ }
+
+ /* if we cannot find a free pool then disable the offload */
+ netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
+ macvlan_release_l2fw_offload(vdev);
+ kfree(accel);
+
+ return 0;
+}
+
+static void ixgbe_defrag_macvlan_pools(struct net_device *dev)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+ /* flush any stale bits out of the fwd bitmask */
+ bitmap_clear(adapter->fwd_bitmask, 1, 63);
+
+ /* walk through upper devices reassigning pools */
+ netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool,
+ adapter);
+}
+
/**
* ixgbe_setup_tc - configure net_device for multiple traffic classes
*
#endif /* CONFIG_IXGBE_DCB */
ixgbe_init_interrupt_scheme(adapter);
+ ixgbe_defrag_macvlan_pools(dev);
+
if (netif_running(dev))
return ixgbe_open(dev);
static int get_macvlan_queue(struct net_device *upper, void *_data)
{
if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper);
struct upper_walk_data *data = _data;
struct ixgbe_adapter *adapter = data->adapter;
int ifindex = data->ifindex;
- if (vadapter && vadapter->netdev->ifindex == ifindex) {
+ if (vadapter && upper->ifindex == ifindex) {
data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
data->action = data->queue;
return 1;
for (j = 0; field_ptr[j].val; j++) {
if (field_ptr[j].off == off) {
- field_ptr[j].val(input, mask, val, m);
+ field_ptr[j].val(input, mask, (__force u32)val,
+ (__force u32)m);
input->filter.formatted.flow_type |=
field_ptr[j].type;
found_entry = true;
}
if (nexthdr) {
if (nexthdr->off == cls->knode.sel->keys[i].off &&
- nexthdr->val == cls->knode.sel->keys[i].val &&
- nexthdr->mask == cls->knode.sel->keys[i].mask)
+ nexthdr->val ==
+ (__force u32)cls->knode.sel->keys[i].val &&
+ nexthdr->mask ==
+ (__force u32)cls->knode.sel->keys[i].mask)
found_jump_field = true;
else
continue;
for (i = 0; nexthdr[i].jump; i++) {
if (nexthdr[i].o != cls->knode.sel->offoff ||
nexthdr[i].s != cls->knode.sel->offshift ||
- nexthdr[i].m != cls->knode.sel->offmask)
+ nexthdr[i].m !=
+ (__force u32)cls->knode.sel->offmask)
return err;
jump = kzalloc(sizeof(*jump), GFP_KERNEL);
return features;
}
+static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter)
+{
+ int rss = min_t(int, ixgbe_max_rss_indices(adapter),
+ num_online_cpus());
+
+ /* go back to full RSS if we're not running SR-IOV */
+ if (!adapter->ring_feature[RING_F_VMDQ].offset)
+ adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED |
+ IXGBE_FLAG_SRIOV_ENABLED);
+
+ adapter->ring_feature[RING_F_RSS].limit = rss;
+ adapter->ring_feature[RING_F_VMDQ].limit = 1;
+
+ ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs);
+}
+
static int ixgbe_set_features(struct net_device *netdev,
netdev_features_t features)
{
}
}
- if (need_reset)
+ if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1)
+ ixgbe_reset_l2fw_offload(adapter);
+ else if (need_reset)
ixgbe_do_reset(netdev);
else if (changed & (NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER))
static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
{
- struct ixgbe_fwd_adapter *fwd_adapter = NULL;
struct ixgbe_adapter *adapter = netdev_priv(pdev);
- int used_pools = adapter->num_vfs + adapter->num_rx_pools;
+ struct ixgbe_fwd_adapter *accel;
int tcs = adapter->hw_tcs ? : 1;
- unsigned int limit;
int pool, err;
- /* Hardware has a limited number of available pools. Each VF, and the
- * PF require a pool. Check to ensure we don't attempt to use more
- * then the available number of pools.
+ /* The hardware supported by ixgbe only filters on the destination MAC
+ * address. In order to avoid issues we only support offloading modes
+ * where the hardware can actually provide the functionality.
*/
- if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
- return ERR_PTR(-EINVAL);
+ if (!macvlan_supports_dest_filter(vdev))
+ return ERR_PTR(-EMEDIUMTYPE);
- if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
- adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) ||
- (adapter->num_rx_pools > IXGBE_MAX_MACVLANS))
- return ERR_PTR(-EBUSY);
+ pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
+ if (pool == adapter->num_rx_pools) {
+ u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
+ u16 reserved_pools;
+
+ if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
+ adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) ||
+ adapter->num_rx_pools > IXGBE_MAX_MACVLANS)
+ return ERR_PTR(-EBUSY);
+
+ /* Hardware has a limited number of available pools. Each VF,
+ * and the PF require a pool. Check to ensure we don't
+ * attempt to use more then the available number of pools.
+ */
+ if (used_pools >= IXGBE_MAX_VF_FUNCTIONS)
+ return ERR_PTR(-EBUSY);
- fwd_adapter = kzalloc(sizeof(*fwd_adapter), GFP_KERNEL);
- if (!fwd_adapter)
- return ERR_PTR(-ENOMEM);
+ /* Enable VMDq flag so device will be set in VM mode */
+ adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED |
+ IXGBE_FLAG_SRIOV_ENABLED;
- pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
- set_bit(pool, adapter->fwd_bitmask);
- limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools + 1);
+ /* Try to reserve as many queues per pool as possible,
+ * we start with the configurations that support 4 queues
+ * per pools, followed by 2, and then by just 1 per pool.
+ */
+ if (used_pools < 32 && adapter->num_rx_pools < 16)
+ reserved_pools = min_t(u16,
+ 32 - used_pools,
+ 16 - adapter->num_rx_pools);
+ else if (adapter->num_rx_pools < 32)
+ reserved_pools = min_t(u16,
+ 64 - used_pools,
+ 32 - adapter->num_rx_pools);
+ else
+ reserved_pools = 64 - used_pools;
- /* Enable VMDq flag so device will be set in VM mode */
- adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED;
- adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
- fwd_adapter->pool = pool;
- fwd_adapter->real_adapter = adapter;
+ if (!reserved_pools)
+ return ERR_PTR(-EBUSY);
- /* Force reinit of ring allocation with VMDQ enabled */
- err = ixgbe_setup_tc(pdev, adapter->hw_tcs);
+ adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools;
- if (!err && netif_running(pdev))
- err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
+ /* Force reinit of ring allocation with VMDQ enabled */
+ err = ixgbe_setup_tc(pdev, adapter->hw_tcs);
+ if (err)
+ return ERR_PTR(err);
- if (!err)
- return fwd_adapter;
+ if (pool >= adapter->num_rx_pools)
+ return ERR_PTR(-ENOMEM);
+ }
- /* unwind counter and free adapter struct */
- netdev_info(pdev,
- "%s: dfwd hardware acceleration failed\n", vdev->name);
- clear_bit(pool, adapter->fwd_bitmask);
- kfree(fwd_adapter);
- return ERR_PTR(err);
+ accel = kzalloc(sizeof(*accel), GFP_KERNEL);
+ if (!accel)
+ return ERR_PTR(-ENOMEM);
+
+ set_bit(pool, adapter->fwd_bitmask);
+ accel->pool = pool;
+ accel->netdev = vdev;
+
+ if (!netif_running(pdev))
+ return accel;
+
+ err = ixgbe_fwd_ring_up(adapter, accel);
+ if (err)
+ return ERR_PTR(err);
+
+ return accel;
}
static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
{
struct ixgbe_fwd_adapter *accel = priv;
- struct ixgbe_adapter *adapter = accel->real_adapter;
+ struct ixgbe_adapter *adapter = netdev_priv(pdev);
unsigned int rxbase = accel->rx_base_queue;
- unsigned int limit, i;
+ unsigned int i;
/* delete unicast filter associated with offloaded interface */
ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr,
VMDQ_P(accel->pool));
- /* disable ability to receive packets for this pool */
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_VMOLR(accel->pool), 0);
-
/* Allow remaining Rx packets to get flushed out of the
* Rx FIFO before we drop the netdev for the ring.
*/
}
clear_bit(accel->pool, adapter->fwd_bitmask);
- limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
- adapter->ring_feature[RING_F_VMDQ].limit = limit + 1;
-
- /* go back to full RSS if we're done with our VMQs */
- if (adapter->ring_feature[RING_F_VMDQ].limit == 1) {
- int rss = min_t(int, ixgbe_max_rss_indices(adapter),
- num_online_cpus());
-
- adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
- adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
- adapter->ring_feature[RING_F_RSS].limit = rss;
- }
-
- ixgbe_setup_tc(pdev, adapter->hw_tcs);
- netdev_dbg(pdev, "pool %i:%i queues %i:%i\n",
- accel->pool, adapter->num_rx_pools,
- accel->rx_base_queue,
- accel->rx_base_queue +
- adapter->num_rx_queues_per_pool);
kfree(accel);
}
}
} else {
for (i = 0; i < adapter->num_rx_queues; i++)
- xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog);
+ (void)xchg(&adapter->rx_ring[i]->xdp_prog,
+ adapter->xdp_prog);
}
if (old_prog)
rtnl_lock();
netif_device_detach(netdev);
+ if (netif_running(netdev))
+ ixgbe_close_suspend(adapter);
+
if (state == pci_channel_io_perm_failure) {
rtnl_unlock();
return PCI_ERS_RESULT_DISCONNECT;
}
- if (netif_running(netdev))
- ixgbe_close_suspend(adapter);
-
if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state))
pci_disable_device(pdev);
rtnl_unlock();
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_MBX_H_
#define _IXGBE_MBX_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel 10 Gigabit PCI Express Linux drive
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_MODEL_H_
#define _IXGBE_MODEL_H_
union ixgbe_atr_input *mask,
u32 val, u32 m)
{
- input->filter.formatted.src_ip[0] = val;
- mask->formatted.src_ip[0] = m;
+ input->filter.formatted.src_ip[0] = (__force __be32)val;
+ mask->formatted.src_ip[0] = (__force __be32)m;
return 0;
}
union ixgbe_atr_input *mask,
u32 val, u32 m)
{
- input->filter.formatted.dst_ip[0] = val;
- mask->formatted.dst_ip[0] = m;
+ input->filter.formatted.dst_ip[0] = (__force __be32)val;
+ mask->formatted.dst_ip[0] = (__force __be32)m;
return 0;
}
union ixgbe_atr_input *mask,
u32 val, u32 m)
{
- input->filter.formatted.src_port = val & 0xffff;
- mask->formatted.src_port = m & 0xffff;
- input->filter.formatted.dst_port = val >> 16;
- mask->formatted.dst_port = m >> 16;
+ input->filter.formatted.src_port = (__force __be16)(val & 0xffff);
+ mask->formatted.src_port = (__force __be16)(m & 0xffff);
+ input->filter.formatted.dst_port = (__force __be16)(val >> 16);
+ mask->formatted.dst_port = (__force __be16)(m >> 16);
return 0;
};
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2014 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_PHY_H_
#define _IXGBE_PHY_H_
-/*******************************************************************************
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
#include "ixgbe.h"
#include <linux/ptp_classify.h>
#include <linux/clocksource.h>
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/types.h>
#include <linux/module.h>
#endif
/* Disable VMDq flag so device will be set in VM mode */
- if (adapter->ring_feature[RING_F_VMDQ].limit == 1) {
+ if (bitmap_weight(adapter->fwd_bitmask, adapter->num_rx_pools) == 1) {
adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
rss = min_t(int, ixgbe_max_rss_indices(adapter),
* other values out of range.
*/
num_tc = adapter->hw_tcs;
- num_rx_pools = adapter->num_rx_pools;
+ num_rx_pools = bitmap_weight(adapter->fwd_bitmask,
+ adapter->num_rx_pools);
limit = (num_tc > 4) ? IXGBE_MAX_VFS_8TC :
(num_tc > 1) ? IXGBE_MAX_VFS_4TC : IXGBE_MAX_VFS_1TC;
/* reply to reset with ack and vf mac address */
msgbuf[0] = IXGBE_VF_RESET;
- if (!is_zero_ether_addr(vf_mac)) {
+ if (!is_zero_ether_addr(vf_mac) && adapter->vfinfo[vf].pf_set_mac) {
msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK;
memcpy(addr, vf_mac, ETH_ALEN);
} else {
msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
- dev_warn(&adapter->pdev->dev,
- "VF %d has no MAC address assigned, you may have to assign one manually\n",
- vf);
}
/*
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_SRIOV_H_
#define _IXGBE_SRIOV_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe.h"
#include "ixgbe_common.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_TYPE_H_
#define _IXGBE_TYPE_H_
-/*******************************************************************************
-
- Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2016 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include <linux/pci.h>
#include <linux/delay.h>
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
- *
- * Intel 10 Gigabit PCI Express Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- *****************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "ixgbe_type.h"
-/*******************************************************************************
- *
- * Intel 10 Gigabit PCI Express Linux driver
- * Copyright(c) 1999 - 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Contact Information:
- * Linux NICS <linux.nics@intel.com>
- * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- ******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
+
#include "ixgbe_x540.h"
#include "ixgbe_type.h"
#include "ixgbe_common.h"
buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM;
/* convert offset from words to bytes */
- buffer.address = cpu_to_be32((offset + current_word) * 2);
- buffer.length = cpu_to_be16(words_to_read * 2);
+ buffer.address = (__force u32)cpu_to_be32((offset +
+ current_word) * 2);
+ buffer.length = (__force u16)cpu_to_be16(words_to_read * 2);
buffer.pad2 = 0;
buffer.pad3 = 0;
buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM;
/* convert offset from words to bytes */
- buffer.address = cpu_to_be32(offset * 2);
+ buffer.address = (__force u32)cpu_to_be32(offset * 2);
/* one word */
- buffer.length = cpu_to_be16(sizeof(u16));
+ buffer.length = (__force u16)cpu_to_be16(sizeof(u16));
status = hw->mac.ops.acquire_swfw_sync(hw, mask);
if (status)
hw->phy.sfp_setup_needed = false;
}
+ if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+ return status;
+
/* Reset PHY */
if (!hw->phy.reset_disable && hw->phy.ops.reset)
hw->phy.ops.reset(hw);
# SPDX-License-Identifier: GPL-2.0
-################################################################################
-#
-# Intel 82599 Virtual Function driver
-# Copyright(c) 1999 - 2012 Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
-# Contact Information:
-# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-#
-################################################################################
-
+# Copyright(c) 1999 - 2018 Intel Corporation.
#
# Makefile for the Intel(R) 82599 VF ethernet driver
#
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBEVF_DEFINES_H_
#define _IXGBEVF_DEFINES_H_
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2018 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/* ethtool support for ixgbevf */
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2018 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBEVF_H_
#define _IXGBEVF_H_
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2018 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
/******************************************************************************
Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
if (!err)
continue;
hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j);
- break;
+ goto err_setup_tx;
}
return 0;
return NETDEV_TX_OK;
}
-static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
struct ixgbevf_ring *tx_ring;
return -EPERM;
ether_addr_copy(hw->mac.addr, addr->sa_data);
+ ether_addr_copy(hw->mac.perm_addr, addr->sa_data);
ether_addr_copy(netdev->dev_addr, addr->sa_data);
return 0;
rtnl_lock();
netif_device_detach(netdev);
+ if (netif_running(netdev))
+ ixgbevf_close_suspend(adapter);
+
if (state == pci_channel_io_perm_failure) {
rtnl_unlock();
return PCI_ERS_RESULT_DISCONNECT;
}
- if (netif_running(netdev))
- ixgbevf_close_suspend(adapter);
-
if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state))
pci_disable_device(pdev);
rtnl_unlock();
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "mbx.h"
#include "ixgbevf.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBE_MBX_H_
#define _IXGBE_MBX_H_
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef _IXGBEVF_REGS_H_
#define _IXGBEVF_REGS_H_
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#include "vf.h"
#include "ixgbevf.h"
/* SPDX-License-Identifier: GPL-2.0 */
-/*******************************************************************************
-
- Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2015 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, see <http://www.gnu.org/licenses/>.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Copyright(c) 1999 - 2018 Intel Corporation. */
#ifndef __IXGBE_VF_H__
#define __IXGBE_VF_H__
depends on ARCH_MVEBU || COMPILE_TEST
depends on HAS_DMA
select MVMDIO
+ select PHYLINK
---help---
This driver supports the network interface units in the
Marvell ARMADA 375, 7K and 8K SoCs.
goto out_mdio;
}
- if (pdev->dev.of_node)
- ret = of_mdiobus_register(bus, pdev->dev.of_node);
- else
- ret = mdiobus_register(bus);
+ ret = of_mdiobus_register(bus, pdev->dev.of_node);
if (ret < 0) {
dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret);
goto out_mdio;
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/phy.h>
+#include <linux/phylink.h>
#include <linux/phy/phy.h>
#include <linux/clk.h>
#include <linux/hrtimer.h>
#define MVPP2_GMAC_FORCE_LINK_PASS BIT(1)
#define MVPP2_GMAC_IN_BAND_AUTONEG BIT(2)
#define MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS BIT(3)
+#define MVPP2_GMAC_IN_BAND_RESTART_AN BIT(4)
#define MVPP2_GMAC_CONFIG_MII_SPEED BIT(5)
#define MVPP2_GMAC_CONFIG_GMII_SPEED BIT(6)
#define MVPP2_GMAC_AN_SPEED_EN BIT(7)
#define MVPP2_GMAC_FC_ADV_EN BIT(9)
+#define MVPP2_GMAC_FC_ADV_ASM_EN BIT(10)
#define MVPP2_GMAC_FLOW_CTRL_AUTONEG BIT(11)
#define MVPP2_GMAC_CONFIG_FULL_DUPLEX BIT(12)
#define MVPP2_GMAC_AN_DUPLEX_EN BIT(13)
#define MVPP2_GMAC_STATUS0 0x10
#define MVPP2_GMAC_STATUS0_LINK_UP BIT(0)
+#define MVPP2_GMAC_STATUS0_GMII_SPEED BIT(1)
+#define MVPP2_GMAC_STATUS0_MII_SPEED BIT(2)
+#define MVPP2_GMAC_STATUS0_FULL_DUPLEX BIT(3)
+#define MVPP2_GMAC_STATUS0_RX_PAUSE BIT(6)
+#define MVPP2_GMAC_STATUS0_TX_PAUSE BIT(7)
+#define MVPP2_GMAC_STATUS0_AN_COMPLETE BIT(11)
#define MVPP2_GMAC_PORT_FIFO_CFG_1_REG 0x1c
#define MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS 6
#define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0
#define MVPP22_GMAC_INT_MASK_LINK_STAT BIT(1)
#define MVPP22_GMAC_CTRL_4_REG 0x90
#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0)
+#define MVPP22_CTRL4_RX_FC_EN BIT(3)
+#define MVPP22_CTRL4_TX_FC_EN BIT(4)
#define MVPP22_CTRL4_DP_CLK_SEL BIT(5)
#define MVPP22_CTRL4_SYNC_BYPASS_DIS BIT(6)
#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7)
#define MVPP22_XLG_CTRL0_PORT_EN BIT(0)
#define MVPP22_XLG_CTRL0_MAC_RESET_DIS BIT(1)
#define MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN BIT(7)
+#define MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN BIT(8)
#define MVPP22_XLG_CTRL0_MIB_CNT_DIS BIT(14)
#define MVPP22_XLG_CTRL1_REG 0x104
#define MVPP22_XLG_CTRL1_FRAMESIZELIMIT_OFFS 0
#define MVPP22_XLG_CTRL4_FWD_FC BIT(5)
#define MVPP22_XLG_CTRL4_FWD_PFC BIT(6)
#define MVPP22_XLG_CTRL4_MACMODSELECT_GMAC BIT(12)
+#define MVPP22_XLG_CTRL4_EN_IDLE_CHECK BIT(14)
/* SMI registers. PPv2.2 only, relative to priv->iface_base. */
#define MVPP22_SMI_MISC_CFG_REG 0x1204
struct clk *pp_clk;
struct clk *gop_clk;
struct clk *mg_clk;
+ struct clk *mg_core_clk;
struct clk *axi_clk;
/* List of pointers to port structures */
/* Firmware node associated to the port */
struct fwnode_handle *fwnode;
+ /* Is a PHY always connected to the port */
+ bool has_phy;
+
/* Per-port registers' base address */
void __iomem *base;
void __iomem *stats_base;
struct mutex gather_stats_lock;
struct delayed_work stats_work;
+ struct device_node *of_node;
+
phy_interface_t phy_interface;
- struct device_node *phy_node;
+ struct phylink *phylink;
struct phy *comphy;
- unsigned int link;
- unsigned int duplex;
- unsigned int speed;
struct mvpp2_bm_pool *pool_long;
struct mvpp2_bm_pool *pool_short;
(addr) < (txq_pcpu)->tso_headers_dma + \
(txq_pcpu)->size * TSO_HEADER_SIZE)
+/* The prototype is added here to be used in start_dev when using ACPI. This
+ * will be removed once phylink is used for all modes (dt+ACPI).
+ */
+static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
+ const struct phylink_link_state *state);
+
/* Queue modes */
#define MVPP2_QDIST_SINGLE_MODE 0
#define MVPP2_QDIST_MULTI_MODE 1
int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE;
for (i = 0; i < MVPP2_PRS_AI_BITS; i++) {
-
if (!(enable & BIT(i)))
continue;
int ai_off = MVPP2_PRS_SRAM_AI_OFFS;
for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) {
-
if (!(mask & BIT(i)))
continue;
mvpp2_prs_sram_ai_update(&pe, 0,
MVPP2_PRS_SRAM_AI_MASK);
+ /* Set result info bits to 'single vlan' */
+ mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_VLAN_SINGLE,
+ MVPP2_PRS_RI_VLAN_MASK);
/* If packet is tagged continue check vid filtering */
mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VID);
} else {
mvpp22_gop_init_rgmii(port);
break;
case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ case PHY_INTERFACE_MODE_2500BASEX:
mvpp22_gop_init_sgmii(port);
break;
case PHY_INTERFACE_MODE_10GKR:
u32 val;
if (phy_interface_mode_is_rgmii(port->phy_interface) ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
+ port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+ port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
+ port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
/* Enable the GMAC link status irq for this port */
val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
val |= MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
if (port->gop_id == 0) {
val = readl(port->base + MVPP22_XLG_EXT_INT_MASK);
val &= ~(MVPP22_XLG_EXT_INT_MASK_XLG |
- MVPP22_XLG_EXT_INT_MASK_GIG);
+ MVPP22_XLG_EXT_INT_MASK_GIG);
writel(val, port->base + MVPP22_XLG_EXT_INT_MASK);
}
if (phy_interface_mode_is_rgmii(port->phy_interface) ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
+ port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+ port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
+ port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
val &= ~MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK);
u32 val;
if (phy_interface_mode_is_rgmii(port->phy_interface) ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
+ port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+ port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
+ port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
val = readl(port->base + MVPP22_GMAC_INT_MASK);
val |= MVPP22_GMAC_INT_MASK_LINK_STAT;
writel(val, port->base + MVPP22_GMAC_INT_MASK);
mvpp22_gop_unmask_irq(port);
}
+/* Sets the PHY mode of the COMPHY (which configures the serdes lanes).
+ *
+ * The PHY mode used by the PPv2 driver comes from the network subsystem, while
+ * the one given to the COMPHY comes from the generic PHY subsystem. Hence they
+ * differ.
+ *
+ * The COMPHY configures the serdes lanes regardless of the actual use of the
+ * lanes by the physical layer. This is why configurations like
+ * "PPv2 (2500BaseX) - COMPHY (2500SGMII)" are valid.
+ */
static int mvpp22_comphy_init(struct mvpp2_port *port)
{
enum phy_mode mode;
switch (port->phy_interface) {
case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
mode = PHY_MODE_SGMII;
break;
+ case PHY_INTERFACE_MODE_2500BASEX:
+ mode = PHY_MODE_2500SGMII;
+ break;
case PHY_INTERFACE_MODE_10GKR:
mode = PHY_MODE_10GKR;
break;
return phy_power_on(port->comphy);
}
-static void mvpp2_port_mii_gmac_configure_mode(struct mvpp2_port *port)
-{
- u32 val;
-
- if (port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
- val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
- val |= MVPP22_CTRL4_SYNC_BYPASS_DIS | MVPP22_CTRL4_DP_CLK_SEL |
- MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
- val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
- writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
- } else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
- val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
- val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
- MVPP22_CTRL4_SYNC_BYPASS_DIS |
- MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
- val &= ~MVPP22_CTRL4_DP_CLK_SEL;
- writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
- }
-
- /* The port is connected to a copper PHY */
- val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
- val &= ~MVPP2_GMAC_PORT_TYPE_MASK;
- writel(val, port->base + MVPP2_GMAC_CTRL_0_REG);
-
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS |
- MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG |
- MVPP2_GMAC_AN_DUPLEX_EN;
- if (port->phy_interface == PHY_INTERFACE_MODE_SGMII)
- val |= MVPP2_GMAC_IN_BAND_AUTONEG;
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-}
-
-static void mvpp2_port_mii_gmac_configure(struct mvpp2_port *port)
-{
- u32 val;
-
- /* Force link down */
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
- val |= MVPP2_GMAC_FORCE_LINK_DOWN;
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-
- /* Set the GMAC in a reset state */
- val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
- val |= MVPP2_GMAC_PORT_RESET_MASK;
- writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
-
- /* Configure the PCS and in-band AN */
- val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
- if (port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
- val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
- } else if (phy_interface_mode_is_rgmii(port->phy_interface)) {
- val &= ~MVPP2_GMAC_PCS_ENABLE_MASK;
- }
- writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
-
- mvpp2_port_mii_gmac_configure_mode(port);
-
- /* Unset the GMAC reset state */
- val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
- val &= ~MVPP2_GMAC_PORT_RESET_MASK;
- writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
-
- /* Stop forcing link down */
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-}
-
-static void mvpp2_port_mii_xlg_configure(struct mvpp2_port *port)
-{
- u32 val;
-
- if (port->gop_id != 0)
- return;
-
- val = readl(port->base + MVPP22_XLG_CTRL0_REG);
- val |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
- writel(val, port->base + MVPP22_XLG_CTRL0_REG);
-
- val = readl(port->base + MVPP22_XLG_CTRL4_REG);
- val &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC;
- val |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC;
- writel(val, port->base + MVPP22_XLG_CTRL4_REG);
-}
-
-static void mvpp22_port_mii_set(struct mvpp2_port *port)
-{
- u32 val;
-
- /* Only GOP port 0 has an XLG MAC */
- if (port->gop_id == 0) {
- val = readl(port->base + MVPP22_XLG_CTRL3_REG);
- val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
-
- if (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
- port->phy_interface == PHY_INTERFACE_MODE_10GKR)
- val |= MVPP22_XLG_CTRL3_MACMODESELECT_10G;
- else
- val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
-
- writel(val, port->base + MVPP22_XLG_CTRL3_REG);
- }
-}
-
-static void mvpp2_port_mii_set(struct mvpp2_port *port)
-{
- if (port->priv->hw_version == MVPP22)
- mvpp22_port_mii_set(port);
-
- if (phy_interface_mode_is_rgmii(port->phy_interface) ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII)
- mvpp2_port_mii_gmac_configure(port);
- else if (port->phy_interface == PHY_INTERFACE_MODE_10GKR)
- mvpp2_port_mii_xlg_configure(port);
-}
-
-static void mvpp2_port_fc_adv_enable(struct mvpp2_port *port)
-{
- u32 val;
-
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val |= MVPP2_GMAC_FC_ADV_EN;
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-}
-
static void mvpp2_port_enable(struct mvpp2_port *port)
{
u32 val;
(port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
port->phy_interface == PHY_INTERFACE_MODE_10GKR)) {
val = readl(port->base + MVPP22_XLG_CTRL0_REG);
- val &= ~(MVPP22_XLG_CTRL0_PORT_EN |
- MVPP22_XLG_CTRL0_MAC_RESET_DIS);
+ val &= ~MVPP22_XLG_CTRL0_PORT_EN;
+ writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+
+ /* Disable & reset should be done separately */
+ val &= ~MVPP22_XLG_CTRL0_MAC_RESET_DIS;
writel(val, port->base + MVPP22_XLG_CTRL0_REG);
} else {
val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
}
/* Configure loopback port */
-static void mvpp2_port_loopback_set(struct mvpp2_port *port)
+static void mvpp2_port_loopback_set(struct mvpp2_port *port,
+ const struct phylink_link_state *state)
{
u32 val;
val = readl(port->base + MVPP2_GMAC_CTRL_1_REG);
- if (port->speed == 1000)
+ if (state->speed == 1000)
val |= MVPP2_GMAC_GMII_LB_EN_MASK;
else
val &= ~MVPP2_GMAC_GMII_LB_EN_MASK;
- if (port->phy_interface == PHY_INTERFACE_MODE_SGMII)
+ if (port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+ port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
+ port->phy_interface == PHY_INTERFACE_MODE_2500BASEX)
val |= MVPP2_GMAC_PCS_LB_EN_MASK;
else
val &= ~MVPP2_GMAC_PCS_LB_EN_MASK;
int tx_port_num, val, queue, ptxq, lrxq;
if (port->priv->hw_version == MVPP21) {
- /* Configure port to loopback if needed */
- if (port->flags & MVPP2_F_LOOPBACK)
- mvpp2_port_loopback_set(port);
-
/* Update TX FIFO MIN Threshold */
val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
MVPP2_AGGR_TXQ_UPDATE_REG, pending);
}
-
/* Check if there are enough free descriptors in aggregated txq.
* If not, update the number of occupied descriptors and repeat the check.
*
MVPP2_AGGR_TXQ_STATUS_REG(cpu));
aggr_txq->count = val & MVPP2_AGGR_TXQ_PENDING_MASK;
- }
-
- if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE)
- return -ENOMEM;
+ if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE)
+ return -ENOMEM;
+ }
return 0;
}
txq_pcpu->reserved_num += mvpp2_txq_alloc_reserved_desc(priv, txq, req);
- /* OK, the descriptor cound has been updated: check again. */
+ /* OK, the descriptor could have been updated: check again. */
if (txq_pcpu->reserved_num < num)
return -ENOMEM;
return 0;
/* Calculate base address in prefetch buffer. We reserve 16 descriptors
* for each existing TXQ.
* TCONTS for PON port must be continuous from 0 to MVPP2_MAX_TCONT
- * GBE ports assumed to be continious from 0 to MVPP2_MAX_PORTS
+ * GBE ports assumed to be continuous from 0 to MVPP2_MAX_PORTS
*/
desc_per_txq = 16;
desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) +
link = true;
}
} else if (phy_interface_mode_is_rgmii(port->phy_interface) ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
+ port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
+ port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
+ port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
val = readl(port->base + MVPP22_GMAC_INT_STAT);
if (val & MVPP22_GMAC_INT_STAT_LINK) {
event = true;
}
}
+ if (port->phylink) {
+ phylink_mac_change(port->phylink, link);
+ goto handled;
+ }
+
if (!netif_running(dev) || !event)
goto handled;
return IRQ_HANDLED;
}
-static void mvpp2_gmac_set_autoneg(struct mvpp2_port *port,
- struct phy_device *phydev)
-{
- u32 val;
-
- if (port->phy_interface != PHY_INTERFACE_MODE_RGMII &&
- port->phy_interface != PHY_INTERFACE_MODE_RGMII_ID &&
- port->phy_interface != PHY_INTERFACE_MODE_RGMII_RXID &&
- port->phy_interface != PHY_INTERFACE_MODE_RGMII_TXID &&
- port->phy_interface != PHY_INTERFACE_MODE_SGMII)
- return;
-
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val &= ~(MVPP2_GMAC_CONFIG_MII_SPEED |
- MVPP2_GMAC_CONFIG_GMII_SPEED |
- MVPP2_GMAC_CONFIG_FULL_DUPLEX |
- MVPP2_GMAC_AN_SPEED_EN |
- MVPP2_GMAC_AN_DUPLEX_EN);
-
- if (phydev->duplex)
- val |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
-
- if (phydev->speed == SPEED_1000)
- val |= MVPP2_GMAC_CONFIG_GMII_SPEED;
- else if (phydev->speed == SPEED_100)
- val |= MVPP2_GMAC_CONFIG_MII_SPEED;
-
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-}
-
-/* Adjust link */
-static void mvpp2_link_event(struct net_device *dev)
-{
- struct mvpp2_port *port = netdev_priv(dev);
- struct phy_device *phydev = dev->phydev;
- bool link_reconfigured = false;
- u32 val;
-
- if (phydev->link) {
- if (port->phy_interface != phydev->interface && port->comphy) {
- /* disable current port for reconfiguration */
- mvpp2_interrupts_disable(port);
- netif_carrier_off(port->dev);
- mvpp2_port_disable(port);
- phy_power_off(port->comphy);
-
- /* comphy reconfiguration */
- port->phy_interface = phydev->interface;
- mvpp22_comphy_init(port);
-
- /* gop/mac reconfiguration */
- mvpp22_gop_init(port);
- mvpp2_port_mii_set(port);
-
- link_reconfigured = true;
- }
-
- if ((port->speed != phydev->speed) ||
- (port->duplex != phydev->duplex)) {
- mvpp2_gmac_set_autoneg(port, phydev);
-
- port->duplex = phydev->duplex;
- port->speed = phydev->speed;
- }
- }
-
- if (phydev->link != port->link || link_reconfigured) {
- port->link = phydev->link;
-
- if (phydev->link) {
- if (port->phy_interface == PHY_INTERFACE_MODE_RGMII ||
- port->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
- port->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID ||
- port->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID ||
- port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
- val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- val |= (MVPP2_GMAC_FORCE_LINK_PASS |
- MVPP2_GMAC_FORCE_LINK_DOWN);
- writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
- }
-
- mvpp2_interrupts_enable(port);
- mvpp2_port_enable(port);
-
- mvpp2_egress_enable(port);
- mvpp2_ingress_enable(port);
- netif_carrier_on(dev);
- netif_tx_wake_all_queues(dev);
- } else {
- port->duplex = -1;
- port->speed = 0;
-
- netif_tx_stop_all_queues(dev);
- netif_carrier_off(dev);
- mvpp2_ingress_disable(port);
- mvpp2_egress_disable(port);
-
- mvpp2_port_disable(port);
- mvpp2_interrupts_disable(port);
- }
-
- phy_print_status(phydev);
- }
-}
-
static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
{
ktime_t interval;
{
u32 status = mvpp2_rxdesc_status_get(port, rx_desc);
size_t sz = mvpp2_rxdesc_size_get(port, rx_desc);
+ char *err_str = NULL;
switch (status & MVPP2_RXD_ERR_CODE_MASK) {
case MVPP2_RXD_ERR_CRC:
- netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n",
- status, sz);
+ err_str = "crc";
break;
case MVPP2_RXD_ERR_OVERRUN:
- netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n",
- status, sz);
+ err_str = "overrun";
break;
case MVPP2_RXD_ERR_RESOURCE:
- netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n",
- status, sz);
+ err_str = "resource";
break;
}
+ if (err_str && net_ratelimit())
+ netdev_err(port->dev,
+ "bad rx status %08x (%s error), size=%zu\n",
+ status, err_str, sz);
}
/* Handle RX checksum offload */
mvpp2_txdesc_size_set(port, tx_desc, frag->size);
buf_dma_addr = dma_map_single(port->dev->dev.parent, addr,
- frag->size,
- DMA_TO_DEVICE);
+ frag->size, DMA_TO_DEVICE);
if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) {
mvpp2_txq_desc_put(txq);
goto cleanup;
return rx_done;
}
-/* Set hw internals when starting port */
-static void mvpp2_start_dev(struct mvpp2_port *port)
+static void mvpp22_mode_reconfigure(struct mvpp2_port *port)
{
- struct net_device *ndev = port->dev;
- int i;
+ u32 ctrl3;
+
+ /* comphy reconfiguration */
+ mvpp22_comphy_init(port);
+
+ /* gop reconfiguration */
+ mvpp22_gop_init(port);
+
+ /* Only GOP port 0 has an XLG MAC */
+ if (port->gop_id == 0) {
+ ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG);
+ ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
+
+ if (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
+ port->phy_interface == PHY_INTERFACE_MODE_10GKR)
+ ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G;
+ else
+ ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
+
+ writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG);
+ }
if (port->gop_id == 0 &&
(port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
mvpp2_xlg_max_rx_size_set(port);
else
mvpp2_gmac_max_rx_size_set(port);
+}
+
+/* Set hw internals when starting port */
+static void mvpp2_start_dev(struct mvpp2_port *port)
+{
+ int i;
mvpp2_txp_max_tx_size_set(port);
/* Enable interrupts on all CPUs */
mvpp2_interrupts_enable(port);
- if (port->priv->hw_version == MVPP22) {
- mvpp22_comphy_init(port);
- mvpp22_gop_init(port);
+ if (port->priv->hw_version == MVPP22)
+ mvpp22_mode_reconfigure(port);
+
+ if (port->phylink) {
+ phylink_start(port->phylink);
+ } else {
+ /* Phylink isn't used as of now for ACPI, so the MAC has to be
+ * configured manually when the interface is started. This will
+ * be removed as soon as the phylink ACPI support lands in.
+ */
+ struct phylink_link_state state = {
+ .interface = port->phy_interface,
+ .link = 1,
+ };
+ mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state);
}
- mvpp2_port_mii_set(port);
- mvpp2_port_enable(port);
- if (ndev->phydev)
- phy_start(ndev->phydev);
netif_tx_start_all_queues(port->dev);
}
/* Set hw internals when stopping port */
static void mvpp2_stop_dev(struct mvpp2_port *port)
{
- struct net_device *ndev = port->dev;
int i;
- /* Stop new packets from arriving to RXQs */
- mvpp2_ingress_disable(port);
-
- mdelay(10);
-
/* Disable interrupts on all CPUs */
mvpp2_interrupts_disable(port);
for (i = 0; i < port->nqvecs; i++)
napi_disable(&port->qvecs[i].napi);
- netif_carrier_off(port->dev);
- netif_tx_stop_all_queues(port->dev);
-
- mvpp2_egress_disable(port);
- mvpp2_port_disable(port);
- if (ndev->phydev)
- phy_stop(ndev->phydev);
+ if (port->phylink)
+ phylink_stop(port->phylink);
phy_power_off(port->comphy);
}
addr[5] = (mac_addr_l >> MVPP2_GMAC_SA_LOW_OFFS) & 0xFF;
}
-static int mvpp2_phy_connect(struct mvpp2_port *port)
-{
- struct phy_device *phy_dev;
-
- /* No PHY is attached */
- if (!port->phy_node)
- return 0;
-
- phy_dev = of_phy_connect(port->dev, port->phy_node, mvpp2_link_event, 0,
- port->phy_interface);
- if (!phy_dev) {
- netdev_err(port->dev, "cannot connect to phy\n");
- return -ENODEV;
- }
- phy_dev->supported &= PHY_GBIT_FEATURES;
- phy_dev->advertising = phy_dev->supported;
-
- port->link = 0;
- port->duplex = 0;
- port->speed = 0;
-
- return 0;
-}
-
-static void mvpp2_phy_disconnect(struct mvpp2_port *port)
-{
- struct net_device *ndev = port->dev;
-
- if (!ndev->phydev)
- return;
-
- phy_disconnect(ndev->phydev);
-}
-
static int mvpp2_irqs_init(struct mvpp2_port *port)
{
int err, i;
struct mvpp2 *priv = port->priv;
unsigned char mac_bcast[ETH_ALEN] = {
0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+ bool valid = false;
int err;
err = mvpp2_prs_mac_da_accept(port, mac_bcast, true);
goto err_cleanup_txqs;
}
- if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq) {
+ /* Phylink isn't supported yet in ACPI mode */
+ if (port->of_node) {
+ err = phylink_of_phy_connect(port->phylink, port->of_node, 0);
+ if (err) {
+ netdev_err(port->dev, "could not attach PHY (%d)\n",
+ err);
+ goto err_free_irq;
+ }
+
+ valid = true;
+ }
+
+ if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) {
err = request_irq(port->link_irq, mvpp2_link_status_isr, 0,
dev->name, port);
if (err) {
}
mvpp22_gop_setup_irq(port);
- }
- /* In default link is down */
- netif_carrier_off(port->dev);
+ /* In default link is down */
+ netif_carrier_off(port->dev);
- err = mvpp2_phy_connect(port);
- if (err < 0)
- goto err_free_link_irq;
+ valid = true;
+ } else {
+ port->link_irq = 0;
+ }
+
+ if (!valid) {
+ netdev_err(port->dev,
+ "invalid configuration: no dt or link IRQ");
+ goto err_free_irq;
+ }
/* Unmask interrupts on all CPUs */
on_each_cpu(mvpp2_interrupts_unmask, port, 1);
return 0;
-err_free_link_irq:
- if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq)
- free_irq(port->link_irq, port);
err_free_irq:
mvpp2_irqs_deinit(port);
err_cleanup_txqs:
{
struct mvpp2_port *port = netdev_priv(dev);
struct mvpp2_port_pcpu *port_pcpu;
- struct mvpp2 *priv = port->priv;
int cpu;
mvpp2_stop_dev(port);
- mvpp2_phy_disconnect(port);
/* Mask interrupts on all CPUs */
on_each_cpu(mvpp2_interrupts_mask, port, 1);
mvpp2_shared_interrupt_mask_unmask(port, true);
- if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq)
+ if (port->phylink)
+ phylink_disconnect_phy(port->phylink);
+ if (port->link_irq)
free_irq(port->link_irq, port);
mvpp2_irqs_deinit(port);
static int mvpp2_set_mac_address(struct net_device *dev, void *p)
{
- struct mvpp2_port *port = netdev_priv(dev);
const struct sockaddr *addr = p;
int err;
- if (!is_valid_ether_addr(addr->sa_data)) {
- err = -EADDRNOTAVAIL;
- goto log_error;
- }
-
- if (!netif_running(dev)) {
- err = mvpp2_prs_update_mac_da(dev, addr->sa_data);
- if (!err)
- return 0;
- /* Reconfigure parser to accept the original MAC address */
- err = mvpp2_prs_update_mac_da(dev, dev->dev_addr);
- if (err)
- goto log_error;
- }
-
- mvpp2_stop_dev(port);
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
err = mvpp2_prs_update_mac_da(dev, addr->sa_data);
- if (!err)
- goto out_start;
-
- /* Reconfigure parser accept the original MAC address */
- err = mvpp2_prs_update_mac_da(dev, dev->dev_addr);
- if (err)
- goto log_error;
-out_start:
- mvpp2_start_dev(port);
- mvpp2_egress_enable(port);
- mvpp2_ingress_enable(port);
- return 0;
-log_error:
- netdev_err(dev, "failed to change MAC address\n");
+ if (err) {
+ /* Reconfigure parser accept the original MAC address */
+ mvpp2_prs_update_mac_da(dev, dev->dev_addr);
+ netdev_err(dev, "failed to change MAC address\n");
+ }
return err;
}
static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
- int ret;
+ struct mvpp2_port *port = netdev_priv(dev);
- if (!dev->phydev)
+ if (!port->phylink)
return -ENOTSUPP;
- ret = phy_mii_ioctl(dev->phydev, ifr, cmd);
- if (!ret)
- mvpp2_link_event(dev);
-
- return ret;
+ return phylink_mii_ioctl(port->phylink, ifr, cmd);
}
static int mvpp2_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
/* Ethtool methods */
+static int mvpp2_ethtool_nway_reset(struct net_device *dev)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!port->phylink)
+ return -ENOTSUPP;
+
+ return phylink_ethtool_nway_reset(port->phylink);
+}
+
/* Set interrupt coalescing for ethtools */
static int mvpp2_ethtool_set_coalesce(struct net_device *dev,
struct ethtool_coalesce *c)
return err;
}
+static void mvpp2_ethtool_get_pause_param(struct net_device *dev,
+ struct ethtool_pauseparam *pause)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!port->phylink)
+ return;
+
+ phylink_ethtool_get_pauseparam(port->phylink, pause);
+}
+
+static int mvpp2_ethtool_set_pause_param(struct net_device *dev,
+ struct ethtool_pauseparam *pause)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!port->phylink)
+ return -ENOTSUPP;
+
+ return phylink_ethtool_set_pauseparam(port->phylink, pause);
+}
+
+static int mvpp2_ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!port->phylink)
+ return -ENOTSUPP;
+
+ return phylink_ethtool_ksettings_get(port->phylink, cmd);
+}
+
+static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (!port->phylink)
+ return -ENOTSUPP;
+
+ return phylink_ethtool_ksettings_set(port->phylink, cmd);
+}
+
/* Device ops */
static const struct net_device_ops mvpp2_netdev_ops = {
};
static const struct ethtool_ops mvpp2_eth_tool_ops = {
- .nway_reset = phy_ethtool_nway_reset,
- .get_link = ethtool_op_get_link,
- .set_coalesce = mvpp2_ethtool_set_coalesce,
- .get_coalesce = mvpp2_ethtool_get_coalesce,
- .get_drvinfo = mvpp2_ethtool_get_drvinfo,
- .get_ringparam = mvpp2_ethtool_get_ringparam,
- .set_ringparam = mvpp2_ethtool_set_ringparam,
- .get_strings = mvpp2_ethtool_get_strings,
- .get_ethtool_stats = mvpp2_ethtool_get_stats,
- .get_sset_count = mvpp2_ethtool_get_sset_count,
- .get_link_ksettings = phy_ethtool_get_link_ksettings,
- .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .nway_reset = mvpp2_ethtool_nway_reset,
+ .get_link = ethtool_op_get_link,
+ .set_coalesce = mvpp2_ethtool_set_coalesce,
+ .get_coalesce = mvpp2_ethtool_get_coalesce,
+ .get_drvinfo = mvpp2_ethtool_get_drvinfo,
+ .get_ringparam = mvpp2_ethtool_get_ringparam,
+ .set_ringparam = mvpp2_ethtool_set_ringparam,
+ .get_strings = mvpp2_ethtool_get_strings,
+ .get_ethtool_stats = mvpp2_ethtool_get_stats,
+ .get_sset_count = mvpp2_ethtool_get_sset_count,
+ .get_pauseparam = mvpp2_ethtool_get_pause_param,
+ .set_pauseparam = mvpp2_ethtool_set_pause_param,
+ .get_link_ksettings = mvpp2_ethtool_get_link_ksettings,
+ .set_link_ksettings = mvpp2_ethtool_set_link_ksettings,
};
/* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
eth_hw_addr_random(dev);
}
+static void mvpp2_phylink_validate(struct net_device *dev,
+ unsigned long *supported,
+ struct phylink_link_state *state)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+ phylink_set(mask, Autoneg);
+ phylink_set_port_modes(mask);
+ phylink_set(mask, Pause);
+ phylink_set(mask, Asym_Pause);
+
+ switch (state->interface) {
+ case PHY_INTERFACE_MODE_10GKR:
+ phylink_set(mask, 10000baseCR_Full);
+ phylink_set(mask, 10000baseSR_Full);
+ phylink_set(mask, 10000baseLR_Full);
+ phylink_set(mask, 10000baseLRM_Full);
+ phylink_set(mask, 10000baseER_Full);
+ phylink_set(mask, 10000baseKR_Full);
+ /* Fall-through */
+ default:
+ phylink_set(mask, 10baseT_Half);
+ phylink_set(mask, 10baseT_Full);
+ phylink_set(mask, 100baseT_Half);
+ phylink_set(mask, 100baseT_Full);
+ phylink_set(mask, 10000baseT_Full);
+ /* Fall-through */
+ case PHY_INTERFACE_MODE_1000BASEX:
+ case PHY_INTERFACE_MODE_2500BASEX:
+ phylink_set(mask, 1000baseT_Full);
+ phylink_set(mask, 1000baseX_Full);
+ phylink_set(mask, 2500baseX_Full);
+ }
+
+ bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
+ bitmap_and(state->advertising, state->advertising, mask,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static void mvpp22_xlg_link_state(struct mvpp2_port *port,
+ struct phylink_link_state *state)
+{
+ u32 val;
+
+ state->speed = SPEED_10000;
+ state->duplex = 1;
+ state->an_complete = 1;
+
+ val = readl(port->base + MVPP22_XLG_STATUS);
+ state->link = !!(val & MVPP22_XLG_STATUS_LINK_UP);
+
+ state->pause = 0;
+ val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+ if (val & MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN)
+ state->pause |= MLO_PAUSE_TX;
+ if (val & MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN)
+ state->pause |= MLO_PAUSE_RX;
+}
+
+static void mvpp2_gmac_link_state(struct mvpp2_port *port,
+ struct phylink_link_state *state)
+{
+ u32 val;
+
+ val = readl(port->base + MVPP2_GMAC_STATUS0);
+
+ state->an_complete = !!(val & MVPP2_GMAC_STATUS0_AN_COMPLETE);
+ state->link = !!(val & MVPP2_GMAC_STATUS0_LINK_UP);
+ state->duplex = !!(val & MVPP2_GMAC_STATUS0_FULL_DUPLEX);
+
+ switch (port->phy_interface) {
+ case PHY_INTERFACE_MODE_1000BASEX:
+ state->speed = SPEED_1000;
+ break;
+ case PHY_INTERFACE_MODE_2500BASEX:
+ state->speed = SPEED_2500;
+ break;
+ default:
+ if (val & MVPP2_GMAC_STATUS0_GMII_SPEED)
+ state->speed = SPEED_1000;
+ else if (val & MVPP2_GMAC_STATUS0_MII_SPEED)
+ state->speed = SPEED_100;
+ else
+ state->speed = SPEED_10;
+ }
+
+ state->pause = 0;
+ if (val & MVPP2_GMAC_STATUS0_RX_PAUSE)
+ state->pause |= MLO_PAUSE_RX;
+ if (val & MVPP2_GMAC_STATUS0_TX_PAUSE)
+ state->pause |= MLO_PAUSE_TX;
+}
+
+static int mvpp2_phylink_mac_link_state(struct net_device *dev,
+ struct phylink_link_state *state)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ if (port->priv->hw_version == MVPP22 && port->gop_id == 0) {
+ u32 mode = readl(port->base + MVPP22_XLG_CTRL3_REG);
+ mode &= MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
+
+ if (mode == MVPP22_XLG_CTRL3_MACMODESELECT_10G) {
+ mvpp22_xlg_link_state(port, state);
+ return 1;
+ }
+ }
+
+ mvpp2_gmac_link_state(port, state);
+ return 1;
+}
+
+static void mvpp2_mac_an_restart(struct net_device *dev)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+ u32 val;
+
+ if (port->phy_interface != PHY_INTERFACE_MODE_SGMII)
+ return;
+
+ val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ /* The RESTART_AN bit is cleared by the h/w after restarting the AN
+ * process.
+ */
+ val |= MVPP2_GMAC_IN_BAND_RESTART_AN | MVPP2_GMAC_IN_BAND_AUTONEG;
+ writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+}
+
+static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ u32 ctrl0, ctrl4;
+
+ ctrl0 = readl(port->base + MVPP22_XLG_CTRL0_REG);
+ ctrl4 = readl(port->base + MVPP22_XLG_CTRL4_REG);
+
+ if (state->pause & MLO_PAUSE_TX)
+ ctrl0 |= MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN;
+ if (state->pause & MLO_PAUSE_RX)
+ ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
+
+ ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC;
+ ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC |
+ MVPP22_XLG_CTRL4_EN_IDLE_CHECK;
+
+ writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
+ writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);
+}
+
+static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ u32 an, ctrl0, ctrl2, ctrl4;
+
+ an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
+ ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
+ ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
+
+ /* Force link down */
+ an &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+ an |= MVPP2_GMAC_FORCE_LINK_DOWN;
+ writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+
+ /* Set the GMAC in a reset state */
+ ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK;
+ writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+
+ an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED |
+ MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN |
+ MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG |
+ MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN |
+ MVPP2_GMAC_FORCE_LINK_DOWN);
+ ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK;
+ ctrl2 &= ~(MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK);
+
+ if (state->interface == PHY_INTERFACE_MODE_1000BASEX ||
+ state->interface == PHY_INTERFACE_MODE_2500BASEX) {
+ /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can
+ * they negotiate duplex: they are always operating with a fixed
+ * speed of 1000/2500Mbps in full duplex, so force 1000/2500
+ * speed and full duplex here.
+ */
+ ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK;
+ an |= MVPP2_GMAC_CONFIG_GMII_SPEED |
+ MVPP2_GMAC_CONFIG_FULL_DUPLEX;
+ } else if (!phy_interface_mode_is_rgmii(state->interface)) {
+ an |= MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG;
+ }
+
+ if (state->duplex)
+ an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
+ if (phylink_test(state->advertising, Pause))
+ an |= MVPP2_GMAC_FC_ADV_EN;
+ if (phylink_test(state->advertising, Asym_Pause))
+ an |= MVPP2_GMAC_FC_ADV_ASM_EN;
+
+ if (state->interface == PHY_INTERFACE_MODE_SGMII ||
+ state->interface == PHY_INTERFACE_MODE_1000BASEX ||
+ state->interface == PHY_INTERFACE_MODE_2500BASEX) {
+ an |= MVPP2_GMAC_IN_BAND_AUTONEG;
+ ctrl2 |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
+
+ ctrl4 &= ~(MVPP22_CTRL4_EXT_PIN_GMII_SEL |
+ MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN);
+ ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
+ MVPP22_CTRL4_DP_CLK_SEL |
+ MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+
+ if (state->pause & MLO_PAUSE_TX)
+ ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
+ if (state->pause & MLO_PAUSE_RX)
+ ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
+ } else if (phy_interface_mode_is_rgmii(state->interface)) {
+ an |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS;
+
+ if (state->speed == SPEED_1000)
+ an |= MVPP2_GMAC_CONFIG_GMII_SPEED;
+ else if (state->speed == SPEED_100)
+ an |= MVPP2_GMAC_CONFIG_MII_SPEED;
+
+ ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL;
+ ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
+ MVPP22_CTRL4_SYNC_BYPASS_DIS |
+ MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+ }
+
+ writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG);
+ writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+ writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG);
+ writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+}
+
+static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+
+ /* Check for invalid configuration */
+ if (state->interface == PHY_INTERFACE_MODE_10GKR && port->gop_id != 0) {
+ netdev_err(dev, "Invalid mode on %s\n", dev->name);
+ return;
+ }
+
+ netif_tx_stop_all_queues(port->dev);
+ if (!port->has_phy)
+ netif_carrier_off(port->dev);
+
+ /* Make sure the port is disabled when reconfiguring the mode */
+ mvpp2_port_disable(port);
+
+ if (port->priv->hw_version == MVPP22 &&
+ port->phy_interface != state->interface) {
+ port->phy_interface = state->interface;
+
+ /* Reconfigure the serdes lanes */
+ phy_power_off(port->comphy);
+ mvpp22_mode_reconfigure(port);
+ }
+
+ /* mac (re)configuration */
+ if (state->interface == PHY_INTERFACE_MODE_10GKR)
+ mvpp2_xlg_config(port, mode, state);
+ else if (phy_interface_mode_is_rgmii(state->interface) ||
+ state->interface == PHY_INTERFACE_MODE_SGMII ||
+ state->interface == PHY_INTERFACE_MODE_1000BASEX ||
+ state->interface == PHY_INTERFACE_MODE_2500BASEX)
+ mvpp2_gmac_config(port, mode, state);
+
+ if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK)
+ mvpp2_port_loopback_set(port, state);
+
+ /* If the port already was up, make sure it's still in the same state */
+ if (state->link || !port->has_phy) {
+ mvpp2_port_enable(port);
+
+ mvpp2_egress_enable(port);
+ mvpp2_ingress_enable(port);
+ if (!port->has_phy)
+ netif_carrier_on(dev);
+ netif_tx_wake_all_queues(dev);
+ }
+}
+
+static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
+ phy_interface_t interface, struct phy_device *phy)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+ u32 val;
+
+ if (!phylink_autoneg_inband(mode) &&
+ interface != PHY_INTERFACE_MODE_10GKR) {
+ val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
+ if (phy_interface_mode_is_rgmii(interface))
+ val |= MVPP2_GMAC_FORCE_LINK_PASS;
+ writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ }
+
+ mvpp2_port_enable(port);
+
+ mvpp2_egress_enable(port);
+ mvpp2_ingress_enable(port);
+ netif_tx_wake_all_queues(dev);
+}
+
+static void mvpp2_mac_link_down(struct net_device *dev, unsigned int mode,
+ phy_interface_t interface)
+{
+ struct mvpp2_port *port = netdev_priv(dev);
+ u32 val;
+
+ if (!phylink_autoneg_inband(mode) &&
+ interface != PHY_INTERFACE_MODE_10GKR) {
+ val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+ val |= MVPP2_GMAC_FORCE_LINK_DOWN;
+ writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ }
+
+ netif_tx_stop_all_queues(dev);
+ mvpp2_egress_disable(port);
+ mvpp2_ingress_disable(port);
+
+ /* When using link interrupts to notify phylink of a MAC state change,
+ * we do not want the port to be disabled (we want to receive further
+ * interrupts, to be notified when the port will have a link later).
+ */
+ if (!port->has_phy)
+ return;
+
+ mvpp2_port_disable(port);
+}
+
+static const struct phylink_mac_ops mvpp2_phylink_ops = {
+ .validate = mvpp2_phylink_validate,
+ .mac_link_state = mvpp2_phylink_mac_link_state,
+ .mac_an_restart = mvpp2_mac_an_restart,
+ .mac_config = mvpp2_mac_config,
+ .mac_link_up = mvpp2_mac_link_up,
+ .mac_link_down = mvpp2_mac_link_down,
+};
+
/* Ports initialization */
static int mvpp2_port_probe(struct platform_device *pdev,
struct fwnode_handle *port_fwnode,
struct mvpp2 *priv)
{
- struct device_node *phy_node;
struct phy *comphy = NULL;
struct mvpp2_port *port;
struct mvpp2_port_pcpu *port_pcpu;
struct device_node *port_node = to_of_node(port_fwnode);
struct net_device *dev;
struct resource *res;
+ struct phylink *phylink;
char *mac_from = "";
unsigned int ntxqs, nrxqs;
bool has_tx_irqs;
if (!dev)
return -ENOMEM;
- if (port_node)
- phy_node = of_parse_phandle(port_node, "phy", 0);
- else
- phy_node = NULL;
-
phy_mode = fwnode_get_phy_mode(port_fwnode);
if (phy_mode < 0) {
dev_err(&pdev->dev, "incorrect phy mode\n");
port = netdev_priv(dev);
port->dev = dev;
port->fwnode = port_fwnode;
+ port->has_phy = !!of_find_property(port_node, "phy", NULL);
port->ntxqs = ntxqs;
port->nrxqs = nrxqs;
port->priv = priv;
else
port->first_rxq = port->id * priv->max_port_rxqs;
- port->phy_node = phy_node;
+ port->of_node = port_node;
port->phy_interface = phy_mode;
port->comphy = comphy;
mvpp2_port_periodic_xon_disable(port);
- if (priv->hw_version == MVPP21)
- mvpp2_port_fc_adv_enable(port);
-
mvpp2_port_reset(port);
port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
/* 9704 == 9728 - 20 and rounding to 8 */
dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE;
+ /* Phylink isn't used w/ ACPI as of now */
+ if (port_node) {
+ phylink = phylink_create(dev, port_fwnode, phy_mode,
+ &mvpp2_phylink_ops);
+ if (IS_ERR(phylink)) {
+ err = PTR_ERR(phylink);
+ goto err_free_port_pcpu;
+ }
+ port->phylink = phylink;
+ } else {
+ port->phylink = NULL;
+ }
+
err = register_netdev(dev);
if (err < 0) {
dev_err(&pdev->dev, "failed to register netdev\n");
- goto err_free_port_pcpu;
+ goto err_phylink;
}
netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
return 0;
+err_phylink:
+ if (port->phylink)
+ phylink_destroy(port->phylink);
err_free_port_pcpu:
free_percpu(port->pcpu);
err_free_txq_pcpu:
err_deinit_qvecs:
mvpp2_queue_vectors_deinit(port);
err_free_netdev:
- of_node_put(phy_node);
free_netdev(dev);
return err;
}
int i;
unregister_netdev(port->dev);
- of_node_put(port->phy_node);
+ if (port->phylink)
+ phylink_destroy(port->phylink);
free_percpu(port->pcpu);
free_percpu(port->stats);
for (i = 0; i < port->ntxqs; i++)
err = clk_prepare_enable(priv->mg_clk);
if (err < 0)
goto err_gop_clk;
+
+ priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk");
+ if (IS_ERR(priv->mg_core_clk)) {
+ priv->mg_core_clk = NULL;
+ } else {
+ err = clk_prepare_enable(priv->mg_core_clk);
+ if (err < 0)
+ goto err_mg_clk;
+ }
}
priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
if (IS_ERR(priv->axi_clk)) {
err = PTR_ERR(priv->axi_clk);
if (err == -EPROBE_DEFER)
- goto err_gop_clk;
+ goto err_mg_core_clk;
priv->axi_clk = NULL;
} else {
err = clk_prepare_enable(priv->axi_clk);
if (err < 0)
- goto err_gop_clk;
+ goto err_mg_core_clk;
}
/* Get system's tclk rate */
if (priv->hw_version == MVPP22) {
err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
if (err)
- goto err_mg_clk;
+ goto err_axi_clk;
/* Sadly, the BM pools all share the same register to
* store the high 32 bits of their address. So they
* must all have the same high 32 bits, which forces
*/
err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
if (err)
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Initialize network controller */
err = mvpp2_init(pdev, priv);
if (err < 0) {
dev_err(&pdev->dev, "failed to initialize controller\n");
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Initialize ports */
if (priv->port_count == 0) {
dev_err(&pdev->dev, "no ports enabled\n");
err = -ENODEV;
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Statistics must be gathered regularly because some of them (like
mvpp2_port_remove(priv->port_list[i]);
i++;
}
-err_mg_clk:
+err_axi_clk:
clk_disable_unprepare(priv->axi_clk);
+
+err_mg_core_clk:
+ if (priv->hw_version == MVPP22)
+ clk_disable_unprepare(priv->mg_core_clk);
+err_mg_clk:
if (priv->hw_version == MVPP22)
clk_disable_unprepare(priv->mg_clk);
err_gop_clk:
return 0;
clk_disable_unprepare(priv->axi_clk);
+ clk_disable_unprepare(priv->mg_core_clk);
clk_disable_unprepare(priv->mg_clk);
clk_disable_unprepare(priv->pp_clk);
clk_disable_unprepare(priv->gop_clk);
if (!coal->tx_max_coalesced_frames_irq)
return -EINVAL;
+ if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) {
+ netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n",
+ __func__, MLX4_EN_MAX_COAL_TIME);
+ return -ERANGE;
+ }
+
+ if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS ||
+ coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) {
+ netdev_info(dev, "%s: maximum coalesced frames supported is %d\n",
+ __func__, MLX4_EN_MAX_COAL_PKTS);
+ return -ERANGE;
+ }
+
priv->rx_frames = (coal->rx_max_coalesced_frames ==
MLX4_EN_AUTO_CONF) ?
MLX4_EN_RX_COAL_TARGET :
MAX_TX_RINGS, GFP_KERNEL);
if (!priv->tx_ring[t]) {
err = -ENOMEM;
- goto err_free_tx;
+ goto out;
}
priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
MAX_TX_RINGS, GFP_KERNEL);
if (!priv->tx_cq[t]) {
- kfree(priv->tx_ring[t]);
err = -ENOMEM;
goto out;
}
return 0;
-err_free_tx:
- while (t--) {
- kfree(priv->tx_ring[t]);
- kfree(priv->tx_cq[t]);
- }
out:
mlx4_en_destroy_netdev(dev);
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
-/* In IPv6 packets, besides subtracting the pseudo header checksum,
- * we also compute/add the IP header checksum which
- * is not added by the HW.
+/* In IPv6 packets, hw_checksum lacks 6 bytes from IPv6 header:
+ * 4 first bytes : priority, version, flow_lbl
+ * and 2 additional bytes : nexthdr, hop_limit.
*/
static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
struct ipv6hdr *ipv6h)
{
__u8 nexthdr = ipv6h->nexthdr;
- __wsum csum_pseudo_hdr = 0;
+ __wsum temp;
if (unlikely(nexthdr == IPPROTO_FRAGMENT ||
nexthdr == IPPROTO_HOPOPTS ||
nexthdr == IPPROTO_SCTP))
return -1;
- hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr));
- csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
- sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
- csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len);
- csum_pseudo_hdr = csum_add(csum_pseudo_hdr,
- (__force __wsum)htons(nexthdr));
-
- skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr);
- skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0));
+ /* priority, version, flow_lbl */
+ temp = csum_add(hw_checksum, *(__wsum *)ipv6h);
+ /* nexthdr and hop_limit */
+ skb->csum = csum_add(temp, (__force __wsum)*(__be16 *)&ipv6h->nexthdr);
return 0;
}
#endif
u16 rings_p_up = priv->num_tx_rings_p_up;
if (netdev_get_num_tc(dev))
- return skb_tx_hash(dev, skb);
+ return fallback(dev, skb);
return fallback(dev, skb) % rings_p_up;
}
[36] = "QinQ VST mode support",
[37] = "sl to vl mapping table change event support",
[38] = "user MAC support",
+ [39] = "Report driver version to FW support",
};
int i;
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP;
if (field32 & (1 << 7))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT;
+ if (field32 & (1 << 8))
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW;
MLX4_GET(field32, outbox, QUERY_DEV_CAP_DIAG_RPRT_PER_PORT);
if (field32 & (1 << 17))
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT;
#define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18)
#define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b)
#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6
+#define INIT_HCA_DRIVER_VERSION_OFFSET 0x140
+#define INIT_HCA_DRIVER_VERSION_SZ 0x40
#define INIT_HCA_FS_PARAM_OFFSET 0x1d0
#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00)
#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12)
if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT)
*(inbox + INIT_HCA_RECOVERABLE_ERROR_EVENT_OFFSET / 4) |= cpu_to_be32(1 << 31);
+ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW) {
+ u8 *dst = (u8 *)(inbox + INIT_HCA_DRIVER_VERSION_OFFSET / 4);
+
+ strncpy(dst, DRV_NAME_FOR_FW, INIT_HCA_DRIVER_VERSION_SZ - 1);
+ mlx4_dbg(dev, "Reporting Driver Version to FW: %s\n", dst);
+ }
+
/* QPC/EEC/CQC/EQC/RDMARC attributes */
MLX4_PUT(inbox, param->qpc_base, INIT_HCA_QPC_BASE_OFFSET);
static int msi_x = 1;
module_param(msi_x, int, 0444);
-MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");
+MODULE_PARM_DESC(msi_x, "0 - don't use MSI-X, 1 - use MSI-X, >1 - limit number of MSI-X irqs to msi_x");
#else /* CONFIG_PCI_MSI */
ret = mlx4_unbond_fs_rules(dev);
if (ret)
- mlx4_warn(dev, "multifunction unbond for flow rules failedi (%d)\n", ret);
+ mlx4_warn(dev, "multifunction unbond for flow rules failed (%d)\n", ret);
ret1 = mlx4_unbond_mac_table(dev);
if (ret1) {
mlx4_warn(dev, "multifunction unbond for MAC table failed (%d)\n", ret1);
dev->caps.num_eqs - dev->caps.reserved_eqs,
MAX_MSIX);
+ if (msi_x > 1)
+ nreq = min_t(int, nreq, msi_x);
+
entries = kcalloc(nreq, sizeof(*entries), GFP_KERNEL);
if (!entries)
goto no_msi;
mlx4_err(dev, "Failed to create file for port %d\n", port);
devlink_port_unregister(&info->devlink_port);
info->port = -1;
+ return err;
}
sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
&info->port_attr);
devlink_port_unregister(&info->devlink_port);
info->port = -1;
+ return err;
}
- return err;
+ return 0;
}
static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
.resume = mlx4_pci_resume,
};
+static int mlx4_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+ struct mlx4_dev *dev = persist->dev;
+
+ mlx4_err(dev, "suspend was called\n");
+ mutex_lock(&persist->interface_state_mutex);
+ if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+ mlx4_unload_one(pdev);
+ mutex_unlock(&persist->interface_state_mutex);
+
+ return 0;
+}
+
+static int mlx4_resume(struct pci_dev *pdev)
+{
+ struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+ struct mlx4_dev *dev = persist->dev;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+ int total_vfs;
+ int ret = 0;
+
+ mlx4_err(dev, "resume was called\n");
+ total_vfs = dev->persist->num_vfs;
+ memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
+
+ mutex_lock(&persist->interface_state_mutex);
+ if (!(persist->interface_state & MLX4_INTERFACE_STATE_UP)) {
+ ret = mlx4_load_one(pdev, priv->pci_dev_data, total_vfs,
+ nvfs, priv, 1);
+ if (!ret) {
+ ret = restore_current_port_types(dev,
+ dev->persist->curr_port_type,
+ dev->persist->curr_port_poss_type);
+ if (ret)
+ mlx4_err(dev, "resume: could not restore original port types (%d)\n", ret);
+ }
+ }
+ mutex_unlock(&persist->interface_state_mutex);
+
+ return ret;
+}
+
static struct pci_driver mlx4_driver = {
.name = DRV_NAME,
.id_table = mlx4_pci_table,
.probe = mlx4_init_one,
.shutdown = mlx4_shutdown,
.remove = mlx4_remove_one,
+ .suspend = mlx4_suspend,
+ .resume = mlx4_resume,
.err_handler = &mlx4_err_handler,
};
static int __init mlx4_verify_params(void)
{
+ if (msi_x < 0) {
+ pr_warn("mlx4_core: bad msi_x: %d\n", msi_x);
+ return -1;
+ }
+
if ((log_num_mac < 0) || (log_num_mac > 7)) {
pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac);
return -1;
#include "fw_qos.h"
#define DRV_NAME "mlx4_core"
-#define PFX DRV_NAME ": "
#define DRV_VERSION "4.0-0"
+#define DRV_NAME_FOR_FW "Linux," DRV_NAME "," DRV_VERSION
#define MLX4_FS_UDP_UC_EN (1 << 1)
#define MLX4_FS_TCP_UC_EN (1 << 2)
#define MLX4_EN_TX_COAL_PKTS 16
#define MLX4_EN_TX_COAL_TIME 0x10
+#define MLX4_EN_MAX_COAL_PKTS U16_MAX
+#define MLX4_EN_MAX_COAL_TIME U16_MAX
+
#define MLX4_EN_RX_RATE_LOW 400000
#define MLX4_EN_RX_COAL_TIME_LOW 0
#define MLX4_EN_RX_RATE_HIGH 450000
u16 rx_usecs_low;
u32 pkt_rate_high;
u16 rx_usecs_high;
- u16 sample_interval;
- u16 adaptive_rx_coal;
+ u32 sample_interval;
+ u32 adaptive_rx_coal;
u32 msg_enable;
u32 loopback_ok;
u32 validate_loopback;
Build support for IPsec cryptography-offload accelaration in the NIC.
Note: Support for hardware with this capability needs to be selected
for this option to become available.
+
+config MLX5_EN_TLS
+ bool "TLS cryptography-offload accelaration"
+ depends on MLX5_CORE_EN
+ depends on TLS_DEVICE
+ depends on MLX5_ACCEL
+ default n
+ ---help---
+ Build support for TLS cryptography-offload accelaration in the NIC.
+ Note: Support for hardware with this capability needs to be selected
+ for this option to become available.
fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
diag/fs_tracepoint.o
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o
+mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
- fpga/ipsec.o
+ fpga/ipsec.o fpga/tls.o
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
en_accel/ipsec_stats.o
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
+
CFLAGS_tracepoint.o := -I$(src)
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/mlx5/device.h>
+
+#include "accel/tls.h"
+#include "mlx5_core.h"
+#include "fpga/tls.h"
+
+int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid)
+{
+ return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info,
+ start_offload_tcp_sn, p_swid);
+}
+
+void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid)
+{
+ mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL);
+}
+
+bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
+{
+ return mlx5_fpga_is_tls_device(mdev);
+}
+
+u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev)
+{
+ return mlx5_fpga_tls_device_caps(mdev);
+}
+
+int mlx5_accel_tls_init(struct mlx5_core_dev *mdev)
+{
+ return mlx5_fpga_tls_init(mdev);
+}
+
+void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev)
+{
+ mlx5_fpga_tls_cleanup(mdev);
+}
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef __MLX5_ACCEL_TLS_H__
+#define __MLX5_ACCEL_TLS_H__
+
+#include <linux/mlx5/driver.h>
+#include <linux/tls.h>
+
+#ifdef CONFIG_MLX5_ACCEL
+
+enum {
+ MLX5_ACCEL_TLS_TX = BIT(0),
+ MLX5_ACCEL_TLS_RX = BIT(1),
+ MLX5_ACCEL_TLS_V12 = BIT(2),
+ MLX5_ACCEL_TLS_V13 = BIT(3),
+ MLX5_ACCEL_TLS_LRO = BIT(4),
+ MLX5_ACCEL_TLS_IPV6 = BIT(5),
+ MLX5_ACCEL_TLS_AES_GCM128 = BIT(30),
+ MLX5_ACCEL_TLS_AES_GCM256 = BIT(31),
+};
+
+struct mlx5_ifc_tls_flow_bits {
+ u8 src_port[0x10];
+ u8 dst_port[0x10];
+ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6;
+ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
+ u8 ipv6[0x1];
+ u8 direction_sx[0x1];
+ u8 reserved_at_2[0x1e];
+};
+
+int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid);
+void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid);
+bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
+u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
+int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
+void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
+
+#else
+
+static inline int
+mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid) { return 0; }
+static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { }
+static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
+static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
+static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
+static inline void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) { }
+
+#endif
+
+#endif /* __MLX5_ACCEL_TLS_H__ */
return cmd->cmd_buf + (idx << cmd->log_stride);
}
+static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg)
+{
+ int size = msg->len;
+ int blen = size - min_t(int, sizeof(msg->first.data), size);
+
+ return DIV_ROUND_UP(blen, MLX5_CMD_DATA_BLOCK_SIZE);
+}
+
static u8 xor8_buf(void *buf, size_t offset, int len)
{
u8 *ptr = buf;
static void calc_chain_sig(struct mlx5_cmd_msg *msg)
{
struct mlx5_cmd_mailbox *next = msg->next;
- int size = msg->len;
- int blen = size - min_t(int, sizeof(msg->first.data), size);
- int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
- / MLX5_CMD_DATA_BLOCK_SIZE;
+ int n = mlx5_calc_cmd_blocks(msg);
int i = 0;
for (i = 0; i < n && next; i++) {
static int verify_signature(struct mlx5_cmd_work_ent *ent)
{
struct mlx5_cmd_mailbox *next = ent->out->next;
+ int n = mlx5_calc_cmd_blocks(ent->out);
int err;
u8 sig;
- int size = ent->out->len;
- int blen = size - min_t(int, sizeof(ent->out->first.data), size);
- int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
- / MLX5_CMD_DATA_BLOCK_SIZE;
int i = 0;
sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
struct mlx5_cmd_msg *msg = input ? ent->in : ent->out;
u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode);
struct mlx5_cmd_mailbox *next = msg->next;
+ int n = mlx5_calc_cmd_blocks(msg);
int data_only;
u32 offset = 0;
int dump_len;
+ int i;
data_only = !!(mlx5_core_debug_mask & (1 << MLX5_CMD_DATA));
offset += sizeof(*ent->lay);
}
- while (next && offset < msg->len) {
+ for (i = 0; i < n && next; i++) {
if (data_only) {
dump_len = min_t(int, MLX5_CMD_DATA_BLOCK_SIZE, msg->len - offset);
dump_buf(next->buf, dump_len, 1, offset);
struct mlx5_cmd_mailbox *tmp, *head = NULL;
struct mlx5_cmd_prot_block *block;
struct mlx5_cmd_msg *msg;
- int blen;
int err;
int n;
int i;
if (!msg)
return ERR_PTR(-ENOMEM);
- blen = size - min_t(int, sizeof(msg->first.data), size);
- n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) / MLX5_CMD_DATA_BLOCK_SIZE;
+ msg->len = size;
+ n = mlx5_calc_cmd_blocks(msg);
for (i = 0; i < n; i++) {
tmp = alloc_cmd_box(dev, flags);
head = tmp;
}
msg->next = head;
- msg->len = size;
return msg;
err_alloc:
switch (dst->type) {
case MLX5_FLOW_DESTINATION_TYPE_VPORT:
- trace_seq_printf(p, "vport=%u\n", dst->vport_num);
+ trace_seq_printf(p, "vport=%u\n", dst->vport.num);
break;
case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
trace_seq_printf(p, "ft=%p\n", dst->ft);
struct page_pool;
+#define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
+#define MLX5E_METADATA_ETHER_LEN 8
+
#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
bool vlan_strip_disable;
bool scatter_fcs_en;
bool rx_dim_enabled;
+ bool tx_dim_enabled;
u32 lro_timeout;
u32 pflags;
struct bpf_prog *xdp_prog;
MLX5E_RQ_STATE_AM,
};
-#define MLX5E_TEST_BIT(state, nr) (state & BIT(nr))
-
struct mlx5e_cq {
/* data path - accessed per cqe */
struct mlx5_cqwq wq;
MLX5E_SQ_STATE_ENABLED,
MLX5E_SQ_STATE_RECOVERING,
MLX5E_SQ_STATE_IPSEC,
+ MLX5E_SQ_STATE_AM,
+ MLX5E_SQ_STATE_TLS,
};
struct mlx5e_sq_wqe_info {
/* dirtied @completion */
u16 cc;
u32 dma_fifo_cc;
+ struct net_dim dim; /* Adaptive Moderation */
/* dirtied @xmit */
u16 pc ____cacheline_aligned_in_smp;
struct mlx5e_tc_table {
struct mlx5_flow_table *t;
- struct rhashtable_params ht_params;
struct rhashtable ht;
DECLARE_HASHTABLE(mod_hdr_tbl, 8);
#ifdef CONFIG_MLX5_EN_IPSEC
struct mlx5e_ipsec *ipsec;
#endif
+#ifdef CONFIG_MLX5_EN_TLS
+ struct mlx5e_tls *tls;
+#endif
};
struct mlx5e_profile {
u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback);
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+ struct mlx5e_tx_wqe *wqe, u16 pi);
void mlx5e_completion_event(struct mlx5_core_cq *mcq);
void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version));
}
+static inline void mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi)
+{
+ struct mlx5_wq_cyc *wq;
+
+ wq = &sq->wq;
+ *pi = sq->pc & wq->sz_m1;
+ *wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+ memset(*wqe, 0, sizeof(**wqe));
+}
+
static inline
struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
{
int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
struct ethtool_flash *flash);
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
- void *cb_priv);
-
/* mlx5e generic netdev management API */
struct net_device*
mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
u16 max_channels, u16 mtu);
u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
void mlx5e_rx_dim_work(struct work_struct *work);
+void mlx5e_tx_dim_work(struct work_struct *work);
#endif /* __MLX5_EN_H__ */
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef __MLX5E_EN_ACCEL_H__
+#define __MLX5E_EN_ACCEL_H__
+
+#ifdef CONFIG_MLX5_ACCEL
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls_rxtx.h"
+#include "en.h"
+
+static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
+ struct mlx5e_txqsq *sq,
+ struct net_device *dev,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi)
+{
+#ifdef CONFIG_MLX5_EN_TLS
+ if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
+ skb = mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi);
+ if (unlikely(!skb))
+ return NULL;
+ }
+#endif
+
+#ifdef CONFIG_MLX5_EN_IPSEC
+ if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) {
+ skb = mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb);
+ if (unlikely(!skb))
+ return NULL;
+ }
+#endif
+
+ return skb;
+}
+
+#endif /* CONFIG_MLX5_ACCEL */
+
+#endif /* __MLX5E_EN_ACCEL_H__ */
#define MLX5E_IPSEC_SADB_RX_BITS 10
#define MLX5E_IPSEC_ESN_SCOPE_MID 0x80000000L
-#define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
-#define MLX5E_METADATA_ETHER_LEN 8
-
struct mlx5e_priv;
struct mlx5e_ipsec_sw_stats {
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <net/ipv6.h>
+#include "en_accel/tls.h"
+#include "accel/tls.h"
+
+static void mlx5e_tls_set_ipv4_flow(void *flow, struct sock *sk)
+{
+ struct inet_sock *inet = inet_sk(sk);
+
+ MLX5_SET(tls_flow, flow, ipv6, 0);
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+ &inet->inet_daddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4));
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+ &inet->inet_rcv_saddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4));
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void mlx5e_tls_set_ipv6_flow(void *flow, struct sock *sk)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ MLX5_SET(tls_flow, flow, ipv6, 1);
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+ &sk->sk_v6_daddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+ &np->saddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+}
+#endif
+
+static void mlx5e_tls_set_flow_tcp_ports(void *flow, struct sock *sk)
+{
+ struct inet_sock *inet = inet_sk(sk);
+
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, src_port), &inet->inet_sport,
+ MLX5_FLD_SZ_BYTES(tls_flow, src_port));
+ memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_port), &inet->inet_dport,
+ MLX5_FLD_SZ_BYTES(tls_flow, dst_port));
+}
+
+static int mlx5e_tls_set_flow(void *flow, struct sock *sk, u32 caps)
+{
+ switch (sk->sk_family) {
+ case AF_INET:
+ mlx5e_tls_set_ipv4_flow(flow, sk);
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ if (!sk->sk_ipv6only &&
+ ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) {
+ mlx5e_tls_set_ipv4_flow(flow, sk);
+ break;
+ }
+ if (!(caps & MLX5_ACCEL_TLS_IPV6))
+ goto error_out;
+
+ mlx5e_tls_set_ipv6_flow(flow, sk);
+ break;
+#endif
+ default:
+ goto error_out;
+ }
+
+ mlx5e_tls_set_flow_tcp_ports(flow, sk);
+ return 0;
+error_out:
+ return -EINVAL;
+}
+
+static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
+ enum tls_offload_ctx_dir direction,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct mlx5_core_dev *mdev = priv->mdev;
+ u32 caps = mlx5_accel_tls_device_caps(mdev);
+ int ret = -ENOMEM;
+ void *flow;
+
+ if (direction != TLS_OFFLOAD_CTX_DIR_TX)
+ return -EINVAL;
+
+ flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
+ if (!flow)
+ return ret;
+
+ ret = mlx5e_tls_set_flow(flow, sk, caps);
+ if (ret)
+ goto free_flow;
+
+ if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+ struct mlx5e_tls_offload_context *tx_ctx =
+ mlx5e_get_tls_tx_context(tls_ctx);
+ u32 swid;
+
+ ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info,
+ start_offload_tcp_sn, &swid);
+ if (ret < 0)
+ goto free_flow;
+
+ tx_ctx->swid = htonl(swid);
+ tx_ctx->expected_seq = start_offload_tcp_sn;
+ }
+
+ return 0;
+free_flow:
+ kfree(flow);
+ return ret;
+}
+
+static void mlx5e_tls_del(struct net_device *netdev,
+ struct tls_context *tls_ctx,
+ enum tls_offload_ctx_dir direction)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+ u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid);
+
+ mlx5_accel_tls_del_tx_flow(priv->mdev, swid);
+ } else {
+ netdev_err(netdev, "unsupported direction %d\n", direction);
+ }
+}
+
+static const struct tlsdev_ops mlx5e_tls_ops = {
+ .tls_dev_add = mlx5e_tls_add,
+ .tls_dev_del = mlx5e_tls_del,
+};
+
+void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
+{
+ struct net_device *netdev = priv->netdev;
+
+ if (!mlx5_accel_is_tls_device(priv->mdev))
+ return;
+
+ netdev->features |= NETIF_F_HW_TLS_TX;
+ netdev->hw_features |= NETIF_F_HW_TLS_TX;
+ netdev->tlsdev_ops = &mlx5e_tls_ops;
+}
+
+int mlx5e_tls_init(struct mlx5e_priv *priv)
+{
+ struct mlx5e_tls *tls = kzalloc(sizeof(*tls), GFP_KERNEL);
+
+ if (!tls)
+ return -ENOMEM;
+
+ priv->tls = tls;
+ return 0;
+}
+
+void mlx5e_tls_cleanup(struct mlx5e_priv *priv)
+{
+ struct mlx5e_tls *tls = priv->tls;
+
+ if (!tls)
+ return;
+
+ kfree(tls);
+ priv->tls = NULL;
+}
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#ifndef __MLX5E_TLS_H__
+#define __MLX5E_TLS_H__
+
+#ifdef CONFIG_MLX5_EN_TLS
+
+#include <net/tls.h>
+#include "en.h"
+
+struct mlx5e_tls_sw_stats {
+ atomic64_t tx_tls_drop_metadata;
+ atomic64_t tx_tls_drop_resync_alloc;
+ atomic64_t tx_tls_drop_no_sync_data;
+ atomic64_t tx_tls_drop_bypass_required;
+};
+
+struct mlx5e_tls {
+ struct mlx5e_tls_sw_stats sw_stats;
+};
+
+struct mlx5e_tls_offload_context {
+ struct tls_offload_context base;
+ u32 expected_seq;
+ __be32 swid;
+};
+
+static inline struct mlx5e_tls_offload_context *
+mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
+{
+ BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
+ TLS_OFFLOAD_CONTEXT_SIZE);
+ return container_of(tls_offload_ctx(tls_ctx),
+ struct mlx5e_tls_offload_context,
+ base);
+}
+
+void mlx5e_tls_build_netdev(struct mlx5e_priv *priv);
+int mlx5e_tls_init(struct mlx5e_priv *priv);
+void mlx5e_tls_cleanup(struct mlx5e_priv *priv);
+
+int mlx5e_tls_get_count(struct mlx5e_priv *priv);
+int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data);
+int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data);
+
+#else
+
+static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { }
+static inline int mlx5e_tls_init(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { }
+static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; }
+static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; }
+static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; }
+
+#endif
+
+#endif /* __MLX5E_TLS_H__ */
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include "en_accel/tls.h"
+#include "en_accel/tls_rxtx.h"
+
+#define SYNDROME_OFFLOAD_REQUIRED 32
+#define SYNDROME_SYNC 33
+
+struct sync_info {
+ u64 rcd_sn;
+ s32 sync_len;
+ int nr_frags;
+ skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+struct mlx5e_tls_metadata {
+ /* One byte of syndrome followed by 3 bytes of swid */
+ __be32 syndrome_swid;
+ __be16 first_seq;
+ /* packet type ID field */
+ __be16 ethertype;
+} __packed;
+
+static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
+{
+ struct mlx5e_tls_metadata *pet;
+ struct ethhdr *eth;
+
+ if (skb_cow_head(skb, sizeof(struct mlx5e_tls_metadata)))
+ return -ENOMEM;
+
+ eth = (struct ethhdr *)skb_push(skb, sizeof(struct mlx5e_tls_metadata));
+ skb->mac_header -= sizeof(struct mlx5e_tls_metadata);
+ pet = (struct mlx5e_tls_metadata *)(eth + 1);
+
+ memmove(skb->data, skb->data + sizeof(struct mlx5e_tls_metadata),
+ 2 * ETH_ALEN);
+
+ eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
+ pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
+
+ return 0;
+}
+
+static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context,
+ u32 tcp_seq, struct sync_info *info)
+{
+ int remaining, i = 0, ret = -EINVAL;
+ struct tls_record_info *record;
+ unsigned long flags;
+ s32 sync_size;
+
+ spin_lock_irqsave(&context->base.lock, flags);
+ record = tls_get_record(&context->base, tcp_seq, &info->rcd_sn);
+
+ if (unlikely(!record))
+ goto out;
+
+ sync_size = tcp_seq - tls_record_start_seq(record);
+ info->sync_len = sync_size;
+ if (unlikely(sync_size < 0)) {
+ if (tls_record_is_start_marker(record))
+ goto done;
+
+ goto out;
+ }
+
+ remaining = sync_size;
+ while (remaining > 0) {
+ info->frags[i] = record->frags[i];
+ __skb_frag_ref(&info->frags[i]);
+ remaining -= skb_frag_size(&info->frags[i]);
+
+ if (remaining < 0)
+ skb_frag_size_add(&info->frags[i], remaining);
+
+ i++;
+ }
+ info->nr_frags = i;
+done:
+ ret = 0;
+out:
+ spin_unlock_irqrestore(&context->base.lock, flags);
+ return ret;
+}
+
+static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
+ struct sk_buff *nskb, u32 tcp_seq,
+ int headln, __be64 rcd_sn)
+{
+ struct mlx5e_tls_metadata *pet;
+ u8 syndrome = SYNDROME_SYNC;
+ struct iphdr *iph;
+ struct tcphdr *th;
+ int data_len, mss;
+
+ nskb->dev = skb->dev;
+ skb_reset_mac_header(nskb);
+ skb_set_network_header(nskb, skb_network_offset(skb));
+ skb_set_transport_header(nskb, skb_transport_offset(skb));
+ memcpy(nskb->data, skb->data, headln);
+ memcpy(nskb->data + headln, &rcd_sn, sizeof(rcd_sn));
+
+ iph = ip_hdr(nskb);
+ iph->tot_len = htons(nskb->len - skb_network_offset(nskb));
+ th = tcp_hdr(nskb);
+ data_len = nskb->len - headln;
+ tcp_seq -= data_len;
+ th->seq = htonl(tcp_seq);
+
+ mss = nskb->dev->mtu - (headln - skb_network_offset(nskb));
+ skb_shinfo(nskb)->gso_size = 0;
+ if (data_len > mss) {
+ skb_shinfo(nskb)->gso_size = mss;
+ skb_shinfo(nskb)->gso_segs = DIV_ROUND_UP(data_len, mss);
+ }
+ skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type;
+
+ pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
+ memcpy(pet, &syndrome, sizeof(syndrome));
+ pet->first_seq = htons(tcp_seq);
+
+ /* MLX5 devices don't care about the checksum partial start, offset
+ * and pseudo header
+ */
+ nskb->ip_summed = CHECKSUM_PARTIAL;
+
+ nskb->xmit_more = 1;
+ nskb->queue_mapping = skb->queue_mapping;
+}
+
+static struct sk_buff *
+mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context,
+ struct mlx5e_txqsq *sq, struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi,
+ struct mlx5e_tls *tls)
+{
+ u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
+ struct sync_info info;
+ struct sk_buff *nskb;
+ int linear_len = 0;
+ int headln;
+ int i;
+
+ sq->stats.tls_ooo++;
+
+ if (mlx5e_tls_get_sync_data(context, tcp_seq, &info)) {
+ /* We might get here if a retransmission reaches the driver
+ * after the relevant record is acked.
+ * It should be safe to drop the packet in this case
+ */
+ atomic64_inc(&tls->sw_stats.tx_tls_drop_no_sync_data);
+ goto err_out;
+ }
+
+ if (unlikely(info.sync_len < 0)) {
+ u32 payload;
+
+ headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ payload = skb->len - headln;
+ if (likely(payload <= -info.sync_len))
+ /* SKB payload doesn't require offload
+ */
+ return skb;
+
+ atomic64_inc(&tls->sw_stats.tx_tls_drop_bypass_required);
+ goto err_out;
+ }
+
+ if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
+ atomic64_inc(&tls->sw_stats.tx_tls_drop_metadata);
+ goto err_out;
+ }
+
+ headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ linear_len += headln + sizeof(info.rcd_sn);
+ nskb = alloc_skb(linear_len, GFP_ATOMIC);
+ if (unlikely(!nskb)) {
+ atomic64_inc(&tls->sw_stats.tx_tls_drop_resync_alloc);
+ goto err_out;
+ }
+
+ context->expected_seq = tcp_seq + skb->len - headln;
+ skb_put(nskb, linear_len);
+ for (i = 0; i < info.nr_frags; i++)
+ skb_shinfo(nskb)->frags[i] = info.frags[i];
+
+ skb_shinfo(nskb)->nr_frags = info.nr_frags;
+ nskb->data_len = info.sync_len;
+ nskb->len += info.sync_len;
+ sq->stats.tls_resync_bytes += nskb->len;
+ mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
+ cpu_to_be64(info.rcd_sn));
+ mlx5e_sq_xmit(sq, nskb, *wqe, *pi);
+ mlx5e_sq_fetch_wqe(sq, wqe, pi);
+ return skb;
+
+err_out:
+ dev_kfree_skb_any(skb);
+ return NULL;
+}
+
+struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5e_tls_offload_context *context;
+ struct tls_context *tls_ctx;
+ u32 expected_seq;
+ int datalen;
+ u32 skb_seq;
+
+ if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
+ goto out;
+
+ datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
+ if (!datalen)
+ goto out;
+
+ tls_ctx = tls_get_ctx(skb->sk);
+ if (unlikely(tls_ctx->netdev != netdev))
+ goto out;
+
+ skb_seq = ntohl(tcp_hdr(skb)->seq);
+ context = mlx5e_get_tls_tx_context(tls_ctx);
+ expected_seq = context->expected_seq;
+
+ if (unlikely(expected_seq != skb_seq)) {
+ skb = mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls);
+ goto out;
+ }
+
+ if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) {
+ atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata);
+ dev_kfree_skb_any(skb);
+ skb = NULL;
+ goto out;
+ }
+
+ context->expected_seq = skb_seq + datalen;
+out:
+ return skb;
+}
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef __MLX5E_TLS_RXTX_H__
+#define __MLX5E_TLS_RXTX_H__
+
+#ifdef CONFIG_MLX5_EN_TLS
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
+ struct mlx5e_txqsq *sq,
+ struct sk_buff *skb,
+ struct mlx5e_tx_wqe **wqe,
+ u16 *pi);
+
+#endif /* CONFIG_MLX5_EN_TLS */
+
+#endif /* __MLX5E_TLS_RXTX_H__ */
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/ethtool.h>
+#include <net/sock.h>
+
+#include "en.h"
+#include "accel/tls.h"
+#include "fpga/sdk.h"
+#include "en_accel/tls.h"
+
+static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_metadata) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_resync_alloc) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_no_sync_data) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) },
+};
+
+#define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \
+ atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset))
+
+#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
+
+int mlx5e_tls_get_count(struct mlx5e_priv *priv)
+{
+ if (!priv->tls)
+ return 0;
+
+ return NUM_TLS_SW_COUNTERS;
+}
+
+int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
+{
+ unsigned int i, idx = 0;
+
+ if (!priv->tls)
+ return 0;
+
+ for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ mlx5e_tls_sw_stats_desc[i].format);
+
+ return NUM_TLS_SW_COUNTERS;
+}
+
+int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
+{
+ int i, idx = 0;
+
+ if (!priv->tls)
+ return 0;
+
+ for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+ data[idx++] =
+ MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats,
+ mlx5e_tls_sw_stats_desc, i);
+
+ return NUM_TLS_SW_COUNTERS;
+}
err = mlx5_modify_rule_destination(rule, &dst, NULL);
if (err)
netdev_warn(priv->netdev,
- "Failed to modfiy aRFS rule destination to rq=%d\n", rxq);
+ "Failed to modify aRFS rule destination to rq=%d\n", rxq);
}
static void arfs_handle_work(struct work_struct *work)
mutex_lock(&priv->state_lock);
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
- goto out;
-
new_channels.params = priv->channels.params;
mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params);
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+
/* Skip if tx_min_inline is the same */
if (new_channels.params.tx_min_inline_mode ==
priv->channels.params.tx_min_inline_mode)
#include <linux/net_dim.h>
#include "en.h"
+static void
+mlx5e_complete_dim_work(struct net_dim *dim, struct net_dim_cq_moder moder,
+ struct mlx5_core_dev *mdev, struct mlx5_core_cq *mcq)
+{
+ mlx5_core_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts);
+ dim->state = NET_DIM_START_MEASURE;
+}
+
void mlx5e_rx_dim_work(struct work_struct *work)
{
- struct net_dim *dim = container_of(work, struct net_dim,
- work);
+ struct net_dim *dim = container_of(work, struct net_dim, work);
struct mlx5e_rq *rq = container_of(dim, struct mlx5e_rq, dim);
- struct net_dim_cq_moder cur_profile = net_dim_get_profile(dim->mode,
- dim->profile_ix);
+ struct net_dim_cq_moder cur_moder =
+ net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
- mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq,
- cur_profile.usec, cur_profile.pkts);
+ mlx5e_complete_dim_work(dim, cur_moder, rq->mdev, &rq->cq.mcq);
+}
- dim->state = NET_DIM_START_MEASURE;
+void mlx5e_tx_dim_work(struct work_struct *work)
+{
+ struct net_dim *dim = container_of(work, struct net_dim, work);
+ struct mlx5e_txqsq *sq = container_of(dim, struct mlx5e_txqsq, dim);
+ struct net_dim_cq_moder cur_moder =
+ net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
+
+ mlx5e_complete_dim_work(dim, cur_moder, sq->cq.mdev, &sq->cq.mcq);
}
int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
struct ethtool_coalesce *coal)
{
+ struct net_dim_cq_moder *rx_moder, *tx_moder;
+
if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
return -EOPNOTSUPP;
- coal->rx_coalesce_usecs = priv->channels.params.rx_cq_moderation.usec;
- coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts;
- coal->tx_coalesce_usecs = priv->channels.params.tx_cq_moderation.usec;
- coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts;
- coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled;
+ rx_moder = &priv->channels.params.rx_cq_moderation;
+ coal->rx_coalesce_usecs = rx_moder->usec;
+ coal->rx_max_coalesced_frames = rx_moder->pkts;
+ coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled;
+
+ tx_moder = &priv->channels.params.tx_cq_moderation;
+ coal->tx_coalesce_usecs = tx_moder->usec;
+ coal->tx_max_coalesced_frames = tx_moder->pkts;
+ coal->use_adaptive_tx_coalesce = priv->channels.params.tx_dim_enabled;
return 0;
}
int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
struct ethtool_coalesce *coal)
{
+ struct net_dim_cq_moder *rx_moder, *tx_moder;
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_channels new_channels = {};
int err = 0;
mutex_lock(&priv->state_lock);
new_channels.params = priv->channels.params;
- new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
- new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
- new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
- new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
- new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce;
+ rx_moder = &new_channels.params.rx_cq_moderation;
+ rx_moder->usec = coal->rx_coalesce_usecs;
+ rx_moder->pkts = coal->rx_max_coalesced_frames;
+ new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce;
+
+ tx_moder = &new_channels.params.tx_cq_moderation;
+ tx_moder->usec = coal->tx_coalesce_usecs;
+ tx_moder->pkts = coal->tx_max_coalesced_frames;
+ new_channels.params.tx_dim_enabled = !!coal->use_adaptive_tx_coalesce;
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
priv->channels.params = new_channels.params;
}
/* we are opened */
- reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled;
+ reset = (!!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled) ||
+ (!!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled);
+
if (!reset) {
mlx5e_set_priv_channels_coalesce(priv, coal);
priv->channels.params = new_channels.params;
}
break;
case MLX5E_VLAN_RULE_TYPE_MATCH_CTAG_VID:
- mlx5e_vport_context_update_vlans(priv);
if (priv->fs.vlan.active_cvlans_rule[vid]) {
mlx5_del_flow_rules(priv->fs.vlan.active_cvlans_rule[vid]);
priv->fs.vlan.active_cvlans_rule[vid] = NULL;
#include "en_rep.h"
#include "en_accel/ipsec.h"
#include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls.h"
#include "accel/ipsec.h"
+#include "accel/tls.h"
#include "vxlan.h"
struct mlx5e_rq_param {
mlx5_core_destroy_rq(rq->mdev, rq->rqn);
}
-static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
+static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
{
- unsigned long exp_time = jiffies + msecs_to_jiffies(20000);
+ unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
struct mlx5e_channel *c = rq->channel;
struct mlx5_wq_ll *wq = &rq->wq;
u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
- while (time_before(jiffies, exp_time)) {
+ do {
if (wq->cur_sz >= min_wqes)
return 0;
msleep(20);
- }
+ } while (time_before(jiffies, exp_time));
+
+ netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
+ c->ix, rq->rqn, wq->cur_sz, min_wqes);
- netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
- rq->rqn, wq->cur_sz, min_wqes);
return -ETIMEDOUT;
}
goto err_destroy_rq;
if (params->rx_dim_enabled)
- c->rq.state |= BIT(MLX5E_RQ_STATE_AM);
+ __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
return 0;
INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
if (MLX5_IPSEC_DEV(c->priv->mdev))
set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
+ if (mlx5_accel_is_tls_device(c->priv->mdev))
+ set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
goto err_sq_wq_destroy;
+ INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work);
+ sq->dim.mode = params->tx_cq_moderation.cq_period_mode;
+
sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
return 0;
if (tx_rate)
mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
+ if (params->tx_dim_enabled)
+ sq->state |= BIT(MLX5E_SQ_STATE_AM);
+
return 0;
err_free_txqsq:
MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en);
param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
- param->wq.linear = 1;
}
static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
int err = 0;
int i;
- for (i = 0; i < chs->num; i++) {
- err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq);
- if (err)
- break;
- }
+ for (i = 0; i < chs->num; i++)
+ err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq,
+ err ? 0 : 20000);
- return err;
+ return err ? -ETIMEDOUT : 0;
}
static void mlx5e_deactivate_channels(struct mlx5e_channels *chs)
#ifdef CONFIG_MLX5_ESWITCH
static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *cls_flower)
+ struct tc_cls_flower_offload *cls_flower,
+ int flags)
{
switch (cls_flower->command) {
case TC_CLSFLOWER_REPLACE:
- return mlx5e_configure_flower(priv, cls_flower);
+ return mlx5e_configure_flower(priv, cls_flower, flags);
case TC_CLSFLOWER_DESTROY:
- return mlx5e_delete_flower(priv, cls_flower);
+ return mlx5e_delete_flower(priv, cls_flower, flags);
case TC_CLSFLOWER_STATS:
- return mlx5e_stats_flower(priv, cls_flower);
+ return mlx5e_stats_flower(priv, cls_flower, flags);
default:
return -EOPNOTSUPP;
}
}
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
- void *cb_priv)
+static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+ void *cb_priv)
{
struct mlx5e_priv *priv = cb_priv;
switch (type) {
case TC_SETUP_CLSFLOWER:
- return mlx5e_setup_tc_cls_flower(priv, type_data);
+ return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
default:
return -EOPNOTSUPP;
}
link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw;
}
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
{
- params->tx_cq_moderation.cq_period_mode = cq_period_mode;
+ struct net_dim_cq_moder moder;
- params->tx_cq_moderation.pkts =
- MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
- params->tx_cq_moderation.usec =
- MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+ moder.cq_period_mode = cq_period_mode;
+ moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+ moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+ if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
+ moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE;
+
+ return moder;
+}
+static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+{
+ struct net_dim_cq_moder moder;
+
+ moder.cq_period_mode = cq_period_mode;
+ moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
+ moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
- params->tx_cq_moderation.usec =
- MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE;
+ moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+
+ return moder;
+}
+
+static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
+{
+ return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
+ NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+ NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+}
+
+void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+ if (params->tx_dim_enabled) {
+ u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
+
+ params->tx_cq_moderation = net_dim_get_def_tx_moderation(dim_period_mode);
+ } else {
+ params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode);
+ }
MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
params->tx_cq_moderation.cq_period_mode ==
void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
{
- params->rx_cq_moderation.cq_period_mode = cq_period_mode;
-
- params->rx_cq_moderation.pkts =
- MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
- params->rx_cq_moderation.usec =
- MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
-
- if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
- params->rx_cq_moderation.usec =
- MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
-
if (params->rx_dim_enabled) {
- switch (cq_period_mode) {
- case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
- params->rx_cq_moderation =
- net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE);
- break;
- case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
- default:
- params->rx_cq_moderation =
- net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE);
- }
+ u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
+
+ params->rx_cq_moderation = net_dim_get_def_rx_moderation(dim_period_mode);
+ } else {
+ params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode);
}
MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+ params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
#endif
mlx5e_ipsec_build_netdev(priv);
+ mlx5e_tls_build_netdev(priv);
}
static void mlx5e_create_q_counters(struct mlx5e_priv *priv)
err = mlx5e_ipsec_init(priv);
if (err)
mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err);
+ err = mlx5e_tls_init(priv);
+ if (err)
+ mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
mlx5e_build_nic_netdev(netdev);
mlx5e_vxlan_init(priv);
}
static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
{
+ mlx5e_tls_cleanup(priv);
mlx5e_ipsec_cleanup(priv);
mlx5e_vxlan_cleanup(priv);
}
goto err_destroy_direct_tirs;
}
- err = mlx5e_tc_init(priv);
+ err = mlx5e_tc_nic_init(priv);
if (err)
goto err_destroy_flow_steering;
static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
{
- mlx5e_tc_cleanup(priv);
+ mlx5e_tc_nic_cleanup(priv);
mlx5e_destroy_flow_steering(priv);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_indirect_tirs(priv);
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
};
-#define NUM_VPORT_REP_COUNTERS ARRAY_SIZE(sw_rep_stats_desc)
+struct vport_stats {
+ u64 vport_rx_packets;
+ u64 vport_tx_packets;
+ u64 vport_rx_bytes;
+ u64 vport_tx_bytes;
+};
+
+static const struct counter_desc vport_rep_stats_desc[] = {
+ { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_packets) },
+ { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_bytes) },
+ { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_packets) },
+ { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_bytes) },
+};
+
+#define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc)
+#define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc)
static void mlx5e_rep_get_strings(struct net_device *dev,
u32 stringset, uint8_t *data)
{
- int i;
+ int i, j;
switch (stringset) {
case ETH_SS_STATS:
- for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+ for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
strcpy(data + (i * ETH_GSTRING_LEN),
sw_rep_stats_desc[i].format);
+ for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
+ strcpy(data + (i * ETH_GSTRING_LEN),
+ vport_rep_stats_desc[j].format);
break;
}
}
struct ethtool_stats *stats, u64 *data)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- int i;
+ int i, j;
if (!data)
return;
mutex_lock(&priv->state_lock);
if (test_bit(MLX5E_STATE_OPENED, &priv->state))
mlx5e_rep_update_sw_counters(priv);
+ mlx5e_rep_update_hw_counters(priv);
mutex_unlock(&priv->state_lock);
- for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
+ for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw,
sw_rep_stats_desc, i);
+
+ for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++)
+ data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport,
+ vport_rep_stats_desc, j);
}
static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
- return NUM_VPORT_REP_COUNTERS;
+ return NUM_VPORT_REP_SW_COUNTERS + NUM_VPORT_REP_HW_COUNTERS;
default:
return -EOPNOTSUPP;
}
goto unlock;
if (!mlx5_modify_vport_admin_state(priv->mdev,
- MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
- rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
+ MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+ rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
netif_carrier_on(dev);
unlock:
mutex_lock(&priv->state_lock);
mlx5_modify_vport_admin_state(priv->mdev,
- MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
- rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+ MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+ rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
ret = mlx5e_close_locked(dev);
mutex_unlock(&priv->state_lock);
return ret;
static int
mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *cls_flower)
+ struct tc_cls_flower_offload *cls_flower, int flags)
{
switch (cls_flower->command) {
case TC_CLSFLOWER_REPLACE:
- return mlx5e_configure_flower(priv, cls_flower);
+ return mlx5e_configure_flower(priv, cls_flower, flags);
case TC_CLSFLOWER_DESTROY:
- return mlx5e_delete_flower(priv, cls_flower);
+ return mlx5e_delete_flower(priv, cls_flower, flags);
case TC_CLSFLOWER_STATS:
- return mlx5e_stats_flower(priv, cls_flower);
+ return mlx5e_stats_flower(priv, cls_flower, flags);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data,
+ void *cb_priv)
+{
+ struct mlx5e_priv *priv = cb_priv;
+
+ if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data))
+ return -EOPNOTSUPP;
+
+ switch (type) {
+ case TC_SETUP_CLSFLOWER:
+ return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS);
default:
return -EOPNOTSUPP;
}
switch (type) {
case TC_SETUP_CLSFLOWER:
- return mlx5e_rep_setup_tc_cls_flower(priv, type_data);
+ return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
default:
return -EOPNOTSUPP;
}
};
static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params)
+ struct mlx5e_params *params, u16 mtu)
{
u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
params->hard_mtu = MLX5E_ETH_HARD_MTU;
+ params->sw_mtu = mtu;
params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
priv->channels.params.num_channels = profile->max_nch(mdev);
- mlx5e_build_rep_params(mdev, &priv->channels.params);
+ mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu);
mlx5e_build_rep_netdev(netdev);
mlx5e_timestamp_init(priv);
}
rpriv->vport_rx_rule = flow_rule;
- err = mlx5e_tc_init(priv);
- if (err)
- goto err_del_flow_rule;
-
return 0;
-err_del_flow_rule:
- mlx5_del_flow_rules(rpriv->vport_rx_rule);
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
{
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- mlx5e_tc_cleanup(priv);
mlx5_del_flow_rules(rpriv->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_rqts(priv);
if (err)
goto err_remove_sqs;
+ /* init shared tc flow table */
+ err = mlx5e_tc_esw_init(&rpriv->tc_ht);
+ if (err)
+ goto err_neigh_cleanup;
+
return 0;
+err_neigh_cleanup:
+ mlx5e_rep_neigh_cleanup(rpriv);
err_remove_sqs:
mlx5e_remove_sqs_fwd_rules(priv);
return err;
if (test_bit(MLX5E_STATE_OPENED, &priv->state))
mlx5e_remove_sqs_fwd_rules(priv);
- /* clean (and re-init) existing uplink offloaded TC rules */
- mlx5e_tc_cleanup(priv);
- mlx5e_tc_init(priv);
+ /* clean uplink offloaded TC rules, delete shared tc flow table */
+ mlx5e_tc_esw_cleanup(&rpriv->tc_ht);
mlx5e_rep_neigh_cleanup(rpriv);
}
uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
upriv = netdev_priv(uplink_rpriv->netdev);
- err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
+ err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev,
upriv);
if (err)
goto err_neigh_cleanup;
return 0;
err_egdev_cleanup:
- tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+ tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
upriv);
err_neigh_cleanup:
uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
REP_ETH);
upriv = netdev_priv(uplink_rpriv->netdev);
- tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+ tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
upriv);
mlx5e_rep_neigh_cleanup(rpriv);
mlx5e_detach_netdev(priv);
struct net_device *netdev;
struct mlx5_flow_handle *vport_rx_rule;
struct list_head vport_sqs_list;
+ struct rhashtable tc_ht; /* valid for uplink rep */
};
static inline
struct mlx5_wq_ll *wq = &rq->wq;
int err;
- if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return false;
if (mlx5_wq_ll_is_full(wq))
struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
struct mlx5_cqe64 *cqe;
- if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
return;
cqe = mlx5_cqwq_get_cqe(&cq->wq);
{
struct mlx5_wq_ll *wq = &rq->wq;
- if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return false;
mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq);
struct mlx5e_rq *rq,
struct sk_buff *skb)
{
+ u8 lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
struct net_device *netdev = rq->netdev;
- int lro_num_seg;
skb->mac_len = ETH_HLEN;
- lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
if (lro_num_seg > 1) {
mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
}
/* returns true if packet was consumed by xdp */
-static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
- struct mlx5e_dma_info *di,
- void *va, u16 *rx_headroom, u32 *len)
+static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
+ struct mlx5e_dma_info *di,
+ void *va, u16 *rx_headroom, u32 *len)
{
struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
struct xdp_buff xdp;
struct mlx5_cqe64 *cqe;
int work_done = 0;
- if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return 0;
if (cq->decmprs_left)
sq = container_of(cq, struct mlx5e_xdpsq, cq);
- if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
return false;
cqe = mlx5_cqwq_get_cqe(&cq->wq);
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
netdev_err(priv->netdev,
- "\tCan't perform loobpack test while device is down\n");
+ "\tCan't perform loopback test while device is down\n");
return -ENODEV;
}
#include "en.h"
#include "en_accel/ipsec.h"
+#include "en_accel/tls.h"
static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+
+#ifdef CONFIG_MLX5_EN_TLS
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) },
+#endif
+
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) },
s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
s->tx_csum_none += sq_stats->csum_none;
s->tx_csum_partial += sq_stats->csum_partial;
+#ifdef CONFIG_MLX5_EN_TLS
+ s->tx_tls_ooo += sq_stats->tls_ooo;
+ s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes;
+#endif
}
}
mlx5e_ipsec_update_stats(priv);
}
+static int mlx5e_grp_tls_get_num_stats(struct mlx5e_priv *priv)
+{
+ return mlx5e_tls_get_count(priv);
+}
+
+static int mlx5e_grp_tls_fill_strings(struct mlx5e_priv *priv, u8 *data,
+ int idx)
+{
+ return idx + mlx5e_tls_get_strings(priv, data + idx * ETH_GSTRING_LEN);
+}
+
+static int mlx5e_grp_tls_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
+{
+ return idx + mlx5e_tls_get_stats(priv, data + idx);
+}
+
static const struct counter_desc rq_stats_desc[] = {
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
.fill_stats = mlx5e_grp_ipsec_fill_stats,
.update_stats = mlx5e_grp_ipsec_update_stats,
},
+ {
+ .get_num_stats = mlx5e_grp_tls_get_num_stats,
+ .fill_strings = mlx5e_grp_tls_fill_strings,
+ .fill_stats = mlx5e_grp_tls_fill_stats,
+ },
{
.get_num_stats = mlx5e_grp_channels_get_num_stats,
.fill_strings = mlx5e_grp_channels_fill_strings,
u64 rx_cache_waive;
u64 ch_eq_rearm;
+#ifdef CONFIG_MLX5_EN_TLS
+ u64 tx_tls_ooo;
+ u64 tx_tls_resync_bytes;
+#endif
+
/* Special handling counters */
u64 link_down_events_phy;
};
u64 csum_partial_inner;
u64 added_vlan_packets;
u64 nop;
+#ifdef CONFIG_MLX5_EN_TLS
+ u64 tls_ooo;
+ u64 tls_resync_bytes;
+#endif
/* less likely accessed in data path */
u64 csum_none;
u64 stopped;
u32 flow_tag;
u32 mod_hdr_id;
u32 hairpin_tirn;
+ u8 match_level;
struct mlx5_flow_table *hairpin_ft;
};
+#define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1)
+
enum {
- MLX5E_TC_FLOW_ESWITCH = BIT(0),
- MLX5E_TC_FLOW_NIC = BIT(1),
- MLX5E_TC_FLOW_OFFLOADED = BIT(2),
- MLX5E_TC_FLOW_HAIRPIN = BIT(3),
- MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(4),
+ MLX5E_TC_FLOW_INGRESS = MLX5E_TC_INGRESS,
+ MLX5E_TC_FLOW_EGRESS = MLX5E_TC_EGRESS,
+ MLX5E_TC_FLOW_ESWITCH = BIT(MLX5E_TC_FLOW_BASE),
+ MLX5E_TC_FLOW_NIC = BIT(MLX5E_TC_FLOW_BASE + 1),
+ MLX5E_TC_FLOW_OFFLOADED = BIT(MLX5E_TC_FLOW_BASE + 2),
+ MLX5E_TC_FLOW_HAIRPIN = BIT(MLX5E_TC_FLOW_BASE + 3),
+ MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4),
};
struct mlx5e_tc_flow {
struct rhash_head node;
+ struct mlx5e_priv *priv;
u64 cookie;
u8 flags;
struct mlx5_flow_handle *rule;
};
#define MLX5E_TC_TABLE_NUM_GROUPS 4
-#define MLX5E_TC_TABLE_MAX_GROUP_SIZE (1 << 16)
+#define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16)
struct mlx5e_hairpin {
struct mlx5_hairpin *pair;
table_created = true;
}
- parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ if (attr->match_level != MLX5_MATCH_NONE)
+ parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
&flow_act, dest, dest_ix);
mlx5_del_flow_rules(flow->rule);
mlx5_fc_destroy(priv->mdev, counter);
- if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
+ if (!mlx5e_tc_num_filters(priv) && priv->fs.tc.t) {
mlx5_destroy_flow_table(priv->fs.tc.t);
priv->fs.tc.t = NULL;
}
out_priv = netdev_priv(encap_dev);
rpriv = out_priv->ppriv;
attr->out_rep = rpriv->rep;
+ attr->out_mdev = out_priv->mdev;
}
err = mlx5_eswitch_add_vlan_action(esw, attr);
}
}
}
+ if (neigh_used)
+ break;
}
if (neigh_used) {
static int __parse_cls_flower(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
struct tc_cls_flower_offload *f,
- u8 *min_inline)
+ u8 *match_level)
{
void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
outer_headers);
u16 addr_type = 0;
u8 ip_proto = 0;
- *min_inline = MLX5_INLINE_MODE_L2;
+ *match_level = MLX5_MATCH_NONE;
if (f->dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
inner_headers);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
- struct flow_dissector_key_control *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->key);
-
- struct flow_dissector_key_control *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->mask);
- addr_type = key->addr_type;
-
- if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
- key->flags & FLOW_DIS_IS_FRAGMENT);
-
- /* the HW doesn't need L3 inline to match on frag=no */
- if (key->flags & FLOW_DIS_IS_FRAGMENT)
- *min_inline = MLX5_INLINE_MODE_IP;
- }
- }
-
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
- struct flow_dissector_key_basic *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
- ip_proto = key->ip_proto;
-
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
- ntohs(mask->n_proto));
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
- ntohs(key->n_proto));
-
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
- mask->ip_proto);
- MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
- key->ip_proto);
-
- if (mask->ip_proto)
- *min_inline = MLX5_INLINE_MODE_IP;
- }
-
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct flow_dissector_key_eth_addrs *key =
skb_flow_dissector_target(f->dissector,
ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
smac_47_16),
key->src);
+
+ if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+ *match_level = MLX5_MATCH_L2;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
+
+ *match_level = MLX5_MATCH_L2;
}
}
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+ struct flow_dissector_key_basic *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->mask);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+ ntohs(mask->n_proto));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+ ntohs(key->n_proto));
+
+ if (mask->n_proto)
+ *match_level = MLX5_MATCH_L2;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_dissector_key_control *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ f->key);
+
+ struct flow_dissector_key_control *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_CONTROL,
+ f->mask);
+ addr_type = key->addr_type;
+
+ /* the HW doesn't support frag first/later */
+ if (mask->flags & FLOW_DIS_FIRST_FRAG)
+ return -EOPNOTSUPP;
+
+ if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
+ key->flags & FLOW_DIS_IS_FRAGMENT);
+
+ /* the HW doesn't need L3 inline to match on frag=no */
+ if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
+ *match_level = MLX5_INLINE_MODE_L2;
+ /* *** L2 attributes parsing up to here *** */
+ else
+ *match_level = MLX5_INLINE_MODE_IP;
+ }
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_dissector_key_basic *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->key);
+ struct flow_dissector_key_basic *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_BASIC,
+ f->mask);
+ ip_proto = key->ip_proto;
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
+ mask->ip_proto);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
+ key->ip_proto);
+
+ if (mask->ip_proto)
+ *match_level = MLX5_MATCH_L3;
+ }
+
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
struct flow_dissector_key_ipv4_addrs *key =
skb_flow_dissector_target(f->dissector,
&key->dst, sizeof(key->dst));
if (mask->src || mask->dst)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY ||
ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) {
return -EOPNOTSUPP;
if (mask->tos || mask->ttl)
- *min_inline = MLX5_INLINE_MODE_IP;
+ *match_level = MLX5_MATCH_L3;
}
+ /* *** L3 attributes parsing up to here *** */
+
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
struct flow_dissector_key_ports *key =
skb_flow_dissector_target(f->dissector,
}
if (mask->src || mask->dst)
- *min_inline = MLX5_INLINE_MODE_TCP_UDP;
+ *match_level = MLX5_MATCH_L4;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) {
ntohs(key->flags));
if (mask->flags)
- *min_inline = MLX5_INLINE_MODE_TCP_UDP;
+ *match_level = MLX5_MATCH_L4;
}
return 0;
struct mlx5_eswitch *esw = dev->priv.eswitch;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep;
- u8 min_inline;
+ u8 match_level;
int err;
- err = __parse_cls_flower(priv, spec, f, &min_inline);
+ err = __parse_cls_flower(priv, spec, f, &match_level);
if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
rep = rpriv->rep;
if (rep->vport != FDB_UPLINK_VPORT &&
(esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
- esw->offloads.inline_mode < min_inline)) {
+ esw->offloads.inline_mode < match_level)) {
netdev_warn(priv->netdev,
"Flow is not offloaded due to min inline setting, required %d actual %d\n",
- min_inline, esw->offloads.inline_mode);
+ match_level, esw->offloads.inline_mode);
return -EOPNOTSUPP;
}
}
+ if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+ flow->esw_attr->match_level = match_level;
+ else
+ flow->nic_attr->match_level = match_level;
+
return err;
}
{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, offsetof(struct pedit_headers, field) + (off)}
static struct mlx5_fields fields[] = {
- OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0),
OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
err = -EOPNOTSUPP; /* can't be all optimistic */
if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
- printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n");
+ netdev_warn(priv->netdev, "legacy pedit isn't offloaded\n");
goto out_err;
}
if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
- printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd);
+ netdev_warn(priv->netdev, "pedit cmd %d isn't offloaded\n", cmd);
goto out_err;
}
for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
cmd_masks = &masks[cmd];
if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
- printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n",
- cmd);
+ netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd);
print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
16, 1, cmd_masks, sizeof(zero_masks), true);
err = -EOPNOTSUPP;
}
ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
- if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+ if (modify_ip_header && ip_proto != IPPROTO_TCP &&
+ ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) {
pr_info("can't offload re-write of ip proto %d\n", ip_proto);
return false;
}
struct mlx5_nic_flow_attr *attr = flow->nic_attr;
const struct tc_action *a;
LIST_HEAD(actions);
+ u32 action = 0;
int err;
if (!tcf_exts_has_actions(exts))
return -EINVAL;
attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
- attr->action = 0;
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
if (is_tcf_gact_shot(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
if (MLX5_CAP_FLOWTABLE(priv->mdev,
flow_table_properties_nic_receive.flow_counter))
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
if (err)
return err;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
if (is_tcf_csum(a)) {
- if (csum_offload_supported(priv, attr->action,
+ if (csum_offload_supported(priv, action,
tcf_csum_update_flags(a)))
continue;
same_hw_devs(priv, netdev_priv(peer_dev))) {
parse_attr->mirred_ifindex = peer_dev->ifindex;
flow->flags |= MLX5E_TC_FLOW_HAIRPIN;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
} else {
netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n",
peer_dev->name);
}
attr->flow_tag = mark;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
return -EINVAL;
}
+ attr->action = action;
if (!actions_match_supported(priv, exts, parse_attr, flow))
return -EOPNOTSUPP;
return 0;
}
+static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
+ struct net_device *peer_netdev)
+{
+ struct mlx5e_priv *peer_priv;
+
+ peer_priv = netdev_priv(peer_netdev);
+
+ return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) &&
+ (priv->netdev->netdev_ops == peer_netdev->netdev_ops) &&
+ same_hw_devs(priv, peer_priv) &&
+ MLX5_VPORT_MANAGER(peer_priv->mdev) &&
+ (peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS));
+}
+
static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
struct net_device *mirred_dev,
struct net_device **out_dev,
const struct tc_action *a;
LIST_HEAD(actions);
bool encap = false;
- int err = 0;
+ u32 action = 0;
if (!tcf_exts_has_actions(exts))
return -EINVAL;
- memset(attr, 0, sizeof(*attr));
attr->in_rep = rpriv->rep;
+ attr->in_mdev = priv->mdev;
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
if (is_tcf_gact_shot(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
if (is_tcf_pedit(a)) {
+ int err;
+
err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
parse_attr);
if (err)
return err;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
continue;
}
if (is_tcf_csum(a)) {
- if (csum_offload_supported(priv, attr->action,
+ if (csum_offload_supported(priv, action,
tcf_csum_update_flags(a)))
continue;
out_dev = tcf_mirred_dev(a);
if (switchdev_port_same_parent_id(priv->netdev,
- out_dev)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ out_dev) ||
+ is_merged_eswitch_dev(priv, out_dev)) {
+ action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
out_priv = netdev_priv(out_dev);
rpriv = out_priv->ppriv;
attr->out_rep = rpriv->rep;
+ attr->out_mdev = out_priv->mdev;
} else if (encap) {
parse_attr->mirred_ifindex = out_dev->ifindex;
parse_attr->tun_info = *info;
attr->parse_attr = parse_attr;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
/* attr->out_rep is resolved when we handle encap */
} else {
pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
if (is_tcf_vlan(a)) {
if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
attr->vlan_vid = tcf_vlan_push_vid(a);
if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
attr->vlan_prio = tcf_vlan_push_prio(a);
}
if (is_tcf_tunnel_release(a)) {
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+ action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
continue;
}
return -EINVAL;
}
+ attr->action = action;
if (!actions_match_supported(priv, exts, parse_attr, flow))
return -EOPNOTSUPP;
- return err;
+ return 0;
+}
+
+static void get_flags(int flags, u8 *flow_flags)
+{
+ u8 __flow_flags = 0;
+
+ if (flags & MLX5E_TC_INGRESS)
+ __flow_flags |= MLX5E_TC_FLOW_INGRESS;
+ if (flags & MLX5E_TC_EGRESS)
+ __flow_flags |= MLX5E_TC_FLOW_EGRESS;
+
+ *flow_flags = __flow_flags;
+}
+
+static const struct rhashtable_params tc_ht_params = {
+ .head_offset = offsetof(struct mlx5e_tc_flow, node),
+ .key_offset = offsetof(struct mlx5e_tc_flow, cookie),
+ .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie),
+ .automatic_shrinking = true,
+};
+
+static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5e_rep_priv *uplink_rpriv;
+
+ if (MLX5_VPORT_MANAGER(priv->mdev) && esw->mode == SRIOV_OFFLOADS) {
+ uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+ return &uplink_rpriv->tc_ht;
+ } else
+ return &priv->fs.tc.ht;
}
int mlx5e_configure_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f)
+ struct tc_cls_flower_offload *f, int flags)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_tc_flow_parse_attr *parse_attr;
- struct mlx5e_tc_table *tc = &priv->fs.tc;
+ struct rhashtable *tc_ht = get_tc_ht(priv);
struct mlx5e_tc_flow *flow;
int attr_size, err = 0;
u8 flow_flags = 0;
+ get_flags(flags, &flow_flags);
+
+ flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
+ if (flow) {
+ netdev_warn_once(priv->netdev, "flow cookie %lx already exists, ignoring\n", f->cookie);
+ return 0;
+ }
+
if (esw && esw->mode == SRIOV_OFFLOADS) {
- flow_flags = MLX5E_TC_FLOW_ESWITCH;
+ flow_flags |= MLX5E_TC_FLOW_ESWITCH;
attr_size = sizeof(struct mlx5_esw_flow_attr);
} else {
- flow_flags = MLX5E_TC_FLOW_NIC;
+ flow_flags |= MLX5E_TC_FLOW_NIC;
attr_size = sizeof(struct mlx5_nic_flow_attr);
}
flow->cookie = f->cookie;
flow->flags = flow_flags;
+ flow->priv = priv;
err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
if (err < 0)
!(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
kvfree(parse_attr);
- err = rhashtable_insert_fast(&tc->ht, &flow->node,
- tc->ht_params);
+ err = rhashtable_insert_fast(tc_ht, &flow->node, tc_ht_params);
if (err) {
mlx5e_tc_del_flow(priv, flow);
kfree(flow);
return err;
}
+#define DIRECTION_MASK (MLX5E_TC_INGRESS | MLX5E_TC_EGRESS)
+#define FLOW_DIRECTION_MASK (MLX5E_TC_FLOW_INGRESS | MLX5E_TC_FLOW_EGRESS)
+
+static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
+{
+ if ((flow->flags & FLOW_DIRECTION_MASK) == (flags & DIRECTION_MASK))
+ return true;
+
+ return false;
+}
+
int mlx5e_delete_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f)
+ struct tc_cls_flower_offload *f, int flags)
{
+ struct rhashtable *tc_ht = get_tc_ht(priv);
struct mlx5e_tc_flow *flow;
- struct mlx5e_tc_table *tc = &priv->fs.tc;
- flow = rhashtable_lookup_fast(&tc->ht, &f->cookie,
- tc->ht_params);
- if (!flow)
+ flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
+ if (!flow || !same_flow_direction(flow, flags))
return -EINVAL;
- rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params);
+ rhashtable_remove_fast(tc_ht, &flow->node, tc_ht_params);
mlx5e_tc_del_flow(priv, flow);
}
int mlx5e_stats_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f)
+ struct tc_cls_flower_offload *f, int flags)
{
- struct mlx5e_tc_table *tc = &priv->fs.tc;
+ struct rhashtable *tc_ht = get_tc_ht(priv);
struct mlx5e_tc_flow *flow;
struct mlx5_fc *counter;
u64 bytes;
u64 packets;
u64 lastuse;
- flow = rhashtable_lookup_fast(&tc->ht, &f->cookie,
- tc->ht_params);
- if (!flow)
+ flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
+ if (!flow || !same_flow_direction(flow, flags))
return -EINVAL;
if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED))
return 0;
}
-static const struct rhashtable_params mlx5e_tc_flow_ht_params = {
- .head_offset = offsetof(struct mlx5e_tc_flow, node),
- .key_offset = offsetof(struct mlx5e_tc_flow, cookie),
- .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie),
- .automatic_shrinking = true,
-};
-
-int mlx5e_tc_init(struct mlx5e_priv *priv)
+int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
{
struct mlx5e_tc_table *tc = &priv->fs.tc;
hash_init(tc->mod_hdr_tbl);
hash_init(tc->hairpin_tbl);
- tc->ht_params = mlx5e_tc_flow_ht_params;
- return rhashtable_init(&tc->ht, &tc->ht_params);
+ return rhashtable_init(&tc->ht, &tc_ht_params);
}
static void _mlx5e_tc_del_flow(void *ptr, void *arg)
{
struct mlx5e_tc_flow *flow = ptr;
- struct mlx5e_priv *priv = arg;
+ struct mlx5e_priv *priv = flow->priv;
mlx5e_tc_del_flow(priv, flow);
kfree(flow);
}
-void mlx5e_tc_cleanup(struct mlx5e_priv *priv)
+void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
{
struct mlx5e_tc_table *tc = &priv->fs.tc;
- rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, priv);
+ rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL);
if (!IS_ERR_OR_NULL(tc->t)) {
mlx5_destroy_flow_table(tc->t);
tc->t = NULL;
}
}
+
+int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
+{
+ return rhashtable_init(tc_ht, &tc_ht_params);
+}
+
+void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
+{
+ rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL);
+}
#define MLX5E_TC_FLOW_ID_MASK 0x0000ffff
#ifdef CONFIG_MLX5_ESWITCH
-int mlx5e_tc_init(struct mlx5e_priv *priv);
-void mlx5e_tc_cleanup(struct mlx5e_priv *priv);
+
+enum {
+ MLX5E_TC_INGRESS = BIT(0),
+ MLX5E_TC_EGRESS = BIT(1),
+ MLX5E_TC_LAST_EXPORTED_BIT = 1,
+};
+
+int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
+void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
+
+int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
+void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
int mlx5e_configure_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f);
+ struct tc_cls_flower_offload *f, int flags);
int mlx5e_delete_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f);
+ struct tc_cls_flower_offload *f, int flags);
int mlx5e_stats_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *f);
+ struct tc_cls_flower_offload *f, int flags);
struct mlx5e_encap_entry;
void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
}
#else /* CONFIG_MLX5_ESWITCH */
-static inline int mlx5e_tc_init(struct mlx5e_priv *priv) { return 0; }
-static inline void mlx5e_tc_cleanup(struct mlx5e_priv *priv) {}
+static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; }
#endif
#include <net/dsfield.h>
#include "en.h"
#include "ipoib/ipoib.h"
-#include "en_accel/ipsec_rxtx.h"
+#include "en_accel/en_accel.h"
#include "lib/clock.h"
#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS
+
+#ifndef CONFIG_MLX5_EN_TLS
#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
MLX5E_SQ_NOPS_ROOM)
+#else
+/* TLS offload requires MLX5E_SQ_STOP_ROOM to have
+ * enough room for a resync SKB, a normal SKB and a NOP
+ */
+#define MLX5E_SQ_STOP_ROOM (2 * MLX5_SEND_WQE_MAX_WQEBBS +\
+ MLX5E_SQ_NOPS_ROOM)
+#endif
static inline void mlx5e_tx_dma_unmap(struct device *pdev,
struct mlx5e_sq_dma *dma)
dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
- return -ENOMEM;
+ goto dma_unmap_wqe_err;
dseg->addr = cpu_to_be64(dma_addr);
dseg->lkey = sq->mkey_be;
dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
- return -ENOMEM;
+ goto dma_unmap_wqe_err;
dseg->addr = cpu_to_be64(dma_addr);
dseg->lkey = sq->mkey_be;
}
return num_dma;
+
+dma_unmap_wqe_err:
+ mlx5e_dma_unmap_wqe_err(sq, num_dma);
+ return -ENOMEM;
}
static inline void
}
}
-static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
- struct mlx5e_tx_wqe *wqe, u16 pi)
+netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+ struct mlx5e_tx_wqe *wqe, u16 pi)
{
struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
(struct mlx5_wqe_data_seg *)cseg + ds_cnt);
if (unlikely(num_dma < 0))
- goto dma_unmap_wqe_err;
+ goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
num_bytes, num_dma, wi, cseg);
return NETDEV_TX_OK;
-dma_unmap_wqe_err:
+err_drop:
sq->stats.dropped++;
- mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)];
- struct mlx5_wq_cyc *wq = &sq->wq;
- u16 pi = sq->pc & wq->sz_m1;
- struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+ struct mlx5e_tx_wqe *wqe;
+ struct mlx5e_txqsq *sq;
+ u16 pi;
- memset(wqe, 0, sizeof(*wqe));
+ sq = priv->txq2sq[skb_get_queue_mapping(skb)];
+ mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
-#ifdef CONFIG_MLX5_EN_IPSEC
- if (sq->state & BIT(MLX5E_SQ_STATE_IPSEC)) {
- skb = mlx5e_ipsec_handle_tx_skb(dev, wqe, skb);
- if (unlikely(!skb))
- return NETDEV_TX_OK;
- }
+#ifdef CONFIG_MLX5_ACCEL
+ /* might send skbs and update wqe and pi */
+ skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
+ if (unlikely(!skb))
+ return NETDEV_TX_OK;
#endif
-
return mlx5e_sq_xmit(sq, skb, wqe, pi);
}
sq = container_of(cq, struct mlx5e_txqsq, cq);
- if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+ if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
return false;
cqe = mlx5_cqwq_get_cqe(&cq->wq);
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
(struct mlx5_wqe_data_seg *)cseg + ds_cnt);
if (unlikely(num_dma < 0))
- goto dma_unmap_wqe_err;
+ goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
num_bytes, num_dma, wi, cseg);
return NETDEV_TX_OK;
-dma_unmap_wqe_err:
+err_drop:
sq->stats.dropped++;
- mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
return cpumask_test_cpu(current_cpu, aff);
}
+static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
+{
+ struct net_dim_sample dim_sample;
+
+ if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state)))
+ return;
+
+ net_dim_sample(sq->cq.event_ctr, sq->stats.packets, sq->stats.bytes,
+ &dim_sample);
+ net_dim(&sq->dim, dim_sample);
+}
+
+static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
+{
+ struct net_dim_sample dim_sample;
+
+ if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state)))
+ return;
+
+ net_dim_sample(rq->cq.event_ctr, rq->stats.packets, rq->stats.bytes,
+ &dim_sample);
+ net_dim(&rq->dim, dim_sample);
+}
+
int mlx5e_napi_poll(struct napi_struct *napi, int budget)
{
struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
if (unlikely(!napi_complete_done(napi, work_done)))
return work_done;
- for (i = 0; i < c->num_tc; i++)
+ for (i = 0; i < c->num_tc; i++) {
+ mlx5e_handle_tx_dim(&c->sq[i]);
mlx5e_cq_arm(&c->sq[i].cq);
-
- if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM)) {
- struct net_dim_sample dim_sample;
- net_dim_sample(c->rq.cq.event_ctr,
- c->rq.stats.packets,
- c->rq.stats.bytes,
- &dim_sample);
- net_dim(&c->rq.dim, dim_sample);
}
+ mlx5e_handle_rx_dim(&c->rq);
+
mlx5e_cq_arm(&c->rq.cq);
mlx5e_cq_arm(&c->icosq.cq);
#include <linux/module.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
#include "mlx5_core.h"
#include "fpga/core.h"
#include "eswitch.h"
MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
}
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_table *table = &dev->priv.eq_table;
+ struct mlx5_eq *eq;
+
+#ifdef CONFIG_RFS_ACCEL
+ if (dev->rmap) {
+ free_irq_cpu_rmap(dev->rmap);
+ dev->rmap = NULL;
+ }
+#endif
+ list_for_each_entry(eq, &table->comp_eqs_list, list)
+ free_irq(eq->irqn, eq);
+
+ free_irq(table->pages_eq.irqn, &table->pages_eq);
+ free_irq(table->async_eq.irqn, &table->async_eq);
+ free_irq(table->cmd_eq.irqn, &table->cmd_eq);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+ if (MLX5_CAP_GEN(dev, pg))
+ free_irq(table->pfault_eq.irqn, &table->pfault_eq);
+#endif
+ pci_free_irq_vectors(dev->pdev);
+}
}
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = vport;
+ dest.vport.num = vport;
esw_debug(esw->dev,
"\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n",
memset(vf_stats, 0, sizeof(*vf_stats));
vf_stats->rx_packets =
MLX5_GET_CTR(out, received_eth_unicast.packets) +
+ MLX5_GET_CTR(out, received_ib_unicast.packets) +
MLX5_GET_CTR(out, received_eth_multicast.packets) +
+ MLX5_GET_CTR(out, received_ib_multicast.packets) +
MLX5_GET_CTR(out, received_eth_broadcast.packets);
vf_stats->rx_bytes =
MLX5_GET_CTR(out, received_eth_unicast.octets) +
+ MLX5_GET_CTR(out, received_ib_unicast.octets) +
MLX5_GET_CTR(out, received_eth_multicast.octets) +
+ MLX5_GET_CTR(out, received_ib_multicast.octets) +
MLX5_GET_CTR(out, received_eth_broadcast.octets);
vf_stats->tx_packets =
MLX5_GET_CTR(out, transmitted_eth_unicast.packets) +
+ MLX5_GET_CTR(out, transmitted_ib_unicast.packets) +
MLX5_GET_CTR(out, transmitted_eth_multicast.packets) +
+ MLX5_GET_CTR(out, transmitted_ib_multicast.packets) +
MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
vf_stats->tx_bytes =
MLX5_GET_CTR(out, transmitted_eth_unicast.octets) +
+ MLX5_GET_CTR(out, transmitted_ib_unicast.octets) +
MLX5_GET_CTR(out, transmitted_eth_multicast.octets) +
+ MLX5_GET_CTR(out, transmitted_ib_multicast.octets) +
MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
vf_stats->multicast =
- MLX5_GET_CTR(out, received_eth_multicast.packets);
+ MLX5_GET_CTR(out, received_eth_multicast.packets) +
+ MLX5_GET_CTR(out, received_ib_multicast.packets);
vf_stats->broadcast =
MLX5_GET_CTR(out, received_eth_broadcast.packets);
SET_VLAN_INSERT = BIT(1)
};
+enum mlx5_flow_match_level {
+ MLX5_MATCH_NONE = MLX5_INLINE_MODE_NONE,
+ MLX5_MATCH_L2 = MLX5_INLINE_MODE_L2,
+ MLX5_MATCH_L3 = MLX5_INLINE_MODE_IP,
+ MLX5_MATCH_L4 = MLX5_INLINE_MODE_TCP_UDP,
+};
+
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_eswitch_rep *out_rep;
+ struct mlx5_core_dev *out_mdev;
+ struct mlx5_core_dev *in_mdev;
int action;
__be16 vlan_proto;
bool vlan_handled;
u32 encap_id;
u32 mod_hdr_id;
+ u8 match_level;
struct mlx5e_tc_flow_parse_attr *parse_attr;
};
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest[i].vport_num = attr->out_rep->vport;
+ dest[i].vport.num = attr->out_rep->vport;
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+ dest[i].vport.vhca_id =
+ MLX5_CAP_GEN(attr->out_mdev, vhca_id);
+ dest[i].vport.vhca_id_valid = 1;
+ }
i++;
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id,
+ MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+
+ if (attr->match_level == MLX5_MATCH_NONE)
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ else
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
+ MLX5_MATCH_MISC_PARAMETERS;
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
- MLX5_MATCH_MISC_PARAMETERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = vport;
+ dest.vport.num = vport;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
dmac_c[0] = 0x01;
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = 0;
+ dest.vport.num = 0;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
esw->offloads.vport_rx_group = g;
out:
- kfree(flow_group_in);
+ kvfree(flow_group_in);
return err;
}
} conn_res;
struct mlx5_fpga_ipsec *ipsec;
+ struct mlx5_fpga_tls *tls;
};
#define mlx5_fpga_dbg(__adev, format, ...) \
#include "fpga/sdk.h"
#include "fpga/core.h"
-#define SBU_QP_QUEUE_SIZE 8
-#define MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC (60 * 1000)
-
enum mlx5_fpga_ipsec_cmd_status {
MLX5_FPGA_IPSEC_CMD_PENDING,
MLX5_FPGA_IPSEC_CMD_SEND_FAIL,
{
struct mlx5_fpga_ipsec_cmd_context *context = ctx;
unsigned long timeout =
- msecs_to_jiffies(MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC);
+ msecs_to_jiffies(MLX5_FPGA_CMD_TIMEOUT_MSEC);
int res;
res = wait_for_completion_timeout(&context->complete, timeout);
* DOC: Innova SDK
* This header defines the in-kernel API for Innova FPGA client drivers.
*/
+#define SBU_QP_QUEUE_SIZE 8
+#define MLX5_FPGA_CMD_TIMEOUT_MSEC (60 * 1000)
enum mlx5_fpga_access_type {
MLX5_FPGA_ACCESS_TYPE_I2C = 0x0,
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/mlx5/device.h>
+#include "fpga/tls.h"
+#include "fpga/cmd.h"
+#include "fpga/sdk.h"
+#include "fpga/core.h"
+#include "accel/tls.h"
+
+struct mlx5_fpga_tls_command_context;
+
+typedef void (*mlx5_fpga_tls_command_complete)
+ (struct mlx5_fpga_conn *conn, struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_tls_command_context *ctx,
+ struct mlx5_fpga_dma_buf *resp);
+
+struct mlx5_fpga_tls_command_context {
+ struct list_head list;
+ /* There is no guarantee on the order between the TX completion
+ * and the command response.
+ * The TX completion is going to touch cmd->buf even in
+ * the case of successful transmission.
+ * So instead of requiring separate allocations for cmd
+ * and cmd->buf we've decided to use a reference counter
+ */
+ refcount_t ref;
+ struct mlx5_fpga_dma_buf buf;
+ mlx5_fpga_tls_command_complete complete;
+};
+
+static void
+mlx5_fpga_tls_put_command_ctx(struct mlx5_fpga_tls_command_context *ctx)
+{
+ if (refcount_dec_and_test(&ctx->ref))
+ kfree(ctx);
+}
+
+static void mlx5_fpga_tls_cmd_complete(struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_dma_buf *resp)
+{
+ struct mlx5_fpga_conn *conn = fdev->tls->conn;
+ struct mlx5_fpga_tls_command_context *ctx;
+ struct mlx5_fpga_tls *tls = fdev->tls;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tls->pending_cmds_lock, flags);
+ ctx = list_first_entry(&tls->pending_cmds,
+ struct mlx5_fpga_tls_command_context, list);
+ list_del(&ctx->list);
+ spin_unlock_irqrestore(&tls->pending_cmds_lock, flags);
+ ctx->complete(conn, fdev, ctx, resp);
+}
+
+static void mlx5_fpga_cmd_send_complete(struct mlx5_fpga_conn *conn,
+ struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_dma_buf *buf,
+ u8 status)
+{
+ struct mlx5_fpga_tls_command_context *ctx =
+ container_of(buf, struct mlx5_fpga_tls_command_context, buf);
+
+ mlx5_fpga_tls_put_command_ctx(ctx);
+
+ if (unlikely(status))
+ mlx5_fpga_tls_cmd_complete(fdev, NULL);
+}
+
+static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_tls_command_context *cmd,
+ mlx5_fpga_tls_command_complete complete)
+{
+ struct mlx5_fpga_tls *tls = fdev->tls;
+ unsigned long flags;
+ int ret;
+
+ refcount_set(&cmd->ref, 2);
+ cmd->complete = complete;
+ cmd->buf.complete = mlx5_fpga_cmd_send_complete;
+
+ spin_lock_irqsave(&tls->pending_cmds_lock, flags);
+ /* mlx5_fpga_sbu_conn_sendmsg is called under pending_cmds_lock
+ * to make sure commands are inserted to the tls->pending_cmds list
+ * and the command QP in the same order.
+ */
+ ret = mlx5_fpga_sbu_conn_sendmsg(tls->conn, &cmd->buf);
+ if (likely(!ret))
+ list_add_tail(&cmd->list, &tls->pending_cmds);
+ else
+ complete(tls->conn, fdev, cmd, NULL);
+ spin_unlock_irqrestore(&tls->pending_cmds_lock, flags);
+}
+
+/* Start of context identifiers range (inclusive) */
+#define SWID_START 0
+/* End of context identifiers range (exclusive) */
+#define SWID_END BIT(24)
+
+static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
+ void *ptr)
+{
+ int ret;
+
+ /* TLS metadata format is 1 byte for syndrome followed
+ * by 3 bytes of swid (software ID)
+ * swid must not exceed 3 bytes.
+ * See tls_rxtx.c:insert_pet() for details
+ */
+ BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_irq(idr_spinlock);
+ ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
+ spin_unlock_irq(idr_spinlock);
+ idr_preload_end();
+
+ return ret;
+}
+
+static void mlx5_fpga_tls_release_swid(struct idr *idr,
+ spinlock_t *idr_spinlock, u32 swid)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(idr_spinlock, flags);
+ idr_remove(idr, swid);
+ spin_unlock_irqrestore(idr_spinlock, flags);
+}
+
+struct mlx5_teardown_stream_context {
+ struct mlx5_fpga_tls_command_context cmd;
+ u32 swid;
+};
+
+static void
+mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
+ struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_tls_command_context *cmd,
+ struct mlx5_fpga_dma_buf *resp)
+{
+ struct mlx5_teardown_stream_context *ctx =
+ container_of(cmd, struct mlx5_teardown_stream_context, cmd);
+
+ if (resp) {
+ u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
+
+ if (syndrome)
+ mlx5_fpga_err(fdev,
+ "Teardown stream failed with syndrome = %d",
+ syndrome);
+ else
+ mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
+ &fdev->tls->idr_spinlock,
+ ctx->swid);
+ }
+ mlx5_fpga_tls_put_command_ctx(cmd);
+}
+
+static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
+{
+ memcpy(MLX5_ADDR_OF(tls_cmd, cmd, src_port), flow,
+ MLX5_BYTE_OFF(tls_flow, ipv6));
+
+ MLX5_SET(tls_cmd, cmd, ipv6, MLX5_GET(tls_flow, flow, ipv6));
+ MLX5_SET(tls_cmd, cmd, direction_sx,
+ MLX5_GET(tls_flow, flow, direction_sx));
+}
+
+void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, void *flow,
+ u32 swid, gfp_t flags)
+{
+ struct mlx5_teardown_stream_context *ctx;
+ struct mlx5_fpga_dma_buf *buf;
+ void *cmd;
+
+ ctx = kzalloc(sizeof(*ctx) + MLX5_TLS_COMMAND_SIZE, flags);
+ if (!ctx)
+ return;
+
+ buf = &ctx->cmd.buf;
+ cmd = (ctx + 1);
+ MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
+ MLX5_SET(tls_cmd, cmd, swid, swid);
+
+ mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+ kfree(flow);
+
+ buf->sg[0].data = cmd;
+ buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+
+ ctx->swid = swid;
+ mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+ mlx5_fpga_tls_teardown_completion);
+}
+
+void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
+ gfp_t flags)
+{
+ struct mlx5_fpga_tls *tls = mdev->fpga->tls;
+ void *flow;
+
+ rcu_read_lock();
+ flow = idr_find(&tls->tx_idr, swid);
+ rcu_read_unlock();
+
+ if (!flow) {
+ mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
+ swid);
+ return;
+ }
+
+ mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
+}
+
+enum mlx5_fpga_setup_stream_status {
+ MLX5_FPGA_CMD_PENDING,
+ MLX5_FPGA_CMD_SEND_FAILED,
+ MLX5_FPGA_CMD_RESPONSE_RECEIVED,
+ MLX5_FPGA_CMD_ABANDONED,
+};
+
+struct mlx5_setup_stream_context {
+ struct mlx5_fpga_tls_command_context cmd;
+ atomic_t status;
+ u32 syndrome;
+ struct completion comp;
+};
+
+static void
+mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn,
+ struct mlx5_fpga_device *fdev,
+ struct mlx5_fpga_tls_command_context *cmd,
+ struct mlx5_fpga_dma_buf *resp)
+{
+ struct mlx5_setup_stream_context *ctx =
+ container_of(cmd, struct mlx5_setup_stream_context, cmd);
+ int status = MLX5_FPGA_CMD_SEND_FAILED;
+ void *tls_cmd = ctx + 1;
+
+ /* If we failed to send to command resp == NULL */
+ if (resp) {
+ ctx->syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
+ status = MLX5_FPGA_CMD_RESPONSE_RECEIVED;
+ }
+
+ status = atomic_xchg_release(&ctx->status, status);
+ if (likely(status != MLX5_FPGA_CMD_ABANDONED)) {
+ complete(&ctx->comp);
+ return;
+ }
+
+ mlx5_fpga_err(fdev, "Command was abandoned, syndrome = %u\n",
+ ctx->syndrome);
+
+ if (!ctx->syndrome) {
+ /* The process was killed while waiting for the context to be
+ * added, and the add completed successfully.
+ * We need to destroy the HW context, and we can't can't reuse
+ * the command context because we might not have received
+ * the tx completion yet.
+ */
+ mlx5_fpga_tls_del_tx_flow(fdev->mdev,
+ MLX5_GET(tls_cmd, tls_cmd, swid),
+ GFP_ATOMIC);
+ }
+
+ mlx5_fpga_tls_put_command_ctx(cmd);
+}
+
+static int mlx5_fpga_tls_setup_stream_cmd(struct mlx5_core_dev *mdev,
+ struct mlx5_setup_stream_context *ctx)
+{
+ struct mlx5_fpga_dma_buf *buf;
+ void *cmd = ctx + 1;
+ int status, ret = 0;
+
+ buf = &ctx->cmd.buf;
+ buf->sg[0].data = cmd;
+ buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+ MLX5_SET(tls_cmd, cmd, command_type, CMD_SETUP_STREAM);
+
+ init_completion(&ctx->comp);
+ atomic_set(&ctx->status, MLX5_FPGA_CMD_PENDING);
+ ctx->syndrome = -1;
+
+ mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+ mlx5_fpga_tls_setup_completion);
+ wait_for_completion_killable(&ctx->comp);
+
+ status = atomic_xchg_acquire(&ctx->status, MLX5_FPGA_CMD_ABANDONED);
+ if (unlikely(status == MLX5_FPGA_CMD_PENDING))
+ /* ctx is going to be released in mlx5_fpga_tls_setup_completion */
+ return -EINTR;
+
+ if (unlikely(ctx->syndrome))
+ ret = -ENOMEM;
+
+ mlx5_fpga_tls_put_command_ctx(&ctx->cmd);
+ return ret;
+}
+
+static void mlx5_fpga_tls_hw_qp_recv_cb(void *cb_arg,
+ struct mlx5_fpga_dma_buf *buf)
+{
+ struct mlx5_fpga_device *fdev = (struct mlx5_fpga_device *)cb_arg;
+
+ mlx5_fpga_tls_cmd_complete(fdev, buf);
+}
+
+bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev)
+{
+ if (!mdev->fpga || !MLX5_CAP_GEN(mdev, fpga))
+ return false;
+
+ if (MLX5_CAP_FPGA(mdev, ieee_vendor_id) !=
+ MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX)
+ return false;
+
+ if (MLX5_CAP_FPGA(mdev, sandbox_product_id) !=
+ MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS)
+ return false;
+
+ if (MLX5_CAP_FPGA(mdev, sandbox_product_version) != 0)
+ return false;
+
+ return true;
+}
+
+static int mlx5_fpga_tls_get_caps(struct mlx5_fpga_device *fdev,
+ u32 *p_caps)
+{
+ int err, cap_size = MLX5_ST_SZ_BYTES(tls_extended_cap);
+ u32 caps = 0;
+ void *buf;
+
+ buf = kzalloc(cap_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ err = mlx5_fpga_get_sbu_caps(fdev, cap_size, buf);
+ if (err)
+ goto out;
+
+ if (MLX5_GET(tls_extended_cap, buf, tx))
+ caps |= MLX5_ACCEL_TLS_TX;
+ if (MLX5_GET(tls_extended_cap, buf, rx))
+ caps |= MLX5_ACCEL_TLS_RX;
+ if (MLX5_GET(tls_extended_cap, buf, tls_v12))
+ caps |= MLX5_ACCEL_TLS_V12;
+ if (MLX5_GET(tls_extended_cap, buf, tls_v13))
+ caps |= MLX5_ACCEL_TLS_V13;
+ if (MLX5_GET(tls_extended_cap, buf, lro))
+ caps |= MLX5_ACCEL_TLS_LRO;
+ if (MLX5_GET(tls_extended_cap, buf, ipv6))
+ caps |= MLX5_ACCEL_TLS_IPV6;
+
+ if (MLX5_GET(tls_extended_cap, buf, aes_gcm_128))
+ caps |= MLX5_ACCEL_TLS_AES_GCM128;
+ if (MLX5_GET(tls_extended_cap, buf, aes_gcm_256))
+ caps |= MLX5_ACCEL_TLS_AES_GCM256;
+
+ *p_caps = caps;
+ err = 0;
+out:
+ kfree(buf);
+ return err;
+}
+
+int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
+{
+ struct mlx5_fpga_device *fdev = mdev->fpga;
+ struct mlx5_fpga_conn_attr init_attr = {0};
+ struct mlx5_fpga_conn *conn;
+ struct mlx5_fpga_tls *tls;
+ int err = 0;
+
+ if (!mlx5_fpga_is_tls_device(mdev) || !fdev)
+ return 0;
+
+ tls = kzalloc(sizeof(*tls), GFP_KERNEL);
+ if (!tls)
+ return -ENOMEM;
+
+ err = mlx5_fpga_tls_get_caps(fdev, &tls->caps);
+ if (err)
+ goto error;
+
+ if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 |
+ MLX5_ACCEL_TLS_AES_GCM128))) {
+ err = -ENOTSUPP;
+ goto error;
+ }
+
+ init_attr.rx_size = SBU_QP_QUEUE_SIZE;
+ init_attr.tx_size = SBU_QP_QUEUE_SIZE;
+ init_attr.recv_cb = mlx5_fpga_tls_hw_qp_recv_cb;
+ init_attr.cb_arg = fdev;
+ conn = mlx5_fpga_sbu_conn_create(fdev, &init_attr);
+ if (IS_ERR(conn)) {
+ err = PTR_ERR(conn);
+ mlx5_fpga_err(fdev, "Error creating TLS command connection %d\n",
+ err);
+ goto error;
+ }
+
+ tls->conn = conn;
+ spin_lock_init(&tls->pending_cmds_lock);
+ INIT_LIST_HEAD(&tls->pending_cmds);
+
+ idr_init(&tls->tx_idr);
+ spin_lock_init(&tls->idr_spinlock);
+ fdev->tls = tls;
+ return 0;
+
+error:
+ kfree(tls);
+ return err;
+}
+
+void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev)
+{
+ struct mlx5_fpga_device *fdev = mdev->fpga;
+
+ if (!fdev || !fdev->tls)
+ return;
+
+ mlx5_fpga_sbu_conn_destroy(fdev->tls->conn);
+ kfree(fdev->tls);
+ fdev->tls = NULL;
+}
+
+static void mlx5_fpga_tls_set_aes_gcm128_ctx(void *cmd,
+ struct tls_crypto_info *info,
+ __be64 *rcd_sn)
+{
+ struct tls12_crypto_info_aes_gcm_128 *crypto_info =
+ (struct tls12_crypto_info_aes_gcm_128 *)info;
+
+ memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_rcd_sn), crypto_info->rec_seq,
+ TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
+
+ memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_implicit_iv),
+ crypto_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+ memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key),
+ crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
+
+ /* in AES-GCM 128 we need to write the key twice */
+ memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key) +
+ TLS_CIPHER_AES_GCM_128_KEY_SIZE,
+ crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
+
+ MLX5_SET(tls_cmd, cmd, alg, MLX5_TLS_ALG_AES_GCM_128);
+}
+
+static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps,
+ struct tls_crypto_info *crypto_info)
+{
+ __be64 rcd_sn;
+
+ switch (crypto_info->cipher_type) {
+ case TLS_CIPHER_AES_GCM_128:
+ if (!(caps & MLX5_ACCEL_TLS_AES_GCM128))
+ return -EINVAL;
+ mlx5_fpga_tls_set_aes_gcm128_ctx(cmd, crypto_info, &rcd_sn);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info, u32 swid,
+ u32 tcp_sn)
+{
+ u32 caps = mlx5_fpga_tls_device_caps(mdev);
+ struct mlx5_setup_stream_context *ctx;
+ int ret = -ENOMEM;
+ size_t cmd_size;
+ void *cmd;
+
+ cmd_size = MLX5_TLS_COMMAND_SIZE + sizeof(*ctx);
+ ctx = kzalloc(cmd_size, GFP_KERNEL);
+ if (!ctx)
+ goto out;
+
+ cmd = ctx + 1;
+ ret = mlx5_fpga_tls_set_key_material(cmd, caps, crypto_info);
+ if (ret)
+ goto free_ctx;
+
+ mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+
+ MLX5_SET(tls_cmd, cmd, swid, swid);
+ MLX5_SET(tls_cmd, cmd, tcp_sn, tcp_sn);
+
+ return mlx5_fpga_tls_setup_stream_cmd(mdev, ctx);
+
+free_ctx:
+ kfree(ctx);
+out:
+ return ret;
+}
+
+int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid)
+{
+ struct mlx5_fpga_tls *tls = mdev->fpga->tls;
+ int ret = -ENOMEM;
+ u32 swid;
+
+ ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow);
+ if (ret < 0)
+ return ret;
+
+ swid = ret;
+ MLX5_SET(tls_flow, flow, direction_sx, 1);
+
+ ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
+ start_offload_tcp_sn);
+ if (ret && ret != -EINTR)
+ goto free_swid;
+
+ *p_swid = swid;
+ return 0;
+free_swid:
+ mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid);
+
+ return ret;
+}
--- /dev/null
+/*
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef __MLX5_FPGA_TLS_H__
+#define __MLX5_FPGA_TLS_H__
+
+#include <linux/mlx5/driver.h>
+
+#include <net/tls.h>
+#include "fpga/core.h"
+
+struct mlx5_fpga_tls {
+ struct list_head pending_cmds;
+ spinlock_t pending_cmds_lock; /* Protects pending_cmds */
+ u32 caps;
+ struct mlx5_fpga_conn *conn;
+
+ struct idr tx_idr;
+ spinlock_t idr_spinlock; /* protects the IDR */
+};
+
+int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn, u32 *p_swid);
+
+void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
+ gfp_t flags);
+
+bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
+int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
+void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev);
+
+static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
+{
+ return mdev->fpga->tls->caps;
+}
+
+#endif /* __MLX5_FPGA_TLS_H__ */
if (dst->dest_attr.type ==
MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) {
id = dst->dest_attr.ft->id;
+ } else if (dst->dest_attr.type ==
+ MLX5_FLOW_DESTINATION_TYPE_VPORT) {
+ id = dst->dest_attr.vport.num;
+ MLX5_SET(dest_format_struct, in_dests,
+ destination_eswitch_owner_vhca_id_valid,
+ dst->dest_attr.vport.vhca_id_valid);
+ MLX5_SET(dest_format_struct, in_dests,
+ destination_eswitch_owner_vhca_id,
+ dst->dest_attr.vport.vhca_id);
} else {
id = dst->dest_attr.tir_num;
}
static void del_sw_hw_rule(struct fs_node *node);
static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
struct mlx5_flow_destination *d2);
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);
static struct mlx5_flow_rule *
find_flow_rule(struct fs_fte *fte,
struct mlx5_flow_destination *dest);
if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER &&
--fte->dests_size) {
- modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+ BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
update_fte = true;
goto out;
struct mlx5_core_dev *dev = get_dev(&ft->node);
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
void *match_criteria_addr;
+ u8 src_esw_owner_mask_on;
+ void *misc;
int err;
u32 *in;
MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index);
MLX5_SET(create_flow_group_in, in, end_flow_index, fg->start_index +
fg->max_ftes - 1);
+
+ misc = MLX5_ADDR_OF(fte_match_param, fg->mask.match_criteria,
+ misc_parameters);
+ src_esw_owner_mask_on = !!MLX5_GET(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+ MLX5_SET(create_flow_group_in, in,
+ source_eswitch_owner_vhca_id_valid, src_esw_owner_mask_on);
+
match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in,
in, match_criteria);
memcpy(match_criteria_addr, fg->mask.match_criteria,
{
if (d1->type == d2->type) {
if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
- d1->vport_num == d2->vport_num) ||
+ d1->vport.num == d2->vport.num) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
d1->ft == d2->ft) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
static int init_root_ns(struct mlx5_flow_steering *steering)
{
+ int err;
+
steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
if (!steering->root_ns)
- goto cleanup;
+ return -ENOMEM;
- if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
- goto cleanup;
+ err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node);
+ if (err)
+ goto out_err;
set_prio_attrs(steering->root_ns);
-
- if (create_anchor_flow_table(steering))
- goto cleanup;
+ err = create_anchor_flow_table(steering);
+ if (err)
+ goto out_err;
return 0;
-cleanup:
- mlx5_cleanup_fs(steering->dev);
- return -ENOMEM;
+out_err:
+ cleanup_root_ns(steering->root_ns);
+ steering->root_ns = NULL;
+ return err;
}
static void clean_tree(struct fs_node *node)
#include "fpga/core.h"
#include "fpga/ipsec.h"
#include "accel/ipsec.h"
+#include "accel/tls.h"
#include "lib/clock.h"
MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
goto err_ipsec_start;
}
+ err = mlx5_accel_tls_init(dev);
+ if (err) {
+ dev_err(&pdev->dev, "TLS device start failed %d\n", err);
+ goto err_tls_start;
+ }
+
err = mlx5_init_fs(dev);
if (err) {
dev_err(&pdev->dev, "Failed to init flow steering\n");
mlx5_cleanup_fs(dev);
err_fs:
+ mlx5_accel_tls_cleanup(dev);
+
+err_tls_start:
mlx5_accel_ipsec_cleanup(dev);
err_ipsec_start:
mlx5_sriov_detach(dev);
mlx5_cleanup_fs(dev);
mlx5_accel_ipsec_cleanup(dev);
+ mlx5_accel_tls_cleanup(dev);
mlx5_fpga_device_stop(dev);
mlx5_irq_clear_affinity_hints(dev);
free_comp_eqs(dev);
mlx5_enter_error_state(dev, true);
+ /* Some platforms requiring freeing the IRQ's in the shutdown
+ * flow. If they aren't freed they can't be allocated after
+ * kexec. There is no need to cleanup the mlx5_core software
+ * contexts.
+ */
+ mlx5_irq_clear_affinity_hints(dev);
+ mlx5_core_eq_free_irqs(dev);
+
return 0;
}
u32 *out, int outlen);
int mlx5_start_eqs(struct mlx5_core_dev *dev);
void mlx5_stop_eqs(struct mlx5_core_dev *dev);
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
void mlx5_cq_tasklet_cb(unsigned long data);
deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key));
write_unlock_irqrestore(&table->lock, flags);
if (!deleted_mkey) {
- mlx5_core_warn(dev, "failed radix tree delete of mkey 0x%x\n",
- mlx5_base_mkey(mkey->key));
+ mlx5_core_dbg(dev, "failed radix tree delete of mkey 0x%x\n",
+ mlx5_base_mkey(mkey->key));
return -ENOENT;
}
case MLX5_CMD_OP_RST2INIT_QP:
if (MBOX_ALLOC(mbox, rst2init_qp))
return -ENOMEM;
- MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
- opt_param_mask, qpc);
- break;
+ MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn,
+ opt_param_mask, qpc);
+ break;
case MLX5_CMD_OP_INIT2RTR_QP:
if (MBOX_ALLOC(mbox, init2rtr_qp))
return -ENOMEM;
- MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn,
- opt_param_mask, qpc);
- break;
+ MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn,
+ opt_param_mask, qpc);
+ break;
case MLX5_CMD_OP_RTR2RTS_QP:
if (MBOX_ALLOC(mbox, rtr2rts_qp))
return -ENOMEM;
- MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn,
- opt_param_mask, qpc);
- break;
+ MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn,
+ opt_param_mask, qpc);
+ break;
case MLX5_CMD_OP_RTS2RTS_QP:
if (MBOX_ALLOC(mbox, rts2rts_qp))
return -ENOMEM;
*system_image_guid = MLX5_GET64(query_nic_vport_context_out, out,
nic_vport_context.system_image_guid);
- kfree(out);
+ kvfree(out);
return 0;
}
*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
nic_vport_context.node_guid);
- kfree(out);
+ kvfree(out);
return 0;
}
*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
nic_vport_context.qkey_violation_counter);
- kfree(out);
+ kvfree(out);
return 0;
}
#include <linux/mlx5/qp.h>
struct mlx5_wq_param {
- int linear;
int buf_numa_node;
int db_numa_node;
};
MLXSW_ITEM32(cmd_mbox, query_aq_cap, max_num_rdqs, 0x04, 0, 8);
/* cmd_mbox_query_aq_cap_log_max_cq_sz
- * Log (base 2) of max CQEs allowed on CQ.
+ * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv0 and CQEv1.
*/
MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cq_sz, 0x08, 24, 8);
+/* cmd_mbox_query_aq_cap_log_max_cqv2_sz
+ * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv2.
+ */
+MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cqv2_sz, 0x08, 16, 8);
+
/* cmd_mbox_query_aq_cap_max_num_cqs
* Maximum number of CQs.
*/
*/
MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1);
+/* cmd_mbox_config_set_cqe_version
+ * Capability bit. Setting a bit to 1 configures the profile
+ * according to the mailbox contents.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1);
+
/* cmd_mbox_config_profile_max_vepa_channels
* Maximum number of VEPA channels per port (0 through 16)
* 0 - multi-channel VEPA is disabled
MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_properties,
0x60, 0, 8, 0x08, 0x00, false);
+/* cmd_mbox_config_profile_cqe_version
+ * CQE version:
+ * 0: CQE version is 0
+ * 1: CQE version is either 1 or 2
+ * CQE ver 1 or 2 is configured by Completion Queue Context field cqe_ver.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, cqe_version, 0xB0, 0, 8);
+
/* ACCESS_REG - Access EMAD Supported Register
* ----------------------------------
* OpMod == 0 (N/A), INMmod == 0 (N/A)
0, cq_number, in_mbox, MLXSW_CMD_MBOX_SIZE);
}
-/* cmd_mbox_sw2hw_cq_cv
+enum mlxsw_cmd_mbox_sw2hw_cq_cqe_ver {
+ MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1,
+ MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2,
+};
+
+/* cmd_mbox_sw2hw_cq_cqe_ver
* CQE Version.
- * 0 - CQE Version 0, 1 - CQE Version 1
*/
-MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4);
+MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cqe_ver, 0x00, 28, 4);
/* cmd_mbox_sw2hw_cq_c_eqn
* Event Queue this CQ reports completion events to.
err_alloc_lag_mapping:
mlxsw_ports_fini(mlxsw_core);
err_ports_init:
- mlxsw_bus->fini(bus_priv);
-err_bus_init:
if (!reload)
devlink_resources_unregister(devlink, NULL);
err_register_resources:
+ mlxsw_bus->fini(bus_priv);
+err_bus_init:
if (!reload)
devlink_free(devlink);
err_devlink_alloc:
void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
void *port_driver_priv, struct net_device *dev,
- bool split, u32 split_group)
+ u32 port_number, bool split,
+ u32 split_port_subnumber)
{
struct mlxsw_core_port *mlxsw_core_port =
&mlxsw_core->ports[local_port];
struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
mlxsw_core_port->port_driver_priv = port_driver_priv;
- if (split)
- devlink_port_split_set(devlink_port, split_group);
+ devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
+ port_number, split, split_port_subnumber);
devlink_port_type_eth_set(devlink_port, dev);
}
EXPORT_SYMBOL(mlxsw_core_port_eth_set);
}
EXPORT_SYMBOL(mlxsw_core_port_type_get);
+int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core,
+ u8 local_port, char *name, size_t len)
+{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
+ struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+ return devlink_port_get_phys_port_name(devlink_port, name, len);
+}
+EXPORT_SYMBOL(mlxsw_core_port_get_phys_port_name);
+
static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core,
const char *buf, size_t size)
{
void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port);
void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
void *port_driver_priv, struct net_device *dev,
- bool split, u32 split_group);
+ u32 port_number, bool split,
+ u32 split_port_subnumber);
void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port,
void *port_driver_priv);
void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u8 local_port,
void *port_driver_priv);
enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
u8 local_port);
+int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core,
+ u8 local_port, char *name, size_t len);
int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
bool mlxsw_core_schedule_work(struct work_struct *work);
struct {
u32 comp_sdq_count;
u32 comp_rdq_count;
+ enum mlxsw_pci_cqe_v v;
} cq;
struct {
u32 ev_cmd_count;
} cmd;
struct mlxsw_bus_info bus_info;
const struct pci_device_id *id;
+ enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */
+ u8 num_sdq_cqs; /* Number of CQs used for SDQs */
};
static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
return owner_bit != !!(q->consumer_counter & q->count);
}
-static char *
-mlxsw_pci_queue_sw_elem_get(struct mlxsw_pci_queue *q,
- u32 (*get_elem_owner_func)(const char *))
-{
- struct mlxsw_pci_queue_elem_info *elem_info;
- char *elem;
- bool owner_bit;
-
- elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
- elem = elem_info->elem;
- owner_bit = get_elem_owner_func(elem);
- if (mlxsw_pci_elem_hw_owned(q, owner_bit))
- return NULL;
- q->consumer_counter++;
- rmb(); /* make sure we read owned bit before the rest of elem */
- return elem;
-}
-
static struct mlxsw_pci_queue_type_group *
mlxsw_pci_queue_type_group_get(struct mlxsw_pci *mlxsw_pci,
enum mlxsw_pci_queue_type q_type)
}
}
+static void mlxsw_pci_cq_pre_init(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q)
+{
+ q->u.cq.v = mlxsw_pci->max_cqe_ver;
+
+ /* For SDQ it is pointless to use CQEv2, so use CQEv1 instead */
+ if (q->u.cq.v == MLXSW_PCI_CQE_V2 &&
+ q->num < mlxsw_pci->num_sdq_cqs)
+ q->u.cq.v = MLXSW_PCI_CQE_V1;
+}
+
static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
struct mlxsw_pci_queue *q)
{
for (i = 0; i < q->count; i++) {
char *elem = mlxsw_pci_queue_elem_get(q, i);
- mlxsw_pci_cqe_owner_set(elem, 1);
+ mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1);
}
- mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */
+ if (q->u.cq.v == MLXSW_PCI_CQE_V1)
+ mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+ MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1);
+ else if (q->u.cq.v == MLXSW_PCI_CQE_V2)
+ mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+ MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2);
+
mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
struct mlxsw_pci_queue *q,
u16 consumer_counter_limit,
- char *cqe)
+ enum mlxsw_pci_cqe_v cqe_v, char *cqe)
{
struct pci_dev *pdev = mlxsw_pci->pdev;
struct mlxsw_pci_queue_elem_info *elem_info;
if (q->consumer_counter++ != consumer_counter_limit)
dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
- if (mlxsw_pci_cqe_lag_get(cqe)) {
+ if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
rx_info.is_lag = true;
- rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe);
- rx_info.lag_port_index = mlxsw_pci_cqe_lag_port_index_get(cqe);
+ rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
+ rx_info.lag_port_index =
+ mlxsw_pci_cqe_lag_subport_get(cqe_v, cqe);
} else {
rx_info.is_lag = false;
rx_info.u.sys_port = mlxsw_pci_cqe_system_port_get(cqe);
rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe);
byte_count = mlxsw_pci_cqe_byte_count_get(cqe);
- if (mlxsw_pci_cqe_crc_get(cqe))
+ if (mlxsw_pci_cqe_crc_get(cqe_v, cqe))
byte_count -= ETH_FCS_LEN;
skb_put(skb, byte_count);
mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q)
{
- return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_cqe_owner_get);
+ struct mlxsw_pci_queue_elem_info *elem_info;
+ char *elem;
+ bool owner_bit;
+
+ elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+ elem = elem_info->elem;
+ owner_bit = mlxsw_pci_cqe_owner_get(q->u.cq.v, elem);
+ if (mlxsw_pci_elem_hw_owned(q, owner_bit))
+ return NULL;
+ q->consumer_counter++;
+ rmb(); /* make sure we read owned bit before the rest of elem */
+ return elem;
}
static void mlxsw_pci_cq_tasklet(unsigned long data)
while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) {
u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
- u8 sendq = mlxsw_pci_cqe_sr_get(cqe);
- u8 dqn = mlxsw_pci_cqe_dqn_get(cqe);
+ u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
+ u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
if (sendq) {
struct mlxsw_pci_queue *sdq;
rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
- wqe_counter, cqe);
+ wqe_counter, q->u.cq.v, cqe);
q->u.cq.comp_rdq_count++;
}
if (++items == credits)
}
}
+static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
+{
+ return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT :
+ MLXSW_PCI_CQE01_COUNT;
+}
+
+static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q)
+{
+ return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE :
+ MLXSW_PCI_CQE01_SIZE;
+}
+
static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
struct mlxsw_pci_queue *q)
{
static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q)
{
- return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_eqe_owner_get);
+ struct mlxsw_pci_queue_elem_info *elem_info;
+ char *elem;
+ bool owner_bit;
+
+ elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+ elem = elem_info->elem;
+ owner_bit = mlxsw_pci_eqe_owner_get(elem);
+ if (mlxsw_pci_elem_hw_owned(q, owner_bit))
+ return NULL;
+ q->consumer_counter++;
+ rmb(); /* make sure we read owned bit before the rest of elem */
+ return elem;
}
static void mlxsw_pci_eq_tasklet(unsigned long data)
struct mlxsw_pci_queue_ops {
const char *name;
enum mlxsw_pci_queue_type type;
+ void (*pre_init)(struct mlxsw_pci *mlxsw_pci,
+ struct mlxsw_pci_queue *q);
int (*init)(struct mlxsw_pci *mlxsw_pci, char *mbox,
struct mlxsw_pci_queue *q);
void (*fini)(struct mlxsw_pci *mlxsw_pci,
struct mlxsw_pci_queue *q);
void (*tasklet)(unsigned long data);
+ u16 (*elem_count_f)(const struct mlxsw_pci_queue *q);
+ u8 (*elem_size_f)(const struct mlxsw_pci_queue *q);
u16 elem_count;
u8 elem_size;
};
static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
.type = MLXSW_PCI_QUEUE_TYPE_CQ,
+ .pre_init = mlxsw_pci_cq_pre_init,
.init = mlxsw_pci_cq_init,
.fini = mlxsw_pci_cq_fini,
.tasklet = mlxsw_pci_cq_tasklet,
- .elem_count = MLXSW_PCI_CQE_COUNT,
- .elem_size = MLXSW_PCI_CQE_SIZE
+ .elem_count_f = mlxsw_pci_cq_elem_count,
+ .elem_size_f = mlxsw_pci_cq_elem_size
};
static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
int i;
int err;
- spin_lock_init(&q->lock);
q->num = q_num;
- q->count = q_ops->elem_count;
- q->elem_size = q_ops->elem_size;
+ if (q_ops->pre_init)
+ q_ops->pre_init(mlxsw_pci, q);
+
+ spin_lock_init(&q->lock);
+ q->count = q_ops->elem_count_f ? q_ops->elem_count_f(q) :
+ q_ops->elem_count;
+ q->elem_size = q_ops->elem_size_f ? q_ops->elem_size_f(q) :
+ q_ops->elem_size;
q->type = q_ops->type;
q->pci = mlxsw_pci;
elem_info = mlxsw_pci_queue_elem_info_get(q, i);
elem_info->elem =
- __mlxsw_pci_queue_elem_get(q, q_ops->elem_size, i);
+ __mlxsw_pci_queue_elem_get(q, q->elem_size, i);
}
mlxsw_cmd_mbox_zero(mbox);
u8 rdq_log2sz;
u8 num_cqs;
u8 cq_log2sz;
+ u8 cqv2_log2sz;
u8 num_eqs;
u8 eq_log2sz;
int err;
rdq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_rdq_sz_get(mbox);
num_cqs = mlxsw_cmd_mbox_query_aq_cap_max_num_cqs_get(mbox);
cq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cq_sz_get(mbox);
+ cqv2_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cqv2_sz_get(mbox);
num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox);
eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox);
if ((1 << sdq_log2sz != MLXSW_PCI_WQE_COUNT) ||
(1 << rdq_log2sz != MLXSW_PCI_WQE_COUNT) ||
- (1 << cq_log2sz != MLXSW_PCI_CQE_COUNT) ||
+ (1 << cq_log2sz != MLXSW_PCI_CQE01_COUNT) ||
+ (mlxsw_pci->max_cqe_ver == MLXSW_PCI_CQE_V2 &&
+ (1 << cqv2_log2sz != MLXSW_PCI_CQE2_COUNT)) ||
(1 << eq_log2sz != MLXSW_PCI_EQE_COUNT)) {
dev_err(&pdev->dev, "Unsupported number of async queue descriptors\n");
return -EINVAL;
}
+ mlxsw_pci->num_sdq_cqs = num_sdqs;
+
err = mlxsw_pci_queue_group_init(mlxsw_pci, mbox, &mlxsw_pci_eq_ops,
num_eqs);
if (err) {
mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i,
&profile->swid_config[i]);
+ if (mlxsw_pci->max_cqe_ver > MLXSW_PCI_CQE_V0) {
+ mlxsw_cmd_mbox_config_profile_set_cqe_version_set(mbox, 1);
+ mlxsw_cmd_mbox_config_profile_cqe_version_set(mbox, 1);
+ }
+
return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox);
}
if (err)
goto err_query_resources;
+ if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V2) &&
+ MLXSW_CORE_RES_GET(mlxsw_core, CQE_V2))
+ mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V2;
+ else if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V1) &&
+ MLXSW_CORE_RES_GET(mlxsw_core, CQE_V1))
+ mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V1;
+ else if ((MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0) &&
+ MLXSW_CORE_RES_GET(mlxsw_core, CQE_V0)) ||
+ !MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0)) {
+ mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V0;
+ } else {
+ dev_err(&pdev->dev, "Invalid supported CQE version combination reported\n");
+ goto err_cqe_v_check;
+ }
+
err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile, res);
if (err)
goto err_config_profile;
mlxsw_pci_aqs_fini(mlxsw_pci);
err_aqs_init:
err_config_profile:
+err_cqe_v_check:
err_query_resources:
err_boardinfo:
mlxsw_pci_fw_area_fini(mlxsw_pci);
#define MLXSW_PCI_AQ_PAGES 8
#define MLXSW_PCI_AQ_SIZE (MLXSW_PCI_PAGE_SIZE * MLXSW_PCI_AQ_PAGES)
#define MLXSW_PCI_WQE_SIZE 32 /* 32 bytes per element */
-#define MLXSW_PCI_CQE_SIZE 16 /* 16 bytes per element */
+#define MLXSW_PCI_CQE01_SIZE 16 /* 16 bytes per element */
+#define MLXSW_PCI_CQE2_SIZE 32 /* 32 bytes per element */
#define MLXSW_PCI_EQE_SIZE 16 /* 16 bytes per element */
#define MLXSW_PCI_WQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE)
-#define MLXSW_PCI_CQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE_SIZE)
+#define MLXSW_PCI_CQE01_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE)
+#define MLXSW_PCI_CQE2_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE2_SIZE)
#define MLXSW_PCI_EQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_EQE_SIZE)
#define MLXSW_PCI_EQE_UPDATE_COUNT 0x80
*/
MLXSW_ITEM64_INDEXED(pci, wqe, address, 0x08, 0, 64, 0x8, 0x0, false);
+enum mlxsw_pci_cqe_v {
+ MLXSW_PCI_CQE_V0,
+ MLXSW_PCI_CQE_V1,
+ MLXSW_PCI_CQE_V2,
+};
+
+#define mlxsw_pci_cqe_item_helpers(name, v0, v1, v2) \
+static inline u32 mlxsw_pci_cqe_##name##_get(enum mlxsw_pci_cqe_v v, char *cqe) \
+{ \
+ switch (v) { \
+ default: \
+ case MLXSW_PCI_CQE_V0: \
+ return mlxsw_pci_cqe##v0##_##name##_get(cqe); \
+ case MLXSW_PCI_CQE_V1: \
+ return mlxsw_pci_cqe##v1##_##name##_get(cqe); \
+ case MLXSW_PCI_CQE_V2: \
+ return mlxsw_pci_cqe##v2##_##name##_get(cqe); \
+ } \
+} \
+static inline void mlxsw_pci_cqe_##name##_set(enum mlxsw_pci_cqe_v v, \
+ char *cqe, u32 val) \
+{ \
+ switch (v) { \
+ default: \
+ case MLXSW_PCI_CQE_V0: \
+ mlxsw_pci_cqe##v0##_##name##_set(cqe, val); \
+ break; \
+ case MLXSW_PCI_CQE_V1: \
+ mlxsw_pci_cqe##v1##_##name##_set(cqe, val); \
+ break; \
+ case MLXSW_PCI_CQE_V2: \
+ mlxsw_pci_cqe##v2##_##name##_set(cqe, val); \
+ break; \
+ } \
+}
+
/* pci_cqe_lag
* Packet arrives from a port which is a LAG
*/
-MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1);
+MLXSW_ITEM32(pci, cqe0, lag, 0x00, 23, 1);
+MLXSW_ITEM32(pci, cqe12, lag, 0x00, 24, 1);
+mlxsw_pci_cqe_item_helpers(lag, 0, 12, 12);
/* pci_cqe_system_port/lag_id
* When lag=0: System port on which the packet was received
* bits [3:0] sub_port on which the packet was received
*/
MLXSW_ITEM32(pci, cqe, system_port, 0x00, 0, 16);
-MLXSW_ITEM32(pci, cqe, lag_id, 0x00, 4, 12);
-MLXSW_ITEM32(pci, cqe, lag_port_index, 0x00, 0, 4);
+MLXSW_ITEM32(pci, cqe0, lag_id, 0x00, 4, 12);
+MLXSW_ITEM32(pci, cqe12, lag_id, 0x00, 0, 16);
+mlxsw_pci_cqe_item_helpers(lag_id, 0, 12, 12);
+MLXSW_ITEM32(pci, cqe0, lag_subport, 0x00, 0, 4);
+MLXSW_ITEM32(pci, cqe12, lag_subport, 0x00, 16, 8);
+mlxsw_pci_cqe_item_helpers(lag_subport, 0, 12, 12);
/* pci_cqe_wqe_counter
* WQE count of the WQEs completed on the associated dqn
* Length include CRC. Indicates the length field includes
* the packet's CRC.
*/
-MLXSW_ITEM32(pci, cqe, crc, 0x0C, 8, 1);
+MLXSW_ITEM32(pci, cqe0, crc, 0x0C, 8, 1);
+MLXSW_ITEM32(pci, cqe12, crc, 0x0C, 9, 1);
+mlxsw_pci_cqe_item_helpers(crc, 0, 12, 12);
/* pci_cqe_e
* CQE with Error.
*/
-MLXSW_ITEM32(pci, cqe, e, 0x0C, 7, 1);
+MLXSW_ITEM32(pci, cqe0, e, 0x0C, 7, 1);
+MLXSW_ITEM32(pci, cqe12, e, 0x00, 27, 1);
+mlxsw_pci_cqe_item_helpers(e, 0, 12, 12);
/* pci_cqe_sr
* 1 - Send Queue
* 0 - Receive Queue
*/
-MLXSW_ITEM32(pci, cqe, sr, 0x0C, 6, 1);
+MLXSW_ITEM32(pci, cqe0, sr, 0x0C, 6, 1);
+MLXSW_ITEM32(pci, cqe12, sr, 0x00, 26, 1);
+mlxsw_pci_cqe_item_helpers(sr, 0, 12, 12);
/* pci_cqe_dqn
* Descriptor Queue (DQ) Number.
*/
-MLXSW_ITEM32(pci, cqe, dqn, 0x0C, 1, 5);
+MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5);
+MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6);
+mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12);
/* pci_cqe_owner
* Ownership bit.
*/
-MLXSW_ITEM32(pci, cqe, owner, 0x0C, 0, 1);
+MLXSW_ITEM32(pci, cqe01, owner, 0x0C, 0, 1);
+MLXSW_ITEM32(pci, cqe2, owner, 0x1C, 0, 1);
+mlxsw_pci_cqe_item_helpers(owner, 01, 01, 2);
/* pci_eqe_event_type
* Event type.
*/
MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH = 0x0,
+ /* Remote SPAN Ethernet VLAN.
+ * The packet is forwarded to the monitoring port on the monitoring
+ * VLAN.
+ */
+ MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH = 0x1,
+
/* Encapsulated Remote SPAN Ethernet L3 GRE.
* The packet is encapsulated with GRE header.
*/
MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
MLXSW_RES_ID_MAX_TRAP_GROUPS,
+ MLXSW_RES_ID_CQE_V0,
+ MLXSW_RES_ID_CQE_V1,
+ MLXSW_RES_ID_CQE_V2,
MLXSW_RES_ID_COUNTER_POOL_SIZE,
MLXSW_RES_ID_MAX_SPAN,
MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES,
[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
+ [MLXSW_RES_ID_CQE_V0] = 0x2210,
+ [MLXSW_RES_ID_CQE_V1] = 0x2211,
+ [MLXSW_RES_ID_CQE_V2] = 0x2212,
[MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410,
[MLXSW_RES_ID_MAX_SPAN] = 0x2420,
[MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443,
mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
}
-int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
- u8 state)
+enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state)
{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- enum mlxsw_reg_spms_state spms_state;
- char *spms_pl;
- int err;
-
switch (state) {
case BR_STATE_FORWARDING:
- spms_state = MLXSW_REG_SPMS_STATE_FORWARDING;
- break;
+ return MLXSW_REG_SPMS_STATE_FORWARDING;
case BR_STATE_LEARNING:
- spms_state = MLXSW_REG_SPMS_STATE_LEARNING;
- break;
+ return MLXSW_REG_SPMS_STATE_LEARNING;
case BR_STATE_LISTENING: /* fall-through */
case BR_STATE_DISABLED: /* fall-through */
case BR_STATE_BLOCKING:
- spms_state = MLXSW_REG_SPMS_STATE_DISCARDING;
- break;
+ return MLXSW_REG_SPMS_STATE_DISCARDING;
default:
BUG();
}
+}
+
+int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
+ u8 state)
+{
+ enum mlxsw_reg_spms_state spms_state = mlxsw_sp_stp_spms_state(state);
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char *spms_pl;
+ int err;
spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL);
if (!spms_pl)
size_t len)
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
- u8 module = mlxsw_sp_port->mapping.module;
- u8 width = mlxsw_sp_port->mapping.width;
- u8 lane = mlxsw_sp_port->mapping.lane;
- int err;
-
- if (!mlxsw_sp_port->split)
- err = snprintf(name, len, "p%d", module + 1);
- else
- err = snprintf(name, len, "p%ds%d", module + 1,
- lane / width);
-
- if (err >= len)
- return -EINVAL;
- return 0;
+ return mlxsw_core_port_get_phys_port_name(mlxsw_sp_port->mlxsw_sp->core,
+ mlxsw_sp_port->local_port,
+ name, len);
}
static struct mlxsw_sp_port_mall_tc_entry *
}
mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port,
- mlxsw_sp_port, dev, mlxsw_sp_port->split,
- module);
+ mlxsw_sp_port, dev, module + 1,
+ mlxsw_sp_port->split, lane / width);
mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0);
return 0;
goto err_lag_init;
}
+ /* Initialize SPAN before router and switchdev, so that those components
+ * can call mlxsw_sp_span_respin().
+ */
+ err = mlxsw_sp_span_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n");
+ goto err_span_init;
+ }
+
err = mlxsw_sp_switchdev_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n");
goto err_afa_init;
}
- err = mlxsw_sp_span_init(mlxsw_sp);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n");
- goto err_span_init;
- }
-
- /* Initialize router after SPAN is initialized, so that the FIB and
- * neighbor event handlers can issue SPAN respin.
- */
err = mlxsw_sp_router_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
err_netdev_notifier:
mlxsw_sp_router_fini(mlxsw_sp);
err_router_init:
- mlxsw_sp_span_fini(mlxsw_sp);
-err_span_init:
mlxsw_sp_afa_fini(mlxsw_sp);
err_afa_init:
mlxsw_sp_counter_pool_fini(mlxsw_sp);
err_counter_pool_init:
mlxsw_sp_switchdev_fini(mlxsw_sp);
err_switchdev_init:
+ mlxsw_sp_span_fini(mlxsw_sp);
+err_span_init:
mlxsw_sp_lag_fini(mlxsw_sp);
err_lag_init:
mlxsw_sp_buffers_fini(mlxsw_sp);
mlxsw_sp_acl_fini(mlxsw_sp);
unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
mlxsw_sp_router_fini(mlxsw_sp);
- mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_afa_fini(mlxsw_sp);
mlxsw_sp_counter_pool_fini(mlxsw_sp);
mlxsw_sp_switchdev_fini(mlxsw_sp);
+ mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_lag_fini(mlxsw_sp);
mlxsw_sp_buffers_fini(mlxsw_sp);
mlxsw_sp_traps_fini(mlxsw_sp);
int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index,
u8 next_index, u32 maxrate);
+enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 stp_state);
int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
u8 state);
int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable);
switch (info->family) {
case AF_INET:
if (!fib4_rule_default(rule) && !rule->l3mdev)
- err = -1;
+ err = -EOPNOTSUPP;
break;
case AF_INET6:
if (!fib6_rule_default(rule) && !rule->l3mdev)
- err = -1;
+ err = -EOPNOTSUPP;
break;
case RTNL_FAMILY_IPMR:
if (!ipmr_rule_default(rule) && !rule->l3mdev)
- err = -1;
+ err = -EOPNOTSUPP;
break;
case RTNL_FAMILY_IP6MR:
if (!ip6mr_rule_default(rule) && !rule->l3mdev)
- err = -1;
+ err = -EOPNOTSUPP;
break;
}
if (err < 0)
- NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported. Aborting offload");
+ NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported");
return err;
}
case FIB_EVENT_RULE_DEL:
err = mlxsw_sp_router_fib_rule_event(event, info,
router->mlxsw_sp);
- if (!err)
- return NOTIFY_DONE;
+ if (!err || info->extack)
+ return notifier_from_errno(err);
+ break;
+ case FIB_EVENT_ENTRY_ADD:
+ if (router->aborted) {
+ NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
+ return notifier_from_errno(-EINVAL);
+ }
+ break;
}
fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
* POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/if_bridge.h>
#include <linux/list.h>
#include <net/arp.h>
#include <net/gre.h>
#include <net/ip6_tunnel.h>
#include "spectrum.h"
-#include "spectrum_span.h"
#include "spectrum_ipip.h"
+#include "spectrum_span.h"
+#include "spectrum_switchdev.h"
int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp)
{
static int mlxsw_sp_span_dmac(struct neigh_table *tbl,
const void *pkey,
- struct net_device *l3edev,
+ struct net_device *dev,
unsigned char dmac[ETH_ALEN])
{
- struct neighbour *neigh = neigh_lookup(tbl, pkey, l3edev);
+ struct neighbour *neigh = neigh_lookup(tbl, pkey, dev);
int err = 0;
if (!neigh) {
- neigh = neigh_create(tbl, pkey, l3edev);
+ neigh = neigh_create(tbl, pkey, dev);
if (IS_ERR(neigh))
return PTR_ERR(neigh);
}
return 0;
}
+static struct net_device *
+mlxsw_sp_span_entry_bridge_8021q(const struct net_device *br_dev,
+ unsigned char *dmac,
+ u16 *p_vid)
+{
+ struct bridge_vlan_info vinfo;
+ struct net_device *edev;
+ u16 vid = *p_vid;
+
+ if (!vid && WARN_ON(br_vlan_get_pvid(br_dev, &vid)))
+ return NULL;
+ if (!vid ||
+ br_vlan_get_info(br_dev, vid, &vinfo) ||
+ !(vinfo.flags & BRIDGE_VLAN_INFO_BRENTRY))
+ return NULL;
+
+ edev = br_fdb_find_port(br_dev, dmac, vid);
+ if (!edev)
+ return NULL;
+
+ if (br_vlan_get_info(edev, vid, &vinfo))
+ return NULL;
+ if (!(vinfo.flags & BRIDGE_VLAN_INFO_UNTAGGED))
+ *p_vid = vid;
+ return edev;
+}
+
+static struct net_device *
+mlxsw_sp_span_entry_bridge_8021d(const struct net_device *br_dev,
+ unsigned char *dmac)
+{
+ return br_fdb_find_port(br_dev, dmac, 0);
+}
+
+static struct net_device *
+mlxsw_sp_span_entry_bridge(const struct net_device *br_dev,
+ unsigned char dmac[ETH_ALEN],
+ u16 *p_vid)
+{
+ struct mlxsw_sp_bridge_port *bridge_port;
+ enum mlxsw_reg_spms_state spms_state;
+ struct net_device *dev = NULL;
+ struct mlxsw_sp_port *port;
+ u8 stp_state;
+
+ if (br_vlan_enabled(br_dev))
+ dev = mlxsw_sp_span_entry_bridge_8021q(br_dev, dmac, p_vid);
+ else if (!*p_vid)
+ dev = mlxsw_sp_span_entry_bridge_8021d(br_dev, dmac);
+ if (!dev)
+ return NULL;
+
+ port = mlxsw_sp_port_dev_lower_find(dev);
+ if (!port)
+ return NULL;
+
+ bridge_port = mlxsw_sp_bridge_port_find(port->mlxsw_sp->bridge, dev);
+ if (!bridge_port)
+ return NULL;
+
+ stp_state = mlxsw_sp_bridge_port_stp_state(bridge_port);
+ spms_state = mlxsw_sp_stp_spms_state(stp_state);
+ if (spms_state != MLXSW_REG_SPMS_STATE_FORWARDING)
+ return NULL;
+
+ return dev;
+}
+
+static struct net_device *
+mlxsw_sp_span_entry_vlan(const struct net_device *vlan_dev,
+ u16 *p_vid)
+{
+ *p_vid = vlan_dev_vlan_id(vlan_dev);
+ return vlan_dev_real_dev(vlan_dev);
+}
+
+static struct net_device *
+mlxsw_sp_span_entry_lag(struct net_device *lag_dev)
+{
+ struct net_device *dev;
+ struct list_head *iter;
+
+ netdev_for_each_lower_dev(lag_dev, dev, iter)
+ if ((dev->flags & IFF_UP) && mlxsw_sp_port_dev_check(dev))
+ return dev;
+
+ return NULL;
+}
+
static __maybe_unused int
-mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev,
+mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *edev,
union mlxsw_sp_l3addr saddr,
union mlxsw_sp_l3addr daddr,
union mlxsw_sp_l3addr gw,
struct mlxsw_sp_span_parms *sparmsp)
{
unsigned char dmac[ETH_ALEN];
+ u16 vid = 0;
if (mlxsw_sp_l3addr_is_zero(gw))
gw = daddr;
- if (!l3edev || !mlxsw_sp_port_dev_check(l3edev) ||
- mlxsw_sp_span_dmac(tbl, &gw, l3edev, dmac))
- return mlxsw_sp_span_entry_unoffloadable(sparmsp);
+ if (!edev || mlxsw_sp_span_dmac(tbl, &gw, edev, dmac))
+ goto unoffloadable;
+
+ if (is_vlan_dev(edev))
+ edev = mlxsw_sp_span_entry_vlan(edev, &vid);
- sparmsp->dest_port = netdev_priv(l3edev);
+ if (netif_is_bridge_master(edev)) {
+ edev = mlxsw_sp_span_entry_bridge(edev, dmac, &vid);
+ if (!edev)
+ goto unoffloadable;
+ }
+
+ if (is_vlan_dev(edev)) {
+ if (vid || !(edev->flags & IFF_UP))
+ goto unoffloadable;
+ edev = mlxsw_sp_span_entry_vlan(edev, &vid);
+ }
+
+ if (netif_is_lag_master(edev)) {
+ if (!(edev->flags & IFF_UP))
+ goto unoffloadable;
+ edev = mlxsw_sp_span_entry_lag(edev);
+ if (!edev)
+ goto unoffloadable;
+ }
+
+ if (!mlxsw_sp_port_dev_check(edev))
+ goto unoffloadable;
+
+ sparmsp->dest_port = netdev_priv(edev);
sparmsp->ttl = ttl;
memcpy(sparmsp->dmac, dmac, ETH_ALEN);
- memcpy(sparmsp->smac, l3edev->dev_addr, ETH_ALEN);
+ memcpy(sparmsp->smac, edev->dev_addr, ETH_ALEN);
sparmsp->saddr = saddr;
sparmsp->daddr = daddr;
+ sparmsp->vid = vid;
return 0;
+
+unoffloadable:
+ return mlxsw_sp_span_entry_unoffloadable(sparmsp);
}
#if IS_ENABLED(CONFIG_NET_IPGRE)
/* Create a new port analayzer entry for local_port. */
mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true,
MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3);
+ mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid);
mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl,
MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER,
- sparms.dmac, false);
+ sparms.dmac, !!sparms.vid);
mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(mpat_pl,
sparms.ttl, sparms.smac,
be32_to_cpu(sparms.saddr.addr4),
/* Create a new port analayzer entry for local_port. */
mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true,
MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3);
+ mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid);
mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl,
MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER,
- sparms.dmac, false);
+ sparms.dmac, !!sparms.vid);
mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(mpat_pl, sparms.ttl, sparms.smac,
sparms.saddr.addr6,
sparms.daddr.addr6);
};
#endif
+static bool
+mlxsw_sp_span_vlan_can_handle(const struct net_device *dev)
+{
+ return is_vlan_dev(dev) &&
+ mlxsw_sp_port_dev_check(vlan_dev_real_dev(dev));
+}
+
+static int
+mlxsw_sp_span_entry_vlan_parms(const struct net_device *to_dev,
+ struct mlxsw_sp_span_parms *sparmsp)
+{
+ struct net_device *real_dev;
+ u16 vid;
+
+ if (!(to_dev->flags & IFF_UP))
+ return mlxsw_sp_span_entry_unoffloadable(sparmsp);
+
+ real_dev = mlxsw_sp_span_entry_vlan(to_dev, &vid);
+ sparmsp->dest_port = netdev_priv(real_dev);
+ sparmsp->vid = vid;
+ return 0;
+}
+
+static int
+mlxsw_sp_span_entry_vlan_configure(struct mlxsw_sp_span_entry *span_entry,
+ struct mlxsw_sp_span_parms sparms)
+{
+ struct mlxsw_sp_port *dest_port = sparms.dest_port;
+ struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp;
+ u8 local_port = dest_port->local_port;
+ char mpat_pl[MLXSW_REG_MPAT_LEN];
+ int pa_id = span_entry->id;
+
+ mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true,
+ MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH);
+ mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl);
+}
+
+static void
+mlxsw_sp_span_entry_vlan_deconfigure(struct mlxsw_sp_span_entry *span_entry)
+{
+ mlxsw_sp_span_entry_deconfigure_common(span_entry,
+ MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH);
+}
+
+static const
+struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_vlan = {
+ .can_handle = mlxsw_sp_span_vlan_can_handle,
+ .parms = mlxsw_sp_span_entry_vlan_parms,
+ .configure = mlxsw_sp_span_entry_vlan_configure,
+ .deconfigure = mlxsw_sp_span_entry_vlan_deconfigure,
+};
+
static const
struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = {
&mlxsw_sp_span_entry_ops_phys,
#if IS_ENABLED(CONFIG_IPV6_GRE)
&mlxsw_sp_span_entry_ops_gretap6,
#endif
+ &mlxsw_sp_span_entry_ops_vlan,
};
static int
span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms);
if (!span_entry)
- return -ENOENT;
+ return -ENOBUFS;
netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n",
span_entry->id);
unsigned char smac[ETH_ALEN];
union mlxsw_sp_l3addr daddr;
union mlxsw_sp_l3addr saddr;
+ u16 vid;
};
struct mlxsw_sp_span_entry_ops;
#include <linux/netlink.h>
#include <net/switchdev.h>
+#include "spectrum_span.h"
#include "spectrum_router.h"
+#include "spectrum_switchdev.h"
#include "spectrum.h"
#include "core.h"
#include "reg.h"
return NULL;
}
-static struct mlxsw_sp_bridge_port *
+struct mlxsw_sp_bridge_port *
mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge,
struct net_device *brport_dev)
{
break;
}
+ if (switchdev_trans_ph_commit(trans))
+ mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp);
+
return err;
}
}
}
+struct mlxsw_sp_span_respin_work {
+ struct work_struct work;
+ struct mlxsw_sp *mlxsw_sp;
+};
+
+static void mlxsw_sp_span_respin_work(struct work_struct *work)
+{
+ struct mlxsw_sp_span_respin_work *respin_work =
+ container_of(work, struct mlxsw_sp_span_respin_work, work);
+
+ rtnl_lock();
+ mlxsw_sp_span_respin(respin_work->mlxsw_sp);
+ rtnl_unlock();
+ kfree(respin_work);
+}
+
+static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_span_respin_work *respin_work;
+
+ respin_work = kzalloc(sizeof(*respin_work), GFP_ATOMIC);
+ if (!respin_work)
+ return;
+
+ INIT_WORK(&respin_work->work, mlxsw_sp_span_respin_work);
+ respin_work->mlxsw_sp = mlxsw_sp;
+
+ mlxsw_core_schedule_work(&respin_work->work);
+}
+
static int mlxsw_sp_port_obj_add(struct net_device *dev,
const struct switchdev_obj *obj,
struct switchdev_trans *trans)
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+ const struct switchdev_obj_port_vlan *vlan;
int err = 0;
switch (obj->id) {
case SWITCHDEV_OBJ_ID_PORT_VLAN:
- err = mlxsw_sp_port_vlans_add(mlxsw_sp_port,
- SWITCHDEV_OBJ_PORT_VLAN(obj),
- trans);
+ vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+ err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans);
+
+ if (switchdev_trans_ph_commit(trans)) {
+ /* The event is emitted before the changes are actually
+ * applied to the bridge. Therefore schedule the respin
+ * call for later, so that the respin logic sees the
+ * updated bridge state.
+ */
+ mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp);
+ }
break;
case SWITCHDEV_OBJ_ID_PORT_MDB:
err = mlxsw_sp_port_mdb_add(mlxsw_sp_port,
struct net_device *dev = mlxsw_sp_port->dev;
int err;
- if (bridge_port->bridge_device->multicast_enabled) {
- if (bridge_port->bridge_device->multicast_enabled) {
- err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
- false);
- if (err)
- netdev_err(dev, "Unable to remove port from SMID\n");
- }
+ if (bridge_port->bridge_device->multicast_enabled &&
+ !bridge_port->mrouter) {
+ err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+ if (err)
+ netdev_err(dev, "Unable to remove port from SMID\n");
}
err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
break;
}
+ mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp);
+
return err;
}
switch (switchdev_work->event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
err = mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, true);
if (err)
break;
break;
case SWITCHDEV_FDB_DEL_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false);
break;
+ case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
+ case SWITCHDEV_FDB_DEL_TO_BRIDGE:
+ /* These events are only used to potentially update an existing
+ * SPAN mirror.
+ */
+ break;
}
+ mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp);
+
out:
rtnl_unlock();
kfree(switchdev_work->fdb_info.addr);
switch (event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */
- case SWITCHDEV_FDB_DEL_TO_DEVICE:
+ case SWITCHDEV_FDB_DEL_TO_DEVICE: /* fall through */
+ case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
+ case SWITCHDEV_FDB_DEL_TO_BRIDGE:
memcpy(&switchdev_work->fdb_info, ptr,
sizeof(switchdev_work->fdb_info));
switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
.notifier_call = mlxsw_sp_switchdev_event,
};
+u8
+mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port)
+{
+ return bridge_port->stp_state;
+}
+
static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge;
--- /dev/null
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/netdevice.h>
+
+struct mlxsw_sp_bridge;
+struct mlxsw_sp_bridge_port;
+
+struct mlxsw_sp_bridge_port *
+mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge,
+ struct net_device *brport_dev);
+
+u8 mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port);
size_t len)
{
struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
- int err;
-
- err = snprintf(name, len, "p%d", mlxsw_sx_port->mapping.module + 1);
- if (err >= len)
- return -EINVAL;
- return 0;
+ return mlxsw_core_port_get_phys_port_name(mlxsw_sx_port->mlxsw_sx->core,
+ mlxsw_sx_port->local_port,
+ name, len);
}
static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
}
mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
- mlxsw_sx_port, dev, false, 0);
+ mlxsw_sx_port, dev, module + 1, false, 0);
mlxsw_sx->ports[local_port] = mlxsw_sx_port;
return 0;
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR MIT)
+config NET_VENDOR_MICROSEMI
+ bool "Microsemi devices"
+ default y
+ help
+ If you have a network (Ethernet) card belonging to this class, say Y.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Microsemi devices.
+
+if NET_VENDOR_MICROSEMI
+
+config MSCC_OCELOT_SWITCH
+ tristate "Ocelot switch driver"
+ depends on NET_SWITCHDEV
+ depends on HAS_IOMEM
+ select PHYLIB
+ select REGMAP_MMIO
+ help
+ This driver supports the Ocelot network switch device.
+
+config MSCC_OCELOT_SWITCH_OCELOT
+ tristate "Ocelot switch driver on Ocelot"
+ depends on MSCC_OCELOT_SWITCH
+ help
+ This driver supports the Ocelot network switch device as present on
+ the Ocelot SoCs.
+
+endif # NET_VENDOR_MICROSEMI
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR MIT)
+obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot_common.o
+mscc_ocelot_common-y := ocelot.o ocelot_io.o
+mscc_ocelot_common-y += ocelot_regs.o
+obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_board.o
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if_bridge.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/skbuff.h>
+#include <net/arp.h>
+#include <net/netevent.h>
+#include <net/rtnetlink.h>
+#include <net/switchdev.h>
+
+#include "ocelot.h"
+
+/* MAC table entry types.
+ * ENTRYTYPE_NORMAL is subject to aging.
+ * ENTRYTYPE_LOCKED is not subject to aging.
+ * ENTRYTYPE_MACv4 is not subject to aging. For IPv4 multicast.
+ * ENTRYTYPE_MACv6 is not subject to aging. For IPv6 multicast.
+ */
+enum macaccess_entry_type {
+ ENTRYTYPE_NORMAL = 0,
+ ENTRYTYPE_LOCKED,
+ ENTRYTYPE_MACv4,
+ ENTRYTYPE_MACv6,
+};
+
+struct ocelot_mact_entry {
+ u8 mac[ETH_ALEN];
+ u16 vid;
+ enum macaccess_entry_type type;
+};
+
+static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
+{
+ unsigned int val, timeout = 10;
+
+ /* Wait for the issued mac table command to be completed, or timeout.
+ * When the command read from ANA_TABLES_MACACCESS is
+ * MACACCESS_CMD_IDLE, the issued command completed successfully.
+ */
+ do {
+ val = ocelot_read(ocelot, ANA_TABLES_MACACCESS);
+ val &= ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M;
+ } while (val != MACACCESS_CMD_IDLE && timeout--);
+
+ if (!timeout)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static void ocelot_mact_select(struct ocelot *ocelot,
+ const unsigned char mac[ETH_ALEN],
+ unsigned int vid)
+{
+ u32 macl = 0, mach = 0;
+
+ /* Set the MAC address to handle and the vlan associated in a format
+ * understood by the hardware.
+ */
+ mach |= vid << 16;
+ mach |= mac[0] << 8;
+ mach |= mac[1] << 0;
+ macl |= mac[2] << 24;
+ macl |= mac[3] << 16;
+ macl |= mac[4] << 8;
+ macl |= mac[5] << 0;
+
+ ocelot_write(ocelot, macl, ANA_TABLES_MACLDATA);
+ ocelot_write(ocelot, mach, ANA_TABLES_MACHDATA);
+
+}
+
+static int ocelot_mact_learn(struct ocelot *ocelot, int port,
+ const unsigned char mac[ETH_ALEN],
+ unsigned int vid,
+ enum macaccess_entry_type type)
+{
+ ocelot_mact_select(ocelot, mac, vid);
+
+ /* Issue a write command */
+ ocelot_write(ocelot, ANA_TABLES_MACACCESS_VALID |
+ ANA_TABLES_MACACCESS_DEST_IDX(port) |
+ ANA_TABLES_MACACCESS_ENTRYTYPE(type) |
+ ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_LEARN),
+ ANA_TABLES_MACACCESS);
+
+ return ocelot_mact_wait_for_completion(ocelot);
+}
+
+static int ocelot_mact_forget(struct ocelot *ocelot,
+ const unsigned char mac[ETH_ALEN],
+ unsigned int vid)
+{
+ ocelot_mact_select(ocelot, mac, vid);
+
+ /* Issue a forget command */
+ ocelot_write(ocelot,
+ ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_FORGET),
+ ANA_TABLES_MACACCESS);
+
+ return ocelot_mact_wait_for_completion(ocelot);
+}
+
+static void ocelot_mact_init(struct ocelot *ocelot)
+{
+ /* Configure the learning mode entries attributes:
+ * - Do not copy the frame to the CPU extraction queues.
+ * - Use the vlan and mac_cpoy for dmac lookup.
+ */
+ ocelot_rmw(ocelot, 0,
+ ANA_AGENCTRL_LEARN_CPU_COPY | ANA_AGENCTRL_IGNORE_DMAC_FLAGS
+ | ANA_AGENCTRL_LEARN_FWD_KILL
+ | ANA_AGENCTRL_LEARN_IGNORE_VLAN,
+ ANA_AGENCTRL);
+
+ /* Clear the MAC table */
+ ocelot_write(ocelot, MACACCESS_CMD_INIT, ANA_TABLES_MACACCESS);
+}
+
+static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
+{
+ unsigned int val, timeout = 10;
+
+ /* Wait for the issued mac table command to be completed, or timeout.
+ * When the command read from ANA_TABLES_MACACCESS is
+ * MACACCESS_CMD_IDLE, the issued command completed successfully.
+ */
+ do {
+ val = ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
+ val &= ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M;
+ } while (val != ANA_TABLES_VLANACCESS_CMD_IDLE && timeout--);
+
+ if (!timeout)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static void ocelot_vlan_init(struct ocelot *ocelot)
+{
+ /* Clear VLAN table, by default all ports are members of all VLANs */
+ ocelot_write(ocelot, ANA_TABLES_VLANACCESS_CMD_INIT,
+ ANA_TABLES_VLANACCESS);
+ ocelot_vlant_wait_for_completion(ocelot);
+}
+
+/* Watermark encode
+ * Bit 8: Unit; 0:1, 1:16
+ * Bit 7-0: Value to be multiplied with unit
+ */
+static u16 ocelot_wm_enc(u16 value)
+{
+ if (value >= BIT(8))
+ return BIT(8) | (value / 16);
+
+ return value;
+}
+
+static void ocelot_port_adjust_link(struct net_device *dev)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ u8 p = port->chip_port;
+ int speed, atop_wm, mode = 0;
+
+ switch (dev->phydev->speed) {
+ case SPEED_10:
+ speed = OCELOT_SPEED_10;
+ break;
+ case SPEED_100:
+ speed = OCELOT_SPEED_100;
+ break;
+ case SPEED_1000:
+ speed = OCELOT_SPEED_1000;
+ mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
+ break;
+ case SPEED_2500:
+ speed = OCELOT_SPEED_2500;
+ mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA;
+ break;
+ default:
+ netdev_err(dev, "Unsupported PHY speed: %d\n",
+ dev->phydev->speed);
+ return;
+ }
+
+ phy_print_status(dev->phydev);
+
+ if (!dev->phydev->link)
+ return;
+
+ /* Only full duplex supported for now */
+ ocelot_port_writel(port, DEV_MAC_MODE_CFG_FDX_ENA |
+ mode, DEV_MAC_MODE_CFG);
+
+ /* Set MAC IFG Gaps
+ * FDX: TX_IFG = 5, RX_IFG1 = RX_IFG2 = 0
+ * !FDX: TX_IFG = 5, RX_IFG1 = RX_IFG2 = 5
+ */
+ ocelot_port_writel(port, DEV_MAC_IFG_CFG_TX_IFG(5), DEV_MAC_IFG_CFG);
+
+ /* Load seed (0) and set MAC HDX late collision */
+ ocelot_port_writel(port, DEV_MAC_HDX_CFG_LATE_COL_POS(67) |
+ DEV_MAC_HDX_CFG_SEED_LOAD,
+ DEV_MAC_HDX_CFG);
+ mdelay(1);
+ ocelot_port_writel(port, DEV_MAC_HDX_CFG_LATE_COL_POS(67),
+ DEV_MAC_HDX_CFG);
+
+ /* Disable HDX fast control */
+ ocelot_port_writel(port, DEV_PORT_MISC_HDX_FAST_DIS, DEV_PORT_MISC);
+
+ /* SGMII only for now */
+ ocelot_port_writel(port, PCS1G_MODE_CFG_SGMII_MODE_ENA, PCS1G_MODE_CFG);
+ ocelot_port_writel(port, PCS1G_SD_CFG_SD_SEL, PCS1G_SD_CFG);
+
+ /* Enable PCS */
+ ocelot_port_writel(port, PCS1G_CFG_PCS_ENA, PCS1G_CFG);
+
+ /* No aneg on SGMII */
+ ocelot_port_writel(port, 0, PCS1G_ANEG_CFG);
+
+ /* No loopback */
+ ocelot_port_writel(port, 0, PCS1G_LB_CFG);
+
+ /* Set Max Length and maximum tags allowed */
+ ocelot_port_writel(port, VLAN_ETH_FRAME_LEN, DEV_MAC_MAXLEN_CFG);
+ ocelot_port_writel(port, DEV_MAC_TAGS_CFG_TAG_ID(ETH_P_8021AD) |
+ DEV_MAC_TAGS_CFG_VLAN_AWR_ENA |
+ DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA,
+ DEV_MAC_TAGS_CFG);
+
+ /* Enable MAC module */
+ ocelot_port_writel(port, DEV_MAC_ENA_CFG_RX_ENA |
+ DEV_MAC_ENA_CFG_TX_ENA, DEV_MAC_ENA_CFG);
+
+ /* Take MAC, Port, Phy (intern) and PCS (SGMII/Serdes) clock out of
+ * reset */
+ ocelot_port_writel(port, DEV_CLOCK_CFG_LINK_SPEED(speed),
+ DEV_CLOCK_CFG);
+
+ /* Set SMAC of Pause frame (00:00:00:00:00:00) */
+ ocelot_port_writel(port, 0, DEV_MAC_FC_MAC_HIGH_CFG);
+ ocelot_port_writel(port, 0, DEV_MAC_FC_MAC_LOW_CFG);
+
+ /* No PFC */
+ ocelot_write_gix(ocelot, ANA_PFC_PFC_CFG_FC_LINK_SPEED(speed),
+ ANA_PFC_PFC_CFG, p);
+
+ /* Set Pause WM hysteresis
+ * 152 = 6 * VLAN_ETH_FRAME_LEN / OCELOT_BUFFER_CELL_SZ
+ * 101 = 4 * VLAN_ETH_FRAME_LEN / OCELOT_BUFFER_CELL_SZ
+ */
+ ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA |
+ SYS_PAUSE_CFG_PAUSE_STOP(101) |
+ SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, p);
+
+ /* Core: Enable port for frame transfer */
+ ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE |
+ QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) |
+ QSYS_SWITCH_PORT_MODE_PORT_ENA,
+ QSYS_SWITCH_PORT_MODE, p);
+
+ /* Flow control */
+ ocelot_write_rix(ocelot, SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) |
+ SYS_MAC_FC_CFG_RX_FC_ENA | SYS_MAC_FC_CFG_TX_FC_ENA |
+ SYS_MAC_FC_CFG_ZERO_PAUSE_ENA |
+ SYS_MAC_FC_CFG_FC_LATENCY_CFG(0x7) |
+ SYS_MAC_FC_CFG_FC_LINK_SPEED(speed),
+ SYS_MAC_FC_CFG, p);
+ ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, p);
+
+ /* Tail dropping watermark */
+ atop_wm = (ocelot->shared_queue_sz - 9 * VLAN_ETH_FRAME_LEN) / OCELOT_BUFFER_CELL_SZ;
+ ocelot_write_rix(ocelot, ocelot_wm_enc(9 * VLAN_ETH_FRAME_LEN),
+ SYS_ATOP, p);
+ ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG);
+}
+
+static int ocelot_port_open(struct net_device *dev)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ int err;
+
+ /* Enable receiving frames on the port, and activate auto-learning of
+ * MAC addresses.
+ */
+ ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_LEARNAUTO |
+ ANA_PORT_PORT_CFG_RECV_ENA |
+ ANA_PORT_PORT_CFG_PORTID_VAL(port->chip_port),
+ ANA_PORT_PORT_CFG, port->chip_port);
+
+ err = phy_connect_direct(dev, port->phy, &ocelot_port_adjust_link,
+ PHY_INTERFACE_MODE_NA);
+ if (err) {
+ netdev_err(dev, "Could not attach to PHY\n");
+ return err;
+ }
+
+ dev->phydev = port->phy;
+
+ phy_attached_info(port->phy);
+ phy_start(port->phy);
+ return 0;
+}
+
+static int ocelot_port_stop(struct net_device *dev)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+
+ phy_disconnect(port->phy);
+
+ dev->phydev = NULL;
+
+ ocelot_port_writel(port, 0, DEV_MAC_ENA_CFG);
+ ocelot_rmw_rix(port->ocelot, 0, QSYS_SWITCH_PORT_MODE_PORT_ENA,
+ QSYS_SWITCH_PORT_MODE, port->chip_port);
+ return 0;
+}
+
+/* Generate the IFH for frame injection
+ *
+ * The IFH is a 128bit-value
+ * bit 127: bypass the analyzer processing
+ * bit 56-67: destination mask
+ * bit 28-29: pop_cnt: 3 disables all rewriting of the frame
+ * bit 20-27: cpu extraction queue mask
+ * bit 16: tag type 0: C-tag, 1: S-tag
+ * bit 0-11: VID
+ */
+static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info)
+{
+ ifh[0] = IFH_INJ_BYPASS;
+ ifh[1] = (0xff00 & info->port) >> 8;
+ ifh[2] = (0xff & info->port) << 24;
+ ifh[3] = IFH_INJ_POP_CNT_DISABLE | (info->cpuq << 20) |
+ (info->tag_type << 16) | info->vid;
+
+ return 0;
+}
+
+static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ u32 val, ifh[IFH_LEN];
+ struct frame_info info = {};
+ u8 grp = 0; /* Send everything on CPU group 0 */
+ unsigned int i, count, last;
+
+ val = ocelot_read(ocelot, QS_INJ_STATUS);
+ if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))) ||
+ (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))))
+ return NETDEV_TX_BUSY;
+
+ ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
+ QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
+
+ info.port = BIT(port->chip_port);
+ info.cpuq = 0xff;
+ ocelot_gen_ifh(ifh, &info);
+
+ for (i = 0; i < IFH_LEN; i++)
+ ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
+
+ count = (skb->len + 3) / 4;
+ last = skb->len % 4;
+ for (i = 0; i < count; i++) {
+ ocelot_write_rix(ocelot, ((u32 *)skb->data)[i], QS_INJ_WR, grp);
+ }
+
+ /* Add padding */
+ while (i < (OCELOT_BUFFER_CELL_SZ / 4)) {
+ ocelot_write_rix(ocelot, 0, QS_INJ_WR, grp);
+ i++;
+ }
+
+ /* Indicate EOF and valid bytes in last word */
+ ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
+ QS_INJ_CTRL_VLD_BYTES(skb->len < OCELOT_BUFFER_CELL_SZ ? 0 : last) |
+ QS_INJ_CTRL_EOF,
+ QS_INJ_CTRL, grp);
+
+ /* Add dummy CRC */
+ ocelot_write_rix(ocelot, 0, QS_INJ_WR, grp);
+ skb_tx_timestamp(skb);
+
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
+ dev_kfree_skb_any(skb);
+
+ return NETDEV_TX_OK;
+}
+
+static void ocelot_mact_mc_reset(struct ocelot_port *port)
+{
+ struct ocelot *ocelot = port->ocelot;
+ struct netdev_hw_addr *ha, *n;
+
+ /* Free and forget all the MAC addresses stored in the port private mc
+ * list. These are mc addresses that were previously added by calling
+ * ocelot_mact_mc_add().
+ */
+ list_for_each_entry_safe(ha, n, &port->mc, list) {
+ ocelot_mact_forget(ocelot, ha->addr, port->pvid);
+ list_del(&ha->list);
+ kfree(ha);
+ }
+}
+
+static int ocelot_mact_mc_add(struct ocelot_port *port,
+ struct netdev_hw_addr *hw_addr)
+{
+ struct ocelot *ocelot = port->ocelot;
+ struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
+
+ if (!ha)
+ return -ENOMEM;
+
+ memcpy(ha, hw_addr, sizeof(*ha));
+ list_add_tail(&ha->list, &port->mc);
+
+ ocelot_mact_learn(ocelot, PGID_CPU, ha->addr, port->pvid,
+ ENTRYTYPE_LOCKED);
+
+ return 0;
+}
+
+static void ocelot_set_rx_mode(struct net_device *dev)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ struct netdev_hw_addr *ha;
+ int i;
+ u32 val;
+
+ /* This doesn't handle promiscuous mode because the bridge core is
+ * setting IFF_PROMISC on all slave interfaces and all frames would be
+ * forwarded to the CPU port.
+ */
+ val = GENMASK(ocelot->num_phys_ports - 1, 0);
+ for (i = ocelot->num_phys_ports + 1; i < PGID_CPU; i++)
+ ocelot_write_rix(ocelot, val, ANA_PGID_PGID, i);
+
+ /* Handle the device multicast addresses. First remove all the
+ * previously installed addresses and then add the latest ones to the
+ * mac table.
+ */
+ ocelot_mact_mc_reset(port);
+ netdev_for_each_mc_addr(ha, dev)
+ ocelot_mact_mc_add(port, ha);
+}
+
+static int ocelot_port_get_phys_port_name(struct net_device *dev,
+ char *buf, size_t len)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ int ret;
+
+ ret = snprintf(buf, len, "p%d", port->chip_port);
+ if (ret >= len)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ocelot_port_set_mac_address(struct net_device *dev, void *p)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ const struct sockaddr *addr = p;
+
+ /* Learn the new net device MAC address in the mac table. */
+ ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data, port->pvid,
+ ENTRYTYPE_LOCKED);
+ /* Then forget the previous one. */
+ ocelot_mact_forget(ocelot, dev->dev_addr, port->pvid);
+
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+ return 0;
+}
+
+static void ocelot_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+
+ /* Configure the port to read the stats from */
+ ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port->chip_port),
+ SYS_STAT_CFG);
+
+ /* Get Rx stats */
+ stats->rx_bytes = ocelot_read(ocelot, SYS_COUNT_RX_OCTETS);
+ stats->rx_packets = ocelot_read(ocelot, SYS_COUNT_RX_SHORTS) +
+ ocelot_read(ocelot, SYS_COUNT_RX_FRAGMENTS) +
+ ocelot_read(ocelot, SYS_COUNT_RX_JABBERS) +
+ ocelot_read(ocelot, SYS_COUNT_RX_LONGS) +
+ ocelot_read(ocelot, SYS_COUNT_RX_64) +
+ ocelot_read(ocelot, SYS_COUNT_RX_65_127) +
+ ocelot_read(ocelot, SYS_COUNT_RX_128_255) +
+ ocelot_read(ocelot, SYS_COUNT_RX_256_1023) +
+ ocelot_read(ocelot, SYS_COUNT_RX_1024_1526) +
+ ocelot_read(ocelot, SYS_COUNT_RX_1527_MAX);
+ stats->multicast = ocelot_read(ocelot, SYS_COUNT_RX_MULTICAST);
+ stats->rx_dropped = dev->stats.rx_dropped;
+
+ /* Get Tx stats */
+ stats->tx_bytes = ocelot_read(ocelot, SYS_COUNT_TX_OCTETS);
+ stats->tx_packets = ocelot_read(ocelot, SYS_COUNT_TX_64) +
+ ocelot_read(ocelot, SYS_COUNT_TX_65_127) +
+ ocelot_read(ocelot, SYS_COUNT_TX_128_511) +
+ ocelot_read(ocelot, SYS_COUNT_TX_512_1023) +
+ ocelot_read(ocelot, SYS_COUNT_TX_1024_1526) +
+ ocelot_read(ocelot, SYS_COUNT_TX_1527_MAX);
+ stats->tx_dropped = ocelot_read(ocelot, SYS_COUNT_TX_DROPS) +
+ ocelot_read(ocelot, SYS_COUNT_TX_AGING);
+ stats->collisions = ocelot_read(ocelot, SYS_COUNT_TX_COLLISION);
+}
+
+static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev, const unsigned char *addr,
+ u16 vid, u16 flags)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+
+ return ocelot_mact_learn(ocelot, port->chip_port, addr, vid,
+ ENTRYTYPE_NORMAL);
+}
+
+static int ocelot_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+
+ return ocelot_mact_forget(ocelot, addr, vid);
+}
+
+struct ocelot_dump_ctx {
+ struct net_device *dev;
+ struct sk_buff *skb;
+ struct netlink_callback *cb;
+ int idx;
+};
+
+static int ocelot_fdb_do_dump(struct ocelot_mact_entry *entry,
+ struct ocelot_dump_ctx *dump)
+{
+ u32 portid = NETLINK_CB(dump->cb->skb).portid;
+ u32 seq = dump->cb->nlh->nlmsg_seq;
+ struct nlmsghdr *nlh;
+ struct ndmsg *ndm;
+
+ if (dump->idx < dump->cb->args[2])
+ goto skip;
+
+ nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH,
+ sizeof(*ndm), NLM_F_MULTI);
+ if (!nlh)
+ return -EMSGSIZE;
+
+ ndm = nlmsg_data(nlh);
+ ndm->ndm_family = AF_BRIDGE;
+ ndm->ndm_pad1 = 0;
+ ndm->ndm_pad2 = 0;
+ ndm->ndm_flags = NTF_SELF;
+ ndm->ndm_type = 0;
+ ndm->ndm_ifindex = dump->dev->ifindex;
+ ndm->ndm_state = NUD_REACHABLE;
+
+ if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, entry->mac))
+ goto nla_put_failure;
+
+ if (entry->vid && nla_put_u16(dump->skb, NDA_VLAN, entry->vid))
+ goto nla_put_failure;
+
+ nlmsg_end(dump->skb, nlh);
+
+skip:
+ dump->idx++;
+ return 0;
+
+nla_put_failure:
+ nlmsg_cancel(dump->skb, nlh);
+ return -EMSGSIZE;
+}
+
+static inline int ocelot_mact_read(struct ocelot_port *port, int row, int col,
+ struct ocelot_mact_entry *entry)
+{
+ struct ocelot *ocelot = port->ocelot;
+ char mac[ETH_ALEN];
+ u32 val, dst, macl, mach;
+
+ /* Set row and column to read from */
+ ocelot_field_write(ocelot, ANA_TABLES_MACTINDX_M_INDEX, row);
+ ocelot_field_write(ocelot, ANA_TABLES_MACTINDX_BUCKET, col);
+
+ /* Issue a read command */
+ ocelot_write(ocelot,
+ ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_READ),
+ ANA_TABLES_MACACCESS);
+
+ if (ocelot_mact_wait_for_completion(ocelot))
+ return -ETIMEDOUT;
+
+ /* Read the entry flags */
+ val = ocelot_read(ocelot, ANA_TABLES_MACACCESS);
+ if (!(val & ANA_TABLES_MACACCESS_VALID))
+ return -EINVAL;
+
+ /* If the entry read has another port configured as its destination,
+ * do not report it.
+ */
+ dst = (val & ANA_TABLES_MACACCESS_DEST_IDX_M) >> 3;
+ if (dst != port->chip_port)
+ return -EINVAL;
+
+ /* Get the entry's MAC address and VLAN id */
+ macl = ocelot_read(ocelot, ANA_TABLES_MACLDATA);
+ mach = ocelot_read(ocelot, ANA_TABLES_MACHDATA);
+
+ mac[0] = (mach >> 8) & 0xff;
+ mac[1] = (mach >> 0) & 0xff;
+ mac[2] = (macl >> 24) & 0xff;
+ mac[3] = (macl >> 16) & 0xff;
+ mac[4] = (macl >> 8) & 0xff;
+ mac[5] = (macl >> 0) & 0xff;
+
+ entry->vid = (mach >> 16) & 0xfff;
+ ether_addr_copy(entry->mac, mac);
+
+ return 0;
+}
+
+static int ocelot_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct net_device *dev,
+ struct net_device *filter_dev, int *idx)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ int i, j, ret = 0;
+ struct ocelot_dump_ctx dump = {
+ .dev = dev,
+ .skb = skb,
+ .cb = cb,
+ .idx = *idx,
+ };
+
+ struct ocelot_mact_entry entry;
+
+ /* Loop through all the mac tables entries. There are 1024 rows of 4
+ * entries.
+ */
+ for (i = 0; i < 1024; i++) {
+ for (j = 0; j < 4; j++) {
+ ret = ocelot_mact_read(port, i, j, &entry);
+ /* If the entry is invalid (wrong port, invalid...),
+ * skip it.
+ */
+ if (ret == -EINVAL)
+ continue;
+ else if (ret)
+ goto end;
+
+ ret = ocelot_fdb_do_dump(&entry, &dump);
+ if (ret)
+ goto end;
+ }
+ }
+
+end:
+ *idx = dump.idx;
+ return ret;
+}
+
+static const struct net_device_ops ocelot_port_netdev_ops = {
+ .ndo_open = ocelot_port_open,
+ .ndo_stop = ocelot_port_stop,
+ .ndo_start_xmit = ocelot_port_xmit,
+ .ndo_set_rx_mode = ocelot_set_rx_mode,
+ .ndo_get_phys_port_name = ocelot_port_get_phys_port_name,
+ .ndo_set_mac_address = ocelot_port_set_mac_address,
+ .ndo_get_stats64 = ocelot_get_stats64,
+ .ndo_fdb_add = ocelot_fdb_add,
+ .ndo_fdb_del = ocelot_fdb_del,
+ .ndo_fdb_dump = ocelot_fdb_dump,
+};
+
+static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
+{
+ struct ocelot_port *port = netdev_priv(netdev);
+ struct ocelot *ocelot = port->ocelot;
+ int i;
+
+ if (sset != ETH_SS_STATS)
+ return;
+
+ for (i = 0; i < ocelot->num_stats; i++)
+ memcpy(data + i * ETH_GSTRING_LEN, ocelot->stats_layout[i].name,
+ ETH_GSTRING_LEN);
+}
+
+static void ocelot_check_stats(struct work_struct *work)
+{
+ struct delayed_work *del_work = to_delayed_work(work);
+ struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
+ int i, j;
+
+ mutex_lock(&ocelot->stats_lock);
+
+ for (i = 0; i < ocelot->num_phys_ports; i++) {
+ /* Configure the port to read the stats from */
+ ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG);
+
+ for (j = 0; j < ocelot->num_stats; j++) {
+ u32 val;
+ unsigned int idx = i * ocelot->num_stats + j;
+
+ val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
+ ocelot->stats_layout[j].offset);
+
+ if (val < (ocelot->stats[idx] & U32_MAX))
+ ocelot->stats[idx] += (u64)1 << 32;
+
+ ocelot->stats[idx] = (ocelot->stats[idx] &
+ ~(u64)U32_MAX) + val;
+ }
+ }
+
+ cancel_delayed_work(&ocelot->stats_work);
+ queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
+ OCELOT_STATS_CHECK_DELAY);
+
+ mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ int i;
+
+ /* check and update now */
+ ocelot_check_stats(&ocelot->stats_work.work);
+
+ /* Copy all counters */
+ for (i = 0; i < ocelot->num_stats; i++)
+ *data++ = ocelot->stats[port->chip_port * ocelot->num_stats + i];
+}
+
+static int ocelot_get_sset_count(struct net_device *dev, int sset)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+
+ if (sset != ETH_SS_STATS)
+ return -EOPNOTSUPP;
+ return ocelot->num_stats;
+}
+
+static const struct ethtool_ops ocelot_ethtool_ops = {
+ .get_strings = ocelot_get_strings,
+ .get_ethtool_stats = ocelot_get_ethtool_stats,
+ .get_sset_count = ocelot_get_sset_count,
+};
+
+static int ocelot_port_attr_get(struct net_device *dev,
+ struct switchdev_attr *attr)
+{
+ struct ocelot_port *ocelot_port = netdev_priv(dev);
+ struct ocelot *ocelot = ocelot_port->ocelot;
+
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+ attr->u.ppid.id_len = sizeof(ocelot->base_mac);
+ memcpy(&attr->u.ppid.id, &ocelot->base_mac,
+ attr->u.ppid.id_len);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port,
+ struct switchdev_trans *trans,
+ u8 state)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+ u32 port_cfg;
+ int port, i;
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ if (!(BIT(ocelot_port->chip_port) & ocelot->bridge_mask))
+ return 0;
+
+ port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG,
+ ocelot_port->chip_port);
+
+ switch (state) {
+ case BR_STATE_FORWARDING:
+ ocelot->bridge_fwd_mask |= BIT(ocelot_port->chip_port);
+ /* Fallthrough */
+ case BR_STATE_LEARNING:
+ port_cfg |= ANA_PORT_PORT_CFG_LEARN_ENA;
+ break;
+
+ default:
+ port_cfg &= ~ANA_PORT_PORT_CFG_LEARN_ENA;
+ ocelot->bridge_fwd_mask &= ~BIT(ocelot_port->chip_port);
+ break;
+ }
+
+ ocelot_write_gix(ocelot, port_cfg, ANA_PORT_PORT_CFG,
+ ocelot_port->chip_port);
+
+ /* Apply FWD mask. The loop is needed to add/remove the current port as
+ * a source for the other ports.
+ */
+ for (port = 0; port < ocelot->num_phys_ports; port++) {
+ if (ocelot->bridge_fwd_mask & BIT(port)) {
+ unsigned long mask = ocelot->bridge_fwd_mask & ~BIT(port);
+
+ for (i = 0; i < ocelot->num_phys_ports; i++) {
+ unsigned long bond_mask = ocelot->lags[i];
+
+ if (!bond_mask)
+ continue;
+
+ if (bond_mask & BIT(port)) {
+ mask &= ~bond_mask;
+ break;
+ }
+ }
+
+ ocelot_write_rix(ocelot,
+ BIT(ocelot->num_phys_ports) | mask,
+ ANA_PGID_PGID, PGID_SRC + port);
+ } else {
+ /* Only the CPU port, this is compatible with link
+ * aggregation.
+ */
+ ocelot_write_rix(ocelot,
+ BIT(ocelot->num_phys_ports),
+ ANA_PGID_PGID, PGID_SRC + port);
+ }
+ }
+
+ return 0;
+}
+
+static void ocelot_port_attr_ageing_set(struct ocelot_port *ocelot_port,
+ unsigned long ageing_clock_t)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+ unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t);
+ u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000;
+
+ ocelot_write(ocelot, ANA_AUTOAGE_AGE_PERIOD(ageing_time / 2),
+ ANA_AUTOAGE);
+}
+
+static void ocelot_port_attr_mc_set(struct ocelot_port *port, bool mc)
+{
+ struct ocelot *ocelot = port->ocelot;
+ u32 val = ocelot_read_gix(ocelot, ANA_PORT_CPU_FWD_CFG,
+ port->chip_port);
+
+ if (mc)
+ val |= ANA_PORT_CPU_FWD_CFG_CPU_IGMP_REDIR_ENA |
+ ANA_PORT_CPU_FWD_CFG_CPU_MLD_REDIR_ENA |
+ ANA_PORT_CPU_FWD_CFG_CPU_IPMC_CTRL_COPY_ENA;
+ else
+ val &= ~(ANA_PORT_CPU_FWD_CFG_CPU_IGMP_REDIR_ENA |
+ ANA_PORT_CPU_FWD_CFG_CPU_MLD_REDIR_ENA |
+ ANA_PORT_CPU_FWD_CFG_CPU_IPMC_CTRL_COPY_ENA);
+
+ ocelot_write_gix(ocelot, val, ANA_PORT_CPU_FWD_CFG, port->chip_port);
+}
+
+static int ocelot_port_attr_set(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans)
+{
+ struct ocelot_port *ocelot_port = netdev_priv(dev);
+ int err = 0;
+
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_ID_PORT_STP_STATE:
+ ocelot_port_attr_stp_state_set(ocelot_port, trans,
+ attr->u.stp_state);
+ break;
+ case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
+ ocelot_port_attr_ageing_set(ocelot_port, attr->u.ageing_time);
+ break;
+ case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
+ ocelot_port_attr_mc_set(ocelot_port, !attr->u.mc_disabled);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
+static struct ocelot_multicast *ocelot_multicast_get(struct ocelot *ocelot,
+ const unsigned char *addr,
+ u16 vid)
+{
+ struct ocelot_multicast *mc;
+
+ list_for_each_entry(mc, &ocelot->multicast, list) {
+ if (ether_addr_equal(mc->addr, addr) && mc->vid == vid)
+ return mc;
+ }
+
+ return NULL;
+}
+
+static int ocelot_port_obj_add_mdb(struct net_device *dev,
+ const struct switchdev_obj_port_mdb *mdb,
+ struct switchdev_trans *trans)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ struct ocelot_multicast *mc;
+ unsigned char addr[ETH_ALEN];
+ u16 vid = mdb->vid;
+ bool new = false;
+
+ if (!vid)
+ vid = 1;
+
+ mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
+ if (!mc) {
+ mc = devm_kzalloc(ocelot->dev, sizeof(*mc), GFP_KERNEL);
+ if (!mc)
+ return -ENOMEM;
+
+ memcpy(mc->addr, mdb->addr, ETH_ALEN);
+ mc->vid = vid;
+
+ list_add_tail(&mc->list, &ocelot->multicast);
+ new = true;
+ }
+
+ memcpy(addr, mc->addr, ETH_ALEN);
+ addr[0] = 0;
+
+ if (!new) {
+ addr[2] = mc->ports << 0;
+ addr[1] = mc->ports << 8;
+ ocelot_mact_forget(ocelot, addr, vid);
+ }
+
+ mc->ports |= BIT(port->chip_port);
+ addr[2] = mc->ports << 0;
+ addr[1] = mc->ports << 8;
+
+ return ocelot_mact_learn(ocelot, 0, addr, vid, ENTRYTYPE_MACv4);
+}
+
+static int ocelot_port_obj_del_mdb(struct net_device *dev,
+ const struct switchdev_obj_port_mdb *mdb)
+{
+ struct ocelot_port *port = netdev_priv(dev);
+ struct ocelot *ocelot = port->ocelot;
+ struct ocelot_multicast *mc;
+ unsigned char addr[ETH_ALEN];
+ u16 vid = mdb->vid;
+
+ if (!vid)
+ vid = 1;
+
+ mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
+ if (!mc)
+ return -ENOENT;
+
+ memcpy(addr, mc->addr, ETH_ALEN);
+ addr[2] = mc->ports << 0;
+ addr[1] = mc->ports << 8;
+ addr[0] = 0;
+ ocelot_mact_forget(ocelot, addr, vid);
+
+ mc->ports &= ~BIT(port->chip_port);
+ if (!mc->ports) {
+ list_del(&mc->list);
+ devm_kfree(ocelot->dev, mc);
+ return 0;
+ }
+
+ addr[2] = mc->ports << 0;
+ addr[1] = mc->ports << 8;
+
+ return ocelot_mact_learn(ocelot, 0, addr, vid, ENTRYTYPE_MACv4);
+}
+
+static int ocelot_port_obj_add(struct net_device *dev,
+ const struct switchdev_obj *obj,
+ struct switchdev_trans *trans)
+{
+ int ret = 0;
+
+ switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_MDB:
+ ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj),
+ trans);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return ret;
+}
+
+static int ocelot_port_obj_del(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ int ret = 0;
+
+ switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_MDB:
+ ret = ocelot_port_obj_del_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj));
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return ret;
+}
+
+static const struct switchdev_ops ocelot_port_switchdev_ops = {
+ .switchdev_port_attr_get = ocelot_port_attr_get,
+ .switchdev_port_attr_set = ocelot_port_attr_set,
+ .switchdev_port_obj_add = ocelot_port_obj_add,
+ .switchdev_port_obj_del = ocelot_port_obj_del,
+};
+
+static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
+ struct net_device *bridge)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+
+ if (!ocelot->bridge_mask) {
+ ocelot->hw_bridge_dev = bridge;
+ } else {
+ if (ocelot->hw_bridge_dev != bridge)
+ /* This is adding the port to a second bridge, this is
+ * unsupported */
+ return -ENODEV;
+ }
+
+ ocelot->bridge_mask |= BIT(ocelot_port->chip_port);
+
+ return 0;
+}
+
+static void ocelot_port_bridge_leave(struct ocelot_port *ocelot_port,
+ struct net_device *bridge)
+{
+ struct ocelot *ocelot = ocelot_port->ocelot;
+
+ ocelot->bridge_mask &= ~BIT(ocelot_port->chip_port);
+
+ if (!ocelot->bridge_mask)
+ ocelot->hw_bridge_dev = NULL;
+}
+
+/* Checks if the net_device instance given to us originate from our driver. */
+static bool ocelot_netdevice_dev_check(const struct net_device *dev)
+{
+ return dev->netdev_ops == &ocelot_port_netdev_ops;
+}
+
+static int ocelot_netdevice_port_event(struct net_device *dev,
+ unsigned long event,
+ struct netdev_notifier_changeupper_info *info)
+{
+ struct ocelot_port *ocelot_port = netdev_priv(dev);
+ int err = 0;
+
+ if (!ocelot_netdevice_dev_check(dev))
+ return 0;
+
+ switch (event) {
+ case NETDEV_CHANGEUPPER:
+ if (netif_is_bridge_master(info->upper_dev)) {
+ if (info->linking)
+ err = ocelot_port_bridge_join(ocelot_port,
+ info->upper_dev);
+ else
+ ocelot_port_bridge_leave(ocelot_port,
+ info->upper_dev);
+ }
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
+static int ocelot_netdevice_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct netdev_notifier_changeupper_info *info = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ int ret;
+
+ if (netif_is_lag_master(dev)) {
+ struct net_device *slave;
+ struct list_head *iter;
+
+ netdev_for_each_lower_dev(dev, slave, iter) {
+ ret = ocelot_netdevice_port_event(slave, event, info);
+ if (ret)
+ goto notify;
+ }
+ } else {
+ ret = ocelot_netdevice_port_event(dev, event, info);
+ }
+
+notify:
+ return notifier_from_errno(ret);
+}
+
+struct notifier_block ocelot_netdevice_nb __read_mostly = {
+ .notifier_call = ocelot_netdevice_event,
+};
+EXPORT_SYMBOL(ocelot_netdevice_nb);
+
+int ocelot_probe_port(struct ocelot *ocelot, u8 port,
+ void __iomem *regs,
+ struct phy_device *phy)
+{
+ struct ocelot_port *ocelot_port;
+ struct net_device *dev;
+ int err;
+
+ dev = alloc_etherdev(sizeof(struct ocelot_port));
+ if (!dev)
+ return -ENOMEM;
+ SET_NETDEV_DEV(dev, ocelot->dev);
+ ocelot_port = netdev_priv(dev);
+ ocelot_port->dev = dev;
+ ocelot_port->ocelot = ocelot;
+ ocelot_port->regs = regs;
+ ocelot_port->chip_port = port;
+ ocelot_port->phy = phy;
+ INIT_LIST_HEAD(&ocelot_port->mc);
+ ocelot->ports[port] = ocelot_port;
+
+ dev->netdev_ops = &ocelot_port_netdev_ops;
+ dev->ethtool_ops = &ocelot_ethtool_ops;
+ dev->switchdev_ops = &ocelot_port_switchdev_ops;
+
+ memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
+ dev->dev_addr[ETH_ALEN - 1] += port;
+ ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid,
+ ENTRYTYPE_LOCKED);
+
+ err = register_netdev(dev);
+ if (err) {
+ dev_err(ocelot->dev, "register_netdev failed\n");
+ goto err_register_netdev;
+ }
+
+ return 0;
+
+err_register_netdev:
+ free_netdev(dev);
+ return err;
+}
+EXPORT_SYMBOL(ocelot_probe_port);
+
+int ocelot_init(struct ocelot *ocelot)
+{
+ u32 port;
+ int i, cpu = ocelot->num_phys_ports;
+ char queue_name[32];
+
+ ocelot->stats = devm_kcalloc(ocelot->dev,
+ ocelot->num_phys_ports * ocelot->num_stats,
+ sizeof(u64), GFP_KERNEL);
+ if (!ocelot->stats)
+ return -ENOMEM;
+
+ mutex_init(&ocelot->stats_lock);
+ snprintf(queue_name, sizeof(queue_name), "%s-stats",
+ dev_name(ocelot->dev));
+ ocelot->stats_queue = create_singlethread_workqueue(queue_name);
+ if (!ocelot->stats_queue)
+ return -ENOMEM;
+
+ ocelot_mact_init(ocelot);
+ ocelot_vlan_init(ocelot);
+
+ for (port = 0; port < ocelot->num_phys_ports; port++) {
+ /* Clear all counters (5 groups) */
+ ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port) |
+ SYS_STAT_CFG_STAT_CLEAR_SHOT(0x7f),
+ SYS_STAT_CFG);
+ }
+
+ /* Only use S-Tag */
+ ocelot_write(ocelot, ETH_P_8021AD, SYS_VLAN_ETYPE_CFG);
+
+ /* Aggregation mode */
+ ocelot_write(ocelot, ANA_AGGR_CFG_AC_SMAC_ENA |
+ ANA_AGGR_CFG_AC_DMAC_ENA |
+ ANA_AGGR_CFG_AC_IP4_SIPDIP_ENA |
+ ANA_AGGR_CFG_AC_IP4_TCPUDP_ENA, ANA_AGGR_CFG);
+
+ /* Set MAC age time to default value. The entry is aged after
+ * 2*AGE_PERIOD
+ */
+ ocelot_write(ocelot,
+ ANA_AUTOAGE_AGE_PERIOD(BR_DEFAULT_AGEING_TIME / 2 / HZ),
+ ANA_AUTOAGE);
+
+ /* Disable learning for frames discarded by VLAN ingress filtering */
+ regmap_field_write(ocelot->regfields[ANA_ADVLEARN_VLAN_CHK], 1);
+
+ /* Setup frame ageing - fixed value "2 sec" - in 6.5 us units */
+ ocelot_write(ocelot, SYS_FRM_AGING_AGE_TX_ENA |
+ SYS_FRM_AGING_MAX_AGE(307692), SYS_FRM_AGING);
+
+ /* Setup flooding PGIDs */
+ ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) |
+ ANA_FLOODING_FLD_BROADCAST(PGID_MC) |
+ ANA_FLOODING_FLD_UNICAST(PGID_UC),
+ ANA_FLOODING, 0);
+ ocelot_write(ocelot, ANA_FLOODING_IPMC_FLD_MC6_DATA(PGID_MCIPV6) |
+ ANA_FLOODING_IPMC_FLD_MC6_CTRL(PGID_MC) |
+ ANA_FLOODING_IPMC_FLD_MC4_DATA(PGID_MCIPV4) |
+ ANA_FLOODING_IPMC_FLD_MC4_CTRL(PGID_MC),
+ ANA_FLOODING_IPMC);
+
+ for (port = 0; port < ocelot->num_phys_ports; port++) {
+ /* Transmit the frame to the local port. */
+ ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, port);
+ /* Do not forward BPDU frames to the front ports. */
+ ocelot_write_gix(ocelot,
+ ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0xffff),
+ ANA_PORT_CPU_FWD_BPDU_CFG,
+ port);
+ /* Ensure bridging is disabled */
+ ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, PGID_SRC + port);
+ }
+
+ /* Configure and enable the CPU port. */
+ ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, cpu);
+ ocelot_write_rix(ocelot, BIT(cpu), ANA_PGID_PGID, PGID_CPU);
+ ocelot_write_gix(ocelot, ANA_PORT_PORT_CFG_RECV_ENA |
+ ANA_PORT_PORT_CFG_PORTID_VAL(cpu),
+ ANA_PORT_PORT_CFG, cpu);
+
+ /* Allow broadcast MAC frames. */
+ for (i = ocelot->num_phys_ports + 1; i < PGID_CPU; i++) {
+ u32 val = ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports - 1, 0));
+
+ ocelot_write_rix(ocelot, val, ANA_PGID_PGID, i);
+ }
+ ocelot_write_rix(ocelot,
+ ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)),
+ ANA_PGID_PGID, PGID_MC);
+ ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, PGID_MCIPV4);
+ ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, PGID_MCIPV6);
+
+ /* CPU port Injection/Extraction configuration */
+ ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE |
+ QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) |
+ QSYS_SWITCH_PORT_MODE_PORT_ENA,
+ QSYS_SWITCH_PORT_MODE, cpu);
+ ocelot_write_rix(ocelot, SYS_PORT_MODE_INCL_XTR_HDR(1) |
+ SYS_PORT_MODE_INCL_INJ_HDR(1), SYS_PORT_MODE, cpu);
+ /* Allow manual injection via DEVCPU_QS registers, and byte swap these
+ * registers endianness.
+ */
+ ocelot_write_rix(ocelot, QS_INJ_GRP_CFG_BYTE_SWAP |
+ QS_INJ_GRP_CFG_MODE(1), QS_INJ_GRP_CFG, 0);
+ ocelot_write_rix(ocelot, QS_XTR_GRP_CFG_BYTE_SWAP |
+ QS_XTR_GRP_CFG_MODE(1), QS_XTR_GRP_CFG, 0);
+ ocelot_write(ocelot, ANA_CPUQ_CFG_CPUQ_MIRROR(2) |
+ ANA_CPUQ_CFG_CPUQ_LRN(2) |
+ ANA_CPUQ_CFG_CPUQ_MAC_COPY(2) |
+ ANA_CPUQ_CFG_CPUQ_SRC_COPY(2) |
+ ANA_CPUQ_CFG_CPUQ_LOCKED_PORTMOVE(2) |
+ ANA_CPUQ_CFG_CPUQ_ALLBRIDGE(6) |
+ ANA_CPUQ_CFG_CPUQ_IPMC_CTRL(6) |
+ ANA_CPUQ_CFG_CPUQ_IGMP(6) |
+ ANA_CPUQ_CFG_CPUQ_MLD(6), ANA_CPUQ_CFG);
+ for (i = 0; i < 16; i++)
+ ocelot_write_rix(ocelot, ANA_CPUQ_8021_CFG_CPUQ_GARP_VAL(6) |
+ ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
+ ANA_CPUQ_8021_CFG, i);
+
+ INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+ queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
+ OCELOT_STATS_CHECK_DELAY);
+ return 0;
+}
+EXPORT_SYMBOL(ocelot_init);
+
+void ocelot_deinit(struct ocelot *ocelot)
+{
+ destroy_workqueue(ocelot->stats_queue);
+ mutex_destroy(&ocelot->stats_lock);
+}
+EXPORT_SYMBOL(ocelot_deinit);
+
+MODULE_LICENSE("Dual MIT/GPL");
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_H_
+#define _MSCC_OCELOT_H_
+
+#include <linux/bitops.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "ocelot_ana.h"
+#include "ocelot_dev.h"
+#include "ocelot_hsio.h"
+#include "ocelot_qsys.h"
+#include "ocelot_rew.h"
+#include "ocelot_sys.h"
+#include "ocelot_qs.h"
+
+#define PGID_AGGR 64
+#define PGID_SRC 80
+
+/* Reserved PGIDs */
+#define PGID_CPU (PGID_AGGR - 5)
+#define PGID_UC (PGID_AGGR - 4)
+#define PGID_MC (PGID_AGGR - 3)
+#define PGID_MCIPV4 (PGID_AGGR - 2)
+#define PGID_MCIPV6 (PGID_AGGR - 1)
+
+#define OCELOT_BUFFER_CELL_SZ 60
+
+#define OCELOT_STATS_CHECK_DELAY (2 * HZ)
+
+#define IFH_LEN 4
+
+struct frame_info {
+ u32 len;
+ u16 port;
+ u16 vid;
+ u8 cpuq;
+ u8 tag_type;
+};
+
+#define IFH_INJ_BYPASS BIT(31)
+#define IFH_INJ_POP_CNT_DISABLE (3 << 28)
+
+#define IFH_TAG_TYPE_C 0
+#define IFH_TAG_TYPE_S 1
+
+#define OCELOT_SPEED_2500 0
+#define OCELOT_SPEED_1000 1
+#define OCELOT_SPEED_100 2
+#define OCELOT_SPEED_10 3
+
+#define TARGET_OFFSET 24
+#define REG_MASK GENMASK(TARGET_OFFSET - 1, 0)
+#define REG(reg, offset) [reg & REG_MASK] = offset
+
+enum ocelot_target {
+ ANA = 1,
+ QS,
+ QSYS,
+ REW,
+ SYS,
+ HSIO,
+ TARGET_MAX,
+};
+
+enum ocelot_reg {
+ ANA_ADVLEARN = ANA << TARGET_OFFSET,
+ ANA_VLANMASK,
+ ANA_PORT_B_DOMAIN,
+ ANA_ANAGEFIL,
+ ANA_ANEVENTS,
+ ANA_STORMLIMIT_BURST,
+ ANA_STORMLIMIT_CFG,
+ ANA_ISOLATED_PORTS,
+ ANA_COMMUNITY_PORTS,
+ ANA_AUTOAGE,
+ ANA_MACTOPTIONS,
+ ANA_LEARNDISC,
+ ANA_AGENCTRL,
+ ANA_MIRRORPORTS,
+ ANA_EMIRRORPORTS,
+ ANA_FLOODING,
+ ANA_FLOODING_IPMC,
+ ANA_SFLOW_CFG,
+ ANA_PORT_MODE,
+ ANA_CUT_THRU_CFG,
+ ANA_PGID_PGID,
+ ANA_TABLES_ANMOVED,
+ ANA_TABLES_MACHDATA,
+ ANA_TABLES_MACLDATA,
+ ANA_TABLES_STREAMDATA,
+ ANA_TABLES_MACACCESS,
+ ANA_TABLES_MACTINDX,
+ ANA_TABLES_VLANACCESS,
+ ANA_TABLES_VLANTIDX,
+ ANA_TABLES_ISDXACCESS,
+ ANA_TABLES_ISDXTIDX,
+ ANA_TABLES_ENTRYLIM,
+ ANA_TABLES_PTP_ID_HIGH,
+ ANA_TABLES_PTP_ID_LOW,
+ ANA_TABLES_STREAMACCESS,
+ ANA_TABLES_STREAMTIDX,
+ ANA_TABLES_SEQ_HISTORY,
+ ANA_TABLES_SEQ_MASK,
+ ANA_TABLES_SFID_MASK,
+ ANA_TABLES_SFIDACCESS,
+ ANA_TABLES_SFIDTIDX,
+ ANA_MSTI_STATE,
+ ANA_OAM_UPM_LM_CNT,
+ ANA_SG_ACCESS_CTRL,
+ ANA_SG_CONFIG_REG_1,
+ ANA_SG_CONFIG_REG_2,
+ ANA_SG_CONFIG_REG_3,
+ ANA_SG_CONFIG_REG_4,
+ ANA_SG_CONFIG_REG_5,
+ ANA_SG_GCL_GS_CONFIG,
+ ANA_SG_GCL_TI_CONFIG,
+ ANA_SG_STATUS_REG_1,
+ ANA_SG_STATUS_REG_2,
+ ANA_SG_STATUS_REG_3,
+ ANA_PORT_VLAN_CFG,
+ ANA_PORT_DROP_CFG,
+ ANA_PORT_QOS_CFG,
+ ANA_PORT_VCAP_CFG,
+ ANA_PORT_VCAP_S1_KEY_CFG,
+ ANA_PORT_VCAP_S2_CFG,
+ ANA_PORT_PCP_DEI_MAP,
+ ANA_PORT_CPU_FWD_CFG,
+ ANA_PORT_CPU_FWD_BPDU_CFG,
+ ANA_PORT_CPU_FWD_GARP_CFG,
+ ANA_PORT_CPU_FWD_CCM_CFG,
+ ANA_PORT_PORT_CFG,
+ ANA_PORT_POL_CFG,
+ ANA_PORT_PTP_CFG,
+ ANA_PORT_PTP_DLY1_CFG,
+ ANA_PORT_PTP_DLY2_CFG,
+ ANA_PORT_SFID_CFG,
+ ANA_PFC_PFC_CFG,
+ ANA_PFC_PFC_TIMER,
+ ANA_IPT_OAM_MEP_CFG,
+ ANA_IPT_IPT,
+ ANA_PPT_PPT,
+ ANA_FID_MAP_FID_MAP,
+ ANA_AGGR_CFG,
+ ANA_CPUQ_CFG,
+ ANA_CPUQ_CFG2,
+ ANA_CPUQ_8021_CFG,
+ ANA_DSCP_CFG,
+ ANA_DSCP_REWR_CFG,
+ ANA_VCAP_RNG_TYPE_CFG,
+ ANA_VCAP_RNG_VAL_CFG,
+ ANA_VRAP_CFG,
+ ANA_VRAP_HDR_DATA,
+ ANA_VRAP_HDR_MASK,
+ ANA_DISCARD_CFG,
+ ANA_FID_CFG,
+ ANA_POL_PIR_CFG,
+ ANA_POL_CIR_CFG,
+ ANA_POL_MODE_CFG,
+ ANA_POL_PIR_STATE,
+ ANA_POL_CIR_STATE,
+ ANA_POL_STATE,
+ ANA_POL_FLOWC,
+ ANA_POL_HYST,
+ ANA_POL_MISC_CFG,
+ QS_XTR_GRP_CFG = QS << TARGET_OFFSET,
+ QS_XTR_RD,
+ QS_XTR_FRM_PRUNING,
+ QS_XTR_FLUSH,
+ QS_XTR_DATA_PRESENT,
+ QS_XTR_CFG,
+ QS_INJ_GRP_CFG,
+ QS_INJ_WR,
+ QS_INJ_CTRL,
+ QS_INJ_STATUS,
+ QS_INJ_ERR,
+ QS_INH_DBG,
+ QSYS_PORT_MODE = QSYS << TARGET_OFFSET,
+ QSYS_SWITCH_PORT_MODE,
+ QSYS_STAT_CNT_CFG,
+ QSYS_EEE_CFG,
+ QSYS_EEE_THRES,
+ QSYS_IGR_NO_SHARING,
+ QSYS_EGR_NO_SHARING,
+ QSYS_SW_STATUS,
+ QSYS_EXT_CPU_CFG,
+ QSYS_PAD_CFG,
+ QSYS_CPU_GROUP_MAP,
+ QSYS_QMAP,
+ QSYS_ISDX_SGRP,
+ QSYS_TIMED_FRAME_ENTRY,
+ QSYS_TFRM_MISC,
+ QSYS_TFRM_PORT_DLY,
+ QSYS_TFRM_TIMER_CFG_1,
+ QSYS_TFRM_TIMER_CFG_2,
+ QSYS_TFRM_TIMER_CFG_3,
+ QSYS_TFRM_TIMER_CFG_4,
+ QSYS_TFRM_TIMER_CFG_5,
+ QSYS_TFRM_TIMER_CFG_6,
+ QSYS_TFRM_TIMER_CFG_7,
+ QSYS_TFRM_TIMER_CFG_8,
+ QSYS_RED_PROFILE,
+ QSYS_RES_QOS_MODE,
+ QSYS_RES_CFG,
+ QSYS_RES_STAT,
+ QSYS_EGR_DROP_MODE,
+ QSYS_EQ_CTRL,
+ QSYS_EVENTS_CORE,
+ QSYS_QMAXSDU_CFG_0,
+ QSYS_QMAXSDU_CFG_1,
+ QSYS_QMAXSDU_CFG_2,
+ QSYS_QMAXSDU_CFG_3,
+ QSYS_QMAXSDU_CFG_4,
+ QSYS_QMAXSDU_CFG_5,
+ QSYS_QMAXSDU_CFG_6,
+ QSYS_QMAXSDU_CFG_7,
+ QSYS_PREEMPTION_CFG,
+ QSYS_CIR_CFG,
+ QSYS_EIR_CFG,
+ QSYS_SE_CFG,
+ QSYS_SE_DWRR_CFG,
+ QSYS_SE_CONNECT,
+ QSYS_SE_DLB_SENSE,
+ QSYS_CIR_STATE,
+ QSYS_EIR_STATE,
+ QSYS_SE_STATE,
+ QSYS_HSCH_MISC_CFG,
+ QSYS_TAG_CONFIG,
+ QSYS_TAS_PARAM_CFG_CTRL,
+ QSYS_PORT_MAX_SDU,
+ QSYS_PARAM_CFG_REG_1,
+ QSYS_PARAM_CFG_REG_2,
+ QSYS_PARAM_CFG_REG_3,
+ QSYS_PARAM_CFG_REG_4,
+ QSYS_PARAM_CFG_REG_5,
+ QSYS_GCL_CFG_REG_1,
+ QSYS_GCL_CFG_REG_2,
+ QSYS_PARAM_STATUS_REG_1,
+ QSYS_PARAM_STATUS_REG_2,
+ QSYS_PARAM_STATUS_REG_3,
+ QSYS_PARAM_STATUS_REG_4,
+ QSYS_PARAM_STATUS_REG_5,
+ QSYS_PARAM_STATUS_REG_6,
+ QSYS_PARAM_STATUS_REG_7,
+ QSYS_PARAM_STATUS_REG_8,
+ QSYS_PARAM_STATUS_REG_9,
+ QSYS_GCL_STATUS_REG_1,
+ QSYS_GCL_STATUS_REG_2,
+ REW_PORT_VLAN_CFG = REW << TARGET_OFFSET,
+ REW_TAG_CFG,
+ REW_PORT_CFG,
+ REW_DSCP_CFG,
+ REW_PCP_DEI_QOS_MAP_CFG,
+ REW_PTP_CFG,
+ REW_PTP_DLY1_CFG,
+ REW_RED_TAG_CFG,
+ REW_DSCP_REMAP_DP1_CFG,
+ REW_DSCP_REMAP_CFG,
+ REW_STAT_CFG,
+ REW_REW_STICKY,
+ REW_PPT,
+ SYS_COUNT_RX_OCTETS = SYS << TARGET_OFFSET,
+ SYS_COUNT_RX_UNICAST,
+ SYS_COUNT_RX_MULTICAST,
+ SYS_COUNT_RX_BROADCAST,
+ SYS_COUNT_RX_SHORTS,
+ SYS_COUNT_RX_FRAGMENTS,
+ SYS_COUNT_RX_JABBERS,
+ SYS_COUNT_RX_CRC_ALIGN_ERRS,
+ SYS_COUNT_RX_SYM_ERRS,
+ SYS_COUNT_RX_64,
+ SYS_COUNT_RX_65_127,
+ SYS_COUNT_RX_128_255,
+ SYS_COUNT_RX_256_1023,
+ SYS_COUNT_RX_1024_1526,
+ SYS_COUNT_RX_1527_MAX,
+ SYS_COUNT_RX_PAUSE,
+ SYS_COUNT_RX_CONTROL,
+ SYS_COUNT_RX_LONGS,
+ SYS_COUNT_RX_CLASSIFIED_DROPS,
+ SYS_COUNT_TX_OCTETS,
+ SYS_COUNT_TX_UNICAST,
+ SYS_COUNT_TX_MULTICAST,
+ SYS_COUNT_TX_BROADCAST,
+ SYS_COUNT_TX_COLLISION,
+ SYS_COUNT_TX_DROPS,
+ SYS_COUNT_TX_PAUSE,
+ SYS_COUNT_TX_64,
+ SYS_COUNT_TX_65_127,
+ SYS_COUNT_TX_128_511,
+ SYS_COUNT_TX_512_1023,
+ SYS_COUNT_TX_1024_1526,
+ SYS_COUNT_TX_1527_MAX,
+ SYS_COUNT_TX_AGING,
+ SYS_RESET_CFG,
+ SYS_SR_ETYPE_CFG,
+ SYS_VLAN_ETYPE_CFG,
+ SYS_PORT_MODE,
+ SYS_FRONT_PORT_MODE,
+ SYS_FRM_AGING,
+ SYS_STAT_CFG,
+ SYS_SW_STATUS,
+ SYS_MISC_CFG,
+ SYS_REW_MAC_HIGH_CFG,
+ SYS_REW_MAC_LOW_CFG,
+ SYS_TIMESTAMP_OFFSET,
+ SYS_CMID,
+ SYS_PAUSE_CFG,
+ SYS_PAUSE_TOT_CFG,
+ SYS_ATOP,
+ SYS_ATOP_TOT_CFG,
+ SYS_MAC_FC_CFG,
+ SYS_MMGT,
+ SYS_MMGT_FAST,
+ SYS_EVENTS_DIF,
+ SYS_EVENTS_CORE,
+ SYS_CNT,
+ SYS_PTP_STATUS,
+ SYS_PTP_TXSTAMP,
+ SYS_PTP_NXT,
+ SYS_PTP_CFG,
+ SYS_RAM_INIT,
+ SYS_CM_ADDR,
+ SYS_CM_DATA_WR,
+ SYS_CM_DATA_RD,
+ SYS_CM_OP,
+ SYS_CM_DATA,
+ HSIO_PLL5G_CFG0 = HSIO << TARGET_OFFSET,
+ HSIO_PLL5G_CFG1,
+ HSIO_PLL5G_CFG2,
+ HSIO_PLL5G_CFG3,
+ HSIO_PLL5G_CFG4,
+ HSIO_PLL5G_CFG5,
+ HSIO_PLL5G_CFG6,
+ HSIO_PLL5G_STATUS0,
+ HSIO_PLL5G_STATUS1,
+ HSIO_PLL5G_BIST_CFG0,
+ HSIO_PLL5G_BIST_CFG1,
+ HSIO_PLL5G_BIST_CFG2,
+ HSIO_PLL5G_BIST_STAT0,
+ HSIO_PLL5G_BIST_STAT1,
+ HSIO_RCOMP_CFG0,
+ HSIO_RCOMP_STATUS,
+ HSIO_SYNC_ETH_CFG,
+ HSIO_SYNC_ETH_PLL_CFG,
+ HSIO_S1G_DES_CFG,
+ HSIO_S1G_IB_CFG,
+ HSIO_S1G_OB_CFG,
+ HSIO_S1G_SER_CFG,
+ HSIO_S1G_COMMON_CFG,
+ HSIO_S1G_PLL_CFG,
+ HSIO_S1G_PLL_STATUS,
+ HSIO_S1G_DFT_CFG0,
+ HSIO_S1G_DFT_CFG1,
+ HSIO_S1G_DFT_CFG2,
+ HSIO_S1G_TP_CFG,
+ HSIO_S1G_RC_PLL_BIST_CFG,
+ HSIO_S1G_MISC_CFG,
+ HSIO_S1G_DFT_STATUS,
+ HSIO_S1G_MISC_STATUS,
+ HSIO_MCB_S1G_ADDR_CFG,
+ HSIO_S6G_DIG_CFG,
+ HSIO_S6G_DFT_CFG0,
+ HSIO_S6G_DFT_CFG1,
+ HSIO_S6G_DFT_CFG2,
+ HSIO_S6G_TP_CFG0,
+ HSIO_S6G_TP_CFG1,
+ HSIO_S6G_RC_PLL_BIST_CFG,
+ HSIO_S6G_MISC_CFG,
+ HSIO_S6G_OB_ANEG_CFG,
+ HSIO_S6G_DFT_STATUS,
+ HSIO_S6G_ERR_CNT,
+ HSIO_S6G_MISC_STATUS,
+ HSIO_S6G_DES_CFG,
+ HSIO_S6G_IB_CFG,
+ HSIO_S6G_IB_CFG1,
+ HSIO_S6G_IB_CFG2,
+ HSIO_S6G_IB_CFG3,
+ HSIO_S6G_IB_CFG4,
+ HSIO_S6G_IB_CFG5,
+ HSIO_S6G_OB_CFG,
+ HSIO_S6G_OB_CFG1,
+ HSIO_S6G_SER_CFG,
+ HSIO_S6G_COMMON_CFG,
+ HSIO_S6G_PLL_CFG,
+ HSIO_S6G_ACJTAG_CFG,
+ HSIO_S6G_GP_CFG,
+ HSIO_S6G_IB_STATUS0,
+ HSIO_S6G_IB_STATUS1,
+ HSIO_S6G_ACJTAG_STATUS,
+ HSIO_S6G_PLL_STATUS,
+ HSIO_S6G_REVID,
+ HSIO_MCB_S6G_ADDR_CFG,
+ HSIO_HW_CFG,
+ HSIO_HW_QSGMII_CFG,
+ HSIO_HW_QSGMII_STAT,
+ HSIO_CLK_CFG,
+ HSIO_TEMP_SENSOR_CTRL,
+ HSIO_TEMP_SENSOR_CFG,
+ HSIO_TEMP_SENSOR_STAT,
+};
+
+enum ocelot_regfield {
+ ANA_ADVLEARN_VLAN_CHK,
+ ANA_ADVLEARN_LEARN_MIRROR,
+ ANA_ANEVENTS_FLOOD_DISCARD,
+ ANA_ANEVENTS_MSTI_DROP,
+ ANA_ANEVENTS_ACLKILL,
+ ANA_ANEVENTS_ACLUSED,
+ ANA_ANEVENTS_AUTOAGE,
+ ANA_ANEVENTS_VS2TTL1,
+ ANA_ANEVENTS_STORM_DROP,
+ ANA_ANEVENTS_LEARN_DROP,
+ ANA_ANEVENTS_AGED_ENTRY,
+ ANA_ANEVENTS_CPU_LEARN_FAILED,
+ ANA_ANEVENTS_AUTO_LEARN_FAILED,
+ ANA_ANEVENTS_LEARN_REMOVE,
+ ANA_ANEVENTS_AUTO_LEARNED,
+ ANA_ANEVENTS_AUTO_MOVED,
+ ANA_ANEVENTS_DROPPED,
+ ANA_ANEVENTS_CLASSIFIED_DROP,
+ ANA_ANEVENTS_CLASSIFIED_COPY,
+ ANA_ANEVENTS_VLAN_DISCARD,
+ ANA_ANEVENTS_FWD_DISCARD,
+ ANA_ANEVENTS_MULTICAST_FLOOD,
+ ANA_ANEVENTS_UNICAST_FLOOD,
+ ANA_ANEVENTS_DEST_KNOWN,
+ ANA_ANEVENTS_BUCKET3_MATCH,
+ ANA_ANEVENTS_BUCKET2_MATCH,
+ ANA_ANEVENTS_BUCKET1_MATCH,
+ ANA_ANEVENTS_BUCKET0_MATCH,
+ ANA_ANEVENTS_CPU_OPERATION,
+ ANA_ANEVENTS_DMAC_LOOKUP,
+ ANA_ANEVENTS_SMAC_LOOKUP,
+ ANA_ANEVENTS_SEQ_GEN_ERR_0,
+ ANA_ANEVENTS_SEQ_GEN_ERR_1,
+ ANA_TABLES_MACACCESS_B_DOM,
+ ANA_TABLES_MACTINDX_BUCKET,
+ ANA_TABLES_MACTINDX_M_INDEX,
+ QSYS_TIMED_FRAME_ENTRY_TFRM_VLD,
+ QSYS_TIMED_FRAME_ENTRY_TFRM_FP,
+ QSYS_TIMED_FRAME_ENTRY_TFRM_PORTNO,
+ QSYS_TIMED_FRAME_ENTRY_TFRM_TM_SEL,
+ QSYS_TIMED_FRAME_ENTRY_TFRM_TM_T,
+ SYS_RESET_CFG_CORE_ENA,
+ SYS_RESET_CFG_MEM_ENA,
+ SYS_RESET_CFG_MEM_INIT,
+ REGFIELD_MAX
+};
+
+struct ocelot_multicast {
+ struct list_head list;
+ unsigned char addr[ETH_ALEN];
+ u16 vid;
+ u16 ports;
+};
+
+struct ocelot_port;
+
+struct ocelot_stat_layout {
+ u32 offset;
+ char name[ETH_GSTRING_LEN];
+};
+
+struct ocelot {
+ struct device *dev;
+
+ struct regmap *targets[TARGET_MAX];
+ struct regmap_field *regfields[REGFIELD_MAX];
+ const u32 *const *map;
+ const struct ocelot_stat_layout *stats_layout;
+ unsigned int num_stats;
+
+ u8 base_mac[ETH_ALEN];
+
+ struct net_device *hw_bridge_dev;
+ u16 bridge_mask;
+ u16 bridge_fwd_mask;
+
+ struct workqueue_struct *ocelot_owq;
+
+ int shared_queue_sz;
+
+ u8 num_phys_ports;
+ u8 num_cpu_ports;
+ struct ocelot_port **ports;
+
+ u16 lags[16];
+
+ /* Keep track of the vlan port masks */
+ u32 vlan_mask[VLAN_N_VID];
+
+ struct list_head multicast;
+
+ /* Workqueue to check statistics for overflow with its lock */
+ struct mutex stats_lock;
+ u64 *stats;
+ struct delayed_work stats_work;
+ struct workqueue_struct *stats_queue;
+};
+
+struct ocelot_port {
+ struct net_device *dev;
+ struct ocelot *ocelot;
+ struct phy_device *phy;
+ void __iomem *regs;
+ u8 chip_port;
+ /* Keep a track of the mc addresses added to the mac table, so that they
+ * can be removed when needed.
+ */
+ struct list_head mc;
+
+ /* Ingress default VLAN (pvid) */
+ u16 pvid;
+
+ /* Egress default VLAN (vid) */
+ u16 vid;
+
+ u8 vlan_aware;
+
+ u64 *stats;
+};
+
+u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset);
+#define ocelot_read_ix(ocelot, reg, gi, ri) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_read_gix(ocelot, reg, gi) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi))
+#define ocelot_read_rix(ocelot, reg, ri) __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri))
+#define ocelot_read(ocelot, reg) __ocelot_read_ix(ocelot, reg, 0)
+
+void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
+#define ocelot_write_ix(ocelot, val, reg, gi, ri) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_write_gix(ocelot, val, reg, gi) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi))
+#define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri))
+#define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0)
+
+void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 mask,
+ u32 offset);
+#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi))
+#define ocelot_rmw_rix(ocelot, val, m, reg, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri))
+#define ocelot_rmw(ocelot, val, m, reg) __ocelot_rmw_ix(ocelot, val, m, reg, 0)
+
+u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
+void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
+
+int ocelot_regfields_init(struct ocelot *ocelot,
+ const struct reg_field *const regfields);
+struct regmap *ocelot_io_platform_init(struct ocelot *ocelot,
+ struct platform_device *pdev,
+ const char *name);
+
+#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val))
+#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val))
+
+int ocelot_init(struct ocelot *ocelot);
+void ocelot_deinit(struct ocelot *ocelot);
+int ocelot_chip_init(struct ocelot *ocelot);
+int ocelot_probe_port(struct ocelot *ocelot, u8 port,
+ void __iomem *regs,
+ struct phy_device *phy);
+
+extern struct notifier_block ocelot_netdevice_nb;
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_ANA_H_
+#define _MSCC_OCELOT_ANA_H_
+
+#define ANA_ANAGEFIL_B_DOM_EN BIT(22)
+#define ANA_ANAGEFIL_B_DOM_VAL BIT(21)
+#define ANA_ANAGEFIL_AGE_LOCKED BIT(20)
+#define ANA_ANAGEFIL_PID_EN BIT(19)
+#define ANA_ANAGEFIL_PID_VAL(x) (((x) << 14) & GENMASK(18, 14))
+#define ANA_ANAGEFIL_PID_VAL_M GENMASK(18, 14)
+#define ANA_ANAGEFIL_PID_VAL_X(x) (((x) & GENMASK(18, 14)) >> 14)
+#define ANA_ANAGEFIL_VID_EN BIT(13)
+#define ANA_ANAGEFIL_VID_VAL(x) ((x) & GENMASK(12, 0))
+#define ANA_ANAGEFIL_VID_VAL_M GENMASK(12, 0)
+
+#define ANA_STORMLIMIT_CFG_RSZ 0x4
+
+#define ANA_STORMLIMIT_CFG_STORM_RATE(x) (((x) << 3) & GENMASK(6, 3))
+#define ANA_STORMLIMIT_CFG_STORM_RATE_M GENMASK(6, 3)
+#define ANA_STORMLIMIT_CFG_STORM_RATE_X(x) (((x) & GENMASK(6, 3)) >> 3)
+#define ANA_STORMLIMIT_CFG_STORM_UNIT BIT(2)
+#define ANA_STORMLIMIT_CFG_STORM_MODE(x) ((x) & GENMASK(1, 0))
+#define ANA_STORMLIMIT_CFG_STORM_MODE_M GENMASK(1, 0)
+
+#define ANA_AUTOAGE_AGE_FAST BIT(21)
+#define ANA_AUTOAGE_AGE_PERIOD(x) (((x) << 1) & GENMASK(20, 1))
+#define ANA_AUTOAGE_AGE_PERIOD_M GENMASK(20, 1)
+#define ANA_AUTOAGE_AGE_PERIOD_X(x) (((x) & GENMASK(20, 1)) >> 1)
+#define ANA_AUTOAGE_AUTOAGE_LOCKED BIT(0)
+
+#define ANA_MACTOPTIONS_REDUCED_TABLE BIT(1)
+#define ANA_MACTOPTIONS_SHADOW BIT(0)
+
+#define ANA_AGENCTRL_FID_MASK(x) (((x) << 12) & GENMASK(23, 12))
+#define ANA_AGENCTRL_FID_MASK_M GENMASK(23, 12)
+#define ANA_AGENCTRL_FID_MASK_X(x) (((x) & GENMASK(23, 12)) >> 12)
+#define ANA_AGENCTRL_IGNORE_DMAC_FLAGS BIT(11)
+#define ANA_AGENCTRL_IGNORE_SMAC_FLAGS BIT(10)
+#define ANA_AGENCTRL_FLOOD_SPECIAL BIT(9)
+#define ANA_AGENCTRL_FLOOD_IGNORE_VLAN BIT(8)
+#define ANA_AGENCTRL_MIRROR_CPU BIT(7)
+#define ANA_AGENCTRL_LEARN_CPU_COPY BIT(6)
+#define ANA_AGENCTRL_LEARN_FWD_KILL BIT(5)
+#define ANA_AGENCTRL_LEARN_IGNORE_VLAN BIT(4)
+#define ANA_AGENCTRL_CPU_CPU_KILL_ENA BIT(3)
+#define ANA_AGENCTRL_GREEN_COUNT_MODE BIT(2)
+#define ANA_AGENCTRL_YELLOW_COUNT_MODE BIT(1)
+#define ANA_AGENCTRL_RED_COUNT_MODE BIT(0)
+
+#define ANA_FLOODING_RSZ 0x4
+
+#define ANA_FLOODING_FLD_UNICAST(x) (((x) << 12) & GENMASK(17, 12))
+#define ANA_FLOODING_FLD_UNICAST_M GENMASK(17, 12)
+#define ANA_FLOODING_FLD_UNICAST_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define ANA_FLOODING_FLD_BROADCAST(x) (((x) << 6) & GENMASK(11, 6))
+#define ANA_FLOODING_FLD_BROADCAST_M GENMASK(11, 6)
+#define ANA_FLOODING_FLD_BROADCAST_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define ANA_FLOODING_FLD_MULTICAST(x) ((x) & GENMASK(5, 0))
+#define ANA_FLOODING_FLD_MULTICAST_M GENMASK(5, 0)
+
+#define ANA_FLOODING_IPMC_FLD_MC4_CTRL(x) (((x) << 18) & GENMASK(23, 18))
+#define ANA_FLOODING_IPMC_FLD_MC4_CTRL_M GENMASK(23, 18)
+#define ANA_FLOODING_IPMC_FLD_MC4_CTRL_X(x) (((x) & GENMASK(23, 18)) >> 18)
+#define ANA_FLOODING_IPMC_FLD_MC4_DATA(x) (((x) << 12) & GENMASK(17, 12))
+#define ANA_FLOODING_IPMC_FLD_MC4_DATA_M GENMASK(17, 12)
+#define ANA_FLOODING_IPMC_FLD_MC4_DATA_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define ANA_FLOODING_IPMC_FLD_MC6_CTRL(x) (((x) << 6) & GENMASK(11, 6))
+#define ANA_FLOODING_IPMC_FLD_MC6_CTRL_M GENMASK(11, 6)
+#define ANA_FLOODING_IPMC_FLD_MC6_CTRL_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define ANA_FLOODING_IPMC_FLD_MC6_DATA(x) ((x) & GENMASK(5, 0))
+#define ANA_FLOODING_IPMC_FLD_MC6_DATA_M GENMASK(5, 0)
+
+#define ANA_SFLOW_CFG_RSZ 0x4
+
+#define ANA_SFLOW_CFG_SF_RATE(x) (((x) << 2) & GENMASK(13, 2))
+#define ANA_SFLOW_CFG_SF_RATE_M GENMASK(13, 2)
+#define ANA_SFLOW_CFG_SF_RATE_X(x) (((x) & GENMASK(13, 2)) >> 2)
+#define ANA_SFLOW_CFG_SF_SAMPLE_RX BIT(1)
+#define ANA_SFLOW_CFG_SF_SAMPLE_TX BIT(0)
+
+#define ANA_PORT_MODE_RSZ 0x4
+
+#define ANA_PORT_MODE_REDTAG_PARSE_CFG BIT(3)
+#define ANA_PORT_MODE_VLAN_PARSE_CFG(x) (((x) << 1) & GENMASK(2, 1))
+#define ANA_PORT_MODE_VLAN_PARSE_CFG_M GENMASK(2, 1)
+#define ANA_PORT_MODE_VLAN_PARSE_CFG_X(x) (((x) & GENMASK(2, 1)) >> 1)
+#define ANA_PORT_MODE_L3_PARSE_CFG BIT(0)
+
+#define ANA_CUT_THRU_CFG_RSZ 0x4
+
+#define ANA_PGID_PGID_RSZ 0x4
+
+#define ANA_PGID_PGID_PGID(x) ((x) & GENMASK(11, 0))
+#define ANA_PGID_PGID_PGID_M GENMASK(11, 0)
+#define ANA_PGID_PGID_CPUQ_DST_PGID(x) (((x) << 27) & GENMASK(29, 27))
+#define ANA_PGID_PGID_CPUQ_DST_PGID_M GENMASK(29, 27)
+#define ANA_PGID_PGID_CPUQ_DST_PGID_X(x) (((x) & GENMASK(29, 27)) >> 27)
+
+#define ANA_TABLES_MACHDATA_VID(x) (((x) << 16) & GENMASK(28, 16))
+#define ANA_TABLES_MACHDATA_VID_M GENMASK(28, 16)
+#define ANA_TABLES_MACHDATA_VID_X(x) (((x) & GENMASK(28, 16)) >> 16)
+#define ANA_TABLES_MACHDATA_MACHDATA(x) ((x) & GENMASK(15, 0))
+#define ANA_TABLES_MACHDATA_MACHDATA_M GENMASK(15, 0)
+
+#define ANA_TABLES_STREAMDATA_SSID_VALID BIT(16)
+#define ANA_TABLES_STREAMDATA_SSID(x) (((x) << 9) & GENMASK(15, 9))
+#define ANA_TABLES_STREAMDATA_SSID_M GENMASK(15, 9)
+#define ANA_TABLES_STREAMDATA_SSID_X(x) (((x) & GENMASK(15, 9)) >> 9)
+#define ANA_TABLES_STREAMDATA_SFID_VALID BIT(8)
+#define ANA_TABLES_STREAMDATA_SFID(x) ((x) & GENMASK(7, 0))
+#define ANA_TABLES_STREAMDATA_SFID_M GENMASK(7, 0)
+
+#define ANA_TABLES_MACACCESS_MAC_CPU_COPY BIT(15)
+#define ANA_TABLES_MACACCESS_SRC_KILL BIT(14)
+#define ANA_TABLES_MACACCESS_IGNORE_VLAN BIT(13)
+#define ANA_TABLES_MACACCESS_AGED_FLAG BIT(12)
+#define ANA_TABLES_MACACCESS_VALID BIT(11)
+#define ANA_TABLES_MACACCESS_ENTRYTYPE(x) (((x) << 9) & GENMASK(10, 9))
+#define ANA_TABLES_MACACCESS_ENTRYTYPE_M GENMASK(10, 9)
+#define ANA_TABLES_MACACCESS_ENTRYTYPE_X(x) (((x) & GENMASK(10, 9)) >> 9)
+#define ANA_TABLES_MACACCESS_DEST_IDX(x) (((x) << 3) & GENMASK(8, 3))
+#define ANA_TABLES_MACACCESS_DEST_IDX_M GENMASK(8, 3)
+#define ANA_TABLES_MACACCESS_DEST_IDX_X(x) (((x) & GENMASK(8, 3)) >> 3)
+#define ANA_TABLES_MACACCESS_MAC_TABLE_CMD(x) ((x) & GENMASK(2, 0))
+#define ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M GENMASK(2, 0)
+#define MACACCESS_CMD_IDLE 0
+#define MACACCESS_CMD_LEARN 1
+#define MACACCESS_CMD_FORGET 2
+#define MACACCESS_CMD_AGE 3
+#define MACACCESS_CMD_GET_NEXT 4
+#define MACACCESS_CMD_INIT 5
+#define MACACCESS_CMD_READ 6
+#define MACACCESS_CMD_WRITE 7
+
+#define ANA_TABLES_VLANACCESS_VLAN_PORT_MASK(x) (((x) << 2) & GENMASK(13, 2))
+#define ANA_TABLES_VLANACCESS_VLAN_PORT_MASK_M GENMASK(13, 2)
+#define ANA_TABLES_VLANACCESS_VLAN_PORT_MASK_X(x) (((x) & GENMASK(13, 2)) >> 2)
+#define ANA_TABLES_VLANACCESS_VLAN_TBL_CMD(x) ((x) & GENMASK(1, 0))
+#define ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M GENMASK(1, 0)
+#define ANA_TABLES_VLANACCESS_CMD_IDLE 0x0
+#define ANA_TABLES_VLANACCESS_CMD_WRITE 0x2
+#define ANA_TABLES_VLANACCESS_CMD_INIT 0x3
+
+#define ANA_TABLES_VLANTIDX_VLAN_SEC_FWD_ENA BIT(17)
+#define ANA_TABLES_VLANTIDX_VLAN_FLOOD_DIS BIT(16)
+#define ANA_TABLES_VLANTIDX_VLAN_PRIV_VLAN BIT(15)
+#define ANA_TABLES_VLANTIDX_VLAN_LEARN_DISABLED BIT(14)
+#define ANA_TABLES_VLANTIDX_VLAN_MIRROR BIT(13)
+#define ANA_TABLES_VLANTIDX_VLAN_SRC_CHK BIT(12)
+#define ANA_TABLES_VLANTIDX_V_INDEX(x) ((x) & GENMASK(11, 0))
+#define ANA_TABLES_VLANTIDX_V_INDEX_M GENMASK(11, 0)
+
+#define ANA_TABLES_ISDXACCESS_ISDX_PORT_MASK(x) (((x) << 2) & GENMASK(8, 2))
+#define ANA_TABLES_ISDXACCESS_ISDX_PORT_MASK_M GENMASK(8, 2)
+#define ANA_TABLES_ISDXACCESS_ISDX_PORT_MASK_X(x) (((x) & GENMASK(8, 2)) >> 2)
+#define ANA_TABLES_ISDXACCESS_ISDX_TBL_CMD(x) ((x) & GENMASK(1, 0))
+#define ANA_TABLES_ISDXACCESS_ISDX_TBL_CMD_M GENMASK(1, 0)
+
+#define ANA_TABLES_ISDXTIDX_ISDX_SDLBI(x) (((x) << 21) & GENMASK(28, 21))
+#define ANA_TABLES_ISDXTIDX_ISDX_SDLBI_M GENMASK(28, 21)
+#define ANA_TABLES_ISDXTIDX_ISDX_SDLBI_X(x) (((x) & GENMASK(28, 21)) >> 21)
+#define ANA_TABLES_ISDXTIDX_ISDX_MSTI(x) (((x) << 15) & GENMASK(20, 15))
+#define ANA_TABLES_ISDXTIDX_ISDX_MSTI_M GENMASK(20, 15)
+#define ANA_TABLES_ISDXTIDX_ISDX_MSTI_X(x) (((x) & GENMASK(20, 15)) >> 15)
+#define ANA_TABLES_ISDXTIDX_ISDX_ES0_KEY_ENA BIT(14)
+#define ANA_TABLES_ISDXTIDX_ISDX_FORCE_ENA BIT(10)
+#define ANA_TABLES_ISDXTIDX_ISDX_INDEX(x) ((x) & GENMASK(7, 0))
+#define ANA_TABLES_ISDXTIDX_ISDX_INDEX_M GENMASK(7, 0)
+
+#define ANA_TABLES_ENTRYLIM_RSZ 0x4
+
+#define ANA_TABLES_ENTRYLIM_ENTRYLIM(x) (((x) << 14) & GENMASK(17, 14))
+#define ANA_TABLES_ENTRYLIM_ENTRYLIM_M GENMASK(17, 14)
+#define ANA_TABLES_ENTRYLIM_ENTRYLIM_X(x) (((x) & GENMASK(17, 14)) >> 14)
+#define ANA_TABLES_ENTRYLIM_ENTRYSTAT(x) ((x) & GENMASK(13, 0))
+#define ANA_TABLES_ENTRYLIM_ENTRYSTAT_M GENMASK(13, 0)
+
+#define ANA_TABLES_STREAMACCESS_GEN_REC_SEQ_NUM(x) (((x) << 4) & GENMASK(31, 4))
+#define ANA_TABLES_STREAMACCESS_GEN_REC_SEQ_NUM_M GENMASK(31, 4)
+#define ANA_TABLES_STREAMACCESS_GEN_REC_SEQ_NUM_X(x) (((x) & GENMASK(31, 4)) >> 4)
+#define ANA_TABLES_STREAMACCESS_SEQ_GEN_REC_ENA BIT(3)
+#define ANA_TABLES_STREAMACCESS_GEN_REC_TYPE BIT(2)
+#define ANA_TABLES_STREAMACCESS_STREAM_TBL_CMD(x) ((x) & GENMASK(1, 0))
+#define ANA_TABLES_STREAMACCESS_STREAM_TBL_CMD_M GENMASK(1, 0)
+
+#define ANA_TABLES_STREAMTIDX_SEQ_GEN_ERR_STATUS(x) (((x) << 30) & GENMASK(31, 30))
+#define ANA_TABLES_STREAMTIDX_SEQ_GEN_ERR_STATUS_M GENMASK(31, 30)
+#define ANA_TABLES_STREAMTIDX_SEQ_GEN_ERR_STATUS_X(x) (((x) & GENMASK(31, 30)) >> 30)
+#define ANA_TABLES_STREAMTIDX_S_INDEX(x) (((x) << 16) & GENMASK(22, 16))
+#define ANA_TABLES_STREAMTIDX_S_INDEX_M GENMASK(22, 16)
+#define ANA_TABLES_STREAMTIDX_S_INDEX_X(x) (((x) & GENMASK(22, 16)) >> 16)
+#define ANA_TABLES_STREAMTIDX_FORCE_SF_BEHAVIOUR BIT(14)
+#define ANA_TABLES_STREAMTIDX_SEQ_HISTORY_LEN(x) (((x) << 8) & GENMASK(13, 8))
+#define ANA_TABLES_STREAMTIDX_SEQ_HISTORY_LEN_M GENMASK(13, 8)
+#define ANA_TABLES_STREAMTIDX_SEQ_HISTORY_LEN_X(x) (((x) & GENMASK(13, 8)) >> 8)
+#define ANA_TABLES_STREAMTIDX_RESET_ON_ROGUE BIT(7)
+#define ANA_TABLES_STREAMTIDX_REDTAG_POP BIT(6)
+#define ANA_TABLES_STREAMTIDX_STREAM_SPLIT BIT(5)
+#define ANA_TABLES_STREAMTIDX_SEQ_SPACE_LOG2(x) ((x) & GENMASK(4, 0))
+#define ANA_TABLES_STREAMTIDX_SEQ_SPACE_LOG2_M GENMASK(4, 0)
+
+#define ANA_TABLES_SEQ_MASK_SPLIT_MASK(x) (((x) << 16) & GENMASK(22, 16))
+#define ANA_TABLES_SEQ_MASK_SPLIT_MASK_M GENMASK(22, 16)
+#define ANA_TABLES_SEQ_MASK_SPLIT_MASK_X(x) (((x) & GENMASK(22, 16)) >> 16)
+#define ANA_TABLES_SEQ_MASK_INPUT_PORT_MASK(x) ((x) & GENMASK(6, 0))
+#define ANA_TABLES_SEQ_MASK_INPUT_PORT_MASK_M GENMASK(6, 0)
+
+#define ANA_TABLES_SFID_MASK_IGR_PORT_MASK(x) (((x) << 1) & GENMASK(7, 1))
+#define ANA_TABLES_SFID_MASK_IGR_PORT_MASK_M GENMASK(7, 1)
+#define ANA_TABLES_SFID_MASK_IGR_PORT_MASK_X(x) (((x) & GENMASK(7, 1)) >> 1)
+#define ANA_TABLES_SFID_MASK_IGR_SRCPORT_MATCH_ENA BIT(0)
+
+#define ANA_TABLES_SFIDACCESS_IGR_PRIO_MATCH_ENA BIT(22)
+#define ANA_TABLES_SFIDACCESS_IGR_PRIO(x) (((x) << 19) & GENMASK(21, 19))
+#define ANA_TABLES_SFIDACCESS_IGR_PRIO_M GENMASK(21, 19)
+#define ANA_TABLES_SFIDACCESS_IGR_PRIO_X(x) (((x) & GENMASK(21, 19)) >> 19)
+#define ANA_TABLES_SFIDACCESS_FORCE_BLOCK BIT(18)
+#define ANA_TABLES_SFIDACCESS_MAX_SDU_LEN(x) (((x) << 2) & GENMASK(17, 2))
+#define ANA_TABLES_SFIDACCESS_MAX_SDU_LEN_M GENMASK(17, 2)
+#define ANA_TABLES_SFIDACCESS_MAX_SDU_LEN_X(x) (((x) & GENMASK(17, 2)) >> 2)
+#define ANA_TABLES_SFIDACCESS_SFID_TBL_CMD(x) ((x) & GENMASK(1, 0))
+#define ANA_TABLES_SFIDACCESS_SFID_TBL_CMD_M GENMASK(1, 0)
+
+#define ANA_TABLES_SFIDTIDX_SGID_VALID BIT(26)
+#define ANA_TABLES_SFIDTIDX_SGID(x) (((x) << 18) & GENMASK(25, 18))
+#define ANA_TABLES_SFIDTIDX_SGID_M GENMASK(25, 18)
+#define ANA_TABLES_SFIDTIDX_SGID_X(x) (((x) & GENMASK(25, 18)) >> 18)
+#define ANA_TABLES_SFIDTIDX_POL_ENA BIT(17)
+#define ANA_TABLES_SFIDTIDX_POL_IDX(x) (((x) << 8) & GENMASK(16, 8))
+#define ANA_TABLES_SFIDTIDX_POL_IDX_M GENMASK(16, 8)
+#define ANA_TABLES_SFIDTIDX_POL_IDX_X(x) (((x) & GENMASK(16, 8)) >> 8)
+#define ANA_TABLES_SFIDTIDX_SFID_INDEX(x) ((x) & GENMASK(7, 0))
+#define ANA_TABLES_SFIDTIDX_SFID_INDEX_M GENMASK(7, 0)
+
+#define ANA_MSTI_STATE_RSZ 0x4
+
+#define ANA_OAM_UPM_LM_CNT_RSZ 0x4
+
+#define ANA_SG_ACCESS_CTRL_SGID(x) ((x) & GENMASK(7, 0))
+#define ANA_SG_ACCESS_CTRL_SGID_M GENMASK(7, 0)
+#define ANA_SG_ACCESS_CTRL_CONFIG_CHANGE BIT(28)
+
+#define ANA_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB(x) ((x) & GENMASK(15, 0))
+#define ANA_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_M GENMASK(15, 0)
+#define ANA_SG_CONFIG_REG_3_LIST_LENGTH(x) (((x) << 16) & GENMASK(18, 16))
+#define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M GENMASK(18, 16)
+#define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(18, 16)) >> 16)
+#define ANA_SG_CONFIG_REG_3_GATE_ENABLE BIT(20)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 24) & GENMASK(27, 24))
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(27, 24)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(27, 24)) >> 24)
+#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(28)
+
+#define ANA_SG_GCL_GS_CONFIG_RSZ 0x4
+
+#define ANA_SG_GCL_GS_CONFIG_IPS(x) ((x) & GENMASK(3, 0))
+#define ANA_SG_GCL_GS_CONFIG_IPS_M GENMASK(3, 0)
+#define ANA_SG_GCL_GS_CONFIG_GATE_STATE BIT(4)
+
+#define ANA_SG_GCL_TI_CONFIG_RSZ 0x4
+
+#define ANA_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB(x) ((x) & GENMASK(15, 0))
+#define ANA_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB_M GENMASK(15, 0)
+#define ANA_SG_STATUS_REG_3_GATE_STATE BIT(16)
+#define ANA_SG_STATUS_REG_3_IPS(x) (((x) << 20) & GENMASK(23, 20))
+#define ANA_SG_STATUS_REG_3_IPS_M GENMASK(23, 20)
+#define ANA_SG_STATUS_REG_3_IPS_X(x) (((x) & GENMASK(23, 20)) >> 20)
+#define ANA_SG_STATUS_REG_3_CONFIG_PENDING BIT(24)
+
+#define ANA_PORT_VLAN_CFG_GSZ 0x100
+
+#define ANA_PORT_VLAN_CFG_VLAN_VID_AS_ISDX BIT(21)
+#define ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA BIT(20)
+#define ANA_PORT_VLAN_CFG_VLAN_POP_CNT(x) (((x) << 18) & GENMASK(19, 18))
+#define ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M GENMASK(19, 18)
+#define ANA_PORT_VLAN_CFG_VLAN_POP_CNT_X(x) (((x) & GENMASK(19, 18)) >> 18)
+#define ANA_PORT_VLAN_CFG_VLAN_INNER_TAG_ENA BIT(17)
+#define ANA_PORT_VLAN_CFG_VLAN_TAG_TYPE BIT(16)
+#define ANA_PORT_VLAN_CFG_VLAN_DEI BIT(15)
+#define ANA_PORT_VLAN_CFG_VLAN_PCP(x) (((x) << 12) & GENMASK(14, 12))
+#define ANA_PORT_VLAN_CFG_VLAN_PCP_M GENMASK(14, 12)
+#define ANA_PORT_VLAN_CFG_VLAN_PCP_X(x) (((x) & GENMASK(14, 12)) >> 12)
+#define ANA_PORT_VLAN_CFG_VLAN_VID(x) ((x) & GENMASK(11, 0))
+#define ANA_PORT_VLAN_CFG_VLAN_VID_M GENMASK(11, 0)
+
+#define ANA_PORT_DROP_CFG_GSZ 0x100
+
+#define ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA BIT(6)
+#define ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA BIT(5)
+#define ANA_PORT_DROP_CFG_DROP_C_TAGGED_ENA BIT(4)
+#define ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA BIT(3)
+#define ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA BIT(2)
+#define ANA_PORT_DROP_CFG_DROP_NULL_MAC_ENA BIT(1)
+#define ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA BIT(0)
+
+#define ANA_PORT_QOS_CFG_GSZ 0x100
+
+#define ANA_PORT_QOS_CFG_DP_DEFAULT_VAL BIT(8)
+#define ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL(x) (((x) << 5) & GENMASK(7, 5))
+#define ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_M GENMASK(7, 5)
+#define ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(x) (((x) & GENMASK(7, 5)) >> 5)
+#define ANA_PORT_QOS_CFG_QOS_DSCP_ENA BIT(4)
+#define ANA_PORT_QOS_CFG_QOS_PCP_ENA BIT(3)
+#define ANA_PORT_QOS_CFG_DSCP_TRANSLATE_ENA BIT(2)
+#define ANA_PORT_QOS_CFG_DSCP_REWR_CFG(x) ((x) & GENMASK(1, 0))
+#define ANA_PORT_QOS_CFG_DSCP_REWR_CFG_M GENMASK(1, 0)
+
+#define ANA_PORT_VCAP_CFG_GSZ 0x100
+
+#define ANA_PORT_VCAP_CFG_S1_ENA BIT(14)
+#define ANA_PORT_VCAP_CFG_S1_DMAC_DIP_ENA(x) (((x) << 11) & GENMASK(13, 11))
+#define ANA_PORT_VCAP_CFG_S1_DMAC_DIP_ENA_M GENMASK(13, 11)
+#define ANA_PORT_VCAP_CFG_S1_DMAC_DIP_ENA_X(x) (((x) & GENMASK(13, 11)) >> 11)
+#define ANA_PORT_VCAP_CFG_S1_VLAN_INNER_TAG_ENA(x) (((x) << 8) & GENMASK(10, 8))
+#define ANA_PORT_VCAP_CFG_S1_VLAN_INNER_TAG_ENA_M GENMASK(10, 8)
+#define ANA_PORT_VCAP_CFG_S1_VLAN_INNER_TAG_ENA_X(x) (((x) & GENMASK(10, 8)) >> 8)
+#define ANA_PORT_VCAP_CFG_PAG_VAL(x) ((x) & GENMASK(7, 0))
+#define ANA_PORT_VCAP_CFG_PAG_VAL_M GENMASK(7, 0)
+
+#define ANA_PORT_VCAP_S1_KEY_CFG_GSZ 0x100
+#define ANA_PORT_VCAP_S1_KEY_CFG_RSZ 0x4
+
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP6_CFG(x) (((x) << 4) & GENMASK(6, 4))
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP6_CFG_M GENMASK(6, 4)
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP6_CFG_X(x) (((x) & GENMASK(6, 4)) >> 4)
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP4_CFG(x) (((x) << 2) & GENMASK(3, 2))
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP4_CFG_M GENMASK(3, 2)
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_IP4_CFG_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_OTHER_CFG(x) ((x) & GENMASK(1, 0))
+#define ANA_PORT_VCAP_S1_KEY_CFG_S1_KEY_OTHER_CFG_M GENMASK(1, 0)
+
+#define ANA_PORT_VCAP_S2_CFG_GSZ 0x100
+
+#define ANA_PORT_VCAP_S2_CFG_S2_UDP_PAYLOAD_ENA(x) (((x) << 17) & GENMASK(18, 17))
+#define ANA_PORT_VCAP_S2_CFG_S2_UDP_PAYLOAD_ENA_M GENMASK(18, 17)
+#define ANA_PORT_VCAP_S2_CFG_S2_UDP_PAYLOAD_ENA_X(x) (((x) & GENMASK(18, 17)) >> 17)
+#define ANA_PORT_VCAP_S2_CFG_S2_ETYPE_PAYLOAD_ENA(x) (((x) << 15) & GENMASK(16, 15))
+#define ANA_PORT_VCAP_S2_CFG_S2_ETYPE_PAYLOAD_ENA_M GENMASK(16, 15)
+#define ANA_PORT_VCAP_S2_CFG_S2_ETYPE_PAYLOAD_ENA_X(x) (((x) & GENMASK(16, 15)) >> 15)
+#define ANA_PORT_VCAP_S2_CFG_S2_ENA BIT(14)
+#define ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(x) (((x) << 12) & GENMASK(13, 12))
+#define ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS_M GENMASK(13, 12)
+#define ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS_X(x) (((x) & GENMASK(13, 12)) >> 12)
+#define ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(x) (((x) << 10) & GENMASK(11, 10))
+#define ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS_M GENMASK(11, 10)
+#define ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS_X(x) (((x) & GENMASK(11, 10)) >> 10)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(x) (((x) << 8) & GENMASK(9, 8))
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS_M GENMASK(9, 8)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS_X(x) (((x) & GENMASK(9, 8)) >> 8)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(x) (((x) << 6) & GENMASK(7, 6))
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS_M GENMASK(7, 6)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS_X(x) (((x) & GENMASK(7, 6)) >> 6)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP6_CFG(x) (((x) << 2) & GENMASK(5, 2))
+#define ANA_PORT_VCAP_S2_CFG_S2_IP6_CFG_M GENMASK(5, 2)
+#define ANA_PORT_VCAP_S2_CFG_S2_IP6_CFG_X(x) (((x) & GENMASK(5, 2)) >> 2)
+#define ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(x) ((x) & GENMASK(1, 0))
+#define ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS_M GENMASK(1, 0)
+
+#define ANA_PORT_PCP_DEI_MAP_GSZ 0x100
+#define ANA_PORT_PCP_DEI_MAP_RSZ 0x4
+
+#define ANA_PORT_PCP_DEI_MAP_DP_PCP_DEI_VAL BIT(3)
+#define ANA_PORT_PCP_DEI_MAP_QOS_PCP_DEI_VAL(x) ((x) & GENMASK(2, 0))
+#define ANA_PORT_PCP_DEI_MAP_QOS_PCP_DEI_VAL_M GENMASK(2, 0)
+
+#define ANA_PORT_CPU_FWD_CFG_GSZ 0x100
+
+#define ANA_PORT_CPU_FWD_CFG_CPU_VRAP_REDIR_ENA BIT(7)
+#define ANA_PORT_CPU_FWD_CFG_CPU_MLD_REDIR_ENA BIT(6)
+#define ANA_PORT_CPU_FWD_CFG_CPU_IGMP_REDIR_ENA BIT(5)
+#define ANA_PORT_CPU_FWD_CFG_CPU_IPMC_CTRL_COPY_ENA BIT(4)
+#define ANA_PORT_CPU_FWD_CFG_CPU_SRC_COPY_ENA BIT(3)
+#define ANA_PORT_CPU_FWD_CFG_CPU_ALLBRIDGE_DROP_ENA BIT(2)
+#define ANA_PORT_CPU_FWD_CFG_CPU_ALLBRIDGE_REDIR_ENA BIT(1)
+#define ANA_PORT_CPU_FWD_CFG_CPU_OAM_ENA BIT(0)
+
+#define ANA_PORT_CPU_FWD_BPDU_CFG_GSZ 0x100
+
+#define ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_DROP_ENA(x) (((x) << 16) & GENMASK(31, 16))
+#define ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_DROP_ENA_M GENMASK(31, 16)
+#define ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_DROP_ENA_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(x) ((x) & GENMASK(15, 0))
+#define ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA_M GENMASK(15, 0)
+
+#define ANA_PORT_CPU_FWD_GARP_CFG_GSZ 0x100
+
+#define ANA_PORT_CPU_FWD_GARP_CFG_GARP_DROP_ENA(x) (((x) << 16) & GENMASK(31, 16))
+#define ANA_PORT_CPU_FWD_GARP_CFG_GARP_DROP_ENA_M GENMASK(31, 16)
+#define ANA_PORT_CPU_FWD_GARP_CFG_GARP_DROP_ENA_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define ANA_PORT_CPU_FWD_GARP_CFG_GARP_REDIR_ENA(x) ((x) & GENMASK(15, 0))
+#define ANA_PORT_CPU_FWD_GARP_CFG_GARP_REDIR_ENA_M GENMASK(15, 0)
+
+#define ANA_PORT_CPU_FWD_CCM_CFG_GSZ 0x100
+
+#define ANA_PORT_CPU_FWD_CCM_CFG_CCM_DROP_ENA(x) (((x) << 16) & GENMASK(31, 16))
+#define ANA_PORT_CPU_FWD_CCM_CFG_CCM_DROP_ENA_M GENMASK(31, 16)
+#define ANA_PORT_CPU_FWD_CCM_CFG_CCM_DROP_ENA_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define ANA_PORT_CPU_FWD_CCM_CFG_CCM_REDIR_ENA(x) ((x) & GENMASK(15, 0))
+#define ANA_PORT_CPU_FWD_CCM_CFG_CCM_REDIR_ENA_M GENMASK(15, 0)
+
+#define ANA_PORT_PORT_CFG_GSZ 0x100
+
+#define ANA_PORT_PORT_CFG_SRC_MIRROR_ENA BIT(15)
+#define ANA_PORT_PORT_CFG_LIMIT_DROP BIT(14)
+#define ANA_PORT_PORT_CFG_LIMIT_CPU BIT(13)
+#define ANA_PORT_PORT_CFG_LOCKED_PORTMOVE_DROP BIT(12)
+#define ANA_PORT_PORT_CFG_LOCKED_PORTMOVE_CPU BIT(11)
+#define ANA_PORT_PORT_CFG_LEARNDROP BIT(10)
+#define ANA_PORT_PORT_CFG_LEARNCPU BIT(9)
+#define ANA_PORT_PORT_CFG_LEARNAUTO BIT(8)
+#define ANA_PORT_PORT_CFG_LEARN_ENA BIT(7)
+#define ANA_PORT_PORT_CFG_RECV_ENA BIT(6)
+#define ANA_PORT_PORT_CFG_PORTID_VAL(x) (((x) << 2) & GENMASK(5, 2))
+#define ANA_PORT_PORT_CFG_PORTID_VAL_M GENMASK(5, 2)
+#define ANA_PORT_PORT_CFG_PORTID_VAL_X(x) (((x) & GENMASK(5, 2)) >> 2)
+#define ANA_PORT_PORT_CFG_USE_B_DOM_TBL BIT(1)
+#define ANA_PORT_PORT_CFG_LSR_MODE BIT(0)
+
+#define ANA_PORT_POL_CFG_GSZ 0x100
+
+#define ANA_PORT_POL_CFG_POL_CPU_REDIR_8021 BIT(19)
+#define ANA_PORT_POL_CFG_POL_CPU_REDIR_IP BIT(18)
+#define ANA_PORT_POL_CFG_PORT_POL_ENA BIT(17)
+#define ANA_PORT_POL_CFG_QUEUE_POL_ENA(x) (((x) << 9) & GENMASK(16, 9))
+#define ANA_PORT_POL_CFG_QUEUE_POL_ENA_M GENMASK(16, 9)
+#define ANA_PORT_POL_CFG_QUEUE_POL_ENA_X(x) (((x) & GENMASK(16, 9)) >> 9)
+#define ANA_PORT_POL_CFG_POL_ORDER(x) ((x) & GENMASK(8, 0))
+#define ANA_PORT_POL_CFG_POL_ORDER_M GENMASK(8, 0)
+
+#define ANA_PORT_PTP_CFG_GSZ 0x100
+
+#define ANA_PORT_PTP_CFG_PTP_BACKPLANE_MODE BIT(0)
+
+#define ANA_PORT_PTP_DLY1_CFG_GSZ 0x100
+
+#define ANA_PORT_PTP_DLY2_CFG_GSZ 0x100
+
+#define ANA_PORT_SFID_CFG_GSZ 0x100
+#define ANA_PORT_SFID_CFG_RSZ 0x4
+
+#define ANA_PORT_SFID_CFG_SFID_VALID BIT(8)
+#define ANA_PORT_SFID_CFG_SFID(x) ((x) & GENMASK(7, 0))
+#define ANA_PORT_SFID_CFG_SFID_M GENMASK(7, 0)
+
+#define ANA_PFC_PFC_CFG_GSZ 0x40
+
+#define ANA_PFC_PFC_CFG_RX_PFC_ENA(x) (((x) << 2) & GENMASK(9, 2))
+#define ANA_PFC_PFC_CFG_RX_PFC_ENA_M GENMASK(9, 2)
+#define ANA_PFC_PFC_CFG_RX_PFC_ENA_X(x) (((x) & GENMASK(9, 2)) >> 2)
+#define ANA_PFC_PFC_CFG_FC_LINK_SPEED(x) ((x) & GENMASK(1, 0))
+#define ANA_PFC_PFC_CFG_FC_LINK_SPEED_M GENMASK(1, 0)
+
+#define ANA_PFC_PFC_TIMER_GSZ 0x40
+#define ANA_PFC_PFC_TIMER_RSZ 0x4
+
+#define ANA_IPT_OAM_MEP_CFG_GSZ 0x8
+
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_P(x) (((x) << 6) & GENMASK(10, 6))
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_P_M GENMASK(10, 6)
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_P_X(x) (((x) & GENMASK(10, 6)) >> 6)
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX(x) (((x) << 1) & GENMASK(5, 1))
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_M GENMASK(5, 1)
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_X(x) (((x) & GENMASK(5, 1)) >> 1)
+#define ANA_IPT_OAM_MEP_CFG_MEP_IDX_ENA BIT(0)
+
+#define ANA_IPT_IPT_GSZ 0x8
+
+#define ANA_IPT_IPT_IPT_CFG(x) (((x) << 15) & GENMASK(16, 15))
+#define ANA_IPT_IPT_IPT_CFG_M GENMASK(16, 15)
+#define ANA_IPT_IPT_IPT_CFG_X(x) (((x) & GENMASK(16, 15)) >> 15)
+#define ANA_IPT_IPT_ISDX_P(x) (((x) << 7) & GENMASK(14, 7))
+#define ANA_IPT_IPT_ISDX_P_M GENMASK(14, 7)
+#define ANA_IPT_IPT_ISDX_P_X(x) (((x) & GENMASK(14, 7)) >> 7)
+#define ANA_IPT_IPT_PPT_IDX(x) ((x) & GENMASK(6, 0))
+#define ANA_IPT_IPT_PPT_IDX_M GENMASK(6, 0)
+
+#define ANA_PPT_PPT_RSZ 0x4
+
+#define ANA_FID_MAP_FID_MAP_RSZ 0x4
+
+#define ANA_FID_MAP_FID_MAP_FID_C_VAL(x) (((x) << 6) & GENMASK(11, 6))
+#define ANA_FID_MAP_FID_MAP_FID_C_VAL_M GENMASK(11, 6)
+#define ANA_FID_MAP_FID_MAP_FID_C_VAL_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define ANA_FID_MAP_FID_MAP_FID_B_VAL(x) ((x) & GENMASK(5, 0))
+#define ANA_FID_MAP_FID_MAP_FID_B_VAL_M GENMASK(5, 0)
+
+#define ANA_AGGR_CFG_AC_RND_ENA BIT(7)
+#define ANA_AGGR_CFG_AC_DMAC_ENA BIT(6)
+#define ANA_AGGR_CFG_AC_SMAC_ENA BIT(5)
+#define ANA_AGGR_CFG_AC_IP6_FLOW_LBL_ENA BIT(4)
+#define ANA_AGGR_CFG_AC_IP6_TCPUDP_ENA BIT(3)
+#define ANA_AGGR_CFG_AC_IP4_SIPDIP_ENA BIT(2)
+#define ANA_AGGR_CFG_AC_IP4_TCPUDP_ENA BIT(1)
+#define ANA_AGGR_CFG_AC_ISDX_ENA BIT(0)
+
+#define ANA_CPUQ_CFG_CPUQ_MLD(x) (((x) << 27) & GENMASK(29, 27))
+#define ANA_CPUQ_CFG_CPUQ_MLD_M GENMASK(29, 27)
+#define ANA_CPUQ_CFG_CPUQ_MLD_X(x) (((x) & GENMASK(29, 27)) >> 27)
+#define ANA_CPUQ_CFG_CPUQ_IGMP(x) (((x) << 24) & GENMASK(26, 24))
+#define ANA_CPUQ_CFG_CPUQ_IGMP_M GENMASK(26, 24)
+#define ANA_CPUQ_CFG_CPUQ_IGMP_X(x) (((x) & GENMASK(26, 24)) >> 24)
+#define ANA_CPUQ_CFG_CPUQ_IPMC_CTRL(x) (((x) << 21) & GENMASK(23, 21))
+#define ANA_CPUQ_CFG_CPUQ_IPMC_CTRL_M GENMASK(23, 21)
+#define ANA_CPUQ_CFG_CPUQ_IPMC_CTRL_X(x) (((x) & GENMASK(23, 21)) >> 21)
+#define ANA_CPUQ_CFG_CPUQ_ALLBRIDGE(x) (((x) << 18) & GENMASK(20, 18))
+#define ANA_CPUQ_CFG_CPUQ_ALLBRIDGE_M GENMASK(20, 18)
+#define ANA_CPUQ_CFG_CPUQ_ALLBRIDGE_X(x) (((x) & GENMASK(20, 18)) >> 18)
+#define ANA_CPUQ_CFG_CPUQ_LOCKED_PORTMOVE(x) (((x) << 15) & GENMASK(17, 15))
+#define ANA_CPUQ_CFG_CPUQ_LOCKED_PORTMOVE_M GENMASK(17, 15)
+#define ANA_CPUQ_CFG_CPUQ_LOCKED_PORTMOVE_X(x) (((x) & GENMASK(17, 15)) >> 15)
+#define ANA_CPUQ_CFG_CPUQ_SRC_COPY(x) (((x) << 12) & GENMASK(14, 12))
+#define ANA_CPUQ_CFG_CPUQ_SRC_COPY_M GENMASK(14, 12)
+#define ANA_CPUQ_CFG_CPUQ_SRC_COPY_X(x) (((x) & GENMASK(14, 12)) >> 12)
+#define ANA_CPUQ_CFG_CPUQ_MAC_COPY(x) (((x) << 9) & GENMASK(11, 9))
+#define ANA_CPUQ_CFG_CPUQ_MAC_COPY_M GENMASK(11, 9)
+#define ANA_CPUQ_CFG_CPUQ_MAC_COPY_X(x) (((x) & GENMASK(11, 9)) >> 9)
+#define ANA_CPUQ_CFG_CPUQ_LRN(x) (((x) << 6) & GENMASK(8, 6))
+#define ANA_CPUQ_CFG_CPUQ_LRN_M GENMASK(8, 6)
+#define ANA_CPUQ_CFG_CPUQ_LRN_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define ANA_CPUQ_CFG_CPUQ_MIRROR(x) (((x) << 3) & GENMASK(5, 3))
+#define ANA_CPUQ_CFG_CPUQ_MIRROR_M GENMASK(5, 3)
+#define ANA_CPUQ_CFG_CPUQ_MIRROR_X(x) (((x) & GENMASK(5, 3)) >> 3)
+#define ANA_CPUQ_CFG_CPUQ_SFLOW(x) ((x) & GENMASK(2, 0))
+#define ANA_CPUQ_CFG_CPUQ_SFLOW_M GENMASK(2, 0)
+
+#define ANA_CPUQ_8021_CFG_RSZ 0x4
+
+#define ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(x) (((x) << 6) & GENMASK(8, 6))
+#define ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL_M GENMASK(8, 6)
+#define ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define ANA_CPUQ_8021_CFG_CPUQ_GARP_VAL(x) (((x) << 3) & GENMASK(5, 3))
+#define ANA_CPUQ_8021_CFG_CPUQ_GARP_VAL_M GENMASK(5, 3)
+#define ANA_CPUQ_8021_CFG_CPUQ_GARP_VAL_X(x) (((x) & GENMASK(5, 3)) >> 3)
+#define ANA_CPUQ_8021_CFG_CPUQ_CCM_VAL(x) ((x) & GENMASK(2, 0))
+#define ANA_CPUQ_8021_CFG_CPUQ_CCM_VAL_M GENMASK(2, 0)
+
+#define ANA_DSCP_CFG_RSZ 0x4
+
+#define ANA_DSCP_CFG_DP_DSCP_VAL BIT(11)
+#define ANA_DSCP_CFG_QOS_DSCP_VAL(x) (((x) << 8) & GENMASK(10, 8))
+#define ANA_DSCP_CFG_QOS_DSCP_VAL_M GENMASK(10, 8)
+#define ANA_DSCP_CFG_QOS_DSCP_VAL_X(x) (((x) & GENMASK(10, 8)) >> 8)
+#define ANA_DSCP_CFG_DSCP_TRANSLATE_VAL(x) (((x) << 2) & GENMASK(7, 2))
+#define ANA_DSCP_CFG_DSCP_TRANSLATE_VAL_M GENMASK(7, 2)
+#define ANA_DSCP_CFG_DSCP_TRANSLATE_VAL_X(x) (((x) & GENMASK(7, 2)) >> 2)
+#define ANA_DSCP_CFG_DSCP_TRUST_ENA BIT(1)
+#define ANA_DSCP_CFG_DSCP_REWR_ENA BIT(0)
+
+#define ANA_DSCP_REWR_CFG_RSZ 0x4
+
+#define ANA_VCAP_RNG_TYPE_CFG_RSZ 0x4
+
+#define ANA_VCAP_RNG_VAL_CFG_RSZ 0x4
+
+#define ANA_VCAP_RNG_VAL_CFG_VCAP_RNG_MIN_VAL(x) (((x) << 16) & GENMASK(31, 16))
+#define ANA_VCAP_RNG_VAL_CFG_VCAP_RNG_MIN_VAL_M GENMASK(31, 16)
+#define ANA_VCAP_RNG_VAL_CFG_VCAP_RNG_MIN_VAL_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define ANA_VCAP_RNG_VAL_CFG_VCAP_RNG_MAX_VAL(x) ((x) & GENMASK(15, 0))
+#define ANA_VCAP_RNG_VAL_CFG_VCAP_RNG_MAX_VAL_M GENMASK(15, 0)
+
+#define ANA_VRAP_CFG_VRAP_VLAN_AWARE_ENA BIT(12)
+#define ANA_VRAP_CFG_VRAP_VID(x) ((x) & GENMASK(11, 0))
+#define ANA_VRAP_CFG_VRAP_VID_M GENMASK(11, 0)
+
+#define ANA_DISCARD_CFG_DROP_TAGGING_ISDX0 BIT(3)
+#define ANA_DISCARD_CFG_DROP_CTRLPROT_ISDX0 BIT(2)
+#define ANA_DISCARD_CFG_DROP_TAGGING_S2_ENA BIT(1)
+#define ANA_DISCARD_CFG_DROP_CTRLPROT_S2_ENA BIT(0)
+
+#define ANA_FID_CFG_VID_MC_ENA BIT(0)
+
+#define ANA_POL_PIR_CFG_GSZ 0x20
+
+#define ANA_POL_PIR_CFG_PIR_RATE(x) (((x) << 6) & GENMASK(20, 6))
+#define ANA_POL_PIR_CFG_PIR_RATE_M GENMASK(20, 6)
+#define ANA_POL_PIR_CFG_PIR_RATE_X(x) (((x) & GENMASK(20, 6)) >> 6)
+#define ANA_POL_PIR_CFG_PIR_BURST(x) ((x) & GENMASK(5, 0))
+#define ANA_POL_PIR_CFG_PIR_BURST_M GENMASK(5, 0)
+
+#define ANA_POL_CIR_CFG_GSZ 0x20
+
+#define ANA_POL_CIR_CFG_CIR_RATE(x) (((x) << 6) & GENMASK(20, 6))
+#define ANA_POL_CIR_CFG_CIR_RATE_M GENMASK(20, 6)
+#define ANA_POL_CIR_CFG_CIR_RATE_X(x) (((x) & GENMASK(20, 6)) >> 6)
+#define ANA_POL_CIR_CFG_CIR_BURST(x) ((x) & GENMASK(5, 0))
+#define ANA_POL_CIR_CFG_CIR_BURST_M GENMASK(5, 0)
+
+#define ANA_POL_MODE_CFG_GSZ 0x20
+
+#define ANA_POL_MODE_CFG_IPG_SIZE(x) (((x) << 5) & GENMASK(9, 5))
+#define ANA_POL_MODE_CFG_IPG_SIZE_M GENMASK(9, 5)
+#define ANA_POL_MODE_CFG_IPG_SIZE_X(x) (((x) & GENMASK(9, 5)) >> 5)
+#define ANA_POL_MODE_CFG_FRM_MODE(x) (((x) << 3) & GENMASK(4, 3))
+#define ANA_POL_MODE_CFG_FRM_MODE_M GENMASK(4, 3)
+#define ANA_POL_MODE_CFG_FRM_MODE_X(x) (((x) & GENMASK(4, 3)) >> 3)
+#define ANA_POL_MODE_CFG_DLB_COUPLED BIT(2)
+#define ANA_POL_MODE_CFG_CIR_ENA BIT(1)
+#define ANA_POL_MODE_CFG_OVERSHOOT_ENA BIT(0)
+
+#define ANA_POL_PIR_STATE_GSZ 0x20
+
+#define ANA_POL_CIR_STATE_GSZ 0x20
+
+#define ANA_POL_STATE_GSZ 0x20
+
+#define ANA_POL_FLOWC_RSZ 0x4
+
+#define ANA_POL_FLOWC_POL_FLOWC BIT(0)
+
+#define ANA_POL_HYST_POL_FC_HYST(x) (((x) << 4) & GENMASK(9, 4))
+#define ANA_POL_HYST_POL_FC_HYST_M GENMASK(9, 4)
+#define ANA_POL_HYST_POL_FC_HYST_X(x) (((x) & GENMASK(9, 4)) >> 4)
+#define ANA_POL_HYST_POL_STOP_HYST(x) ((x) & GENMASK(3, 0))
+#define ANA_POL_HYST_POL_STOP_HYST_M GENMASK(3, 0)
+
+#define ANA_POL_MISC_CFG_POL_CLOSE_ALL BIT(1)
+#define ANA_POL_MISC_CFG_POL_LEAK_DIS BIT(0)
+
+#endif
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/skbuff.h>
+
+#include "ocelot.h"
+
+static int ocelot_parse_ifh(u32 *ifh, struct frame_info *info)
+{
+ int i;
+ u8 llen, wlen;
+
+ /* The IFH is in network order, switch to CPU order */
+ for (i = 0; i < IFH_LEN; i++)
+ ifh[i] = ntohl((__force __be32)ifh[i]);
+
+ wlen = (ifh[1] >> 7) & 0xff;
+ llen = (ifh[1] >> 15) & 0x3f;
+ info->len = OCELOT_BUFFER_CELL_SZ * wlen + llen - 80;
+
+ info->port = (ifh[2] & GENMASK(14, 11)) >> 11;
+
+ info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20;
+ info->tag_type = (ifh[3] & GENMASK(16, 16)) >> 16;
+ info->vid = ifh[3] & GENMASK(11, 0);
+
+ return 0;
+}
+
+static int ocelot_rx_frame_word(struct ocelot *ocelot, u8 grp, bool ifh,
+ u32 *rval)
+{
+ u32 val;
+ u32 bytes_valid;
+
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ if (val == XTR_NOT_READY) {
+ if (ifh)
+ return -EIO;
+
+ do {
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ } while (val == XTR_NOT_READY);
+ }
+
+ switch (val) {
+ case XTR_ABORT:
+ return -EIO;
+ case XTR_EOF_0:
+ case XTR_EOF_1:
+ case XTR_EOF_2:
+ case XTR_EOF_3:
+ case XTR_PRUNED:
+ bytes_valid = XTR_VALID_BYTES(val);
+ val = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ if (val == XTR_ESCAPE)
+ *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ else
+ *rval = val;
+
+ return bytes_valid;
+ case XTR_ESCAPE:
+ *rval = ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+
+ return 4;
+ default:
+ *rval = val;
+
+ return 4;
+ }
+}
+
+static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
+{
+ struct ocelot *ocelot = arg;
+ int i = 0, grp = 0;
+ int err = 0;
+
+ if (!(ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)))
+ return IRQ_NONE;
+
+ do {
+ struct sk_buff *skb;
+ struct net_device *dev;
+ u32 *buf;
+ int sz, len;
+ u32 ifh[4];
+ u32 val;
+ struct frame_info info;
+
+ for (i = 0; i < IFH_LEN; i++) {
+ err = ocelot_rx_frame_word(ocelot, grp, true, &ifh[i]);
+ if (err != 4)
+ break;
+ }
+
+ if (err != 4)
+ break;
+
+ ocelot_parse_ifh(ifh, &info);
+
+ dev = ocelot->ports[info.port]->dev;
+
+ skb = netdev_alloc_skb(dev, info.len);
+
+ if (unlikely(!skb)) {
+ netdev_err(dev, "Unable to allocate sk_buff\n");
+ err = -ENOMEM;
+ break;
+ }
+ buf = (u32 *)skb_put(skb, info.len);
+
+ len = 0;
+ do {
+ sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
+ *buf++ = val;
+ len += sz;
+ } while ((sz == 4) && (len < info.len));
+
+ if (sz < 0) {
+ err = sz;
+ break;
+ }
+
+ /* Everything we see on an interface that is in the HW bridge
+ * has already been forwarded.
+ */
+ if (ocelot->bridge_mask & BIT(info.port))
+ skb->offload_fwd_mark = 1;
+
+ skb->protocol = eth_type_trans(skb, dev);
+ netif_rx(skb);
+ dev->stats.rx_bytes += len;
+ dev->stats.rx_packets++;
+ } while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp));
+
+ if (err)
+ while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
+ ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+
+ return IRQ_HANDLED;
+}
+
+static const struct of_device_id mscc_ocelot_match[] = {
+ { .compatible = "mscc,vsc7514-switch" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, mscc_ocelot_match);
+
+static int mscc_ocelot_probe(struct platform_device *pdev)
+{
+ int err, irq;
+ unsigned int i;
+ struct device_node *np = pdev->dev.of_node;
+ struct device_node *ports, *portnp;
+ struct ocelot *ocelot;
+ u32 val;
+
+ struct {
+ enum ocelot_target id;
+ char *name;
+ } res[] = {
+ { SYS, "sys" },
+ { REW, "rew" },
+ { QSYS, "qsys" },
+ { ANA, "ana" },
+ { QS, "qs" },
+ { HSIO, "hsio" },
+ };
+
+ if (!np && !pdev->dev.platform_data)
+ return -ENODEV;
+
+ ocelot = devm_kzalloc(&pdev->dev, sizeof(*ocelot), GFP_KERNEL);
+ if (!ocelot)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, ocelot);
+ ocelot->dev = &pdev->dev;
+
+ for (i = 0; i < ARRAY_SIZE(res); i++) {
+ struct regmap *target;
+
+ target = ocelot_io_platform_init(ocelot, pdev, res[i].name);
+ if (IS_ERR(target))
+ return PTR_ERR(target);
+
+ ocelot->targets[res[i].id] = target;
+ }
+
+ err = ocelot_chip_init(ocelot);
+ if (err)
+ return err;
+
+ irq = platform_get_irq_byname(pdev, "xtr");
+ if (irq < 0)
+ return -ENODEV;
+
+ err = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+ ocelot_xtr_irq_handler, IRQF_ONESHOT,
+ "frame extraction", ocelot);
+ if (err)
+ return err;
+
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1);
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
+
+ do {
+ msleep(1);
+ regmap_field_read(ocelot->regfields[SYS_RESET_CFG_MEM_INIT],
+ &val);
+ } while (val);
+
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1);
+ regmap_field_write(ocelot->regfields[SYS_RESET_CFG_CORE_ENA], 1);
+
+ ocelot->num_cpu_ports = 1; /* 1 port on the switch, two groups */
+
+ ports = of_get_child_by_name(np, "ethernet-ports");
+ if (!ports) {
+ dev_err(&pdev->dev, "no ethernet-ports child node found\n");
+ return -ENODEV;
+ }
+
+ ocelot->num_phys_ports = of_get_child_count(ports);
+
+ ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports,
+ sizeof(struct ocelot_port *), GFP_KERNEL);
+
+ INIT_LIST_HEAD(&ocelot->multicast);
+ ocelot_init(ocelot);
+
+ ocelot_rmw(ocelot, HSIO_HW_CFG_DEV1G_4_MODE |
+ HSIO_HW_CFG_DEV1G_6_MODE |
+ HSIO_HW_CFG_DEV1G_9_MODE,
+ HSIO_HW_CFG_DEV1G_4_MODE |
+ HSIO_HW_CFG_DEV1G_6_MODE |
+ HSIO_HW_CFG_DEV1G_9_MODE,
+ HSIO_HW_CFG);
+
+ for_each_available_child_of_node(ports, portnp) {
+ struct device_node *phy_node;
+ struct phy_device *phy;
+ struct resource *res;
+ void __iomem *regs;
+ char res_name[8];
+ u32 port;
+
+ if (of_property_read_u32(portnp, "reg", &port))
+ continue;
+
+ snprintf(res_name, sizeof(res_name), "port%d", port);
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ res_name);
+ regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(regs))
+ continue;
+
+ phy_node = of_parse_phandle(portnp, "phy-handle", 0);
+ if (!phy_node)
+ continue;
+
+ phy = of_phy_find_device(phy_node);
+ if (!phy)
+ continue;
+
+ err = ocelot_probe_port(ocelot, port, regs, phy);
+ if (err) {
+ dev_err(&pdev->dev, "failed to probe ports\n");
+ goto err_probe_ports;
+ }
+ }
+
+ register_netdevice_notifier(&ocelot_netdevice_nb);
+
+ dev_info(&pdev->dev, "Ocelot switch probed\n");
+
+ return 0;
+
+err_probe_ports:
+ return err;
+}
+
+static int mscc_ocelot_remove(struct platform_device *pdev)
+{
+ struct ocelot *ocelot = platform_get_drvdata(pdev);
+
+ ocelot_deinit(ocelot);
+ unregister_netdevice_notifier(&ocelot_netdevice_nb);
+
+ return 0;
+}
+
+static struct platform_driver mscc_ocelot_driver = {
+ .probe = mscc_ocelot_probe,
+ .remove = mscc_ocelot_remove,
+ .driver = {
+ .name = "ocelot-switch",
+ .of_match_table = mscc_ocelot_match,
+ },
+};
+
+module_platform_driver(mscc_ocelot_driver);
+
+MODULE_DESCRIPTION("Microsemi Ocelot switch driver");
+MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@bootlin.com>");
+MODULE_LICENSE("Dual MIT/GPL");
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_DEV_H_
+#define _MSCC_OCELOT_DEV_H_
+
+#define DEV_CLOCK_CFG 0x0
+
+#define DEV_CLOCK_CFG_MAC_TX_RST BIT(7)
+#define DEV_CLOCK_CFG_MAC_RX_RST BIT(6)
+#define DEV_CLOCK_CFG_PCS_TX_RST BIT(5)
+#define DEV_CLOCK_CFG_PCS_RX_RST BIT(4)
+#define DEV_CLOCK_CFG_PORT_RST BIT(3)
+#define DEV_CLOCK_CFG_PHY_RST BIT(2)
+#define DEV_CLOCK_CFG_LINK_SPEED(x) ((x) & GENMASK(1, 0))
+#define DEV_CLOCK_CFG_LINK_SPEED_M GENMASK(1, 0)
+
+#define DEV_PORT_MISC 0x4
+
+#define DEV_PORT_MISC_FWD_ERROR_ENA BIT(4)
+#define DEV_PORT_MISC_FWD_PAUSE_ENA BIT(3)
+#define DEV_PORT_MISC_FWD_CTRL_ENA BIT(2)
+#define DEV_PORT_MISC_DEV_LOOP_ENA BIT(1)
+#define DEV_PORT_MISC_HDX_FAST_DIS BIT(0)
+
+#define DEV_EVENTS 0x8
+
+#define DEV_EEE_CFG 0xc
+
+#define DEV_EEE_CFG_EEE_ENA BIT(22)
+#define DEV_EEE_CFG_EEE_TIMER_AGE(x) (((x) << 15) & GENMASK(21, 15))
+#define DEV_EEE_CFG_EEE_TIMER_AGE_M GENMASK(21, 15)
+#define DEV_EEE_CFG_EEE_TIMER_AGE_X(x) (((x) & GENMASK(21, 15)) >> 15)
+#define DEV_EEE_CFG_EEE_TIMER_WAKEUP(x) (((x) << 8) & GENMASK(14, 8))
+#define DEV_EEE_CFG_EEE_TIMER_WAKEUP_M GENMASK(14, 8)
+#define DEV_EEE_CFG_EEE_TIMER_WAKEUP_X(x) (((x) & GENMASK(14, 8)) >> 8)
+#define DEV_EEE_CFG_EEE_TIMER_HOLDOFF(x) (((x) << 1) & GENMASK(7, 1))
+#define DEV_EEE_CFG_EEE_TIMER_HOLDOFF_M GENMASK(7, 1)
+#define DEV_EEE_CFG_EEE_TIMER_HOLDOFF_X(x) (((x) & GENMASK(7, 1)) >> 1)
+#define DEV_EEE_CFG_PORT_LPI BIT(0)
+
+#define DEV_RX_PATH_DELAY 0x10
+
+#define DEV_TX_PATH_DELAY 0x14
+
+#define DEV_PTP_PREDICT_CFG 0x18
+
+#define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG(x) (((x) << 4) & GENMASK(11, 4))
+#define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG_M GENMASK(11, 4)
+#define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG_X(x) (((x) & GENMASK(11, 4)) >> 4)
+#define DEV_PTP_PREDICT_CFG_PTP_PHASE_PREDICT_CFG(x) ((x) & GENMASK(3, 0))
+#define DEV_PTP_PREDICT_CFG_PTP_PHASE_PREDICT_CFG_M GENMASK(3, 0)
+
+#define DEV_MAC_ENA_CFG 0x1c
+
+#define DEV_MAC_ENA_CFG_RX_ENA BIT(4)
+#define DEV_MAC_ENA_CFG_TX_ENA BIT(0)
+
+#define DEV_MAC_MODE_CFG 0x20
+
+#define DEV_MAC_MODE_CFG_FC_WORD_SYNC_ENA BIT(8)
+#define DEV_MAC_MODE_CFG_GIGA_MODE_ENA BIT(4)
+#define DEV_MAC_MODE_CFG_FDX_ENA BIT(0)
+
+#define DEV_MAC_MAXLEN_CFG 0x24
+
+#define DEV_MAC_TAGS_CFG 0x28
+
+#define DEV_MAC_TAGS_CFG_TAG_ID(x) (((x) << 16) & GENMASK(31, 16))
+#define DEV_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16)
+#define DEV_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(2)
+#define DEV_MAC_TAGS_CFG_PB_ENA BIT(1)
+#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0)
+
+#define DEV_MAC_ADV_CHK_CFG 0x2c
+
+#define DEV_MAC_ADV_CHK_CFG_LEN_DROP_ENA BIT(0)
+
+#define DEV_MAC_IFG_CFG 0x30
+
+#define DEV_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK BIT(17)
+#define DEV_MAC_IFG_CFG_REDUCED_TX_IFG BIT(16)
+#define DEV_MAC_IFG_CFG_TX_IFG(x) (((x) << 8) & GENMASK(12, 8))
+#define DEV_MAC_IFG_CFG_TX_IFG_M GENMASK(12, 8)
+#define DEV_MAC_IFG_CFG_TX_IFG_X(x) (((x) & GENMASK(12, 8)) >> 8)
+#define DEV_MAC_IFG_CFG_RX_IFG2(x) (((x) << 4) & GENMASK(7, 4))
+#define DEV_MAC_IFG_CFG_RX_IFG2_M GENMASK(7, 4)
+#define DEV_MAC_IFG_CFG_RX_IFG2_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define DEV_MAC_IFG_CFG_RX_IFG1(x) ((x) & GENMASK(3, 0))
+#define DEV_MAC_IFG_CFG_RX_IFG1_M GENMASK(3, 0)
+
+#define DEV_MAC_HDX_CFG 0x34
+
+#define DEV_MAC_HDX_CFG_BYPASS_COL_SYNC BIT(26)
+#define DEV_MAC_HDX_CFG_OB_ENA BIT(25)
+#define DEV_MAC_HDX_CFG_WEXC_DIS BIT(24)
+#define DEV_MAC_HDX_CFG_SEED(x) (((x) << 16) & GENMASK(23, 16))
+#define DEV_MAC_HDX_CFG_SEED_M GENMASK(23, 16)
+#define DEV_MAC_HDX_CFG_SEED_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define DEV_MAC_HDX_CFG_SEED_LOAD BIT(12)
+#define DEV_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA BIT(8)
+#define DEV_MAC_HDX_CFG_LATE_COL_POS(x) ((x) & GENMASK(6, 0))
+#define DEV_MAC_HDX_CFG_LATE_COL_POS_M GENMASK(6, 0)
+
+#define DEV_MAC_DBG_CFG 0x38
+
+#define DEV_MAC_DBG_CFG_TBI_MODE BIT(4)
+#define DEV_MAC_DBG_CFG_IFG_CRS_EXT_CHK_ENA BIT(0)
+
+#define DEV_MAC_FC_MAC_LOW_CFG 0x3c
+
+#define DEV_MAC_FC_MAC_HIGH_CFG 0x40
+
+#define DEV_MAC_STICKY 0x44
+
+#define DEV_MAC_STICKY_RX_IPG_SHRINK_STICKY BIT(9)
+#define DEV_MAC_STICKY_RX_PREAM_SHRINK_STICKY BIT(8)
+#define DEV_MAC_STICKY_RX_CARRIER_EXT_STICKY BIT(7)
+#define DEV_MAC_STICKY_RX_CARRIER_EXT_ERR_STICKY BIT(6)
+#define DEV_MAC_STICKY_RX_JUNK_STICKY BIT(5)
+#define DEV_MAC_STICKY_TX_RETRANSMIT_STICKY BIT(4)
+#define DEV_MAC_STICKY_TX_JAM_STICKY BIT(3)
+#define DEV_MAC_STICKY_TX_FIFO_OFLW_STICKY BIT(2)
+#define DEV_MAC_STICKY_TX_FRM_LEN_OVR_STICKY BIT(1)
+#define DEV_MAC_STICKY_TX_ABORT_STICKY BIT(0)
+
+#define PCS1G_CFG 0x48
+
+#define PCS1G_CFG_LINK_STATUS_TYPE BIT(4)
+#define PCS1G_CFG_AN_LINK_CTRL_ENA BIT(1)
+#define PCS1G_CFG_PCS_ENA BIT(0)
+
+#define PCS1G_MODE_CFG 0x4c
+
+#define PCS1G_MODE_CFG_UNIDIR_MODE_ENA BIT(4)
+#define PCS1G_MODE_CFG_SGMII_MODE_ENA BIT(0)
+
+#define PCS1G_SD_CFG 0x50
+
+#define PCS1G_SD_CFG_SD_SEL BIT(8)
+#define PCS1G_SD_CFG_SD_POL BIT(4)
+#define PCS1G_SD_CFG_SD_ENA BIT(0)
+
+#define PCS1G_ANEG_CFG 0x54
+
+#define PCS1G_ANEG_CFG_ADV_ABILITY(x) (((x) << 16) & GENMASK(31, 16))
+#define PCS1G_ANEG_CFG_ADV_ABILITY_M GENMASK(31, 16)
+#define PCS1G_ANEG_CFG_ADV_ABILITY_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define PCS1G_ANEG_CFG_SW_RESOLVE_ENA BIT(8)
+#define PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT BIT(1)
+#define PCS1G_ANEG_CFG_ANEG_ENA BIT(0)
+
+#define PCS1G_ANEG_NP_CFG 0x58
+
+#define PCS1G_ANEG_NP_CFG_NP_TX(x) (((x) << 16) & GENMASK(31, 16))
+#define PCS1G_ANEG_NP_CFG_NP_TX_M GENMASK(31, 16)
+#define PCS1G_ANEG_NP_CFG_NP_TX_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define PCS1G_ANEG_NP_CFG_NP_LOADED_ONE_SHOT BIT(0)
+
+#define PCS1G_LB_CFG 0x5c
+
+#define PCS1G_LB_CFG_RA_ENA BIT(4)
+#define PCS1G_LB_CFG_GMII_PHY_LB_ENA BIT(1)
+#define PCS1G_LB_CFG_TBI_HOST_LB_ENA BIT(0)
+
+#define PCS1G_DBG_CFG 0x60
+
+#define PCS1G_DBG_CFG_UDLT BIT(0)
+
+#define PCS1G_CDET_CFG 0x64
+
+#define PCS1G_CDET_CFG_CDET_ENA BIT(0)
+
+#define PCS1G_ANEG_STATUS 0x68
+
+#define PCS1G_ANEG_STATUS_LP_ADV_ABILITY(x) (((x) << 16) & GENMASK(31, 16))
+#define PCS1G_ANEG_STATUS_LP_ADV_ABILITY_M GENMASK(31, 16)
+#define PCS1G_ANEG_STATUS_LP_ADV_ABILITY_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define PCS1G_ANEG_STATUS_PR BIT(4)
+#define PCS1G_ANEG_STATUS_PAGE_RX_STICKY BIT(3)
+#define PCS1G_ANEG_STATUS_ANEG_COMPLETE BIT(0)
+
+#define PCS1G_ANEG_NP_STATUS 0x6c
+
+#define PCS1G_LINK_STATUS 0x70
+
+#define PCS1G_LINK_STATUS_DELAY_VAR(x) (((x) << 12) & GENMASK(15, 12))
+#define PCS1G_LINK_STATUS_DELAY_VAR_M GENMASK(15, 12)
+#define PCS1G_LINK_STATUS_DELAY_VAR_X(x) (((x) & GENMASK(15, 12)) >> 12)
+#define PCS1G_LINK_STATUS_SIGNAL_DETECT BIT(8)
+#define PCS1G_LINK_STATUS_LINK_STATUS BIT(4)
+#define PCS1G_LINK_STATUS_SYNC_STATUS BIT(0)
+
+#define PCS1G_LINK_DOWN_CNT 0x74
+
+#define PCS1G_STICKY 0x78
+
+#define PCS1G_STICKY_LINK_DOWN_STICKY BIT(4)
+#define PCS1G_STICKY_OUT_OF_SYNC_STICKY BIT(0)
+
+#define PCS1G_DEBUG_STATUS 0x7c
+
+#define PCS1G_LPI_CFG 0x80
+
+#define PCS1G_LPI_CFG_QSGMII_MS_SEL BIT(20)
+#define PCS1G_LPI_CFG_RX_LPI_OUT_DIS BIT(17)
+#define PCS1G_LPI_CFG_LPI_TESTMODE BIT(16)
+#define PCS1G_LPI_CFG_LPI_RX_WTIM(x) (((x) << 4) & GENMASK(5, 4))
+#define PCS1G_LPI_CFG_LPI_RX_WTIM_M GENMASK(5, 4)
+#define PCS1G_LPI_CFG_LPI_RX_WTIM_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define PCS1G_LPI_CFG_TX_ASSERT_LPIDLE BIT(0)
+
+#define PCS1G_LPI_WAKE_ERROR_CNT 0x84
+
+#define PCS1G_LPI_STATUS 0x88
+
+#define PCS1G_LPI_STATUS_RX_LPI_FAIL BIT(16)
+#define PCS1G_LPI_STATUS_RX_LPI_EVENT_STICKY BIT(12)
+#define PCS1G_LPI_STATUS_RX_QUIET BIT(9)
+#define PCS1G_LPI_STATUS_RX_LPI_MODE BIT(8)
+#define PCS1G_LPI_STATUS_TX_LPI_EVENT_STICKY BIT(4)
+#define PCS1G_LPI_STATUS_TX_QUIET BIT(1)
+#define PCS1G_LPI_STATUS_TX_LPI_MODE BIT(0)
+
+#define PCS1G_TSTPAT_MODE_CFG 0x8c
+
+#define PCS1G_TSTPAT_STATUS 0x90
+
+#define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT(x) (((x) << 8) & GENMASK(15, 8))
+#define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT_M GENMASK(15, 8)
+#define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define PCS1G_TSTPAT_STATUS_JTP_ERR BIT(4)
+#define PCS1G_TSTPAT_STATUS_JTP_LOCK BIT(0)
+
+#define DEV_PCS_FX100_CFG 0x94
+
+#define DEV_PCS_FX100_CFG_SD_SEL BIT(26)
+#define DEV_PCS_FX100_CFG_SD_POL BIT(25)
+#define DEV_PCS_FX100_CFG_SD_ENA BIT(24)
+#define DEV_PCS_FX100_CFG_LOOPBACK_ENA BIT(20)
+#define DEV_PCS_FX100_CFG_SWAP_MII_ENA BIT(16)
+#define DEV_PCS_FX100_CFG_RXBITSEL(x) (((x) << 12) & GENMASK(15, 12))
+#define DEV_PCS_FX100_CFG_RXBITSEL_M GENMASK(15, 12)
+#define DEV_PCS_FX100_CFG_RXBITSEL_X(x) (((x) & GENMASK(15, 12)) >> 12)
+#define DEV_PCS_FX100_CFG_SIGDET_CFG(x) (((x) << 9) & GENMASK(10, 9))
+#define DEV_PCS_FX100_CFG_SIGDET_CFG_M GENMASK(10, 9)
+#define DEV_PCS_FX100_CFG_SIGDET_CFG_X(x) (((x) & GENMASK(10, 9)) >> 9)
+#define DEV_PCS_FX100_CFG_LINKHYST_TM_ENA BIT(8)
+#define DEV_PCS_FX100_CFG_LINKHYSTTIMER(x) (((x) << 4) & GENMASK(7, 4))
+#define DEV_PCS_FX100_CFG_LINKHYSTTIMER_M GENMASK(7, 4)
+#define DEV_PCS_FX100_CFG_LINKHYSTTIMER_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define DEV_PCS_FX100_CFG_UNIDIR_MODE_ENA BIT(3)
+#define DEV_PCS_FX100_CFG_FEFCHK_ENA BIT(2)
+#define DEV_PCS_FX100_CFG_FEFGEN_ENA BIT(1)
+#define DEV_PCS_FX100_CFG_PCS_ENA BIT(0)
+
+#define DEV_PCS_FX100_STATUS 0x98
+
+#define DEV_PCS_FX100_STATUS_EDGE_POS_PTP(x) (((x) << 8) & GENMASK(11, 8))
+#define DEV_PCS_FX100_STATUS_EDGE_POS_PTP_M GENMASK(11, 8)
+#define DEV_PCS_FX100_STATUS_EDGE_POS_PTP_X(x) (((x) & GENMASK(11, 8)) >> 8)
+#define DEV_PCS_FX100_STATUS_PCS_ERROR_STICKY BIT(7)
+#define DEV_PCS_FX100_STATUS_FEF_FOUND_STICKY BIT(6)
+#define DEV_PCS_FX100_STATUS_SSD_ERROR_STICKY BIT(5)
+#define DEV_PCS_FX100_STATUS_SYNC_LOST_STICKY BIT(4)
+#define DEV_PCS_FX100_STATUS_FEF_STATUS BIT(2)
+#define DEV_PCS_FX100_STATUS_SIGNAL_DETECT BIT(1)
+#define DEV_PCS_FX100_STATUS_SYNC_STATUS BIT(0)
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_DEV_GMII_H_
+#define _MSCC_OCELOT_DEV_GMII_H_
+
+#define DEV_GMII_PORT_MODE_CLOCK_CFG 0x0
+
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_MAC_TX_RST BIT(5)
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_MAC_RX_RST BIT(4)
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_PORT_RST BIT(3)
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_PHY_RST BIT(2)
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_LINK_SPEED(x) ((x) & GENMASK(1, 0))
+#define DEV_GMII_PORT_MODE_CLOCK_CFG_LINK_SPEED_M GENMASK(1, 0)
+
+#define DEV_GMII_PORT_MODE_PORT_MISC 0x4
+
+#define DEV_GMII_PORT_MODE_PORT_MISC_MPLS_RX_ENA BIT(5)
+#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_ERROR_ENA BIT(4)
+#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_PAUSE_ENA BIT(3)
+#define DEV_GMII_PORT_MODE_PORT_MISC_FWD_CTRL_ENA BIT(2)
+#define DEV_GMII_PORT_MODE_PORT_MISC_GMII_LOOP_ENA BIT(1)
+#define DEV_GMII_PORT_MODE_PORT_MISC_DEV_LOOP_ENA BIT(0)
+
+#define DEV_GMII_PORT_MODE_EVENTS 0x8
+
+#define DEV_GMII_PORT_MODE_EEE_CFG 0xc
+
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_ENA BIT(22)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE(x) (((x) << 15) & GENMASK(21, 15))
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE_M GENMASK(21, 15)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_AGE_X(x) (((x) & GENMASK(21, 15)) >> 15)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP(x) (((x) << 8) & GENMASK(14, 8))
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP_M GENMASK(14, 8)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_WAKEUP_X(x) (((x) & GENMASK(14, 8)) >> 8)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF(x) (((x) << 1) & GENMASK(7, 1))
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF_M GENMASK(7, 1)
+#define DEV_GMII_PORT_MODE_EEE_CFG_EEE_TIMER_HOLDOFF_X(x) (((x) & GENMASK(7, 1)) >> 1)
+#define DEV_GMII_PORT_MODE_EEE_CFG_PORT_LPI BIT(0)
+
+#define DEV_GMII_PORT_MODE_RX_PATH_DELAY 0x10
+
+#define DEV_GMII_PORT_MODE_TX_PATH_DELAY 0x14
+
+#define DEV_GMII_PORT_MODE_PTP_PREDICT_CFG 0x18
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG 0x1c
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG_RX_ENA BIT(4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_ENA_CFG_TX_ENA BIT(0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG 0x20
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_FC_WORD_SYNC_ENA BIT(8)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_GIGA_MODE_ENA BIT(4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_MODE_CFG_FDX_ENA BIT(0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_MAXLEN_CFG 0x24
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG 0x28
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID(x) (((x) << 16) & GENMASK(31, 16))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_PB_ENA BIT(1)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(2)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_ADV_CHK_CFG 0x2c
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_ADV_CHK_CFG_LEN_DROP_ENA BIT(0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG 0x30
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK BIT(17)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_REDUCED_TX_IFG BIT(16)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG(x) (((x) << 8) & GENMASK(12, 8))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG_M GENMASK(12, 8)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_TX_IFG_X(x) (((x) & GENMASK(12, 8)) >> 8)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2(x) (((x) << 4) & GENMASK(7, 4))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2_M GENMASK(7, 4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG2_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG1(x) ((x) & GENMASK(3, 0))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_IFG_CFG_RX_IFG1_M GENMASK(3, 0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG 0x34
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_BYPASS_COL_SYNC BIT(26)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_OB_ENA BIT(25)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_WEXC_DIS BIT(24)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED(x) (((x) << 16) & GENMASK(23, 16))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_M GENMASK(23, 16)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_SEED_LOAD BIT(12)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA BIT(8)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_LATE_COL_POS(x) ((x) & GENMASK(6, 0))
+#define DEV_GMII_MAC_CFG_STATUS_MAC_HDX_CFG_LATE_COL_POS_M GENMASK(6, 0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG 0x38
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG_TBI_MODE BIT(4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_DBG_CFG_IFG_CRS_EXT_CHK_ENA BIT(0)
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_FC_MAC_LOW_CFG 0x3c
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_FC_MAC_HIGH_CFG 0x40
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY 0x44
+
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_IPG_SHRINK_STICKY BIT(9)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_PREAM_SHRINK_STICKY BIT(8)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_CARRIER_EXT_STICKY BIT(7)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_CARRIER_EXT_ERR_STICKY BIT(6)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_RX_JUNK_STICKY BIT(5)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_RETRANSMIT_STICKY BIT(4)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_JAM_STICKY BIT(3)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_FIFO_OFLW_STICKY BIT(2)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_FRM_LEN_OVR_STICKY BIT(1)
+#define DEV_GMII_MAC_CFG_STATUS_MAC_STICKY_TX_ABORT_STICKY BIT(0)
+
+#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG 0x48
+
+#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_MM_RX_ENA BIT(0)
+#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_MM_TX_ENA BIT(4)
+#define DEV_GMII_MM_CONFIG_ENABLE_CONFIG_KEEP_S_AFTER_D BIT(8)
+
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG 0x4c
+
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_DIS BIT(0)
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME(x) (((x) << 4) & GENMASK(11, 4))
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME_M GENMASK(11, 4)
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_PRM_VERIFY_TIME_X(x) (((x) & GENMASK(11, 4)) >> 4)
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS(x) (((x) << 12) & GENMASK(13, 12))
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS_M GENMASK(13, 12)
+#define DEV_GMII_MM_CONFIG_VERIF_CONFIG_VERIF_TIMER_UNITS_X(x) (((x) & GENMASK(13, 12)) >> 12)
+
+#define DEV_GMII_MM_STATISTICS_MM_STATUS 0x50
+
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_ACTIVE_STATUS BIT(0)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_ACTIVE_STICKY BIT(4)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE(x) (((x) << 8) & GENMASK(10, 8))
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE_M GENMASK(10, 8)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_PRMPT_VERIFY_STATE_X(x) (((x) & GENMASK(10, 8)) >> 8)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_UNEXP_RX_PFRM_STICKY BIT(12)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_UNEXP_TX_PFRM_STICKY BIT(16)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_RX_FRAME_STATUS BIT(20)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_TX_FRAME_STATUS BIT(24)
+#define DEV_GMII_MM_STATISTICS_MM_STATUS_MM_TX_PRMPT_STATUS BIT(28)
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_HSIO_H_
+#define _MSCC_OCELOT_HSIO_H_
+
+#define HSIO_PLL5G_CFG0_ENA_ROT BIT(31)
+#define HSIO_PLL5G_CFG0_ENA_LANE BIT(30)
+#define HSIO_PLL5G_CFG0_ENA_CLKTREE BIT(29)
+#define HSIO_PLL5G_CFG0_DIV4 BIT(28)
+#define HSIO_PLL5G_CFG0_ENA_LOCK_FINE BIT(27)
+#define HSIO_PLL5G_CFG0_SELBGV820(x) (((x) << 23) & GENMASK(26, 23))
+#define HSIO_PLL5G_CFG0_SELBGV820_M GENMASK(26, 23)
+#define HSIO_PLL5G_CFG0_SELBGV820_X(x) (((x) & GENMASK(26, 23)) >> 23)
+#define HSIO_PLL5G_CFG0_LOOP_BW_RES(x) (((x) << 18) & GENMASK(22, 18))
+#define HSIO_PLL5G_CFG0_LOOP_BW_RES_M GENMASK(22, 18)
+#define HSIO_PLL5G_CFG0_LOOP_BW_RES_X(x) (((x) & GENMASK(22, 18)) >> 18)
+#define HSIO_PLL5G_CFG0_SELCPI(x) (((x) << 16) & GENMASK(17, 16))
+#define HSIO_PLL5G_CFG0_SELCPI_M GENMASK(17, 16)
+#define HSIO_PLL5G_CFG0_SELCPI_X(x) (((x) & GENMASK(17, 16)) >> 16)
+#define HSIO_PLL5G_CFG0_ENA_VCO_CONTRH BIT(15)
+#define HSIO_PLL5G_CFG0_ENA_CP1 BIT(14)
+#define HSIO_PLL5G_CFG0_ENA_VCO_BUF BIT(13)
+#define HSIO_PLL5G_CFG0_ENA_BIAS BIT(12)
+#define HSIO_PLL5G_CFG0_CPU_CLK_DIV(x) (((x) << 6) & GENMASK(11, 6))
+#define HSIO_PLL5G_CFG0_CPU_CLK_DIV_M GENMASK(11, 6)
+#define HSIO_PLL5G_CFG0_CPU_CLK_DIV_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define HSIO_PLL5G_CFG0_CORE_CLK_DIV(x) ((x) & GENMASK(5, 0))
+#define HSIO_PLL5G_CFG0_CORE_CLK_DIV_M GENMASK(5, 0)
+
+#define HSIO_PLL5G_CFG1_ENA_DIRECT BIT(18)
+#define HSIO_PLL5G_CFG1_ROT_SPEED BIT(17)
+#define HSIO_PLL5G_CFG1_ROT_DIR BIT(16)
+#define HSIO_PLL5G_CFG1_READBACK_DATA_SEL BIT(15)
+#define HSIO_PLL5G_CFG1_RC_ENABLE BIT(14)
+#define HSIO_PLL5G_CFG1_RC_CTRL_DATA(x) (((x) << 6) & GENMASK(13, 6))
+#define HSIO_PLL5G_CFG1_RC_CTRL_DATA_M GENMASK(13, 6)
+#define HSIO_PLL5G_CFG1_RC_CTRL_DATA_X(x) (((x) & GENMASK(13, 6)) >> 6)
+#define HSIO_PLL5G_CFG1_QUARTER_RATE BIT(5)
+#define HSIO_PLL5G_CFG1_PWD_TX BIT(4)
+#define HSIO_PLL5G_CFG1_PWD_RX BIT(3)
+#define HSIO_PLL5G_CFG1_OUT_OF_RANGE_RECAL_ENA BIT(2)
+#define HSIO_PLL5G_CFG1_HALF_RATE BIT(1)
+#define HSIO_PLL5G_CFG1_FORCE_SET_ENA BIT(0)
+
+#define HSIO_PLL5G_CFG2_ENA_TEST_MODE BIT(30)
+#define HSIO_PLL5G_CFG2_ENA_PFD_IN_FLIP BIT(29)
+#define HSIO_PLL5G_CFG2_ENA_VCO_NREF_TESTOUT BIT(28)
+#define HSIO_PLL5G_CFG2_ENA_FBTESTOUT BIT(27)
+#define HSIO_PLL5G_CFG2_ENA_RCPLL BIT(26)
+#define HSIO_PLL5G_CFG2_ENA_CP2 BIT(25)
+#define HSIO_PLL5G_CFG2_ENA_CLK_BYPASS1 BIT(24)
+#define HSIO_PLL5G_CFG2_AMPC_SEL(x) (((x) << 16) & GENMASK(23, 16))
+#define HSIO_PLL5G_CFG2_AMPC_SEL_M GENMASK(23, 16)
+#define HSIO_PLL5G_CFG2_AMPC_SEL_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define HSIO_PLL5G_CFG2_ENA_CLK_BYPASS BIT(15)
+#define HSIO_PLL5G_CFG2_PWD_AMPCTRL_N BIT(14)
+#define HSIO_PLL5G_CFG2_ENA_AMPCTRL BIT(13)
+#define HSIO_PLL5G_CFG2_ENA_AMP_CTRL_FORCE BIT(12)
+#define HSIO_PLL5G_CFG2_FRC_FSM_POR BIT(11)
+#define HSIO_PLL5G_CFG2_DISABLE_FSM_POR BIT(10)
+#define HSIO_PLL5G_CFG2_GAIN_TEST(x) (((x) << 5) & GENMASK(9, 5))
+#define HSIO_PLL5G_CFG2_GAIN_TEST_M GENMASK(9, 5)
+#define HSIO_PLL5G_CFG2_GAIN_TEST_X(x) (((x) & GENMASK(9, 5)) >> 5)
+#define HSIO_PLL5G_CFG2_EN_RESET_OVERRUN BIT(4)
+#define HSIO_PLL5G_CFG2_EN_RESET_LIM_DET BIT(3)
+#define HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET BIT(2)
+#define HSIO_PLL5G_CFG2_DISABLE_FSM BIT(1)
+#define HSIO_PLL5G_CFG2_ENA_GAIN_TEST BIT(0)
+
+#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL(x) (((x) << 22) & GENMASK(23, 22))
+#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL_M GENMASK(23, 22)
+#define HSIO_PLL5G_CFG3_TEST_ANA_OUT_SEL_X(x) (((x) & GENMASK(23, 22)) >> 22)
+#define HSIO_PLL5G_CFG3_TESTOUT_SEL(x) (((x) << 19) & GENMASK(21, 19))
+#define HSIO_PLL5G_CFG3_TESTOUT_SEL_M GENMASK(21, 19)
+#define HSIO_PLL5G_CFG3_TESTOUT_SEL_X(x) (((x) & GENMASK(21, 19)) >> 19)
+#define HSIO_PLL5G_CFG3_ENA_ANA_TEST_OUT BIT(18)
+#define HSIO_PLL5G_CFG3_ENA_TEST_OUT BIT(17)
+#define HSIO_PLL5G_CFG3_SEL_FBDCLK BIT(16)
+#define HSIO_PLL5G_CFG3_SEL_CML_CMOS_PFD BIT(15)
+#define HSIO_PLL5G_CFG3_RST_FB_N BIT(14)
+#define HSIO_PLL5G_CFG3_FORCE_VCO_CONTRH BIT(13)
+#define HSIO_PLL5G_CFG3_FORCE_LO BIT(12)
+#define HSIO_PLL5G_CFG3_FORCE_HI BIT(11)
+#define HSIO_PLL5G_CFG3_FORCE_ENA BIT(10)
+#define HSIO_PLL5G_CFG3_FORCE_CP BIT(9)
+#define HSIO_PLL5G_CFG3_FBDIVSEL_TST_ENA BIT(8)
+#define HSIO_PLL5G_CFG3_FBDIVSEL(x) ((x) & GENMASK(7, 0))
+#define HSIO_PLL5G_CFG3_FBDIVSEL_M GENMASK(7, 0)
+
+#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL(x) (((x) << 16) & GENMASK(23, 16))
+#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL_M GENMASK(23, 16)
+#define HSIO_PLL5G_CFG4_IB_BIAS_CTRL_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define HSIO_PLL5G_CFG4_IB_CTRL(x) ((x) & GENMASK(15, 0))
+#define HSIO_PLL5G_CFG4_IB_CTRL_M GENMASK(15, 0)
+
+#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL(x) (((x) << 16) & GENMASK(23, 16))
+#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL_M GENMASK(23, 16)
+#define HSIO_PLL5G_CFG5_OB_BIAS_CTRL_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define HSIO_PLL5G_CFG5_OB_CTRL(x) ((x) & GENMASK(15, 0))
+#define HSIO_PLL5G_CFG5_OB_CTRL_M GENMASK(15, 0)
+
+#define HSIO_PLL5G_CFG6_REFCLK_SEL_SRC BIT(23)
+#define HSIO_PLL5G_CFG6_REFCLK_SEL(x) (((x) << 20) & GENMASK(22, 20))
+#define HSIO_PLL5G_CFG6_REFCLK_SEL_M GENMASK(22, 20)
+#define HSIO_PLL5G_CFG6_REFCLK_SEL_X(x) (((x) & GENMASK(22, 20)) >> 20)
+#define HSIO_PLL5G_CFG6_REFCLK_SRC BIT(19)
+#define HSIO_PLL5G_CFG6_POR_DEL_SEL(x) (((x) << 16) & GENMASK(17, 16))
+#define HSIO_PLL5G_CFG6_POR_DEL_SEL_M GENMASK(17, 16)
+#define HSIO_PLL5G_CFG6_POR_DEL_SEL_X(x) (((x) & GENMASK(17, 16)) >> 16)
+#define HSIO_PLL5G_CFG6_DIV125REF_SEL(x) (((x) << 8) & GENMASK(15, 8))
+#define HSIO_PLL5G_CFG6_DIV125REF_SEL_M GENMASK(15, 8)
+#define HSIO_PLL5G_CFG6_DIV125REF_SEL_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define HSIO_PLL5G_CFG6_ENA_REFCLKC2 BIT(7)
+#define HSIO_PLL5G_CFG6_ENA_FBCLKC2 BIT(6)
+#define HSIO_PLL5G_CFG6_DDR_CLK_DIV(x) ((x) & GENMASK(5, 0))
+#define HSIO_PLL5G_CFG6_DDR_CLK_DIV_M GENMASK(5, 0)
+
+#define HSIO_PLL5G_STATUS0_RANGE_LIM BIT(12)
+#define HSIO_PLL5G_STATUS0_OUT_OF_RANGE_ERR BIT(11)
+#define HSIO_PLL5G_STATUS0_CALIBRATION_ERR BIT(10)
+#define HSIO_PLL5G_STATUS0_CALIBRATION_DONE BIT(9)
+#define HSIO_PLL5G_STATUS0_READBACK_DATA(x) (((x) << 1) & GENMASK(8, 1))
+#define HSIO_PLL5G_STATUS0_READBACK_DATA_M GENMASK(8, 1)
+#define HSIO_PLL5G_STATUS0_READBACK_DATA_X(x) (((x) & GENMASK(8, 1)) >> 1)
+#define HSIO_PLL5G_STATUS0_LOCK_STATUS BIT(0)
+
+#define HSIO_PLL5G_STATUS1_SIG_DEL(x) (((x) << 21) & GENMASK(28, 21))
+#define HSIO_PLL5G_STATUS1_SIG_DEL_M GENMASK(28, 21)
+#define HSIO_PLL5G_STATUS1_SIG_DEL_X(x) (((x) & GENMASK(28, 21)) >> 21)
+#define HSIO_PLL5G_STATUS1_GAIN_STAT(x) (((x) << 16) & GENMASK(20, 16))
+#define HSIO_PLL5G_STATUS1_GAIN_STAT_M GENMASK(20, 16)
+#define HSIO_PLL5G_STATUS1_GAIN_STAT_X(x) (((x) & GENMASK(20, 16)) >> 16)
+#define HSIO_PLL5G_STATUS1_FBCNT_DIF(x) (((x) << 4) & GENMASK(13, 4))
+#define HSIO_PLL5G_STATUS1_FBCNT_DIF_M GENMASK(13, 4)
+#define HSIO_PLL5G_STATUS1_FBCNT_DIF_X(x) (((x) & GENMASK(13, 4)) >> 4)
+#define HSIO_PLL5G_STATUS1_FSM_STAT(x) (((x) << 1) & GENMASK(3, 1))
+#define HSIO_PLL5G_STATUS1_FSM_STAT_M GENMASK(3, 1)
+#define HSIO_PLL5G_STATUS1_FSM_STAT_X(x) (((x) & GENMASK(3, 1)) >> 1)
+#define HSIO_PLL5G_STATUS1_FSM_LOCK BIT(0)
+
+#define HSIO_PLL5G_BIST_CFG0_PLLB_START_BIST BIT(31)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_MEAS_MODE BIT(30)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT(x) (((x) << 20) & GENMASK(23, 20))
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT_M GENMASK(23, 20)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_REPEAT_X(x) (((x) & GENMASK(23, 20)) >> 20)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT(x) (((x) << 16) & GENMASK(19, 16))
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT_M GENMASK(19, 16)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_LOCK_UNCERT_X(x) (((x) & GENMASK(19, 16)) >> 16)
+#define HSIO_PLL5G_BIST_CFG0_PLLB_DIV_FACTOR_PRE(x) ((x) & GENMASK(15, 0))
+#define HSIO_PLL5G_BIST_CFG0_PLLB_DIV_FACTOR_PRE_M GENMASK(15, 0)
+
+#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT_M GENMASK(7, 4)
+#define HSIO_PLL5G_BIST_STAT0_PLLB_FSM_STAT_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_PLL5G_BIST_STAT0_PLLB_BUSY BIT(2)
+#define HSIO_PLL5G_BIST_STAT0_PLLB_DONE_N BIT(1)
+#define HSIO_PLL5G_BIST_STAT0_PLLB_FAIL BIT(0)
+
+#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT(x) (((x) << 16) & GENMASK(31, 16))
+#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT_M GENMASK(31, 16)
+#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_OUT_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_REF_DIFF(x) ((x) & GENMASK(15, 0))
+#define HSIO_PLL5G_BIST_STAT1_PLLB_CNT_REF_DIFF_M GENMASK(15, 0)
+
+#define HSIO_RCOMP_CFG0_PWD_ENA BIT(13)
+#define HSIO_RCOMP_CFG0_RUN_CAL BIT(12)
+#define HSIO_RCOMP_CFG0_SPEED_SEL(x) (((x) << 10) & GENMASK(11, 10))
+#define HSIO_RCOMP_CFG0_SPEED_SEL_M GENMASK(11, 10)
+#define HSIO_RCOMP_CFG0_SPEED_SEL_X(x) (((x) & GENMASK(11, 10)) >> 10)
+#define HSIO_RCOMP_CFG0_MODE_SEL(x) (((x) << 8) & GENMASK(9, 8))
+#define HSIO_RCOMP_CFG0_MODE_SEL_M GENMASK(9, 8)
+#define HSIO_RCOMP_CFG0_MODE_SEL_X(x) (((x) & GENMASK(9, 8)) >> 8)
+#define HSIO_RCOMP_CFG0_FORCE_ENA BIT(4)
+#define HSIO_RCOMP_CFG0_RCOMP_VAL(x) ((x) & GENMASK(3, 0))
+#define HSIO_RCOMP_CFG0_RCOMP_VAL_M GENMASK(3, 0)
+
+#define HSIO_RCOMP_STATUS_BUSY BIT(12)
+#define HSIO_RCOMP_STATUS_DELTA_ALERT BIT(7)
+#define HSIO_RCOMP_STATUS_RCOMP(x) ((x) & GENMASK(3, 0))
+#define HSIO_RCOMP_STATUS_RCOMP_M GENMASK(3, 0)
+
+#define HSIO_SYNC_ETH_CFG_RSZ 0x4
+
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC_M GENMASK(7, 4)
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_SRC_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV(x) (((x) << 1) & GENMASK(3, 1))
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV_M GENMASK(3, 1)
+#define HSIO_SYNC_ETH_CFG_SEL_RECO_CLK_DIV_X(x) (((x) & GENMASK(3, 1)) >> 1)
+#define HSIO_SYNC_ETH_CFG_RECO_CLK_ENA BIT(0)
+
+#define HSIO_SYNC_ETH_PLL_CFG_PLL_AUTO_SQUELCH_ENA BIT(0)
+
+#define HSIO_S1G_DES_CFG_DES_PHS_CTRL(x) (((x) << 13) & GENMASK(16, 13))
+#define HSIO_S1G_DES_CFG_DES_PHS_CTRL_M GENMASK(16, 13)
+#define HSIO_S1G_DES_CFG_DES_PHS_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13)
+#define HSIO_S1G_DES_CFG_DES_CPMD_SEL(x) (((x) << 11) & GENMASK(12, 11))
+#define HSIO_S1G_DES_CFG_DES_CPMD_SEL_M GENMASK(12, 11)
+#define HSIO_S1G_DES_CFG_DES_CPMD_SEL_X(x) (((x) & GENMASK(12, 11)) >> 11)
+#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL(x) (((x) << 8) & GENMASK(10, 8))
+#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL_M GENMASK(10, 8)
+#define HSIO_S1G_DES_CFG_DES_MBTR_CTRL_X(x) (((x) & GENMASK(10, 8)) >> 8)
+#define HSIO_S1G_DES_CFG_DES_BW_ANA(x) (((x) << 5) & GENMASK(7, 5))
+#define HSIO_S1G_DES_CFG_DES_BW_ANA_M GENMASK(7, 5)
+#define HSIO_S1G_DES_CFG_DES_BW_ANA_X(x) (((x) & GENMASK(7, 5)) >> 5)
+#define HSIO_S1G_DES_CFG_DES_SWAP_ANA BIT(4)
+#define HSIO_S1G_DES_CFG_DES_BW_HYST(x) (((x) << 1) & GENMASK(3, 1))
+#define HSIO_S1G_DES_CFG_DES_BW_HYST_M GENMASK(3, 1)
+#define HSIO_S1G_DES_CFG_DES_BW_HYST_X(x) (((x) & GENMASK(3, 1)) >> 1)
+#define HSIO_S1G_DES_CFG_DES_SWAP_HYST BIT(0)
+
+#define HSIO_S1G_IB_CFG_IB_FX100_ENA BIT(27)
+#define HSIO_S1G_IB_CFG_ACJTAG_HYST(x) (((x) << 24) & GENMASK(26, 24))
+#define HSIO_S1G_IB_CFG_ACJTAG_HYST_M GENMASK(26, 24)
+#define HSIO_S1G_IB_CFG_ACJTAG_HYST_X(x) (((x) & GENMASK(26, 24)) >> 24)
+#define HSIO_S1G_IB_CFG_IB_DET_LEV(x) (((x) << 19) & GENMASK(21, 19))
+#define HSIO_S1G_IB_CFG_IB_DET_LEV_M GENMASK(21, 19)
+#define HSIO_S1G_IB_CFG_IB_DET_LEV_X(x) (((x) & GENMASK(21, 19)) >> 19)
+#define HSIO_S1G_IB_CFG_IB_HYST_LEV BIT(14)
+#define HSIO_S1G_IB_CFG_IB_ENA_CMV_TERM BIT(13)
+#define HSIO_S1G_IB_CFG_IB_ENA_DC_COUPLING BIT(12)
+#define HSIO_S1G_IB_CFG_IB_ENA_DETLEV BIT(11)
+#define HSIO_S1G_IB_CFG_IB_ENA_HYST BIT(10)
+#define HSIO_S1G_IB_CFG_IB_ENA_OFFSET_COMP BIT(9)
+#define HSIO_S1G_IB_CFG_IB_EQ_GAIN(x) (((x) << 6) & GENMASK(8, 6))
+#define HSIO_S1G_IB_CFG_IB_EQ_GAIN_M GENMASK(8, 6)
+#define HSIO_S1G_IB_CFG_IB_EQ_GAIN_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ(x) (((x) << 4) & GENMASK(5, 4))
+#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ_M GENMASK(5, 4)
+#define HSIO_S1G_IB_CFG_IB_SEL_CORNER_FREQ_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define HSIO_S1G_IB_CFG_IB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0))
+#define HSIO_S1G_IB_CFG_IB_RESISTOR_CTRL_M GENMASK(3, 0)
+
+#define HSIO_S1G_OB_CFG_OB_SLP(x) (((x) << 17) & GENMASK(18, 17))
+#define HSIO_S1G_OB_CFG_OB_SLP_M GENMASK(18, 17)
+#define HSIO_S1G_OB_CFG_OB_SLP_X(x) (((x) & GENMASK(18, 17)) >> 17)
+#define HSIO_S1G_OB_CFG_OB_AMP_CTRL(x) (((x) << 13) & GENMASK(16, 13))
+#define HSIO_S1G_OB_CFG_OB_AMP_CTRL_M GENMASK(16, 13)
+#define HSIO_S1G_OB_CFG_OB_AMP_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13)
+#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL(x) (((x) << 10) & GENMASK(12, 10))
+#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL_M GENMASK(12, 10)
+#define HSIO_S1G_OB_CFG_OB_CMM_BIAS_CTRL_X(x) (((x) & GENMASK(12, 10)) >> 10)
+#define HSIO_S1G_OB_CFG_OB_DIS_VCM_CTRL BIT(9)
+#define HSIO_S1G_OB_CFG_OB_EN_MEAS_VREG BIT(8)
+#define HSIO_S1G_OB_CFG_OB_VCM_CTRL(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S1G_OB_CFG_OB_VCM_CTRL_M GENMASK(7, 4)
+#define HSIO_S1G_OB_CFG_OB_VCM_CTRL_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S1G_OB_CFG_OB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0))
+#define HSIO_S1G_OB_CFG_OB_RESISTOR_CTRL_M GENMASK(3, 0)
+
+#define HSIO_S1G_SER_CFG_SER_IDLE BIT(9)
+#define HSIO_S1G_SER_CFG_SER_DEEMPH BIT(8)
+#define HSIO_S1G_SER_CFG_SER_CPMD_SEL BIT(7)
+#define HSIO_S1G_SER_CFG_SER_SWAP_CPMD BIT(6)
+#define HSIO_S1G_SER_CFG_SER_ALISEL(x) (((x) << 4) & GENMASK(5, 4))
+#define HSIO_S1G_SER_CFG_SER_ALISEL_M GENMASK(5, 4)
+#define HSIO_S1G_SER_CFG_SER_ALISEL_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define HSIO_S1G_SER_CFG_SER_ENHYS BIT(3)
+#define HSIO_S1G_SER_CFG_SER_BIG_WIN BIT(2)
+#define HSIO_S1G_SER_CFG_SER_EN_WIN BIT(1)
+#define HSIO_S1G_SER_CFG_SER_ENALI BIT(0)
+
+#define HSIO_S1G_COMMON_CFG_SYS_RST BIT(31)
+#define HSIO_S1G_COMMON_CFG_SE_AUTO_SQUELCH_ENA BIT(21)
+#define HSIO_S1G_COMMON_CFG_ENA_LANE BIT(18)
+#define HSIO_S1G_COMMON_CFG_PWD_RX BIT(17)
+#define HSIO_S1G_COMMON_CFG_PWD_TX BIT(16)
+#define HSIO_S1G_COMMON_CFG_LANE_CTRL(x) (((x) << 13) & GENMASK(15, 13))
+#define HSIO_S1G_COMMON_CFG_LANE_CTRL_M GENMASK(15, 13)
+#define HSIO_S1G_COMMON_CFG_LANE_CTRL_X(x) (((x) & GENMASK(15, 13)) >> 13)
+#define HSIO_S1G_COMMON_CFG_ENA_DIRECT BIT(12)
+#define HSIO_S1G_COMMON_CFG_ENA_ELOOP BIT(11)
+#define HSIO_S1G_COMMON_CFG_ENA_FLOOP BIT(10)
+#define HSIO_S1G_COMMON_CFG_ENA_ILOOP BIT(9)
+#define HSIO_S1G_COMMON_CFG_ENA_PLOOP BIT(8)
+#define HSIO_S1G_COMMON_CFG_HRATE BIT(7)
+#define HSIO_S1G_COMMON_CFG_IF_MODE BIT(0)
+
+#define HSIO_S1G_PLL_CFG_PLL_ENA_FB_DIV2 BIT(22)
+#define HSIO_S1G_PLL_CFG_PLL_ENA_RC_DIV2 BIT(21)
+#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA(x) (((x) << 8) & GENMASK(15, 8))
+#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA_M GENMASK(15, 8)
+#define HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define HSIO_S1G_PLL_CFG_PLL_FSM_ENA BIT(7)
+#define HSIO_S1G_PLL_CFG_PLL_FSM_FORCE_SET_ENA BIT(6)
+#define HSIO_S1G_PLL_CFG_PLL_FSM_OOR_RECAL_ENA BIT(5)
+#define HSIO_S1G_PLL_CFG_PLL_RB_DATA_SEL BIT(3)
+
+#define HSIO_S1G_PLL_STATUS_PLL_CAL_NOT_DONE BIT(12)
+#define HSIO_S1G_PLL_STATUS_PLL_CAL_ERR BIT(11)
+#define HSIO_S1G_PLL_STATUS_PLL_OUT_OF_RANGE_ERR BIT(10)
+#define HSIO_S1G_PLL_STATUS_PLL_RB_DATA(x) ((x) & GENMASK(7, 0))
+#define HSIO_S1G_PLL_STATUS_PLL_RB_DATA_M GENMASK(7, 0)
+
+#define HSIO_S1G_DFT_CFG0_LAZYBIT BIT(31)
+#define HSIO_S1G_DFT_CFG0_INV_DIS BIT(23)
+#define HSIO_S1G_DFT_CFG0_PRBS_SEL(x) (((x) << 20) & GENMASK(21, 20))
+#define HSIO_S1G_DFT_CFG0_PRBS_SEL_M GENMASK(21, 20)
+#define HSIO_S1G_DFT_CFG0_PRBS_SEL_X(x) (((x) & GENMASK(21, 20)) >> 20)
+#define HSIO_S1G_DFT_CFG0_TEST_MODE(x) (((x) << 16) & GENMASK(18, 16))
+#define HSIO_S1G_DFT_CFG0_TEST_MODE_M GENMASK(18, 16)
+#define HSIO_S1G_DFT_CFG0_TEST_MODE_X(x) (((x) & GENMASK(18, 16)) >> 16)
+#define HSIO_S1G_DFT_CFG0_RX_PHS_CORR_DIS BIT(4)
+#define HSIO_S1G_DFT_CFG0_RX_PDSENS_ENA BIT(3)
+#define HSIO_S1G_DFT_CFG0_RX_DFT_ENA BIT(2)
+#define HSIO_S1G_DFT_CFG0_TX_DFT_ENA BIT(0)
+
+#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8))
+#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL_M GENMASK(17, 8)
+#define HSIO_S1G_DFT_CFG1_TX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8)
+#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ_M GENMASK(7, 4)
+#define HSIO_S1G_DFT_CFG1_TX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S1G_DFT_CFG1_TX_JI_ENA BIT(3)
+#define HSIO_S1G_DFT_CFG1_TX_WAVEFORM_SEL BIT(2)
+#define HSIO_S1G_DFT_CFG1_TX_FREQOFF_DIR BIT(1)
+#define HSIO_S1G_DFT_CFG1_TX_FREQOFF_ENA BIT(0)
+
+#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8))
+#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL_M GENMASK(17, 8)
+#define HSIO_S1G_DFT_CFG2_RX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8)
+#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ_M GENMASK(7, 4)
+#define HSIO_S1G_DFT_CFG2_RX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S1G_DFT_CFG2_RX_JI_ENA BIT(3)
+#define HSIO_S1G_DFT_CFG2_RX_WAVEFORM_SEL BIT(2)
+#define HSIO_S1G_DFT_CFG2_RX_FREQOFF_DIR BIT(1)
+#define HSIO_S1G_DFT_CFG2_RX_FREQOFF_ENA BIT(0)
+
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_ENA BIT(20)
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH(x) (((x) << 16) & GENMASK(17, 16))
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_M GENMASK(17, 16)
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_X(x) (((x) & GENMASK(17, 16)) >> 16)
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH(x) (((x) << 8) & GENMASK(15, 8))
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_M GENMASK(15, 8)
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_LOW(x) ((x) & GENMASK(7, 0))
+#define HSIO_S1G_RC_PLL_BIST_CFG_PLL_BIST_LOW_M GENMASK(7, 0)
+
+#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE(x) (((x) << 11) & GENMASK(12, 11))
+#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE_M GENMASK(12, 11)
+#define HSIO_S1G_MISC_CFG_DES_100FX_KICK_MODE_X(x) (((x) & GENMASK(12, 11)) >> 11)
+#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_SWAP BIT(10)
+#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_MODE BIT(9)
+#define HSIO_S1G_MISC_CFG_DES_100FX_CPMD_ENA BIT(8)
+#define HSIO_S1G_MISC_CFG_RX_LPI_MODE_ENA BIT(5)
+#define HSIO_S1G_MISC_CFG_TX_LPI_MODE_ENA BIT(4)
+#define HSIO_S1G_MISC_CFG_RX_DATA_INV_ENA BIT(3)
+#define HSIO_S1G_MISC_CFG_TX_DATA_INV_ENA BIT(2)
+#define HSIO_S1G_MISC_CFG_LANE_RST BIT(0)
+
+#define HSIO_S1G_DFT_STATUS_PLL_BIST_NOT_DONE BIT(7)
+#define HSIO_S1G_DFT_STATUS_PLL_BIST_FAILED BIT(6)
+#define HSIO_S1G_DFT_STATUS_PLL_BIST_TIMEOUT_ERR BIT(5)
+#define HSIO_S1G_DFT_STATUS_BIST_ACTIVE BIT(3)
+#define HSIO_S1G_DFT_STATUS_BIST_NOSYNC BIT(2)
+#define HSIO_S1G_DFT_STATUS_BIST_COMPLETE_N BIT(1)
+#define HSIO_S1G_DFT_STATUS_BIST_ERROR BIT(0)
+
+#define HSIO_S1G_MISC_STATUS_DES_100FX_PHASE_SEL BIT(0)
+
+#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_WR_ONE_SHOT BIT(31)
+#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_RD_ONE_SHOT BIT(30)
+#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_ADDR(x) ((x) & GENMASK(8, 0))
+#define HSIO_MCB_S1G_ADDR_CFG_SERDES1G_ADDR_M GENMASK(8, 0)
+
+#define HSIO_S6G_DIG_CFG_GP(x) (((x) << 16) & GENMASK(18, 16))
+#define HSIO_S6G_DIG_CFG_GP_M GENMASK(18, 16)
+#define HSIO_S6G_DIG_CFG_GP_X(x) (((x) & GENMASK(18, 16)) >> 16)
+#define HSIO_S6G_DIG_CFG_TX_BIT_DOUBLING_MODE_ENA BIT(7)
+#define HSIO_S6G_DIG_CFG_SIGDET_TESTMODE BIT(6)
+#define HSIO_S6G_DIG_CFG_SIGDET_AST(x) (((x) << 3) & GENMASK(5, 3))
+#define HSIO_S6G_DIG_CFG_SIGDET_AST_M GENMASK(5, 3)
+#define HSIO_S6G_DIG_CFG_SIGDET_AST_X(x) (((x) & GENMASK(5, 3)) >> 3)
+#define HSIO_S6G_DIG_CFG_SIGDET_DST(x) ((x) & GENMASK(2, 0))
+#define HSIO_S6G_DIG_CFG_SIGDET_DST_M GENMASK(2, 0)
+
+#define HSIO_S6G_DFT_CFG0_LAZYBIT BIT(31)
+#define HSIO_S6G_DFT_CFG0_INV_DIS BIT(23)
+#define HSIO_S6G_DFT_CFG0_PRBS_SEL(x) (((x) << 20) & GENMASK(21, 20))
+#define HSIO_S6G_DFT_CFG0_PRBS_SEL_M GENMASK(21, 20)
+#define HSIO_S6G_DFT_CFG0_PRBS_SEL_X(x) (((x) & GENMASK(21, 20)) >> 20)
+#define HSIO_S6G_DFT_CFG0_TEST_MODE(x) (((x) << 16) & GENMASK(18, 16))
+#define HSIO_S6G_DFT_CFG0_TEST_MODE_M GENMASK(18, 16)
+#define HSIO_S6G_DFT_CFG0_TEST_MODE_X(x) (((x) & GENMASK(18, 16)) >> 16)
+#define HSIO_S6G_DFT_CFG0_RX_PHS_CORR_DIS BIT(4)
+#define HSIO_S6G_DFT_CFG0_RX_PDSENS_ENA BIT(3)
+#define HSIO_S6G_DFT_CFG0_RX_DFT_ENA BIT(2)
+#define HSIO_S6G_DFT_CFG0_TX_DFT_ENA BIT(0)
+
+#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8))
+#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL_M GENMASK(17, 8)
+#define HSIO_S6G_DFT_CFG1_TX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8)
+#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ_M GENMASK(7, 4)
+#define HSIO_S6G_DFT_CFG1_TX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S6G_DFT_CFG1_TX_JI_ENA BIT(3)
+#define HSIO_S6G_DFT_CFG1_TX_WAVEFORM_SEL BIT(2)
+#define HSIO_S6G_DFT_CFG1_TX_FREQOFF_DIR BIT(1)
+#define HSIO_S6G_DFT_CFG1_TX_FREQOFF_ENA BIT(0)
+
+#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL(x) (((x) << 8) & GENMASK(17, 8))
+#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL_M GENMASK(17, 8)
+#define HSIO_S6G_DFT_CFG2_RX_JITTER_AMPL_X(x) (((x) & GENMASK(17, 8)) >> 8)
+#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ_M GENMASK(7, 4)
+#define HSIO_S6G_DFT_CFG2_RX_STEP_FREQ_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S6G_DFT_CFG2_RX_JI_ENA BIT(3)
+#define HSIO_S6G_DFT_CFG2_RX_WAVEFORM_SEL BIT(2)
+#define HSIO_S6G_DFT_CFG2_RX_FREQOFF_DIR BIT(1)
+#define HSIO_S6G_DFT_CFG2_RX_FREQOFF_ENA BIT(0)
+
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_ENA BIT(20)
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH(x) (((x) << 16) & GENMASK(19, 16))
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_M GENMASK(19, 16)
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_FBS_HIGH_X(x) (((x) & GENMASK(19, 16)) >> 16)
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH(x) (((x) << 8) & GENMASK(15, 8))
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_M GENMASK(15, 8)
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_HIGH_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_LOW(x) ((x) & GENMASK(7, 0))
+#define HSIO_S6G_RC_PLL_BIST_CFG_PLL_BIST_LOW_M GENMASK(7, 0)
+
+#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK(x) (((x) << 13) & GENMASK(14, 13))
+#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK_M GENMASK(14, 13)
+#define HSIO_S6G_MISC_CFG_SEL_RECO_CLK_X(x) (((x) & GENMASK(14, 13)) >> 13)
+#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE(x) (((x) << 11) & GENMASK(12, 11))
+#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE_M GENMASK(12, 11)
+#define HSIO_S6G_MISC_CFG_DES_100FX_KICK_MODE_X(x) (((x) & GENMASK(12, 11)) >> 11)
+#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_SWAP BIT(10)
+#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_MODE BIT(9)
+#define HSIO_S6G_MISC_CFG_DES_100FX_CPMD_ENA BIT(8)
+#define HSIO_S6G_MISC_CFG_RX_BUS_FLIP_ENA BIT(7)
+#define HSIO_S6G_MISC_CFG_TX_BUS_FLIP_ENA BIT(6)
+#define HSIO_S6G_MISC_CFG_RX_LPI_MODE_ENA BIT(5)
+#define HSIO_S6G_MISC_CFG_TX_LPI_MODE_ENA BIT(4)
+#define HSIO_S6G_MISC_CFG_RX_DATA_INV_ENA BIT(3)
+#define HSIO_S6G_MISC_CFG_TX_DATA_INV_ENA BIT(2)
+#define HSIO_S6G_MISC_CFG_LANE_RST BIT(0)
+
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0(x) (((x) << 23) & GENMASK(28, 23))
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0_M GENMASK(28, 23)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST0_X(x) (((x) & GENMASK(28, 23)) >> 23)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1(x) (((x) << 18) & GENMASK(22, 18))
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1_M GENMASK(22, 18)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_POST1_X(x) (((x) & GENMASK(22, 18)) >> 18)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC(x) (((x) << 13) & GENMASK(17, 13))
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC_M GENMASK(17, 13)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_PREC_X(x) (((x) & GENMASK(17, 13)) >> 13)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS(x) (((x) << 6) & GENMASK(8, 6))
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS_M GENMASK(8, 6)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_ENA_CAS_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_LEV(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_OB_ANEG_CFG_AN_OB_LEV_M GENMASK(5, 0)
+
+#define HSIO_S6G_DFT_STATUS_PRBS_SYNC_STAT BIT(8)
+#define HSIO_S6G_DFT_STATUS_PLL_BIST_NOT_DONE BIT(7)
+#define HSIO_S6G_DFT_STATUS_PLL_BIST_FAILED BIT(6)
+#define HSIO_S6G_DFT_STATUS_PLL_BIST_TIMEOUT_ERR BIT(5)
+#define HSIO_S6G_DFT_STATUS_BIST_ACTIVE BIT(3)
+#define HSIO_S6G_DFT_STATUS_BIST_NOSYNC BIT(2)
+#define HSIO_S6G_DFT_STATUS_BIST_COMPLETE_N BIT(1)
+#define HSIO_S6G_DFT_STATUS_BIST_ERROR BIT(0)
+
+#define HSIO_S6G_MISC_STATUS_DES_100FX_PHASE_SEL BIT(0)
+
+#define HSIO_S6G_DES_CFG_DES_PHS_CTRL(x) (((x) << 13) & GENMASK(16, 13))
+#define HSIO_S6G_DES_CFG_DES_PHS_CTRL_M GENMASK(16, 13)
+#define HSIO_S6G_DES_CFG_DES_PHS_CTRL_X(x) (((x) & GENMASK(16, 13)) >> 13)
+#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL(x) (((x) << 10) & GENMASK(12, 10))
+#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL_M GENMASK(12, 10)
+#define HSIO_S6G_DES_CFG_DES_MBTR_CTRL_X(x) (((x) & GENMASK(12, 10)) >> 10)
+#define HSIO_S6G_DES_CFG_DES_CPMD_SEL(x) (((x) << 8) & GENMASK(9, 8))
+#define HSIO_S6G_DES_CFG_DES_CPMD_SEL_M GENMASK(9, 8)
+#define HSIO_S6G_DES_CFG_DES_CPMD_SEL_X(x) (((x) & GENMASK(9, 8)) >> 8)
+#define HSIO_S6G_DES_CFG_DES_BW_HYST(x) (((x) << 5) & GENMASK(7, 5))
+#define HSIO_S6G_DES_CFG_DES_BW_HYST_M GENMASK(7, 5)
+#define HSIO_S6G_DES_CFG_DES_BW_HYST_X(x) (((x) & GENMASK(7, 5)) >> 5)
+#define HSIO_S6G_DES_CFG_DES_SWAP_HYST BIT(4)
+#define HSIO_S6G_DES_CFG_DES_BW_ANA(x) (((x) << 1) & GENMASK(3, 1))
+#define HSIO_S6G_DES_CFG_DES_BW_ANA_M GENMASK(3, 1)
+#define HSIO_S6G_DES_CFG_DES_BW_ANA_X(x) (((x) & GENMASK(3, 1)) >> 1)
+#define HSIO_S6G_DES_CFG_DES_SWAP_ANA BIT(0)
+
+#define HSIO_S6G_IB_CFG_IB_SOFSI(x) (((x) << 29) & GENMASK(30, 29))
+#define HSIO_S6G_IB_CFG_IB_SOFSI_M GENMASK(30, 29)
+#define HSIO_S6G_IB_CFG_IB_SOFSI_X(x) (((x) & GENMASK(30, 29)) >> 29)
+#define HSIO_S6G_IB_CFG_IB_VBULK_SEL BIT(28)
+#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ(x) (((x) << 24) & GENMASK(27, 24))
+#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ_M GENMASK(27, 24)
+#define HSIO_S6G_IB_CFG_IB_RTRM_ADJ_X(x) (((x) & GENMASK(27, 24)) >> 24)
+#define HSIO_S6G_IB_CFG_IB_ICML_ADJ(x) (((x) << 20) & GENMASK(23, 20))
+#define HSIO_S6G_IB_CFG_IB_ICML_ADJ_M GENMASK(23, 20)
+#define HSIO_S6G_IB_CFG_IB_ICML_ADJ_X(x) (((x) & GENMASK(23, 20)) >> 20)
+#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL(x) (((x) << 18) & GENMASK(19, 18))
+#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL_M GENMASK(19, 18)
+#define HSIO_S6G_IB_CFG_IB_TERM_MODE_SEL_X(x) (((x) & GENMASK(19, 18)) >> 18)
+#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL(x) (((x) << 15) & GENMASK(17, 15))
+#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL_M GENMASK(17, 15)
+#define HSIO_S6G_IB_CFG_IB_SIG_DET_CLK_SEL_X(x) (((x) & GENMASK(17, 15)) >> 15)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP(x) (((x) << 13) & GENMASK(14, 13))
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP_M GENMASK(14, 13)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_HP_X(x) (((x) & GENMASK(14, 13)) >> 13)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID(x) (((x) << 11) & GENMASK(12, 11))
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID_M GENMASK(12, 11)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_MID_X(x) (((x) & GENMASK(12, 11)) >> 11)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP(x) (((x) << 9) & GENMASK(10, 9))
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP_M GENMASK(10, 9)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_LP_X(x) (((x) & GENMASK(10, 9)) >> 9)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET(x) (((x) << 7) & GENMASK(8, 7))
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET_M GENMASK(8, 7)
+#define HSIO_S6G_IB_CFG_IB_REG_PAT_SEL_OFFSET_X(x) (((x) & GENMASK(8, 7)) >> 7)
+#define HSIO_S6G_IB_CFG_IB_ANA_TEST_ENA BIT(6)
+#define HSIO_S6G_IB_CFG_IB_SIG_DET_ENA BIT(5)
+#define HSIO_S6G_IB_CFG_IB_CONCUR BIT(4)
+#define HSIO_S6G_IB_CFG_IB_CAL_ENA BIT(3)
+#define HSIO_S6G_IB_CFG_IB_SAM_ENA BIT(2)
+#define HSIO_S6G_IB_CFG_IB_EQZ_ENA BIT(1)
+#define HSIO_S6G_IB_CFG_IB_REG_ENA BIT(0)
+
+#define HSIO_S6G_IB_CFG1_IB_TJTAG(x) (((x) << 17) & GENMASK(21, 17))
+#define HSIO_S6G_IB_CFG1_IB_TJTAG_M GENMASK(21, 17)
+#define HSIO_S6G_IB_CFG1_IB_TJTAG_X(x) (((x) & GENMASK(21, 17)) >> 17)
+#define HSIO_S6G_IB_CFG1_IB_TSDET(x) (((x) << 12) & GENMASK(16, 12))
+#define HSIO_S6G_IB_CFG1_IB_TSDET_M GENMASK(16, 12)
+#define HSIO_S6G_IB_CFG1_IB_TSDET_X(x) (((x) & GENMASK(16, 12)) >> 12)
+#define HSIO_S6G_IB_CFG1_IB_SCALY(x) (((x) << 8) & GENMASK(11, 8))
+#define HSIO_S6G_IB_CFG1_IB_SCALY_M GENMASK(11, 8)
+#define HSIO_S6G_IB_CFG1_IB_SCALY_X(x) (((x) & GENMASK(11, 8)) >> 8)
+#define HSIO_S6G_IB_CFG1_IB_FILT_HP BIT(7)
+#define HSIO_S6G_IB_CFG1_IB_FILT_MID BIT(6)
+#define HSIO_S6G_IB_CFG1_IB_FILT_LP BIT(5)
+#define HSIO_S6G_IB_CFG1_IB_FILT_OFFSET BIT(4)
+#define HSIO_S6G_IB_CFG1_IB_FRC_HP BIT(3)
+#define HSIO_S6G_IB_CFG1_IB_FRC_MID BIT(2)
+#define HSIO_S6G_IB_CFG1_IB_FRC_LP BIT(1)
+#define HSIO_S6G_IB_CFG1_IB_FRC_OFFSET BIT(0)
+
+#define HSIO_S6G_IB_CFG2_IB_TINFV(x) (((x) << 27) & GENMASK(29, 27))
+#define HSIO_S6G_IB_CFG2_IB_TINFV_M GENMASK(29, 27)
+#define HSIO_S6G_IB_CFG2_IB_TINFV_X(x) (((x) & GENMASK(29, 27)) >> 27)
+#define HSIO_S6G_IB_CFG2_IB_OINFI(x) (((x) << 22) & GENMASK(26, 22))
+#define HSIO_S6G_IB_CFG2_IB_OINFI_M GENMASK(26, 22)
+#define HSIO_S6G_IB_CFG2_IB_OINFI_X(x) (((x) & GENMASK(26, 22)) >> 22)
+#define HSIO_S6G_IB_CFG2_IB_TAUX(x) (((x) << 19) & GENMASK(21, 19))
+#define HSIO_S6G_IB_CFG2_IB_TAUX_M GENMASK(21, 19)
+#define HSIO_S6G_IB_CFG2_IB_TAUX_X(x) (((x) & GENMASK(21, 19)) >> 19)
+#define HSIO_S6G_IB_CFG2_IB_OINFS(x) (((x) << 16) & GENMASK(18, 16))
+#define HSIO_S6G_IB_CFG2_IB_OINFS_M GENMASK(18, 16)
+#define HSIO_S6G_IB_CFG2_IB_OINFS_X(x) (((x) & GENMASK(18, 16)) >> 16)
+#define HSIO_S6G_IB_CFG2_IB_OCALS(x) (((x) << 10) & GENMASK(15, 10))
+#define HSIO_S6G_IB_CFG2_IB_OCALS_M GENMASK(15, 10)
+#define HSIO_S6G_IB_CFG2_IB_OCALS_X(x) (((x) & GENMASK(15, 10)) >> 10)
+#define HSIO_S6G_IB_CFG2_IB_TCALV(x) (((x) << 5) & GENMASK(9, 5))
+#define HSIO_S6G_IB_CFG2_IB_TCALV_M GENMASK(9, 5)
+#define HSIO_S6G_IB_CFG2_IB_TCALV_X(x) (((x) & GENMASK(9, 5)) >> 5)
+#define HSIO_S6G_IB_CFG2_IB_UMAX(x) (((x) << 3) & GENMASK(4, 3))
+#define HSIO_S6G_IB_CFG2_IB_UMAX_M GENMASK(4, 3)
+#define HSIO_S6G_IB_CFG2_IB_UMAX_X(x) (((x) & GENMASK(4, 3)) >> 3)
+#define HSIO_S6G_IB_CFG2_IB_UREG(x) ((x) & GENMASK(2, 0))
+#define HSIO_S6G_IB_CFG2_IB_UREG_M GENMASK(2, 0)
+
+#define HSIO_S6G_IB_CFG3_IB_INI_HP(x) (((x) << 18) & GENMASK(23, 18))
+#define HSIO_S6G_IB_CFG3_IB_INI_HP_M GENMASK(23, 18)
+#define HSIO_S6G_IB_CFG3_IB_INI_HP_X(x) (((x) & GENMASK(23, 18)) >> 18)
+#define HSIO_S6G_IB_CFG3_IB_INI_MID(x) (((x) << 12) & GENMASK(17, 12))
+#define HSIO_S6G_IB_CFG3_IB_INI_MID_M GENMASK(17, 12)
+#define HSIO_S6G_IB_CFG3_IB_INI_MID_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define HSIO_S6G_IB_CFG3_IB_INI_LP(x) (((x) << 6) & GENMASK(11, 6))
+#define HSIO_S6G_IB_CFG3_IB_INI_LP_M GENMASK(11, 6)
+#define HSIO_S6G_IB_CFG3_IB_INI_LP_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define HSIO_S6G_IB_CFG3_IB_INI_OFFSET(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_IB_CFG3_IB_INI_OFFSET_M GENMASK(5, 0)
+
+#define HSIO_S6G_IB_CFG4_IB_MAX_HP(x) (((x) << 18) & GENMASK(23, 18))
+#define HSIO_S6G_IB_CFG4_IB_MAX_HP_M GENMASK(23, 18)
+#define HSIO_S6G_IB_CFG4_IB_MAX_HP_X(x) (((x) & GENMASK(23, 18)) >> 18)
+#define HSIO_S6G_IB_CFG4_IB_MAX_MID(x) (((x) << 12) & GENMASK(17, 12))
+#define HSIO_S6G_IB_CFG4_IB_MAX_MID_M GENMASK(17, 12)
+#define HSIO_S6G_IB_CFG4_IB_MAX_MID_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define HSIO_S6G_IB_CFG4_IB_MAX_LP(x) (((x) << 6) & GENMASK(11, 6))
+#define HSIO_S6G_IB_CFG4_IB_MAX_LP_M GENMASK(11, 6)
+#define HSIO_S6G_IB_CFG4_IB_MAX_LP_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define HSIO_S6G_IB_CFG4_IB_MAX_OFFSET(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_IB_CFG4_IB_MAX_OFFSET_M GENMASK(5, 0)
+
+#define HSIO_S6G_IB_CFG5_IB_MIN_HP(x) (((x) << 18) & GENMASK(23, 18))
+#define HSIO_S6G_IB_CFG5_IB_MIN_HP_M GENMASK(23, 18)
+#define HSIO_S6G_IB_CFG5_IB_MIN_HP_X(x) (((x) & GENMASK(23, 18)) >> 18)
+#define HSIO_S6G_IB_CFG5_IB_MIN_MID(x) (((x) << 12) & GENMASK(17, 12))
+#define HSIO_S6G_IB_CFG5_IB_MIN_MID_M GENMASK(17, 12)
+#define HSIO_S6G_IB_CFG5_IB_MIN_MID_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define HSIO_S6G_IB_CFG5_IB_MIN_LP(x) (((x) << 6) & GENMASK(11, 6))
+#define HSIO_S6G_IB_CFG5_IB_MIN_LP_M GENMASK(11, 6)
+#define HSIO_S6G_IB_CFG5_IB_MIN_LP_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define HSIO_S6G_IB_CFG5_IB_MIN_OFFSET(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_IB_CFG5_IB_MIN_OFFSET_M GENMASK(5, 0)
+
+#define HSIO_S6G_OB_CFG_OB_IDLE BIT(31)
+#define HSIO_S6G_OB_CFG_OB_ENA1V_MODE BIT(30)
+#define HSIO_S6G_OB_CFG_OB_POL BIT(29)
+#define HSIO_S6G_OB_CFG_OB_POST0(x) (((x) << 23) & GENMASK(28, 23))
+#define HSIO_S6G_OB_CFG_OB_POST0_M GENMASK(28, 23)
+#define HSIO_S6G_OB_CFG_OB_POST0_X(x) (((x) & GENMASK(28, 23)) >> 23)
+#define HSIO_S6G_OB_CFG_OB_PREC(x) (((x) << 18) & GENMASK(22, 18))
+#define HSIO_S6G_OB_CFG_OB_PREC_M GENMASK(22, 18)
+#define HSIO_S6G_OB_CFG_OB_PREC_X(x) (((x) & GENMASK(22, 18)) >> 18)
+#define HSIO_S6G_OB_CFG_OB_R_ADJ_MUX BIT(17)
+#define HSIO_S6G_OB_CFG_OB_R_ADJ_PDR BIT(16)
+#define HSIO_S6G_OB_CFG_OB_POST1(x) (((x) << 11) & GENMASK(15, 11))
+#define HSIO_S6G_OB_CFG_OB_POST1_M GENMASK(15, 11)
+#define HSIO_S6G_OB_CFG_OB_POST1_X(x) (((x) & GENMASK(15, 11)) >> 11)
+#define HSIO_S6G_OB_CFG_OB_R_COR BIT(10)
+#define HSIO_S6G_OB_CFG_OB_SEL_RCTRL BIT(9)
+#define HSIO_S6G_OB_CFG_OB_SR_H BIT(8)
+#define HSIO_S6G_OB_CFG_OB_SR(x) (((x) << 4) & GENMASK(7, 4))
+#define HSIO_S6G_OB_CFG_OB_SR_M GENMASK(7, 4)
+#define HSIO_S6G_OB_CFG_OB_SR_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define HSIO_S6G_OB_CFG_OB_RESISTOR_CTRL(x) ((x) & GENMASK(3, 0))
+#define HSIO_S6G_OB_CFG_OB_RESISTOR_CTRL_M GENMASK(3, 0)
+
+#define HSIO_S6G_OB_CFG1_OB_ENA_CAS(x) (((x) << 6) & GENMASK(8, 6))
+#define HSIO_S6G_OB_CFG1_OB_ENA_CAS_M GENMASK(8, 6)
+#define HSIO_S6G_OB_CFG1_OB_ENA_CAS_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define HSIO_S6G_OB_CFG1_OB_LEV(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_OB_CFG1_OB_LEV_M GENMASK(5, 0)
+
+#define HSIO_S6G_SER_CFG_SER_4TAP_ENA BIT(8)
+#define HSIO_S6G_SER_CFG_SER_CPMD_SEL BIT(7)
+#define HSIO_S6G_SER_CFG_SER_SWAP_CPMD BIT(6)
+#define HSIO_S6G_SER_CFG_SER_ALISEL(x) (((x) << 4) & GENMASK(5, 4))
+#define HSIO_S6G_SER_CFG_SER_ALISEL_M GENMASK(5, 4)
+#define HSIO_S6G_SER_CFG_SER_ALISEL_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define HSIO_S6G_SER_CFG_SER_ENHYS BIT(3)
+#define HSIO_S6G_SER_CFG_SER_BIG_WIN BIT(2)
+#define HSIO_S6G_SER_CFG_SER_EN_WIN BIT(1)
+#define HSIO_S6G_SER_CFG_SER_ENALI BIT(0)
+
+#define HSIO_S6G_COMMON_CFG_SYS_RST BIT(17)
+#define HSIO_S6G_COMMON_CFG_SE_DIV2_ENA BIT(16)
+#define HSIO_S6G_COMMON_CFG_SE_AUTO_SQUELCH_ENA BIT(15)
+#define HSIO_S6G_COMMON_CFG_ENA_LANE BIT(14)
+#define HSIO_S6G_COMMON_CFG_PWD_RX BIT(13)
+#define HSIO_S6G_COMMON_CFG_PWD_TX BIT(12)
+#define HSIO_S6G_COMMON_CFG_LANE_CTRL(x) (((x) << 9) & GENMASK(11, 9))
+#define HSIO_S6G_COMMON_CFG_LANE_CTRL_M GENMASK(11, 9)
+#define HSIO_S6G_COMMON_CFG_LANE_CTRL_X(x) (((x) & GENMASK(11, 9)) >> 9)
+#define HSIO_S6G_COMMON_CFG_ENA_DIRECT BIT(8)
+#define HSIO_S6G_COMMON_CFG_ENA_ELOOP BIT(7)
+#define HSIO_S6G_COMMON_CFG_ENA_FLOOP BIT(6)
+#define HSIO_S6G_COMMON_CFG_ENA_ILOOP BIT(5)
+#define HSIO_S6G_COMMON_CFG_ENA_PLOOP BIT(4)
+#define HSIO_S6G_COMMON_CFG_HRATE BIT(3)
+#define HSIO_S6G_COMMON_CFG_QRATE BIT(2)
+#define HSIO_S6G_COMMON_CFG_IF_MODE(x) ((x) & GENMASK(1, 0))
+#define HSIO_S6G_COMMON_CFG_IF_MODE_M GENMASK(1, 0)
+
+#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS(x) (((x) << 16) & GENMASK(17, 16))
+#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS_M GENMASK(17, 16)
+#define HSIO_S6G_PLL_CFG_PLL_ENA_OFFS_X(x) (((x) & GENMASK(17, 16)) >> 16)
+#define HSIO_S6G_PLL_CFG_PLL_DIV4 BIT(15)
+#define HSIO_S6G_PLL_CFG_PLL_ENA_ROT BIT(14)
+#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA(x) (((x) << 6) & GENMASK(13, 6))
+#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA_M GENMASK(13, 6)
+#define HSIO_S6G_PLL_CFG_PLL_FSM_CTRL_DATA_X(x) (((x) & GENMASK(13, 6)) >> 6)
+#define HSIO_S6G_PLL_CFG_PLL_FSM_ENA BIT(5)
+#define HSIO_S6G_PLL_CFG_PLL_FSM_FORCE_SET_ENA BIT(4)
+#define HSIO_S6G_PLL_CFG_PLL_FSM_OOR_RECAL_ENA BIT(3)
+#define HSIO_S6G_PLL_CFG_PLL_RB_DATA_SEL BIT(2)
+#define HSIO_S6G_PLL_CFG_PLL_ROT_DIR BIT(1)
+#define HSIO_S6G_PLL_CFG_PLL_ROT_FRQ BIT(0)
+
+#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_DATA_N BIT(5)
+#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_DATA_P BIT(4)
+#define HSIO_S6G_ACJTAG_CFG_ACJTAG_INIT_CLK BIT(3)
+#define HSIO_S6G_ACJTAG_CFG_OB_DIRECT BIT(2)
+#define HSIO_S6G_ACJTAG_CFG_ACJTAG_ENA BIT(1)
+#define HSIO_S6G_ACJTAG_CFG_JTAG_CTRL_ENA BIT(0)
+
+#define HSIO_S6G_GP_CFG_GP_MSB(x) (((x) << 16) & GENMASK(31, 16))
+#define HSIO_S6G_GP_CFG_GP_MSB_M GENMASK(31, 16)
+#define HSIO_S6G_GP_CFG_GP_MSB_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define HSIO_S6G_GP_CFG_GP_LSB(x) ((x) & GENMASK(15, 0))
+#define HSIO_S6G_GP_CFG_GP_LSB_M GENMASK(15, 0)
+
+#define HSIO_S6G_IB_STATUS0_IB_CAL_DONE BIT(8)
+#define HSIO_S6G_IB_STATUS0_IB_HP_GAIN_ACT BIT(7)
+#define HSIO_S6G_IB_STATUS0_IB_MID_GAIN_ACT BIT(6)
+#define HSIO_S6G_IB_STATUS0_IB_LP_GAIN_ACT BIT(5)
+#define HSIO_S6G_IB_STATUS0_IB_OFFSET_ACT BIT(4)
+#define HSIO_S6G_IB_STATUS0_IB_OFFSET_VLD BIT(3)
+#define HSIO_S6G_IB_STATUS0_IB_OFFSET_ERR BIT(2)
+#define HSIO_S6G_IB_STATUS0_IB_OFFSDIR BIT(1)
+#define HSIO_S6G_IB_STATUS0_IB_SIG_DET BIT(0)
+
+#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT(x) (((x) << 18) & GENMASK(23, 18))
+#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT_M GENMASK(23, 18)
+#define HSIO_S6G_IB_STATUS1_IB_HP_GAIN_STAT_X(x) (((x) & GENMASK(23, 18)) >> 18)
+#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT(x) (((x) << 12) & GENMASK(17, 12))
+#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT_M GENMASK(17, 12)
+#define HSIO_S6G_IB_STATUS1_IB_MID_GAIN_STAT_X(x) (((x) & GENMASK(17, 12)) >> 12)
+#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT(x) (((x) << 6) & GENMASK(11, 6))
+#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT_M GENMASK(11, 6)
+#define HSIO_S6G_IB_STATUS1_IB_LP_GAIN_STAT_X(x) (((x) & GENMASK(11, 6)) >> 6)
+#define HSIO_S6G_IB_STATUS1_IB_OFFSET_STAT(x) ((x) & GENMASK(5, 0))
+#define HSIO_S6G_IB_STATUS1_IB_OFFSET_STAT_M GENMASK(5, 0)
+
+#define HSIO_S6G_ACJTAG_STATUS_ACJTAG_CAPT_DATA_N BIT(2)
+#define HSIO_S6G_ACJTAG_STATUS_ACJTAG_CAPT_DATA_P BIT(1)
+#define HSIO_S6G_ACJTAG_STATUS_IB_DIRECT BIT(0)
+
+#define HSIO_S6G_PLL_STATUS_PLL_CAL_NOT_DONE BIT(10)
+#define HSIO_S6G_PLL_STATUS_PLL_CAL_ERR BIT(9)
+#define HSIO_S6G_PLL_STATUS_PLL_OUT_OF_RANGE_ERR BIT(8)
+#define HSIO_S6G_PLL_STATUS_PLL_RB_DATA(x) ((x) & GENMASK(7, 0))
+#define HSIO_S6G_PLL_STATUS_PLL_RB_DATA_M GENMASK(7, 0)
+
+#define HSIO_S6G_REVID_SERDES_REV(x) (((x) << 26) & GENMASK(31, 26))
+#define HSIO_S6G_REVID_SERDES_REV_M GENMASK(31, 26)
+#define HSIO_S6G_REVID_SERDES_REV_X(x) (((x) & GENMASK(31, 26)) >> 26)
+#define HSIO_S6G_REVID_RCPLL_REV(x) (((x) << 21) & GENMASK(25, 21))
+#define HSIO_S6G_REVID_RCPLL_REV_M GENMASK(25, 21)
+#define HSIO_S6G_REVID_RCPLL_REV_X(x) (((x) & GENMASK(25, 21)) >> 21)
+#define HSIO_S6G_REVID_SER_REV(x) (((x) << 16) & GENMASK(20, 16))
+#define HSIO_S6G_REVID_SER_REV_M GENMASK(20, 16)
+#define HSIO_S6G_REVID_SER_REV_X(x) (((x) & GENMASK(20, 16)) >> 16)
+#define HSIO_S6G_REVID_DES_REV(x) (((x) << 10) & GENMASK(15, 10))
+#define HSIO_S6G_REVID_DES_REV_M GENMASK(15, 10)
+#define HSIO_S6G_REVID_DES_REV_X(x) (((x) & GENMASK(15, 10)) >> 10)
+#define HSIO_S6G_REVID_OB_REV(x) (((x) << 5) & GENMASK(9, 5))
+#define HSIO_S6G_REVID_OB_REV_M GENMASK(9, 5)
+#define HSIO_S6G_REVID_OB_REV_X(x) (((x) & GENMASK(9, 5)) >> 5)
+#define HSIO_S6G_REVID_IB_REV(x) ((x) & GENMASK(4, 0))
+#define HSIO_S6G_REVID_IB_REV_M GENMASK(4, 0)
+
+#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_WR_ONE_SHOT BIT(31)
+#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_RD_ONE_SHOT BIT(30)
+#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_ADDR(x) ((x) & GENMASK(24, 0))
+#define HSIO_MCB_S6G_ADDR_CFG_SERDES6G_ADDR_M GENMASK(24, 0)
+
+#define HSIO_HW_CFG_DEV2G5_10_MODE BIT(6)
+#define HSIO_HW_CFG_DEV1G_9_MODE BIT(5)
+#define HSIO_HW_CFG_DEV1G_6_MODE BIT(4)
+#define HSIO_HW_CFG_DEV1G_5_MODE BIT(3)
+#define HSIO_HW_CFG_DEV1G_4_MODE BIT(2)
+#define HSIO_HW_CFG_PCIE_ENA BIT(1)
+#define HSIO_HW_CFG_QSGMII_ENA BIT(0)
+
+#define HSIO_HW_QSGMII_CFG_SHYST_DIS BIT(3)
+#define HSIO_HW_QSGMII_CFG_E_DET_ENA BIT(2)
+#define HSIO_HW_QSGMII_CFG_USE_I1_ENA BIT(1)
+#define HSIO_HW_QSGMII_CFG_FLIP_LANES BIT(0)
+
+#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS(x) (((x) << 1) & GENMASK(6, 1))
+#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS_M GENMASK(6, 1)
+#define HSIO_HW_QSGMII_STAT_DELAY_VAR_X200PS_X(x) (((x) & GENMASK(6, 1)) >> 1)
+#define HSIO_HW_QSGMII_STAT_SYNC BIT(0)
+
+#define HSIO_CLK_CFG_CLKDIV_PHY(x) (((x) << 1) & GENMASK(8, 1))
+#define HSIO_CLK_CFG_CLKDIV_PHY_M GENMASK(8, 1)
+#define HSIO_CLK_CFG_CLKDIV_PHY_X(x) (((x) & GENMASK(8, 1)) >> 1)
+#define HSIO_CLK_CFG_CLKDIV_PHY_DIS BIT(0)
+
+#define HSIO_TEMP_SENSOR_CTRL_FORCE_TEMP_RD BIT(5)
+#define HSIO_TEMP_SENSOR_CTRL_FORCE_RUN BIT(4)
+#define HSIO_TEMP_SENSOR_CTRL_FORCE_NO_RST BIT(3)
+#define HSIO_TEMP_SENSOR_CTRL_FORCE_POWER_UP BIT(2)
+#define HSIO_TEMP_SENSOR_CTRL_FORCE_CLK BIT(1)
+#define HSIO_TEMP_SENSOR_CTRL_SAMPLE_ENA BIT(0)
+
+#define HSIO_TEMP_SENSOR_CFG_RUN_WID(x) (((x) << 8) & GENMASK(15, 8))
+#define HSIO_TEMP_SENSOR_CFG_RUN_WID_M GENMASK(15, 8)
+#define HSIO_TEMP_SENSOR_CFG_RUN_WID_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define HSIO_TEMP_SENSOR_CFG_SAMPLE_PER(x) ((x) & GENMASK(7, 0))
+#define HSIO_TEMP_SENSOR_CFG_SAMPLE_PER_M GENMASK(7, 0)
+
+#define HSIO_TEMP_SENSOR_STAT_TEMP_VALID BIT(8)
+#define HSIO_TEMP_SENSOR_STAT_TEMP(x) ((x) & GENMASK(7, 0))
+#define HSIO_TEMP_SENSOR_STAT_TEMP_M GENMASK(7, 0)
+
+#endif
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#include "ocelot.h"
+
+u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset)
+{
+ u16 target = reg >> TARGET_OFFSET;
+ u32 val;
+
+ WARN_ON(!target);
+
+ regmap_read(ocelot->targets[target],
+ ocelot->map[target][reg & REG_MASK] + offset, &val);
+ return val;
+}
+EXPORT_SYMBOL(__ocelot_read_ix);
+
+void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset)
+{
+ u16 target = reg >> TARGET_OFFSET;
+
+ WARN_ON(!target);
+
+ regmap_write(ocelot->targets[target],
+ ocelot->map[target][reg & REG_MASK] + offset, val);
+}
+EXPORT_SYMBOL(__ocelot_write_ix);
+
+void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
+ u32 offset)
+{
+ u16 target = reg >> TARGET_OFFSET;
+
+ WARN_ON(!target);
+
+ regmap_update_bits(ocelot->targets[target],
+ ocelot->map[target][reg & REG_MASK] + offset,
+ mask, val);
+}
+EXPORT_SYMBOL(__ocelot_rmw_ix);
+
+u32 ocelot_port_readl(struct ocelot_port *port, u32 reg)
+{
+ return readl(port->regs + reg);
+}
+EXPORT_SYMBOL(ocelot_port_readl);
+
+void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg)
+{
+ writel(val, port->regs + reg);
+}
+EXPORT_SYMBOL(ocelot_port_writel);
+
+int ocelot_regfields_init(struct ocelot *ocelot,
+ const struct reg_field *const regfields)
+{
+ unsigned int i;
+ u16 target;
+
+ for (i = 0; i < REGFIELD_MAX; i++) {
+ struct reg_field regfield = {};
+ u32 reg = regfields[i].reg;
+
+ if (!reg)
+ continue;
+
+ target = regfields[i].reg >> TARGET_OFFSET;
+
+ regfield.reg = ocelot->map[target][reg & REG_MASK];
+ regfield.lsb = regfields[i].lsb;
+ regfield.msb = regfields[i].msb;
+
+ ocelot->regfields[i] =
+ devm_regmap_field_alloc(ocelot->dev,
+ ocelot->targets[target],
+ regfield);
+
+ if (IS_ERR(ocelot->regfields[i]))
+ return PTR_ERR(ocelot->regfields[i]);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(ocelot_regfields_init);
+
+static struct regmap_config ocelot_regmap_config = {
+ .reg_bits = 32,
+ .val_bits = 32,
+ .reg_stride = 4,
+};
+
+struct regmap *ocelot_io_platform_init(struct ocelot *ocelot,
+ struct platform_device *pdev,
+ const char *name)
+{
+ struct resource *res;
+ void __iomem *regs;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+ regs = devm_ioremap_resource(ocelot->dev, res);
+ if (IS_ERR(regs))
+ return ERR_CAST(regs);
+
+ ocelot_regmap_config.name = name;
+ return devm_regmap_init_mmio(ocelot->dev, regs,
+ &ocelot_regmap_config);
+}
+EXPORT_SYMBOL(ocelot_io_platform_init);
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_QS_H_
+#define _MSCC_OCELOT_QS_H_
+
+/* TODO handle BE */
+#define XTR_EOF_0 0x00000080U
+#define XTR_EOF_1 0x01000080U
+#define XTR_EOF_2 0x02000080U
+#define XTR_EOF_3 0x03000080U
+#define XTR_PRUNED 0x04000080U
+#define XTR_ABORT 0x05000080U
+#define XTR_ESCAPE 0x06000080U
+#define XTR_NOT_READY 0x07000080U
+#define XTR_VALID_BYTES(x) (4 - (((x) >> 24) & 3))
+
+#define QS_XTR_GRP_CFG_RSZ 0x4
+
+#define QS_XTR_GRP_CFG_MODE(x) (((x) << 2) & GENMASK(3, 2))
+#define QS_XTR_GRP_CFG_MODE_M GENMASK(3, 2)
+#define QS_XTR_GRP_CFG_MODE_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define QS_XTR_GRP_CFG_STATUS_WORD_POS BIT(1)
+#define QS_XTR_GRP_CFG_BYTE_SWAP BIT(0)
+
+#define QS_XTR_RD_RSZ 0x4
+
+#define QS_XTR_FRM_PRUNING_RSZ 0x4
+
+#define QS_XTR_CFG_DP_WM(x) (((x) << 5) & GENMASK(7, 5))
+#define QS_XTR_CFG_DP_WM_M GENMASK(7, 5)
+#define QS_XTR_CFG_DP_WM_X(x) (((x) & GENMASK(7, 5)) >> 5)
+#define QS_XTR_CFG_SCH_WM(x) (((x) << 2) & GENMASK(4, 2))
+#define QS_XTR_CFG_SCH_WM_M GENMASK(4, 2)
+#define QS_XTR_CFG_SCH_WM_X(x) (((x) & GENMASK(4, 2)) >> 2)
+#define QS_XTR_CFG_OFLW_ERR_STICKY(x) ((x) & GENMASK(1, 0))
+#define QS_XTR_CFG_OFLW_ERR_STICKY_M GENMASK(1, 0)
+
+#define QS_INJ_GRP_CFG_RSZ 0x4
+
+#define QS_INJ_GRP_CFG_MODE(x) (((x) << 2) & GENMASK(3, 2))
+#define QS_INJ_GRP_CFG_MODE_M GENMASK(3, 2)
+#define QS_INJ_GRP_CFG_MODE_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define QS_INJ_GRP_CFG_BYTE_SWAP BIT(0)
+
+#define QS_INJ_WR_RSZ 0x4
+
+#define QS_INJ_CTRL_RSZ 0x4
+
+#define QS_INJ_CTRL_GAP_SIZE(x) (((x) << 21) & GENMASK(24, 21))
+#define QS_INJ_CTRL_GAP_SIZE_M GENMASK(24, 21)
+#define QS_INJ_CTRL_GAP_SIZE_X(x) (((x) & GENMASK(24, 21)) >> 21)
+#define QS_INJ_CTRL_ABORT BIT(20)
+#define QS_INJ_CTRL_EOF BIT(19)
+#define QS_INJ_CTRL_SOF BIT(18)
+#define QS_INJ_CTRL_VLD_BYTES(x) (((x) << 16) & GENMASK(17, 16))
+#define QS_INJ_CTRL_VLD_BYTES_M GENMASK(17, 16)
+#define QS_INJ_CTRL_VLD_BYTES_X(x) (((x) & GENMASK(17, 16)) >> 16)
+
+#define QS_INJ_STATUS_WMARK_REACHED(x) (((x) << 4) & GENMASK(5, 4))
+#define QS_INJ_STATUS_WMARK_REACHED_M GENMASK(5, 4)
+#define QS_INJ_STATUS_WMARK_REACHED_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define QS_INJ_STATUS_FIFO_RDY(x) (((x) << 2) & GENMASK(3, 2))
+#define QS_INJ_STATUS_FIFO_RDY_M GENMASK(3, 2)
+#define QS_INJ_STATUS_FIFO_RDY_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define QS_INJ_STATUS_INJ_IN_PROGRESS(x) ((x) & GENMASK(1, 0))
+#define QS_INJ_STATUS_INJ_IN_PROGRESS_M GENMASK(1, 0)
+
+#define QS_INJ_ERR_RSZ 0x4
+
+#define QS_INJ_ERR_ABORT_ERR_STICKY BIT(1)
+#define QS_INJ_ERR_WR_ERR_STICKY BIT(0)
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_QSYS_H_
+#define _MSCC_OCELOT_QSYS_H_
+
+#define QSYS_PORT_MODE_RSZ 0x4
+
+#define QSYS_PORT_MODE_DEQUEUE_DIS BIT(1)
+#define QSYS_PORT_MODE_DEQUEUE_LATE BIT(0)
+
+#define QSYS_SWITCH_PORT_MODE_RSZ 0x4
+
+#define QSYS_SWITCH_PORT_MODE_PORT_ENA BIT(14)
+#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(x) (((x) << 11) & GENMASK(13, 11))
+#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG_M GENMASK(13, 11)
+#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG_X(x) (((x) & GENMASK(13, 11)) >> 11)
+#define QSYS_SWITCH_PORT_MODE_YEL_RSRVD BIT(10)
+#define QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE BIT(9)
+#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA(x) (((x) << 1) & GENMASK(8, 1))
+#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA_M GENMASK(8, 1)
+#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA_X(x) (((x) & GENMASK(8, 1)) >> 1)
+#define QSYS_SWITCH_PORT_MODE_TX_PFC_MODE BIT(0)
+
+#define QSYS_STAT_CNT_CFG_TX_GREEN_CNT_MODE BIT(5)
+#define QSYS_STAT_CNT_CFG_TX_YELLOW_CNT_MODE BIT(4)
+#define QSYS_STAT_CNT_CFG_DROP_GREEN_CNT_MODE BIT(3)
+#define QSYS_STAT_CNT_CFG_DROP_YELLOW_CNT_MODE BIT(2)
+#define QSYS_STAT_CNT_CFG_DROP_COUNT_ONCE BIT(1)
+#define QSYS_STAT_CNT_CFG_DROP_COUNT_EGRESS BIT(0)
+
+#define QSYS_EEE_CFG_RSZ 0x4
+
+#define QSYS_EEE_THRES_EEE_HIGH_BYTES(x) (((x) << 8) & GENMASK(15, 8))
+#define QSYS_EEE_THRES_EEE_HIGH_BYTES_M GENMASK(15, 8)
+#define QSYS_EEE_THRES_EEE_HIGH_BYTES_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define QSYS_EEE_THRES_EEE_HIGH_FRAMES(x) ((x) & GENMASK(7, 0))
+#define QSYS_EEE_THRES_EEE_HIGH_FRAMES_M GENMASK(7, 0)
+
+#define QSYS_SW_STATUS_RSZ 0x4
+
+#define QSYS_EXT_CPU_CFG_EXT_CPU_PORT(x) (((x) << 8) & GENMASK(12, 8))
+#define QSYS_EXT_CPU_CFG_EXT_CPU_PORT_M GENMASK(12, 8)
+#define QSYS_EXT_CPU_CFG_EXT_CPU_PORT_X(x) (((x) & GENMASK(12, 8)) >> 8)
+#define QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK(x) ((x) & GENMASK(7, 0))
+#define QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M GENMASK(7, 0)
+
+#define QSYS_QMAP_GSZ 0x4
+
+#define QSYS_QMAP_SE_BASE(x) (((x) << 5) & GENMASK(12, 5))
+#define QSYS_QMAP_SE_BASE_M GENMASK(12, 5)
+#define QSYS_QMAP_SE_BASE_X(x) (((x) & GENMASK(12, 5)) >> 5)
+#define QSYS_QMAP_SE_IDX_SEL(x) (((x) << 2) & GENMASK(4, 2))
+#define QSYS_QMAP_SE_IDX_SEL_M GENMASK(4, 2)
+#define QSYS_QMAP_SE_IDX_SEL_X(x) (((x) & GENMASK(4, 2)) >> 2)
+#define QSYS_QMAP_SE_INP_SEL(x) ((x) & GENMASK(1, 0))
+#define QSYS_QMAP_SE_INP_SEL_M GENMASK(1, 0)
+
+#define QSYS_ISDX_SGRP_GSZ 0x4
+
+#define QSYS_TIMED_FRAME_ENTRY_GSZ 0x4
+
+#define QSYS_TFRM_MISC_TIMED_CANCEL_SLOT(x) (((x) << 9) & GENMASK(18, 9))
+#define QSYS_TFRM_MISC_TIMED_CANCEL_SLOT_M GENMASK(18, 9)
+#define QSYS_TFRM_MISC_TIMED_CANCEL_SLOT_X(x) (((x) & GENMASK(18, 9)) >> 9)
+#define QSYS_TFRM_MISC_TIMED_CANCEL_1SHOT BIT(8)
+#define QSYS_TFRM_MISC_TIMED_SLOT_MODE_MC BIT(7)
+#define QSYS_TFRM_MISC_TIMED_ENTRY_FAST_CNT(x) ((x) & GENMASK(6, 0))
+#define QSYS_TFRM_MISC_TIMED_ENTRY_FAST_CNT_M GENMASK(6, 0)
+
+#define QSYS_RED_PROFILE_RSZ 0x4
+
+#define QSYS_RED_PROFILE_WM_RED_LOW(x) (((x) << 8) & GENMASK(15, 8))
+#define QSYS_RED_PROFILE_WM_RED_LOW_M GENMASK(15, 8)
+#define QSYS_RED_PROFILE_WM_RED_LOW_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define QSYS_RED_PROFILE_WM_RED_HIGH(x) ((x) & GENMASK(7, 0))
+#define QSYS_RED_PROFILE_WM_RED_HIGH_M GENMASK(7, 0)
+
+#define QSYS_RES_CFG_GSZ 0x8
+
+#define QSYS_RES_STAT_GSZ 0x8
+
+#define QSYS_RES_STAT_INUSE(x) (((x) << 12) & GENMASK(23, 12))
+#define QSYS_RES_STAT_INUSE_M GENMASK(23, 12)
+#define QSYS_RES_STAT_INUSE_X(x) (((x) & GENMASK(23, 12)) >> 12)
+#define QSYS_RES_STAT_MAXUSE(x) ((x) & GENMASK(11, 0))
+#define QSYS_RES_STAT_MAXUSE_M GENMASK(11, 0)
+
+#define QSYS_EVENTS_CORE_EV_FDC(x) (((x) << 2) & GENMASK(4, 2))
+#define QSYS_EVENTS_CORE_EV_FDC_M GENMASK(4, 2)
+#define QSYS_EVENTS_CORE_EV_FDC_X(x) (((x) & GENMASK(4, 2)) >> 2)
+#define QSYS_EVENTS_CORE_EV_FRD(x) ((x) & GENMASK(1, 0))
+#define QSYS_EVENTS_CORE_EV_FRD_M GENMASK(1, 0)
+
+#define QSYS_QMAXSDU_CFG_0_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_1_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_2_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_3_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_4_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_5_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_6_RSZ 0x4
+
+#define QSYS_QMAXSDU_CFG_7_RSZ 0x4
+
+#define QSYS_PREEMPTION_CFG_RSZ 0x4
+
+#define QSYS_PREEMPTION_CFG_P_QUEUES(x) ((x) & GENMASK(7, 0))
+#define QSYS_PREEMPTION_CFG_P_QUEUES_M GENMASK(7, 0)
+#define QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE(x) (((x) << 8) & GENMASK(9, 8))
+#define QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_M GENMASK(9, 8)
+#define QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_X(x) (((x) & GENMASK(9, 8)) >> 8)
+#define QSYS_PREEMPTION_CFG_STRICT_IPG(x) (((x) << 12) & GENMASK(13, 12))
+#define QSYS_PREEMPTION_CFG_STRICT_IPG_M GENMASK(13, 12)
+#define QSYS_PREEMPTION_CFG_STRICT_IPG_X(x) (((x) & GENMASK(13, 12)) >> 12)
+#define QSYS_PREEMPTION_CFG_HOLD_ADVANCE(x) (((x) << 16) & GENMASK(31, 16))
+#define QSYS_PREEMPTION_CFG_HOLD_ADVANCE_M GENMASK(31, 16)
+#define QSYS_PREEMPTION_CFG_HOLD_ADVANCE_X(x) (((x) & GENMASK(31, 16)) >> 16)
+
+#define QSYS_CIR_CFG_GSZ 0x80
+
+#define QSYS_CIR_CFG_CIR_RATE(x) (((x) << 6) & GENMASK(20, 6))
+#define QSYS_CIR_CFG_CIR_RATE_M GENMASK(20, 6)
+#define QSYS_CIR_CFG_CIR_RATE_X(x) (((x) & GENMASK(20, 6)) >> 6)
+#define QSYS_CIR_CFG_CIR_BURST(x) ((x) & GENMASK(5, 0))
+#define QSYS_CIR_CFG_CIR_BURST_M GENMASK(5, 0)
+
+#define QSYS_EIR_CFG_GSZ 0x80
+
+#define QSYS_EIR_CFG_EIR_RATE(x) (((x) << 7) & GENMASK(21, 7))
+#define QSYS_EIR_CFG_EIR_RATE_M GENMASK(21, 7)
+#define QSYS_EIR_CFG_EIR_RATE_X(x) (((x) & GENMASK(21, 7)) >> 7)
+#define QSYS_EIR_CFG_EIR_BURST(x) (((x) << 1) & GENMASK(6, 1))
+#define QSYS_EIR_CFG_EIR_BURST_M GENMASK(6, 1)
+#define QSYS_EIR_CFG_EIR_BURST_X(x) (((x) & GENMASK(6, 1)) >> 1)
+#define QSYS_EIR_CFG_EIR_MARK_ENA BIT(0)
+
+#define QSYS_SE_CFG_GSZ 0x80
+
+#define QSYS_SE_CFG_SE_DWRR_CNT(x) (((x) << 6) & GENMASK(9, 6))
+#define QSYS_SE_CFG_SE_DWRR_CNT_M GENMASK(9, 6)
+#define QSYS_SE_CFG_SE_DWRR_CNT_X(x) (((x) & GENMASK(9, 6)) >> 6)
+#define QSYS_SE_CFG_SE_RR_ENA BIT(5)
+#define QSYS_SE_CFG_SE_AVB_ENA BIT(4)
+#define QSYS_SE_CFG_SE_FRM_MODE(x) (((x) << 2) & GENMASK(3, 2))
+#define QSYS_SE_CFG_SE_FRM_MODE_M GENMASK(3, 2)
+#define QSYS_SE_CFG_SE_FRM_MODE_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define QSYS_SE_CFG_SE_EXC_ENA BIT(1)
+#define QSYS_SE_CFG_SE_EXC_FWD BIT(0)
+
+#define QSYS_SE_DWRR_CFG_GSZ 0x80
+#define QSYS_SE_DWRR_CFG_RSZ 0x4
+
+#define QSYS_SE_CONNECT_GSZ 0x80
+
+#define QSYS_SE_CONNECT_SE_OUTP_IDX(x) (((x) << 17) & GENMASK(24, 17))
+#define QSYS_SE_CONNECT_SE_OUTP_IDX_M GENMASK(24, 17)
+#define QSYS_SE_CONNECT_SE_OUTP_IDX_X(x) (((x) & GENMASK(24, 17)) >> 17)
+#define QSYS_SE_CONNECT_SE_INP_IDX(x) (((x) << 9) & GENMASK(16, 9))
+#define QSYS_SE_CONNECT_SE_INP_IDX_M GENMASK(16, 9)
+#define QSYS_SE_CONNECT_SE_INP_IDX_X(x) (((x) & GENMASK(16, 9)) >> 9)
+#define QSYS_SE_CONNECT_SE_OUTP_CON(x) (((x) << 5) & GENMASK(8, 5))
+#define QSYS_SE_CONNECT_SE_OUTP_CON_M GENMASK(8, 5)
+#define QSYS_SE_CONNECT_SE_OUTP_CON_X(x) (((x) & GENMASK(8, 5)) >> 5)
+#define QSYS_SE_CONNECT_SE_INP_CNT(x) (((x) << 1) & GENMASK(4, 1))
+#define QSYS_SE_CONNECT_SE_INP_CNT_M GENMASK(4, 1)
+#define QSYS_SE_CONNECT_SE_INP_CNT_X(x) (((x) & GENMASK(4, 1)) >> 1)
+#define QSYS_SE_CONNECT_SE_TERMINAL BIT(0)
+
+#define QSYS_SE_DLB_SENSE_GSZ 0x80
+
+#define QSYS_SE_DLB_SENSE_SE_DLB_PRIO(x) (((x) << 11) & GENMASK(13, 11))
+#define QSYS_SE_DLB_SENSE_SE_DLB_PRIO_M GENMASK(13, 11)
+#define QSYS_SE_DLB_SENSE_SE_DLB_PRIO_X(x) (((x) & GENMASK(13, 11)) >> 11)
+#define QSYS_SE_DLB_SENSE_SE_DLB_SPORT(x) (((x) << 7) & GENMASK(10, 7))
+#define QSYS_SE_DLB_SENSE_SE_DLB_SPORT_M GENMASK(10, 7)
+#define QSYS_SE_DLB_SENSE_SE_DLB_SPORT_X(x) (((x) & GENMASK(10, 7)) >> 7)
+#define QSYS_SE_DLB_SENSE_SE_DLB_DPORT(x) (((x) << 3) & GENMASK(6, 3))
+#define QSYS_SE_DLB_SENSE_SE_DLB_DPORT_M GENMASK(6, 3)
+#define QSYS_SE_DLB_SENSE_SE_DLB_DPORT_X(x) (((x) & GENMASK(6, 3)) >> 3)
+#define QSYS_SE_DLB_SENSE_SE_DLB_PRIO_ENA BIT(2)
+#define QSYS_SE_DLB_SENSE_SE_DLB_SPORT_ENA BIT(1)
+#define QSYS_SE_DLB_SENSE_SE_DLB_DPORT_ENA BIT(0)
+
+#define QSYS_CIR_STATE_GSZ 0x80
+
+#define QSYS_CIR_STATE_CIR_LVL(x) (((x) << 4) & GENMASK(25, 4))
+#define QSYS_CIR_STATE_CIR_LVL_M GENMASK(25, 4)
+#define QSYS_CIR_STATE_CIR_LVL_X(x) (((x) & GENMASK(25, 4)) >> 4)
+#define QSYS_CIR_STATE_SHP_TIME(x) ((x) & GENMASK(3, 0))
+#define QSYS_CIR_STATE_SHP_TIME_M GENMASK(3, 0)
+
+#define QSYS_EIR_STATE_GSZ 0x80
+
+#define QSYS_SE_STATE_GSZ 0x80
+
+#define QSYS_SE_STATE_SE_OUTP_LVL(x) (((x) << 1) & GENMASK(2, 1))
+#define QSYS_SE_STATE_SE_OUTP_LVL_M GENMASK(2, 1)
+#define QSYS_SE_STATE_SE_OUTP_LVL_X(x) (((x) & GENMASK(2, 1)) >> 1)
+#define QSYS_SE_STATE_SE_WAS_YEL BIT(0)
+
+#define QSYS_HSCH_MISC_CFG_SE_CONNECT_VLD BIT(8)
+#define QSYS_HSCH_MISC_CFG_FRM_ADJ(x) (((x) << 3) & GENMASK(7, 3))
+#define QSYS_HSCH_MISC_CFG_FRM_ADJ_M GENMASK(7, 3)
+#define QSYS_HSCH_MISC_CFG_FRM_ADJ_X(x) (((x) & GENMASK(7, 3)) >> 3)
+#define QSYS_HSCH_MISC_CFG_LEAK_DIS BIT(2)
+#define QSYS_HSCH_MISC_CFG_QSHP_EXC_ENA BIT(1)
+#define QSYS_HSCH_MISC_CFG_PFC_BYP_UPD BIT(0)
+
+#define QSYS_TAG_CONFIG_RSZ 0x4
+
+#define QSYS_TAG_CONFIG_ENABLE BIT(0)
+#define QSYS_TAG_CONFIG_LINK_SPEED(x) (((x) << 4) & GENMASK(5, 4))
+#define QSYS_TAG_CONFIG_LINK_SPEED_M GENMASK(5, 4)
+#define QSYS_TAG_CONFIG_LINK_SPEED_X(x) (((x) & GENMASK(5, 4)) >> 4)
+#define QSYS_TAG_CONFIG_INIT_GATE_STATE(x) (((x) << 8) & GENMASK(15, 8))
+#define QSYS_TAG_CONFIG_INIT_GATE_STATE_M GENMASK(15, 8)
+#define QSYS_TAG_CONFIG_INIT_GATE_STATE_X(x) (((x) & GENMASK(15, 8)) >> 8)
+#define QSYS_TAG_CONFIG_SCH_TRAFFIC_QUEUES(x) (((x) << 16) & GENMASK(23, 16))
+#define QSYS_TAG_CONFIG_SCH_TRAFFIC_QUEUES_M GENMASK(23, 16)
+#define QSYS_TAG_CONFIG_SCH_TRAFFIC_QUEUES_X(x) (((x) & GENMASK(23, 16)) >> 16)
+
+#define QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM(x) ((x) & GENMASK(7, 0))
+#define QSYS_TAS_PARAM_CFG_CTRL_PORT_NUM_M GENMASK(7, 0)
+#define QSYS_TAS_PARAM_CFG_CTRL_ALWAYS_GUARD_BAND_SCH_Q BIT(8)
+#define QSYS_TAS_PARAM_CFG_CTRL_CONFIG_CHANGE BIT(16)
+
+#define QSYS_PORT_MAX_SDU_RSZ 0x4
+
+#define QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB(x) ((x) & GENMASK(15, 0))
+#define QSYS_PARAM_CFG_REG_3_BASE_TIME_SEC_MSB_M GENMASK(15, 0)
+#define QSYS_PARAM_CFG_REG_3_LIST_LENGTH(x) (((x) << 16) & GENMASK(31, 16))
+#define QSYS_PARAM_CFG_REG_3_LIST_LENGTH_M GENMASK(31, 16)
+#define QSYS_PARAM_CFG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(31, 16)) >> 16)
+
+#define QSYS_GCL_CFG_REG_1_GCL_ENTRY_NUM(x) ((x) & GENMASK(5, 0))
+#define QSYS_GCL_CFG_REG_1_GCL_ENTRY_NUM_M GENMASK(5, 0)
+#define QSYS_GCL_CFG_REG_1_GATE_STATE(x) (((x) << 8) & GENMASK(15, 8))
+#define QSYS_GCL_CFG_REG_1_GATE_STATE_M GENMASK(15, 8)
+#define QSYS_GCL_CFG_REG_1_GATE_STATE_X(x) (((x) & GENMASK(15, 8)) >> 8)
+
+#define QSYS_PARAM_STATUS_REG_3_BASE_TIME_SEC_MSB(x) ((x) & GENMASK(15, 0))
+#define QSYS_PARAM_STATUS_REG_3_BASE_TIME_SEC_MSB_M GENMASK(15, 0)
+#define QSYS_PARAM_STATUS_REG_3_LIST_LENGTH(x) (((x) << 16) & GENMASK(31, 16))
+#define QSYS_PARAM_STATUS_REG_3_LIST_LENGTH_M GENMASK(31, 16)
+#define QSYS_PARAM_STATUS_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(31, 16)) >> 16)
+
+#define QSYS_PARAM_STATUS_REG_8_CFG_CHG_TIME_SEC_MSB(x) ((x) & GENMASK(15, 0))
+#define QSYS_PARAM_STATUS_REG_8_CFG_CHG_TIME_SEC_MSB_M GENMASK(15, 0)
+#define QSYS_PARAM_STATUS_REG_8_OPER_GATE_STATE(x) (((x) << 16) & GENMASK(23, 16))
+#define QSYS_PARAM_STATUS_REG_8_OPER_GATE_STATE_M GENMASK(23, 16)
+#define QSYS_PARAM_STATUS_REG_8_OPER_GATE_STATE_X(x) (((x) & GENMASK(23, 16)) >> 16)
+#define QSYS_PARAM_STATUS_REG_8_CONFIG_PENDING BIT(24)
+
+#define QSYS_GCL_STATUS_REG_1_GCL_ENTRY_NUM(x) ((x) & GENMASK(5, 0))
+#define QSYS_GCL_STATUS_REG_1_GCL_ENTRY_NUM_M GENMASK(5, 0)
+#define QSYS_GCL_STATUS_REG_1_GATE_STATE(x) (((x) << 8) & GENMASK(15, 8))
+#define QSYS_GCL_STATUS_REG_1_GATE_STATE_M GENMASK(15, 8)
+#define QSYS_GCL_STATUS_REG_1_GATE_STATE_X(x) (((x) & GENMASK(15, 8)) >> 8)
+
+#endif
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+#include "ocelot.h"
+
+static const u32 ocelot_ana_regmap[] = {
+ REG(ANA_ADVLEARN, 0x009000),
+ REG(ANA_VLANMASK, 0x009004),
+ REG(ANA_PORT_B_DOMAIN, 0x009008),
+ REG(ANA_ANAGEFIL, 0x00900c),
+ REG(ANA_ANEVENTS, 0x009010),
+ REG(ANA_STORMLIMIT_BURST, 0x009014),
+ REG(ANA_STORMLIMIT_CFG, 0x009018),
+ REG(ANA_ISOLATED_PORTS, 0x009028),
+ REG(ANA_COMMUNITY_PORTS, 0x00902c),
+ REG(ANA_AUTOAGE, 0x009030),
+ REG(ANA_MACTOPTIONS, 0x009034),
+ REG(ANA_LEARNDISC, 0x009038),
+ REG(ANA_AGENCTRL, 0x00903c),
+ REG(ANA_MIRRORPORTS, 0x009040),
+ REG(ANA_EMIRRORPORTS, 0x009044),
+ REG(ANA_FLOODING, 0x009048),
+ REG(ANA_FLOODING_IPMC, 0x00904c),
+ REG(ANA_SFLOW_CFG, 0x009050),
+ REG(ANA_PORT_MODE, 0x009080),
+ REG(ANA_PGID_PGID, 0x008c00),
+ REG(ANA_TABLES_ANMOVED, 0x008b30),
+ REG(ANA_TABLES_MACHDATA, 0x008b34),
+ REG(ANA_TABLES_MACLDATA, 0x008b38),
+ REG(ANA_TABLES_MACACCESS, 0x008b3c),
+ REG(ANA_TABLES_MACTINDX, 0x008b40),
+ REG(ANA_TABLES_VLANACCESS, 0x008b44),
+ REG(ANA_TABLES_VLANTIDX, 0x008b48),
+ REG(ANA_TABLES_ISDXACCESS, 0x008b4c),
+ REG(ANA_TABLES_ISDXTIDX, 0x008b50),
+ REG(ANA_TABLES_ENTRYLIM, 0x008b00),
+ REG(ANA_TABLES_PTP_ID_HIGH, 0x008b54),
+ REG(ANA_TABLES_PTP_ID_LOW, 0x008b58),
+ REG(ANA_MSTI_STATE, 0x008e00),
+ REG(ANA_PORT_VLAN_CFG, 0x007000),
+ REG(ANA_PORT_DROP_CFG, 0x007004),
+ REG(ANA_PORT_QOS_CFG, 0x007008),
+ REG(ANA_PORT_VCAP_CFG, 0x00700c),
+ REG(ANA_PORT_VCAP_S1_KEY_CFG, 0x007010),
+ REG(ANA_PORT_VCAP_S2_CFG, 0x00701c),
+ REG(ANA_PORT_PCP_DEI_MAP, 0x007020),
+ REG(ANA_PORT_CPU_FWD_CFG, 0x007060),
+ REG(ANA_PORT_CPU_FWD_BPDU_CFG, 0x007064),
+ REG(ANA_PORT_CPU_FWD_GARP_CFG, 0x007068),
+ REG(ANA_PORT_CPU_FWD_CCM_CFG, 0x00706c),
+ REG(ANA_PORT_PORT_CFG, 0x007070),
+ REG(ANA_PORT_POL_CFG, 0x007074),
+ REG(ANA_PORT_PTP_CFG, 0x007078),
+ REG(ANA_PORT_PTP_DLY1_CFG, 0x00707c),
+ REG(ANA_OAM_UPM_LM_CNT, 0x007c00),
+ REG(ANA_PORT_PTP_DLY2_CFG, 0x007080),
+ REG(ANA_PFC_PFC_CFG, 0x008800),
+ REG(ANA_PFC_PFC_TIMER, 0x008804),
+ REG(ANA_IPT_OAM_MEP_CFG, 0x008000),
+ REG(ANA_IPT_IPT, 0x008004),
+ REG(ANA_PPT_PPT, 0x008ac0),
+ REG(ANA_FID_MAP_FID_MAP, 0x000000),
+ REG(ANA_AGGR_CFG, 0x0090b4),
+ REG(ANA_CPUQ_CFG, 0x0090b8),
+ REG(ANA_CPUQ_CFG2, 0x0090bc),
+ REG(ANA_CPUQ_8021_CFG, 0x0090c0),
+ REG(ANA_DSCP_CFG, 0x009100),
+ REG(ANA_DSCP_REWR_CFG, 0x009200),
+ REG(ANA_VCAP_RNG_TYPE_CFG, 0x009240),
+ REG(ANA_VCAP_RNG_VAL_CFG, 0x009260),
+ REG(ANA_VRAP_CFG, 0x009280),
+ REG(ANA_VRAP_HDR_DATA, 0x009284),
+ REG(ANA_VRAP_HDR_MASK, 0x009288),
+ REG(ANA_DISCARD_CFG, 0x00928c),
+ REG(ANA_FID_CFG, 0x009290),
+ REG(ANA_POL_PIR_CFG, 0x004000),
+ REG(ANA_POL_CIR_CFG, 0x004004),
+ REG(ANA_POL_MODE_CFG, 0x004008),
+ REG(ANA_POL_PIR_STATE, 0x00400c),
+ REG(ANA_POL_CIR_STATE, 0x004010),
+ REG(ANA_POL_STATE, 0x004014),
+ REG(ANA_POL_FLOWC, 0x008b80),
+ REG(ANA_POL_HYST, 0x008bec),
+ REG(ANA_POL_MISC_CFG, 0x008bf0),
+};
+
+static const u32 ocelot_qs_regmap[] = {
+ REG(QS_XTR_GRP_CFG, 0x000000),
+ REG(QS_XTR_RD, 0x000008),
+ REG(QS_XTR_FRM_PRUNING, 0x000010),
+ REG(QS_XTR_FLUSH, 0x000018),
+ REG(QS_XTR_DATA_PRESENT, 0x00001c),
+ REG(QS_XTR_CFG, 0x000020),
+ REG(QS_INJ_GRP_CFG, 0x000024),
+ REG(QS_INJ_WR, 0x00002c),
+ REG(QS_INJ_CTRL, 0x000034),
+ REG(QS_INJ_STATUS, 0x00003c),
+ REG(QS_INJ_ERR, 0x000040),
+ REG(QS_INH_DBG, 0x000048),
+};
+
+static const u32 ocelot_hsio_regmap[] = {
+ REG(HSIO_PLL5G_CFG0, 0x000000),
+ REG(HSIO_PLL5G_CFG1, 0x000004),
+ REG(HSIO_PLL5G_CFG2, 0x000008),
+ REG(HSIO_PLL5G_CFG3, 0x00000c),
+ REG(HSIO_PLL5G_CFG4, 0x000010),
+ REG(HSIO_PLL5G_CFG5, 0x000014),
+ REG(HSIO_PLL5G_CFG6, 0x000018),
+ REG(HSIO_PLL5G_STATUS0, 0x00001c),
+ REG(HSIO_PLL5G_STATUS1, 0x000020),
+ REG(HSIO_PLL5G_BIST_CFG0, 0x000024),
+ REG(HSIO_PLL5G_BIST_CFG1, 0x000028),
+ REG(HSIO_PLL5G_BIST_CFG2, 0x00002c),
+ REG(HSIO_PLL5G_BIST_STAT0, 0x000030),
+ REG(HSIO_PLL5G_BIST_STAT1, 0x000034),
+ REG(HSIO_RCOMP_CFG0, 0x000038),
+ REG(HSIO_RCOMP_STATUS, 0x00003c),
+ REG(HSIO_SYNC_ETH_CFG, 0x000040),
+ REG(HSIO_SYNC_ETH_PLL_CFG, 0x000048),
+ REG(HSIO_S1G_DES_CFG, 0x00004c),
+ REG(HSIO_S1G_IB_CFG, 0x000050),
+ REG(HSIO_S1G_OB_CFG, 0x000054),
+ REG(HSIO_S1G_SER_CFG, 0x000058),
+ REG(HSIO_S1G_COMMON_CFG, 0x00005c),
+ REG(HSIO_S1G_PLL_CFG, 0x000060),
+ REG(HSIO_S1G_PLL_STATUS, 0x000064),
+ REG(HSIO_S1G_DFT_CFG0, 0x000068),
+ REG(HSIO_S1G_DFT_CFG1, 0x00006c),
+ REG(HSIO_S1G_DFT_CFG2, 0x000070),
+ REG(HSIO_S1G_TP_CFG, 0x000074),
+ REG(HSIO_S1G_RC_PLL_BIST_CFG, 0x000078),
+ REG(HSIO_S1G_MISC_CFG, 0x00007c),
+ REG(HSIO_S1G_DFT_STATUS, 0x000080),
+ REG(HSIO_S1G_MISC_STATUS, 0x000084),
+ REG(HSIO_MCB_S1G_ADDR_CFG, 0x000088),
+ REG(HSIO_S6G_DIG_CFG, 0x00008c),
+ REG(HSIO_S6G_DFT_CFG0, 0x000090),
+ REG(HSIO_S6G_DFT_CFG1, 0x000094),
+ REG(HSIO_S6G_DFT_CFG2, 0x000098),
+ REG(HSIO_S6G_TP_CFG0, 0x00009c),
+ REG(HSIO_S6G_TP_CFG1, 0x0000a0),
+ REG(HSIO_S6G_RC_PLL_BIST_CFG, 0x0000a4),
+ REG(HSIO_S6G_MISC_CFG, 0x0000a8),
+ REG(HSIO_S6G_OB_ANEG_CFG, 0x0000ac),
+ REG(HSIO_S6G_DFT_STATUS, 0x0000b0),
+ REG(HSIO_S6G_ERR_CNT, 0x0000b4),
+ REG(HSIO_S6G_MISC_STATUS, 0x0000b8),
+ REG(HSIO_S6G_DES_CFG, 0x0000bc),
+ REG(HSIO_S6G_IB_CFG, 0x0000c0),
+ REG(HSIO_S6G_IB_CFG1, 0x0000c4),
+ REG(HSIO_S6G_IB_CFG2, 0x0000c8),
+ REG(HSIO_S6G_IB_CFG3, 0x0000cc),
+ REG(HSIO_S6G_IB_CFG4, 0x0000d0),
+ REG(HSIO_S6G_IB_CFG5, 0x0000d4),
+ REG(HSIO_S6G_OB_CFG, 0x0000d8),
+ REG(HSIO_S6G_OB_CFG1, 0x0000dc),
+ REG(HSIO_S6G_SER_CFG, 0x0000e0),
+ REG(HSIO_S6G_COMMON_CFG, 0x0000e4),
+ REG(HSIO_S6G_PLL_CFG, 0x0000e8),
+ REG(HSIO_S6G_ACJTAG_CFG, 0x0000ec),
+ REG(HSIO_S6G_GP_CFG, 0x0000f0),
+ REG(HSIO_S6G_IB_STATUS0, 0x0000f4),
+ REG(HSIO_S6G_IB_STATUS1, 0x0000f8),
+ REG(HSIO_S6G_ACJTAG_STATUS, 0x0000fc),
+ REG(HSIO_S6G_PLL_STATUS, 0x000100),
+ REG(HSIO_S6G_REVID, 0x000104),
+ REG(HSIO_MCB_S6G_ADDR_CFG, 0x000108),
+ REG(HSIO_HW_CFG, 0x00010c),
+ REG(HSIO_HW_QSGMII_CFG, 0x000110),
+ REG(HSIO_HW_QSGMII_STAT, 0x000114),
+ REG(HSIO_CLK_CFG, 0x000118),
+ REG(HSIO_TEMP_SENSOR_CTRL, 0x00011c),
+ REG(HSIO_TEMP_SENSOR_CFG, 0x000120),
+ REG(HSIO_TEMP_SENSOR_STAT, 0x000124),
+};
+
+static const u32 ocelot_qsys_regmap[] = {
+ REG(QSYS_PORT_MODE, 0x011200),
+ REG(QSYS_SWITCH_PORT_MODE, 0x011234),
+ REG(QSYS_STAT_CNT_CFG, 0x011264),
+ REG(QSYS_EEE_CFG, 0x011268),
+ REG(QSYS_EEE_THRES, 0x011294),
+ REG(QSYS_IGR_NO_SHARING, 0x011298),
+ REG(QSYS_EGR_NO_SHARING, 0x01129c),
+ REG(QSYS_SW_STATUS, 0x0112a0),
+ REG(QSYS_EXT_CPU_CFG, 0x0112d0),
+ REG(QSYS_PAD_CFG, 0x0112d4),
+ REG(QSYS_CPU_GROUP_MAP, 0x0112d8),
+ REG(QSYS_QMAP, 0x0112dc),
+ REG(QSYS_ISDX_SGRP, 0x011400),
+ REG(QSYS_TIMED_FRAME_ENTRY, 0x014000),
+ REG(QSYS_TFRM_MISC, 0x011310),
+ REG(QSYS_TFRM_PORT_DLY, 0x011314),
+ REG(QSYS_TFRM_TIMER_CFG_1, 0x011318),
+ REG(QSYS_TFRM_TIMER_CFG_2, 0x01131c),
+ REG(QSYS_TFRM_TIMER_CFG_3, 0x011320),
+ REG(QSYS_TFRM_TIMER_CFG_4, 0x011324),
+ REG(QSYS_TFRM_TIMER_CFG_5, 0x011328),
+ REG(QSYS_TFRM_TIMER_CFG_6, 0x01132c),
+ REG(QSYS_TFRM_TIMER_CFG_7, 0x011330),
+ REG(QSYS_TFRM_TIMER_CFG_8, 0x011334),
+ REG(QSYS_RED_PROFILE, 0x011338),
+ REG(QSYS_RES_QOS_MODE, 0x011378),
+ REG(QSYS_RES_CFG, 0x012000),
+ REG(QSYS_RES_STAT, 0x012004),
+ REG(QSYS_EGR_DROP_MODE, 0x01137c),
+ REG(QSYS_EQ_CTRL, 0x011380),
+ REG(QSYS_EVENTS_CORE, 0x011384),
+ REG(QSYS_CIR_CFG, 0x000000),
+ REG(QSYS_EIR_CFG, 0x000004),
+ REG(QSYS_SE_CFG, 0x000008),
+ REG(QSYS_SE_DWRR_CFG, 0x00000c),
+ REG(QSYS_SE_CONNECT, 0x00003c),
+ REG(QSYS_SE_DLB_SENSE, 0x000040),
+ REG(QSYS_CIR_STATE, 0x000044),
+ REG(QSYS_EIR_STATE, 0x000048),
+ REG(QSYS_SE_STATE, 0x00004c),
+ REG(QSYS_HSCH_MISC_CFG, 0x011388),
+};
+
+static const u32 ocelot_rew_regmap[] = {
+ REG(REW_PORT_VLAN_CFG, 0x000000),
+ REG(REW_TAG_CFG, 0x000004),
+ REG(REW_PORT_CFG, 0x000008),
+ REG(REW_DSCP_CFG, 0x00000c),
+ REG(REW_PCP_DEI_QOS_MAP_CFG, 0x000010),
+ REG(REW_PTP_CFG, 0x000050),
+ REG(REW_PTP_DLY1_CFG, 0x000054),
+ REG(REW_DSCP_REMAP_DP1_CFG, 0x000690),
+ REG(REW_DSCP_REMAP_CFG, 0x000790),
+ REG(REW_STAT_CFG, 0x000890),
+ REG(REW_PPT, 0x000680),
+};
+
+static const u32 ocelot_sys_regmap[] = {
+ REG(SYS_COUNT_RX_OCTETS, 0x000000),
+ REG(SYS_COUNT_RX_UNICAST, 0x000004),
+ REG(SYS_COUNT_RX_MULTICAST, 0x000008),
+ REG(SYS_COUNT_RX_BROADCAST, 0x00000c),
+ REG(SYS_COUNT_RX_SHORTS, 0x000010),
+ REG(SYS_COUNT_RX_FRAGMENTS, 0x000014),
+ REG(SYS_COUNT_RX_JABBERS, 0x000018),
+ REG(SYS_COUNT_RX_CRC_ALIGN_ERRS, 0x00001c),
+ REG(SYS_COUNT_RX_SYM_ERRS, 0x000020),
+ REG(SYS_COUNT_RX_64, 0x000024),
+ REG(SYS_COUNT_RX_65_127, 0x000028),
+ REG(SYS_COUNT_RX_128_255, 0x00002c),
+ REG(SYS_COUNT_RX_256_1023, 0x000030),
+ REG(SYS_COUNT_RX_1024_1526, 0x000034),
+ REG(SYS_COUNT_RX_1527_MAX, 0x000038),
+ REG(SYS_COUNT_RX_PAUSE, 0x00003c),
+ REG(SYS_COUNT_RX_CONTROL, 0x000040),
+ REG(SYS_COUNT_RX_LONGS, 0x000044),
+ REG(SYS_COUNT_RX_CLASSIFIED_DROPS, 0x000048),
+ REG(SYS_COUNT_TX_OCTETS, 0x000100),
+ REG(SYS_COUNT_TX_UNICAST, 0x000104),
+ REG(SYS_COUNT_TX_MULTICAST, 0x000108),
+ REG(SYS_COUNT_TX_BROADCAST, 0x00010c),
+ REG(SYS_COUNT_TX_COLLISION, 0x000110),
+ REG(SYS_COUNT_TX_DROPS, 0x000114),
+ REG(SYS_COUNT_TX_PAUSE, 0x000118),
+ REG(SYS_COUNT_TX_64, 0x00011c),
+ REG(SYS_COUNT_TX_65_127, 0x000120),
+ REG(SYS_COUNT_TX_128_511, 0x000124),
+ REG(SYS_COUNT_TX_512_1023, 0x000128),
+ REG(SYS_COUNT_TX_1024_1526, 0x00012c),
+ REG(SYS_COUNT_TX_1527_MAX, 0x000130),
+ REG(SYS_COUNT_TX_AGING, 0x000170),
+ REG(SYS_RESET_CFG, 0x000508),
+ REG(SYS_CMID, 0x00050c),
+ REG(SYS_VLAN_ETYPE_CFG, 0x000510),
+ REG(SYS_PORT_MODE, 0x000514),
+ REG(SYS_FRONT_PORT_MODE, 0x000548),
+ REG(SYS_FRM_AGING, 0x000574),
+ REG(SYS_STAT_CFG, 0x000578),
+ REG(SYS_SW_STATUS, 0x00057c),
+ REG(SYS_MISC_CFG, 0x0005ac),
+ REG(SYS_REW_MAC_HIGH_CFG, 0x0005b0),
+ REG(SYS_REW_MAC_LOW_CFG, 0x0005dc),
+ REG(SYS_CM_ADDR, 0x000500),
+ REG(SYS_CM_DATA, 0x000504),
+ REG(SYS_PAUSE_CFG, 0x000608),
+ REG(SYS_PAUSE_TOT_CFG, 0x000638),
+ REG(SYS_ATOP, 0x00063c),
+ REG(SYS_ATOP_TOT_CFG, 0x00066c),
+ REG(SYS_MAC_FC_CFG, 0x000670),
+ REG(SYS_MMGT, 0x00069c),
+ REG(SYS_MMGT_FAST, 0x0006a0),
+ REG(SYS_EVENTS_DIF, 0x0006a4),
+ REG(SYS_EVENTS_CORE, 0x0006b4),
+ REG(SYS_CNT, 0x000000),
+ REG(SYS_PTP_STATUS, 0x0006b8),
+ REG(SYS_PTP_TXSTAMP, 0x0006bc),
+ REG(SYS_PTP_NXT, 0x0006c0),
+ REG(SYS_PTP_CFG, 0x0006c4),
+};
+
+static const u32 *ocelot_regmap[] = {
+ [ANA] = ocelot_ana_regmap,
+ [QS] = ocelot_qs_regmap,
+ [HSIO] = ocelot_hsio_regmap,
+ [QSYS] = ocelot_qsys_regmap,
+ [REW] = ocelot_rew_regmap,
+ [SYS] = ocelot_sys_regmap,
+};
+
+static const struct reg_field ocelot_regfields[] = {
+ [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 11, 11),
+ [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 10),
+ [ANA_ANEVENTS_MSTI_DROP] = REG_FIELD(ANA_ANEVENTS, 27, 27),
+ [ANA_ANEVENTS_ACLKILL] = REG_FIELD(ANA_ANEVENTS, 26, 26),
+ [ANA_ANEVENTS_ACLUSED] = REG_FIELD(ANA_ANEVENTS, 25, 25),
+ [ANA_ANEVENTS_AUTOAGE] = REG_FIELD(ANA_ANEVENTS, 24, 24),
+ [ANA_ANEVENTS_VS2TTL1] = REG_FIELD(ANA_ANEVENTS, 23, 23),
+ [ANA_ANEVENTS_STORM_DROP] = REG_FIELD(ANA_ANEVENTS, 22, 22),
+ [ANA_ANEVENTS_LEARN_DROP] = REG_FIELD(ANA_ANEVENTS, 21, 21),
+ [ANA_ANEVENTS_AGED_ENTRY] = REG_FIELD(ANA_ANEVENTS, 20, 20),
+ [ANA_ANEVENTS_CPU_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 19, 19),
+ [ANA_ANEVENTS_AUTO_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 18, 18),
+ [ANA_ANEVENTS_LEARN_REMOVE] = REG_FIELD(ANA_ANEVENTS, 17, 17),
+ [ANA_ANEVENTS_AUTO_LEARNED] = REG_FIELD(ANA_ANEVENTS, 16, 16),
+ [ANA_ANEVENTS_AUTO_MOVED] = REG_FIELD(ANA_ANEVENTS, 15, 15),
+ [ANA_ANEVENTS_DROPPED] = REG_FIELD(ANA_ANEVENTS, 14, 14),
+ [ANA_ANEVENTS_CLASSIFIED_DROP] = REG_FIELD(ANA_ANEVENTS, 13, 13),
+ [ANA_ANEVENTS_CLASSIFIED_COPY] = REG_FIELD(ANA_ANEVENTS, 12, 12),
+ [ANA_ANEVENTS_VLAN_DISCARD] = REG_FIELD(ANA_ANEVENTS, 11, 11),
+ [ANA_ANEVENTS_FWD_DISCARD] = REG_FIELD(ANA_ANEVENTS, 10, 10),
+ [ANA_ANEVENTS_MULTICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 9, 9),
+ [ANA_ANEVENTS_UNICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 8, 8),
+ [ANA_ANEVENTS_DEST_KNOWN] = REG_FIELD(ANA_ANEVENTS, 7, 7),
+ [ANA_ANEVENTS_BUCKET3_MATCH] = REG_FIELD(ANA_ANEVENTS, 6, 6),
+ [ANA_ANEVENTS_BUCKET2_MATCH] = REG_FIELD(ANA_ANEVENTS, 5, 5),
+ [ANA_ANEVENTS_BUCKET1_MATCH] = REG_FIELD(ANA_ANEVENTS, 4, 4),
+ [ANA_ANEVENTS_BUCKET0_MATCH] = REG_FIELD(ANA_ANEVENTS, 3, 3),
+ [ANA_ANEVENTS_CPU_OPERATION] = REG_FIELD(ANA_ANEVENTS, 2, 2),
+ [ANA_ANEVENTS_DMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 1, 1),
+ [ANA_ANEVENTS_SMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 0, 0),
+ [ANA_TABLES_MACACCESS_B_DOM] = REG_FIELD(ANA_TABLES_MACACCESS, 18, 18),
+ [ANA_TABLES_MACTINDX_BUCKET] = REG_FIELD(ANA_TABLES_MACTINDX, 10, 11),
+ [ANA_TABLES_MACTINDX_M_INDEX] = REG_FIELD(ANA_TABLES_MACTINDX, 0, 9),
+ [QSYS_TIMED_FRAME_ENTRY_TFRM_VLD] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 20, 20),
+ [QSYS_TIMED_FRAME_ENTRY_TFRM_FP] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 8, 19),
+ [QSYS_TIMED_FRAME_ENTRY_TFRM_PORTNO] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 4, 7),
+ [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_SEL] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 1, 3),
+ [QSYS_TIMED_FRAME_ENTRY_TFRM_TM_T] = REG_FIELD(QSYS_TIMED_FRAME_ENTRY, 0, 0),
+ [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 2, 2),
+ [SYS_RESET_CFG_MEM_ENA] = REG_FIELD(SYS_RESET_CFG, 1, 1),
+ [SYS_RESET_CFG_MEM_INIT] = REG_FIELD(SYS_RESET_CFG, 0, 0),
+};
+
+static const struct ocelot_stat_layout ocelot_stats_layout[] = {
+ { .name = "rx_octets", .offset = 0x00, },
+ { .name = "rx_unicast", .offset = 0x01, },
+ { .name = "rx_multicast", .offset = 0x02, },
+ { .name = "rx_broadcast", .offset = 0x03, },
+ { .name = "rx_shorts", .offset = 0x04, },
+ { .name = "rx_fragments", .offset = 0x05, },
+ { .name = "rx_jabbers", .offset = 0x06, },
+ { .name = "rx_crc_align_errs", .offset = 0x07, },
+ { .name = "rx_sym_errs", .offset = 0x08, },
+ { .name = "rx_frames_below_65_octets", .offset = 0x09, },
+ { .name = "rx_frames_65_to_127_octets", .offset = 0x0A, },
+ { .name = "rx_frames_128_to_255_octets", .offset = 0x0B, },
+ { .name = "rx_frames_256_to_511_octets", .offset = 0x0C, },
+ { .name = "rx_frames_512_to_1023_octets", .offset = 0x0D, },
+ { .name = "rx_frames_1024_to_1526_octets", .offset = 0x0E, },
+ { .name = "rx_frames_over_1526_octets", .offset = 0x0F, },
+ { .name = "rx_pause", .offset = 0x10, },
+ { .name = "rx_control", .offset = 0x11, },
+ { .name = "rx_longs", .offset = 0x12, },
+ { .name = "rx_classified_drops", .offset = 0x13, },
+ { .name = "rx_red_prio_0", .offset = 0x14, },
+ { .name = "rx_red_prio_1", .offset = 0x15, },
+ { .name = "rx_red_prio_2", .offset = 0x16, },
+ { .name = "rx_red_prio_3", .offset = 0x17, },
+ { .name = "rx_red_prio_4", .offset = 0x18, },
+ { .name = "rx_red_prio_5", .offset = 0x19, },
+ { .name = "rx_red_prio_6", .offset = 0x1A, },
+ { .name = "rx_red_prio_7", .offset = 0x1B, },
+ { .name = "rx_yellow_prio_0", .offset = 0x1C, },
+ { .name = "rx_yellow_prio_1", .offset = 0x1D, },
+ { .name = "rx_yellow_prio_2", .offset = 0x1E, },
+ { .name = "rx_yellow_prio_3", .offset = 0x1F, },
+ { .name = "rx_yellow_prio_4", .offset = 0x20, },
+ { .name = "rx_yellow_prio_5", .offset = 0x21, },
+ { .name = "rx_yellow_prio_6", .offset = 0x22, },
+ { .name = "rx_yellow_prio_7", .offset = 0x23, },
+ { .name = "rx_green_prio_0", .offset = 0x24, },
+ { .name = "rx_green_prio_1", .offset = 0x25, },
+ { .name = "rx_green_prio_2", .offset = 0x26, },
+ { .name = "rx_green_prio_3", .offset = 0x27, },
+ { .name = "rx_green_prio_4", .offset = 0x28, },
+ { .name = "rx_green_prio_5", .offset = 0x29, },
+ { .name = "rx_green_prio_6", .offset = 0x2A, },
+ { .name = "rx_green_prio_7", .offset = 0x2B, },
+ { .name = "tx_octets", .offset = 0x40, },
+ { .name = "tx_unicast", .offset = 0x41, },
+ { .name = "tx_multicast", .offset = 0x42, },
+ { .name = "tx_broadcast", .offset = 0x43, },
+ { .name = "tx_collision", .offset = 0x44, },
+ { .name = "tx_drops", .offset = 0x45, },
+ { .name = "tx_pause", .offset = 0x46, },
+ { .name = "tx_frames_below_65_octets", .offset = 0x47, },
+ { .name = "tx_frames_65_to_127_octets", .offset = 0x48, },
+ { .name = "tx_frames_128_255_octets", .offset = 0x49, },
+ { .name = "tx_frames_256_511_octets", .offset = 0x4A, },
+ { .name = "tx_frames_512_1023_octets", .offset = 0x4B, },
+ { .name = "tx_frames_1024_1526_octets", .offset = 0x4C, },
+ { .name = "tx_frames_over_1526_octets", .offset = 0x4D, },
+ { .name = "tx_yellow_prio_0", .offset = 0x4E, },
+ { .name = "tx_yellow_prio_1", .offset = 0x4F, },
+ { .name = "tx_yellow_prio_2", .offset = 0x50, },
+ { .name = "tx_yellow_prio_3", .offset = 0x51, },
+ { .name = "tx_yellow_prio_4", .offset = 0x52, },
+ { .name = "tx_yellow_prio_5", .offset = 0x53, },
+ { .name = "tx_yellow_prio_6", .offset = 0x54, },
+ { .name = "tx_yellow_prio_7", .offset = 0x55, },
+ { .name = "tx_green_prio_0", .offset = 0x56, },
+ { .name = "tx_green_prio_1", .offset = 0x57, },
+ { .name = "tx_green_prio_2", .offset = 0x58, },
+ { .name = "tx_green_prio_3", .offset = 0x59, },
+ { .name = "tx_green_prio_4", .offset = 0x5A, },
+ { .name = "tx_green_prio_5", .offset = 0x5B, },
+ { .name = "tx_green_prio_6", .offset = 0x5C, },
+ { .name = "tx_green_prio_7", .offset = 0x5D, },
+ { .name = "tx_aged", .offset = 0x5E, },
+ { .name = "drop_local", .offset = 0x80, },
+ { .name = "drop_tail", .offset = 0x81, },
+ { .name = "drop_yellow_prio_0", .offset = 0x82, },
+ { .name = "drop_yellow_prio_1", .offset = 0x83, },
+ { .name = "drop_yellow_prio_2", .offset = 0x84, },
+ { .name = "drop_yellow_prio_3", .offset = 0x85, },
+ { .name = "drop_yellow_prio_4", .offset = 0x86, },
+ { .name = "drop_yellow_prio_5", .offset = 0x87, },
+ { .name = "drop_yellow_prio_6", .offset = 0x88, },
+ { .name = "drop_yellow_prio_7", .offset = 0x89, },
+ { .name = "drop_green_prio_0", .offset = 0x8A, },
+ { .name = "drop_green_prio_1", .offset = 0x8B, },
+ { .name = "drop_green_prio_2", .offset = 0x8C, },
+ { .name = "drop_green_prio_3", .offset = 0x8D, },
+ { .name = "drop_green_prio_4", .offset = 0x8E, },
+ { .name = "drop_green_prio_5", .offset = 0x8F, },
+ { .name = "drop_green_prio_6", .offset = 0x90, },
+ { .name = "drop_green_prio_7", .offset = 0x91, },
+};
+
+static void ocelot_pll5_init(struct ocelot *ocelot)
+{
+ /* Configure PLL5. This will need a proper CCF driver
+ * The values are coming from the VTSS API for Ocelot
+ */
+ ocelot_write(ocelot, HSIO_PLL5G_CFG4_IB_CTRL(0x7600) |
+ HSIO_PLL5G_CFG4_IB_BIAS_CTRL(0x8), HSIO_PLL5G_CFG4);
+ ocelot_write(ocelot, HSIO_PLL5G_CFG0_CORE_CLK_DIV(0x11) |
+ HSIO_PLL5G_CFG0_CPU_CLK_DIV(2) |
+ HSIO_PLL5G_CFG0_ENA_BIAS |
+ HSIO_PLL5G_CFG0_ENA_VCO_BUF |
+ HSIO_PLL5G_CFG0_ENA_CP1 |
+ HSIO_PLL5G_CFG0_SELCPI(2) |
+ HSIO_PLL5G_CFG0_LOOP_BW_RES(0xe) |
+ HSIO_PLL5G_CFG0_SELBGV820(4) |
+ HSIO_PLL5G_CFG0_DIV4 |
+ HSIO_PLL5G_CFG0_ENA_CLKTREE |
+ HSIO_PLL5G_CFG0_ENA_LANE, HSIO_PLL5G_CFG0);
+ ocelot_write(ocelot, HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET |
+ HSIO_PLL5G_CFG2_EN_RESET_OVERRUN |
+ HSIO_PLL5G_CFG2_GAIN_TEST(0x8) |
+ HSIO_PLL5G_CFG2_ENA_AMPCTRL |
+ HSIO_PLL5G_CFG2_PWD_AMPCTRL_N |
+ HSIO_PLL5G_CFG2_AMPC_SEL(0x10), HSIO_PLL5G_CFG2);
+}
+
+int ocelot_chip_init(struct ocelot *ocelot)
+{
+ int ret;
+
+ ocelot->map = ocelot_regmap;
+ ocelot->stats_layout = ocelot_stats_layout;
+ ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout);
+ ocelot->shared_queue_sz = 224 * 1024;
+
+ ret = ocelot_regfields_init(ocelot, ocelot_regfields);
+ if (ret)
+ return ret;
+
+ ocelot_pll5_init(ocelot);
+
+ eth_random_addr(ocelot->base_mac);
+ ocelot->base_mac[5] &= 0xf0;
+
+ return 0;
+}
+EXPORT_SYMBOL(ocelot_chip_init);
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_REW_H_
+#define _MSCC_OCELOT_REW_H_
+
+#define REW_PORT_VLAN_CFG_GSZ 0x80
+
+#define REW_PORT_VLAN_CFG_PORT_TPID(x) (((x) << 16) & GENMASK(31, 16))
+#define REW_PORT_VLAN_CFG_PORT_TPID_M GENMASK(31, 16)
+#define REW_PORT_VLAN_CFG_PORT_TPID_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define REW_PORT_VLAN_CFG_PORT_DEI BIT(15)
+#define REW_PORT_VLAN_CFG_PORT_PCP(x) (((x) << 12) & GENMASK(14, 12))
+#define REW_PORT_VLAN_CFG_PORT_PCP_M GENMASK(14, 12)
+#define REW_PORT_VLAN_CFG_PORT_PCP_X(x) (((x) & GENMASK(14, 12)) >> 12)
+#define REW_PORT_VLAN_CFG_PORT_VID(x) ((x) & GENMASK(11, 0))
+#define REW_PORT_VLAN_CFG_PORT_VID_M GENMASK(11, 0)
+
+#define REW_TAG_CFG_GSZ 0x80
+
+#define REW_TAG_CFG_TAG_CFG(x) (((x) << 7) & GENMASK(8, 7))
+#define REW_TAG_CFG_TAG_CFG_M GENMASK(8, 7)
+#define REW_TAG_CFG_TAG_CFG_X(x) (((x) & GENMASK(8, 7)) >> 7)
+#define REW_TAG_CFG_TAG_TPID_CFG(x) (((x) << 5) & GENMASK(6, 5))
+#define REW_TAG_CFG_TAG_TPID_CFG_M GENMASK(6, 5)
+#define REW_TAG_CFG_TAG_TPID_CFG_X(x) (((x) & GENMASK(6, 5)) >> 5)
+#define REW_TAG_CFG_TAG_VID_CFG BIT(4)
+#define REW_TAG_CFG_TAG_PCP_CFG(x) (((x) << 2) & GENMASK(3, 2))
+#define REW_TAG_CFG_TAG_PCP_CFG_M GENMASK(3, 2)
+#define REW_TAG_CFG_TAG_PCP_CFG_X(x) (((x) & GENMASK(3, 2)) >> 2)
+#define REW_TAG_CFG_TAG_DEI_CFG(x) ((x) & GENMASK(1, 0))
+#define REW_TAG_CFG_TAG_DEI_CFG_M GENMASK(1, 0)
+
+#define REW_PORT_CFG_GSZ 0x80
+
+#define REW_PORT_CFG_ES0_EN BIT(5)
+#define REW_PORT_CFG_FCS_UPDATE_NONCPU_CFG(x) (((x) << 3) & GENMASK(4, 3))
+#define REW_PORT_CFG_FCS_UPDATE_NONCPU_CFG_M GENMASK(4, 3)
+#define REW_PORT_CFG_FCS_UPDATE_NONCPU_CFG_X(x) (((x) & GENMASK(4, 3)) >> 3)
+#define REW_PORT_CFG_FCS_UPDATE_CPU_ENA BIT(2)
+#define REW_PORT_CFG_FLUSH_ENA BIT(1)
+#define REW_PORT_CFG_AGE_DIS BIT(0)
+
+#define REW_DSCP_CFG_GSZ 0x80
+
+#define REW_PCP_DEI_QOS_MAP_CFG_GSZ 0x80
+#define REW_PCP_DEI_QOS_MAP_CFG_RSZ 0x4
+
+#define REW_PCP_DEI_QOS_MAP_CFG_DEI_QOS_VAL BIT(3)
+#define REW_PCP_DEI_QOS_MAP_CFG_PCP_QOS_VAL(x) ((x) & GENMASK(2, 0))
+#define REW_PCP_DEI_QOS_MAP_CFG_PCP_QOS_VAL_M GENMASK(2, 0)
+
+#define REW_PTP_CFG_GSZ 0x80
+
+#define REW_PTP_CFG_PTP_BACKPLANE_MODE BIT(7)
+#define REW_PTP_CFG_GP_CFG_UNUSED(x) (((x) << 3) & GENMASK(6, 3))
+#define REW_PTP_CFG_GP_CFG_UNUSED_M GENMASK(6, 3)
+#define REW_PTP_CFG_GP_CFG_UNUSED_X(x) (((x) & GENMASK(6, 3)) >> 3)
+#define REW_PTP_CFG_PTP_1STEP_DIS BIT(2)
+#define REW_PTP_CFG_PTP_2STEP_DIS BIT(1)
+#define REW_PTP_CFG_PTP_UDP_KEEP BIT(0)
+
+#define REW_PTP_DLY1_CFG_GSZ 0x80
+
+#define REW_RED_TAG_CFG_GSZ 0x80
+
+#define REW_RED_TAG_CFG_RED_TAG_CFG BIT(0)
+
+#define REW_DSCP_REMAP_DP1_CFG_RSZ 0x4
+
+#define REW_DSCP_REMAP_CFG_RSZ 0x4
+
+#define REW_REW_STICKY_ES0_TAGB_PUSH_FAILED BIT(0)
+
+#define REW_PPT_RSZ 0x4
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_SYS_H_
+#define _MSCC_OCELOT_SYS_H_
+
+#define SYS_COUNT_RX_OCTETS_RSZ 0x4
+
+#define SYS_COUNT_TX_OCTETS_RSZ 0x4
+
+#define SYS_PORT_MODE_RSZ 0x4
+
+#define SYS_PORT_MODE_DATA_WO_TS(x) (((x) << 5) & GENMASK(6, 5))
+#define SYS_PORT_MODE_DATA_WO_TS_M GENMASK(6, 5)
+#define SYS_PORT_MODE_DATA_WO_TS_X(x) (((x) & GENMASK(6, 5)) >> 5)
+#define SYS_PORT_MODE_INCL_INJ_HDR(x) (((x) << 3) & GENMASK(4, 3))
+#define SYS_PORT_MODE_INCL_INJ_HDR_M GENMASK(4, 3)
+#define SYS_PORT_MODE_INCL_INJ_HDR_X(x) (((x) & GENMASK(4, 3)) >> 3)
+#define SYS_PORT_MODE_INCL_XTR_HDR(x) (((x) << 1) & GENMASK(2, 1))
+#define SYS_PORT_MODE_INCL_XTR_HDR_M GENMASK(2, 1)
+#define SYS_PORT_MODE_INCL_XTR_HDR_X(x) (((x) & GENMASK(2, 1)) >> 1)
+#define SYS_PORT_MODE_INJ_HDR_ERR BIT(0)
+
+#define SYS_FRONT_PORT_MODE_RSZ 0x4
+
+#define SYS_FRONT_PORT_MODE_HDX_MODE BIT(0)
+
+#define SYS_FRM_AGING_AGE_TX_ENA BIT(20)
+#define SYS_FRM_AGING_MAX_AGE(x) ((x) & GENMASK(19, 0))
+#define SYS_FRM_AGING_MAX_AGE_M GENMASK(19, 0)
+
+#define SYS_STAT_CFG_STAT_CLEAR_SHOT(x) (((x) << 10) & GENMASK(16, 10))
+#define SYS_STAT_CFG_STAT_CLEAR_SHOT_M GENMASK(16, 10)
+#define SYS_STAT_CFG_STAT_CLEAR_SHOT_X(x) (((x) & GENMASK(16, 10)) >> 10)
+#define SYS_STAT_CFG_STAT_VIEW(x) ((x) & GENMASK(9, 0))
+#define SYS_STAT_CFG_STAT_VIEW_M GENMASK(9, 0)
+
+#define SYS_SW_STATUS_RSZ 0x4
+
+#define SYS_SW_STATUS_PORT_RX_PAUSED BIT(0)
+
+#define SYS_MISC_CFG_PTP_RSRV_CLR BIT(1)
+#define SYS_MISC_CFG_PTP_DIS_NEG_RO BIT(0)
+
+#define SYS_REW_MAC_HIGH_CFG_RSZ 0x4
+
+#define SYS_REW_MAC_LOW_CFG_RSZ 0x4
+
+#define SYS_TIMESTAMP_OFFSET_ETH_TYPE_CFG(x) (((x) << 6) & GENMASK(21, 6))
+#define SYS_TIMESTAMP_OFFSET_ETH_TYPE_CFG_M GENMASK(21, 6)
+#define SYS_TIMESTAMP_OFFSET_ETH_TYPE_CFG_X(x) (((x) & GENMASK(21, 6)) >> 6)
+#define SYS_TIMESTAMP_OFFSET_TIMESTAMP_OFFSET(x) ((x) & GENMASK(5, 0))
+#define SYS_TIMESTAMP_OFFSET_TIMESTAMP_OFFSET_M GENMASK(5, 0)
+
+#define SYS_PAUSE_CFG_RSZ 0x4
+
+#define SYS_PAUSE_CFG_PAUSE_START(x) (((x) << 10) & GENMASK(18, 10))
+#define SYS_PAUSE_CFG_PAUSE_START_M GENMASK(18, 10)
+#define SYS_PAUSE_CFG_PAUSE_START_X(x) (((x) & GENMASK(18, 10)) >> 10)
+#define SYS_PAUSE_CFG_PAUSE_STOP(x) (((x) << 1) & GENMASK(9, 1))
+#define SYS_PAUSE_CFG_PAUSE_STOP_M GENMASK(9, 1)
+#define SYS_PAUSE_CFG_PAUSE_STOP_X(x) (((x) & GENMASK(9, 1)) >> 1)
+#define SYS_PAUSE_CFG_PAUSE_ENA BIT(0)
+
+#define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START(x) (((x) << 9) & GENMASK(17, 9))
+#define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START_M GENMASK(17, 9)
+#define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START_X(x) (((x) & GENMASK(17, 9)) >> 9)
+#define SYS_PAUSE_TOT_CFG_PAUSE_TOT_STOP(x) ((x) & GENMASK(8, 0))
+#define SYS_PAUSE_TOT_CFG_PAUSE_TOT_STOP_M GENMASK(8, 0)
+
+#define SYS_ATOP_RSZ 0x4
+
+#define SYS_MAC_FC_CFG_RSZ 0x4
+
+#define SYS_MAC_FC_CFG_FC_LINK_SPEED(x) (((x) << 26) & GENMASK(27, 26))
+#define SYS_MAC_FC_CFG_FC_LINK_SPEED_M GENMASK(27, 26)
+#define SYS_MAC_FC_CFG_FC_LINK_SPEED_X(x) (((x) & GENMASK(27, 26)) >> 26)
+#define SYS_MAC_FC_CFG_FC_LATENCY_CFG(x) (((x) << 20) & GENMASK(25, 20))
+#define SYS_MAC_FC_CFG_FC_LATENCY_CFG_M GENMASK(25, 20)
+#define SYS_MAC_FC_CFG_FC_LATENCY_CFG_X(x) (((x) & GENMASK(25, 20)) >> 20)
+#define SYS_MAC_FC_CFG_ZERO_PAUSE_ENA BIT(18)
+#define SYS_MAC_FC_CFG_TX_FC_ENA BIT(17)
+#define SYS_MAC_FC_CFG_RX_FC_ENA BIT(16)
+#define SYS_MAC_FC_CFG_PAUSE_VAL_CFG(x) ((x) & GENMASK(15, 0))
+#define SYS_MAC_FC_CFG_PAUSE_VAL_CFG_M GENMASK(15, 0)
+
+#define SYS_MMGT_RELCNT(x) (((x) << 16) & GENMASK(31, 16))
+#define SYS_MMGT_RELCNT_M GENMASK(31, 16)
+#define SYS_MMGT_RELCNT_X(x) (((x) & GENMASK(31, 16)) >> 16)
+#define SYS_MMGT_FREECNT(x) ((x) & GENMASK(15, 0))
+#define SYS_MMGT_FREECNT_M GENMASK(15, 0)
+
+#define SYS_MMGT_FAST_FREEVLD(x) (((x) << 4) & GENMASK(7, 4))
+#define SYS_MMGT_FAST_FREEVLD_M GENMASK(7, 4)
+#define SYS_MMGT_FAST_FREEVLD_X(x) (((x) & GENMASK(7, 4)) >> 4)
+#define SYS_MMGT_FAST_RELVLD(x) ((x) & GENMASK(3, 0))
+#define SYS_MMGT_FAST_RELVLD_M GENMASK(3, 0)
+
+#define SYS_EVENTS_DIF_RSZ 0x4
+
+#define SYS_EVENTS_DIF_EV_DRX(x) (((x) << 6) & GENMASK(8, 6))
+#define SYS_EVENTS_DIF_EV_DRX_M GENMASK(8, 6)
+#define SYS_EVENTS_DIF_EV_DRX_X(x) (((x) & GENMASK(8, 6)) >> 6)
+#define SYS_EVENTS_DIF_EV_DTX(x) ((x) & GENMASK(5, 0))
+#define SYS_EVENTS_DIF_EV_DTX_M GENMASK(5, 0)
+
+#define SYS_EVENTS_CORE_EV_FWR BIT(2)
+#define SYS_EVENTS_CORE_EV_ANA(x) ((x) & GENMASK(1, 0))
+#define SYS_EVENTS_CORE_EV_ANA_M GENMASK(1, 0)
+
+#define SYS_CNT_GSZ 0x4
+
+#define SYS_PTP_STATUS_PTP_TXSTAMP_OAM BIT(29)
+#define SYS_PTP_STATUS_PTP_OVFL BIT(28)
+#define SYS_PTP_STATUS_PTP_MESS_VLD BIT(27)
+#define SYS_PTP_STATUS_PTP_MESS_ID(x) (((x) << 21) & GENMASK(26, 21))
+#define SYS_PTP_STATUS_PTP_MESS_ID_M GENMASK(26, 21)
+#define SYS_PTP_STATUS_PTP_MESS_ID_X(x) (((x) & GENMASK(26, 21)) >> 21)
+#define SYS_PTP_STATUS_PTP_MESS_TXPORT(x) (((x) << 16) & GENMASK(20, 16))
+#define SYS_PTP_STATUS_PTP_MESS_TXPORT_M GENMASK(20, 16)
+#define SYS_PTP_STATUS_PTP_MESS_TXPORT_X(x) (((x) & GENMASK(20, 16)) >> 16)
+#define SYS_PTP_STATUS_PTP_MESS_SEQ_ID(x) ((x) & GENMASK(15, 0))
+#define SYS_PTP_STATUS_PTP_MESS_SEQ_ID_M GENMASK(15, 0)
+
+#define SYS_PTP_TXSTAMP_PTP_TXSTAMP(x) ((x) & GENMASK(29, 0))
+#define SYS_PTP_TXSTAMP_PTP_TXSTAMP_M GENMASK(29, 0)
+#define SYS_PTP_TXSTAMP_PTP_TXSTAMP_SEC BIT(31)
+
+#define SYS_PTP_NXT_PTP_NXT BIT(0)
+
+#define SYS_PTP_CFG_PTP_STAMP_WID(x) (((x) << 2) & GENMASK(7, 2))
+#define SYS_PTP_CFG_PTP_STAMP_WID_M GENMASK(7, 2)
+#define SYS_PTP_CFG_PTP_STAMP_WID_X(x) (((x) & GENMASK(7, 2)) >> 2)
+#define SYS_PTP_CFG_PTP_CF_ROLL_MODE(x) ((x) & GENMASK(1, 0))
+#define SYS_PTP_CFG_PTP_CF_ROLL_MODE_M GENMASK(1, 0)
+
+#define SYS_RAM_INIT_RAM_INIT BIT(1)
+#define SYS_RAM_INIT_RAM_CFG_HOOK BIT(0)
+
+#endif
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
return nfp_bpf_cmsg_alloc(bpf, size);
}
+static u8 nfp_bpf_cmsg_get_type(struct sk_buff *skb)
+{
+ struct cmsg_hdr *hdr;
+
+ hdr = (struct cmsg_hdr *)skb->data;
+
+ return hdr->type;
+}
+
static unsigned int nfp_bpf_cmsg_get_tag(struct sk_buff *skb)
{
struct cmsg_hdr *hdr;
goto err_free;
}
+ if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) {
+ nfp_bpf_event_output(bpf, skb);
+ return;
+ }
+
nfp_ctrl_lock(bpf->app->ctrl);
tag = nfp_bpf_cmsg_get_tag(skb);
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include <linux/bitops.h>
#include <linux/types.h>
+/* Kernel's enum bpf_reg_type is not uABI so people may change it breaking
+ * our FW ABI. In that case we will do translation in the driver.
+ */
+#define NFP_BPF_SCALAR_VALUE 1
+#define NFP_BPF_MAP_VALUE 4
+#define NFP_BPF_STACK 6
+#define NFP_BPF_PACKET_DATA 8
+
enum bpf_cap_tlv_type {
NFP_BPF_CAP_TYPE_FUNC = 1,
NFP_BPF_CAP_TYPE_ADJUST_HEAD = 2,
NFP_BPF_CAP_TYPE_MAPS = 3,
NFP_BPF_CAP_TYPE_RANDOM = 4,
+ NFP_BPF_CAP_TYPE_QUEUE_SELECT = 5,
};
struct nfp_bpf_cap_tlv_func {
CMSG_TYPE_MAP_DELETE = 5,
CMSG_TYPE_MAP_GETNEXT = 6,
CMSG_TYPE_MAP_GETFIRST = 7,
+ CMSG_TYPE_BPF_EVENT = 8,
__CMSG_TYPE_MAP_MAX,
};
__be32 resv;
struct cmsg_key_value_pair elem[0];
};
+
+struct cmsg_bpf_event {
+ struct cmsg_hdr hdr;
+ __be32 cpu_id;
+ __be64 map_ptr;
+ __be32 data_size;
+ __be32 pkt_size;
+ u8 data[0];
+};
#endif
/*
- * Copyright (C) 2016-2017 Netronome Systems, Inc.
+ * Copyright (C) 2016-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include "main.h"
#include "../nfp_asm.h"
+#include "../nfp_net_ctrl.h"
/* --- NFP prog --- */
/* Foreach "multiple" entries macros provide pos and next<n> pointers.
return 0;
}
-static int
-wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
- enum br_mask br_mask, bool swap)
+static const struct jmp_code_map {
+ enum br_mask br_mask;
+ bool swap;
+} jmp_code_map[] = {
+ [BPF_JGT >> 4] = { BR_BLO, true },
+ [BPF_JGE >> 4] = { BR_BHS, false },
+ [BPF_JLT >> 4] = { BR_BLO, false },
+ [BPF_JLE >> 4] = { BR_BHS, true },
+ [BPF_JSGT >> 4] = { BR_BLT, true },
+ [BPF_JSGE >> 4] = { BR_BGE, false },
+ [BPF_JSLT >> 4] = { BR_BLT, false },
+ [BPF_JSLE >> 4] = { BR_BGE, true },
+};
+
+static const struct jmp_code_map *nfp_jmp_code_get(struct nfp_insn_meta *meta)
+{
+ unsigned int op;
+
+ op = BPF_OP(meta->insn.code) >> 4;
+ /* br_mask of 0 is BR_BEQ which we don't use in jump code table */
+ if (WARN_ONCE(op >= ARRAY_SIZE(jmp_code_map) ||
+ !jmp_code_map[op].br_mask,
+ "no code found for jump instruction"))
+ return NULL;
+
+ return &jmp_code_map[op];
+}
+
+static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
u64 imm = insn->imm; /* sign extend */
+ const struct jmp_code_map *code;
+ enum alu_op alu_op, carry_op;
u8 reg = insn->dst_reg * 2;
swreg tmp_reg;
+ code = nfp_jmp_code_get(meta);
+ if (!code)
+ return -EINVAL;
+
+ alu_op = meta->jump_neg_op ? ALU_OP_ADD : ALU_OP_SUB;
+ carry_op = meta->jump_neg_op ? ALU_OP_ADD_C : ALU_OP_SUB_C;
+
tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
- if (!swap)
- emit_alu(nfp_prog, reg_none(), reg_a(reg), ALU_OP_SUB, tmp_reg);
+ if (!code->swap)
+ emit_alu(nfp_prog, reg_none(), reg_a(reg), alu_op, tmp_reg);
else
- emit_alu(nfp_prog, reg_none(), tmp_reg, ALU_OP_SUB, reg_a(reg));
+ emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg));
tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
- if (!swap)
+ if (!code->swap)
emit_alu(nfp_prog, reg_none(),
- reg_a(reg + 1), ALU_OP_SUB_C, tmp_reg);
+ reg_a(reg + 1), carry_op, tmp_reg);
else
emit_alu(nfp_prog, reg_none(),
- tmp_reg, ALU_OP_SUB_C, reg_a(reg + 1));
+ tmp_reg, carry_op, reg_a(reg + 1));
- emit_br(nfp_prog, br_mask, insn->off, 0);
+ emit_br(nfp_prog, code->br_mask, insn->off, 0);
return 0;
}
-static int
-wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
- enum br_mask br_mask, bool swap)
+static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
+ const struct jmp_code_map *code;
u8 areg, breg;
+ code = nfp_jmp_code_get(meta);
+ if (!code)
+ return -EINVAL;
+
areg = insn->dst_reg * 2;
breg = insn->src_reg * 2;
- if (swap) {
+ if (code->swap) {
areg ^= breg;
breg ^= areg;
areg ^= breg;
emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg));
emit_alu(nfp_prog, reg_none(),
reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
- emit_br(nfp_prog, br_mask, insn->off, 0);
+ emit_br(nfp_prog, code->br_mask, insn->off, 0);
return 0;
}
static int
map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
- struct bpf_offloaded_map *offmap;
- struct nfp_bpf_map *nfp_map;
bool load_lm_ptr;
u32 ret_tgt;
s64 lm_off;
- swreg tid;
-
- offmap = (struct bpf_offloaded_map *)meta->arg1.map_ptr;
- nfp_map = offmap->dev_priv;
/* We only have to reload LM0 if the key is not at start of stack */
lm_off = nfp_prog->stack_depth;
if (meta->func_id == BPF_FUNC_map_update_elem)
emit_csr_wr(nfp_prog, reg_b(3 * 2), NFP_CSR_ACT_LM_ADDR2);
- /* Load map ID into a register, it should actually fit as an immediate
- * but in case it doesn't deal with it here, not in the delay slots.
- */
- tid = ur_load_imm_any(nfp_prog, nfp_map->tid, imm_a(nfp_prog));
-
emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO + meta->func_id,
2, RELO_BR_HELPER);
ret_tgt = nfp_prog_current_offset(nfp_prog) + 2;
/* Load map ID into A0 */
- wrp_mov(nfp_prog, reg_a(0), tid);
+ wrp_mov(nfp_prog, reg_a(0), reg_a(2));
/* Load the return address into B0 */
wrp_immed_relo(nfp_prog, reg_b(0), ret_tgt, RELO_IMMED_REL);
if (!load_lm_ptr)
return 0;
- emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0);
+ emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0);
wrp_nops(nfp_prog, 3);
return 0;
return 0;
}
+static int
+nfp_perf_event_output(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ swreg ptr_type;
+ u32 ret_tgt;
+
+ ptr_type = ur_load_imm_any(nfp_prog, meta->arg1.type, imm_a(nfp_prog));
+
+ ret_tgt = nfp_prog_current_offset(nfp_prog) + 3;
+
+ emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO + meta->func_id,
+ 2, RELO_BR_HELPER);
+
+ /* Load ptr type into A1 */
+ wrp_mov(nfp_prog, reg_a(1), ptr_type);
+
+ /* Load the return address into B0 */
+ wrp_immed_relo(nfp_prog, reg_b(0), ret_tgt, RELO_IMMED_REL);
+
+ if (!nfp_prog_confirm_current_offset(nfp_prog, ret_tgt))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int
+nfp_queue_select(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ u32 jmp_tgt;
+
+ jmp_tgt = nfp_prog_current_offset(nfp_prog) + 5;
+
+ /* Make sure the queue id fits into FW field */
+ emit_alu(nfp_prog, reg_none(), reg_a(meta->insn.src_reg * 2),
+ ALU_OP_AND_NOT_B, reg_imm(0xff));
+ emit_br(nfp_prog, BR_BEQ, jmp_tgt, 2);
+
+ /* Set the 'queue selected' bit and the queue value */
+ emit_shf(nfp_prog, pv_qsel_set(nfp_prog),
+ pv_qsel_set(nfp_prog), SHF_OP_OR, reg_imm(1),
+ SHF_SC_L_SHF, PKT_VEL_QSEL_SET_BIT);
+ emit_ld_field(nfp_prog,
+ pv_qsel_val(nfp_prog), 0x1, reg_b(meta->insn.src_reg * 2),
+ SHF_SC_NONE, 0);
+ /* Delay slots end here, we will jump over next instruction if queue
+ * value fits into the field.
+ */
+ emit_ld_field(nfp_prog,
+ pv_qsel_val(nfp_prog), 0x1, reg_imm(NFP_NET_RXR_MAX),
+ SHF_SC_NONE, 0);
+
+ if (!nfp_prog_confirm_current_offset(nfp_prog, jmp_tgt))
+ return -EINVAL;
+
+ return 0;
+}
+
/* --- Callbacks --- */
static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
false, wrp_lmem_store);
}
+static int mem_stx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ switch (meta->insn.off) {
+ case offsetof(struct xdp_md, rx_queue_index):
+ return nfp_queue_select(nfp_prog, meta);
+ }
+
+ WARN_ON_ONCE(1); /* verifier should have rejected bad accesses */
+ return -EOPNOTSUPP;
+}
+
static int
mem_stx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
unsigned int size)
static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
+ if (meta->ptr.type == PTR_TO_CTX)
+ if (nfp_prog->type == BPF_PROG_TYPE_XDP)
+ return mem_stx_xdp(nfp_prog, meta);
return mem_stx(nfp_prog, meta, 4);
}
return 0;
}
-static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true);
-}
-
-static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false);
-}
-
-static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false);
-}
-
-static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true);
-}
-
-static int jsgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BLT, true);
-}
-
-static int jsge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BGE, false);
-}
-
-static int jslt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BLT, false);
-}
-
-static int jsle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_imm(nfp_prog, meta, BR_BGE, true);
-}
-
static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
const struct bpf_insn *insn = &meta->insn;
return 0;
}
-static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true);
-}
-
-static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false);
-}
-
-static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false);
-}
-
-static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true);
-}
-
-static int jsgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BLT, true);
-}
-
-static int jsge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BGE, false);
-}
-
-static int jslt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BLT, false);
-}
-
-static int jsle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-{
- return wrp_cmp_reg(nfp_prog, meta, BR_BGE, true);
-}
-
static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
return wrp_test_reg(nfp_prog, meta, ALU_OP_AND, BR_BNE);
return map_call_stack_common(nfp_prog, meta);
case BPF_FUNC_get_prandom_u32:
return nfp_get_prandom_u32(nfp_prog, meta);
+ case BPF_FUNC_perf_event_output:
+ return nfp_perf_event_output(nfp_prog, meta);
default:
WARN_ONCE(1, "verifier allowed unsupported function\n");
return -EOPNOTSUPP;
[BPF_ST | BPF_MEM | BPF_DW] = mem_st8,
[BPF_JMP | BPF_JA | BPF_K] = jump,
[BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm,
- [BPF_JMP | BPF_JGT | BPF_K] = jgt_imm,
- [BPF_JMP | BPF_JGE | BPF_K] = jge_imm,
- [BPF_JMP | BPF_JLT | BPF_K] = jlt_imm,
- [BPF_JMP | BPF_JLE | BPF_K] = jle_imm,
- [BPF_JMP | BPF_JSGT | BPF_K] = jsgt_imm,
- [BPF_JMP | BPF_JSGE | BPF_K] = jsge_imm,
- [BPF_JMP | BPF_JSLT | BPF_K] = jslt_imm,
- [BPF_JMP | BPF_JSLE | BPF_K] = jsle_imm,
+ [BPF_JMP | BPF_JGT | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JGE | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JLT | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JLE | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JSGT | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JSGE | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JSLT | BPF_K] = cmp_imm,
+ [BPF_JMP | BPF_JSLE | BPF_K] = cmp_imm,
[BPF_JMP | BPF_JSET | BPF_K] = jset_imm,
[BPF_JMP | BPF_JNE | BPF_K] = jne_imm,
[BPF_JMP | BPF_JEQ | BPF_X] = jeq_reg,
- [BPF_JMP | BPF_JGT | BPF_X] = jgt_reg,
- [BPF_JMP | BPF_JGE | BPF_X] = jge_reg,
- [BPF_JMP | BPF_JLT | BPF_X] = jlt_reg,
- [BPF_JMP | BPF_JLE | BPF_X] = jle_reg,
- [BPF_JMP | BPF_JSGT | BPF_X] = jsgt_reg,
- [BPF_JMP | BPF_JSGE | BPF_X] = jsge_reg,
- [BPF_JMP | BPF_JSLT | BPF_X] = jslt_reg,
- [BPF_JMP | BPF_JSLE | BPF_X] = jsle_reg,
+ [BPF_JMP | BPF_JGT | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JGE | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JLT | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JLE | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JSGT | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JSGE | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JSLT | BPF_X] = cmp_reg,
+ [BPF_JMP | BPF_JSLE | BPF_X] = cmp_reg,
[BPF_JMP | BPF_JSET | BPF_X] = jset_reg,
[BPF_JMP | BPF_JNE | BPF_X] = jne_reg,
[BPF_JMP | BPF_CALL] = call,
}
}
+/* abs(insn.imm) will fit better into unrestricted reg immediate -
+ * convert add/sub of a negative number into a sub/add of a positive one.
+ */
+static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
+{
+ struct nfp_insn_meta *meta;
+
+ list_for_each_entry(meta, &nfp_prog->insns, l) {
+ struct bpf_insn insn = meta->insn;
+
+ if (meta->skip)
+ continue;
+
+ if (BPF_CLASS(insn.code) != BPF_ALU &&
+ BPF_CLASS(insn.code) != BPF_ALU64 &&
+ BPF_CLASS(insn.code) != BPF_JMP)
+ continue;
+ if (BPF_SRC(insn.code) != BPF_K)
+ continue;
+ if (insn.imm >= 0)
+ continue;
+
+ if (BPF_CLASS(insn.code) == BPF_JMP) {
+ switch (BPF_OP(insn.code)) {
+ case BPF_JGE:
+ case BPF_JSGE:
+ case BPF_JLT:
+ case BPF_JSLT:
+ meta->jump_neg_op = true;
+ break;
+ default:
+ continue;
+ }
+ } else {
+ if (BPF_OP(insn.code) == BPF_ADD)
+ insn.code = BPF_CLASS(insn.code) | BPF_SUB;
+ else if (BPF_OP(insn.code) == BPF_SUB)
+ insn.code = BPF_CLASS(insn.code) | BPF_ADD;
+ else
+ continue;
+
+ meta->insn.code = insn.code | BPF_K;
+ }
+
+ meta->insn.imm = -insn.imm;
+ }
+}
+
/* Remove masking after load since our load guarantees this is not needed */
static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
{
{
nfp_bpf_opt_reg_init(nfp_prog);
+ nfp_bpf_opt_neg_add_sub(nfp_prog);
nfp_bpf_opt_ld_mask(nfp_prog);
nfp_bpf_opt_ld_shift(nfp_prog);
nfp_bpf_opt_ldst_gather(nfp_prog);
return 0;
}
+static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
+{
+ struct nfp_insn_meta *meta1, *meta2;
+ struct nfp_bpf_map *nfp_map;
+ struct bpf_map *map;
+
+ nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
+ if (meta1->skip || meta2->skip)
+ continue;
+
+ if (meta1->insn.code != (BPF_LD | BPF_IMM | BPF_DW) ||
+ meta1->insn.src_reg != BPF_PSEUDO_MAP_FD)
+ continue;
+
+ map = (void *)(unsigned long)((u32)meta1->insn.imm |
+ (u64)meta2->insn.imm << 32);
+ if (bpf_map_offload_neutral(map))
+ continue;
+ nfp_map = map_to_offmap(map)->dev_priv;
+
+ meta1->insn.imm = nfp_map->tid;
+ meta2->insn.imm = 0;
+ }
+
+ return 0;
+}
+
static int nfp_bpf_ustore_calc(u64 *prog, unsigned int len)
{
__le64 *ustore = (__force __le64 *)prog;
{
int ret;
+ ret = nfp_bpf_replace_map_ptrs(nfp_prog);
+ if (ret)
+ return ret;
+
ret = nfp_bpf_optimize(nfp_prog);
if (ret)
return ret;
case BPF_FUNC_map_delete_elem:
val = nfp_prog->bpf->helpers.map_delete;
break;
+ case BPF_FUNC_perf_event_output:
+ val = nfp_prog->bpf->helpers.perf_event_output;
+ break;
default:
pr_err("relocation of unknown helper %d\n",
val);
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include "fw.h"
#include "main.h"
+const struct rhashtable_params nfp_bpf_maps_neutral_params = {
+ .nelem_hint = 4,
+ .key_len = FIELD_SIZEOF(struct nfp_bpf_neutral_map, ptr),
+ .key_offset = offsetof(struct nfp_bpf_neutral_map, ptr),
+ .head_offset = offsetof(struct nfp_bpf_neutral_map, l),
+ .automatic_shrinking = true,
+};
+
static bool nfp_net_ebpf_capable(struct nfp_net *nn)
{
#ifdef __LITTLE_ENDIAN
case BPF_FUNC_map_delete_elem:
bpf->helpers.map_delete = readl(&cap->func_addr);
break;
+ case BPF_FUNC_perf_event_output:
+ bpf->helpers.perf_event_output = readl(&cap->func_addr);
+ break;
}
return 0;
return 0;
}
+static int
+nfp_bpf_parse_cap_qsel(struct nfp_app_bpf *bpf, void __iomem *value, u32 length)
+{
+ bpf->queue_select = true;
+ return 0;
+}
+
static int nfp_bpf_parse_capabilities(struct nfp_app *app)
{
struct nfp_cpp *cpp = app->pf->cpp;
return PTR_ERR(mem) == -ENOENT ? 0 : PTR_ERR(mem);
start = mem;
- while (mem - start + 8 < nfp_cpp_area_size(area)) {
+ while (mem - start + 8 <= nfp_cpp_area_size(area)) {
u8 __iomem *value;
u32 type, length;
if (nfp_bpf_parse_cap_random(app->priv, value, length))
goto err_release_free;
break;
+ case NFP_BPF_CAP_TYPE_QUEUE_SELECT:
+ if (nfp_bpf_parse_cap_qsel(app->priv, value, length))
+ goto err_release_free;
+ break;
default:
nfp_dbg(cpp, "unknown BPF capability: %d\n", type);
break;
init_waitqueue_head(&bpf->cmsg_wq);
INIT_LIST_HEAD(&bpf->map_list);
- err = nfp_bpf_parse_capabilities(app);
+ err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params);
if (err)
goto err_free_bpf;
+ err = nfp_bpf_parse_capabilities(app);
+ if (err)
+ goto err_free_neutral_maps;
+
return 0;
+err_free_neutral_maps:
+ rhashtable_destroy(&bpf->maps_neutral);
err_free_bpf:
kfree(bpf);
return err;
}
+static void nfp_check_rhashtable_empty(void *ptr, void *arg)
+{
+ WARN_ON_ONCE(1);
+}
+
static void nfp_bpf_clean(struct nfp_app *app)
{
struct nfp_app_bpf *bpf = app->priv;
WARN_ON(!skb_queue_empty(&bpf->cmsg_replies));
WARN_ON(!list_empty(&bpf->map_list));
WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use);
+ rhashtable_free_and_destroy(&bpf->maps_neutral,
+ nfp_check_rhashtable_empty, NULL);
kfree(bpf);
}
/*
- * Copyright (C) 2016-2017 Netronome Systems, Inc.
+ * Copyright (C) 2016-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include <linux/bpf_verifier.h>
#include <linux/kernel.h>
#include <linux/list.h>
+#include <linux/rhashtable.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/wait.h>
enum pkt_vec {
PKT_VEC_PKT_LEN = 0,
PKT_VEC_PKT_PTR = 2,
+ PKT_VEC_QSEL_SET = 4,
+ PKT_VEC_QSEL_VAL = 6,
};
+#define PKT_VEL_QSEL_SET_BIT 4
+
#define pv_len(np) reg_lm(1, PKT_VEC_PKT_LEN)
#define pv_ctm_ptr(np) reg_lm(1, PKT_VEC_PKT_PTR)
+#define pv_qsel_set(np) reg_lm(1, PKT_VEC_QSEL_SET)
+#define pv_qsel_val(np) reg_lm(1, PKT_VEC_QSEL_VAL)
#define stack_reg(np) reg_a(STATIC_REG_STACK)
#define stack_imm(np) imm_b(np)
* @maps_in_use: number of currently offloaded maps
* @map_elems_in_use: number of elements allocated to offloaded maps
*
+ * @maps_neutral: hash table of offload-neutral maps (on pointer)
+ *
* @adjust_head: adjust head capability
* @adjust_head.flags: extra flags for adjust head
* @adjust_head.off_min: minimal packet offset within buffer required
* @helpers.map_lookup: map lookup helper address
* @helpers.map_update: map update helper address
* @helpers.map_delete: map delete helper address
+ * @helpers.perf_event_output: output perf event to a ring buffer
*
* @pseudo_random: FW initialized the pseudo-random machinery (CSRs)
+ * @queue_select: BPF can set the RX queue ID in packet vector
*/
struct nfp_app_bpf {
struct nfp_app *app;
unsigned int maps_in_use;
unsigned int map_elems_in_use;
+ struct rhashtable maps_neutral;
+
struct nfp_bpf_cap_adjust_head {
u32 flags;
int off_min;
u32 map_lookup;
u32 map_update;
u32 map_delete;
+ u32 perf_event_output;
} helpers;
bool pseudo_random;
+ bool queue_select;
};
enum nfp_bpf_map_use {
enum nfp_bpf_map_use use_map[];
};
+struct nfp_bpf_neutral_map {
+ struct rhash_head l;
+ struct bpf_map *ptr;
+ u32 count;
+};
+
+extern const struct rhashtable_params nfp_bpf_maps_neutral_params;
+
struct nfp_prog;
struct nfp_insn_meta;
typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *);
* @xadd_over_16bit: 16bit immediate is not guaranteed
* @xadd_maybe_16bit: 16bit immediate is possible
* @jmp_dst: destination info for jump instructions
+ * @jump_neg_op: jump instruction has inverted immediate, use ADD instead of SUB
* @func_id: function id for call instructions
* @arg1: arg1 for call instructions
* @arg2: arg2 for call instructions
bool xadd_maybe_16bit;
};
/* jump */
- struct nfp_insn_meta *jmp_dst;
+ struct {
+ struct nfp_insn_meta *jmp_dst;
+ bool jump_neg_op;
+ };
/* function calls */
struct {
u32 func_id;
* @error: error code if something went wrong
* @stack_depth: max stack depth from the verifier
* @adjust_head_location: if program has single adjust head call - the insn no.
+ * @map_records_cnt: the number of map pointers recorded for this prog
+ * @map_records: the map record pointers from bpf->maps_neutral
* @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
*/
struct nfp_prog {
unsigned int stack_depth;
unsigned int adjust_head_location;
+ unsigned int map_records_cnt;
+ struct nfp_bpf_neutral_map **map_records;
+
struct list_head insns;
};
int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
void *key, void *next_key);
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb);
+
void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb);
#endif
/*
- * Copyright (C) 2016-2017 Netronome Systems, Inc.
+ * Copyright (C) 2016-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include "../nfp_net_ctrl.h"
#include "../nfp_net.h"
+static int
+nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
+ struct bpf_map *map)
+{
+ struct nfp_bpf_neutral_map *record;
+ int err;
+
+ /* Map record paths are entered via ndo, update side is protected. */
+ ASSERT_RTNL();
+
+ /* Reuse path - other offloaded program is already tracking this map. */
+ record = rhashtable_lookup_fast(&bpf->maps_neutral, &map,
+ nfp_bpf_maps_neutral_params);
+ if (record) {
+ nfp_prog->map_records[nfp_prog->map_records_cnt++] = record;
+ record->count++;
+ return 0;
+ }
+
+ /* Grab a single ref to the map for our record. The prog destroy ndo
+ * happens after free_used_maps().
+ */
+ map = bpf_map_inc(map, false);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ record = kmalloc(sizeof(*record), GFP_KERNEL);
+ if (!record) {
+ err = -ENOMEM;
+ goto err_map_put;
+ }
+
+ record->ptr = map;
+ record->count = 1;
+
+ err = rhashtable_insert_fast(&bpf->maps_neutral, &record->l,
+ nfp_bpf_maps_neutral_params);
+ if (err)
+ goto err_free_rec;
+
+ nfp_prog->map_records[nfp_prog->map_records_cnt++] = record;
+
+ return 0;
+
+err_free_rec:
+ kfree(record);
+err_map_put:
+ bpf_map_put(map);
+ return err;
+}
+
+static void
+nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog)
+{
+ bool freed = false;
+ int i;
+
+ ASSERT_RTNL();
+
+ for (i = 0; i < nfp_prog->map_records_cnt; i++) {
+ if (--nfp_prog->map_records[i]->count) {
+ nfp_prog->map_records[i] = NULL;
+ continue;
+ }
+
+ WARN_ON(rhashtable_remove_fast(&bpf->maps_neutral,
+ &nfp_prog->map_records[i]->l,
+ nfp_bpf_maps_neutral_params));
+ freed = true;
+ }
+
+ if (freed) {
+ synchronize_rcu();
+
+ for (i = 0; i < nfp_prog->map_records_cnt; i++)
+ if (nfp_prog->map_records[i]) {
+ bpf_map_put(nfp_prog->map_records[i]->ptr);
+ kfree(nfp_prog->map_records[i]);
+ }
+ }
+
+ kfree(nfp_prog->map_records);
+ nfp_prog->map_records = NULL;
+ nfp_prog->map_records_cnt = 0;
+}
+
+static int
+nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
+ struct bpf_prog *prog)
+{
+ int i, cnt, err;
+
+ /* Quickly count the maps we will have to remember */
+ cnt = 0;
+ for (i = 0; i < prog->aux->used_map_cnt; i++)
+ if (bpf_map_offload_neutral(prog->aux->used_maps[i]))
+ cnt++;
+ if (!cnt)
+ return 0;
+
+ nfp_prog->map_records = kmalloc_array(cnt,
+ sizeof(nfp_prog->map_records[0]),
+ GFP_KERNEL);
+ if (!nfp_prog->map_records)
+ return -ENOMEM;
+
+ for (i = 0; i < prog->aux->used_map_cnt; i++)
+ if (bpf_map_offload_neutral(prog->aux->used_maps[i])) {
+ err = nfp_map_ptr_record(bpf, nfp_prog,
+ prog->aux->used_maps[i]);
+ if (err) {
+ nfp_map_ptrs_forget(bpf, nfp_prog);
+ return err;
+ }
+ }
+ WARN_ON(cnt != nfp_prog->map_records_cnt);
+
+ return 0;
+}
+
static int
nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
unsigned int cnt)
prog->aux->offload->jited_len = nfp_prog->prog_len * sizeof(u64);
prog->aux->offload->jited_image = nfp_prog->prog;
- return 0;
+ return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog);
}
static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog)
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
kvfree(nfp_prog->prog);
+ nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog);
nfp_prog_free(nfp_prog);
return 0;
}
}
+static unsigned long
+nfp_bpf_perf_event_copy(void *dst, const void *src,
+ unsigned long off, unsigned long len)
+{
+ memcpy(dst, src + off, len);
+ return 0;
+}
+
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb)
+{
+ struct cmsg_bpf_event *cbe = (void *)skb->data;
+ u32 pkt_size, data_size;
+ struct bpf_map *map;
+
+ if (skb->len < sizeof(struct cmsg_bpf_event))
+ goto err_drop;
+
+ pkt_size = be32_to_cpu(cbe->pkt_size);
+ data_size = be32_to_cpu(cbe->data_size);
+ map = (void *)(unsigned long)be64_to_cpu(cbe->map_ptr);
+
+ if (skb->len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
+ goto err_drop;
+ if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION)
+ goto err_drop;
+
+ rcu_read_lock();
+ if (!rhashtable_lookup_fast(&bpf->maps_neutral, &map,
+ nfp_bpf_maps_neutral_params)) {
+ rcu_read_unlock();
+ pr_warn("perf event: dest map pointer %px not recognized, dropping event\n",
+ map);
+ goto err_drop;
+ }
+
+ bpf_event_output(map, be32_to_cpu(cbe->cpu_id),
+ &cbe->data[round_up(pkt_size, 4)], data_size,
+ cbe->data, pkt_size, nfp_bpf_perf_event_copy);
+ rcu_read_unlock();
+
+ dev_consume_skb_any(skb);
+ return 0;
+err_drop:
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+}
+
static int
nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
/*
- * Copyright (C) 2016-2017 Netronome Systems, Inc.
+ * Copyright (C) 2016-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
#include <linux/kernel.h>
#include <linux/pkt_cls.h>
+#include "../nfp_app.h"
+#include "../nfp_main.h"
#include "fw.h"
#include "main.h"
return false;
}
- /* Rest of the checks is only if we re-parse the same insn */
- if (!meta->func_id)
- return true;
-
- if (meta->arg1.map_ptr != reg1->map_ptr) {
- pr_vlog(env, "%s: called for different map\n", fname);
- return false;
- }
-
return true;
}
pr_vlog(env, "bpf_get_prandom_u32(): FW doesn't support random number generation\n");
return -EOPNOTSUPP;
+ case BPF_FUNC_perf_event_output:
+ BUILD_BUG_ON(NFP_BPF_SCALAR_VALUE != SCALAR_VALUE ||
+ NFP_BPF_MAP_VALUE != PTR_TO_MAP_VALUE ||
+ NFP_BPF_STACK != PTR_TO_STACK ||
+ NFP_BPF_PACKET_DATA != PTR_TO_PACKET);
+
+ if (!bpf->helpers.perf_event_output) {
+ pr_vlog(env, "event_output: not supported by FW\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Force current CPU to make sure we can report the event
+ * wherever we get the control message from FW.
+ */
+ if (reg3->var_off.mask & BPF_F_INDEX_MASK ||
+ (reg3->var_off.value & BPF_F_INDEX_MASK) !=
+ BPF_F_CURRENT_CPU) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg3->var_off);
+ pr_vlog(env, "event_output: must use BPF_F_CURRENT_CPU, var_off: %s\n",
+ tn_buf);
+ return -EOPNOTSUPP;
+ }
+
+ /* Save space in meta, we don't care about arguments other
+ * than 4th meta, shove it into arg1.
+ */
+ reg1 = cur_regs(env) + BPF_REG_4;
+
+ if (reg1->type != SCALAR_VALUE /* NULL ptr */ &&
+ reg1->type != PTR_TO_STACK &&
+ reg1->type != PTR_TO_MAP_VALUE &&
+ reg1->type != PTR_TO_PACKET) {
+ pr_vlog(env, "event_output: unsupported ptr type: %d\n",
+ reg1->type);
+ return -EOPNOTSUPP;
+ }
+
+ if (reg1->type == PTR_TO_STACK &&
+ !nfp_bpf_stack_arg_ok("event_output", env, reg1, NULL))
+ return -EOPNOTSUPP;
+
+ /* Warn user that on offload NFP may return success even if map
+ * is not going to accept the event, since the event output is
+ * fully async and device won't know the state of the map.
+ * There is also FW limitation on the event length.
+ *
+ * Lost events will not show up on the perf ring, driver
+ * won't see them at all. Events may also get reordered.
+ */
+ dev_warn_once(&nfp_prog->bpf->app->pf->pdev->dev,
+ "bpf: note: return codes and behavior of bpf_event_output() helper differs for offloaded programs!\n");
+ pr_vlog(env, "warning: return codes and behavior of event_output helper differ for offload!\n");
+
+ if (!meta->func_id)
+ break;
+
+ if (reg1->type != meta->arg1.type) {
+ pr_vlog(env, "event_output: ptr type changed: %d %d\n",
+ meta->arg1.type, reg1->type);
+ return -EINVAL;
+ }
+ break;
+
default:
pr_vlog(env, "unsupported function id: %d\n", func_id);
return -EOPNOTSUPP;
return 0;
}
+static int
+nfp_bpf_check_store(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+ struct bpf_verifier_env *env)
+{
+ const struct bpf_reg_state *reg = cur_regs(env) + meta->insn.dst_reg;
+
+ if (reg->type == PTR_TO_CTX) {
+ if (nfp_prog->type == BPF_PROG_TYPE_XDP) {
+ /* XDP ctx accesses must be 4B in size */
+ switch (meta->insn.off) {
+ case offsetof(struct xdp_md, rx_queue_index):
+ if (nfp_prog->bpf->queue_select)
+ goto exit_check_ptr;
+ pr_vlog(env, "queue selection not supported by FW\n");
+ return -EOPNOTSUPP;
+ }
+ }
+ pr_vlog(env, "unsupported store to context field\n");
+ return -EOPNOTSUPP;
+ }
+exit_check_ptr:
+ return nfp_bpf_check_ptr(nfp_prog, meta, env, meta->insn.dst_reg);
+}
+
static int
nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
struct bpf_verifier_env *env)
return nfp_bpf_check_ptr(nfp_prog, meta, env,
meta->insn.src_reg);
if (is_mbpf_store(meta))
- return nfp_bpf_check_ptr(nfp_prog, meta, env,
- meta->insn.dst_reg);
+ return nfp_bpf_check_store(nfp_prog, meta, env);
+
if (is_mbpf_xadd(meta))
return nfp_bpf_check_xadd(nfp_prog, meta, env);
nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
const struct tc_action *action,
struct nfp_fl_pre_tunnel *pre_tun,
- enum nfp_flower_tun_type tun_type)
+ enum nfp_flower_tun_type tun_type,
+ struct net_device *netdev)
{
size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
u32 tmp_set_ip_tun_type_index = 0;
/* Currently support one pre-tunnel so index is always 0. */
int pretun_idx = 0;
+ struct net *net;
if (ip_tun->options_len)
return -EOPNOTSUPP;
+ net = dev_net(netdev);
+
set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
set_tun->tun_id = ip_tun->key.tun_id;
+ set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
/* Complete pre_tunnel action. */
pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
*a_len += sizeof(struct nfp_fl_pre_tunnel);
set_tun = (void *)&nfp_fl->action_data[*a_len];
- err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type);
+ err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
+ netdev);
if (err)
return err;
*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
__be16 reserved;
__be64 tun_id __packed;
__be32 tun_type_index;
- __be32 extra[3];
+ __be16 reserved2;
+ u8 ttl;
+ u8 reserved3;
+ __be32 extra[2];
};
/* Metadata with L2 (1W/4B)
#define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL
-#define NFP_FLOWER_FRAME_HEADROOM 158
-
static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn)
{
return "FLOWER";
err = -ENOMEM;
goto err_reprs_clean;
}
- RCU_INIT_POINTER(reprs->reprs[i], repr);
/* For now we only support 1 PF */
WARN_ON(repr_type == NFP_REPR_TYPE_PF && i);
port = nfp_port_alloc(app, port_type, repr);
+ if (IS_ERR(port)) {
+ err = PTR_ERR(port);
+ nfp_repr_free(repr);
+ goto err_reprs_clean;
+ }
if (repr_type == NFP_REPR_TYPE_PF) {
port->pf_id = i;
port->vnic = priv->nn->dp.ctrl_bar;
port_id, port, priv->nn->dp.netdev);
if (err) {
nfp_port_free(port);
+ nfp_repr_free(repr);
goto err_reprs_clean;
}
+ RCU_INIT_POINTER(reprs->reprs[i], repr);
nfp_info(app->cpp, "%s%d Representor(%s) created\n",
repr_type == NFP_REPR_TYPE_PF ? "PF" : "VF", i,
repr->name);
err = -ENOMEM;
goto err_reprs_clean;
}
- RCU_INIT_POINTER(reprs->reprs[phys_port], repr);
port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr);
if (IS_ERR(port)) {
err = PTR_ERR(port);
+ nfp_repr_free(repr);
goto err_reprs_clean;
}
err = nfp_port_init_phy_port(app->pf, app, port, i);
if (err) {
nfp_port_free(port);
+ nfp_repr_free(repr);
goto err_reprs_clean;
}
SET_NETDEV_DEV(repr, &priv->nn->pdev->dev);
- nfp_net_get_mac_addr(app->pf, port);
+ nfp_net_get_mac_addr(app->pf, repr, port);
cmsg_port_id = nfp_flower_cmsg_phys_port(phys_port);
err = nfp_repr_init(app, repr,
cmsg_port_id, port, priv->nn->dp.netdev);
if (err) {
nfp_port_free(port);
+ nfp_repr_free(repr);
goto err_reprs_clean;
}
eth_tbl->ports[i].base,
phys_port);
+ RCU_INIT_POINTER(reprs->reprs[phys_port], repr);
nfp_info(app->cpp, "Phys Port %d Representor(%s) created\n",
phys_port, repr->name);
}
app->priv = NULL;
}
-static int
-nfp_flower_check_mtu(struct nfp_app *app, struct net_device *netdev,
- int new_mtu)
-{
- /* The flower fw reserves NFP_FLOWER_FRAME_HEADROOM bytes of the
- * supported max MTU to allow for appending tunnel headers. To prevent
- * unexpected behaviour this needs to be accounted for.
- */
- if (new_mtu > netdev->max_mtu - NFP_FLOWER_FRAME_HEADROOM) {
- nfp_err(app->cpp, "New MTU (%d) is not valid\n", new_mtu);
- return -EINVAL;
- }
-
- return 0;
-}
-
static bool nfp_flower_check_ack(struct nfp_flower_priv *app_priv)
{
bool ret;
.init = nfp_flower_init,
.clean = nfp_flower_clean,
- .check_mtu = nfp_flower_check_mtu,
.repr_change_mtu = nfp_flower_repr_change_mtu,
.vnic_alloc = nfp_flower_vnic_alloc,
struct net_device;
struct nfp_app;
+#define NFP_FL_STATS_CTX_DONT_CARE cpu_to_be32(0xffffffff)
#define NFP_FL_STATS_ENTRY_RS BIT(20)
#define NFP_FL_STATS_ELEM_RS 4
#define NFP_FL_REPEATED_HASH_MAX BIT(17)
spinlock_t lock; /* lock stats */
struct nfp_fl_stats stats;
__be32 nfp_tun_ipv4_addr;
+ struct net_device *ingress_dev;
char *unmasked_data;
char *mask_data;
char *action_data;
+ bool ingress_offload;
};
struct nfp_fl_stats_frame {
struct nfp_fl_payload *nfp_flow);
int nfp_compile_flow_metadata(struct nfp_app *app,
struct tc_cls_flower_offload *flow,
- struct nfp_fl_payload *nfp_flow);
+ struct nfp_fl_payload *nfp_flow,
+ struct net_device *netdev);
int nfp_modify_flow_metadata(struct nfp_app *app,
struct nfp_fl_payload *nfp_flow);
struct nfp_fl_payload *
-nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
+nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
+ struct net_device *netdev, __be32 host_ctx);
struct nfp_fl_payload *
nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
/* Must be called with either RTNL or rcu_read_lock */
struct nfp_fl_payload *
-nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie)
+nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
+ struct net_device *netdev, __be32 host_ctx)
{
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload *flower_entry;
hash_for_each_possible_rcu(priv->flow_table, flower_entry, link,
tc_flower_cookie)
- if (flower_entry->tc_flower_cookie == tc_flower_cookie)
+ if (flower_entry->tc_flower_cookie == tc_flower_cookie &&
+ (!netdev || flower_entry->ingress_dev == netdev) &&
+ (host_ctx == NFP_FL_STATS_CTX_DONT_CARE ||
+ flower_entry->meta.host_ctx_id == host_ctx))
return flower_entry;
return NULL;
flower_cookie = be64_to_cpu(stats->stats_cookie);
rcu_read_lock();
- nfp_flow = nfp_flower_search_fl_table(app, flower_cookie);
+ nfp_flow = nfp_flower_search_fl_table(app, flower_cookie, NULL,
+ stats->stats_con_id);
if (!nfp_flow)
goto exit_rcu_unlock;
- if (nfp_flow->meta.host_ctx_id != stats->stats_con_id)
- goto exit_rcu_unlock;
-
spin_lock(&nfp_flow->lock);
nfp_flow->stats.pkts += be32_to_cpu(stats->pkt_count);
nfp_flow->stats.bytes += be64_to_cpu(stats->byte_count);
int nfp_compile_flow_metadata(struct nfp_app *app,
struct tc_cls_flower_offload *flow,
- struct nfp_fl_payload *nfp_flow)
+ struct nfp_fl_payload *nfp_flow,
+ struct net_device *netdev)
{
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload *check_entry;
nfp_flow->stats.bytes = 0;
nfp_flow->stats.used = jiffies;
- check_entry = nfp_flower_search_fl_table(app, flow->cookie);
+ check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev,
+ NFP_FL_STATS_CTX_DONT_CARE);
if (check_entry) {
if (nfp_release_stats_entry(app, stats_cxt))
return -EINVAL;
}
static struct nfp_fl_payload *
-nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
+nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress)
{
struct nfp_fl_payload *flow_pay;
flow_pay->meta.flags = 0;
spin_lock_init(&flow_pay->lock);
+ flow_pay->ingress_offload = !egress;
+
return flow_pay;
err_free_mask:
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload *flow_pay;
struct nfp_fl_key_ls *key_layer;
+ struct net_device *ingr_dev;
int err;
+ ingr_dev = egress ? NULL : netdev;
+ flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
+ NFP_FL_STATS_CTX_DONT_CARE);
+ if (flow_pay) {
+ /* Ignore as duplicate if it has been added by different cb. */
+ if (flow_pay->ingress_offload && egress)
+ return 0;
+ else
+ return -EOPNOTSUPP;
+ }
+
key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL);
if (!key_layer)
return -ENOMEM;
if (err)
goto err_free_key_ls;
- flow_pay = nfp_flower_allocate_new(key_layer);
+ flow_pay = nfp_flower_allocate_new(key_layer, egress);
if (!flow_pay) {
err = -ENOMEM;
goto err_free_key_ls;
}
+ flow_pay->ingress_dev = egress ? NULL : netdev;
+
err = nfp_flower_compile_flow_match(flow, key_layer, netdev, flow_pay,
tun_type);
if (err)
if (err)
goto err_destroy_flow;
- err = nfp_compile_flow_metadata(app, flow, flow_pay);
+ err = nfp_compile_flow_metadata(app, flow, flow_pay,
+ flow_pay->ingress_dev);
if (err)
goto err_destroy_flow;
* @app: Pointer to the APP handle
* @netdev: netdev structure.
* @flow: TC flower classifier offload structure
+ * @egress: Netdev is the egress dev.
*
* Removes a flow from the repeated hash structure and clears the
* action payload.
*/
static int
nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
- struct tc_cls_flower_offload *flow)
+ struct tc_cls_flower_offload *flow, bool egress)
{
struct nfp_port *port = nfp_port_from_netdev(netdev);
struct nfp_fl_payload *nfp_flow;
+ struct net_device *ingr_dev;
int err;
- nfp_flow = nfp_flower_search_fl_table(app, flow->cookie);
+ ingr_dev = egress ? NULL : netdev;
+ nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
+ NFP_FL_STATS_CTX_DONT_CARE);
if (!nfp_flow)
- return -ENOENT;
+ return egress ? 0 : -ENOENT;
err = nfp_modify_flow_metadata(app, nfp_flow);
if (err)
/**
* nfp_flower_get_stats() - Populates flow stats obtained from hardware.
* @app: Pointer to the APP handle
+ * @netdev: Netdev structure.
* @flow: TC flower classifier offload structure
+ * @egress: Netdev is the egress dev.
*
* Populates a flow statistics structure which which corresponds to a
* specific flow.
* Return: negative value on error, 0 if stats populated successfully.
*/
static int
-nfp_flower_get_stats(struct nfp_app *app, struct tc_cls_flower_offload *flow)
+nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
+ struct tc_cls_flower_offload *flow, bool egress)
{
struct nfp_fl_payload *nfp_flow;
+ struct net_device *ingr_dev;
- nfp_flow = nfp_flower_search_fl_table(app, flow->cookie);
+ ingr_dev = egress ? NULL : netdev;
+ nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
+ NFP_FL_STATS_CTX_DONT_CARE);
if (!nfp_flow)
return -EINVAL;
+ if (nfp_flow->ingress_offload && egress)
+ return 0;
+
spin_lock_bh(&nfp_flow->lock);
tcf_exts_stats_update(flow->exts, nfp_flow->stats.bytes,
nfp_flow->stats.pkts, nfp_flow->stats.used);
case TC_CLSFLOWER_REPLACE:
return nfp_flower_add_offload(app, netdev, flower, egress);
case TC_CLSFLOWER_DESTROY:
- return nfp_flower_del_offload(app, netdev, flower);
+ return nfp_flower_del_offload(app, netdev, flower, egress);
case TC_CLSFLOWER_STATS:
- return nfp_flower_get_stats(app, flower);
+ return nfp_flower_get_stats(app, netdev, flower, egress);
}
return -EOPNOTSUPP;
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
if (err)
return err < 0 ? err : 0;
- nfp_net_get_mac_addr(app->pf, nn->port);
+ nfp_net_get_mac_addr(app->pf, nn->dp.netdev, nn->port);
return 0;
}
#define OP_ALU_DST_LMEXTN 0x80000000000ULL
enum alu_op {
- ALU_OP_NONE = 0x00,
- ALU_OP_ADD = 0x01,
- ALU_OP_NOT = 0x04,
- ALU_OP_ADD_2B = 0x05,
- ALU_OP_AND = 0x08,
- ALU_OP_SUB_C = 0x0d,
- ALU_OP_ADD_C = 0x11,
- ALU_OP_OR = 0x14,
- ALU_OP_SUB = 0x15,
- ALU_OP_XOR = 0x18,
+ ALU_OP_NONE = 0x00,
+ ALU_OP_ADD = 0x01,
+ ALU_OP_NOT = 0x04,
+ ALU_OP_ADD_2B = 0x05,
+ ALU_OP_AND = 0x08,
+ ALU_OP_AND_NOT_A = 0x0c,
+ ALU_OP_SUB_C = 0x0d,
+ ALU_OP_AND_NOT_B = 0x10,
+ ALU_OP_ADD_C = 0x11,
+ ALU_OP_OR = 0x14,
+ ALU_OP_SUB = 0x15,
+ ALU_OP_XOR = 0x18,
};
enum alu_dst_ab {
return ret;
devlink_port_type_eth_set(&port->dl_port, port->netdev);
- if (eth_port.is_split)
- devlink_port_split_set(&port->dl_port, eth_port.label_port);
+ devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
+ eth_port.label_port, eth_port.is_split,
+ eth_port.label_subport);
devlink = priv_to_devlink(app->pf);
goto err_disable_msix;
}
+ err = nfp_resource_table_init(pf->cpp);
+ if (err)
+ goto err_cpp_free;
+
pf->hwinfo = nfp_hwinfo_read(pf->cpp);
dev_info(&pdev->dev, "Assembly: %s%s%s-%s CPLD: %s\n",
vfree(pf->dumpspec);
err_hwinfo_free:
kfree(pf->hwinfo);
+err_cpp_free:
nfp_cpp_free(pf->cpp);
err_disable_msix:
destroy_workqueue(pf->wq);
int nfp_hwmon_register(struct nfp_pf *pf);
void nfp_hwmon_unregister(struct nfp_pf *pf);
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port);
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+ struct nfp_port *port);
bool nfp_ctrl_tx(struct nfp_net *nn, struct sk_buff *skb);
/**
* nfp_net_get_mac_addr() - Get the MAC address.
* @pf: NFP PF handle
+ * @netdev: net_device to set MAC address on
* @port: NFP port structure
*
* First try to get the MAC address from NSP ETH table. If that
* fails generate a random address.
*/
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port)
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+ struct nfp_port *port)
{
struct nfp_eth_table_port *eth_port;
eth_port = __nfp_port_get_eth_port(port);
if (!eth_port) {
- eth_hw_addr_random(port->netdev);
+ eth_hw_addr_random(netdev);
return;
}
- ether_addr_copy(port->netdev->dev_addr, eth_port->mac_addr);
- ether_addr_copy(port->netdev->perm_addr, eth_port->mac_addr);
+ ether_addr_copy(netdev->dev_addr, eth_port->mac_addr);
+ ether_addr_copy(netdev->perm_addr, eth_port->mac_addr);
}
static struct nfp_eth_table_port *
return PTR_ERR(mem);
}
- min_size = NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
- pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
- "net.macstats", min_size,
- &pf->mac_stats_bar);
- if (IS_ERR(pf->mac_stats_mem)) {
- if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
- err = PTR_ERR(pf->mac_stats_mem);
- goto err_unmap_ctrl;
+ if (pf->eth_tbl) {
+ min_size = NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
+ pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
+ "net.macstats", min_size,
+ &pf->mac_stats_bar);
+ if (IS_ERR(pf->mac_stats_mem)) {
+ if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
+ err = PTR_ERR(pf->mac_stats_mem);
+ goto err_unmap_ctrl;
+ }
+ pf->mac_stats_mem = NULL;
}
- pf->mac_stats_mem = NULL;
}
pf->vf_cfg_mem = nfp_net_pf_map_rtsym(pf, "net.vfcfg",
return err;
}
-static void nfp_repr_free(struct nfp_repr *repr)
+static void __nfp_repr_free(struct nfp_repr *repr)
{
free_percpu(repr->stats);
free_netdev(repr->netdev);
}
+void nfp_repr_free(struct net_device *netdev)
+{
+ __nfp_repr_free(netdev_priv(netdev));
+}
+
struct net_device *nfp_repr_alloc(struct nfp_app *app)
{
struct net_device *netdev;
nfp_info(repr->app->cpp, "Destroying Representor(%s)\n",
repr->netdev->name);
nfp_repr_clean(repr);
- nfp_repr_free(repr);
+ __nfp_repr_free(repr);
}
void nfp_reprs_clean_and_free(struct nfp_app *app, struct nfp_reprs *reprs)
int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
u32 cmsg_port_id, struct nfp_port *port,
struct net_device *pf_netdev);
+void nfp_repr_free(struct net_device *netdev);
struct net_device *nfp_repr_alloc(struct nfp_app *app);
void nfp_reprs_clean_and_free(struct nfp_app *app, struct nfp_reprs *reprs);
void nfp_reprs_clean_and_free_by_type(struct nfp_app *app,
/* MAC Statistics Accumulator */
#define NFP_RESOURCE_MAC_STATISTICS "mac.stat"
+int nfp_resource_table_init(struct nfp_cpp *cpp);
+
struct nfp_resource *
nfp_resource_acquire(struct nfp_cpp *cpp, const char *name);
/* Finished with card initialization. */
dev_info(&pdev->dev,
"Netronome Flow Processor NFP4000/NFP6000 PCIe Card Probe\n");
+ pcie_print_link_status(pdev);
nfp = kzalloc(sizeof(*nfp), GFP_KERNEL);
if (!nfp) {
int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex);
int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex);
int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex);
+int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target,
+ unsigned long long address);
/**
* nfp_cppcore_pcie_unit() - Get PCI Unit of a CPP handle
return (u32)interface << 16 | 0x0000;
}
+static u32 nfp_mutex_owner(u32 val)
+{
+ return val >> 16;
+}
+
static bool nfp_mutex_is_locked(u32 val)
{
return (val & 0xffff) == 0x000f;
return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
}
+
+/**
+ * nfp_cpp_mutex_reclaim() - Unlock mutex if held by local endpoint
+ * @cpp: NFP CPP handle
+ * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address: Offset into the address space of the NFP CPP target ID
+ *
+ * Release lock if held by local system. Extreme care is advised, call only
+ * when no local lock users can exist.
+ *
+ * Return: 0 if the lock was OK, 1 if locked by us, -errno on invalid mutex
+ */
+int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target,
+ unsigned long long address)
+{
+ const u32 mur = NFP_CPP_ID(target, 3, 0); /* atomic_read */
+ const u32 muw = NFP_CPP_ID(target, 4, 0); /* atomic_write */
+ u16 interface = nfp_cpp_interface(cpp);
+ int err;
+ u32 tmp;
+
+ err = nfp_cpp_mutex_validate(interface, &target, address);
+ if (err)
+ return err;
+
+ /* Check lock */
+ err = nfp_cpp_readl(cpp, mur, address, &tmp);
+ if (err < 0)
+ return err;
+
+ if (nfp_mutex_is_unlocked(tmp) || nfp_mutex_owner(tmp) != interface)
+ return 0;
+
+ /* Bust the lock */
+ err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_unlocked(interface));
+ if (err < 0)
+ return err;
+
+ return 1;
+}
{
return res->size;
}
+
+/**
+ * nfp_resource_table_init() - Run initial checks on the resource table
+ * @cpp: NFP CPP handle
+ *
+ * Start-of-day init procedure for resource table. Must be called before
+ * any local resource table users may exist.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int nfp_resource_table_init(struct nfp_cpp *cpp)
+{
+ struct nfp_cpp_mutex *dev_mutex;
+ int i, err;
+
+ err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET,
+ NFP_RESOURCE_TBL_BASE);
+ if (err < 0) {
+ nfp_err(cpp, "Error: failed to reclaim resource table mutex\n");
+ return err;
+ }
+ if (err)
+ nfp_warn(cpp, "Warning: busted main resource table mutex\n");
+
+ dev_mutex = nfp_cpp_mutex_alloc(cpp, NFP_RESOURCE_TBL_TARGET,
+ NFP_RESOURCE_TBL_BASE,
+ NFP_RESOURCE_TBL_KEY);
+ if (!dev_mutex)
+ return -ENOMEM;
+
+ if (nfp_cpp_mutex_lock(dev_mutex)) {
+ nfp_err(cpp, "Error: failed to claim resource table mutex\n");
+ nfp_cpp_mutex_free(dev_mutex);
+ return -EINVAL;
+ }
+
+ /* Resource 0 is the dev_mutex, start from 1 */
+ for (i = 1; i < NFP_RESOURCE_TBL_ENTRIES; i++) {
+ u64 addr = NFP_RESOURCE_TBL_BASE +
+ sizeof(struct nfp_resource_entry) * i;
+
+ err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET, addr);
+ if (err < 0) {
+ nfp_err(cpp,
+ "Error: failed to reclaim resource %d mutex\n",
+ i);
+ goto err_unlock;
+ }
+ if (err)
+ nfp_warn(cpp, "Warning: busted resource %d mutex\n", i);
+ }
+
+ err = 0;
+err_unlock:
+ nfp_cpp_mutex_unlock(dev_mutex);
+ nfp_cpp_mutex_free(dev_mutex);
+
+ return err;
+}
cell = nvmem_cell_get(dev, "address");
if (IS_ERR(cell))
- return cell;
+ return NULL;
mac = nvmem_cell_read(cell, &cell_size);
nvmem_cell_put(cell);
struct nixge_priv *priv;
struct net_device *ndev;
struct resource *dmares;
- const char *mac_addr;
+ const u8 *mac_addr;
int err;
ndev = alloc_etherdev(sizeof(*priv));
ndev->max_mtu = NIXGE_JUMBO_MTU;
mac_addr = nixge_get_nvmem_address(&pdev->dev);
- if (mac_addr && is_valid_ether_addr(mac_addr))
+ if (mac_addr && is_valid_ether_addr(mac_addr)) {
ether_addr_copy(ndev->dev_addr, mac_addr);
- else
+ kfree(mac_addr);
+ } else {
eth_hw_addr_random(ndev);
+ }
priv = netdev_priv(ndev);
priv->ndev = ndev;
u32 init_ops_size;
};
+enum qed_mf_mode_bit {
+ /* Supports PF-classification based on tag */
+ QED_MF_OVLAN_CLSS,
+
+ /* Supports PF-classification based on MAC */
+ QED_MF_LLH_MAC_CLSS,
+
+ /* Supports PF-classification based on protocol type */
+ QED_MF_LLH_PROTO_CLSS,
+
+ /* Requires a default PF to be set */
+ QED_MF_NEED_DEF_PF,
+
+ /* Allow LL2 to multicast/broadcast */
+ QED_MF_LL2_NON_UNICAST,
+
+ /* Allow Cross-PF [& child VFs] Tx-switching */
+ QED_MF_INTER_PF_SWITCH,
+
+ /* Unified Fabtic Port support enabled */
+ QED_MF_UFP_SPECIFIC,
+
+ /* Disable Accelerated Receive Flow Steering (aRFS) */
+ QED_MF_DISABLE_ARFS,
+
+ /* Use vlan for steering */
+ QED_MF_8021Q_TAGGING,
+
+ /* Use stag for steering */
+ QED_MF_8021AD_TAGGING,
+
+ /* Allow DSCP to TC mapping */
+ QED_MF_DSCP_TO_TC_MAP,
+};
+
+enum qed_ufp_mode {
+ QED_UFP_MODE_ETS,
+ QED_UFP_MODE_VNIC_BW,
+ QED_UFP_MODE_UNKNOWN
+};
+
+enum qed_ufp_pri_type {
+ QED_UFP_PRI_OS,
+ QED_UFP_PRI_VNIC,
+ QED_UFP_PRI_UNKNOWN
+};
+
+struct qed_ufp_info {
+ enum qed_ufp_pri_type pri_type;
+ enum qed_ufp_mode mode;
+ u8 tc;
+};
+
enum BAR_ID {
BAR_ID_0, /* used for GRC */
BAR_ID_1 /* Used for doorbells */
struct qed_dcbx_info *p_dcbx_info;
+ struct qed_ufp_info ufp_info;
+
struct qed_dmae_info dmae_info;
/* QM init */
u8 num_funcs_in_port;
u8 path_id;
- enum qed_mf_mode mf_mode;
-#define IS_MF_DEFAULT(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_DEFAULT)
-#define IS_MF_SI(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_NPAR)
-#define IS_MF_SD(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_OVLAN)
+
+ unsigned long mf_bits;
int pcie_width;
int pcie_speed;
u32 pri_tc_tbl, int count, u8 dcbx_version)
{
enum dcbx_protocol_type type;
+ bool enable, ieee, eth_tlv;
u8 tc, priority_map;
- bool enable, ieee;
u16 protocol_id;
int priority;
int i;
DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Num APP entries = %d\n", count);
ieee = (dcbx_version == DCBX_CONFIG_VERSION_IEEE);
+ eth_tlv = false;
/* Parse APP TLV */
for (i = 0; i < count; i++) {
protocol_id = QED_MFW_GET_FIELD(p_tbl[i].entry,
* indication, but we only got here if there was an
* app tlv for the protocol, so dcbx must be enabled.
*/
- enable = !(type == DCBX_PROTOCOL_ETH);
+ if (type == DCBX_PROTOCOL_ETH) {
+ enable = false;
+ eth_tlv = true;
+ } else {
+ enable = true;
+ }
qed_dcbx_update_app_info(p_data, p_hwfn, enable,
priority, tc, type);
}
}
+ /* If Eth TLV is not detected, use UFP TC as default TC */
+ if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) && !eth_tlv)
+ p_data->arr[DCBX_PROTOCOL_ETH].tc = p_hwfn->ufp_info.tc;
+
/* Update ramrod protocol data and hw_info fields
* with default info when corresponding APP TLV's are not detected.
* The enabled field has a different logic for ethernet as only for
#define NUM_RSS_MEM_TYPES 5
#define NUM_BIG_RAM_TYPES 3
+#define BIG_RAM_NAME_LEN 3
#define NUM_PHY_TBUS_ADDRESSES 2048
#define PHY_DUMP_SIZE_DWORDS (NUM_PHY_TBUS_ADDRESSES / 2)
BIT(big_ram->is_256b_bit_offset[dev_data->chip_id]) ? 256
: 128;
- strscpy(type_name, big_ram->instance_name, sizeof(type_name));
- strscpy(mem_name, big_ram->instance_name, sizeof(mem_name));
+ strncpy(type_name, big_ram->instance_name, BIG_RAM_NAME_LEN);
+ strncpy(mem_name, big_ram->instance_name, BIG_RAM_NAME_LEN);
/* Dump memory header */
offset += qed_grc_dump_mem_hdr(p_hwfn,
return -EINVAL;
}
- switch (p_hwfn->cdev->mf_mode) {
- case QED_MF_DEFAULT:
- case QED_MF_NPAR:
- hw_mode |= 1 << MODE_MF_SI;
- break;
- case QED_MF_OVLAN:
+ if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits))
hw_mode |= 1 << MODE_MF_SD;
- break;
- default:
- DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n");
+ else
hw_mode |= 1 << MODE_MF_SI;
- }
hw_mode |= 1 << MODE_ASIC;
STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET, 1);
STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET,
p_hwfn->hw_info.ovlan);
+
+ DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
+ "Configuring LLH_FUNC_FILTER_HDR_SEL\n");
+ STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET,
+ 1);
}
/* Enable classification by MAC if needed */
/* send function start command */
rc = qed_sp_pf_start(p_hwfn, p_ptt, p_tunn,
- p_hwfn->cdev->mf_mode,
allow_npar_tx_switch);
if (rc) {
DP_NOTICE(p_hwfn, "Function start ramrod failed\n");
bool b_default_mtu = true;
struct qed_hwfn *p_hwfn;
int rc = 0, mfw_rc, i;
+ u16 ether_type;
if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
if (rc)
return rc;
+ if (IS_PF(cdev) && (test_bit(QED_MF_8021Q_TAGGING,
+ &cdev->mf_bits) ||
+ test_bit(QED_MF_8021AD_TAGGING,
+ &cdev->mf_bits))) {
+ if (test_bit(QED_MF_8021Q_TAGGING, &cdev->mf_bits))
+ ether_type = ETH_P_8021Q;
+ else
+ ether_type = ETH_P_8021AD;
+ STORE_RT_REG(p_hwfn, PRS_REG_TAG_ETHERTYPE_0_RT_OFFSET,
+ ether_type);
+ STORE_RT_REG(p_hwfn, NIG_REG_TAG_ETHERTYPE_0_RT_OFFSET,
+ ether_type);
+ STORE_RT_REG(p_hwfn, PBF_REG_TAG_ETHERTYPE_0_RT_OFFSET,
+ ether_type);
+ STORE_RT_REG(p_hwfn, DORQ_REG_TAG1_ETHERTYPE_RT_OFFSET,
+ ether_type);
+ }
+
qed_fill_load_req_params(&load_req_params,
p_params->p_drv_load_params);
rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt,
link->pause.autoneg,
p_caps->default_eee, p_caps->eee_lpi_timer);
- /* Read Multi-function information from shmem */
- addr = MCP_REG_SCRATCH + nvm_cfg1_offset +
- offsetof(struct nvm_cfg1, glob) +
- offsetof(struct nvm_cfg1_glob, generic_cont0);
+ if (IS_LEAD_HWFN(p_hwfn)) {
+ struct qed_dev *cdev = p_hwfn->cdev;
- generic_cont0 = qed_rd(p_hwfn, p_ptt, addr);
+ /* Read Multi-function information from shmem */
+ addr = MCP_REG_SCRATCH + nvm_cfg1_offset +
+ offsetof(struct nvm_cfg1, glob) +
+ offsetof(struct nvm_cfg1_glob, generic_cont0);
- mf_mode = (generic_cont0 & NVM_CFG1_GLOB_MF_MODE_MASK) >>
- NVM_CFG1_GLOB_MF_MODE_OFFSET;
+ generic_cont0 = qed_rd(p_hwfn, p_ptt, addr);
- switch (mf_mode) {
- case NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED:
- p_hwfn->cdev->mf_mode = QED_MF_OVLAN;
- break;
- case NVM_CFG1_GLOB_MF_MODE_NPAR1_0:
- p_hwfn->cdev->mf_mode = QED_MF_NPAR;
- break;
- case NVM_CFG1_GLOB_MF_MODE_DEFAULT:
- p_hwfn->cdev->mf_mode = QED_MF_DEFAULT;
- break;
+ mf_mode = (generic_cont0 & NVM_CFG1_GLOB_MF_MODE_MASK) >>
+ NVM_CFG1_GLOB_MF_MODE_OFFSET;
+
+ switch (mf_mode) {
+ case NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED:
+ cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS);
+ break;
+ case NVM_CFG1_GLOB_MF_MODE_UFP:
+ cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) |
+ BIT(QED_MF_LLH_PROTO_CLSS) |
+ BIT(QED_MF_UFP_SPECIFIC) |
+ BIT(QED_MF_8021Q_TAGGING);
+ break;
+ case NVM_CFG1_GLOB_MF_MODE_BD:
+ cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) |
+ BIT(QED_MF_LLH_PROTO_CLSS) |
+ BIT(QED_MF_8021AD_TAGGING);
+ break;
+ case NVM_CFG1_GLOB_MF_MODE_NPAR1_0:
+ cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
+ BIT(QED_MF_LLH_PROTO_CLSS) |
+ BIT(QED_MF_LL2_NON_UNICAST) |
+ BIT(QED_MF_INTER_PF_SWITCH);
+ break;
+ case NVM_CFG1_GLOB_MF_MODE_DEFAULT:
+ cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
+ BIT(QED_MF_LLH_PROTO_CLSS) |
+ BIT(QED_MF_LL2_NON_UNICAST);
+ if (QED_IS_BB(p_hwfn->cdev))
+ cdev->mf_bits |= BIT(QED_MF_NEED_DEF_PF);
+ break;
+ }
+
+ DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
+ cdev->mf_bits);
}
- DP_INFO(p_hwfn, "Multi function mode is %08x\n",
- p_hwfn->cdev->mf_mode);
- /* Read Multi-function information from shmem */
+ DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
+ p_hwfn->cdev->mf_bits);
+
+ /* Read device capabilities information from shmem */
addr = MCP_REG_SCRATCH + nvm_cfg1_offset +
offsetof(struct nvm_cfg1, glob) +
offsetof(struct nvm_cfg1_glob, device_capabilities);
qed_mcp_cmd_port_init(p_hwfn, p_ptt);
qed_get_eee_caps(p_hwfn, p_ptt);
+
+ qed_mcp_read_ufp_config(p_hwfn, p_ptt);
}
if (qed_mcp_is_init(p_hwfn)) {
u32 high = 0, low = 0, en;
int i;
- if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn)))
+ if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits))
return 0;
qed_llh_mac_to_filter(&high, &low, p_filter);
u32 high = 0, low = 0;
int i;
- if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn)))
+ if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits))
return;
qed_llh_mac_to_filter(&high, &low, p_filter);
u32 high = 0, low = 0, en;
int i;
- if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn)))
+ if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits))
return 0;
switch (type) {
u32 high = 0, low = 0;
int i;
- if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn)))
+ if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits))
return;
switch (type) {
p_data->d_id.addr_mid = p_conn->d_id.addr_mid;
p_data->d_id.addr_lo = p_conn->d_id.addr_lo;
p_data->flags = p_conn->flags;
+ if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+ SET_FIELD(p_data->flags,
+ FCOE_CONN_OFFLOAD_RAMROD_DATA_B_SINGLE_VLAN, 1);
p_data->def_q_idx = p_conn->def_q_idx;
return qed_spq_post(p_hwfn, p_ent, NULL);
#define EEE_REMOTE_TW_TX_OFFSET 0
#define EEE_REMOTE_TW_RX_MASK 0xffff0000
#define EEE_REMOTE_TW_RX_OFFSET 16
+
+ u32 oem_cfg_port;
+#define OEM_CFG_CHANNEL_TYPE_MASK 0x00000003
+#define OEM_CFG_CHANNEL_TYPE_OFFSET 0
+#define OEM_CFG_CHANNEL_TYPE_VLAN_PARTITION 0x1
+#define OEM_CFG_CHANNEL_TYPE_STAGGED 0x2
+#define OEM_CFG_SCHED_TYPE_MASK 0x0000000C
+#define OEM_CFG_SCHED_TYPE_OFFSET 2
+#define OEM_CFG_SCHED_TYPE_ETS 0x1
+#define OEM_CFG_SCHED_TYPE_VNIC_BW 0x2
};
struct public_func {
#define DRV_ID_DRV_INIT_HW_MASK 0x80000000
#define DRV_ID_DRV_INIT_HW_SHIFT 31
#define DRV_ID_DRV_INIT_HW_FLAG (1 << DRV_ID_DRV_INIT_HW_SHIFT)
+
+ u32 oem_cfg_func;
+#define OEM_CFG_FUNC_TC_MASK 0x0000000F
+#define OEM_CFG_FUNC_TC_OFFSET 0
+#define OEM_CFG_FUNC_TC_0 0x0
+#define OEM_CFG_FUNC_TC_1 0x1
+#define OEM_CFG_FUNC_TC_2 0x2
+#define OEM_CFG_FUNC_TC_3 0x3
+#define OEM_CFG_FUNC_TC_4 0x4
+#define OEM_CFG_FUNC_TC_5 0x5
+#define OEM_CFG_FUNC_TC_6 0x6
+#define OEM_CFG_FUNC_TC_7 0x7
+
+#define OEM_CFG_FUNC_HOST_PRI_CTRL_MASK 0x00000030
+#define OEM_CFG_FUNC_HOST_PRI_CTRL_OFFSET 4
+#define OEM_CFG_FUNC_HOST_PRI_CTRL_VNIC 0x1
+#define OEM_CFG_FUNC_HOST_PRI_CTRL_OS 0x2
};
struct mcp_mac {
MFW_DRV_MSG_BW_UPDATE10,
MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
MFW_DRV_MSG_BW_UPDATE11,
+ MFW_DRV_MSG_OEM_CFG_UPDATE,
MFW_DRV_MSG_MAX
};
void qed_l2_setup(struct qed_hwfn *p_hwfn)
{
- if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
- p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+ if (!QED_IS_L2_PERSONALITY(p_hwfn))
return;
mutex_init(&p_hwfn->p_l2_info->lock);
{
u32 i;
- if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
- p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+ if (!QED_IS_L2_PERSONALITY(p_hwfn))
return;
if (!p_hwfn->p_l2_info)
struct qed_ll2_tx_packet *p_pkt = NULL;
struct qed_ll2_info *p_ll2_conn;
struct qed_ll2_tx_queue *p_tx;
+ unsigned long flags = 0;
dma_addr_t tx_frag;
p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
p_tx = &p_ll2_conn->tx_queue;
+ spin_lock_irqsave(&p_tx->lock, flags);
while (!list_empty(&p_tx->active_descq)) {
p_pkt = list_first_entry(&p_tx->active_descq,
struct qed_ll2_tx_packet, list_entry);
list_del(&p_pkt->list_entry);
b_last_packet = list_empty(&p_tx->active_descq);
list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
+ spin_unlock_irqrestore(&p_tx->lock, flags);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
struct qed_ooo_buffer *p_buffer;
b_last_frag,
b_last_packet);
}
+ spin_lock_irqsave(&p_tx->lock, flags);
}
+ spin_unlock_irqrestore(&p_tx->lock, flags);
}
static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
struct qed_ll2_info *p_ll2_conn = NULL;
struct qed_ll2_rx_packet *p_pkt = NULL;
struct qed_ll2_rx_queue *p_rx;
+ unsigned long flags = 0;
p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
if (!p_ll2_conn)
p_rx = &p_ll2_conn->rx_queue;
+ spin_lock_irqsave(&p_rx->lock, flags);
while (!list_empty(&p_rx->active_descq)) {
p_pkt = list_first_entry(&p_rx->active_descq,
struct qed_ll2_rx_packet, list_entry);
if (!p_pkt)
break;
-
list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
+ spin_unlock_irqrestore(&p_rx->lock, flags);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
struct qed_ooo_buffer *p_buffer;
cookie,
rx_buf_addr, b_last);
}
+ spin_lock_irqsave(&p_rx->lock, flags);
}
+ spin_unlock_irqrestore(&p_rx->lock, flags);
+}
+
+static bool
+qed_ll2_lb_rxq_handler_slowpath(struct qed_hwfn *p_hwfn,
+ struct core_rx_slow_path_cqe *p_cqe)
+{
+ struct ooo_opaque *iscsi_ooo;
+ u32 cid;
+
+ if (p_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH)
+ return false;
+
+ iscsi_ooo = (struct ooo_opaque *)&p_cqe->opaque_data;
+ if (iscsi_ooo->ooo_opcode != TCP_EVENT_DELETE_ISLES)
+ return false;
+
+ /* Need to make a flush */
+ cid = le32_to_cpu(iscsi_ooo->cid);
+ qed_ooo_release_connection_isles(p_hwfn, p_hwfn->p_ooo_info, cid);
+
+ return true;
}
static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn,
cq_old_idx = qed_chain_get_cons_idx(&p_rx->rcq_chain);
cqe_type = cqe->rx_cqe_sp.type;
+ if (cqe_type == CORE_RX_CQE_TYPE_SLOW_PATH)
+ if (qed_ll2_lb_rxq_handler_slowpath(p_hwfn,
+ &cqe->rx_cqe_sp))
+ continue;
+
if (cqe_type != CORE_RX_CQE_TYPE_REGULAR) {
DP_NOTICE(p_hwfn,
"Got a non-regular LB LL2 completion [type 0x%02x]\n",
struct qed_ll2_info *p_ll2_conn = (struct qed_ll2_info *)p_cookie;
int rc;
+ if (!QED_LL2_RX_REGISTERED(p_ll2_conn))
+ return 0;
+
rc = qed_ll2_lb_rxq_handler(p_hwfn, p_ll2_conn);
if (rc)
return rc;
u16 new_idx = 0, num_bds = 0;
int rc;
+ if (!QED_LL2_TX_REGISTERED(p_ll2_conn))
+ return 0;
+
new_idx = le16_to_cpu(*p_tx->p_fw_cons);
num_bds = ((s16)new_idx - (s16)p_tx->bds_idx);
p_ramrod->drop_ttl0_flg = p_ll2_conn->input.rx_drop_ttl0_flg;
p_ramrod->inner_vlan_stripping_en =
p_ll2_conn->input.rx_vlan_removal_en;
+
+ if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) &&
+ p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE)
+ p_ramrod->report_outer_vlan = 1;
p_ramrod->queue_id = p_ll2_conn->queue_id;
p_ramrod->main_func_queue = p_ll2_conn->main_func_queue ? 1 : 0;
- if ((IS_MF_DEFAULT(p_hwfn) || IS_MF_SI(p_hwfn)) &&
- p_ramrod->main_func_queue && (conn_type != QED_LL2_TYPE_ROCE) &&
- (conn_type != QED_LL2_TYPE_IWARP)) {
+ if (test_bit(QED_MF_LL2_NON_UNICAST, &p_hwfn->cdev->mf_bits) &&
+ p_ramrod->main_func_queue && conn_type != QED_LL2_TYPE_ROCE &&
+ conn_type != QED_LL2_TYPE_IWARP) {
p_ramrod->mf_si_bcast_accept_all = 1;
p_ramrod->mf_si_mcast_accept_all = 1;
} else {
qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) {
+ if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+ qed_llh_add_protocol_filter(p_hwfn, p_ptt,
+ ETH_P_FCOE, 0,
+ QED_LLH_FILTER_ETHERTYPE);
qed_llh_add_protocol_filter(p_hwfn, p_ptt,
- 0x8906, 0,
- QED_LLH_FILTER_ETHERTYPE);
- qed_llh_add_protocol_filter(p_hwfn, p_ptt,
- 0x8914, 0,
+ ETH_P_FIP, 0,
QED_LLH_FILTER_ETHERTYPE);
}
start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
if (QED_IS_IWARP_PERSONALITY(p_hwfn) &&
- p_ll2->input.conn_type == QED_LL2_TYPE_OOO)
+ p_ll2->input.conn_type == QED_LL2_TYPE_OOO) {
start_bd->nw_vlan_or_lb_echo =
cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE);
- else
+ } else {
start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan);
+ if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) &&
+ p_ll2->input.conn_type == QED_LL2_TYPE_FCOE)
+ pkt->remove_stag = true;
+ }
+
SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
cpu_to_le16(pkt->l4_hdr_offset_w));
SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_CSUM, !!(pkt->enable_ip_cksum));
SET_FIELD(bd_data, CORE_TX_BD_DATA_L4_CSUM, !!(pkt->enable_l4_cksum));
SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_LEN, !!(pkt->calc_ip_len));
+ SET_FIELD(bd_data, CORE_TX_BD_DATA_DISABLE_STAG_INSERTION,
+ !!(pkt->remove_stag));
+
start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data);
DMA_REGPAIR_LE(start_bd->addr, pkt->first_frag);
start_bd->nbytes = cpu_to_le16(pkt->first_frag_len);
/* Stop Tx & Rx of connection, if needed */
if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
+ p_ll2_conn->tx_queue.b_cb_registred = false;
+ smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
goto out;
+
qed_ll2_txq_flush(p_hwfn, connection_handle);
+ qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
}
if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
+ p_ll2_conn->rx_queue.b_cb_registred = false;
+ smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
goto out;
+
qed_ll2_rxq_flush(p_hwfn, connection_handle);
+ qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
}
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO)
qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) {
+ if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+ qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
+ ETH_P_FCOE, 0,
+ QED_LLH_FILTER_ETHERTYPE);
qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
- 0x8906, 0,
- QED_LLH_FILTER_ETHERTYPE);
- qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
- 0x8914, 0,
+ ETH_P_FIP, 0,
QED_LLH_FILTER_ETHERTYPE);
}
if (!p_ll2_conn)
return;
- if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
- p_ll2_conn->rx_queue.b_cb_registred = false;
- qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
- }
-
- if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
- p_ll2_conn->tx_queue.b_cb_registred = false;
- qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
- }
-
kfree(p_ll2_conn->tx_queue.descq_mem);
qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain);
return -EINVAL;
}
-static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
+static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
+ unsigned long xmit_flags)
{
struct qed_ll2_tx_pkt_info pkt;
const skb_frag_t *frag;
u8 flags = 0;
if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
- DP_INFO(cdev, "Cannot transmit a checksumed packet\n");
+ DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
return -EINVAL;
}
pkt.first_frag = mapping;
pkt.first_frag_len = skb->len;
pkt.cookie = skb;
+ if (test_bit(QED_MF_UFP_SPECIFIC, &cdev->mf_bits) &&
+ test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags))
+ pkt.remove_stag = true;
rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle,
&pkt, 1);
dev_info->pci_mem_end = cdev->pci_params.mem_end;
dev_info->pci_irq = cdev->pci_params.irq;
dev_info->rdma_supported = QED_IS_RDMA_PERSONALITY(p_hwfn);
- dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]);
dev_info->dev_type = cdev->type;
ether_addr_copy(dev_info->hw_mac, hw_info->hw_mac_addr);
dev_info->fw_minor = FW_MINOR_VERSION;
dev_info->fw_rev = FW_REVISION_VERSION;
dev_info->fw_eng = FW_ENGINEERING_VERSION;
- dev_info->mf_mode = cdev->mf_mode;
+ dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH,
+ &cdev->mf_bits);
dev_info->tx_switching = true;
if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME)
tasklet_disable(p_hwfn->sp_dpc);
p_hwfn->b_sp_dpc_enabled = false;
DP_VERBOSE(cdev, NETIF_MSG_IFDOWN,
- "Disabled sp taskelt [hwfn %d] at %p\n",
+ "Disabled sp tasklet [hwfn %d] at %p\n",
i, p_hwfn->sp_dpc);
}
}
#include <linux/string.h>
#include <linux/etherdevice.h>
#include "qed.h"
+#include "qed_cxt.h"
#include "qed_dcbx.h"
#include "qed_hsi.h"
#include "qed_hw.h"
&resp, ¶m);
}
+void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ struct public_func shmem_info;
+ u32 port_cfg, val;
+
+ if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+ return;
+
+ memset(&p_hwfn->ufp_info, 0, sizeof(p_hwfn->ufp_info));
+ port_cfg = qed_rd(p_hwfn, p_ptt, p_hwfn->mcp_info->port_addr +
+ offsetof(struct public_port, oem_cfg_port));
+ val = (port_cfg & OEM_CFG_CHANNEL_TYPE_MASK) >>
+ OEM_CFG_CHANNEL_TYPE_OFFSET;
+ if (val != OEM_CFG_CHANNEL_TYPE_STAGGED)
+ DP_NOTICE(p_hwfn, "Incorrect UFP Channel type %d\n", val);
+
+ val = (port_cfg & OEM_CFG_SCHED_TYPE_MASK) >> OEM_CFG_SCHED_TYPE_OFFSET;
+ if (val == OEM_CFG_SCHED_TYPE_ETS) {
+ p_hwfn->ufp_info.mode = QED_UFP_MODE_ETS;
+ } else if (val == OEM_CFG_SCHED_TYPE_VNIC_BW) {
+ p_hwfn->ufp_info.mode = QED_UFP_MODE_VNIC_BW;
+ } else {
+ p_hwfn->ufp_info.mode = QED_UFP_MODE_UNKNOWN;
+ DP_NOTICE(p_hwfn, "Unknown UFP scheduling mode %d\n", val);
+ }
+
+ qed_mcp_get_shmem_func(p_hwfn, p_ptt, &shmem_info, MCP_PF_ID(p_hwfn));
+ val = (port_cfg & OEM_CFG_FUNC_TC_MASK) >> OEM_CFG_FUNC_TC_OFFSET;
+ p_hwfn->ufp_info.tc = (u8)val;
+ val = (port_cfg & OEM_CFG_FUNC_HOST_PRI_CTRL_MASK) >>
+ OEM_CFG_FUNC_HOST_PRI_CTRL_OFFSET;
+ if (val == OEM_CFG_FUNC_HOST_PRI_CTRL_VNIC) {
+ p_hwfn->ufp_info.pri_type = QED_UFP_PRI_VNIC;
+ } else if (val == OEM_CFG_FUNC_HOST_PRI_CTRL_OS) {
+ p_hwfn->ufp_info.pri_type = QED_UFP_PRI_OS;
+ } else {
+ p_hwfn->ufp_info.pri_type = QED_UFP_PRI_UNKNOWN;
+ DP_NOTICE(p_hwfn, "Unknown Host priority control %d\n", val);
+ }
+
+ DP_NOTICE(p_hwfn,
+ "UFP shmem config: mode = %d tc = %d pri_type = %d\n",
+ p_hwfn->ufp_info.mode,
+ p_hwfn->ufp_info.tc, p_hwfn->ufp_info.pri_type);
+}
+
+static int
+qed_mcp_handle_ufp_event(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ qed_mcp_read_ufp_config(p_hwfn, p_ptt);
+
+ if (p_hwfn->ufp_info.mode == QED_UFP_MODE_VNIC_BW) {
+ p_hwfn->qm_info.ooo_tc = p_hwfn->ufp_info.tc;
+ p_hwfn->hw_info.offload_tc = p_hwfn->ufp_info.tc;
+
+ qed_qm_reconf(p_hwfn, p_ptt);
+ } else if (p_hwfn->ufp_info.mode == QED_UFP_MODE_ETS) {
+ /* Merge UFP TC with the dcbx TC data */
+ qed_dcbx_mib_update_event(p_hwfn, p_ptt,
+ QED_DCBX_OPERATIONAL_MIB);
+ } else {
+ DP_ERR(p_hwfn, "Invalid sched type, discard the UFP config\n");
+ return -EINVAL;
+ }
+
+ /* update storm FW with negotiation results */
+ qed_sp_pf_update_ufp(p_hwfn);
+
+ /* update stag pcp value */
+ qed_sp_pf_update_stag(p_hwfn);
+
+ return 0;
+}
+
int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt)
{
qed_dcbx_mib_update_event(p_hwfn, p_ptt,
QED_DCBX_OPERATIONAL_MIB);
break;
+ case MFW_DRV_MSG_OEM_CFG_UPDATE:
+ qed_mcp_handle_ufp_event(p_hwfn, p_ptt);
+ break;
case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE:
qed_mcp_handle_transceiver_change(p_hwfn, p_ptt);
break;
*/
int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+/**
+ * @brief Read ufp config from the shared memory.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ */
+void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
/**
* @brief Populate the nvm info shadow in the given hardware function
*
if (!(qp->resp_offloaded)) {
DP_NOTICE(p_hwfn,
- "The responder's qp should be offloded before requester's\n");
+ "The responder's qp should be offloaded before requester's\n");
return -EINVAL;
}
* @param p_hwfn
* @param p_ptt
* @param p_tunn
- * @param mode
* @param allow_npar_tx_switch
*
* @return int
int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_tunnel_info *p_tunn,
- enum qed_mf_mode mode, bool allow_npar_tx_switch);
+ bool allow_npar_tx_switch);
/**
* @brief qed_sp_pf_update - PF Function Update Ramrod
* @return int
*/
+/**
+ * @brief qed_sp_pf_update_ufp - PF ufp update Ramrod
+ *
+ * @param p_hwfn
+ *
+ * @return int
+ */
+int qed_sp_pf_update_ufp(struct qed_hwfn *p_hwfn);
+
int qed_sp_pf_stop(struct qed_hwfn *p_hwfn);
int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
int qed_sp_pf_start(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_tunnel_info *p_tunn,
- enum qed_mf_mode mode, bool allow_npar_tx_switch)
+ bool allow_npar_tx_switch)
{
struct pf_start_ramrod_data *p_ramrod = NULL;
u16 sb = qed_int_get_sp_sb_id(p_hwfn);
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
int rc = -EINVAL;
- u8 page_cnt;
+ u8 page_cnt, i;
/* update initial eq producer */
qed_eq_prod_update(p_hwfn,
p_ramrod->dont_log_ramrods = 0;
p_ramrod->log_type_mask = cpu_to_le16(0xf);
- switch (mode) {
- case QED_MF_DEFAULT:
- case QED_MF_NPAR:
- p_ramrod->mf_mode = MF_NPAR;
- break;
- case QED_MF_OVLAN:
+ if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits))
p_ramrod->mf_mode = MF_OVLAN;
- break;
- default:
- DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n");
+ else
p_ramrod->mf_mode = MF_NPAR;
- }
p_ramrod->outer_tag_config.outer_tag.tci =
- cpu_to_le16(p_hwfn->hw_info.ovlan);
+ cpu_to_le16(p_hwfn->hw_info.ovlan);
+ if (test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits)) {
+ p_ramrod->outer_tag_config.outer_tag.tpid = ETH_P_8021Q;
+ } else if (test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits)) {
+ p_ramrod->outer_tag_config.outer_tag.tpid = ETH_P_8021AD;
+ p_ramrod->outer_tag_config.enable_stag_pri_change = 1;
+ }
+
+ p_ramrod->outer_tag_config.pri_map_valid = 1;
+ for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+ p_ramrod->outer_tag_config.inner_to_outer_pri_map[i] = i;
+
+ /* enable_stag_pri_change should be set if port is in BD mode or,
+ * UFP with Host Control mode.
+ */
+ if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) {
+ if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_OS)
+ p_ramrod->outer_tag_config.enable_stag_pri_change = 1;
+ else
+ p_ramrod->outer_tag_config.enable_stag_pri_change = 0;
+
+ p_ramrod->outer_tag_config.outer_tag.tci |=
+ cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13));
+ }
/* Place EQ address in RAMROD */
DMA_REGPAIR_LE(p_ramrod->event_ring_pbl_addr,
qed_tunn_set_pf_start_params(p_hwfn, p_tunn, &p_ramrod->tunnel_config);
- if (IS_MF_SI(p_hwfn))
+ if (test_bit(QED_MF_INTER_PF_SWITCH, &p_hwfn->cdev->mf_bits))
p_ramrod->allow_npar_tx_switching = allow_npar_tx_switch;
switch (p_hwfn->hw_info.personality) {
return qed_spq_post(p_hwfn, p_ent, NULL);
}
+int qed_sp_pf_update_ufp(struct qed_hwfn *p_hwfn)
+{
+ struct qed_spq_entry *p_ent = NULL;
+ struct qed_sp_init_data init_data;
+ int rc = -EOPNOTSUPP;
+
+ if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_UNKNOWN) {
+ DP_INFO(p_hwfn, "Invalid priority type %d\n",
+ p_hwfn->ufp_info.pri_type);
+ return -EINVAL;
+ }
+
+ /* Get SPQ entry */
+ memset(&init_data, 0, sizeof(init_data));
+ init_data.cid = qed_spq_get_cid(p_hwfn);
+ init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
+ init_data.comp_mode = QED_SPQ_MODE_CB;
+
+ rc = qed_sp_init_request(p_hwfn, &p_ent,
+ COMMON_RAMROD_PF_UPDATE, PROTOCOLID_COMMON,
+ &init_data);
+ if (rc)
+ return rc;
+
+ p_ent->ramrod.pf_update.update_enable_stag_pri_change = true;
+ if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_OS)
+ p_ent->ramrod.pf_update.enable_stag_pri_change = 1;
+ else
+ p_ent->ramrod.pf_update.enable_stag_pri_change = 0;
+
+ return qed_spq_post(p_hwfn, p_ent, NULL);
+}
+
/* Set pf update ramrod command params */
int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
* aggregation.
*/
struct sw_rx_data buffer;
- dma_addr_t buffer_mapping;
-
struct sk_buff *skb;
/* We need some structs from the start cookie until termination */
u16 vlan_tag;
- u16 start_cqe_bd_len;
- u8 start_cqe_placement_offset;
+ bool tpa_start_fail;
u8 state;
u8 frag_id;
len = le16_to_cpu(fp_cqe->len_on_first_bd);
data_ptr = (u8 *)(page_address(sw_rx_data->data) +
fp_cqe->placement_offset +
- sw_rx_data->page_offset);
+ sw_rx_data->page_offset +
+ rxq->rx_headroom);
if (ether_addr_equal(data_ptr, edev->ndev->dev_addr) &&
ether_addr_equal(data_ptr + ETH_ALEN,
edev->ndev->dev_addr)) {
/* Add one frag and update the appropriate fields in the skb */
skb_fill_page_desc(skb, tpa_info->frag_id++,
- current_bd->data, current_bd->page_offset,
+ current_bd->data,
+ current_bd->page_offset + rxq->rx_headroom,
len_on_bd);
if (unlikely(qede_realloc_rx_buffer(rxq, current_bd))) {
goto out;
}
- qed_chain_consume(&rxq->rx_bd_ring);
- rxq->sw_rx_cons++;
+ qede_rx_bd_ring_consume(rxq);
skb->data_len += len_on_bd;
skb->truesize += rxq->rx_buf_seg_size;
return QEDE_CSUM_UNNECESSARY | tcsum;
}
+static inline struct sk_buff *
+qede_build_skb(struct qede_rx_queue *rxq,
+ struct sw_rx_data *bd, u16 len, u16 pad)
+{
+ struct sk_buff *skb;
+ void *buf;
+
+ buf = page_address(bd->data) + bd->page_offset;
+ skb = build_skb(buf, rxq->rx_buf_seg_size);
+
+ skb_reserve(skb, pad);
+ skb_put(skb, len);
+
+ return skb;
+}
+
+static struct sk_buff *
+qede_tpa_rx_build_skb(struct qede_dev *edev,
+ struct qede_rx_queue *rxq,
+ struct sw_rx_data *bd, u16 len, u16 pad,
+ bool alloc_skb)
+{
+ struct sk_buff *skb;
+
+ skb = qede_build_skb(rxq, bd, len, pad);
+ bd->page_offset += rxq->rx_buf_seg_size;
+
+ if (bd->page_offset == PAGE_SIZE) {
+ if (unlikely(qede_alloc_rx_buffer(rxq, true))) {
+ DP_NOTICE(edev,
+ "Failed to allocate RX buffer for tpa start\n");
+ bd->page_offset -= rxq->rx_buf_seg_size;
+ page_ref_inc(bd->data);
+ dev_kfree_skb_any(skb);
+ return NULL;
+ }
+ } else {
+ page_ref_inc(bd->data);
+ qede_reuse_page(rxq, bd);
+ }
+
+ /* We've consumed the first BD and prepared an SKB */
+ qede_rx_bd_ring_consume(rxq);
+
+ return skb;
+}
+
+static struct sk_buff *
+qede_rx_build_skb(struct qede_dev *edev,
+ struct qede_rx_queue *rxq,
+ struct sw_rx_data *bd, u16 len, u16 pad)
+{
+ struct sk_buff *skb = NULL;
+
+ /* For smaller frames still need to allocate skb, memcpy
+ * data and benefit in reusing the page segment instead of
+ * un-mapping it.
+ */
+ if ((len + pad <= edev->rx_copybreak)) {
+ unsigned int offset = bd->page_offset + pad;
+
+ skb = netdev_alloc_skb(edev->ndev, QEDE_RX_HDR_SIZE);
+ if (unlikely(!skb))
+ return NULL;
+
+ skb_reserve(skb, pad);
+ memcpy(skb_put(skb, len),
+ page_address(bd->data) + offset, len);
+ qede_reuse_page(rxq, bd);
+ goto out;
+ }
+
+ skb = qede_build_skb(rxq, bd, len, pad);
+
+ if (unlikely(qede_realloc_rx_buffer(rxq, bd))) {
+ /* Incr page ref count to reuse on allocation failure so
+ * that it doesn't get freed while freeing SKB [as its
+ * already mapped there].
+ */
+ page_ref_inc(bd->data);
+ dev_kfree_skb_any(skb);
+ return NULL;
+ }
+out:
+ /* We've consumed the first BD and prepared an SKB */
+ qede_rx_bd_ring_consume(rxq);
+
+ return skb;
+}
+
static void qede_tpa_start(struct qede_dev *edev,
struct qede_rx_queue *rxq,
struct eth_fast_path_rx_tpa_start_cqe *cqe)
{
struct qede_agg_info *tpa_info = &rxq->tpa_info[cqe->tpa_agg_index];
- struct eth_rx_bd *rx_bd_cons = qed_chain_consume(&rxq->rx_bd_ring);
- struct eth_rx_bd *rx_bd_prod = qed_chain_produce(&rxq->rx_bd_ring);
- struct sw_rx_data *replace_buf = &tpa_info->buffer;
- dma_addr_t mapping = tpa_info->buffer_mapping;
struct sw_rx_data *sw_rx_data_cons;
- struct sw_rx_data *sw_rx_data_prod;
+ u16 pad;
sw_rx_data_cons = &rxq->sw_rx_ring[rxq->sw_rx_cons & NUM_RX_BDS_MAX];
- sw_rx_data_prod = &rxq->sw_rx_ring[rxq->sw_rx_prod & NUM_RX_BDS_MAX];
+ pad = cqe->placement_offset + rxq->rx_headroom;
- /* Use pre-allocated replacement buffer - we can't release the agg.
- * start until its over and we don't want to risk allocation failing
- * here, so re-allocate when aggregation will be over.
- */
- sw_rx_data_prod->mapping = replace_buf->mapping;
-
- sw_rx_data_prod->data = replace_buf->data;
- rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(mapping));
- rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(mapping));
- sw_rx_data_prod->page_offset = replace_buf->page_offset;
-
- rxq->sw_rx_prod++;
+ tpa_info->skb = qede_tpa_rx_build_skb(edev, rxq, sw_rx_data_cons,
+ le16_to_cpu(cqe->len_on_first_bd),
+ pad, false);
+ tpa_info->buffer.page_offset = sw_rx_data_cons->page_offset;
+ tpa_info->buffer.mapping = sw_rx_data_cons->mapping;
- /* move partial skb from cons to pool (don't unmap yet)
- * save mapping, incase we drop the packet later on.
- */
- tpa_info->buffer = *sw_rx_data_cons;
- mapping = HILO_U64(le32_to_cpu(rx_bd_cons->addr.hi),
- le32_to_cpu(rx_bd_cons->addr.lo));
-
- tpa_info->buffer_mapping = mapping;
- rxq->sw_rx_cons++;
-
- /* set tpa state to start only if we are able to allocate skb
- * for this aggregation, otherwise mark as error and aggregation will
- * be dropped
- */
- tpa_info->skb = netdev_alloc_skb(edev->ndev,
- le16_to_cpu(cqe->len_on_first_bd));
if (unlikely(!tpa_info->skb)) {
DP_NOTICE(edev, "Failed to allocate SKB for gro\n");
+
+ /* Consume from ring but do not produce since
+ * this might be used by FW still, it will be re-used
+ * at TPA end.
+ */
+ tpa_info->tpa_start_fail = true;
+ qede_rx_bd_ring_consume(rxq);
tpa_info->state = QEDE_AGG_STATE_ERROR;
goto cons_buf;
}
- /* Start filling in the aggregation info */
- skb_put(tpa_info->skb, le16_to_cpu(cqe->len_on_first_bd));
tpa_info->frag_id = 0;
tpa_info->state = QEDE_AGG_STATE_START;
- /* Store some information from first CQE */
- tpa_info->start_cqe_placement_offset = cqe->placement_offset;
- tpa_info->start_cqe_bd_len = le16_to_cpu(cqe->len_on_first_bd);
if ((le16_to_cpu(cqe->pars_flags.flags) >>
PARSING_AND_ERR_FLAGS_TAG8021QEXIST_SHIFT) &
PARSING_AND_ERR_FLAGS_TAG8021QEXIST_MASK)
tpa_info = &rxq->tpa_info[cqe->tpa_agg_index];
skb = tpa_info->skb;
+ if (tpa_info->buffer.page_offset == PAGE_SIZE)
+ dma_unmap_page(rxq->dev, tpa_info->buffer.mapping,
+ PAGE_SIZE, rxq->data_direction);
+
for (i = 0; cqe->len_list[i]; i++)
qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index,
le16_to_cpu(cqe->len_list[i]));
"Strange - total packet len [cqe] is %4x but SKB has len %04x\n",
le16_to_cpu(cqe->total_packet_len), skb->len);
- memcpy(skb->data,
- page_address(tpa_info->buffer.data) +
- tpa_info->start_cqe_placement_offset +
- tpa_info->buffer.page_offset, tpa_info->start_cqe_bd_len);
-
/* Finalize the SKB */
skb->protocol = eth_type_trans(skb, edev->ndev);
skb->ip_summed = CHECKSUM_UNNECESSARY;
return 1;
err:
tpa_info->state = QEDE_AGG_STATE_NONE;
+
+ if (tpa_info->tpa_start_fail) {
+ qede_reuse_page(rxq, &tpa_info->buffer);
+ tpa_info->tpa_start_fail = false;
+ }
+
dev_kfree_skb_any(tpa_info->skb);
tpa_info->skb = NULL;
return 0;
return false;
}
-static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
- struct qede_rx_queue *rxq,
- struct sw_rx_data *bd, u16 len,
- u16 pad)
-{
- unsigned int offset = bd->page_offset + pad;
- struct skb_frag_struct *frag;
- struct page *page = bd->data;
- unsigned int pull_len;
- struct sk_buff *skb;
- unsigned char *va;
-
- /* Allocate a new SKB with a sufficient large header len */
- skb = netdev_alloc_skb(edev->ndev, QEDE_RX_HDR_SIZE);
- if (unlikely(!skb))
- return NULL;
-
- /* Copy data into SKB - if it's small, we can simply copy it and
- * re-use the already allcoated & mapped memory.
- */
- if (len + pad <= edev->rx_copybreak) {
- skb_put_data(skb, page_address(page) + offset, len);
- qede_reuse_page(rxq, bd);
- goto out;
- }
-
- frag = &skb_shinfo(skb)->frags[0];
-
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- page, offset, len, rxq->rx_buf_seg_size);
-
- va = skb_frag_address(frag);
- pull_len = eth_get_headlen(va, QEDE_RX_HDR_SIZE);
-
- /* Align the pull_len to optimize memcpy */
- memcpy(skb->data, va, ALIGN(pull_len, sizeof(long)));
-
- /* Correct the skb & frag sizes offset after the pull */
- skb_frag_size_sub(frag, pull_len);
- frag->page_offset += pull_len;
- skb->data_len -= pull_len;
- skb->tail += pull_len;
-
- if (unlikely(qede_realloc_rx_buffer(rxq, bd))) {
- /* Incr page ref count to reuse on allocation failure so
- * that it doesn't get freed while freeing SKB [as its
- * already mapped there].
- */
- page_ref_inc(page);
- dev_kfree_skb_any(skb);
- return NULL;
- }
-
-out:
- /* We've consumed the first BD and prepared an SKB */
- qede_rx_bd_ring_consume(rxq);
- return skb;
-}
-
static int qede_rx_build_jumbo(struct qede_dev *edev,
struct qede_rx_queue *rxq,
struct sk_buff *skb,
PAGE_SIZE, DMA_FROM_DEVICE);
skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags++,
- bd->data, 0, cur_size);
+ bd->data, rxq->rx_headroom, cur_size);
skb->truesize += PAGE_SIZE;
skb->data_len += cur_size;
/* Basic validation passed; Need to prepare an SKB. This would also
* guarantee to finally consume the first BD upon success.
*/
- skb = qede_rx_allocate_skb(edev, rxq, bd, len, pad);
+ skb = qede_rx_build_skb(edev, rxq, bd, len, pad);
if (!skb) {
rxq->rx_alloc_errors++;
qede_recycle_rx_bd_ring(rxq, fp_cqe->bd_num);
/* Enable/Disable Tx switching for PF */
if ((rc == num_vfs_param) && netif_running(edev->ndev) &&
- qed_info->mf_mode != QED_MF_NPAR && qed_info->tx_switching) {
+ !qed_info->b_inter_pf_switch && qed_info->tx_switching) {
vport_params->vport_id = 0;
vport_params->update_tx_switching_flg = 1;
vport_params->tx_switching_flg = num_vfs_param ? 1 : 0;
DP_INFO(edev, "Starting qede_remove\n");
+ qede_rdma_dev_remove(edev);
unregister_netdev(ndev);
cancel_delayed_work_sync(&edev->sp_task);
qede_ptp_disable(edev);
- qede_rdma_dev_remove(edev);
-
edev->ops->common->set_power_state(cdev, PCI_D0);
pci_set_drvdata(pdev, NULL);
}
}
-static void qede_free_sge_mem(struct qede_dev *edev, struct qede_rx_queue *rxq)
-{
- int i;
-
- if (edev->gro_disable)
- return;
-
- for (i = 0; i < ETH_TPA_MAX_AGGS_NUM; i++) {
- struct qede_agg_info *tpa_info = &rxq->tpa_info[i];
- struct sw_rx_data *replace_buf = &tpa_info->buffer;
-
- if (replace_buf->data) {
- dma_unmap_page(&edev->pdev->dev,
- replace_buf->mapping,
- PAGE_SIZE, DMA_FROM_DEVICE);
- __free_page(replace_buf->data);
- }
- }
-}
-
static void qede_free_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
{
- qede_free_sge_mem(edev, rxq);
-
/* Free rx buffers */
qede_free_rx_buffers(edev, rxq);
edev->ops->common->chain_free(edev->cdev, &rxq->rx_comp_ring);
}
-static int qede_alloc_sge_mem(struct qede_dev *edev, struct qede_rx_queue *rxq)
+static void qede_set_tpa_param(struct qede_rx_queue *rxq)
{
- dma_addr_t mapping;
int i;
- if (edev->gro_disable)
- return 0;
-
for (i = 0; i < ETH_TPA_MAX_AGGS_NUM; i++) {
struct qede_agg_info *tpa_info = &rxq->tpa_info[i];
- struct sw_rx_data *replace_buf = &tpa_info->buffer;
- replace_buf->data = alloc_pages(GFP_ATOMIC, 0);
- if (unlikely(!replace_buf->data)) {
- DP_NOTICE(edev,
- "Failed to allocate TPA skb pool [replacement buffer]\n");
- goto err;
- }
-
- mapping = dma_map_page(&edev->pdev->dev, replace_buf->data, 0,
- PAGE_SIZE, DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) {
- DP_NOTICE(edev,
- "Failed to map TPA replacement buffer\n");
- goto err;
- }
-
- replace_buf->mapping = mapping;
- tpa_info->buffer.page_offset = 0;
- tpa_info->buffer_mapping = mapping;
tpa_info->state = QEDE_AGG_STATE_NONE;
}
-
- return 0;
-err:
- qede_free_sge_mem(edev, rxq);
- edev->gro_disable = 1;
- edev->ndev->features &= ~NETIF_F_GRO_HW;
- return -ENOMEM;
}
/* This function allocates all memory needed per Rx queue */
rxq->num_rx_buffers = edev->q_num_rx_buffers;
rxq->rx_buf_size = NET_IP_ALIGN + ETH_OVERHEAD + edev->ndev->mtu;
- rxq->rx_headroom = edev->xdp_prog ? XDP_PACKET_HEADROOM : 0;
+
+ rxq->rx_headroom = edev->xdp_prog ? XDP_PACKET_HEADROOM : NET_SKB_PAD;
+ size = rxq->rx_headroom +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
/* Make sure that the headroom and payload fit in a single page */
- if (rxq->rx_buf_size + rxq->rx_headroom > PAGE_SIZE)
- rxq->rx_buf_size = PAGE_SIZE - rxq->rx_headroom;
+ if (rxq->rx_buf_size + size > PAGE_SIZE)
+ rxq->rx_buf_size = PAGE_SIZE - size;
- /* Segment size to spilt a page in multiple equal parts,
+ /* Segment size to spilt a page in multiple equal parts ,
* unless XDP is used in which case we'd use the entire page.
*/
- if (!edev->xdp_prog)
- rxq->rx_buf_seg_size = roundup_pow_of_two(rxq->rx_buf_size);
- else
+ if (!edev->xdp_prog) {
+ size = size + rxq->rx_buf_size;
+ rxq->rx_buf_seg_size = roundup_pow_of_two(size);
+ } else {
rxq->rx_buf_seg_size = PAGE_SIZE;
+ }
/* Allocate the parallel driver ring for Rx buffers */
size = sizeof(*rxq->sw_rx_ring) * RX_RING_SIZE;
}
}
- rc = qede_alloc_sge_mem(edev, rxq);
+ if (!edev->gro_disable)
+ qede_set_tpa_param(rxq);
err:
return rc;
}
vport_update_params->update_vport_active_flg = 1;
vport_update_params->vport_active_flg = 1;
- if ((qed_info->mf_mode == QED_MF_NPAR || pci_num_vf(edev->pdev)) &&
+ if ((qed_info->b_inter_pf_switch || pci_num_vf(edev->pdev)) &&
qed_info->tx_switching) {
vport_update_params->update_tx_switching_flg = 1;
vport_update_params->tx_switching_flg = 1;
}
if (!found) {
- event_node = kzalloc(sizeof(*event_node), GFP_KERNEL);
+ event_node = kzalloc(sizeof(*event_node), GFP_ATOMIC);
if (!event_node) {
DP_NOTICE(edev,
"qedr: Could not allocate memory for rdma work\n");
struct emac_tx_queue *tx_q)
{
struct emac_ring_header *ring_header = &adpt->ring_header;
+ int node = dev_to_node(adpt->netdev->dev.parent);
size_t size;
size = sizeof(struct emac_buffer) * tx_q->tpd.count;
- tx_q->tpd.tpbuff = kzalloc(size, GFP_KERNEL);
+ tx_q->tpd.tpbuff = kzalloc_node(size, GFP_KERNEL, node);
if (!tx_q->tpd.tpbuff)
return -ENOMEM;
static int emac_rx_descs_alloc(struct emac_adapter *adpt)
{
struct emac_ring_header *ring_header = &adpt->ring_header;
+ int node = dev_to_node(adpt->netdev->dev.parent);
struct emac_rx_queue *rx_q = &adpt->rx_q;
size_t size;
size = sizeof(struct emac_buffer) * rx_q->rfd.count;
- rx_q->rfd.rfbuff = kzalloc(size, GFP_KERNEL);
+ rx_q->rfd.rfbuff = kzalloc_node(size, GFP_KERNEL, node);
if (!rx_q->rfd.rfbuff)
return -ENOMEM;
static void emac_adjust_link(struct net_device *netdev)
{
struct emac_adapter *adpt = netdev_priv(netdev);
- struct emac_sgmii *sgmii = &adpt->phy;
struct phy_device *phydev = netdev->phydev;
if (phydev->link) {
emac_mac_start(adpt);
- sgmii->link_up(adpt);
+ emac_sgmii_link_change(adpt, true);
} else {
- sgmii->link_down(adpt);
+ emac_sgmii_link_change(adpt, false);
emac_mac_stop(adpt);
}
#define SERDES_START_WAIT_TIMES 100
+int emac_sgmii_init(struct emac_adapter *adpt)
+{
+ if (!(adpt->phy.sgmii_ops && adpt->phy.sgmii_ops->init))
+ return 0;
+
+ return adpt->phy.sgmii_ops->init(adpt);
+}
+
+int emac_sgmii_open(struct emac_adapter *adpt)
+{
+ if (!(adpt->phy.sgmii_ops && adpt->phy.sgmii_ops->open))
+ return 0;
+
+ return adpt->phy.sgmii_ops->open(adpt);
+}
+
+void emac_sgmii_close(struct emac_adapter *adpt)
+{
+ if (!(adpt->phy.sgmii_ops && adpt->phy.sgmii_ops->close))
+ return;
+
+ adpt->phy.sgmii_ops->close(adpt);
+}
+
+int emac_sgmii_link_change(struct emac_adapter *adpt, bool link_state)
+{
+ if (!(adpt->phy.sgmii_ops && adpt->phy.sgmii_ops->link_change))
+ return 0;
+
+ return adpt->phy.sgmii_ops->link_change(adpt, link_state);
+}
+
+void emac_sgmii_reset(struct emac_adapter *adpt)
+{
+ if (!(adpt->phy.sgmii_ops && adpt->phy.sgmii_ops->reset))
+ return;
+
+ adpt->phy.sgmii_ops->reset(adpt);
+}
+
/* Initialize the SGMII link between the internal and external PHYs. */
static void emac_sgmii_link_init(struct emac_adapter *adpt)
{
msleep(50);
}
-void emac_sgmii_reset(struct emac_adapter *adpt)
+static void emac_sgmii_common_reset(struct emac_adapter *adpt)
{
int ret;
emac_sgmii_reset_prepare(adpt);
emac_sgmii_link_init(adpt);
- ret = adpt->phy.initialize(adpt);
+ ret = emac_sgmii_init(adpt);
if (ret)
netdev_err(adpt->netdev,
"could not reinitialize internal PHY (error=%i)\n",
ret);
}
-static int emac_sgmii_open(struct emac_adapter *adpt)
+static int emac_sgmii_common_open(struct emac_adapter *adpt)
{
struct emac_sgmii *sgmii = &adpt->phy;
int ret;
return 0;
}
-static int emac_sgmii_close(struct emac_adapter *adpt)
+static void emac_sgmii_common_close(struct emac_adapter *adpt)
{
struct emac_sgmii *sgmii = &adpt->phy;
/* Make sure interrupts are disabled */
writel(0, sgmii->base + EMAC_SGMII_PHY_INTERRUPT_MASK);
free_irq(sgmii->irq, adpt);
-
- return 0;
}
/* The error interrupts are only valid after the link is up */
-static int emac_sgmii_link_up(struct emac_adapter *adpt)
+static int emac_sgmii_common_link_change(struct emac_adapter *adpt, bool linkup)
{
struct emac_sgmii *sgmii = &adpt->phy;
int ret;
- /* Clear and enable interrupts */
- ret = emac_sgmii_irq_clear(adpt, 0xff);
- if (ret)
- return ret;
+ if (linkup) {
+ /* Clear and enable interrupts */
+ ret = emac_sgmii_irq_clear(adpt, 0xff);
+ if (ret)
+ return ret;
- writel(SGMII_ISR_MASK, sgmii->base + EMAC_SGMII_PHY_INTERRUPT_MASK);
+ writel(SGMII_ISR_MASK,
+ sgmii->base + EMAC_SGMII_PHY_INTERRUPT_MASK);
+ } else {
+ /* Disable interrupts */
+ writel(0, sgmii->base + EMAC_SGMII_PHY_INTERRUPT_MASK);
+ synchronize_irq(sgmii->irq);
+ }
return 0;
}
-static int emac_sgmii_link_down(struct emac_adapter *adpt)
-{
- struct emac_sgmii *sgmii = &adpt->phy;
-
- /* Disable interrupts */
- writel(0, sgmii->base + EMAC_SGMII_PHY_INTERRUPT_MASK);
- synchronize_irq(sgmii->irq);
+static struct sgmii_ops qdf2432_ops = {
+ .init = emac_sgmii_init_qdf2432,
+ .open = emac_sgmii_common_open,
+ .close = emac_sgmii_common_close,
+ .link_change = emac_sgmii_common_link_change,
+ .reset = emac_sgmii_common_reset,
+};
- return 0;
-}
+static struct sgmii_ops qdf2400_ops = {
+ .init = emac_sgmii_init_qdf2400,
+ .open = emac_sgmii_common_open,
+ .close = emac_sgmii_common_close,
+ .link_change = emac_sgmii_common_link_change,
+ .reset = emac_sgmii_common_reset,
+};
static int emac_sgmii_acpi_match(struct device *dev, void *data)
{
{}
};
const struct acpi_device_id *id = acpi_match_device(match_table, dev);
- emac_sgmii_function *initialize = data;
+ struct sgmii_ops **ops = data;
if (id) {
acpi_handle handle = ACPI_HANDLE(dev);
switch (hrv) {
case 1:
- *initialize = emac_sgmii_init_qdf2432;
+ *ops = &qdf2432_ops;
return 1;
case 2:
- *initialize = emac_sgmii_init_qdf2400;
+ *ops = &qdf2400_ops;
return 1;
}
}
{}
};
-/* Dummy function for systems without an internal PHY. This avoids having
- * to check for NULL pointers before calling the functions.
- */
-static int emac_sgmii_dummy(struct emac_adapter *adpt)
-{
- return 0;
-}
-
int emac_sgmii_config(struct platform_device *pdev, struct emac_adapter *adpt)
{
struct platform_device *sgmii_pdev = NULL;
if (has_acpi_companion(&pdev->dev)) {
struct device *dev;
- dev = device_find_child(&pdev->dev, &phy->initialize,
+ dev = device_find_child(&pdev->dev, &phy->sgmii_ops,
emac_sgmii_acpi_match);
if (!dev) {
dev_warn(&pdev->dev, "cannot find internal phy node\n");
- /* There is typically no internal PHY on emulation
- * systems, so if we can't find the node, assume
- * we are on an emulation system and stub-out
- * support for the internal PHY. These systems only
- * use ACPI.
- */
- phy->open = emac_sgmii_dummy;
- phy->close = emac_sgmii_dummy;
- phy->link_up = emac_sgmii_dummy;
- phy->link_down = emac_sgmii_dummy;
-
return 0;
}
goto error_put_device;
}
- phy->initialize = (emac_sgmii_function)match->data;
+ phy->sgmii_ops->init = match->data;
}
- phy->open = emac_sgmii_open;
- phy->close = emac_sgmii_close;
- phy->link_up = emac_sgmii_link_up;
- phy->link_down = emac_sgmii_link_down;
-
/* Base address is the first address */
res = platform_get_resource(sgmii_pdev, IORESOURCE_MEM, 0);
if (!res) {
}
}
- ret = phy->initialize(adpt);
+ ret = emac_sgmii_init(adpt);
if (ret)
goto error;
struct emac_adapter;
struct platform_device;
-typedef int (*emac_sgmii_function)(struct emac_adapter *adpt);
+/** emac_sgmii - internal emac phy
+ * @init initialization function
+ * @open called when the driver is opened
+ * @close called when the driver is closed
+ * @link_change called when the link state changes
+ */
+struct sgmii_ops {
+ int (*init)(struct emac_adapter *adpt);
+ int (*open)(struct emac_adapter *adpt);
+ void (*close)(struct emac_adapter *adpt);
+ int (*link_change)(struct emac_adapter *adpt, bool link_state);
+ void (*reset)(struct emac_adapter *adpt);
+};
/** emac_sgmii - internal emac phy
* @base base address
* @digital per-lane digital block
* @irq the interrupt number
* @decode_error_count reference count of consecutive decode errors
- * @initialize initialization function
- * @open called when the driver is opened
- * @close called when the driver is closed
- * @link_up called when the link comes up
- * @link_down called when the link comes down
+ * @sgmii_ops sgmii ops
*/
struct emac_sgmii {
void __iomem *base;
void __iomem *digital;
unsigned int irq;
atomic_t decode_error_count;
- emac_sgmii_function initialize;
- emac_sgmii_function open;
- emac_sgmii_function close;
- emac_sgmii_function link_up;
- emac_sgmii_function link_down;
+ struct sgmii_ops *sgmii_ops;
};
int emac_sgmii_config(struct platform_device *pdev, struct emac_adapter *adpt);
-void emac_sgmii_reset(struct emac_adapter *adpt);
int emac_sgmii_init_fsm9900(struct emac_adapter *adpt);
int emac_sgmii_init_qdf2432(struct emac_adapter *adpt);
int emac_sgmii_init_qdf2400(struct emac_adapter *adpt);
+int emac_sgmii_init(struct emac_adapter *adpt);
+int emac_sgmii_open(struct emac_adapter *adpt);
+void emac_sgmii_close(struct emac_adapter *adpt);
+int emac_sgmii_link_change(struct emac_adapter *adpt, bool link_state);
+void emac_sgmii_reset(struct emac_adapter *adpt);
#endif
return ret;
}
- ret = adpt->phy.open(adpt);
+ ret = emac_sgmii_open(adpt);
if (ret) {
emac_mac_rx_tx_rings_free_all(adpt);
free_irq(irq->irq, irq);
if (ret) {
emac_mac_rx_tx_rings_free_all(adpt);
free_irq(irq->irq, irq);
- adpt->phy.close(adpt);
+ emac_sgmii_close(adpt);
return ret;
}
mutex_lock(&adpt->reset_lock);
- adpt->phy.close(adpt);
+ emac_sgmii_close(adpt);
emac_mac_down(adpt);
emac_mac_rx_tx_rings_free_all(adpt);
{
struct net_device *netdev = dev_get_drvdata(&pdev->dev);
struct emac_adapter *adpt = netdev_priv(netdev);
- struct emac_sgmii *sgmii = &adpt->phy;
if (netdev->flags & IFF_UP) {
/* Closing the SGMII turns off its interrupts */
- sgmii->close(adpt);
+ emac_sgmii_close(adpt);
/* Resetting the MAC turns off all DMA and its interrupts */
emac_mac_reset(adpt);
struct u64_stats_sync syncp;
};
+struct rmnet_priv_stats {
+ u64 csum_ok;
+ u64 csum_valid_unset;
+ u64 csum_validation_failed;
+ u64 csum_err_bad_buffer;
+ u64 csum_err_invalid_ip_version;
+ u64 csum_err_invalid_transport;
+ u64 csum_fragmented_pkt;
+ u64 csum_skipped;
+ u64 csum_sw;
+};
+
struct rmnet_priv {
u8 mux_id;
struct net_device *real_dev;
struct rmnet_pcpu_stats __percpu *pcpu_stats;
struct gro_cells gro_cells;
+ struct rmnet_priv_stats stats;
};
struct rmnet_port *rmnet_get_port(struct net_device *real_dev);
if (skb_headroom(skb) < required_headroom) {
if (pskb_expand_head(skb, required_headroom, 0, GFP_KERNEL))
- goto fail;
+ return -ENOMEM;
}
if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV4)
map_header = rmnet_map_add_map_header(skb, additional_header_len, 0);
if (!map_header)
- goto fail;
+ return -ENOMEM;
map_header->mux_id = mux_id;
skb->protocol = htons(ETH_P_MAP);
return 0;
-
-fail:
- kfree_skb(skb);
- return -ENOMEM;
}
static void
mux_id = priv->mux_id;
port = rmnet_get_port(skb->dev);
- if (!port) {
- kfree_skb(skb);
- return;
- }
+ if (!port)
+ goto drop;
if (rmnet_map_egress_handler(skb, port, mux_id, orig_dev))
- return;
+ goto drop;
rmnet_vnd_tx_fixup(skb, orig_dev);
dev_queue_xmit(skb);
+ return;
+
+drop:
+ this_cpu_inc(priv->pcpu_stats->stats.tx_drops);
+ kfree_skb(skb);
}
struct rmnet_map_control_command *cmd;
int xmit_status;
- if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) {
- if (skb->len < sizeof(struct rmnet_map_header) +
- RMNET_MAP_GET_LENGTH(skb) +
- sizeof(struct rmnet_map_dl_csum_trailer)) {
- kfree_skb(skb);
- return;
- }
-
- skb_trim(skb, skb->len -
- sizeof(struct rmnet_map_dl_csum_trailer));
- }
+ if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4)
+ skb_trim(skb,
+ skb->len - sizeof(struct rmnet_map_dl_csum_trailer));
skb->protocol = htons(ETH_P_MAP);
static int
rmnet_map_ipv4_dl_csum_trailer(struct sk_buff *skb,
- struct rmnet_map_dl_csum_trailer *csum_trailer)
+ struct rmnet_map_dl_csum_trailer *csum_trailer,
+ struct rmnet_priv *priv)
{
__sum16 *csum_field, csum_temp, pseudo_csum, hdr_csum, ip_payload_csum;
u16 csum_value, csum_value_final;
ip4h = (struct iphdr *)(skb->data);
if ((ntohs(ip4h->frag_off) & IP_MF) ||
- ((ntohs(ip4h->frag_off) & IP_OFFSET) > 0))
+ ((ntohs(ip4h->frag_off) & IP_OFFSET) > 0)) {
+ priv->stats.csum_fragmented_pkt++;
return -EOPNOTSUPP;
+ }
txporthdr = skb->data + ip4h->ihl * 4;
csum_field = rmnet_map_get_csum_field(ip4h->protocol, txporthdr);
- if (!csum_field)
+ if (!csum_field) {
+ priv->stats.csum_err_invalid_transport++;
return -EPROTONOSUPPORT;
+ }
/* RFC 768 - Skip IPv4 UDP packets where sender checksum field is 0 */
- if (*csum_field == 0 && ip4h->protocol == IPPROTO_UDP)
+ if (*csum_field == 0 && ip4h->protocol == IPPROTO_UDP) {
+ priv->stats.csum_skipped++;
return 0;
+ }
csum_value = ~ntohs(csum_trailer->csum_value);
hdr_csum = ~ip_fast_csum(ip4h, (int)ip4h->ihl);
}
}
- if (csum_value_final == ntohs((__force __be16)*csum_field))
+ if (csum_value_final == ntohs((__force __be16)*csum_field)) {
+ priv->stats.csum_ok++;
return 0;
- else
+ } else {
+ priv->stats.csum_validation_failed++;
return -EINVAL;
+ }
}
#if IS_ENABLED(CONFIG_IPV6)
static int
rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb,
- struct rmnet_map_dl_csum_trailer *csum_trailer)
+ struct rmnet_map_dl_csum_trailer *csum_trailer,
+ struct rmnet_priv *priv)
{
__sum16 *csum_field, ip6_payload_csum, pseudo_csum, csum_temp;
u16 csum_value, csum_value_final;
txporthdr = skb->data + sizeof(struct ipv6hdr);
csum_field = rmnet_map_get_csum_field(ip6h->nexthdr, txporthdr);
- if (!csum_field)
+ if (!csum_field) {
+ priv->stats.csum_err_invalid_transport++;
return -EPROTONOSUPPORT;
+ }
csum_value = ~ntohs(csum_trailer->csum_value);
ip6_hdr_csum = (__force __be16)
}
}
- if (csum_value_final == ntohs((__force __be16)*csum_field))
+ if (csum_value_final == ntohs((__force __be16)*csum_field)) {
+ priv->stats.csum_ok++;
return 0;
- else
+ } else {
+ priv->stats.csum_validation_failed++;
return -EINVAL;
+ }
}
#endif
*/
int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len)
{
+ struct rmnet_priv *priv = netdev_priv(skb->dev);
struct rmnet_map_dl_csum_trailer *csum_trailer;
- if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM)))
+ if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) {
+ priv->stats.csum_sw++;
return -EOPNOTSUPP;
+ }
csum_trailer = (struct rmnet_map_dl_csum_trailer *)(skb->data + len);
- if (!csum_trailer->valid)
+ if (!csum_trailer->valid) {
+ priv->stats.csum_valid_unset++;
return -EINVAL;
+ }
- if (skb->protocol == htons(ETH_P_IP))
- return rmnet_map_ipv4_dl_csum_trailer(skb, csum_trailer);
- else if (skb->protocol == htons(ETH_P_IPV6))
+ if (skb->protocol == htons(ETH_P_IP)) {
+ return rmnet_map_ipv4_dl_csum_trailer(skb, csum_trailer, priv);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
#if IS_ENABLED(CONFIG_IPV6)
- return rmnet_map_ipv6_dl_csum_trailer(skb, csum_trailer);
+ return rmnet_map_ipv6_dl_csum_trailer(skb, csum_trailer, priv);
#else
+ priv->stats.csum_err_invalid_ip_version++;
return -EPROTONOSUPPORT;
#endif
+ } else {
+ priv->stats.csum_err_invalid_ip_version++;
+ return -EPROTONOSUPPORT;
+ }
return 0;
}
void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
struct net_device *orig_dev)
{
+ struct rmnet_priv *priv = netdev_priv(orig_dev);
struct rmnet_map_ul_csum_header *ul_header;
void *iphdr;
rmnet_map_ipv6_ul_csum_header(iphdr, ul_header, skb);
return;
#else
+ priv->stats.csum_err_invalid_ip_version++;
goto sw_csum;
#endif
+ } else {
+ priv->stats.csum_err_invalid_ip_version++;
}
}
ul_header->csum_insert_offset = 0;
ul_header->csum_enabled = 0;
ul_header->udp_ip4_ind = 0;
+
+ priv->stats.csum_sw++;
}
.ndo_get_stats64 = rmnet_get_stats64,
};
+static const char rmnet_gstrings_stats[][ETH_GSTRING_LEN] = {
+ "Checksum ok",
+ "Checksum valid bit not set",
+ "Checksum validation failed",
+ "Checksum error bad buffer",
+ "Checksum error bad ip version",
+ "Checksum error bad transport",
+ "Checksum skipped on ip fragment",
+ "Checksum skipped",
+ "Checksum computed in software",
+};
+
+static void rmnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+ switch (stringset) {
+ case ETH_SS_STATS:
+ memcpy(buf, &rmnet_gstrings_stats,
+ sizeof(rmnet_gstrings_stats));
+ break;
+ }
+}
+
+static int rmnet_get_sset_count(struct net_device *dev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ARRAY_SIZE(rmnet_gstrings_stats);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void rmnet_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct rmnet_priv *priv = netdev_priv(dev);
+ struct rmnet_priv_stats *st = &priv->stats;
+
+ if (!data)
+ return;
+
+ memcpy(data, st, ARRAY_SIZE(rmnet_gstrings_stats) * sizeof(u64));
+}
+
+static const struct ethtool_ops rmnet_ethtool_ops = {
+ .get_ethtool_stats = rmnet_get_ethtool_stats,
+ .get_strings = rmnet_get_strings,
+ .get_sset_count = rmnet_get_sset_count,
+};
+
/* Called by kernel whenever a new rmnet<n> device is created. Sets MTU,
* flags, ARP type, needed headroom, etc...
*/
rmnet_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
rmnet_dev->needs_free_netdev = true;
+ rmnet_dev->ethtool_ops = &rmnet_ethtool_ops;
}
/* Exposed API */
struct rtl8139_private *tp = netdev_priv(dev);
const int irq = tp->pci_dev->irq;
- disable_irq(irq);
+ disable_irq_nosync(irq);
rtl8139_interrupt(irq, dev);
enable_irq(irq);
}
CSIAR = 0x68,
#define CSIAR_FLAG 0x80000000
#define CSIAR_WRITE_CMD 0x80000000
-#define CSIAR_BYTE_ENABLE 0x0f
-#define CSIAR_BYTE_ENABLE_SHIFT 12
-#define CSIAR_ADDR_MASK 0x0fff
-#define CSIAR_FUNC_CARD 0x00000000
-#define CSIAR_FUNC_SDIO 0x00010000
-#define CSIAR_FUNC_NIC 0x00020000
-#define CSIAR_FUNC_NIC2 0x00010000
+#define CSIAR_BYTE_ENABLE 0x0000f000
+#define CSIAR_ADDR_MASK 0x00000fff
PMCH = 0x6f,
EPHYAR = 0x80,
#define EPHYAR_FLAG 0x80000000
RxChkSum = (1 << 5),
PCIDAC = (1 << 4),
PCIMulRW = (1 << 3),
+#define INTT_MASK GENMASK(1, 0)
INTT_0 = 0x0000, // 8168
INTT_1 = 0x0001, // 8168
INTT_2 = 0x0002, // 8168
};
#define RsvdMask 0x3fffc000
+#define CPCMD_QUIRK_MASK (Normal_mode | RxVlan | RxChkSum | INTT_MASK)
struct TxDesc {
__le32 opts1;
int (*read)(struct rtl8169_private *, int);
} mdio_ops;
- struct pll_power_ops {
- void (*down)(struct rtl8169_private *);
- void (*up)(struct rtl8169_private *);
- } pll_power_ops;
-
struct jumbo_ops {
void (*enable)(struct rtl8169_private *);
void (*disable)(struct rtl8169_private *);
} jumbo_ops;
- struct csi_ops {
- void (*write)(struct rtl8169_private *, int, int);
- u32 (*read)(struct rtl8169_private *, int);
- } csi_ops;
-
int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
int (*get_link_ksettings)(struct net_device *,
struct ethtool_link_ksettings *);
if (options & LinkUp)
wolopts |= WAKE_PHY;
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_34:
- case RTL_GIGA_MAC_VER_35:
- case RTL_GIGA_MAC_VER_36:
- case RTL_GIGA_MAC_VER_37:
- case RTL_GIGA_MAC_VER_38:
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2)
wolopts |= WAKE_MAGIC;
break;
RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_34:
- case RTL_GIGA_MAC_VER_35:
- case RTL_GIGA_MAC_VER_36:
- case RTL_GIGA_MAC_VER_37:
- case RTL_GIGA_MAC_VER_38:
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
tmp = ARRAY_SIZE(cfg) - 1;
if (wolopts & WAKE_MAGIC)
rtl_w0w1_eri(tp,
return features;
}
-static void __rtl8169_set_features(struct net_device *dev,
- netdev_features_t features)
+static int rtl8169_set_features(struct net_device *dev,
+ netdev_features_t features)
{
struct rtl8169_private *tp = netdev_priv(dev);
u32 rx_config;
+ rtl_lock_work(tp);
+
rx_config = RTL_R32(tp, RxConfig);
if (features & NETIF_F_RXALL)
rx_config |= (AcceptErr | AcceptRunt);
else
tp->cp_cmd &= ~RxVlan;
- tp->cp_cmd |= RTL_R16(tp, CPlusCmd) & ~(RxVlan | RxChkSum);
-
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
RTL_R16(tp, CPlusCmd);
-}
-
-static int rtl8169_set_features(struct net_device *dev,
- netdev_features_t features)
-{
- struct rtl8169_private *tp = netdev_priv(dev);
- features &= NETIF_F_RXALL | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX;
-
- rtl_lock_work(tp);
- if (features ^ dev->features)
- __rtl8169_set_features(dev, features);
rtl_unlock_work(tp);
return 0;
}
-
static inline u32 rtl8169_tx_vlan_tag(struct sk_buff *skb)
{
return (skb_vlan_tag_present(skb)) ?
if (IS_ERR(ci))
return PTR_ERR(ci);
- scale = &ci->scalev[RTL_R16(tp, CPlusCmd) & 3];
+ scale = &ci->scalev[tp->cp_cmd & INTT_MASK];
/* read IntrMitigate and adjust according to scale */
for (w = RTL_R16(tp, IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) {
RTL_W16(tp, IntrMitigate, swab16(w));
- tp->cp_cmd = (tp->cp_cmd & ~3) | cp01;
+ tp->cp_cmd = (tp->cp_cmd & ~INTT_MASK) | cp01;
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
RTL_R16(tp, CPlusCmd);
ops->write = r8168dp_2_mdio_write;
ops->read = r8168dp_2_mdio_read;
break;
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
ops->write = r8168g_mdio_write;
ops->read = r8168g_mdio_read;
break;
case RTL_GIGA_MAC_VER_32:
case RTL_GIGA_MAC_VER_33:
case RTL_GIGA_MAC_VER_34:
- case RTL_GIGA_MAC_VER_37:
- case RTL_GIGA_MAC_VER_38:
- case RTL_GIGA_MAC_VER_39:
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_51:
RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
break;
return true;
}
-static void r810x_phy_power_down(struct rtl8169_private *tp)
-{
- rtl_writephy(tp, 0x1f, 0x0000);
- rtl_writephy(tp, MII_BMCR, BMCR_PDOWN);
-}
-
-static void r810x_phy_power_up(struct rtl8169_private *tp)
-{
- rtl_writephy(tp, 0x1f, 0x0000);
- rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE);
-}
-
-static void r810x_pll_power_down(struct rtl8169_private *tp)
-{
- if (rtl_wol_pll_power_down(tp))
- return;
-
- r810x_phy_power_down(tp);
-
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_07:
- case RTL_GIGA_MAC_VER_08:
- case RTL_GIGA_MAC_VER_09:
- case RTL_GIGA_MAC_VER_10:
- case RTL_GIGA_MAC_VER_13:
- case RTL_GIGA_MAC_VER_16:
- break;
- default:
- RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80);
- break;
- }
-}
-
-static void r810x_pll_power_up(struct rtl8169_private *tp)
-{
- r810x_phy_power_up(tp);
-
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_07:
- case RTL_GIGA_MAC_VER_08:
- case RTL_GIGA_MAC_VER_09:
- case RTL_GIGA_MAC_VER_10:
- case RTL_GIGA_MAC_VER_13:
- case RTL_GIGA_MAC_VER_16:
- break;
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0);
- break;
- default:
- RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80);
- break;
- }
-}
-
static void r8168_phy_power_up(struct rtl8169_private *tp)
{
rtl_writephy(tp, 0x1f, 0x0000);
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_11:
case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_18:
- case RTL_GIGA_MAC_VER_19:
- case RTL_GIGA_MAC_VER_20:
- case RTL_GIGA_MAC_VER_21:
- case RTL_GIGA_MAC_VER_22:
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
+ case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
case RTL_GIGA_MAC_VER_31:
rtl_writephy(tp, 0x0e, 0x0000);
break;
break;
}
rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE);
+
+ /* give MAC/PHY some time to resume */
+ msleep(20);
}
static void r8168_phy_power_down(struct rtl8169_private *tp)
case RTL_GIGA_MAC_VER_11:
case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_18:
- case RTL_GIGA_MAC_VER_19:
- case RTL_GIGA_MAC_VER_20:
- case RTL_GIGA_MAC_VER_21:
- case RTL_GIGA_MAC_VER_22:
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
+ case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
case RTL_GIGA_MAC_VER_31:
rtl_writephy(tp, 0x0e, 0x0200);
default:
if (r8168_check_dash(tp))
return;
- if ((tp->mac_version == RTL_GIGA_MAC_VER_23 ||
- tp->mac_version == RTL_GIGA_MAC_VER_24) &&
- (RTL_R16(tp, CPlusCmd) & ASF)) {
- return;
- }
-
if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
tp->mac_version == RTL_GIGA_MAC_VER_33)
rtl_ephy_write(tp, 0x19, 0xff64);
r8168_phy_power_down(tp);
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_37:
+ case RTL_GIGA_MAC_VER_39:
+ case RTL_GIGA_MAC_VER_43:
case RTL_GIGA_MAC_VER_44:
case RTL_GIGA_MAC_VER_45:
case RTL_GIGA_MAC_VER_46:
+ case RTL_GIGA_MAC_VER_47:
+ case RTL_GIGA_MAC_VER_48:
case RTL_GIGA_MAC_VER_50:
case RTL_GIGA_MAC_VER_51:
RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80);
static void r8168_pll_power_up(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_37:
+ case RTL_GIGA_MAC_VER_39:
+ case RTL_GIGA_MAC_VER_43:
RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80);
break;
case RTL_GIGA_MAC_VER_44:
case RTL_GIGA_MAC_VER_45:
case RTL_GIGA_MAC_VER_46:
+ case RTL_GIGA_MAC_VER_47:
+ case RTL_GIGA_MAC_VER_48:
case RTL_GIGA_MAC_VER_50:
case RTL_GIGA_MAC_VER_51:
RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0);
r8168_phy_power_up(tp);
}
-static void rtl_generic_op(struct rtl8169_private *tp,
- void (*op)(struct rtl8169_private *))
-{
- if (op)
- op(tp);
-}
-
static void rtl_pll_power_down(struct rtl8169_private *tp)
{
- rtl_generic_op(tp, tp->pll_power_ops.down);
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+ case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15:
+ break;
+ default:
+ r8168_pll_power_down(tp);
+ }
}
static void rtl_pll_power_up(struct rtl8169_private *tp)
{
- rtl_generic_op(tp, tp->pll_power_ops.up);
-}
-
-static void rtl_init_pll_power_ops(struct rtl8169_private *tp)
-{
- struct pll_power_ops *ops = &tp->pll_power_ops;
-
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_07:
- case RTL_GIGA_MAC_VER_08:
- case RTL_GIGA_MAC_VER_09:
- case RTL_GIGA_MAC_VER_10:
- case RTL_GIGA_MAC_VER_16:
- case RTL_GIGA_MAC_VER_29:
- case RTL_GIGA_MAC_VER_30:
- case RTL_GIGA_MAC_VER_37:
- case RTL_GIGA_MAC_VER_39:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- ops->down = r810x_pll_power_down;
- ops->up = r810x_pll_power_up;
- break;
-
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_18:
- case RTL_GIGA_MAC_VER_19:
- case RTL_GIGA_MAC_VER_20:
- case RTL_GIGA_MAC_VER_21:
- case RTL_GIGA_MAC_VER_22:
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
- case RTL_GIGA_MAC_VER_25:
- case RTL_GIGA_MAC_VER_26:
- case RTL_GIGA_MAC_VER_27:
- case RTL_GIGA_MAC_VER_28:
- case RTL_GIGA_MAC_VER_31:
- case RTL_GIGA_MAC_VER_32:
- case RTL_GIGA_MAC_VER_33:
- case RTL_GIGA_MAC_VER_34:
- case RTL_GIGA_MAC_VER_35:
- case RTL_GIGA_MAC_VER_36:
- case RTL_GIGA_MAC_VER_38:
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
- ops->down = r8168_pll_power_down;
- ops->up = r8168_pll_power_up;
+ case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+ case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15:
break;
-
default:
- ops->down = NULL;
- ops->up = NULL;
- break;
+ r8168_pll_power_up(tp);
}
}
static void rtl_init_rxcfg(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_01:
- case RTL_GIGA_MAC_VER_02:
- case RTL_GIGA_MAC_VER_03:
- case RTL_GIGA_MAC_VER_04:
- case RTL_GIGA_MAC_VER_05:
- case RTL_GIGA_MAC_VER_06:
- case RTL_GIGA_MAC_VER_10:
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_13:
- case RTL_GIGA_MAC_VER_14:
- case RTL_GIGA_MAC_VER_15:
- case RTL_GIGA_MAC_VER_16:
- case RTL_GIGA_MAC_VER_17:
+ case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+ case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
RTL_W32(tp, RxConfig, RX_FIFO_THRESH | RX_DMA_BURST);
break;
- case RTL_GIGA_MAC_VER_18:
- case RTL_GIGA_MAC_VER_19:
- case RTL_GIGA_MAC_VER_20:
- case RTL_GIGA_MAC_VER_21:
- case RTL_GIGA_MAC_VER_22:
- case RTL_GIGA_MAC_VER_23:
- case RTL_GIGA_MAC_VER_24:
+ case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
case RTL_GIGA_MAC_VER_34:
case RTL_GIGA_MAC_VER_35:
RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
break;
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
break;
default:
static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
{
- RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
- rtl_generic_op(tp, tp->jumbo_ops.enable);
- RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+ if (tp->jumbo_ops.enable) {
+ RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+ tp->jumbo_ops.enable(tp);
+ RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+ }
}
static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
{
- RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
- rtl_generic_op(tp, tp->jumbo_ops.disable);
- RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+ if (tp->jumbo_ops.disable) {
+ RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+ tp->jumbo_ops.disable(tp);
+ RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+ }
}
static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp)
* No action needed for jumbo frames with 8169.
* No jumbo for 810x at all.
*/
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
default:
ops->disable = NULL;
ops->enable = NULL;
rtl_rx_close(tp);
- if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
- tp->mac_version == RTL_GIGA_MAC_VER_28 ||
- tp->mac_version == RTL_GIGA_MAC_VER_31) {
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_27:
+ case RTL_GIGA_MAC_VER_28:
+ case RTL_GIGA_MAC_VER_31:
rtl_udelay_loop_wait_low(tp, &rtl_npq_cond, 20, 42*42);
- } else if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
- tp->mac_version == RTL_GIGA_MAC_VER_35 ||
- tp->mac_version == RTL_GIGA_MAC_VER_36 ||
- tp->mac_version == RTL_GIGA_MAC_VER_37 ||
- tp->mac_version == RTL_GIGA_MAC_VER_38 ||
- tp->mac_version == RTL_GIGA_MAC_VER_40 ||
- tp->mac_version == RTL_GIGA_MAC_VER_41 ||
- tp->mac_version == RTL_GIGA_MAC_VER_42 ||
- tp->mac_version == RTL_GIGA_MAC_VER_43 ||
- tp->mac_version == RTL_GIGA_MAC_VER_44 ||
- tp->mac_version == RTL_GIGA_MAC_VER_45 ||
- tp->mac_version == RTL_GIGA_MAC_VER_46 ||
- tp->mac_version == RTL_GIGA_MAC_VER_47 ||
- tp->mac_version == RTL_GIGA_MAC_VER_48 ||
- tp->mac_version == RTL_GIGA_MAC_VER_49 ||
- tp->mac_version == RTL_GIGA_MAC_VER_50 ||
- tp->mac_version == RTL_GIGA_MAC_VER_51) {
+ break;
+ case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
- } else {
+ break;
+ default:
RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
udelay(100);
+ break;
}
rtl_hw_reset(tp);
(InterFrameGap << TxInterFrameGapShift));
}
-static void rtl_hw_start(struct rtl8169_private *tp)
+static void rtl_set_rx_max_size(struct rtl8169_private *tp)
{
- tp->hw_start(tp);
- rtl_irq_enable_all(tp);
+ /* Low hurts. Let's disable the filtering. */
+ RTL_W16(tp, RxMaxSize, R8169_RX_BUF_SIZE + 1);
}
static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp)
RTL_W32(tp, RxDescAddrLow, ((u64) tp->RxPhyAddr) & DMA_BIT_MASK(32));
}
-static u16 rtl_rw_cpluscmd(struct rtl8169_private *tp)
-{
- u16 cmd;
-
- cmd = RTL_R16(tp, CPlusCmd);
- RTL_W16(tp, CPlusCmd, cmd);
- return cmd;
-}
-
-static void rtl_set_rx_max_size(struct rtl8169_private *tp)
-{
- /* Low hurts. Let's disable the filtering. */
- RTL_W16(tp, RxMaxSize, R8169_RX_BUF_SIZE + 1);
-}
-
static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_version)
{
static const struct rtl_cfg2_info {
RTL_W32(tp, RxConfig, tmp);
}
-static void rtl_hw_start_8169(struct rtl8169_private *tp)
+static void rtl_hw_start(struct rtl8169_private *tp)
{
- if (tp->mac_version == RTL_GIGA_MAC_VER_05) {
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) | PCIMulRW);
- pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
- }
-
RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
- if (tp->mac_version == RTL_GIGA_MAC_VER_01 ||
- tp->mac_version == RTL_GIGA_MAC_VER_02 ||
- tp->mac_version == RTL_GIGA_MAC_VER_03 ||
- tp->mac_version == RTL_GIGA_MAC_VER_04)
- RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
- rtl_init_rxcfg(tp);
-
- RTL_W8(tp, EarlyTxThres, NoEarlyTx);
+ tp->hw_start(tp);
rtl_set_rx_max_size(tp);
+ rtl_set_rx_tx_desc_registers(tp);
+ rtl_set_rx_tx_config_registers(tp);
+ RTL_W8(tp, Cfg9346, Cfg9346_Lock);
- if (tp->mac_version == RTL_GIGA_MAC_VER_01 ||
- tp->mac_version == RTL_GIGA_MAC_VER_02 ||
- tp->mac_version == RTL_GIGA_MAC_VER_03 ||
- tp->mac_version == RTL_GIGA_MAC_VER_04)
- rtl_set_rx_tx_config_registers(tp);
+ /* Initially a 10 us delay. Turned it into a PCI commit. - FR */
+ RTL_R8(tp, IntrMask);
+ RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
+ rtl_set_rx_mode(tp->dev);
+ /* no early-rx interrupts */
+ RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
+ rtl_irq_enable_all(tp);
+}
- tp->cp_cmd |= rtl_rw_cpluscmd(tp) | PCIMulRW;
+static void rtl_hw_start_8169(struct rtl8169_private *tp)
+{
+ if (tp->mac_version == RTL_GIGA_MAC_VER_05)
+ pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
+
+ RTL_W8(tp, EarlyTxThres, NoEarlyTx);
+
+ tp->cp_cmd |= PCIMulRW;
if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
tp->mac_version == RTL_GIGA_MAC_VER_03) {
*/
RTL_W16(tp, IntrMitigate, 0x0000);
- rtl_set_rx_tx_desc_registers(tp);
-
- if (tp->mac_version != RTL_GIGA_MAC_VER_01 &&
- tp->mac_version != RTL_GIGA_MAC_VER_02 &&
- tp->mac_version != RTL_GIGA_MAC_VER_03 &&
- tp->mac_version != RTL_GIGA_MAC_VER_04) {
- RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
- rtl_set_rx_tx_config_registers(tp);
- }
-
- RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-
- /* Initially a 10 us delay. Turned it into a PCI commit. - FR */
- RTL_R8(tp, IntrMask);
-
RTL_W32(tp, RxMissed, 0);
-
- rtl_set_rx_mode(tp->dev);
-
- /* no early-rx interrupts */
- RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
-}
-
-static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value)
-{
- if (tp->csi_ops.write)
- tp->csi_ops.write(tp, addr, value);
-}
-
-static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
-{
- return tp->csi_ops.read ? tp->csi_ops.read(tp, addr) : ~0;
-}
-
-static void rtl_csi_access_enable(struct rtl8169_private *tp, u32 bits)
-{
- u32 csi;
-
- csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff;
- rtl_csi_write(tp, 0x070c, csi | bits);
-}
-
-static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
-{
- rtl_csi_access_enable(tp, 0x17000000);
-}
-
-static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
-{
- rtl_csi_access_enable(tp, 0x27000000);
}
DECLARE_RTL_COND(rtl_csiar_cond)
return RTL_R32(tp, CSIAR) & CSIAR_FLAG;
}
-static void r8169_csi_write(struct rtl8169_private *tp, int addr, int value)
+static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value)
{
+ u32 func = PCI_FUNC(tp->pci_dev->devfn);
+
RTL_W32(tp, CSIDR, value);
RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+ CSIAR_BYTE_ENABLE | func << 16);
rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100);
}
-static u32 r8169_csi_read(struct rtl8169_private *tp, int addr)
+static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
{
- RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+ u32 func = PCI_FUNC(tp->pci_dev->devfn);
+
+ RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | func << 16 |
+ CSIAR_BYTE_ENABLE);
return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ?
RTL_R32(tp, CSIDR) : ~0;
}
-static void r8402_csi_write(struct rtl8169_private *tp, int addr, int value)
+static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
{
- RTL_W32(tp, CSIDR, value);
- RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT |
- CSIAR_FUNC_NIC);
-
- rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100);
-}
+ struct pci_dev *pdev = tp->pci_dev;
+ u32 csi;
-static u32 r8402_csi_read(struct rtl8169_private *tp, int addr)
-{
- RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
+ /* According to Realtek the value at config space address 0x070f
+ * controls the L0s/L1 entrance latency. We try standard ECAM access
+ * first and if it fails fall back to CSI.
+ */
+ if (pdev->cfg_size > 0x070f &&
+ pci_write_config_byte(pdev, 0x070f, val) == PCIBIOS_SUCCESSFUL)
+ return;
- return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ?
- RTL_R32(tp, CSIDR) : ~0;
+ netdev_notice_once(tp->dev,
+ "No native access to PCI extended config space, falling back to CSI\n");
+ csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff;
+ rtl_csi_write(tp, 0x070c, csi | val << 24);
}
-static void r8411_csi_write(struct rtl8169_private *tp, int addr, int value)
+static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
{
- RTL_W32(tp, CSIDR, value);
- RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT |
- CSIAR_FUNC_NIC2);
-
- rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100);
+ rtl_csi_access_enable(tp, 0x17);
}
-static u32 r8411_csi_read(struct rtl8169_private *tp, int addr)
+static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
{
- RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC2 |
- CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT);
-
- return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ?
- RTL_R32(tp, CSIDR) : ~0;
-}
-
-static void rtl_init_csi_ops(struct rtl8169_private *tp)
-{
- struct csi_ops *ops = &tp->csi_ops;
-
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_01:
- case RTL_GIGA_MAC_VER_02:
- case RTL_GIGA_MAC_VER_03:
- case RTL_GIGA_MAC_VER_04:
- case RTL_GIGA_MAC_VER_05:
- case RTL_GIGA_MAC_VER_06:
- case RTL_GIGA_MAC_VER_10:
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_13:
- case RTL_GIGA_MAC_VER_14:
- case RTL_GIGA_MAC_VER_15:
- case RTL_GIGA_MAC_VER_16:
- case RTL_GIGA_MAC_VER_17:
- ops->write = NULL;
- ops->read = NULL;
- break;
-
- case RTL_GIGA_MAC_VER_37:
- case RTL_GIGA_MAC_VER_38:
- ops->write = r8402_csi_write;
- ops->read = r8402_csi_read;
- break;
-
- case RTL_GIGA_MAC_VER_44:
- ops->write = r8411_csi_write;
- ops->read = r8411_csi_read;
- break;
-
- default:
- ops->write = r8169_csi_write;
- ops->read = r8169_csi_read;
- break;
- }
+ rtl_csi_access_enable(tp, 0x27);
}
struct ephy_info {
RTL_W8(tp, Config3, data);
}
-#define R8168_CPCMD_QUIRK_MASK (\
- EnableBist | \
- Mac_dbgo_oe | \
- Force_half_dup | \
- Force_rxflow_en | \
- Force_txflow_en | \
- Cxpl_dbg_sel | \
- ASF | \
- PktCntrDisable | \
- Mac_dbgo_sel)
-
static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
{
RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
+ RTL_W16(tp, CPlusCmd, tp->cp_cmd);
if (tp->dev->mtu <= ETH_DATA_LEN) {
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B |
rtl_disable_clock_request(tp);
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
+ RTL_W16(tp, CPlusCmd, tp->cp_cmd);
}
static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
if (tp->dev->mtu <= ETH_DATA_LEN)
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
+ RTL_W16(tp, CPlusCmd, tp->cp_cmd);
}
static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
if (tp->dev->mtu <= ETH_DATA_LEN)
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
+ RTL_W16(tp, CPlusCmd, tp->cp_cmd);
}
static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
if (tp->dev->mtu <= ETH_DATA_LEN)
rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
- RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK);
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
+ RTL_W16(tp, CPlusCmd, tp->cp_cmd);
}
static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
static void rtl_hw_start_8168(struct rtl8169_private *tp)
{
- RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
-
RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
- rtl_set_rx_max_size(tp);
-
- tp->cp_cmd |= RTL_R16(tp, CPlusCmd) | PktCntrDisable | INTT_1;
-
+ tp->cp_cmd &= ~INTT_MASK;
+ tp->cp_cmd |= PktCntrDisable | INTT_1;
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
RTL_W16(tp, IntrMitigate, 0x5151);
tp->event_slow &= ~RxOverflow;
}
- rtl_set_rx_tx_desc_registers(tp);
-
- rtl_set_rx_tx_config_registers(tp);
-
- RTL_R8(tp, IntrMask);
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_11:
rtl_hw_start_8168bb(tp);
tp->dev->name, tp->mac_version);
break;
}
-
- RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-
- RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
-
- rtl_set_rx_mode(tp->dev);
-
- RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
}
-#define R810X_CPCMD_QUIRK_MASK (\
- EnableBist | \
- Mac_dbgo_oe | \
- Force_half_dup | \
- Force_rxflow_en | \
- Force_txflow_en | \
- Cxpl_dbg_sel | \
- ASF | \
- PktCntrDisable | \
- Mac_dbgo_sel)
-
static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
{
static const struct ephy_info e_info_8102e_1[] = {
pcie_capability_set_word(tp->pci_dev, PCI_EXP_DEVCTL,
PCI_EXP_DEVCTL_NOSNOOP_EN);
- RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
-
RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
- rtl_set_rx_max_size(tp);
-
- tp->cp_cmd &= ~R810X_CPCMD_QUIRK_MASK;
+ tp->cp_cmd &= CPCMD_QUIRK_MASK;
RTL_W16(tp, CPlusCmd, tp->cp_cmd);
- rtl_set_rx_tx_desc_registers(tp);
-
- rtl_set_rx_tx_config_registers(tp);
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_07:
rtl_hw_start_8102e_1(tp);
break;
}
- RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-
RTL_W16(tp, IntrMitigate, 0x0000);
-
- RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
-
- rtl_set_rx_mode(tp->dev);
-
- RTL_R8(tp, IntrMask);
-
- RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
}
static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
return ret;
}
-static inline __be16 get_protocol(struct sk_buff *skb)
-{
- __be16 protocol;
-
- if (skb->protocol == htons(ETH_P_8021Q))
- protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
- else
- protocol = skb->protocol;
-
- return protocol;
-}
-
static bool rtl8169_tso_csum_v1(struct rtl8169_private *tp,
struct sk_buff *skb, u32 *opts)
{
return false;
}
- switch (get_protocol(skb)) {
+ switch (vlan_get_protocol(skb)) {
case htons(ETH_P_IP):
opts[0] |= TD1_GTSENV4;
break;
return false;
}
- switch (get_protocol(skb)) {
+ switch (vlan_get_protocol(skb)) {
case htons(ETH_P_IP):
opts[1] |= TD1_IPv4_CS;
ip_protocol = ip_hdr(skb)->protocol;
rtl8169_init_phy(dev, tp);
- __rtl8169_set_features(dev, dev->features);
-
rtl_pll_power_up(tp);
rtl_hw_start(tp);
static void rtl_hw_initialize(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_40:
- case RTL_GIGA_MAC_VER_41:
- case RTL_GIGA_MAC_VER_42:
- case RTL_GIGA_MAC_VER_43:
- case RTL_GIGA_MAC_VER_44:
- case RTL_GIGA_MAC_VER_45:
- case RTL_GIGA_MAC_VER_46:
- case RTL_GIGA_MAC_VER_47:
- case RTL_GIGA_MAC_VER_48:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
rtl_hw_init_8168g(tp);
break;
- case RTL_GIGA_MAC_VER_49:
- case RTL_GIGA_MAC_VER_50:
- case RTL_GIGA_MAC_VER_51:
+ case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_51:
rtl_hw_init_8168ep(tp);
break;
default:
/* Identify chip attached to board */
rtl8169_get_mac_version(tp, cfg->default_ver);
- tp->cp_cmd = 0;
+ tp->cp_cmd = RTL_R16(tp, CPlusCmd);
if ((sizeof(dma_addr_t) > 4) &&
(use_dac == 1 || (use_dac == -1 && pci_is_pcie(pdev) &&
pci_set_master(pdev);
rtl_init_mdio_ops(tp);
- rtl_init_pll_power_ops(tp);
rtl_init_jumbo_ops(tp);
- rtl_init_csi_ops(tp);
rtl8169_print_mac_version(tp);
u64_stats_init(&tp->tx_stats.syncp);
/* Get MAC address */
- if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
- tp->mac_version == RTL_GIGA_MAC_VER_36 ||
- tp->mac_version == RTL_GIGA_MAC_VER_37 ||
- tp->mac_version == RTL_GIGA_MAC_VER_38 ||
- tp->mac_version == RTL_GIGA_MAC_VER_40 ||
- tp->mac_version == RTL_GIGA_MAC_VER_41 ||
- tp->mac_version == RTL_GIGA_MAC_VER_42 ||
- tp->mac_version == RTL_GIGA_MAC_VER_43 ||
- tp->mac_version == RTL_GIGA_MAC_VER_44 ||
- tp->mac_version == RTL_GIGA_MAC_VER_45 ||
- tp->mac_version == RTL_GIGA_MAC_VER_46 ||
- tp->mac_version == RTL_GIGA_MAC_VER_47 ||
- tp->mac_version == RTL_GIGA_MAC_VER_48 ||
- tp->mac_version == RTL_GIGA_MAC_VER_49 ||
- tp->mac_version == RTL_GIGA_MAC_VER_50 ||
- tp->mac_version == RTL_GIGA_MAC_VER_51) {
- u16 mac_addr[3];
-
+ switch (tp->mac_version) {
+ u8 mac_addr[ETH_ALEN] __aligned(4);
+ case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
*(u32 *)&mac_addr[0] = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC);
- *(u16 *)&mac_addr[2] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC);
+ *(u16 *)&mac_addr[4] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC);
- if (is_valid_ether_addr((u8 *)mac_addr))
- rtl_rar_set(tp, (u8 *)mac_addr);
+ if (is_valid_ether_addr(mac_addr))
+ rtl_rar_set(tp, mac_addr);
+ break;
+ default:
+ break;
}
for (i = 0; i < ETH_ALEN; i++)
dev->dev_addr[i] = RTL_R8(tp, MAC0 + i);
static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
int enum_index)
{
- iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]);
+ u16 offset = mdp->reg_offset[enum_index];
+
+ if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
+ return;
+
+ iowrite32(data, mdp->tsu_addr + offset);
}
static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index)
{
- return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]);
+ u16 offset = mdp->reg_offset[enum_index];
+
+ if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
+ return ~0U;
+
+ return ioread32(mdp->tsu_addr + offset);
}
static void sh_eth_select_mii(struct net_device *ndev)
u32 value;
switch (mdp->phy_interface) {
+ case PHY_INTERFACE_MODE_RGMII ... PHY_INTERFACE_MODE_RGMII_TXID:
+ value = 0x3;
+ break;
case PHY_INTERFACE_MODE_GMII:
value = 0x2;
break;
EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
- .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
+ .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO,
.eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE,
.fdr_value = 0x00000f0f,
EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
- .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
+ .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO,
.eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE,
.fdr_value = 0x00000f0f,
.rmiimode = 1,
.magic = 1,
};
+
+/* R8A77980 */
+static struct sh_eth_cpu_data r8a77980_data = {
+ .soft_reset = sh_eth_soft_reset_gether,
+
+ .set_duplex = sh_eth_set_duplex,
+ .set_rate = sh_eth_set_rate_gether,
+
+ .register_type = SH_ETH_REG_GIGABIT,
+
+ .edtrr_trns = EDTRR_TRNS_GETHER,
+ .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD | ECSR_MPD,
+ .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP |
+ ECSIPR_MPDIP,
+ .eesipr_value = EESIPR_RFCOFIP | EESIPR_ECIIP |
+ EESIPR_FTCIP | EESIPR_TDEIP | EESIPR_TFUFIP |
+ EESIPR_FRIP | EESIPR_RDEIP | EESIPR_RFOFIP |
+ EESIPR_RMAFIP | EESIPR_RRFIP |
+ EESIPR_RTLFIP | EESIPR_RTSFIP |
+ EESIPR_PREIP | EESIPR_CERFIP,
+
+ .tx_check = EESR_FTC | EESR_CD | EESR_TRO,
+ .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT |
+ EESR_RFE | EESR_RDE | EESR_RFRMER |
+ EESR_TFE | EESR_TDE | EESR_ECI,
+ .fdr_value = 0x0000070f,
+
+ .apr = 1,
+ .mpr = 1,
+ .tpauser = 1,
+ .bculr = 1,
+ .hw_swap = 1,
+ .nbst = 1,
+ .rpadir = 1,
+ .rpadir_value = 2 << 16,
+ .no_trimd = 1,
+ .no_ade = 1,
+ .xdfar_rw = 1,
+ .hw_checksum = 1,
+ .select_mii = 1,
+ .magic = 1,
+ .cexcr = 1,
+};
#endif /* CONFIG_OF */
static void sh_eth_set_rate_sh7724(struct net_device *ndev)
EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
- .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
+ .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO,
.eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE,
EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
- .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
+ .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO,
.eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE,
sh_eth_write(ndev, mdp->cd->trscer_err_mask, TRSCER);
+ /* DMA transfer burst mode */
+ if (mdp->cd->nbst)
+ sh_eth_modify(ndev, EDMR, EDMR_NBST, EDMR_NBST);
+
+ /* Burst cycle count upper-limit */
if (mdp->cd->bculr)
- sh_eth_write(ndev, 0x800, BCULR); /* Burst sycle set */
+ sh_eth_write(ndev, 0x800, BCULR);
sh_eth_write(ndev, mdp->cd->fcftr_value, FCFTR);
}
/* For TSU_POSTn. Please refer to the manual about this (strange) bitfields */
-static void *sh_eth_tsu_get_post_reg_offset(struct sh_eth_private *mdp,
- int entry)
-{
- return sh_eth_tsu_get_offset(mdp, TSU_POST1) + (entry / 8 * 4);
-}
-
static u32 sh_eth_tsu_get_post_mask(int entry)
{
return 0x0f << (28 - ((entry % 8) * 4));
int entry)
{
struct sh_eth_private *mdp = netdev_priv(ndev);
+ int reg = TSU_POST1 + entry / 8;
u32 tmp;
- void *reg_offset;
- reg_offset = sh_eth_tsu_get_post_reg_offset(mdp, entry);
- tmp = ioread32(reg_offset);
- iowrite32(tmp | sh_eth_tsu_get_post_bit(mdp, entry), reg_offset);
+ tmp = sh_eth_tsu_read(mdp, reg);
+ sh_eth_tsu_write(mdp, tmp | sh_eth_tsu_get_post_bit(mdp, entry), reg);
}
static bool sh_eth_tsu_disable_cam_entry_post(struct net_device *ndev,
int entry)
{
struct sh_eth_private *mdp = netdev_priv(ndev);
+ int reg = TSU_POST1 + entry / 8;
u32 post_mask, ref_mask, tmp;
- void *reg_offset;
- reg_offset = sh_eth_tsu_get_post_reg_offset(mdp, entry);
post_mask = sh_eth_tsu_get_post_mask(entry);
ref_mask = sh_eth_tsu_get_post_bit(mdp, entry) & ~post_mask;
- tmp = ioread32(reg_offset);
- iowrite32(tmp & ~post_mask, reg_offset);
+ tmp = sh_eth_tsu_read(mdp, reg);
+ sh_eth_tsu_write(mdp, tmp & ~post_mask, reg);
/* If other port enables, the function returns "true" */
return tmp & ref_mask;
pdev->name, pdev->id);
/* register MDIO bus */
- if (dev->of_node) {
- ret = of_mdiobus_register(mdp->mii_bus, dev->of_node);
- } else {
- if (pd->phy_irq > 0)
- mdp->mii_bus->irq[pd->phy] = pd->phy_irq;
-
- ret = mdiobus_register(mdp->mii_bus);
- }
+ if (pd->phy_irq > 0)
+ mdp->mii_bus->irq[pd->phy] = pd->phy_irq;
+ ret = of_mdiobus_register(mdp->mii_bus, dev->of_node);
if (ret)
goto out_free_bus;
{ .compatible = "renesas,ether-r8a7791", .data = &rcar_gen2_data },
{ .compatible = "renesas,ether-r8a7793", .data = &rcar_gen2_data },
{ .compatible = "renesas,ether-r8a7794", .data = &rcar_gen2_data },
+ { .compatible = "renesas,gether-r8a77980", .data = &r8a77980_data },
{ .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data },
{ .compatible = "renesas,rcar-gen1-ether", .data = &rcar_gen1_data },
{ .compatible = "renesas,rcar-gen2-ether", .data = &rcar_gen2_data },
};
/* Driver's parameters */
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_RENESAS)
#define SH_ETH_RX_ALIGN 32
#else
#define SH_ETH_RX_ALIGN 2
/* EDMR */
enum DMAC_M_BIT {
+ EDMR_NBST = 0x80,
EDMR_EL = 0x40, /* Litte endian */
EDMR_DL1 = 0x20, EDMR_DL0 = 0x10,
EDMR_SRST_GETHER = 0x03,
EESR_CND = 0x00000800,
EESR_DLC = 0x00000400,
EESR_CD = 0x00000200,
- EESR_RTO = 0x00000100,
+ EESR_TRO = 0x00000100,
EESR_RMAF = 0x00000080,
EESR_CEEF = 0x00000040,
EESR_CELF = 0x00000020,
EESR_CERF) /* Recv frame CRC error */
#define DEFAULT_TX_CHECK (EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | \
- EESR_RTO)
+ EESR_TRO)
#define DEFAULT_EESR_ERR_CHECK (EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | \
EESR_RDE | EESR_RFRMER | EESR_ADE | \
EESR_TFE | EESR_TDE)
/* hardware features */
unsigned long irq_flags; /* IRQ configuration flags */
- unsigned no_psr:1; /* EtherC DO NOT have PSR */
- unsigned apr:1; /* EtherC have APR */
- unsigned mpr:1; /* EtherC have MPR */
- unsigned tpauser:1; /* EtherC have TPAUSER */
- unsigned bculr:1; /* EtherC have BCULR */
- unsigned tsu:1; /* EtherC have TSU */
- unsigned hw_swap:1; /* E-DMAC have DE bit in EDMR */
- unsigned rpadir:1; /* E-DMAC have RPADIR */
- unsigned no_trimd:1; /* E-DMAC DO NOT have TRIMD */
- unsigned no_ade:1; /* E-DMAC DO NOT have ADE bit in EESR */
+ unsigned no_psr:1; /* EtherC DOES NOT have PSR */
+ unsigned apr:1; /* EtherC has APR */
+ unsigned mpr:1; /* EtherC has MPR */
+ unsigned tpauser:1; /* EtherC has TPAUSER */
+ unsigned bculr:1; /* EtherC has BCULR */
+ unsigned tsu:1; /* EtherC has TSU */
+ unsigned hw_swap:1; /* E-DMAC has DE bit in EDMR */
+ unsigned nbst:1; /* E-DMAC has NBST bit in EDMR */
+ unsigned rpadir:1; /* E-DMAC has RPADIR */
+ unsigned no_trimd:1; /* E-DMAC DOES NOT have TRIMD */
+ unsigned no_ade:1; /* E-DMAC DOES NOT have ADE bit in EESR */
unsigned no_xdfar:1; /* E-DMAC DOES NOT have RDFAR/TDFAR */
unsigned xdfar_rw:1; /* E-DMAC has writeable RDFAR/TDFAR */
unsigned hw_checksum:1; /* E-DMAC has CSMR */
- unsigned select_mii:1; /* EtherC have RMII_MII (MII select register) */
+ unsigned select_mii:1; /* EtherC has RMII_MII (MII select register) */
unsigned rmiimode:1; /* EtherC has RMIIMODE register */
unsigned rtrate:1; /* EtherC has RTRATE register */
unsigned magic:1; /* EtherC has ECMR.MPDE and ECSR.MPD */
switch (switchdev_work->event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
err = rocker_world_port_fdb_add(rocker_port, fdb_info);
if (err) {
netdev_dbg(rocker_port->dev, "fdb add failed err=%d\n", err);
break;
case SWITCHDEV_FDB_DEL_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
err = rocker_world_port_fdb_del(rocker_port, fdb_info);
if (err)
netdev_dbg(rocker_port->dev, "fdb add failed err=%d\n", err);
atomic_set(&efx->active_queues, 0);
}
-static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right)
-{
- if ((left->match_flags ^ right->match_flags) |
- ((left->flags ^ right->flags) &
- (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
- return false;
-
- return memcmp(&left->outer_vid, &right->outer_vid,
- sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
-{
- BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
- return jhash2((const u32 *)&spec->outer_vid,
- (sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) / 4,
- 0);
- /* XXX should we randomise the initval? */
-}
-
/* Decide whether a filter should be exclusive or else should allow
* delivery to additional recipients. Currently we decide that
* filters for specific local unicast MAC and IP addresses are
goto out_unlock;
match_pri = rc;
- hash = efx_ef10_filter_hash(spec);
+ hash = efx_filter_spec_hash(spec);
is_mc_recip = efx_filter_is_mc_recipient(spec);
if (is_mc_recip)
bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
if (!saved_spec) {
if (ins_index < 0)
ins_index = i;
- } else if (efx_ef10_filter_equal(spec, saved_spec)) {
+ } else if (efx_filter_spec_equal(spec, saved_spec)) {
if (spec->priority < saved_spec->priority &&
spec->priority != EFX_FILTER_PRI_AUTO) {
rc = -EPERM;
static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
unsigned int filter_idx)
{
+ struct efx_filter_spec *spec, saved_spec;
struct efx_ef10_filter_table *table;
- struct efx_filter_spec *spec;
- bool ret;
+ struct efx_arfs_rule *rule = NULL;
+ bool ret = true, force = false;
+ u16 arfs_id;
down_read(&efx->filter_sem);
table = efx->filter_state;
down_write(&table->lock);
spec = efx_ef10_filter_entry_spec(table, filter_idx);
- if (!spec || spec->priority != EFX_FILTER_PRI_HINT) {
- ret = true;
+ if (!spec || spec->priority != EFX_FILTER_PRI_HINT)
goto out_unlock;
- }
- if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, 0)) {
+ spin_lock_bh(&efx->rps_hash_lock);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always return 0 to ARFS. */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, spec);
+ if (!rule)
+ /* ARFS table doesn't know of this filter, so remove it */
+ goto expire;
+ arfs_id = rule->arfs_id;
+ ret = efx_rps_check_rule(rule, filter_idx, &force);
+ if (force)
+ goto expire;
+ if (!ret) {
+ spin_unlock_bh(&efx->rps_hash_lock);
+ goto out_unlock;
+ }
+ }
+ if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id))
ret = false;
- goto out_unlock;
+ else if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+expire:
+ saved_spec = *spec; /* remove operation will kfree spec */
+ spin_unlock_bh(&efx->rps_hash_lock);
+ /* At this point (since we dropped the lock), another thread might queue
+ * up a fresh insertion request (but the actual insertion will be held
+ * up by our possession of the filter table lock). In that case, it
+ * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that
+ * the rule is not removed by efx_rps_hash_del() below.
+ */
+ if (ret)
+ ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
+ filter_idx, true) == 0;
+ /* While we can't safely dereference rule (we dropped the lock), we can
+ * still test it for NULL.
+ */
+ if (ret && rule) {
+ /* Expiring, so remove entry from ARFS table */
+ spin_lock_bh(&efx->rps_hash_lock);
+ efx_rps_hash_del(efx, &saved_spec);
+ spin_unlock_bh(&efx->rps_hash_lock);
}
-
- ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
- filter_idx, true) == 0;
out_unlock:
up_write(&table->lock);
up_read(&efx->filter_sem);
mutex_init(&efx->mac_lock);
#ifdef CONFIG_RFS_ACCEL
mutex_init(&efx->rps_mutex);
+ spin_lock_init(&efx->rps_hash_lock);
+ /* Failure to allocate is not fatal, but may degrade ARFS performance */
+ efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
+ sizeof(*efx->rps_hash_table), GFP_KERNEL);
#endif
efx->phy_op = &efx_dummy_phy_operations;
efx->mdio.dev = net_dev;
{
int i;
+#ifdef CONFIG_RFS_ACCEL
+ kfree(efx->rps_hash_table);
+#endif
+
for (i = 0; i < EFX_MAX_CHANNELS; i++)
kfree(efx->channel[i]);
stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
}
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right)
+{
+ if ((left->match_flags ^ right->match_flags) |
+ ((left->flags ^ right->flags) &
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+ return false;
+
+ return memcmp(&left->outer_vid, &right->outer_vid,
+ sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
+{
+ BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+ return jhash2((const u32 *)&spec->outer_vid,
+ (sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) / 4,
+ 0);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force)
+{
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
+ /* ARFS is currently updating this entry, leave it */
+ return false;
+ }
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
+ /* ARFS tried and failed to update this, so it's probably out
+ * of date. Remove the filter and the ARFS rule entry.
+ */
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ *force = true;
+ return true;
+ } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
+ /* ARFS has moved on, so old filter is not needed. Since we did
+ * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
+ * not be removed by efx_rps_hash_del() subsequently.
+ */
+ *force = true;
+ return true;
+ }
+ /* Remove it iff ARFS wants to. */
+ return true;
+}
+
+struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ u32 hash = efx_filter_spec_hash(spec);
+
+ WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+ if (!efx->rps_hash_table)
+ return NULL;
+ return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
+}
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec))
+ return rule;
+ }
+ return NULL;
+}
+
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ *new = false;
+ return rule;
+ }
+ }
+ rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
+ *new = true;
+ if (rule) {
+ memcpy(&rule->spec, spec, sizeof(rule->spec));
+ hlist_add_head(&rule->node, head);
+ }
+ return rule;
+}
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (WARN_ON(!head))
+ return;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ /* Someone already reused the entry. We know that if
+ * this check doesn't fire (i.e. filter_id == REMOVING)
+ * then the REMOVING mark was put there by our caller,
+ * because caller is holding a lock on filter table and
+ * only holders of that lock set REMOVING.
+ */
+ if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
+ return;
+ hlist_del(node);
+ kfree(rule);
+ return;
+ }
+ }
+ /* We didn't find it. */
+ WARN_ON(1);
+}
+#endif
+
/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
* (a) this is an infrequent control-plane operation and (b) n is small (max 64)
*/
#endif
bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right);
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force);
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec);
+
+/* @new is written to indicate if entry was newly added (true) or if an old
+ * entry was found and returned (false).
+ */
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new);
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
+#endif
+
/* RSS contexts */
struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
{
struct efx_farch_filter_state *state = efx->filter_state;
struct efx_farch_filter_table *table;
- bool ret = false;
+ bool ret = false, force = false;
+ u16 arfs_id;
down_write(&state->lock);
+ spin_lock_bh(&efx->rps_hash_lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
if (test_bit(index, table->used_bitmap) &&
- table->spec[index].priority == EFX_FILTER_PRI_HINT &&
- rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id,
- flow_id, 0)) {
- efx_farch_filter_table_clear_entry(efx, table, index);
- ret = true;
+ table->spec[index].priority == EFX_FILTER_PRI_HINT) {
+ struct efx_arfs_rule *rule = NULL;
+ struct efx_filter_spec spec;
+
+ efx_farch_filter_to_gen_spec(&spec, &table->spec[index]);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always returned 0 to
+ * ARFS, so use the same to query it.
+ */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, &spec);
+ if (!rule) {
+ /* ARFS table doesn't know of this filter, remove it */
+ force = true;
+ } else {
+ arfs_id = rule->arfs_id;
+ if (!efx_rps_check_rule(rule, index, &force))
+ goto out_unlock;
+ }
+ }
+ if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id,
+ flow_id, arfs_id)) {
+ if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ efx_rps_hash_del(efx, &spec);
+ efx_farch_filter_table_clear_entry(efx, table, index);
+ ret = true;
+ }
}
-
+out_unlock:
+ spin_unlock_bh(&efx->rps_hash_lock);
up_write(&state->lock);
return ret;
}
};
#ifdef CONFIG_RFS_ACCEL
+/* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING
+ * is used to test if filter does or will exist.
+ */
+#define EFX_ARFS_FILTER_ID_PENDING -1
+#define EFX_ARFS_FILTER_ID_ERROR -2
+#define EFX_ARFS_FILTER_ID_REMOVING -3
+/**
+ * struct efx_arfs_rule - record of an ARFS filter and its IDs
+ * @node: linkage into hash table
+ * @spec: details of the filter (used as key for hash table). Use efx->type to
+ * determine which member to use.
+ * @rxq_index: channel to which the filter will steer traffic.
+ * @arfs_id: filter ID which was returned to ARFS
+ * @filter_id: index in software filter table. May be
+ * %EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet,
+ * %EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or
+ * %EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter.
+ */
+struct efx_arfs_rule {
+ struct hlist_node node;
+ struct efx_filter_spec spec;
+ u16 rxq_index;
+ u16 arfs_id;
+ s32 filter_id;
+};
+
+/* Size chosen so that the table is one page (4kB) */
+#define EFX_ARFS_HASH_TABLE_SIZE 512
+
/**
* struct efx_async_filter_insertion - Request to asynchronously insert a filter
* @net_dev: Reference to the netdevice
* @rps_expire_channel's @rps_flow_id
* @rps_slot_map: bitmap of in-flight entries in @rps_slot
* @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work()
+ * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and
+ * @rps_next_id).
+ * @rps_hash_table: Mapping between ARFS filters and their various IDs
+ * @rps_next_id: next arfs_id for an ARFS filter
* @active_queues: Count of RX and TX queues that haven't been flushed and drained.
* @rxq_flush_pending: Count of number of receive queues that need to be flushed.
* Decremented when the efx_flush_rx_queue() is called.
unsigned int rps_expire_index;
unsigned long rps_slot_map;
struct efx_async_filter_insertion rps_slot[EFX_RPS_MAX_IN_FLIGHT];
+ spinlock_t rps_hash_lock;
+ struct hlist_head *rps_hash_table;
+ u32 rps_next_id;
#endif
atomic_t active_queues;
struct efx_nic *efx = netdev_priv(req->net_dev);
struct efx_channel *channel = efx_get_channel(efx, req->rxq_index);
int slot_idx = req - efx->rps_slot;
+ struct efx_arfs_rule *rule;
+ u16 arfs_id = 0;
int rc;
rc = efx->type->filter_insert(efx, &req->spec, true);
+ if (rc >= 0)
+ rc %= efx->type->max_rx_ip_filters;
+ if (efx->rps_hash_table) {
+ spin_lock_bh(&efx->rps_hash_lock);
+ rule = efx_rps_hash_find(efx, &req->spec);
+ /* The rule might have already gone, if someone else's request
+ * for the same spec was already worked and then expired before
+ * we got around to our work. In that case we have nothing
+ * tying us to an arfs_id, meaning that as soon as the filter
+ * is considered for expiry it will be removed.
+ */
+ if (rule) {
+ if (rc < 0)
+ rule->filter_id = EFX_ARFS_FILTER_ID_ERROR;
+ else
+ rule->filter_id = rc;
+ arfs_id = rule->arfs_id;
+ }
+ spin_unlock_bh(&efx->rps_hash_lock);
+ }
if (rc >= 0) {
/* Remember this so we can check whether to expire the filter
* later.
if (req->spec.ether_type == htons(ETH_P_IP))
netif_info(efx, rx_status, efx->net_dev,
- "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
+ "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
else
netif_info(efx, rx_status, efx->net_dev,
- "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
+ "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
}
/* Release references */
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_async_filter_insertion *req;
+ struct efx_arfs_rule *rule;
struct flow_keys fk;
int slot_idx;
+ bool new;
int rc;
/* find a free slot */
req->spec.rem_port = fk.ports.src;
req->spec.loc_port = fk.ports.dst;
+ if (efx->rps_hash_table) {
+ /* Add it to ARFS hash table */
+ spin_lock(&efx->rps_hash_lock);
+ rule = efx_rps_hash_add(efx, &req->spec, &new);
+ if (!rule) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+ if (new)
+ rule->arfs_id = efx->rps_next_id++ % RPS_NO_FILTER;
+ rc = rule->arfs_id;
+ /* Skip if existing or pending filter already does the right thing */
+ if (!new && rule->rxq_index == rxq_index &&
+ rule->filter_id >= EFX_ARFS_FILTER_ID_PENDING)
+ goto out_unlock;
+ rule->rxq_index = rxq_index;
+ rule->filter_id = EFX_ARFS_FILTER_ID_PENDING;
+ spin_unlock(&efx->rps_hash_lock);
+ } else {
+ /* Without an ARFS hash table, we just use arfs_id 0 for all
+ * filters. This means if multiple flows hash to the same
+ * flow_id, all but the most recently touched will be eligible
+ * for expiry.
+ */
+ rc = 0;
+ }
+
+ /* Queue the request */
dev_hold(req->net_dev = net_dev);
INIT_WORK(&req->work, efx_filter_rfs_work);
req->rxq_index = rxq_index;
req->flow_id = flow_id;
schedule_work(&req->work);
- return 0;
+ return rc;
+out_unlock:
+ spin_unlock(&efx->rps_hash_lock);
out_clear:
clear_bit(slot_idx, &efx->rps_slot_map);
return rc;
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o \
dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
- $(stmmac-y)
+ stmmac_tc.o $(stmmac-y)
# Ordering matters. Generic driver must be last.
obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o
unsigned int rx_fifo_size;
/* Automotive Safety Package */
unsigned int asp;
+ /* RX Parser */
+ unsigned int frpsel;
+ unsigned int frpbs;
+ unsigned int frpes;
};
/* GMAC TX FIFO is 8K, Rx FIFO is 16K */
const struct stmmac_dma_ops *dma;
const struct stmmac_mode_ops *mode;
const struct stmmac_hwtimestamp *ptp;
+ const struct stmmac_tc_ops *tc;
struct mii_regs mii; /* MII register Addresses */
struct mac_link link;
void __iomem *pcsr; /* vpointer to device CSRs */
#include <linux/io.h>
#include <linux/ioport.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/of_net.h>
#include <linux/mfd/syscon.h>
#include <linux/platform_device.h>
#define PRG_ETH0_RGMII_MODE BIT(0)
+#define PRG_ETH0_EXT_PHY_MODE_MASK GENMASK(2, 0)
+#define PRG_ETH0_EXT_RGMII_MODE 1
+#define PRG_ETH0_EXT_RMII_MODE 4
+
/* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */
#define PRG_ETH0_CLK_M250_SEL_SHIFT 4
#define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4)
#define MUX_CLK_NUM_PARENTS 2
+struct meson8b_dwmac;
+
+struct meson8b_dwmac_data {
+ int (*set_phy_mode)(struct meson8b_dwmac *dwmac);
+};
+
struct meson8b_dwmac {
- struct device *dev;
- void __iomem *regs;
- phy_interface_t phy_mode;
- struct clk *rgmii_tx_clk;
- u32 tx_delay_ns;
+ struct device *dev;
+ void __iomem *regs;
+
+ const struct meson8b_dwmac_data *data;
+ phy_interface_t phy_mode;
+ struct clk *rgmii_tx_clk;
+ u32 tx_delay_ns;
};
struct meson8b_dwmac_clk_configs {
return 0;
}
+static int meson8b_set_phy_mode(struct meson8b_dwmac *dwmac)
+{
+ switch (dwmac->phy_mode) {
+ case PHY_INTERFACE_MODE_RGMII:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ /* enable RGMII mode */
+ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
+ PRG_ETH0_RGMII_MODE,
+ PRG_ETH0_RGMII_MODE);
+ break;
+ case PHY_INTERFACE_MODE_RMII:
+ /* disable RGMII mode -> enables RMII mode */
+ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
+ PRG_ETH0_RGMII_MODE, 0);
+ break;
+ default:
+ dev_err(dwmac->dev, "fail to set phy-mode %s\n",
+ phy_modes(dwmac->phy_mode));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int meson_axg_set_phy_mode(struct meson8b_dwmac *dwmac)
+{
+ switch (dwmac->phy_mode) {
+ case PHY_INTERFACE_MODE_RGMII:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ /* enable RGMII mode */
+ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
+ PRG_ETH0_EXT_PHY_MODE_MASK,
+ PRG_ETH0_EXT_RGMII_MODE);
+ break;
+ case PHY_INTERFACE_MODE_RMII:
+ /* disable RGMII mode -> enables RMII mode */
+ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
+ PRG_ETH0_EXT_PHY_MODE_MASK,
+ PRG_ETH0_EXT_RMII_MODE);
+ break;
+ default:
+ dev_err(dwmac->dev, "fail to set phy-mode %s\n",
+ phy_modes(dwmac->phy_mode));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac)
{
int ret;
case PHY_INTERFACE_MODE_RGMII_ID:
case PHY_INTERFACE_MODE_RGMII_TXID:
- /* enable RGMII mode */
- meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE,
- PRG_ETH0_RGMII_MODE);
-
/* only relevant for RMII mode -> disable in RGMII mode */
meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
PRG_ETH0_INVERTED_RMII_CLK, 0);
break;
case PHY_INTERFACE_MODE_RMII:
- /* disable RGMII mode -> enables RMII mode */
- meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE,
- 0);
-
/* invert internal clk_rmii_i to generate 25/2.5 tx_rx_clk */
meson8b_dwmac_mask_bits(dwmac, PRG_ETH0,
PRG_ETH0_INVERTED_RMII_CLK,
goto err_remove_config_dt;
}
+ dwmac->data = (const struct meson8b_dwmac_data *)
+ of_device_get_match_data(&pdev->dev);
+ if (!dwmac->data)
+ return -EINVAL;
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
dwmac->regs = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(dwmac->regs)) {
if (ret)
goto err_remove_config_dt;
+ ret = dwmac->data->set_phy_mode(dwmac);
+ if (ret)
+ goto err_remove_config_dt;
+
ret = meson8b_init_prg_eth(dwmac);
if (ret)
goto err_remove_config_dt;
return ret;
}
+static const struct meson8b_dwmac_data meson8b_dwmac_data = {
+ .set_phy_mode = meson8b_set_phy_mode,
+};
+
+static const struct meson8b_dwmac_data meson_axg_dwmac_data = {
+ .set_phy_mode = meson_axg_set_phy_mode,
+};
+
static const struct of_device_id meson8b_dwmac_match[] = {
- { .compatible = "amlogic,meson8b-dwmac" },
- { .compatible = "amlogic,meson8m2-dwmac" },
- { .compatible = "amlogic,meson-gxbb-dwmac" },
+ {
+ .compatible = "amlogic,meson8b-dwmac",
+ .data = &meson8b_dwmac_data,
+ },
+ {
+ .compatible = "amlogic,meson8m2-dwmac",
+ .data = &meson8b_dwmac_data,
+ },
+ {
+ .compatible = "amlogic,meson-gxbb-dwmac",
+ .data = &meson8b_dwmac_data,
+ },
+ {
+ .compatible = "amlogic,meson-axg-dwmac",
+ .data = &meson_axg_dwmac_data,
+ },
{ }
};
MODULE_DEVICE_TABLE(of, meson8b_dwmac_match);
} else {
if (bsp_priv->clk_enabled) {
if (phy_iface == PHY_INTERFACE_MODE_RMII) {
- if (!IS_ERR(bsp_priv->mac_clk_rx))
- clk_disable_unprepare(
- bsp_priv->mac_clk_rx);
+ clk_disable_unprepare(bsp_priv->mac_clk_rx);
- if (!IS_ERR(bsp_priv->clk_mac_ref))
- clk_disable_unprepare(
- bsp_priv->clk_mac_ref);
+ clk_disable_unprepare(bsp_priv->clk_mac_ref);
- if (!IS_ERR(bsp_priv->clk_mac_refout))
- clk_disable_unprepare(
- bsp_priv->clk_mac_refout);
+ clk_disable_unprepare(bsp_priv->clk_mac_refout);
}
- if (!IS_ERR(bsp_priv->clk_phy))
- clk_disable_unprepare(bsp_priv->clk_phy);
+ clk_disable_unprepare(bsp_priv->clk_phy);
- if (!IS_ERR(bsp_priv->aclk_mac))
- clk_disable_unprepare(bsp_priv->aclk_mac);
+ clk_disable_unprepare(bsp_priv->aclk_mac);
- if (!IS_ERR(bsp_priv->pclk_mac))
- clk_disable_unprepare(bsp_priv->pclk_mac);
+ clk_disable_unprepare(bsp_priv->pclk_mac);
- if (!IS_ERR(bsp_priv->mac_clk_tx))
- clk_disable_unprepare(bsp_priv->mac_clk_tx);
+ clk_disable_unprepare(bsp_priv->mac_clk_tx);
/**
* if (!IS_ERR(bsp_priv->clk_mac))
* clk_disable_unprepare(bsp_priv->clk_mac);
* This value is used for disabling properly EMAC
* and used as a good starting value in case of the
* boot process(uboot) leave some stuff.
+ * @syscon_field reg_field for the syscon's gmac register
* @soc_has_internal_phy: Does the MAC embed an internal PHY
* @support_mii: Does the MAC handle MII
* @support_rmii: Does the MAC handle RMII
* @support_rgmii: Does the MAC handle RGMII
+ *
+ * @rx_delay_max: Maximum raw value for RX delay chain
+ * @tx_delay_max: Maximum raw value for TX delay chain
+ * These two also indicate the bitmask for
+ * the RX and TX delay chain registers. A
+ * value of zero indicates this is not supported.
*/
struct emac_variant {
u32 default_syscon_value;
+ const struct reg_field *syscon_field;
bool soc_has_internal_phy;
bool support_mii;
bool support_rmii;
bool support_rgmii;
+ u8 rx_delay_max;
+ u8 tx_delay_max;
};
/* struct sunxi_priv_data - hold all sunxi private data
struct regulator *regulator;
struct reset_control *rst_ephy;
const struct emac_variant *variant;
- struct regmap *regmap;
+ struct regmap_field *regmap_field;
bool internal_phy_powered;
void *mux_handle;
};
+/* EMAC clock register @ 0x30 in the "system control" address range */
+static const struct reg_field sun8i_syscon_reg_field = {
+ .reg = 0x30,
+ .lsb = 0,
+ .msb = 31,
+};
+
+/* EMAC clock register @ 0x164 in the CCU address range */
+static const struct reg_field sun8i_ccu_reg_field = {
+ .reg = 0x164,
+ .lsb = 0,
+ .msb = 31,
+};
+
static const struct emac_variant emac_variant_h3 = {
.default_syscon_value = 0x58000,
+ .syscon_field = &sun8i_syscon_reg_field,
.soc_has_internal_phy = true,
.support_mii = true,
.support_rmii = true,
- .support_rgmii = true
+ .support_rgmii = true,
+ .rx_delay_max = 31,
+ .tx_delay_max = 7,
};
static const struct emac_variant emac_variant_v3s = {
.default_syscon_value = 0x38000,
+ .syscon_field = &sun8i_syscon_reg_field,
.soc_has_internal_phy = true,
.support_mii = true
};
static const struct emac_variant emac_variant_a83t = {
.default_syscon_value = 0,
+ .syscon_field = &sun8i_syscon_reg_field,
.soc_has_internal_phy = false,
.support_mii = true,
- .support_rgmii = true
+ .support_rgmii = true,
+ .rx_delay_max = 31,
+ .tx_delay_max = 7,
+};
+
+static const struct emac_variant emac_variant_r40 = {
+ .default_syscon_value = 0,
+ .syscon_field = &sun8i_ccu_reg_field,
+ .support_mii = true,
+ .support_rgmii = true,
+ .rx_delay_max = 7,
};
static const struct emac_variant emac_variant_a64 = {
.default_syscon_value = 0,
+ .syscon_field = &sun8i_syscon_reg_field,
.soc_has_internal_phy = false,
.support_mii = true,
.support_rmii = true,
- .support_rgmii = true
+ .support_rgmii = true,
+ .rx_delay_max = 31,
+ .tx_delay_max = 7,
};
#define EMAC_BASIC_CTL0 0x00
#define SYSCON_RMII_EN BIT(13) /* 1: enable RMII (overrides EPIT) */
/* Generic system control EMAC_CLK bits */
-#define SYSCON_ETXDC_MASK GENMASK(2, 0)
#define SYSCON_ETXDC_SHIFT 10
-#define SYSCON_ERXDC_MASK GENMASK(4, 0)
#define SYSCON_ERXDC_SHIFT 5
/* EMAC PHY Interface Type */
#define SYSCON_EPIT BIT(2) /* 1: RGMII, 0: MII */
#define SYSCON_ETCS_MII 0x0
#define SYSCON_ETCS_EXT_GMII 0x1
#define SYSCON_ETCS_INT_GMII 0x2
-#define SYSCON_EMAC_REG 0x30
/* sun8i_dwmac_dma_reset() - reset the EMAC
* Called from stmmac via stmmac_dma_ops->reset
* Called from stmmac via stmmac_dma_ops->init
*/
static void sun8i_dwmac_dma_init(void __iomem *ioaddr,
- struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx, u32 dma_rx, int atds)
+ struct stmmac_dma_cfg *dma_cfg, int atds)
{
- /* Write TX and RX descriptors address */
- writel(dma_rx, ioaddr + EMAC_RX_DESC_LIST);
- writel(dma_tx, ioaddr + EMAC_TX_DESC_LIST);
-
writel(EMAC_RX_INT | EMAC_TX_INT, ioaddr + EMAC_INT_EN);
writel(0x1FFFFFF, ioaddr + EMAC_INT_STA);
}
+static void sun8i_dwmac_dma_init_rx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_rx_phy, u32 chan)
+{
+ /* Write RX descriptors address */
+ writel(dma_rx_phy, ioaddr + EMAC_RX_DESC_LIST);
+}
+
+static void sun8i_dwmac_dma_init_tx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_tx_phy, u32 chan)
+{
+ /* Write TX descriptors address */
+ writel(dma_tx_phy, ioaddr + EMAC_TX_DESC_LIST);
+}
+
/* sun8i_dwmac_dump_regs() - Dump EMAC address space
* Called from stmmac_dma_ops->dump_regs
* Used for ethtool
return ret;
}
-static void sun8i_dwmac_dma_operation_mode(void __iomem *ioaddr, int txmode,
- int rxmode, int rxfifosz)
+static void sun8i_dwmac_dma_operation_mode_rx(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz, u8 qmode)
+{
+ u32 v;
+
+ v = readl(ioaddr + EMAC_RX_CTL1);
+ if (mode == SF_DMA_MODE) {
+ v |= EMAC_RX_MD;
+ } else {
+ v &= ~EMAC_RX_MD;
+ v &= ~EMAC_RX_TH_MASK;
+ if (mode < 32)
+ v |= EMAC_RX_TH_32;
+ else if (mode < 64)
+ v |= EMAC_RX_TH_64;
+ else if (mode < 96)
+ v |= EMAC_RX_TH_96;
+ else if (mode < 128)
+ v |= EMAC_RX_TH_128;
+ }
+ writel(v, ioaddr + EMAC_RX_CTL1);
+}
+
+static void sun8i_dwmac_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz, u8 qmode)
{
u32 v;
v = readl(ioaddr + EMAC_TX_CTL1);
- if (txmode == SF_DMA_MODE) {
+ if (mode == SF_DMA_MODE) {
v |= EMAC_TX_MD;
/* Undocumented bit (called TX_NEXT_FRM in BSP), the original
* comment is
} else {
v &= ~EMAC_TX_MD;
v &= ~EMAC_TX_TH_MASK;
- if (txmode < 64)
+ if (mode < 64)
v |= EMAC_TX_TH_64;
- else if (txmode < 128)
+ else if (mode < 128)
v |= EMAC_TX_TH_128;
- else if (txmode < 192)
+ else if (mode < 192)
v |= EMAC_TX_TH_192;
- else if (txmode < 256)
+ else if (mode < 256)
v |= EMAC_TX_TH_256;
}
writel(v, ioaddr + EMAC_TX_CTL1);
-
- v = readl(ioaddr + EMAC_RX_CTL1);
- if (rxmode == SF_DMA_MODE) {
- v |= EMAC_RX_MD;
- } else {
- v &= ~EMAC_RX_MD;
- v &= ~EMAC_RX_TH_MASK;
- if (rxmode < 32)
- v |= EMAC_RX_TH_32;
- else if (rxmode < 64)
- v |= EMAC_RX_TH_64;
- else if (rxmode < 96)
- v |= EMAC_RX_TH_96;
- else if (rxmode < 128)
- v |= EMAC_RX_TH_128;
- }
- writel(v, ioaddr + EMAC_RX_CTL1);
}
static const struct stmmac_dma_ops sun8i_dwmac_dma_ops = {
.reset = sun8i_dwmac_dma_reset,
.init = sun8i_dwmac_dma_init,
+ .init_rx_chan = sun8i_dwmac_dma_init_rx,
+ .init_tx_chan = sun8i_dwmac_dma_init_tx,
.dump_regs = sun8i_dwmac_dump_regs,
- .dma_mode = sun8i_dwmac_dma_operation_mode,
+ .dma_rx_mode = sun8i_dwmac_dma_operation_mode_rx,
+ .dma_tx_mode = sun8i_dwmac_dma_operation_mode_tx,
.enable_dma_transmission = sun8i_dwmac_enable_dma_transmission,
.enable_dma_irq = sun8i_dwmac_enable_dma_irq,
.disable_dma_irq = sun8i_dwmac_disable_dma_irq,
bool need_power_ephy = false;
if (current_child ^ desired_child) {
- regmap_read(gmac->regmap, SYSCON_EMAC_REG, ®);
+ regmap_field_read(gmac->regmap_field, ®);
switch (desired_child) {
case DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID:
dev_info(priv->device, "Switch mux to internal PHY");
desired_child);
return -EINVAL;
}
- regmap_write(gmac->regmap, SYSCON_EMAC_REG, val);
+ regmap_field_write(gmac->regmap_field, val);
if (need_power_ephy) {
ret = sun8i_dwmac_power_internal_phy(priv);
if (ret)
int ret;
u32 reg, val;
- regmap_read(gmac->regmap, SYSCON_EMAC_REG, &val);
+ regmap_field_read(gmac->regmap_field, &val);
reg = gmac->variant->default_syscon_value;
if (reg != val)
dev_warn(priv->device,
}
val /= 100;
dev_dbg(priv->device, "set tx-delay to %x\n", val);
- if (val <= SYSCON_ETXDC_MASK) {
- reg &= ~(SYSCON_ETXDC_MASK << SYSCON_ETXDC_SHIFT);
+ if (val <= gmac->variant->tx_delay_max) {
+ reg &= ~(gmac->variant->tx_delay_max <<
+ SYSCON_ETXDC_SHIFT);
reg |= (val << SYSCON_ETXDC_SHIFT);
} else {
dev_err(priv->device, "Invalid TX clock delay: %d\n",
}
val /= 100;
dev_dbg(priv->device, "set rx-delay to %x\n", val);
- if (val <= SYSCON_ERXDC_MASK) {
- reg &= ~(SYSCON_ERXDC_MASK << SYSCON_ERXDC_SHIFT);
+ if (val <= gmac->variant->rx_delay_max) {
+ reg &= ~(gmac->variant->rx_delay_max <<
+ SYSCON_ERXDC_SHIFT);
reg |= (val << SYSCON_ERXDC_SHIFT);
} else {
dev_err(priv->device, "Invalid RX clock delay: %d\n",
return -EINVAL;
}
- regmap_write(gmac->regmap, SYSCON_EMAC_REG, reg);
+ regmap_field_write(gmac->regmap_field, reg);
return 0;
}
{
u32 reg = gmac->variant->default_syscon_value;
- regmap_write(gmac->regmap, SYSCON_EMAC_REG, reg);
+ regmap_field_write(gmac->regmap_field, reg);
}
static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv)
return mac;
}
+static struct regmap *sun8i_dwmac_get_syscon_from_dev(struct device_node *node)
+{
+ struct device_node *syscon_node;
+ struct platform_device *syscon_pdev;
+ struct regmap *regmap = NULL;
+
+ syscon_node = of_parse_phandle(node, "syscon", 0);
+ if (!syscon_node)
+ return ERR_PTR(-ENODEV);
+
+ syscon_pdev = of_find_device_by_node(syscon_node);
+ if (!syscon_pdev) {
+ /* platform device might not be probed yet */
+ regmap = ERR_PTR(-EPROBE_DEFER);
+ goto out_put_node;
+ }
+
+ /* If no regmap is found then the other device driver is at fault */
+ regmap = dev_get_regmap(&syscon_pdev->dev, NULL);
+ if (!regmap)
+ regmap = ERR_PTR(-EINVAL);
+
+ platform_device_put(syscon_pdev);
+out_put_node:
+ of_node_put(syscon_node);
+ return regmap;
+}
+
static int sun8i_dwmac_probe(struct platform_device *pdev)
{
struct plat_stmmacenet_data *plat_dat;
int ret;
struct stmmac_priv *priv;
struct net_device *ndev;
+ struct regmap *regmap;
ret = stmmac_get_platform_resources(pdev, &stmmac_res);
if (ret)
gmac->regulator = NULL;
}
- gmac->regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
- "syscon");
- if (IS_ERR(gmac->regmap)) {
- ret = PTR_ERR(gmac->regmap);
+ /* The "GMAC clock control" register might be located in the
+ * CCU address range (on the R40), or the system control address
+ * range (on most other sun8i and later SoCs).
+ *
+ * The former controls most if not all clocks in the SoC. The
+ * latter has an SoC identification register, and on some SoCs,
+ * controls to map device specific SRAM to either the intended
+ * peripheral, or the CPU address space.
+ *
+ * In either case, there should be a coordinated and restricted
+ * method of accessing the register needed here. This is done by
+ * having the device export a custom regmap, instead of a generic
+ * syscon, which grants all access to all registers.
+ *
+ * To support old device trees, we fall back to using the syscon
+ * interface if possible.
+ */
+ regmap = sun8i_dwmac_get_syscon_from_dev(pdev->dev.of_node);
+ if (IS_ERR(regmap))
+ regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+ "syscon");
+ if (IS_ERR(regmap)) {
+ ret = PTR_ERR(regmap);
dev_err(&pdev->dev, "Unable to map syscon: %d\n", ret);
return ret;
}
+ gmac->regmap_field = devm_regmap_field_alloc(dev, regmap,
+ *gmac->variant->syscon_field);
+ if (IS_ERR(gmac->regmap_field)) {
+ ret = PTR_ERR(gmac->regmap_field);
+ dev_err(dev, "Unable to map syscon register: %d\n", ret);
+ return ret;
+ }
+
plat_dat->interface = of_get_phy_mode(dev->of_node);
/* platform data specifying hardware features and callbacks.
.data = &emac_variant_v3s },
{ .compatible = "allwinner,sun8i-a83t-emac",
.data = &emac_variant_a83t },
+ { .compatible = "allwinner,sun8i-r40-gmac",
+ .data = &emac_variant_r40 },
{ .compatible = "allwinner,sun50i-a64-emac",
.data = &emac_variant_a64 },
{ }
}
static void dwmac1000_dma_init(void __iomem *ioaddr,
- struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx, u32 dma_rx, int atds)
+ struct stmmac_dma_cfg *dma_cfg, int atds)
{
u32 value = readl(ioaddr + DMA_BUS_MODE);
int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
/* Mask interrupts by writing to CSR7 */
writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
+}
- /* RX/TX descriptor base address lists must be written into
- * DMA CSR3 and CSR4, respectively
- */
- writel(dma_tx, ioaddr + DMA_TX_BASE_ADDR);
- writel(dma_rx, ioaddr + DMA_RCV_BASE_ADDR);
+static void dwmac1000_dma_init_rx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_rx_phy, u32 chan)
+{
+ /* RX descriptor base address list must be written into DMA CSR3 */
+ writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+}
+
+static void dwmac1000_dma_init_tx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_tx_phy, u32 chan)
+{
+ /* TX descriptor base address list must be written into DMA CSR4 */
+ writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
}
static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
return csr6;
}
-static void dwmac1000_dma_operation_mode(void __iomem *ioaddr, int txmode,
- int rxmode, int rxfifosz)
+static void dwmac1000_dma_operation_mode_rx(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz, u8 qmode)
+{
+ u32 csr6 = readl(ioaddr + DMA_CONTROL);
+
+ if (mode == SF_DMA_MODE) {
+ pr_debug("GMAC: enable RX store and forward mode\n");
+ csr6 |= DMA_CONTROL_RSF;
+ } else {
+ pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+ csr6 &= ~DMA_CONTROL_RSF;
+ csr6 &= DMA_CONTROL_TC_RX_MASK;
+ if (mode <= 32)
+ csr6 |= DMA_CONTROL_RTC_32;
+ else if (mode <= 64)
+ csr6 |= DMA_CONTROL_RTC_64;
+ else if (mode <= 96)
+ csr6 |= DMA_CONTROL_RTC_96;
+ else
+ csr6 |= DMA_CONTROL_RTC_128;
+ }
+
+ /* Configure flow control based on rx fifo size */
+ csr6 = dwmac1000_configure_fc(csr6, fifosz);
+
+ writel(csr6, ioaddr + DMA_CONTROL);
+}
+
+static void dwmac1000_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz, u8 qmode)
{
u32 csr6 = readl(ioaddr + DMA_CONTROL);
- if (txmode == SF_DMA_MODE) {
+ if (mode == SF_DMA_MODE) {
pr_debug("GMAC: enable TX store and forward mode\n");
/* Transmit COE type 2 cannot be done in cut-through mode. */
csr6 |= DMA_CONTROL_TSF;
*/
csr6 |= DMA_CONTROL_OSF;
} else {
- pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+ pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
csr6 &= ~DMA_CONTROL_TSF;
csr6 &= DMA_CONTROL_TC_TX_MASK;
/* Set the transmit threshold */
- if (txmode <= 32)
+ if (mode <= 32)
csr6 |= DMA_CONTROL_TTC_32;
- else if (txmode <= 64)
+ else if (mode <= 64)
csr6 |= DMA_CONTROL_TTC_64;
- else if (txmode <= 128)
+ else if (mode <= 128)
csr6 |= DMA_CONTROL_TTC_128;
- else if (txmode <= 192)
+ else if (mode <= 192)
csr6 |= DMA_CONTROL_TTC_192;
else
csr6 |= DMA_CONTROL_TTC_256;
}
- if (rxmode == SF_DMA_MODE) {
- pr_debug("GMAC: enable RX store and forward mode\n");
- csr6 |= DMA_CONTROL_RSF;
- } else {
- pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
- csr6 &= ~DMA_CONTROL_RSF;
- csr6 &= DMA_CONTROL_TC_RX_MASK;
- if (rxmode <= 32)
- csr6 |= DMA_CONTROL_RTC_32;
- else if (rxmode <= 64)
- csr6 |= DMA_CONTROL_RTC_64;
- else if (rxmode <= 96)
- csr6 |= DMA_CONTROL_RTC_96;
- else
- csr6 |= DMA_CONTROL_RTC_128;
- }
-
- /* Configure flow control based on rx fifo size */
- csr6 = dwmac1000_configure_fc(csr6, rxfifosz);
-
writel(csr6, ioaddr + DMA_CONTROL);
}
const struct stmmac_dma_ops dwmac1000_dma_ops = {
.reset = dwmac_dma_reset,
.init = dwmac1000_dma_init,
+ .init_rx_chan = dwmac1000_dma_init_rx,
+ .init_tx_chan = dwmac1000_dma_init_tx,
.axi = dwmac1000_dma_axi,
.dump_regs = dwmac1000_dump_dma_regs,
- .dma_mode = dwmac1000_dma_operation_mode,
+ .dma_rx_mode = dwmac1000_dma_operation_mode_rx,
+ .dma_tx_mode = dwmac1000_dma_operation_mode_tx,
.enable_dma_transmission = dwmac_enable_dma_transmission,
.enable_dma_irq = dwmac_enable_dma_irq,
.disable_dma_irq = dwmac_disable_dma_irq,
#include "dwmac_dma.h"
static void dwmac100_dma_init(void __iomem *ioaddr,
- struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx, u32 dma_rx, int atds)
+ struct stmmac_dma_cfg *dma_cfg, int atds)
{
/* Enable Application Access by writing to DMA CSR0 */
writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT),
/* Mask interrupts by writing to CSR7 */
writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
+}
- /* RX/TX descriptor base addr lists must be written into
- * DMA CSR3 and CSR4, respectively
- */
- writel(dma_tx, ioaddr + DMA_TX_BASE_ADDR);
- writel(dma_rx, ioaddr + DMA_RCV_BASE_ADDR);
+static void dwmac100_dma_init_rx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_rx_phy, u32 chan)
+{
+ /* RX descriptor base addr lists must be written into DMA CSR3 */
+ writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+}
+
+static void dwmac100_dma_init_tx(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_tx_phy, u32 chan)
+{
+ /* TX descriptor base addr lists must be written into DMA CSR4 */
+ writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
}
/* Store and Forward capability is not used at all.
* The transmit threshold can be programmed by setting the TTC bits in the DMA
* control register.
*/
-static void dwmac100_dma_operation_mode(void __iomem *ioaddr, int txmode,
- int rxmode, int rxfifosz)
+static void dwmac100_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz, u8 qmode)
{
u32 csr6 = readl(ioaddr + DMA_CONTROL);
- if (txmode <= 32)
+ if (mode <= 32)
csr6 |= DMA_CONTROL_TTC_32;
- else if (txmode <= 64)
+ else if (mode <= 64)
csr6 |= DMA_CONTROL_TTC_64;
else
csr6 |= DMA_CONTROL_TTC_128;
const struct stmmac_dma_ops dwmac100_dma_ops = {
.reset = dwmac_dma_reset,
.init = dwmac100_dma_init,
+ .init_rx_chan = dwmac100_dma_init_rx,
+ .init_tx_chan = dwmac100_dma_init_tx,
.dump_regs = dwmac100_dump_dma_regs,
- .dma_mode = dwmac100_dma_operation_mode,
+ .dma_tx_mode = dwmac100_dma_operation_mode_tx,
.dma_diagnostic_fr = dwmac100_dma_diagnostic_fr,
.enable_dma_transmission = dwmac_enable_dma_transmission,
.enable_dma_irq = dwmac_enable_dma_irq,
/* MAC HW features3 bitmap */
#define GMAC_HW_FEAT_ASP GENMASK(29, 28)
+#define GMAC_HW_FEAT_FRPES GENMASK(14, 13)
+#define GMAC_HW_FEAT_FRPBS GENMASK(12, 11)
+#define GMAC_HW_FEAT_FRPSEL BIT(10)
/* MAC HW ADDR regs */
#define GMAC_HI_DCS GENMASK(18, 16)
/* MTL registers */
#define MTL_OPERATION_MODE 0x00000c00
+#define MTL_FRPE BIT(15)
#define MTL_OPERATION_SCHALG_MASK GENMASK(6, 5)
#define MTL_OPERATION_SCHALG_WRR (0x0 << 5)
#define MTL_OPERATION_SCHALG_WFQ (0x1 << 5)
.safety_feat_config = dwmac5_safety_feat_config,
.safety_feat_irq_status = dwmac5_safety_feat_irq_status,
.safety_feat_dump = dwmac5_safety_feat_dump,
+ .rxp_config = dwmac5_rxp_config,
};
int dwmac4_setup(struct stmmac_priv *priv)
p->des3 |= cpu_to_le32(TDES3_OWN);
}
-static void dwmac4_set_rx_owner(struct dma_desc *p)
+static void dwmac4_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
{
- p->des3 |= cpu_to_le32(RDES3_OWN);
+ p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
+
+ if (!disable_rx_ic)
+ p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
}
static int dwmac4_get_tx_ls(struct dma_desc *p)
static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
int mode, int end)
{
- p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
-
- if (!disable_rx_ic)
- p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
+ dwmac4_set_rx_owner(p, disable_rx_ic);
}
static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
p->des3 = cpu_to_le32(TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV);
}
+static void dwmac4_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+ *addr = le32_to_cpu(p->des0);
+}
+
+static void dwmac4_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+ p->des0 = cpu_to_le32(addr);
+ p->des1 = 0;
+}
+
+static void dwmac4_clear(struct dma_desc *p)
+{
+ p->des0 = 0;
+ p->des1 = 0;
+ p->des2 = 0;
+ p->des3 = 0;
+}
+
const struct stmmac_desc_ops dwmac4_desc_ops = {
.tx_status = dwmac4_wrback_get_tx_status,
.rx_status = dwmac4_wrback_get_rx_status,
.init_tx_desc = dwmac4_rd_init_tx_desc,
.display_ring = dwmac4_display_ring,
.set_mss = dwmac4_set_mss_ctxt,
+ .get_addr = dwmac4_get_addr,
+ .set_addr = dwmac4_set_addr,
+ .clear = dwmac4_clear,
};
const struct stmmac_mode_ops dwmac4_ring_mode_ops = { };
value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
+
+ /* Enable OSP to get best performance */
+ value |= DMA_CONTROL_OSP;
+
writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
}
static void dwmac4_dma_init(void __iomem *ioaddr,
- struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx, u32 dma_rx, int atds)
+ struct stmmac_dma_cfg *dma_cfg, int atds)
{
u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
/* 5.10 Features */
dma_cap->asp = (hw_cap & GMAC_HW_FEAT_ASP) >> 28;
+ dma_cap->frpes = (hw_cap & GMAC_HW_FEAT_FRPES) >> 13;
+ dma_cap->frpbs = (hw_cap & GMAC_HW_FEAT_FRPBS) >> 11;
+ dma_cap->frpsel = (hw_cap & GMAC_HW_FEAT_FRPSEL) >> 10;
}
/* Enable/disable TSO feature and set MSS */
#define DMA_CHAN0_DBG_STAT_RPS_SHIFT 8
int dwmac4_dma_reset(void __iomem *ioaddr);
-void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
#include "common.h"
#include "dwmac4.h"
#include "dwmac5.h"
+#include "stmmac.h"
struct dwmac5_error_desc {
bool valid;
*desc = dwmac5_all_errors[module].desc[offset].desc;
return 0;
}
+
+static int dwmac5_rxp_disable(void __iomem *ioaddr)
+{
+ u32 val;
+ int ret;
+
+ val = readl(ioaddr + MTL_OPERATION_MODE);
+ val &= ~MTL_FRPE;
+ writel(val, ioaddr + MTL_OPERATION_MODE);
+
+ ret = readl_poll_timeout(ioaddr + MTL_RXP_CONTROL_STATUS, val,
+ val & RXPI, 1, 10000);
+ if (ret)
+ return ret;
+ return 0;
+}
+
+static void dwmac5_rxp_enable(void __iomem *ioaddr)
+{
+ u32 val;
+
+ val = readl(ioaddr + MTL_OPERATION_MODE);
+ val |= MTL_FRPE;
+ writel(val, ioaddr + MTL_OPERATION_MODE);
+}
+
+static int dwmac5_rxp_update_single_entry(void __iomem *ioaddr,
+ struct stmmac_tc_entry *entry,
+ int pos)
+{
+ int ret, i;
+
+ for (i = 0; i < (sizeof(entry->val) / sizeof(u32)); i++) {
+ int real_pos = pos * (sizeof(entry->val) / sizeof(u32)) + i;
+ u32 val;
+
+ /* Wait for ready */
+ ret = readl_poll_timeout(ioaddr + MTL_RXP_IACC_CTRL_STATUS,
+ val, !(val & STARTBUSY), 1, 10000);
+ if (ret)
+ return ret;
+
+ /* Write data */
+ val = *((u32 *)&entry->val + i);
+ writel(val, ioaddr + MTL_RXP_IACC_DATA);
+
+ /* Write pos */
+ val = real_pos & ADDR;
+ writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS);
+
+ /* Write OP */
+ val |= WRRDN;
+ writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS);
+
+ /* Start Write */
+ val |= STARTBUSY;
+ writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS);
+
+ /* Wait for done */
+ ret = readl_poll_timeout(ioaddr + MTL_RXP_IACC_CTRL_STATUS,
+ val, !(val & STARTBUSY), 1, 10000);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static struct stmmac_tc_entry *
+dwmac5_rxp_get_next_entry(struct stmmac_tc_entry *entries, unsigned int count,
+ u32 curr_prio)
+{
+ struct stmmac_tc_entry *entry;
+ u32 min_prio = ~0x0;
+ int i, min_prio_idx;
+ bool found = false;
+
+ for (i = count - 1; i >= 0; i--) {
+ entry = &entries[i];
+
+ /* Do not update unused entries */
+ if (!entry->in_use)
+ continue;
+ /* Do not update already updated entries (i.e. fragments) */
+ if (entry->in_hw)
+ continue;
+ /* Let last entry be updated last */
+ if (entry->is_last)
+ continue;
+ /* Do not return fragments */
+ if (entry->is_frag)
+ continue;
+ /* Check if we already checked this prio */
+ if (entry->prio < curr_prio)
+ continue;
+ /* Check if this is the minimum prio */
+ if (entry->prio < min_prio) {
+ min_prio = entry->prio;
+ min_prio_idx = i;
+ found = true;
+ }
+ }
+
+ if (found)
+ return &entries[min_prio_idx];
+ return NULL;
+}
+
+int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries,
+ unsigned int count)
+{
+ struct stmmac_tc_entry *entry, *frag;
+ int i, ret, nve = 0;
+ u32 curr_prio = 0;
+ u32 old_val, val;
+
+ /* Force disable RX */
+ old_val = readl(ioaddr + GMAC_CONFIG);
+ val = old_val & ~GMAC_CONFIG_RE;
+ writel(val, ioaddr + GMAC_CONFIG);
+
+ /* Disable RX Parser */
+ ret = dwmac5_rxp_disable(ioaddr);
+ if (ret)
+ goto re_enable;
+
+ /* Set all entries as NOT in HW */
+ for (i = 0; i < count; i++) {
+ entry = &entries[i];
+ entry->in_hw = false;
+ }
+
+ /* Update entries by reverse order */
+ while (1) {
+ entry = dwmac5_rxp_get_next_entry(entries, count, curr_prio);
+ if (!entry)
+ break;
+
+ curr_prio = entry->prio;
+ frag = entry->frag_ptr;
+
+ /* Set special fragment requirements */
+ if (frag) {
+ entry->val.af = 0;
+ entry->val.rf = 0;
+ entry->val.nc = 1;
+ entry->val.ok_index = nve + 2;
+ }
+
+ ret = dwmac5_rxp_update_single_entry(ioaddr, entry, nve);
+ if (ret)
+ goto re_enable;
+
+ entry->table_pos = nve++;
+ entry->in_hw = true;
+
+ if (frag && !frag->in_hw) {
+ ret = dwmac5_rxp_update_single_entry(ioaddr, frag, nve);
+ if (ret)
+ goto re_enable;
+ frag->table_pos = nve++;
+ frag->in_hw = true;
+ }
+ }
+
+ if (!nve)
+ goto re_enable;
+
+ /* Update all pass entry */
+ for (i = 0; i < count; i++) {
+ entry = &entries[i];
+ if (!entry->is_last)
+ continue;
+
+ ret = dwmac5_rxp_update_single_entry(ioaddr, entry, nve);
+ if (ret)
+ goto re_enable;
+
+ entry->table_pos = nve++;
+ }
+
+ /* Assume n. of parsable entries == n. of valid entries */
+ val = (nve << 16) & NPE;
+ val |= nve & NVE;
+ writel(val, ioaddr + MTL_RXP_CONTROL_STATUS);
+
+ /* Enable RX Parser */
+ dwmac5_rxp_enable(ioaddr);
+
+re_enable:
+ /* Re-enable RX */
+ writel(old_val, ioaddr + GMAC_CONFIG);
+ return ret;
+}
#define PRTYEN BIT(1)
#define TMOUTEN BIT(0)
+#define MTL_RXP_CONTROL_STATUS 0x00000ca0
+#define RXPI BIT(31)
+#define NPE GENMASK(23, 16)
+#define NVE GENMASK(7, 0)
+#define MTL_RXP_IACC_CTRL_STATUS 0x00000cb0
+#define STARTBUSY BIT(31)
+#define RXPEIEC GENMASK(22, 21)
+#define RXPEIEE BIT(20)
+#define WRRDN BIT(16)
+#define ADDR GENMASK(15, 0)
+#define MTL_RXP_IACC_DATA 0x00000cb4
#define MTL_ECC_CONTROL 0x00000cc0
#define TSOEE BIT(4)
#define MRXPEE BIT(3)
struct stmmac_safety_stats *stats);
int dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats,
int index, unsigned long *count, const char **desc);
+int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries,
+ unsigned int count);
#endif /* __DWMAC5_H__ */
p->des0 |= cpu_to_le32(ETDES0_OWN);
}
-static void enh_desc_set_rx_owner(struct dma_desc *p)
+static void enh_desc_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
{
p->des0 |= cpu_to_le32(RDES0_OWN);
}
pr_info("\n");
}
+static void enh_desc_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+ *addr = le32_to_cpu(p->des2);
+}
+
+static void enh_desc_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+ p->des2 = cpu_to_le32(addr);
+}
+
+static void enh_desc_clear(struct dma_desc *p)
+{
+ p->des2 = 0;
+}
+
const struct stmmac_desc_ops enh_desc_ops = {
.tx_status = enh_desc_get_tx_status,
.rx_status = enh_desc_get_rx_status,
.get_timestamp = enh_desc_get_timestamp,
.get_rx_timestamp_status = enh_desc_get_rx_timestamp_status,
.display_ring = enh_desc_display_ring,
+ .get_addr = enh_desc_get_addr,
+ .set_addr = enh_desc_set_addr,
+ .clear = enh_desc_clear,
};
#include "common.h"
#include "stmmac.h"
+#include "stmmac_ptp.h"
static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg)
{
bool gmac;
bool gmac4;
u32 min_id;
+ const struct stmmac_regs_off regs;
const void *desc;
const void *dma;
const void *mac;
const void *hwtimestamp;
const void *mode;
+ const void *tc;
int (*setup)(struct stmmac_priv *priv);
int (*quirks)(struct stmmac_priv *priv);
} stmmac_hw[] = {
.gmac = false,
.gmac4 = false,
.min_id = 0,
+ .regs = {
+ .ptp_off = PTP_GMAC3_X_OFFSET,
+ .mmc_off = MMC_GMAC3_X_OFFSET,
+ },
.desc = NULL,
.dma = &dwmac100_dma_ops,
.mac = &dwmac100_ops,
.hwtimestamp = &stmmac_ptp,
.mode = NULL,
+ .tc = NULL,
.setup = dwmac100_setup,
.quirks = stmmac_dwmac1_quirks,
}, {
.gmac = true,
.gmac4 = false,
.min_id = 0,
+ .regs = {
+ .ptp_off = PTP_GMAC3_X_OFFSET,
+ .mmc_off = MMC_GMAC3_X_OFFSET,
+ },
.desc = NULL,
.dma = &dwmac1000_dma_ops,
.mac = &dwmac1000_ops,
.hwtimestamp = &stmmac_ptp,
.mode = NULL,
+ .tc = NULL,
.setup = dwmac1000_setup,
.quirks = stmmac_dwmac1_quirks,
}, {
.gmac = false,
.gmac4 = true,
.min_id = 0,
+ .regs = {
+ .ptp_off = PTP_GMAC4_OFFSET,
+ .mmc_off = MMC_GMAC4_OFFSET,
+ },
.desc = &dwmac4_desc_ops,
.dma = &dwmac4_dma_ops,
.mac = &dwmac4_ops,
.hwtimestamp = &stmmac_ptp,
.mode = NULL,
+ .tc = NULL,
.setup = dwmac4_setup,
.quirks = stmmac_dwmac4_quirks,
}, {
.gmac = false,
.gmac4 = true,
.min_id = DWMAC_CORE_4_00,
+ .regs = {
+ .ptp_off = PTP_GMAC4_OFFSET,
+ .mmc_off = MMC_GMAC4_OFFSET,
+ },
.desc = &dwmac4_desc_ops,
.dma = &dwmac4_dma_ops,
.mac = &dwmac410_ops,
.hwtimestamp = &stmmac_ptp,
.mode = &dwmac4_ring_mode_ops,
+ .tc = NULL,
.setup = dwmac4_setup,
.quirks = NULL,
}, {
.gmac = false,
.gmac4 = true,
.min_id = DWMAC_CORE_4_10,
+ .regs = {
+ .ptp_off = PTP_GMAC4_OFFSET,
+ .mmc_off = MMC_GMAC4_OFFSET,
+ },
.desc = &dwmac4_desc_ops,
.dma = &dwmac410_dma_ops,
.mac = &dwmac410_ops,
.hwtimestamp = &stmmac_ptp,
.mode = &dwmac4_ring_mode_ops,
+ .tc = NULL,
.setup = dwmac4_setup,
.quirks = NULL,
}, {
.gmac = false,
.gmac4 = true,
.min_id = DWMAC_CORE_5_10,
+ .regs = {
+ .ptp_off = PTP_GMAC4_OFFSET,
+ .mmc_off = MMC_GMAC4_OFFSET,
+ },
.desc = &dwmac4_desc_ops,
.dma = &dwmac410_dma_ops,
.mac = &dwmac510_ops,
.hwtimestamp = &stmmac_ptp,
.mode = &dwmac4_ring_mode_ops,
+ .tc = &dwmac510_tc_ops,
.setup = dwmac4_setup,
.quirks = NULL,
}
bool needs_gmac = priv->plat->has_gmac;
const struct stmmac_hwif_entry *entry;
struct mac_device_info *mac;
+ bool needs_setup = true;
int i, ret;
u32 id;
if (needs_gmac) {
id = stmmac_get_id(priv, GMAC_VERSION);
- } else {
+ } else if (needs_gmac4) {
id = stmmac_get_id(priv, GMAC4_VERSION);
+ } else {
+ id = 0;
}
/* Save ID for later use */
priv->synopsys_id = id;
+ /* Lets assume some safe values first */
+ priv->ptpaddr = priv->ioaddr +
+ (needs_gmac4 ? PTP_GMAC4_OFFSET : PTP_GMAC3_X_OFFSET);
+ priv->mmcaddr = priv->ioaddr +
+ (needs_gmac4 ? MMC_GMAC4_OFFSET : MMC_GMAC3_X_OFFSET);
+
/* Check for HW specific setup first */
if (priv->plat->setup) {
- priv->hw = priv->plat->setup(priv);
- if (!priv->hw)
- return -ENOMEM;
- return 0;
+ mac = priv->plat->setup(priv);
+ needs_setup = false;
+ } else {
+ mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
}
- mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
if (!mac)
return -ENOMEM;
continue;
if (needs_gmac4 ^ entry->gmac4)
continue;
- if (id < entry->min_id)
+ /* Use synopsys_id var because some setups can override this */
+ if (priv->synopsys_id < entry->min_id)
continue;
- mac->desc = entry->desc;
- mac->dma = entry->dma;
- mac->mac = entry->mac;
- mac->ptp = entry->hwtimestamp;
- mac->mode = entry->mode;
+ /* Only use generic HW helpers if needed */
+ mac->desc = mac->desc ? : entry->desc;
+ mac->dma = mac->dma ? : entry->dma;
+ mac->mac = mac->mac ? : entry->mac;
+ mac->ptp = mac->ptp ? : entry->hwtimestamp;
+ mac->mode = mac->mode ? : entry->mode;
+ mac->tc = mac->tc ? : entry->tc;
priv->hw = mac;
+ priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off;
+ priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off;
/* Entry found */
- ret = entry->setup(priv);
- if (ret)
- return ret;
+ if (needs_setup) {
+ ret = entry->setup(priv);
+ if (ret)
+ return ret;
+ }
/* Run quirks, if needed */
if (entry->quirks) {
#ifndef __STMMAC_HWIF_H__
#define __STMMAC_HWIF_H__
+#include <linux/netdevice.h>
+
#define stmmac_do_void_callback(__priv, __module, __cname, __arg0, __args...) \
({ \
int __result = -EINVAL; \
- if ((__priv)->hw->__module->__cname) { \
+ if ((__priv)->hw->__module && (__priv)->hw->__module->__cname) { \
(__priv)->hw->__module->__cname((__arg0), ##__args); \
__result = 0; \
} \
#define stmmac_do_callback(__priv, __module, __cname, __arg0, __args...) \
({ \
int __result = -EINVAL; \
- if ((__priv)->hw->__module->__cname) \
+ if ((__priv)->hw->__module && (__priv)->hw->__module->__cname) \
__result = (__priv)->hw->__module->__cname((__arg0), ##__args); \
__result; \
})
/* Get the buffer size from the descriptor */
int (*get_tx_len)(struct dma_desc *p);
/* Handle extra events on specific interrupts hw dependent */
- void (*set_rx_owner)(struct dma_desc *p);
+ void (*set_rx_owner)(struct dma_desc *p, int disable_rx_ic);
/* Get the receive frame size */
int (*get_rx_frame_len)(struct dma_desc *p, int rx_coe_type);
/* Return the reception status looking at the RDES1 */
void (*display_ring)(void *head, unsigned int size, bool rx);
/* set MSS via context descriptor */
void (*set_mss)(struct dma_desc *p, unsigned int mss);
+ /* get descriptor skbuff address */
+ void (*get_addr)(struct dma_desc *p, unsigned int *addr);
+ /* set descriptor skbuff address */
+ void (*set_addr)(struct dma_desc *p, dma_addr_t addr);
+ /* clear descriptor */
+ void (*clear)(struct dma_desc *p);
};
#define stmmac_init_rx_desc(__priv, __args...) \
stmmac_do_void_callback(__priv, desc, display_ring, __args)
#define stmmac_set_mss(__priv, __args...) \
stmmac_do_void_callback(__priv, desc, set_mss, __args)
+#define stmmac_get_desc_addr(__priv, __args...) \
+ stmmac_do_void_callback(__priv, desc, get_addr, __args)
+#define stmmac_set_desc_addr(__priv, __args...) \
+ stmmac_do_void_callback(__priv, desc, set_addr, __args)
+#define stmmac_clear_desc(__priv, __args...) \
+ stmmac_do_void_callback(__priv, desc, clear, __args)
struct stmmac_dma_cfg;
struct dma_features;
/* DMA core initialization */
int (*reset)(void __iomem *ioaddr);
void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx, u32 dma_rx, int atds);
+ int atds);
void (*init_chan)(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg, u32 chan);
void (*init_rx_chan)(void __iomem *ioaddr,
void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
/* Dump DMA registers */
void (*dump_regs)(void __iomem *ioaddr, u32 *reg_space);
- /* Set tx/rx threshold in the csr6 register
- * An invalid value enables the store-and-forward mode */
- void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
- int rxfifosz);
void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
int fifosz, u8 qmode);
void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel,
stmmac_do_void_callback(__priv, dma, axi, __args)
#define stmmac_dump_dma_regs(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, dump_regs, __args)
-#define stmmac_dma_mode(__priv, __args...) \
- stmmac_do_void_callback(__priv, dma, dma_mode, __args)
#define stmmac_dma_rx_mode(__priv, __args...) \
stmmac_do_void_callback(__priv, dma, dma_rx_mode, __args)
#define stmmac_dma_tx_mode(__priv, __args...) \
struct net_device;
struct rgmii_adv;
struct stmmac_safety_stats;
+struct stmmac_tc_entry;
/* Helpers to program the MAC core */
struct stmmac_ops {
struct stmmac_safety_stats *stats);
int (*safety_feat_dump)(struct stmmac_safety_stats *stats,
int index, unsigned long *count, const char **desc);
+ /* Flexible RX Parser */
+ int (*rxp_config)(void __iomem *ioaddr, struct stmmac_tc_entry *entries,
+ unsigned int count);
};
#define stmmac_core_init(__priv, __args...) \
stmmac_do_callback(__priv, mac, safety_feat_irq_status, __args)
#define stmmac_safety_feat_dump(__priv, __args...) \
stmmac_do_callback(__priv, mac, safety_feat_dump, __args)
+#define stmmac_rxp_config(__priv, __args...) \
+ stmmac_do_callback(__priv, mac, rxp_config, __args)
/* PTP and HW Timer helpers */
struct stmmac_hwtimestamp {
stmmac_do_void_callback(__priv, mode, clean_desc3, __args)
struct stmmac_priv;
+struct tc_cls_u32_offload;
+
+struct stmmac_tc_ops {
+ int (*init)(struct stmmac_priv *priv);
+ int (*setup_cls_u32)(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls);
+};
+
+#define stmmac_tc_init(__priv, __args...) \
+ stmmac_do_callback(__priv, tc, init, __args)
+#define stmmac_tc_setup_cls_u32(__priv, __args...) \
+ stmmac_do_callback(__priv, tc, setup_cls_u32, __args)
+
+struct stmmac_regs_off {
+ u32 ptp_off;
+ u32 mmc_off;
+};
extern const struct stmmac_ops dwmac100_ops;
extern const struct stmmac_dma_ops dwmac100_dma_ops;
extern const struct stmmac_ops dwmac410_ops;
extern const struct stmmac_dma_ops dwmac410_dma_ops;
extern const struct stmmac_ops dwmac510_ops;
+extern const struct stmmac_tc_ops dwmac510_tc_ops;
#define GMAC_VERSION 0x00000020 /* GMAC CORE Version */
#define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */
p->des0 |= cpu_to_le32(TDES0_OWN);
}
-static void ndesc_set_rx_owner(struct dma_desc *p)
+static void ndesc_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
{
p->des0 |= cpu_to_le32(RDES0_OWN);
}
pr_info("\n");
}
+static void ndesc_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+ *addr = le32_to_cpu(p->des2);
+}
+
+static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+ p->des2 = cpu_to_le32(addr);
+}
+
+static void ndesc_clear(struct dma_desc *p)
+{
+ p->des2 = 0;
+}
+
const struct stmmac_desc_ops ndesc_ops = {
.tx_status = ndesc_get_tx_status,
.rx_status = ndesc_get_rx_status,
.get_timestamp = ndesc_get_timestamp,
.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
.display_ring = ndesc_display_ring,
+ .get_addr = ndesc_get_addr,
+ .set_addr = ndesc_set_addr,
+ .clear = ndesc_clear,
};
struct napi_struct napi ____cacheline_aligned_in_smp;
};
+struct stmmac_tc_entry {
+ bool in_use;
+ bool in_hw;
+ bool is_last;
+ bool is_frag;
+ void *frag_ptr;
+ unsigned int table_pos;
+ u32 handle;
+ u32 prio;
+ struct {
+ u32 match_data;
+ u32 match_en;
+ u8 af:1;
+ u8 rf:1;
+ u8 im:1;
+ u8 nc:1;
+ u8 res1:4;
+ u8 frame_offset;
+ u8 ok_index;
+ u8 dma_ch_no;
+ u32 res2;
+ } __packed val;
+};
+
struct stmmac_priv {
/* Frequently used values are kept adjacent for cache effect */
u32 tx_count_frames;
u32 tx_coal_frames;
u32 tx_coal_timer;
+ bool tx_timer_armed;
int tx_coalesce;
int hwts_tx_en;
unsigned long state;
struct workqueue_struct *wq;
struct work_struct service_task;
+
+ /* TC Handling */
+ unsigned int tc_entries_max;
+ unsigned int tc_off_max;
+ struct stmmac_tc_entry *tc_entries;
};
enum stmmac_state {
#include <linux/seq_file.h>
#endif /* CONFIG_DEBUG_FS */
#include <linux/net_tstamp.h>
+#include <net/pkt_cls.h>
#include "stmmac_ptp.h"
#include "stmmac.h"
#include <linux/reset.h>
return -EINVAL;
}
- if (priv->synopsys_id >= DWMAC_CORE_4_00)
- p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
- else
- p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
+ stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[i]);
if (priv->dma_buf_sz == BUF_SIZE_16KiB)
stmmac_init_desc3(priv, p);
else
p = tx_q->dma_tx + i;
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- p->des0 = 0;
- p->des1 = 0;
- p->des2 = 0;
- p->des3 = 0;
- } else {
- p->des2 = 0;
- }
+ stmmac_clear_desc(priv, p);
tx_q->tx_skbuff_dma[i].buf = 0;
tx_q->tx_skbuff_dma[i].map_as_page = false;
}
/* configure all channels */
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- for (chan = 0; chan < rx_channels_count; chan++) {
- qmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
+ for (chan = 0; chan < rx_channels_count; chan++) {
+ qmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
- stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
- rxfifosz, qmode);
- }
+ stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
+ rxfifosz, qmode);
+ }
- for (chan = 0; chan < tx_channels_count; chan++) {
- qmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
+ for (chan = 0; chan < tx_channels_count; chan++) {
+ qmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
- stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan,
- txfifosz, qmode);
- }
- } else {
- stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz);
+ stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan,
+ txfifosz, qmode);
}
}
rxfifosz /= rx_channels_count;
txfifosz /= tx_channels_count;
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz,
- rxqmode);
- stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, txfifosz,
- txqmode);
- } else {
- stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz);
- }
+ stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz, rxqmode);
+ stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, txfifosz, txqmode);
}
static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv)
{
- int ret = false;
+ int ret;
- /* Safety features are only available in cores >= 5.10 */
- if (priv->synopsys_id < DWMAC_CORE_5_10)
- return ret;
ret = stmmac_safety_feat_irq_status(priv, priv->dev,
priv->ioaddr, priv->dma_cap.asp, &priv->sstats);
if (ret && (ret != -EINVAL)) {
tx_channel_count : rx_channel_count;
u32 chan;
bool poll_scheduled = false;
- int status[channels_to_check];
+ int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)];
+
+ /* Make sure we never check beyond our status buffer. */
+ if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status)))
+ channels_to_check = ARRAY_SIZE(status);
/* Each DMA channel can be used for rx and tx simultaneously, yet
* napi_struct is embedded in struct stmmac_rx_queue rather than in a
unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET;
- priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET;
- } else {
- priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET;
- priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET;
- }
-
dwmac_mmc_intr_all_mask(priv->mmcaddr);
if (priv->dma_cap.rmon) {
{
u32 rx_channels_count = priv->plat->rx_queues_to_use;
u32 tx_channels_count = priv->plat->tx_queues_to_use;
+ u32 dma_csr_ch = max(rx_channels_count, tx_channels_count);
struct stmmac_rx_queue *rx_q;
struct stmmac_tx_queue *tx_q;
- u32 dummy_dma_rx_phy = 0;
- u32 dummy_dma_tx_phy = 0;
u32 chan = 0;
int atds = 0;
int ret = 0;
return ret;
}
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- /* DMA Configuration */
- stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg,
- dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
-
- /* DMA RX Channel Configuration */
- for (chan = 0; chan < rx_channels_count; chan++) {
- rx_q = &priv->rx_queue[chan];
-
- stmmac_init_rx_chan(priv, priv->ioaddr,
- priv->plat->dma_cfg, rx_q->dma_rx_phy,
- chan);
-
- rx_q->rx_tail_addr = rx_q->dma_rx_phy +
- (DMA_RX_SIZE * sizeof(struct dma_desc));
- stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
- rx_q->rx_tail_addr, chan);
- }
-
- /* DMA TX Channel Configuration */
- for (chan = 0; chan < tx_channels_count; chan++) {
- tx_q = &priv->tx_queue[chan];
+ /* DMA RX Channel Configuration */
+ for (chan = 0; chan < rx_channels_count; chan++) {
+ rx_q = &priv->rx_queue[chan];
- stmmac_init_chan(priv, priv->ioaddr,
- priv->plat->dma_cfg, chan);
+ stmmac_init_rx_chan(priv, priv->ioaddr, priv->plat->dma_cfg,
+ rx_q->dma_rx_phy, chan);
- stmmac_init_tx_chan(priv, priv->ioaddr,
- priv->plat->dma_cfg, tx_q->dma_tx_phy,
- chan);
+ rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+ (DMA_RX_SIZE * sizeof(struct dma_desc));
+ stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
+ rx_q->rx_tail_addr, chan);
+ }
- tx_q->tx_tail_addr = tx_q->dma_tx_phy +
- (DMA_TX_SIZE * sizeof(struct dma_desc));
- stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
- tx_q->tx_tail_addr, chan);
- }
- } else {
- rx_q = &priv->rx_queue[chan];
+ /* DMA TX Channel Configuration */
+ for (chan = 0; chan < tx_channels_count; chan++) {
tx_q = &priv->tx_queue[chan];
- stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg,
- tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds);
+
+ stmmac_init_tx_chan(priv, priv->ioaddr, priv->plat->dma_cfg,
+ tx_q->dma_tx_phy, chan);
+
+ tx_q->tx_tail_addr = tx_q->dma_tx_phy +
+ (DMA_TX_SIZE * sizeof(struct dma_desc));
+ stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
+ tx_q->tx_tail_addr, chan);
}
+ /* DMA CSR Channel configuration */
+ for (chan = 0; chan < dma_csr_ch; chan++)
+ stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
+
+ /* DMA Configuration */
+ stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
+
if (priv->plat->axi)
stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
stmmac_core_init(priv, priv->hw, dev);
/* Initialize MTL*/
- if (priv->synopsys_id >= DWMAC_CORE_4_00)
- stmmac_mtl_configuration(priv);
+ stmmac_mtl_configuration(priv);
/* Initialize Safety Features */
- if (priv->synopsys_id >= DWMAC_CORE_5_10)
- stmmac_safety_feat_configuration(priv);
+ stmmac_safety_feat_configuration(priv);
ret = stmmac_rx_ipc(priv, priv->hw);
if (!ret) {
if (enh_desc)
is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc);
- if (unlikely(is_jumbo) && likely(priv->synopsys_id <
- DWMAC_CORE_4_00)) {
+ if (unlikely(is_jumbo)) {
entry = stmmac_jumbo_frm(priv, tx_q, skb, csum_insertion);
- if (unlikely(entry < 0))
+ if (unlikely(entry < 0) && (entry != -EINVAL))
goto dma_map_err;
}
goto dma_map_err; /* should reuse desc w/o issues */
tx_q->tx_skbuff_dma[entry].buf = des;
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
- desc->des0 = cpu_to_le32(des);
- else
- desc->des2 = cpu_to_le32(des);
+
+ stmmac_set_desc_addr(priv, desc, des);
tx_q->tx_skbuff_dma[entry].map_as_page = true;
tx_q->tx_skbuff_dma[entry].len = len;
* element in case of no SG.
*/
priv->tx_count_frames += nfrags + 1;
- if (likely(priv->tx_coal_frames > priv->tx_count_frames)) {
+ if (likely(priv->tx_coal_frames > priv->tx_count_frames) &&
+ !priv->tx_timer_armed) {
mod_timer(&priv->txtimer,
STMMAC_COAL_TIMER(priv->tx_coal_timer));
+ priv->tx_timer_armed = true;
} else {
priv->tx_count_frames = 0;
stmmac_set_tx_ic(priv, desc);
priv->xstats.tx_set_ic_bit++;
+ priv->tx_timer_armed = false;
}
skb_tx_timestamp(skb);
goto dma_map_err;
tx_q->tx_skbuff_dma[first_entry].buf = des;
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
- first->des0 = cpu_to_le32(des);
- else
- first->des2 = cpu_to_le32(des);
+
+ stmmac_set_desc_addr(priv, first, des);
tx_q->tx_skbuff_dma[first_entry].len = nopaged_len;
tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment;
netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
- if (priv->synopsys_id < DWMAC_CORE_4_00)
- stmmac_enable_dma_transmission(priv, priv->ioaddr);
- else
- stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr,
- queue);
+ stmmac_enable_dma_transmission(priv, priv->ioaddr);
+ stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
return NETDEV_TX_OK;
break;
}
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
- p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
- p->des1 = 0;
- } else {
- p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
- }
-
+ stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[entry]);
stmmac_refill_desc3(priv, rx_q, p);
if (rx_q->rx_zeroc_thresh > 0)
}
dma_wmb();
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
- stmmac_init_rx_desc(priv, p, priv->use_riwt, 0, 0);
- else
- stmmac_set_rx_owner(priv, p);
+ stmmac_set_rx_owner(priv, p, priv->use_riwt);
dma_wmb();
int frame_len;
unsigned int des;
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
- des = le32_to_cpu(p->des0);
- else
- des = le32_to_cpu(p->des2);
-
+ stmmac_get_desc_addr(priv, p, &des);
frame_len = stmmac_get_rx_frame_len(priv, p, coe);
/* If frame length is greater than skb buffer size
/* To handle GMAC own interrupts */
if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
+ int mtl_status;
if (unlikely(status)) {
/* For LPI we need to save the tx status */
priv->tx_path_in_lpi_mode = false;
}
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- for (queue = 0; queue < queues_count; queue++) {
- struct stmmac_rx_queue *rx_q =
- &priv->rx_queue[queue];
+ for (queue = 0; queue < queues_count; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
- status |= stmmac_host_mtl_irq_status(priv,
- priv->hw, queue);
+ mtl_status = stmmac_host_mtl_irq_status(priv, priv->hw,
+ queue);
+ if (mtl_status != -EINVAL)
+ status |= mtl_status;
- if (status & CORE_IRQ_MTL_RX_OVERFLOW)
- stmmac_set_rx_tail_ptr(priv,
- priv->ioaddr,
- rx_q->rx_tail_addr,
- queue);
- }
+ if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+ stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
+ rx_q->rx_tail_addr,
+ queue);
}
/* PCS link status */
return ret;
}
+static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+ void *cb_priv)
+{
+ struct stmmac_priv *priv = cb_priv;
+ int ret = -EOPNOTSUPP;
+
+ stmmac_disable_all_queues(priv);
+
+ switch (type) {
+ case TC_SETUP_CLSU32:
+ if (tc_cls_can_offload_and_chain0(priv->dev, type_data))
+ ret = stmmac_tc_setup_cls_u32(priv, priv, type_data);
+ break;
+ default:
+ break;
+ }
+
+ stmmac_enable_all_queues(priv);
+ return ret;
+}
+
+static int stmmac_setup_tc_block(struct stmmac_priv *priv,
+ struct tc_block_offload *f)
+{
+ if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ return -EOPNOTSUPP;
+
+ switch (f->command) {
+ case TC_BLOCK_BIND:
+ return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
+ priv, priv);
+ case TC_BLOCK_UNBIND:
+ tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+ void *type_data)
+{
+ struct stmmac_priv *priv = netdev_priv(ndev);
+
+ switch (type) {
+ case TC_SETUP_BLOCK:
+ return stmmac_setup_tc_block(priv, type_data);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
{
struct stmmac_priv *priv = netdev_priv(ndev);
.ndo_set_rx_mode = stmmac_set_rx_mode,
.ndo_tx_timeout = stmmac_tx_timeout,
.ndo_do_ioctl = stmmac_ioctl,
+ .ndo_setup_tc = stmmac_setup_tc,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = stmmac_poll_controller,
#endif
ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM;
+ ret = stmmac_tc_init(priv, priv);
+ if (!ret) {
+ ndev->hw_features |= NETIF_F_HW_TC;
+ }
+
if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
priv->tso = true;
new_bus->phy_mask = mdio_bus_data->phy_mask;
new_bus->parent = priv->device;
- if (mdio_node)
- err = of_mdiobus_register(new_bus, mdio_node);
- else
- err = mdiobus_register(new_bus);
+ err = of_mdiobus_register(new_bus, mdio_node);
if (err != 0) {
dev_err(dev, "Cannot register the MDIO bus\n");
goto bus_register_fail;
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac TC Handling (HW only)
+ */
+
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include "common.h"
+#include "dwmac4.h"
+#include "dwmac5.h"
+#include "stmmac.h"
+
+static void tc_fill_all_pass_entry(struct stmmac_tc_entry *entry)
+{
+ memset(entry, 0, sizeof(*entry));
+ entry->in_use = true;
+ entry->is_last = true;
+ entry->is_frag = false;
+ entry->prio = ~0x0;
+ entry->handle = 0;
+ entry->val.match_data = 0x0;
+ entry->val.match_en = 0x0;
+ entry->val.af = 1;
+ entry->val.dma_ch_no = 0x0;
+}
+
+static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls,
+ bool free)
+{
+ struct stmmac_tc_entry *entry, *first = NULL, *dup = NULL;
+ u32 loc = cls->knode.handle;
+ int i;
+
+ for (i = 0; i < priv->tc_entries_max; i++) {
+ entry = &priv->tc_entries[i];
+ if (!entry->in_use && !first && free)
+ first = entry;
+ if (entry->handle == loc && !free)
+ dup = entry;
+ }
+
+ if (dup)
+ return dup;
+ if (first) {
+ first->handle = loc;
+ first->in_use = true;
+
+ /* Reset HW values */
+ memset(&first->val, 0, sizeof(first->val));
+ }
+
+ return first;
+}
+
+static int tc_fill_actions(struct stmmac_tc_entry *entry,
+ struct stmmac_tc_entry *frag,
+ struct tc_cls_u32_offload *cls)
+{
+ struct stmmac_tc_entry *action_entry = entry;
+ const struct tc_action *act;
+ struct tcf_exts *exts;
+ LIST_HEAD(actions);
+
+ exts = cls->knode.exts;
+ if (!tcf_exts_has_actions(exts))
+ return -EINVAL;
+ if (frag)
+ action_entry = frag;
+
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(act, &actions, list) {
+ /* Accept */
+ if (is_tcf_gact_ok(act)) {
+ action_entry->val.af = 1;
+ break;
+ }
+ /* Drop */
+ if (is_tcf_gact_shot(act)) {
+ action_entry->val.rf = 1;
+ break;
+ }
+
+ /* Unsupported */
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int tc_fill_entry(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls)
+{
+ struct stmmac_tc_entry *entry, *frag = NULL;
+ struct tc_u32_sel *sel = cls->knode.sel;
+ u32 off, data, mask, real_off, rem;
+ u32 prio = cls->common.prio;
+ int ret;
+
+ /* Only 1 match per entry */
+ if (sel->nkeys <= 0 || sel->nkeys > 1)
+ return -EINVAL;
+
+ off = sel->keys[0].off << sel->offshift;
+ data = sel->keys[0].val;
+ mask = sel->keys[0].mask;
+
+ switch (ntohs(cls->common.protocol)) {
+ case ETH_P_ALL:
+ break;
+ case ETH_P_IP:
+ off += ETH_HLEN;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (off > priv->tc_off_max)
+ return -EINVAL;
+
+ real_off = off / 4;
+ rem = off % 4;
+
+ entry = tc_find_entry(priv, cls, true);
+ if (!entry)
+ return -EINVAL;
+
+ if (rem) {
+ frag = tc_find_entry(priv, cls, true);
+ if (!frag) {
+ ret = -EINVAL;
+ goto err_unuse;
+ }
+
+ entry->frag_ptr = frag;
+ entry->val.match_en = (mask << (rem * 8)) &
+ GENMASK(31, rem * 8);
+ entry->val.match_data = (data << (rem * 8)) &
+ GENMASK(31, rem * 8);
+ entry->val.frame_offset = real_off;
+ entry->prio = prio;
+
+ frag->val.match_en = (mask >> (rem * 8)) &
+ GENMASK(rem * 8 - 1, 0);
+ frag->val.match_data = (data >> (rem * 8)) &
+ GENMASK(rem * 8 - 1, 0);
+ frag->val.frame_offset = real_off + 1;
+ frag->prio = prio;
+ frag->is_frag = true;
+ } else {
+ entry->frag_ptr = NULL;
+ entry->val.match_en = mask;
+ entry->val.match_data = data;
+ entry->val.frame_offset = real_off;
+ entry->prio = prio;
+ }
+
+ ret = tc_fill_actions(entry, frag, cls);
+ if (ret)
+ goto err_unuse;
+
+ return 0;
+
+err_unuse:
+ if (frag)
+ frag->in_use = false;
+ entry->in_use = false;
+ return ret;
+}
+
+static void tc_unfill_entry(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls)
+{
+ struct stmmac_tc_entry *entry;
+
+ entry = tc_find_entry(priv, cls, false);
+ if (!entry)
+ return;
+
+ entry->in_use = false;
+ if (entry->frag_ptr) {
+ entry = entry->frag_ptr;
+ entry->is_frag = false;
+ entry->in_use = false;
+ }
+}
+
+static int tc_config_knode(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls)
+{
+ int ret;
+
+ ret = tc_fill_entry(priv, cls);
+ if (ret)
+ return ret;
+
+ ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries,
+ priv->tc_entries_max);
+ if (ret)
+ goto err_unfill;
+
+ return 0;
+
+err_unfill:
+ tc_unfill_entry(priv, cls);
+ return ret;
+}
+
+static int tc_delete_knode(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls)
+{
+ int ret;
+
+ /* Set entry and fragments as not used */
+ tc_unfill_entry(priv, cls);
+
+ ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries,
+ priv->tc_entries_max);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int tc_setup_cls_u32(struct stmmac_priv *priv,
+ struct tc_cls_u32_offload *cls)
+{
+ switch (cls->command) {
+ case TC_CLSU32_REPLACE_KNODE:
+ tc_unfill_entry(priv, cls);
+ /* Fall through */
+ case TC_CLSU32_NEW_KNODE:
+ return tc_config_knode(priv, cls);
+ case TC_CLSU32_DELETE_KNODE:
+ return tc_delete_knode(priv, cls);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int tc_init(struct stmmac_priv *priv)
+{
+ struct dma_features *dma_cap = &priv->dma_cap;
+ unsigned int count;
+
+ if (!dma_cap->frpsel)
+ return -EINVAL;
+
+ switch (dma_cap->frpbs) {
+ case 0x0:
+ priv->tc_off_max = 64;
+ break;
+ case 0x1:
+ priv->tc_off_max = 128;
+ break;
+ case 0x2:
+ priv->tc_off_max = 256;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (dma_cap->frpes) {
+ case 0x0:
+ count = 64;
+ break;
+ case 0x1:
+ count = 128;
+ break;
+ case 0x2:
+ count = 256;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* Reserve one last filter which lets all pass */
+ priv->tc_entries_max = count;
+ priv->tc_entries = devm_kzalloc(priv->device,
+ sizeof(*priv->tc_entries) * count, GFP_KERNEL);
+ if (!priv->tc_entries)
+ return -ENOMEM;
+
+ tc_fill_all_pass_entry(&priv->tc_entries[count - 1]);
+
+ dev_info(priv->device, "Enabling HW TC (entries=%d, max_off=%d)\n",
+ priv->tc_entries_max, priv->tc_off_max);
+ return 0;
+}
+
+const struct stmmac_tc_ops dwmac510_tc_ops = {
+ .init = tc_init,
+ .setup_cls_u32 = tc_setup_cls_u32,
+};
len = (val & RCR_ENTRY_L2_LEN) >>
RCR_ENTRY_L2_LEN_SHIFT;
- len -= ETH_FCS_LEN;
+ append_size = len + ETH_HLEN + ETH_FCS_LEN;
addr = (val & RCR_ENTRY_PKT_BUF_ADDR) <<
RCR_ENTRY_PKT_BUF_ADDR_SHIFT;
RCR_ENTRY_PKTBUFSZ_SHIFT];
off = addr & ~PAGE_MASK;
- append_size = rcr_size;
if (num_rcr == 1) {
int ptype;
else
skb_checksum_none_assert(skb);
} else if (!(val & RCR_ENTRY_MULTI))
- append_size = len - skb->len;
+ append_size = append_size - skb->len;
niu_rx_skb_append(skb, page, off, append_size, rcr_size);
if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
config TI_DAVINCI_EMAC
tristate "TI DaVinci EMAC Support"
- depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 )
+ depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 ) || COMPILE_TEST
select TI_DAVINCI_MDIO
select TI_DAVINCI_CPDMA
select PHYLIB
config TI_DAVINCI_MDIO
tristate "TI DaVinci MDIO Support"
- depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE
+ depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
select PHYLIB
---help---
This driver supports TI's DaVinci MDIO module.
config TI_DAVINCI_CPDMA
tristate "TI DaVinci CPDMA Support"
- depends on ARCH_DAVINCI || ARCH_OMAP2PLUS
+ depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
---help---
This driver supports TI's DaVinci CPDMA dma engine.
config TI_CPSW
tristate "TI CPSW Switch Support"
- depends on ARCH_DAVINCI || ARCH_OMAP2PLUS
+ depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
select TI_DAVINCI_CPDMA
select TI_DAVINCI_MDIO
select TI_CPSW_PHY_SEL
config TI_CPTS
bool "TI Common Platform Time Sync (CPTS) Support"
- depends on TI_CPSW || TI_KEYSTONE_NETCP
+ depends on TI_CPSW || TI_KEYSTONE_NETCP || COMPILE_TEST
depends on POSIX_TIMERS
---help---
This driver supports the Common Platform Time Sync unit of
}
dev = bus_find_device(&platform_bus_type, NULL, node, match);
- of_node_put(node);
+ if (!dev) {
+ dev_err(dev, "unable to find platform device for %pOF\n", node);
+ goto out;
+ }
+
priv = dev_get_drvdata(dev);
priv->cpsw_phy_sel(priv, phy_mode, slave);
put_device(dev);
+out:
+ of_node_put(node);
}
EXPORT_SYMBOL_GPL(cpsw_phy_sel);
#include <linux/of_device.h>
#include <linux/if_vlan.h>
#include <linux/kmemleak.h>
+#include <linux/sys_soc.h>
#include <linux/pinctrl/consumer.h>
#define RX_PRIORITY_MAPPING 0x76543210
#define TX_PRIORITY_MAPPING 0x33221100
-#define CPDMA_TX_PRIORITY_MAP 0x01234567
+#define CPDMA_TX_PRIORITY_MAP 0x76543210
#define CPSW_VLAN_AWARE BIT(1)
#define CPSW_RX_VLAN_ENCAP BIT(2)
return IRQ_HANDLED;
}
-static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
+static int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
{
u32 ch_map;
int num_tx, cur_budget, ch;
if (num_tx < budget) {
napi_complete(napi_tx);
writel(0xff, &cpsw->wr_regs->tx_en);
- if (cpsw->quirk_irq && cpsw->tx_irq_disabled) {
+ }
+
+ return num_tx;
+}
+
+static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
+{
+ struct cpsw_common *cpsw = napi_to_cpsw(napi_tx);
+ int num_tx;
+
+ num_tx = cpdma_chan_process(cpsw->txv[0].ch, budget);
+ if (num_tx < budget) {
+ napi_complete(napi_tx);
+ writel(0xff, &cpsw->wr_regs->tx_en);
+ if (cpsw->tx_irq_disabled) {
cpsw->tx_irq_disabled = false;
enable_irq(cpsw->irqs_table[1]);
}
return num_tx;
}
-static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
+static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
{
u32 ch_map;
int num_rx, cur_budget, ch;
if (num_rx < budget) {
napi_complete_done(napi_rx, num_rx);
writel(0xff, &cpsw->wr_regs->rx_en);
- if (cpsw->quirk_irq && cpsw->rx_irq_disabled) {
+ }
+
+ return num_rx;
+}
+
+static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
+{
+ struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
+ int num_rx;
+
+ num_rx = cpdma_chan_process(cpsw->rxv[0].ch, budget);
+ if (num_rx < budget) {
+ napi_complete_done(napi_rx, num_rx);
+ writel(0xff, &cpsw->wr_regs->rx_en);
+ if (cpsw->rx_irq_disabled) {
cpsw->rx_irq_disabled = false;
enable_irq(cpsw->irqs_table[0]);
}
for (i = 0; i < ch_stats_len; i++) {
line = i % CPSW_STATS_CH_LEN;
snprintf(*p, ETH_GSTRING_LEN,
- "%s DMA chan %d: %s", rx_dir ? "Rx" : "Tx",
- i / CPSW_STATS_CH_LEN,
+ "%s DMA chan %ld: %s", rx_dir ? "Rx" : "Tx",
+ (long)(i / CPSW_STATS_CH_LEN),
cpsw_gstrings_ch_stats[line].stat_string);
*p += ETH_GSTRING_LEN;
}
cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
HOST_PORT_NUM, ALE_VLAN |
ALE_SECURE, slave->port_vlan);
+ cpsw_ale_control_set(cpsw->ale, slave_port,
+ ALE_PORT_DROP_UNKNOWN_VLAN, 1);
}
static void soft_reset_slave(struct cpsw_slave *slave)
{
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+ ch->max_rx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
+ ch->max_tx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
ch->max_combined = 0;
- ch->max_rx = CPSW_MAX_QUEUES;
- ch->max_tx = CPSW_MAX_QUEUES;
ch->max_other = 0;
ch->other_count = 0;
ch->rx_count = cpsw->rx_ch_num;
static int cpsw_check_ch_settings(struct cpsw_common *cpsw,
struct ethtool_channels *ch)
{
+ if (cpsw->quirk_irq) {
+ dev_err(cpsw->dev, "Maximum one tx/rx queue is allowed");
+ return -EOPNOTSUPP;
+ }
+
if (ch->combined_count)
return -EINVAL;
return ret;
}
-#define CPSW_QUIRK_IRQ BIT(0)
-
-static const struct platform_device_id cpsw_devtype[] = {
- {
- /* keep it for existing comaptibles */
- .name = "cpsw",
- .driver_data = CPSW_QUIRK_IRQ,
- }, {
- .name = "am335x-cpsw",
- .driver_data = CPSW_QUIRK_IRQ,
- }, {
- .name = "am4372-cpsw",
- .driver_data = 0,
- }, {
- .name = "dra7-cpsw",
- .driver_data = 0,
- }, {
- /* sentinel */
- }
-};
-MODULE_DEVICE_TABLE(platform, cpsw_devtype);
-
-enum ti_cpsw_type {
- CPSW = 0,
- AM335X_CPSW,
- AM4372_CPSW,
- DRA7_CPSW,
-};
-
static const struct of_device_id cpsw_of_mtable[] = {
- { .compatible = "ti,cpsw", .data = &cpsw_devtype[CPSW], },
- { .compatible = "ti,am335x-cpsw", .data = &cpsw_devtype[AM335X_CPSW], },
- { .compatible = "ti,am4372-cpsw", .data = &cpsw_devtype[AM4372_CPSW], },
- { .compatible = "ti,dra7-cpsw", .data = &cpsw_devtype[DRA7_CPSW], },
+ { .compatible = "ti,cpsw"},
+ { .compatible = "ti,am335x-cpsw"},
+ { .compatible = "ti,am4372-cpsw"},
+ { .compatible = "ti,dra7-cpsw"},
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, cpsw_of_mtable);
+static const struct soc_device_attribute cpsw_soc_devices[] = {
+ { .family = "AM33xx", .revision = "ES1.0"},
+ { /* sentinel */ }
+};
+
static int cpsw_probe(struct platform_device *pdev)
{
struct clk *clk;
void __iomem *ss_regs;
void __iomem *cpts_regs;
struct resource *res, *ss_res;
- const struct of_device_id *of_id;
struct gpio_descs *mode;
u32 slave_offset, sliver_offset, slave_size;
+ const struct soc_device_attribute *soc;
struct cpsw_common *cpsw;
int ret = 0, i;
int irq;
goto clean_dt_ret;
}
+ soc = soc_device_match(cpsw_soc_devices);
+ if (soc)
+ cpsw->quirk_irq = 1;
+
cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0);
if (IS_ERR(cpsw->txv[0].ch)) {
dev_err(priv->dev, "error initializing tx dma channel\n");
goto clean_dma_ret;
}
- of_id = of_match_device(cpsw_of_mtable, &pdev->dev);
- if (of_id) {
- pdev->id_entry = of_id->data;
- if (pdev->id_entry->driver_data)
- cpsw->quirk_irq = true;
- }
-
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
- netif_napi_add(ndev, &cpsw->napi_rx, cpsw_rx_poll, CPSW_POLL_WEIGHT);
- netif_tx_napi_add(ndev, &cpsw->napi_tx, cpsw_tx_poll, CPSW_POLL_WEIGHT);
+ netif_napi_add(ndev, &cpsw->napi_rx,
+ cpsw->quirk_irq ? cpsw_rx_poll : cpsw_rx_mq_poll,
+ CPSW_POLL_WEIGHT);
+ netif_tx_napi_add(ndev, &cpsw->napi_tx,
+ cpsw->quirk_irq ? cpsw_tx_poll : cpsw_tx_mq_poll,
+ CPSW_POLL_WEIGHT);
cpsw_split_res(ndev);
/* register the network device */
delay = CPTS_SKB_TX_WORK_TIMEOUT;
spin_unlock_irqrestore(&cpts->lock, flags);
- pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec);
+ pr_debug("cpts overflow check at %lld.%09ld\n",
+ (long long)ts.tv_sec, ts.tv_nsec);
return (long)delay;
}
cpts->refclk = devm_clk_get(dev, "cpts");
if (IS_ERR(cpts->refclk)) {
dev_err(dev, "Failed to get cpts refclk\n");
- return ERR_PTR(PTR_ERR(cpts->refclk));
+ return ERR_CAST(cpts->refclk);
}
clk_prepare(cpts->refclk);
return;
WARN(gen_pool_size(pool->gen_pool) != gen_pool_avail(pool->gen_pool),
- "cpdma_desc_pool size %d != avail %d",
+ "cpdma_desc_pool size %zd != avail %zd",
gen_pool_size(pool->gen_pool),
gen_pool_avail(pool->gen_pool));
if (pool->cpumap)
writel_relaxed(buffer, &desc->hw_buffer);
writel_relaxed(len, &desc->hw_len);
writel_relaxed(mode | len, &desc->hw_mode);
- writel_relaxed(token, &desc->sw_token);
+ writel_relaxed((uintptr_t)token, &desc->sw_token);
writel_relaxed(buffer, &desc->sw_buffer);
writel_relaxed(len, &desc->sw_len);
desc_read(desc, sw_len);
struct cpdma_desc_pool *pool = ctlr->pool;
dma_addr_t buff_dma;
int origlen;
- void *token;
+ uintptr_t token;
- token = (void *)desc_read(desc, sw_token);
+ token = desc_read(desc, sw_token);
buff_dma = desc_read(desc, sw_buffer);
origlen = desc_read(desc, sw_len);
dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
cpdma_desc_free(pool, desc, 1);
- (*chan->handler)(token, outlen, status);
+ (*chan->handler)((void *)token, outlen, status);
}
static int __cpdma_chan_process(struct cpdma_chan *chan)
if (netif_msg_probe(priv)) {
dev_notice(&pdev->dev, "DaVinci EMAC Probe found device "
- "(regs: %p, irq: %d)\n",
- (void *)priv->emac_base_phys, ndev->irq);
+ "(regs: %pa, irq: %d)\n",
+ &priv->emac_base_phys, ndev->irq);
}
pm_runtime_put(&pdev->dev);
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/io.h>
+#include <linux/iopoll.h>
#include <linux/pm_runtime.h>
#include <linux/davinci_emac.h>
#include <linux/of.h>
static inline int wait_for_idle(struct davinci_mdio_data *data)
{
struct davinci_mdio_regs __iomem *regs = data->regs;
- unsigned long timeout = jiffies + msecs_to_jiffies(MDIO_TIMEOUT);
+ u32 val, ret;
- while (time_after(timeout, jiffies)) {
- if (__raw_readl(®s->control) & CONTROL_IDLE)
- return 0;
- }
- dev_err(data->dev, "timed out waiting for idle\n");
- return -ETIMEDOUT;
+ ret = readl_poll_timeout(®s->control, val, val & CONTROL_IDLE,
+ 0, MDIO_TIMEOUT * 1000);
+ if (ret)
+ dev_err(data->dev, "timed out waiting for idle\n");
+
+ return ret;
}
static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg)
* defined to support backward compatibility with DTs which assume that
* Davinci MDIO will always scan the bus for PHYs detection.
*/
- if (dev->of_node && of_get_child_count(dev->of_node)) {
+ if (dev->of_node && of_get_child_count(dev->of_node))
data->skip_scan = true;
- ret = of_mdiobus_register(data->bus, dev->of_node);
- } else {
- ret = mdiobus_register(data->bus);
- }
+
+ ret = of_mdiobus_register(data->bus, dev->of_node);
if (ret)
goto bail_out;
c = *s++;
else if (len > 1)
c = crc >> 8;
- else if (len > 0)
+ else
c = crc & 0xff;
len--;
dev->name);
goto drop;
case E_FRM_ERR:
- printk(KERN_WARNING "%s: Framming Error\n",
+ printk(KERN_WARNING "%s: Framing Error\n",
dev->name);
goto drop;
case E_FLG_SYN_ERR:
u16 hashkey_size;
/* The offset of the secret key from the beginning of this structure */
- u32 kashkey_offset;
+ u32 hashkey_offset;
u32 processor_masks_offset;
u32 num_processor_masks;
sync_change_bit(index, net_device->send_section_map);
}
-static void netvsc_send_tx_complete(struct netvsc_device *net_device,
- struct vmbus_channel *incoming_channel,
- struct hv_device *device,
+static void netvsc_send_tx_complete(struct net_device *ndev,
+ struct netvsc_device *net_device,
+ struct vmbus_channel *channel,
const struct vmpacket_descriptor *desc,
int budget)
{
struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
- struct net_device *ndev = hv_get_drvdata(device);
struct net_device_context *ndev_ctx = netdev_priv(ndev);
- struct vmbus_channel *channel = device->channel;
u16 q_idx = 0;
int queue_sends;
if (send_index != NETVSC_INVALID_INDEX)
netvsc_free_send_slot(net_device, send_index);
q_idx = packet->q_idx;
- channel = incoming_channel;
tx_stats = &net_device->chan_table[q_idx].tx_stats;
}
}
-static void netvsc_send_completion(struct netvsc_device *net_device,
+static void netvsc_send_completion(struct net_device *ndev,
+ struct netvsc_device *net_device,
struct vmbus_channel *incoming_channel,
- struct hv_device *device,
const struct vmpacket_descriptor *desc,
int budget)
{
- struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
- struct net_device *ndev = hv_get_drvdata(device);
+ const struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
switch (nvsp_packet->hdr.msg_type) {
case NVSP_MSG_TYPE_INIT_COMPLETE:
break;
case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE:
- netvsc_send_tx_complete(net_device, incoming_channel,
- device, desc, budget);
+ netvsc_send_tx_complete(ndev, net_device, incoming_channel,
+ desc, budget);
break;
default:
static int netvsc_receive(struct net_device *ndev,
struct netvsc_device *net_device,
- struct net_device_context *net_device_ctx,
- struct hv_device *device,
struct vmbus_channel *channel,
const struct vmpacket_descriptor *desc,
- struct nvsp_message *nvsp)
+ const struct nvsp_message *nvsp)
{
+ struct net_device_context *net_device_ctx = netdev_priv(ndev);
const struct vmtransfer_page_packet_header *vmxferpage_packet
= container_of(desc, const struct vmtransfer_page_packet_header, d);
u16 q_idx = channel->offermsg.offer.sub_channel_index;
return count;
}
-static void netvsc_send_table(struct hv_device *hdev,
- struct nvsp_message *nvmsg)
+static void netvsc_send_table(struct net_device *ndev,
+ const struct nvsp_message *nvmsg)
{
- struct net_device *ndev = hv_get_drvdata(hdev);
struct net_device_context *net_device_ctx = netdev_priv(ndev);
- int i;
u32 count, *tab;
+ int i;
count = nvmsg->msg.v5_msg.send_table.count;
if (count != VRSS_SEND_TAB_SIZE) {
net_device_ctx->tx_table[i] = tab[i];
}
-static void netvsc_send_vf(struct net_device_context *net_device_ctx,
- struct nvsp_message *nvmsg)
+static void netvsc_send_vf(struct net_device *ndev,
+ const struct nvsp_message *nvmsg)
{
+ struct net_device_context *net_device_ctx = netdev_priv(ndev);
+
net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
}
-static inline void netvsc_receive_inband(struct hv_device *hdev,
- struct net_device_context *net_device_ctx,
- struct nvsp_message *nvmsg)
+static void netvsc_receive_inband(struct net_device *ndev,
+ const struct nvsp_message *nvmsg)
{
switch (nvmsg->hdr.msg_type) {
case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE:
- netvsc_send_table(hdev, nvmsg);
+ netvsc_send_table(ndev, nvmsg);
break;
case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
- netvsc_send_vf(net_device_ctx, nvmsg);
+ netvsc_send_vf(ndev, nvmsg);
break;
}
}
const struct vmpacket_descriptor *desc,
int budget)
{
- struct net_device_context *net_device_ctx = netdev_priv(ndev);
- struct nvsp_message *nvmsg = hv_pkt_data(desc);
+ const struct nvsp_message *nvmsg = hv_pkt_data(desc);
trace_nvsp_recv(ndev, channel, nvmsg);
switch (desc->type) {
case VM_PKT_COMP:
- netvsc_send_completion(net_device, channel, device,
+ netvsc_send_completion(ndev, net_device, channel,
desc, budget);
break;
case VM_PKT_DATA_USING_XFER_PAGES:
- return netvsc_receive(ndev, net_device, net_device_ctx,
- device, channel, desc, nvmsg);
+ return netvsc_receive(ndev, net_device, channel,
+ desc, nvmsg);
break;
case VM_PKT_DATA_INBAND:
- netvsc_receive_inband(device, net_device_ctx, nvmsg);
+ netvsc_receive_inband(ndev, nvmsg);
break;
default:
goto rx_handler_failed;
}
- ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
+ ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+ NULL, NULL, NULL);
if (ret != 0) {
netdev_err(vf_netdev,
"can not set master device %s (err = %d)\n",
rssp->indirect_tabsize = 4*ITAB_NUM;
rssp->indirect_taboffset = sizeof(struct ndis_recv_scale_param);
rssp->hashkey_size = NETVSC_HASH_KEYLEN;
- rssp->kashkey_offset = rssp->indirect_taboffset +
+ rssp->hashkey_offset = rssp->indirect_taboffset +
rssp->indirect_tabsize;
/* Set indirection table entries */
itab[i] = rdev->rx_table[i];
/* Set hask key values */
- keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset);
+ keyp = (u8 *)((unsigned long)rssp + rssp->hashkey_offset);
memcpy(keyp, rss_key, NETVSC_HASH_KEYLEN);
ret = rndis_filter_send_request(rdev, request);
rndis_device->link_state ? "down" : "up");
if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
- return net_device;
+ goto out;
rndis_filter_query_link_speed(rndis_device, net_device);
atusb->tx_dr.bRequest = ATUSB_TX;
atusb->tx_dr.wValue = cpu_to_le16(0);
- atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC);
+ atusb->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!atusb->tx_urb)
goto fail;
ret = mcr20a_get_platform_data(spi, pdata);
if (ret < 0) {
dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n");
- return ret;
+ goto free_pdata;
}
/* init reset gpio */
ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio,
GPIOF_OUT_INIT_HIGH, "reset");
if (ret)
- return ret;
+ goto free_pdata;
}
/* reset mcr20a */
hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops);
if (!hw) {
dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto free_pdata;
}
/* init mcr20a local data */
/* init buf */
lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL);
- if (!lp->buf)
- return -ENOMEM;
+ if (!lp->buf) {
+ ret = -ENOMEM;
+ goto free_dev;
+ }
mcr20a_setup_tx_spi_messages(lp);
mcr20a_setup_rx_spi_messages(lp);
free_dev:
ieee802154_free_hw(lp->hw);
+free_pdata:
+ kfree(pdata);
return ret;
}
break;
case NETDEV_CHANGEADDR:
- list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
+ }
break;
case NETDEV_PRE_TYPE_CHANGE:
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
+ void *accel_priv = NULL;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
}
}
+ /* For packets that are non-multicast and not bridged we will pass
+ * the necessary information so that the lowerdev can distinguish
+ * the source of the packets via the accel_priv value.
+ */
+ accel_priv = vlan->accel_priv;
xmit_world:
skb->dev = vlan->lowerdev;
- return dev_queue_xmit(skb);
+ return dev_queue_xmit_accel(skb, accel_priv);
}
static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
+ struct macvlan_dev *vlan = netdev_priv(dev);
unsigned int len = skb->len;
int ret;
- struct macvlan_dev *vlan = netdev_priv(dev);
if (unlikely(netpoll_tx_running(dev)))
return macvlan_netpoll_send_skb(vlan, skb);
- if (vlan->fwd_priv) {
- skb->dev = vlan->lowerdev;
- ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
- } else {
- ret = macvlan_queue_xmit(skb, dev);
- }
+ ret = macvlan_queue_xmit(skb, dev);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *pcpu_stats;
goto hash_add;
}
- if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
- vlan->fwd_priv =
- lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
-
- /* If we get a NULL pointer back, or if we get an error
- * then we should just fall through to the non accelerated path
- */
- if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
- vlan->fwd_priv = NULL;
- } else
- return 0;
- }
-
err = -EBUSY;
if (macvlan_addr_busy(vlan->port, dev->dev_addr))
goto out;
- err = dev_uc_add(lowerdev, dev->dev_addr);
- if (err < 0)
- goto out;
+ /* Attempt to populate accel_priv which is used to offload the L2
+ * forwarding requests for unicast packets.
+ */
+ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD)
+ vlan->accel_priv =
+ lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
+
+ /* If earlier attempt to offload failed, or accel_priv is not
+ * populated we must add the unicast address to the lower device.
+ */
+ if (IS_ERR_OR_NULL(vlan->accel_priv)) {
+ vlan->accel_priv = NULL;
+ err = dev_uc_add(lowerdev, dev->dev_addr);
+ if (err < 0)
+ goto out;
+ }
+
if (dev->flags & IFF_ALLMULTI) {
err = dev_set_allmulti(lowerdev, 1);
if (err < 0)
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
del_unicast:
- dev_uc_del(lowerdev, dev->dev_addr);
-out:
- if (vlan->fwd_priv) {
+ if (vlan->accel_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
- vlan->fwd_priv);
- vlan->fwd_priv = NULL;
+ vlan->accel_priv);
+ vlan->accel_priv = NULL;
+ } else {
+ dev_uc_del(lowerdev, dev->dev_addr);
}
+out:
return err;
}
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
- if (vlan->fwd_priv) {
+ if (vlan->accel_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
- vlan->fwd_priv);
- vlan->fwd_priv = NULL;
- return 0;
+ vlan->accel_priv);
+ vlan->accel_priv = NULL;
}
dev_uc_unsync(lowerdev, dev);
config MDIO_MOXART
tristate "MOXA ART MDIO interface support"
- depends on ARCH_MOXART
+ depends on ARCH_MOXART || COMPILE_TEST
help
This driver supports the MDIO interface found in the network
interface units of the MOXA ART SoC
+config MDIO_MSCC_MIIM
+ tristate "Microsemi MIIM interface support"
+ depends on HAS_IOMEM
+ help
+ This driver supports the MIIM (MDIO) interface found in the network
+ switches of the Microsemi SoCs
+
config MDIO_OCTEON
tristate "Octeon and some ThunderX SOCs MDIO buses"
depends on 64BIT
config MDIO_SUN4I
tristate "Allwinner sun4i MDIO interface support"
- depends on ARCH_SUNXI
+ depends on ARCH_SUNXI || COMPILE_TEST
help
This driver supports the MDIO interface found in the network
interface units of the Allwinner SoC that have an EMAC (A10,
---help---
Supports the DP83822 PHY.
+config DP83TC811_PHY
+ tristate "Texas Instruments DP83TC822 PHY"
+ ---help---
+ Supports the DP83TC822 PHY.
+
config DP83848_PHY
tristate "Texas Instruments DP83848 PHY"
---help---
help
Supports the LAN88XX PHYs.
+config MICROCHIP_T1_PHY
+ tristate "Microchip T1 PHYs"
+ ---help---
+ Supports the LAN87XX PHYs.
+
config MICROSEMI_PHY
tristate "Microsemi PHYs"
---help---
obj-$(CONFIG_MDIO_HISI_FEMAC) += mdio-hisi-femac.o
obj-$(CONFIG_MDIO_I2C) += mdio-i2c.o
obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o
+obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o
obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o
obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o
obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o
obj-$(CONFIG_DAVICOM_PHY) += davicom.o
obj-$(CONFIG_DP83640_PHY) += dp83640.o
obj-$(CONFIG_DP83822_PHY) += dp83822.o
+obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o
obj-$(CONFIG_DP83848_PHY) += dp83848.o
obj-$(CONFIG_DP83867_PHY) += dp83867.o
obj-$(CONFIG_FIXED_PHY) += fixed_phy.o
obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o
obj-$(CONFIG_MICREL_PHY) += micrel.o
obj-$(CONFIG_MICROCHIP_PHY) += microchip.o
+obj-$(CONFIG_MICROCHIP_T1_PHY) += microchip_t1.o
obj-$(CONFIG_MICROSEMI_PHY) += mscc.o
obj-$(CONFIG_NATIONAL_PHY) += national.o
obj-$(CONFIG_QSEMI_PHY) += qsemi.o
}
EXPORT_SYMBOL_GPL(bcm_phy_get_strings);
-#ifndef UINT64_MAX
-#define UINT64_MAX (u64)(~((u64)0))
-#endif
-
/* Caller is supposed to provide appropriate storage for the library code to
* access the shadow copy
*/
val = phy_read(phydev, stat.reg);
if (val < 0) {
- ret = UINT64_MAX;
+ ret = U64_MAX;
} else {
val >>= stat.shift;
val = val & ((1 << stat.bits) - 1);
.get_strings = bcm_phy_get_strings,
.get_stats = bcm53xx_phy_get_stats,
.probe = bcm53xx_phy_probe,
+}, {
+ .phy_id = PHY_ID_BCM89610,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM89610",
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = bcm54xx_config_init,
+ .ack_interrupt = bcm_phy_ack_intr,
+ .config_intr = bcm_phy_config_intr,
} };
module_phy_driver(broadcom_drivers);
{ PHY_ID_BCMAC131, 0xfffffff0 },
{ PHY_ID_BCM5241, 0xfffffff0 },
{ PHY_ID_BCM5395, 0xfffffff0 },
+ { PHY_ID_BCM89610, 0xfffffff0 },
{ }
};
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for the Texas Instruments DP83TC811 PHY
+ *
+ * Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ */
+
+#include <linux/ethtool.h>
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy.h>
+#include <linux/netdevice.h>
+
+#define DP83TC811_PHY_ID 0x2000a253
+#define DP83811_DEVADDR 0x1f
+
+#define MII_DP83811_SGMII_CTRL 0x09
+#define MII_DP83811_INT_STAT1 0x12
+#define MII_DP83811_INT_STAT2 0x13
+#define MII_DP83811_RESET_CTRL 0x1f
+
+#define DP83811_HW_RESET BIT(15)
+#define DP83811_SW_RESET BIT(14)
+
+/* INT_STAT1 bits */
+#define DP83811_RX_ERR_HF_INT_EN BIT(0)
+#define DP83811_MS_TRAINING_INT_EN BIT(1)
+#define DP83811_ANEG_COMPLETE_INT_EN BIT(2)
+#define DP83811_ESD_EVENT_INT_EN BIT(3)
+#define DP83811_WOL_INT_EN BIT(4)
+#define DP83811_LINK_STAT_INT_EN BIT(5)
+#define DP83811_ENERGY_DET_INT_EN BIT(6)
+#define DP83811_LINK_QUAL_INT_EN BIT(7)
+
+/* INT_STAT2 bits */
+#define DP83811_JABBER_DET_INT_EN BIT(0)
+#define DP83811_POLARITY_INT_EN BIT(1)
+#define DP83811_SLEEP_MODE_INT_EN BIT(2)
+#define DP83811_OVERTEMP_INT_EN BIT(3)
+#define DP83811_OVERVOLTAGE_INT_EN BIT(6)
+#define DP83811_UNDERVOLTAGE_INT_EN BIT(7)
+
+#define MII_DP83811_RXSOP1 0x04a5
+#define MII_DP83811_RXSOP2 0x04a6
+#define MII_DP83811_RXSOP3 0x04a7
+
+/* WoL Registers */
+#define MII_DP83811_WOL_CFG 0x04a0
+#define MII_DP83811_WOL_STAT 0x04a1
+#define MII_DP83811_WOL_DA1 0x04a2
+#define MII_DP83811_WOL_DA2 0x04a3
+#define MII_DP83811_WOL_DA3 0x04a4
+
+/* WoL bits */
+#define DP83811_WOL_MAGIC_EN BIT(0)
+#define DP83811_WOL_SECURE_ON BIT(5)
+#define DP83811_WOL_EN BIT(7)
+#define DP83811_WOL_INDICATION_SEL BIT(8)
+#define DP83811_WOL_CLR_INDICATION BIT(11)
+
+/* SGMII CTRL bits */
+#define DP83811_TDR_AUTO BIT(8)
+#define DP83811_SGMII_EN BIT(12)
+#define DP83811_SGMII_AUTO_NEG_EN BIT(13)
+#define DP83811_SGMII_TX_ERR_DIS BIT(14)
+#define DP83811_SGMII_SOFT_RESET BIT(15)
+
+static int dp83811_ack_interrupt(struct phy_device *phydev)
+{
+ int err;
+
+ err = phy_read(phydev, MII_DP83811_INT_STAT1);
+ if (err < 0)
+ return err;
+
+ err = phy_read(phydev, MII_DP83811_INT_STAT2);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static int dp83811_set_wol(struct phy_device *phydev,
+ struct ethtool_wolinfo *wol)
+{
+ struct net_device *ndev = phydev->attached_dev;
+ const u8 *mac;
+ u16 value;
+
+ if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
+ mac = (const u8 *)ndev->dev_addr;
+
+ if (!is_valid_ether_addr(mac))
+ return -EINVAL;
+
+ /* MAC addresses start with byte 5, but stored in mac[0].
+ * 811 PHYs store bytes 4|5, 2|3, 0|1
+ */
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA1,
+ (mac[1] << 8) | mac[0]);
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA2,
+ (mac[3] << 8) | mac[2]);
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA3,
+ (mac[5] << 8) | mac[4]);
+
+ value = phy_read_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_WOL_CFG);
+ if (wol->wolopts & WAKE_MAGIC)
+ value |= DP83811_WOL_MAGIC_EN;
+ else
+ value &= ~DP83811_WOL_MAGIC_EN;
+
+ if (wol->wolopts & WAKE_MAGICSECURE) {
+ phy_write_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP1,
+ (wol->sopass[1] << 8) | wol->sopass[0]);
+ phy_write_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP2,
+ (wol->sopass[3] << 8) | wol->sopass[2]);
+ phy_write_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP3,
+ (wol->sopass[5] << 8) | wol->sopass[4]);
+ value |= DP83811_WOL_SECURE_ON;
+ } else {
+ value &= ~DP83811_WOL_SECURE_ON;
+ }
+
+ value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL |
+ DP83811_WOL_CLR_INDICATION);
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
+ value);
+ } else {
+ value = phy_read_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_WOL_CFG);
+ value &= ~DP83811_WOL_EN;
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
+ value);
+ }
+
+ return 0;
+}
+
+static void dp83811_get_wol(struct phy_device *phydev,
+ struct ethtool_wolinfo *wol)
+{
+ u16 sopass_val;
+ int value;
+
+ wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE);
+ wol->wolopts = 0;
+
+ value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG);
+
+ if (value & DP83811_WOL_MAGIC_EN)
+ wol->wolopts |= WAKE_MAGIC;
+
+ if (value & DP83811_WOL_SECURE_ON) {
+ sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP1);
+ wol->sopass[0] = (sopass_val & 0xff);
+ wol->sopass[1] = (sopass_val >> 8);
+
+ sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP2);
+ wol->sopass[2] = (sopass_val & 0xff);
+ wol->sopass[3] = (sopass_val >> 8);
+
+ sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR,
+ MII_DP83811_RXSOP3);
+ wol->sopass[4] = (sopass_val & 0xff);
+ wol->sopass[5] = (sopass_val >> 8);
+
+ wol->wolopts |= WAKE_MAGICSECURE;
+ }
+
+ /* WoL is not enabled so set wolopts to 0 */
+ if (!(value & DP83811_WOL_EN))
+ wol->wolopts = 0;
+}
+
+static int dp83811_config_intr(struct phy_device *phydev)
+{
+ int misr_status, err;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ misr_status = phy_read(phydev, MII_DP83811_INT_STAT1);
+ if (misr_status < 0)
+ return misr_status;
+
+ misr_status |= (DP83811_RX_ERR_HF_INT_EN |
+ DP83811_MS_TRAINING_INT_EN |
+ DP83811_ANEG_COMPLETE_INT_EN |
+ DP83811_ESD_EVENT_INT_EN |
+ DP83811_WOL_INT_EN |
+ DP83811_LINK_STAT_INT_EN |
+ DP83811_ENERGY_DET_INT_EN |
+ DP83811_LINK_QUAL_INT_EN);
+
+ err = phy_write(phydev, MII_DP83811_INT_STAT1, misr_status);
+ if (err < 0)
+ return err;
+
+ misr_status = phy_read(phydev, MII_DP83811_INT_STAT2);
+ if (misr_status < 0)
+ return misr_status;
+
+ misr_status |= (DP83811_JABBER_DET_INT_EN |
+ DP83811_POLARITY_INT_EN |
+ DP83811_SLEEP_MODE_INT_EN |
+ DP83811_OVERTEMP_INT_EN |
+ DP83811_OVERVOLTAGE_INT_EN |
+ DP83811_UNDERVOLTAGE_INT_EN);
+
+ err = phy_write(phydev, MII_DP83811_INT_STAT2, misr_status);
+
+ } else {
+ err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ if (err < 0)
+ return err;
+
+ err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+ }
+
+ return err;
+}
+
+static int dp83811_config_aneg(struct phy_device *phydev)
+{
+ int value, err;
+
+ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
+ value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
+ if (phydev->autoneg == AUTONEG_ENABLE) {
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ (DP83811_SGMII_AUTO_NEG_EN | value));
+ if (err < 0)
+ return err;
+ } else {
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ (~DP83811_SGMII_AUTO_NEG_EN & value));
+ if (err < 0)
+ return err;
+ }
+ }
+
+ return genphy_config_aneg(phydev);
+}
+
+static int dp83811_config_init(struct phy_device *phydev)
+{
+ int value, err;
+
+ err = genphy_config_init(phydev);
+ if (err < 0)
+ return err;
+
+ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
+ value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
+ if (!(value & DP83811_SGMII_EN)) {
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ (DP83811_SGMII_EN | value));
+ if (err < 0)
+ return err;
+ } else {
+ err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+ (~DP83811_SGMII_EN & value));
+ if (err < 0)
+ return err;
+ }
+ }
+
+ value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN;
+
+ return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
+ value);
+}
+
+static int dp83811_phy_reset(struct phy_device *phydev)
+{
+ int err;
+
+ err = phy_write(phydev, MII_DP83811_RESET_CTRL, DP83811_HW_RESET);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static int dp83811_suspend(struct phy_device *phydev)
+{
+ int value;
+
+ value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG);
+
+ if (!(value & DP83811_WOL_EN))
+ genphy_suspend(phydev);
+
+ return 0;
+}
+
+static int dp83811_resume(struct phy_device *phydev)
+{
+ int value;
+
+ genphy_resume(phydev);
+
+ value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG);
+
+ phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, value |
+ DP83811_WOL_CLR_INDICATION);
+
+ return 0;
+}
+
+static struct phy_driver dp83811_driver[] = {
+ {
+ .phy_id = DP83TC811_PHY_ID,
+ .phy_id_mask = 0xfffffff0,
+ .name = "TI DP83TC811",
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = dp83811_config_init,
+ .config_aneg = dp83811_config_aneg,
+ .soft_reset = dp83811_phy_reset,
+ .get_wol = dp83811_get_wol,
+ .set_wol = dp83811_set_wol,
+ .ack_interrupt = dp83811_ack_interrupt,
+ .config_intr = dp83811_config_intr,
+ .suspend = dp83811_suspend,
+ .resume = dp83811_resume,
+ },
+};
+module_phy_driver(dp83811_driver);
+
+static struct mdio_device_id __maybe_unused dp83811_tbl[] = {
+ { DP83TC811_PHY_ID, 0xfffffff0 },
+ { },
+};
+MODULE_DEVICE_TABLE(mdio, dp83811_tbl);
+
+MODULE_DESCRIPTION("Texas Instruments DP83TC811 PHY driver");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com");
+MODULE_LICENSE("GPL");
if (err < 0)
goto error;
+ /* If WOL event happened once, the LED[2] interrupt pin
+ * will not be cleared unless we reading the interrupt status
+ * register. If interrupts are in use, the normal interrupt
+ * handling will clear the WOL event. Clear the WOL event
+ * before enabling it if !phy_interrupt_is_valid()
+ */
+ if (!phy_interrupt_is_valid(phydev))
+ phy_read(phydev, MII_M1011_IEVENT);
+
/* Enable the WOL interrupt */
err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
MII_88E1318S_PHY_CSIER_WOL_EIE);
}
}
-#ifndef UINT64_MAX
-#define UINT64_MAX (u64)(~((u64)0))
-#endif
static u64 marvell_get_stat(struct phy_device *phydev, int i)
{
struct marvell_hw_stat stat = marvell_hw_stats[i];
val = phy_read_paged(phydev, stat.page, stat.reg);
if (val < 0) {
- ret = UINT64_MAX;
+ ret = U64_MAX;
} else {
val = val & ((1 << stat.bits) - 1);
priv->stats[i] += val;
if (!new_bus)
return -ENODEV;
- if (pdev->dev.of_node)
- ret = of_mdiobus_register(new_bus, pdev->dev.of_node);
- else
- ret = mdiobus_register(new_bus);
-
+ ret = of_mdiobus_register(new_bus, pdev->dev.of_node);
if (ret)
mdio_gpio_bus_deinit(&pdev->dev);
--- /dev/null
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Driver for the MDIO interface of Microsemi network switches.
+ *
+ * Author: Alexandre Belloni <alexandre.belloni@bootlin.com>
+ * Copyright (c) 2017 Microsemi Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/of_mdio.h>
+
+#define MSCC_MIIM_REG_STATUS 0x0
+#define MSCC_MIIM_STATUS_STAT_BUSY BIT(3)
+#define MSCC_MIIM_REG_CMD 0x8
+#define MSCC_MIIM_CMD_OPR_WRITE BIT(1)
+#define MSCC_MIIM_CMD_OPR_READ BIT(2)
+#define MSCC_MIIM_CMD_WRDATA_SHIFT 4
+#define MSCC_MIIM_CMD_REGAD_SHIFT 20
+#define MSCC_MIIM_CMD_PHYAD_SHIFT 25
+#define MSCC_MIIM_CMD_VLD BIT(31)
+#define MSCC_MIIM_REG_DATA 0xC
+#define MSCC_MIIM_DATA_ERROR (BIT(16) | BIT(17))
+
+#define MSCC_PHY_REG_PHY_CFG 0x0
+#define PHY_CFG_PHY_ENA (BIT(0) | BIT(1) | BIT(2) | BIT(3))
+#define PHY_CFG_PHY_COMMON_RESET BIT(4)
+#define PHY_CFG_PHY_RESET (BIT(5) | BIT(6) | BIT(7) | BIT(8))
+#define MSCC_PHY_REG_PHY_STATUS 0x4
+
+struct mscc_miim_dev {
+ void __iomem *regs;
+ void __iomem *phy_regs;
+};
+
+static int mscc_miim_wait_ready(struct mii_bus *bus)
+{
+ struct mscc_miim_dev *miim = bus->priv;
+ u32 val;
+
+ readl_poll_timeout(miim->regs + MSCC_MIIM_REG_STATUS, val,
+ !(val & MSCC_MIIM_STATUS_STAT_BUSY), 100, 250000);
+ if (val & MSCC_MIIM_STATUS_STAT_BUSY)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum)
+{
+ struct mscc_miim_dev *miim = bus->priv;
+ u32 val;
+ int ret;
+
+ ret = mscc_miim_wait_ready(bus);
+ if (ret)
+ goto out;
+
+ writel(MSCC_MIIM_CMD_VLD | (mii_id << MSCC_MIIM_CMD_PHYAD_SHIFT) |
+ (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | MSCC_MIIM_CMD_OPR_READ,
+ miim->regs + MSCC_MIIM_REG_CMD);
+
+ ret = mscc_miim_wait_ready(bus);
+ if (ret)
+ goto out;
+
+ val = readl(miim->regs + MSCC_MIIM_REG_DATA);
+ if (val & MSCC_MIIM_DATA_ERROR) {
+ ret = -EIO;
+ goto out;
+ }
+
+ ret = val & 0xFFFF;
+out:
+ return ret;
+}
+
+static int mscc_miim_write(struct mii_bus *bus, int mii_id,
+ int regnum, u16 value)
+{
+ struct mscc_miim_dev *miim = bus->priv;
+ int ret;
+
+ ret = mscc_miim_wait_ready(bus);
+ if (ret < 0)
+ goto out;
+
+ writel(MSCC_MIIM_CMD_VLD | (mii_id << MSCC_MIIM_CMD_PHYAD_SHIFT) |
+ (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) |
+ (value << MSCC_MIIM_CMD_WRDATA_SHIFT) |
+ MSCC_MIIM_CMD_OPR_WRITE,
+ miim->regs + MSCC_MIIM_REG_CMD);
+
+out:
+ return ret;
+}
+
+static int mscc_miim_reset(struct mii_bus *bus)
+{
+ struct mscc_miim_dev *miim = bus->priv;
+
+ if (miim->phy_regs) {
+ writel(0, miim->phy_regs + MSCC_PHY_REG_PHY_CFG);
+ writel(0x1ff, miim->phy_regs + MSCC_PHY_REG_PHY_CFG);
+ mdelay(500);
+ }
+
+ return 0;
+}
+
+static int mscc_miim_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ struct mii_bus *bus;
+ struct mscc_miim_dev *dev;
+ int ret;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENODEV;
+
+ bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev));
+ if (!bus)
+ return -ENOMEM;
+
+ bus->name = "mscc_miim";
+ bus->read = mscc_miim_read;
+ bus->write = mscc_miim_write;
+ bus->reset = mscc_miim_reset;
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev));
+ bus->parent = &pdev->dev;
+
+ dev = bus->priv;
+ dev->regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(dev->regs)) {
+ dev_err(&pdev->dev, "Unable to map MIIM registers\n");
+ return PTR_ERR(dev->regs);
+ }
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (res) {
+ dev->phy_regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(dev->phy_regs)) {
+ dev_err(&pdev->dev, "Unable to map internal phy registers\n");
+ return PTR_ERR(dev->phy_regs);
+ }
+ }
+
+ ret = of_mdiobus_register(bus, pdev->dev.of_node);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret);
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, bus);
+
+ return 0;
+}
+
+static int mscc_miim_remove(struct platform_device *pdev)
+{
+ struct mii_bus *bus = platform_get_drvdata(pdev);
+
+ mdiobus_unregister(bus);
+
+ return 0;
+}
+
+static const struct of_device_id mscc_miim_match[] = {
+ { .compatible = "mscc,ocelot-miim" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, mscc_miim_match);
+
+static struct platform_driver mscc_miim_driver = {
+ .probe = mscc_miim_probe,
+ .remove = mscc_miim_remove,
+ .driver = {
+ .name = "mscc-miim",
+ .of_match_table = mscc_miim_match,
+ },
+};
+
+module_platform_driver(mscc_miim_driver);
+
+MODULE_DESCRIPTION("Microsemi MIIM driver");
+MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@bootlin.com>");
+MODULE_LICENSE("Dual MIT/GPL");
ksz9031_of_load_skew_values(phydev, of_node,
MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4,
tx_data_skews, 4);
+
+ /* Silicon Errata Sheet (DS80000691D or DS80000692D):
+ * When the device links in the 1000BASE-T slave mode only,
+ * the optional 125MHz reference output clock (CLK125_NDO)
+ * has wide duty cycle variation.
+ *
+ * The optional CLK125_NDO clock does not meet the RGMII
+ * 45/55 percent (min/max) duty cycle requirement and therefore
+ * cannot be used directly by the MAC side for clocking
+ * applications that have setup/hold time requirements on
+ * rising and falling clock edges.
+ *
+ * Workaround:
+ * Force the phy to be the master to receive a stable clock
+ * which meets the duty cycle requirement.
+ */
+ if (of_property_read_bool(of_node, "micrel,force-master")) {
+ result = phy_read(phydev, MII_CTRL1000);
+ if (result < 0)
+ goto err_force_master;
+
+ /* enable master mode, config & prefer master */
+ result |= CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER;
+ result = phy_write(phydev, MII_CTRL1000, result);
+ if (result < 0)
+ goto err_force_master;
+ }
}
return ksz9031_center_flp_timing(phydev);
+
+err_force_master:
+ phydev_err(phydev, "failed to force the phy to master mode\n");
+ return result;
}
#define KSZ8873MLL_GLOBAL_CONTROL_4 0x06
}
}
-#ifndef UINT64_MAX
-#define UINT64_MAX (u64)(~((u64)0))
-#endif
static u64 kszphy_get_stat(struct phy_device *phydev, int i)
{
struct kszphy_hw_stat stat = kszphy_hw_stats[i];
val = phy_read(phydev, stat.reg);
if (val < 0) {
- ret = UINT64_MAX;
+ ret = U64_MAX;
} else {
val = val & ((1 << stat.bits) - 1);
priv->stats[i] += val;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Microchip Technology
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+
+/* Interrupt Source Register */
+#define LAN87XX_INTERRUPT_SOURCE (0x18)
+
+/* Interrupt Mask Register */
+#define LAN87XX_INTERRUPT_MASK (0x19)
+#define LAN87XX_MASK_LINK_UP (0x0004)
+#define LAN87XX_MASK_LINK_DOWN (0x0002)
+
+#define DRIVER_AUTHOR "Nisar Sayed <nisar.sayed@microchip.com>"
+#define DRIVER_DESC "Microchip LAN87XX T1 PHY driver"
+
+static int lan87xx_phy_config_intr(struct phy_device *phydev)
+{
+ int rc, val = 0;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* unmask all source and clear them before enable */
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF);
+ rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+ val = LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN;
+ }
+
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+
+ return rc < 0 ? rc : 0;
+}
+
+static int lan87xx_phy_ack_interrupt(struct phy_device *phydev)
+{
+ int rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+
+ return rc < 0 ? rc : 0;
+}
+
+static struct phy_driver microchip_t1_phy_driver[] = {
+ {
+ .phy_id = 0x0007c150,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Microchip LAN87xx T1",
+
+ .features = SUPPORTED_100baseT_Full,
+ .flags = PHY_HAS_INTERRUPT,
+
+ .config_init = genphy_config_init,
+ .config_aneg = genphy_config_aneg,
+
+ .ack_interrupt = lan87xx_phy_ack_interrupt,
+ .config_intr = lan87xx_phy_config_intr,
+
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ }
+};
+
+module_phy_driver(microchip_t1_phy_driver);
+
+static struct mdio_device_id __maybe_unused microchip_t1_tbl[] = {
+ { 0x0007c150, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, microchip_t1_tbl);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
/* Grab the bits from PHYIR1, and put them in the upper half */
phy_reg = mdiobus_read(bus, addr, MII_PHYSID1);
- if (phy_reg < 0)
+ if (phy_reg < 0) {
+ /* if there is no device, return without an error so scanning
+ * the bus works properly
+ */
+ if (phy_reg == -EIO || phy_reg == -ENODEV) {
+ *phy_id = 0xffffffff;
+ return 0;
+ }
+
return -EIO;
+ }
*phy_id = (phy_reg & 0xffff) << 16;
#include <linux/phylink.h>
#include <linux/rtnetlink.h>
#include <linux/spinlock.h>
+#include <linux/timer.h>
#include <linux/workqueue.h>
#include "sfp.h"
/* The link configuration settings */
struct phylink_link_state link_config;
struct gpio_desc *link_gpio;
+ struct timer_list link_poll;
void (*get_fixed_state)(struct net_device *dev,
struct phylink_link_state *s);
if (pl->get_fixed_state)
pl->get_fixed_state(pl->netdev, state);
else if (pl->link_gpio)
- state->link = !!gpiod_get_value(pl->link_gpio);
+ state->link = !!gpiod_get_value_cansleep(pl->link_gpio);
}
/* Flow control is resolved according to our and the link partners
queue_work(system_power_efficient_wq, &pl->resolve);
}
+static void phylink_fixed_poll(struct timer_list *t)
+{
+ struct phylink *pl = container_of(t, struct phylink, link_poll);
+
+ mod_timer(t, jiffies + HZ);
+
+ phylink_run_resolve(pl);
+}
+
static const struct sfp_upstream_ops sfp_phylink_ops;
static int phylink_register_sfp(struct phylink *pl,
pl->link_config.an_enabled = true;
pl->ops = ops;
__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
+ timer_setup(&pl->link_poll, phylink_fixed_poll, 0);
bitmap_fill(pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
linkmode_copy(pl->link_config.advertising, pl->supported);
{
if (pl->sfp_bus)
sfp_unregister_upstream(pl->sfp_bus);
+ if (!IS_ERR_OR_NULL(pl->link_gpio))
+ gpiod_put(pl->link_gpio);
cancel_work_sync(&pl->resolve);
kfree(pl);
clear_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
phylink_run_resolve(pl);
+ if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio))
+ mod_timer(&pl->link_poll, jiffies + HZ);
if (pl->sfp_bus)
sfp_upstream_start(pl->sfp_bus);
if (pl->phydev)
phy_stop(pl->phydev);
if (pl->sfp_bus)
sfp_upstream_stop(pl->sfp_bus);
+ if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio))
+ del_timer_sync(&pl->link_poll);
set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
queue_work(system_power_efficient_wq, &pl->resolve);
if (id->base.br_nominal) {
if (id->base.br_nominal != 255) {
br_nom = id->base.br_nominal * 100;
- br_min = br_nom + id->base.br_nominal * id->ext.br_min;
+ br_min = br_nom - id->base.br_nominal * id->ext.br_min;
br_max = br_nom + id->base.br_nominal * id->ext.br_max;
} else if (id->ext.br_max) {
br_nom = 250 * id->ext.br_max;
br_max = br_nom + br_nom * id->ext.br_min / 100;
br_min = br_nom - br_nom * id->ext.br_min / 100;
}
+
+ /* When using passive cables, in case neither BR,min nor BR,max
+ * are specified, set br_min to 0 as the nominal value is then
+ * used as the maximum.
+ */
+ if (br_min == br_max && id->base.sfp_ct_passive)
+ br_min = 0;
}
/* Set ethtool support from the compliance fields. */
}
}
-#ifndef UINT64_MAX
-#define UINT64_MAX (u64)(~((u64)0))
-#endif
static u64 smsc_get_stat(struct phy_device *phydev, int i)
{
struct smsc_hw_stat stat = smsc_hw_stats[i];
val = phy_read(phydev, stat.reg);
if (val < 0)
- ret = UINT64_MAX;
+ ret = U64_MAX;
else
ret = val;
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppox))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OE)
goto end;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
{
struct netpoll *np;
int err;
- if (!team->dev->npinfo)
- return 0;
-
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
return err;
}
+static int team_port_enable_netpoll(struct team_port *port)
+{
+ if (!port->team->dev->npinfo)
+ return 0;
+
+ return __team_port_enable_netpoll(port);
+}
+
static void team_port_disable_netpoll(struct team_port *port)
{
struct netpoll *np = port->np;
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
{
return 0;
}
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = __team_port_enable_netpoll(port);
if (err) {
__team_netpoll_cleanup(team);
break;
skb_queue_purge(&tfile->sk.sk_error_queue);
}
-static void tun_cleanup_tx_ring(struct tun_file *tfile)
-{
- if (tfile->tx_ring.queue) {
- ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
- xdp_rxq_info_unreg(&tfile->xdp_rxq);
- memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
- }
-}
-
static void __tun_detach(struct tun_file *tfile, bool clean)
{
struct tun_file *ntfile;
tun->dev->reg_state == NETREG_REGISTERED)
unregister_netdevice(tun->dev);
}
- tun_cleanup_tx_ring(tfile);
+ if (tun)
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
+ ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
sock_put(&tfile->sk);
}
}
tun_napi_del(tun, tfile);
/* Drop read queue */
tun_queue_purge(tfile);
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
sock_put(&tfile->sk);
- tun_cleanup_tx_ring(tfile);
}
list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
tun_enable_queue(tfile);
tun_queue_purge(tfile);
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
sock_put(&tfile->sk);
- tun_cleanup_tx_ring(tfile);
}
BUG_ON(tun->numdisabled != 0);
}
if (!tfile->detached &&
- ptr_ring_init(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL)) {
+ ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len,
+ GFP_KERNEL, tun_ptr_free)) {
err = -ENOMEM;
goto out;
}
unsigned long arg, int ifreq_len)
{
struct tun_file *tfile = file->private_data;
+ struct net *net = sock_net(&tfile->sk);
struct tun_struct *tun;
void __user* argp = (void __user*)arg;
struct ifreq ifr;
- struct net *net;
kuid_t owner;
kgid_t group;
int sndbuf;
*/
return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
(unsigned int __user*)argp);
- } else if (cmd == TUNSETQUEUE)
+ } else if (cmd == TUNSETQUEUE) {
return tun_set_queue(file, &ifr);
+ } else if (cmd == SIOCGSKNS) {
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ return open_related_ns(&net->ns, get_net_ns);
+ }
ret = 0;
rtnl_lock();
tun = tun_get(tfile);
- net = sock_net(&tfile->sk);
if (cmd == TUNSETIFF) {
ret = -EEXIST;
if (tun)
tfile->ifindex = ifindex;
goto unlock;
}
- if (cmd == SIOCGSKNS) {
- ret = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto unlock;
-
- ret = open_related_ns(&net->ns, get_net_ns);
- goto unlock;
- }
ret = -EBADFD;
if (!tun)
&tun_proto, 0);
if (!tfile)
return -ENOMEM;
+ if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) {
+ sk_free(&tfile->sk);
+ return -ENOMEM;
+ }
+
RCU_INIT_POINTER(tfile->tun, NULL);
tfile->flags = 0;
tfile->ifindex = 0;
sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
- memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
-
return 0;
}
select MII
select PHYLIB
select MICROCHIP_PHY
+ select FIXED_PHY
help
This option adds support for Microchip LAN78XX based USB 2
& USB 3 10/100/1000 Ethernet adapters.
#include <linux/irq.h>
#include <linux/irqchip/chained_irq.h>
#include <linux/microchipphy.h>
-#include <linux/phy.h>
+#include <linux/phy_fixed.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include "lan78xx.h"
#define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>"
#define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices"
#define DRIVER_NAME "lan78xx"
-#define DRIVER_VERSION "1.0.6"
#define TX_TIMEOUT_JIFFIES (5 * HZ)
#define THROTTLE_JIFFIES (HZ / 8)
struct lan78xx_net *dev = netdev_priv(net);
strncpy(info->driver, DRIVER_NAME, sizeof(info->driver));
- strncpy(info->version, DRIVER_VERSION, sizeof(info->version));
usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info));
}
}
node = of_get_child_by_name(dev->udev->dev.of_node, "mdio");
- if (node) {
- ret = of_mdiobus_register(dev->mdiobus, node);
+ ret = of_mdiobus_register(dev->mdiobus, node);
+ if (node)
of_node_put(node);
- } else {
- ret = mdiobus_register(dev->mdiobus);
- }
if (ret) {
netdev_err(dev->net, "can't register MDIO bus\n");
goto exit1;
return 1;
}
-static int lan78xx_phy_init(struct lan78xx_net *dev)
+static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
{
+ u32 buf;
int ret;
- u32 mii_adv;
+ struct fixed_phy_status fphy_status = {
+ .link = 1,
+ .speed = SPEED_1000,
+ .duplex = DUPLEX_FULL,
+ };
struct phy_device *phydev;
phydev = phy_find_first(dev->mdiobus);
if (!phydev) {
- netdev_err(dev->net, "no PHY found\n");
- return -EIO;
- }
-
- if ((dev->chipid == ID_REV_CHIP_ID_7800_) ||
- (dev->chipid == ID_REV_CHIP_ID_7850_)) {
- phydev->is_internal = true;
- dev->interface = PHY_INTERFACE_MODE_GMII;
-
- } else if (dev->chipid == ID_REV_CHIP_ID_7801_) {
+ netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n");
+ phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1,
+ NULL);
+ if (IS_ERR(phydev)) {
+ netdev_err(dev->net, "No PHY/fixed_PHY found\n");
+ return NULL;
+ }
+ netdev_dbg(dev->net, "Registered FIXED PHY\n");
+ dev->interface = PHY_INTERFACE_MODE_RGMII;
+ ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
+ MAC_RGMII_ID_TXC_DELAY_EN_);
+ ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
+ ret = lan78xx_read_reg(dev, HW_CFG, &buf);
+ buf |= HW_CFG_CLK125_EN_;
+ buf |= HW_CFG_REFCLK25_EN_;
+ ret = lan78xx_write_reg(dev, HW_CFG, buf);
+ } else {
if (!phydev->drv) {
netdev_err(dev->net, "no PHY driver found\n");
- return -EIO;
+ return NULL;
}
-
dev->interface = PHY_INTERFACE_MODE_RGMII;
-
/* external PHY fixup for KSZ9031RNX */
ret = phy_register_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0,
ksz9031rnx_fixup);
if (ret < 0) {
- netdev_err(dev->net, "fail to register fixup\n");
- return ret;
+ netdev_err(dev->net, "Failed to register fixup for PHY_KSZ9031RNX\n");
+ return NULL;
}
/* external PHY fixup for LAN8835 */
ret = phy_register_fixup_for_uid(PHY_LAN8835, 0xfffffff0,
lan8835_fixup);
if (ret < 0) {
- netdev_err(dev->net, "fail to register fixup\n");
- return ret;
+ netdev_err(dev->net, "Failed to register fixup for PHY_LAN8835\n");
+ return NULL;
}
/* add more external PHY fixup here if needed */
phydev->is_internal = false;
- } else {
- netdev_err(dev->net, "unknown ID found\n");
- ret = -EIO;
- goto error;
+ }
+ return phydev;
+}
+
+static int lan78xx_phy_init(struct lan78xx_net *dev)
+{
+ int ret;
+ u32 mii_adv;
+ struct phy_device *phydev;
+
+ switch (dev->chipid) {
+ case ID_REV_CHIP_ID_7801_:
+ phydev = lan7801_phy_init(dev);
+ if (!phydev) {
+ netdev_err(dev->net, "lan7801: PHY Init Failed");
+ return -EIO;
+ }
+ break;
+
+ case ID_REV_CHIP_ID_7800_:
+ case ID_REV_CHIP_ID_7850_:
+ phydev = phy_find_first(dev->mdiobus);
+ if (!phydev) {
+ netdev_err(dev->net, "no PHY found\n");
+ return -EIO;
+ }
+ phydev->is_internal = true;
+ dev->interface = PHY_INTERFACE_MODE_GMII;
+ break;
+
+ default:
+ netdev_err(dev->net, "Unknown CHIP ID found\n");
+ return -EIO;
}
/* if phyirq is not set, use polling mode in phylib */
if (ret) {
netdev_err(dev->net, "can't attach PHY to %s\n",
dev->mdiobus->id);
+ if (dev->chipid == ID_REV_CHIP_ID_7801_) {
+ if (phy_is_pseudo_fixed_link(phydev)) {
+ fixed_phy_unregister(phydev);
+ } else {
+ phy_unregister_fixup_for_uid(PHY_KSZ9031RNX,
+ 0xfffffff0);
+ phy_unregister_fixup_for_uid(PHY_LAN8835,
+ 0xfffffff0);
+ }
+ }
return -EIO;
}
dev->fc_autoneg = phydev->autoneg;
return 0;
-
-error:
- phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0);
- phy_unregister_fixup_for_uid(PHY_LAN8835, 0xfffffff0);
-
- return ret;
}
static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size)
struct lan78xx_net *dev;
struct usb_device *udev;
struct net_device *net;
+ struct phy_device *phydev;
dev = usb_get_intfdata(intf);
usb_set_intfdata(intf, NULL);
udev = interface_to_usbdev(intf);
net = dev->net;
+ phydev = net->phydev;
phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0);
phy_unregister_fixup_for_uid(PHY_LAN8835, 0xfffffff0);
phy_disconnect(net->phydev);
+ if (phy_is_pseudo_fixed_link(phydev))
+ fixed_phy_unregister(phydev);
+
unregister_netdev(net);
cancel_delayed_work_sync(&dev->wq);
{QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
{QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x90b2, 3)}, /* ublox R410M */
{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
{QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)}, /* YUGA CLM920-NC5 */
id->driver_info = (unsigned long)&qmi_wwan_info;
}
+ /* There are devices where the same interface number can be
+ * configured as different functions. We should only bind to
+ * vendor specific functions when matching on interface number
+ */
+ if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER &&
+ desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) {
+ dev_dbg(&intf->dev,
+ "Rejecting interface number match for class %02x\n",
+ desc->bInterfaceClass);
+ return -ENODEV;
+ }
+
/* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */
if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) {
dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n");
/* recalculate len if xdp.data or xdp.data_end were
* adjusted
*/
- len = xdp.data_end - xdp.data;
+ len = xdp.data_end - xdp.data + vi->hdr_len;
/* We can only create skb based on xdp_page. */
if (unlikely(xdp_page != page)) {
rcu_read_unlock();
gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
+ /* Prevent any &gdesc->tcd field from being (speculatively)
+ * read before (&gdesc->tcd)->gen is read.
+ */
+ dma_rmb();
+
completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
&gdesc->tcd), tq, adapter->pdev,
adapter);
gdesc->txd.tci = skb_vlan_tag_get(skb);
}
+ /* Ensure that the write to (&gdesc->txd)->gen will be observed after
+ * all other writes to &gdesc->txd.
+ */
+ dma_wmb();
+
/* finally flips the GEN bit of the SOP desc. */
gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
VMXNET3_TXD_GEN);
*/
break;
}
+
+ /* Prevent any rcd field from being (speculatively) read before
+ * rcd->gen is read.
+ */
+ dma_rmb();
+
BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
rcd->rqID != rq->dataRingQid);
idx = rcd->rxdIdx;
ring->next2comp = idx;
num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring);
ring = rq->rx_ring + ring_idx;
+
+ /* Ensure that the writes to rxd->gen bits will be observed
+ * after all other writes to rxd objects.
+ */
+ dma_wmb();
+
while (num_to_alloc) {
vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd,
&rxCmdDesc);
/* ==================== initialization and cleanup routines ============ */
static int
-vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
+vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter)
{
int err;
unsigned long mmio_start, mmio_len;
return err;
}
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
- if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_consistent_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = true;
- } else {
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = false;
- }
-
err = pci_request_selected_regions(pdev, (1 << 2) - 1,
vmxnet3_driver_name);
if (err) {
dev_err(&pdev->dev,
"Failed to request region for adapter: error %d\n", err);
- goto err_set_mask;
+ goto err_enable_device;
}
pci_set_master(pdev);
iounmap(adapter->hw_addr0);
err_ioremap:
pci_release_selected_regions(pdev, (1 << 2) - 1);
-err_set_mask:
+err_enable_device:
pci_disable_device(pdev);
return err;
}
* completion.
*/
while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
- msleep(1);
+ usleep_range(1000, 2000);
vmxnet3_quiesce_dev(adapter);
* completion.
*/
while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
- msleep(1);
+ usleep_range(1000, 2000);
if (netif_running(netdev)) {
vmxnet3_quiesce_dev(adapter);
#endif
};
int err;
- bool dma64 = false; /* stupid gcc */
+ bool dma64;
u32 ver;
struct net_device *netdev;
struct vmxnet3_adapter *adapter;
adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_consistent_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = true;
+ } else {
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = false;
+ }
+
spin_lock_init(&adapter->cmd_lock);
adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
sizeof(struct vmxnet3_adapter),
if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
dev_err(&pdev->dev, "Failed to map dma\n");
err = -EFAULT;
- goto err_dma_map;
+ goto err_set_mask;
}
adapter->shared = dma_alloc_coherent(
&adapter->pdev->dev,
}
#endif /* VMXNET3_RSS */
- err = vmxnet3_alloc_pci_resources(adapter, &dma64);
+ err = vmxnet3_alloc_pci_resources(adapter);
if (err < 0)
goto err_alloc_pci;
err_alloc_shared:
dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
-err_dma_map:
+err_set_mask:
free_netdev(netdev);
return err;
}
* completion.
*/
while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
- msleep(1);
+ usleep_range(1000, 2000);
if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED,
&adapter->state)) {
* completion.
*/
while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
- msleep(1);
+ usleep_range(1000, 2000);
if (netif_running(netdev)) {
vmxnet3_quiesce_dev(adapter);
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.14.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.16.0-k"
-/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040e00
+/* Each byte of this 32-bit integer encodes a version number in
+ * VMXNET3_DRIVER_VERSION_STRING.
+ */
+#define VMXNET3_DRIVER_VERSION_NUM 0x01041000
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
{
u8 *ies = NULL, *wpa_ie = NULL, *pos;
size_t ies_len = 0;
- struct station_info sinfo;
+ struct station_info *sinfo;
ath6kl_dbg(ATH6KL_DBG_TRC, "new station %pM aid=%d\n", mac_addr, aid);
keymgmt, ucipher, auth, apsd_info);
/* send event to application */
- memset(&sinfo, 0, sizeof(sinfo));
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo)
+ return;
/* TODO: sinfo.generation */
- sinfo.assoc_req_ies = ies;
- sinfo.assoc_req_ies_len = ies_len;
+ sinfo->assoc_req_ies = ies;
+ sinfo->assoc_req_ies_len = ies_len;
- cfg80211_new_sta(vif->ndev, mac_addr, &sinfo, GFP_KERNEL);
+ cfg80211_new_sta(vif->ndev, mac_addr, sinfo, GFP_KERNEL);
netif_wake_queue(vif->ndev);
+
+ kfree(sinfo);
}
void disconnect_timer_handler(struct timer_list *t)
static int wil_link_debugfs_show(struct seq_file *s, void *data)
{
struct wil6210_priv *wil = s->private;
- struct station_info sinfo;
- int i, rc;
+ struct station_info *sinfo;
+ int i, rc = 0;
+
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo)
+ return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
struct wil_sta_info *p = &wil->sta[i];
vif = (mid < wil->max_vifs) ? wil->vifs[mid] : NULL;
if (vif) {
- rc = wil_cid_fill_sinfo(vif, i, &sinfo);
+ rc = wil_cid_fill_sinfo(vif, i, sinfo);
if (rc)
- return rc;
+ goto out;
- seq_printf(s, " Tx_mcs = %d\n", sinfo.txrate.mcs);
- seq_printf(s, " Rx_mcs = %d\n", sinfo.rxrate.mcs);
- seq_printf(s, " SQ = %d\n", sinfo.signal);
+ seq_printf(s, " Tx_mcs = %d\n", sinfo->txrate.mcs);
+ seq_printf(s, " Rx_mcs = %d\n", sinfo->rxrate.mcs);
+ seq_printf(s, " SQ = %d\n", sinfo->signal);
} else {
seq_puts(s, " INVALID MID\n");
}
}
- return 0;
+out:
+ kfree(sinfo);
+ return rc;
}
static int wil_link_seq_open(struct inode *inode, struct file *file)
struct wireless_dev *wdev = vif_to_wdev(vif);
struct wmi_connect_event *evt = d;
int ch; /* channel number */
- struct station_info sinfo;
+ struct station_info *sinfo;
u8 *assoc_req_ie, *assoc_resp_ie;
size_t assoc_req_ielen, assoc_resp_ielen;
/* capinfo(u16) + listen_interval(u16) + IEs */
vif->bss = NULL;
} else if ((wdev->iftype == NL80211_IFTYPE_AP) ||
(wdev->iftype == NL80211_IFTYPE_P2P_GO)) {
+
if (rc) {
if (disable_ap_sme)
/* notify new_sta has failed */
goto out;
}
- memset(&sinfo, 0, sizeof(sinfo));
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo) {
+ rc = -ENOMEM;
+ goto out;
+ }
- sinfo.generation = wil->sinfo_gen++;
+ sinfo->generation = wil->sinfo_gen++;
if (assoc_req_ie) {
- sinfo.assoc_req_ies = assoc_req_ie;
- sinfo.assoc_req_ies_len = assoc_req_ielen;
+ sinfo->assoc_req_ies = assoc_req_ie;
+ sinfo->assoc_req_ies_len = assoc_req_ielen;
}
- cfg80211_new_sta(ndev, evt->bssid, &sinfo, GFP_KERNEL);
+ cfg80211_new_sta(ndev, evt->bssid, sinfo, GFP_KERNEL);
+
+ kfree(sinfo);
} else {
wil_err(wil, "unhandled iftype %d for CID %d\n", wdev->iftype,
evt->cid);
int slot, firstused;
bool frame_succeed;
int skip;
- static u8 err_out1, err_out2;
+ static u8 err_out1;
ring = parse_cookie(dev, status->cookie, &slot);
if (unlikely(!ring))
}
} else {
/* More than a single header/data pair were missed.
- * Report this error once.
+ * Report this error, and reset the controller to
+ * revive operation.
*/
- if (!err_out2)
- b43dbg(dev->wl,
- "Out of order TX status report on DMA ring %d. Expected %d, but got %d\n",
- ring->index, firstused, slot);
- err_out2 = 1;
+ b43dbg(dev->wl,
+ "Out of order TX status report on DMA ring %d. Expected %d, but got %d\n",
+ ring->index, firstused, slot);
+ b43_controller_restart(dev, "Out of order TX");
return;
}
}
meta->dmaaddr = map_descbuffer(ring, skb->data, skb->len, 1);
/* create a bounce buffer in zone_dma on mapping failure. */
if (b43legacy_dma_mapping_error(ring, meta->dmaaddr, skb->len, 1)) {
- bounce_skb = alloc_skb(skb->len, GFP_ATOMIC | GFP_DMA);
+ bounce_skb = alloc_skb(skb->len, GFP_KERNEL | GFP_DMA);
if (!bounce_skb) {
ring->current_slot = old_top_slot;
ring->used_slots = old_used_slots;
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43340),
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43341),
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43362),
+ BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43364),
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4335_4339),
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4339),
BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43430),
struct brcmf_bss_info_le *bi)
{
struct wiphy *wiphy = cfg_to_wiphy(cfg);
- struct ieee80211_channel *notify_channel;
struct cfg80211_bss *bss;
- struct ieee80211_supported_band *band;
+ enum nl80211_band band;
struct brcmu_chan ch;
u16 channel;
u32 freq;
u16 notify_interval;
u8 *notify_ie;
size_t notify_ielen;
- s32 notify_signal;
+ struct cfg80211_inform_bss bss_data = {};
if (le32_to_cpu(bi->length) > WL_BSS_INFO_MAX) {
brcmf_err("Bss info is larger than buffer. Discarding\n");
channel = bi->ctl_ch;
if (channel <= CH_MAX_2G_CHANNEL)
- band = wiphy->bands[NL80211_BAND_2GHZ];
+ band = NL80211_BAND_2GHZ;
else
- band = wiphy->bands[NL80211_BAND_5GHZ];
+ band = NL80211_BAND_5GHZ;
- freq = ieee80211_channel_to_frequency(channel, band->band);
- notify_channel = ieee80211_get_channel(wiphy, freq);
+ freq = ieee80211_channel_to_frequency(channel, band);
+ bss_data.chan = ieee80211_get_channel(wiphy, freq);
+ bss_data.scan_width = NL80211_BSS_CHAN_WIDTH_20;
+ bss_data.boottime_ns = ktime_to_ns(ktime_get_boottime());
notify_capability = le16_to_cpu(bi->capability);
notify_interval = le16_to_cpu(bi->beacon_period);
notify_ie = (u8 *)bi + le16_to_cpu(bi->ie_offset);
notify_ielen = le32_to_cpu(bi->ie_length);
- notify_signal = (s16)le16_to_cpu(bi->RSSI) * 100;
+ bss_data.signal = (s16)le16_to_cpu(bi->RSSI) * 100;
brcmf_dbg(CONN, "bssid: %pM\n", bi->BSSID);
brcmf_dbg(CONN, "Channel: %d(%d)\n", channel, freq);
brcmf_dbg(CONN, "Capability: %X\n", notify_capability);
brcmf_dbg(CONN, "Beacon interval: %d\n", notify_interval);
- brcmf_dbg(CONN, "Signal: %d\n", notify_signal);
+ brcmf_dbg(CONN, "Signal: %d\n", bss_data.signal);
- bss = cfg80211_inform_bss(wiphy, notify_channel,
- CFG80211_BSS_FTYPE_UNKNOWN,
- (const u8 *)bi->BSSID,
- 0, notify_capability,
- notify_interval, notify_ie,
- notify_ielen, notify_signal,
- GFP_KERNEL);
+ bss = cfg80211_inform_bss_data(wiphy, &bss_data,
+ CFG80211_BSS_FTYPE_UNKNOWN,
+ (const u8 *)bi->BSSID,
+ 0, notify_capability,
+ notify_interval, notify_ie,
+ notify_ielen, GFP_KERNEL);
if (!bss)
return -ENOMEM;
static int generation;
u32 event = e->event_code;
u32 reason = e->reason;
- struct station_info sinfo;
+ struct station_info *sinfo;
brcmf_dbg(CONN, "event %s (%u), reason %d\n",
brcmf_fweh_event_name(event), event, reason);
if (((event == BRCMF_E_ASSOC_IND) || (event == BRCMF_E_REASSOC_IND)) &&
(reason == BRCMF_E_STATUS_SUCCESS)) {
- memset(&sinfo, 0, sizeof(sinfo));
if (!data) {
brcmf_err("No IEs present in ASSOC/REASSOC_IND");
return -EINVAL;
}
- sinfo.assoc_req_ies = data;
- sinfo.assoc_req_ies_len = e->datalen;
+
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo)
+ return -ENOMEM;
+
+ sinfo->assoc_req_ies = data;
+ sinfo->assoc_req_ies_len = e->datalen;
generation++;
- sinfo.generation = generation;
- cfg80211_new_sta(ndev, e->addr, &sinfo, GFP_KERNEL);
+ sinfo->generation = generation;
+ cfg80211_new_sta(ndev, e->addr, sinfo, GFP_KERNEL);
+
+ kfree(sinfo);
} else if ((event == BRCMF_E_DISASSOC_IND) ||
(event == BRCMF_E_DEAUTH_IND) ||
(event == BRCMF_E_DEAUTH)) {
wiphy->flags |= WIPHY_FLAG_NETNS_OK |
WIPHY_FLAG_PS_ON_BY_DEFAULT |
+ WIPHY_FLAG_HAVE_AP_SME |
WIPHY_FLAG_OFFCHAN_TX |
WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_TDLS))
kfree(req);
}
-static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
+static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
{
struct brcmf_fw *fwctx = ctx;
struct brcmf_fw_item *cur;
brcmf_dbg(TRACE, "nvram %p len %d\n", nvram, nvram_length);
cur->nv_data.data = nvram;
cur->nv_data.len = nvram_length;
- return;
+ return 0;
fail:
- brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev));
- fwctx->done(fwctx->dev, -ENOENT, NULL);
- brcmf_fw_free_request(fwctx->req);
- kfree(fwctx);
+ return -ENOENT;
}
static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
brcmf_dbg(TRACE, "enter: firmware %s %sfound\n", cur->path,
fw ? "" : "not ");
- if (fw) {
- if (cur->type == BRCMF_FW_TYPE_BINARY)
- cur->binary = fw;
- else if (cur->type == BRCMF_FW_TYPE_NVRAM)
- brcmf_fw_request_nvram_done(fw, fwctx);
- else
- release_firmware(fw);
- } else if (cur->type == BRCMF_FW_TYPE_NVRAM) {
- brcmf_fw_request_nvram_done(NULL, fwctx);
- } else if (!(cur->flags & BRCMF_FW_REQF_OPTIONAL)) {
+ if (!fw)
ret = -ENOENT;
+
+ switch (cur->type) {
+ case BRCMF_FW_TYPE_NVRAM:
+ ret = brcmf_fw_request_nvram_done(fw, fwctx);
+ break;
+ case BRCMF_FW_TYPE_BINARY:
+ cur->binary = fw;
+ break;
+ default:
+ /* something fishy here so bail out early */
+ brcmf_err("unknown fw type: %d\n", cur->type);
+ release_firmware(fw);
+ ret = -EINVAL;
goto fail;
}
+ if (ret < 0 && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
+ goto fail;
+
do {
if (++fwctx->curpos == fwctx->req->n_items) {
ret = 0;
struct brcmf_fw_request *
brcmf_fw_alloc_request(u32 chip, u32 chiprev,
- struct brcmf_firmware_mapping mapping_table[],
+ const struct brcmf_firmware_mapping mapping_table[],
u32 table_size, struct brcmf_fw_name *fwnames,
u32 n_fwnames)
{
struct brcmf_fw_request *
brcmf_fw_alloc_request(u32 chip, u32 chiprev,
- struct brcmf_firmware_mapping mapping_table[],
+ const struct brcmf_firmware_mapping mapping_table[],
u32 table_size, struct brcmf_fw_name *fwnames,
u32 n_fwnames);
#define BRCMF_H2D_MSGRING_CONTROL_SUBMIT_ITEMSIZE 40
#define BRCMF_H2D_MSGRING_RXPOST_SUBMIT_ITEMSIZE 32
#define BRCMF_D2H_MSGRING_CONTROL_COMPLETE_ITEMSIZE 24
-#define BRCMF_D2H_MSGRING_TX_COMPLETE_ITEMSIZE 16
-#define BRCMF_D2H_MSGRING_RX_COMPLETE_ITEMSIZE 32
+#define BRCMF_D2H_MSGRING_TX_COMPLETE_ITEMSIZE_PRE_V7 16
+#define BRCMF_D2H_MSGRING_TX_COMPLETE_ITEMSIZE 24
+#define BRCMF_D2H_MSGRING_RX_COMPLETE_ITEMSIZE_PRE_V7 32
+#define BRCMF_D2H_MSGRING_RX_COMPLETE_ITEMSIZE 40
#define BRCMF_H2D_TXFLOWRING_ITEMSIZE 48
struct msgbuf_buf_addr {
}
pri_ifp = p2p->bss_idx[P2PAPI_BSSCFG_PRIMARY].vif->ifp;
+
+ /* firmware requires unique mac address for p2pdev interface */
+ if (addr && ether_addr_equal(addr, pri_ifp->mac_addr)) {
+ brcmf_err("discovery vif must be different from primary interface\n");
+ return ERR_PTR(-EINVAL);
+ }
+
brcmf_p2p_generate_bss_mac(p2p, addr);
brcmf_p2p_set_firmware(pri_ifp, p2p->dev_addr);
BRCMF_FW_DEF(4366C, "brcmfmac4366c-pcie");
BRCMF_FW_DEF(4371, "brcmfmac4371-pcie");
-static struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = {
+static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = {
BRCMF_FW_ENTRY(BRCM_CC_43602_CHIP_ID, 0xFFFFFFFF, 43602),
BRCMF_FW_ENTRY(BRCM_CC_43465_CHIP_ID, 0xFFFFFFF0, 4366C),
BRCMF_FW_ENTRY(BRCM_CC_4350_CHIP_ID, 0x000000FF, 4350C),
#define BRCMF_PCIE_PCIE2REG_MAILBOXMASK 0x4C
#define BRCMF_PCIE_PCIE2REG_CONFIGADDR 0x120
#define BRCMF_PCIE_PCIE2REG_CONFIGDATA 0x124
-#define BRCMF_PCIE_PCIE2REG_H2D_MAILBOX 0x140
+#define BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_0 0x140
+#define BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_1 0x144
#define BRCMF_PCIE2_INTA 0x01
#define BRCMF_PCIE2_INTB 0x02
BRCMF_PCIE_MB_INT_D2H3_DB0 | \
BRCMF_PCIE_MB_INT_D2H3_DB1)
+#define BRCMF_PCIE_SHARED_VERSION_7 7
#define BRCMF_PCIE_MIN_SHARED_VERSION 5
-#define BRCMF_PCIE_MAX_SHARED_VERSION 6
+#define BRCMF_PCIE_MAX_SHARED_VERSION BRCMF_PCIE_SHARED_VERSION_7
#define BRCMF_PCIE_SHARED_VERSION_MASK 0x00FF
#define BRCMF_PCIE_SHARED_DMA_INDEX 0x10000
#define BRCMF_PCIE_SHARED_DMA_2B_IDX 0x100000
+#define BRCMF_PCIE_SHARED_HOSTRDY_DB1 0x10000000
#define BRCMF_PCIE_FLAGS_HTOD_SPLIT 0x4000
#define BRCMF_PCIE_FLAGS_DTOH_SPLIT 0x8000
BRCMF_D2H_MSGRING_RX_COMPLETE_MAX_ITEM
};
+static const u32 brcmf_ring_itemsize_pre_v7[BRCMF_NROF_COMMON_MSGRINGS] = {
+ BRCMF_H2D_MSGRING_CONTROL_SUBMIT_ITEMSIZE,
+ BRCMF_H2D_MSGRING_RXPOST_SUBMIT_ITEMSIZE,
+ BRCMF_D2H_MSGRING_CONTROL_COMPLETE_ITEMSIZE,
+ BRCMF_D2H_MSGRING_TX_COMPLETE_ITEMSIZE_PRE_V7,
+ BRCMF_D2H_MSGRING_RX_COMPLETE_ITEMSIZE_PRE_V7
+};
+
static const u32 brcmf_ring_itemsize[BRCMF_NROF_COMMON_MSGRINGS] = {
BRCMF_H2D_MSGRING_CONTROL_SUBMIT_ITEMSIZE,
BRCMF_H2D_MSGRING_RXPOST_SUBMIT_ITEMSIZE,
BRCMF_PCIE_MB_INT_FN0_1);
}
+static void brcmf_pcie_hostready(struct brcmf_pciedev_info *devinfo)
+{
+ if (devinfo->shared.flags & BRCMF_PCIE_SHARED_HOSTRDY_DB1)
+ brcmf_pcie_write_reg32(devinfo,
+ BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_1, 1);
+}
static irqreturn_t brcmf_pcie_quick_check_isr(int irq, void *arg)
{
brcmf_dbg(PCIE, "RING !\n");
/* Any arbitrary value will do, lets use 1 */
- brcmf_pcie_write_reg32(devinfo, BRCMF_PCIE_PCIE2REG_H2D_MAILBOX, 1);
+ brcmf_pcie_write_reg32(devinfo, BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_0, 1);
return 0;
}
struct brcmf_pcie_ringbuf *ring;
u32 size;
u32 addr;
+ const u32 *ring_itemsize_array;
+
+ if (devinfo->shared.version < BRCMF_PCIE_SHARED_VERSION_7)
+ ring_itemsize_array = brcmf_ring_itemsize_pre_v7;
+ else
+ ring_itemsize_array = brcmf_ring_itemsize;
- size = brcmf_ring_max_item[ring_id] * brcmf_ring_itemsize[ring_id];
+ size = brcmf_ring_max_item[ring_id] * ring_itemsize_array[ring_id];
dma_buf = brcmf_pcie_init_dmabuffer_for_device(devinfo, size,
tcm_ring_phys_addr + BRCMF_RING_MEM_BASE_ADDR_OFFSET,
&dma_handle);
addr = tcm_ring_phys_addr + BRCMF_RING_MAX_ITEM_OFFSET;
brcmf_pcie_write_tcm16(devinfo, addr, brcmf_ring_max_item[ring_id]);
addr = tcm_ring_phys_addr + BRCMF_RING_LEN_ITEMS_OFFSET;
- brcmf_pcie_write_tcm16(devinfo, addr, brcmf_ring_itemsize[ring_id]);
+ brcmf_pcie_write_tcm16(devinfo, addr, ring_itemsize_array[ring_id]);
ring = kzalloc(sizeof(*ring), GFP_KERNEL);
if (!ring) {
return NULL;
}
brcmf_commonring_config(&ring->commonring, brcmf_ring_max_item[ring_id],
- brcmf_ring_itemsize[ring_id], dma_buf);
+ ring_itemsize_array[ring_id], dma_buf);
ring->dma_handle = dma_handle;
ring->devinfo = devinfo;
brcmf_commonring_register_cb(&ring->commonring,
init_waitqueue_head(&devinfo->mbdata_resp_wait);
brcmf_pcie_intr_enable(devinfo);
+ brcmf_pcie_hostready(devinfo);
if (brcmf_attach(&devinfo->pdev->dev, devinfo->settings) == 0)
return;
brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2);
brcmf_bus_change_state(bus, BRCMF_BUS_UP);
brcmf_pcie_intr_enable(devinfo);
+ brcmf_pcie_hostready(devinfo);
return 0;
}
BRCMF_FW_DEF(4356, "brcmfmac4356-sdio");
BRCMF_FW_DEF(4373, "brcmfmac4373-sdio");
-static struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
+static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143),
BRCMF_FW_ENTRY(BRCM_CC_43241_CHIP_ID, 0x0000001F, 43241B0),
BRCMF_FW_ENTRY(BRCM_CC_43241_CHIP_ID, 0x00000020, 43241B4),
BRCMF_FW_DEF(43569, "brcmfmac43569");
BRCMF_FW_DEF(4373, "brcmfmac4373");
-static struct brcmf_firmware_mapping brcmf_usb_fwnames[] = {
+static const struct brcmf_firmware_mapping brcmf_usb_fwnames[] = {
BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143),
BRCMF_FW_ENTRY(BRCM_CC_43235_CHIP_ID, 0x00000008, 43236B),
BRCMF_FW_ENTRY(BRCM_CC_43236_CHIP_ID, 0x00000008, 43236B),
IPW2100_ORD(ASSOCIATED_AP_PTR,
"0 if not associated, else pointer to AP table entry"),
IPW2100_ORD(AVAILABLE_AP_CNT,
- "AP's decsribed in the AP table"),
+ "AP's described in the AP table"),
IPW2100_ORD(AP_LIST_PTR, "Ptr to list of available APs"),
IPW2100_ORD(STAT_AP_ASSNS, "associations"),
IPW2100_ORD(STAT_ASSN_FAIL, "association failures"),
IPW_ORD_STAT_PERCENT_RETRIES, // current calculation of % missed tx retries
IPW_ORD_ASSOCIATED_AP_PTR, // If associated, this is ptr to the associated
// AP table entry. set to 0 if not associated
- IPW_ORD_AVAILABLE_AP_CNT, // # of AP's decsribed in the AP table
+ IPW_ORD_AVAILABLE_AP_CNT, // # of AP's described in the AP table
IPW_ORD_AP_LIST_PTR, // Ptr to list of available APs
IPW_ORD_STAT_AP_ASSNS, // # of associations
IPW_ORD_STAT_ASSN_FAIL, // # of association failures
#ifdef CONFIG_IPW2200_QOS
module_param(qos_enable, int, 0444);
-MODULE_PARM_DESC(qos_enable, "enable all QoS functionalitis");
+MODULE_PARM_DESC(qos_enable, "enable all QoS functionalities");
module_param(qos_burst_enable, int, 0444);
MODULE_PARM_DESC(qos_burst_enable, "enable QoS burst mode");
/******************************************************************************
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
#include <linux/module.h>
#include <linux/stringify.h>
#include "iwl-config.h"
-#include "iwl-csr.h"
#include "iwl-agn-hw.h"
/* Highest firmware API version supported */
.base_params = &iwl1000_base_params, \
.eeprom_params = &iwl1000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl1000_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 1000 BGN",
.eeprom_params = &iwl1000_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
.rx_with_siso_diversity = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl100_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 100 BGN",
/******************************************************************************
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
.base_params = &iwl2000_base_params, \
.eeprom_params = &iwl20x0_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl2000_2bgn_cfg = {
.base_params = &iwl2030_base_params, \
.eeprom_params = &iwl20x0_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl2030_2bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 2230 BGN",
.eeprom_params = &iwl20x0_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
.rx_with_siso_diversity = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl105_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 105 BGN",
.eeprom_params = &iwl20x0_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
.rx_with_siso_diversity = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl135_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 135 BGN",
#include <linux/module.h>
#include <linux/stringify.h>
#include "iwl-config.h"
-#include "iwl-agn-hw.h"
/* Highest firmware API version supported */
#define IWL_22000_UCODE_API_MAX 38
.ucode_api_max = IWL_22000_UCODE_API_MAX, \
.ucode_api_min = IWL_22000_UCODE_API_MIN, \
.device_family = IWL_DEVICE_FAMILY_22000, \
- .max_inst_size = IWL60_RTC_INST_SIZE, \
- .max_data_size = IWL60_RTC_DATA_SIZE, \
.base_params = &iwl_22000_base_params, \
.led_mode = IWL_LED_RF_STATE, \
.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_22000, \
.name = "Intel(R) Dual Band Wireless AC 22000",
.fw_name_pre = IWL_22000_HR_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AC 22000",
.fw_name_pre = IWL_22000_HR_CDB_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AC 22000",
.fw_name_pre = IWL_22000_JF_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AX 22000",
.fw_name_pre = IWL_22000_HR_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AX 22000",
.fw_name_pre = IWL_22000_HR_F0_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AX 22000",
.fw_name_pre = IWL_22000_JF_B0_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
.name = "Intel(R) Dual Band Wireless AX 22000",
.fw_name_pre = IWL_22000_HR_A0_FW_PRE,
IWL_DEVICE_22000,
+ .csr = &iwl_csr_v1,
.ht_params = &iwl_22000_ht_params,
.nvm_ver = IWL_22000_NVM_VERSION,
.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
/******************************************************************************
*
* Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
#include <linux/stringify.h>
#include "iwl-config.h"
#include "iwl-agn-hw.h"
-#include "iwl-csr.h"
/* Highest firmware API version supported */
#define IWL5000_UCODE_API_MAX 5
.base_params = &iwl5000_base_params, \
.eeprom_params = &iwl5000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl5300_agn_cfg = {
.name = "Intel(R) Ultimate N WiFi Link 5300 AGN",
.eeprom_params = &iwl5000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
.internal_wimax_coex = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl5150_agn_cfg = {
.name = "Intel(R) WiMAX/WiFi Link 5150 AGN",
/******************************************************************************
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
.base_params = &iwl6000_g2_base_params, \
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6005_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N 6205 AGN",
.base_params = &iwl6000_g2_base_params, \
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6030_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N 6230 AGN",
.base_params = &iwl6000_g2_base_params, \
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_RF_STATE, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6035_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N 6235 AGN",
.base_params = &iwl6000_base_params, \
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6000i_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N 6200 AGN",
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
.internal_wimax_coex = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6050_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 AGN",
.eeprom_params = &iwl6000_eeprom_params, \
.led_mode = IWL_LED_BLINK, \
.internal_wimax_coex = true, \
- .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+ .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl6150_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2015 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <linux/module.h>
#include <linux/stringify.h>
#include "iwl-config.h"
-#include "iwl-agn-hw.h"
/* Highest firmware API version supported */
#define IWL7260_UCODE_API_MAX 17
#define IWL_DEVICE_7000_COMMON \
.device_family = IWL_DEVICE_FAMILY_7000, \
- .max_inst_size = IWL60_RTC_INST_SIZE, \
- .max_data_size = IWL60_RTC_DATA_SIZE, \
.base_params = &iwl7000_base_params, \
.led_mode = IWL_LED_RF_STATE, \
.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_7000, \
.non_shared_ant = ANT_A, \
.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \
- .dccm_offset = IWL7000_DCCM_OFFSET
+ .dccm_offset = IWL7000_DCCM_OFFSET, \
+ .csr = &iwl_csr_v1
#define IWL_DEVICE_7000 \
IWL_DEVICE_7000_COMMON, \
*
* Copyright(c) 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2014 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* Copyright(c) 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2014 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <linux/module.h>
#include <linux/stringify.h>
#include "iwl-config.h"
-#include "iwl-agn-hw.h"
/* Highest firmware API version supported */
#define IWL8000_UCODE_API_MAX 36
#define IWL_DEVICE_8000_COMMON \
.device_family = IWL_DEVICE_FAMILY_8000, \
- .max_inst_size = IWL60_RTC_INST_SIZE, \
- .max_data_size = IWL60_RTC_DATA_SIZE, \
.base_params = &iwl8000_base_params, \
.led_mode = IWL_LED_RF_STATE, \
.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_8000, \
.apmg_not_supported = true, \
.nvm_type = IWL_NVM_EXT, \
.dbgc_supported = true, \
- .min_umac_error_event_table = 0x800000
+ .min_umac_error_event_table = 0x800000, \
+ .csr = &iwl_csr_v1
#define IWL_DEVICE_8000 \
IWL_DEVICE_8000_COMMON, \
#include <linux/module.h>
#include <linux/stringify.h>
#include "iwl-config.h"
-#include "iwl-agn-hw.h"
#include "fw/file.h"
/* Highest firmware API version supported */
.ucode_api_max = IWL9000_UCODE_API_MAX, \
.ucode_api_min = IWL9000_UCODE_API_MIN, \
.device_family = IWL_DEVICE_FAMILY_9000, \
- .max_inst_size = IWL60_RTC_INST_SIZE, \
- .max_data_size = IWL60_RTC_DATA_SIZE, \
.base_params = &iwl9000_base_params, \
.led_mode = IWL_LED_RF_STATE, \
.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_9000, \
.rf_id = true, \
.nvm_type = IWL_NVM_EXT, \
.dbgc_supported = true, \
- .min_umac_error_event_table = 0x800000
+ .min_umac_error_event_table = 0x800000, \
+ .csr = &iwl_csr_v1
const struct iwl_cfg iwl9160_2ac_cfg = {
.name = "Intel(R) Dual Band Wireless AC 9160",
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
} __packed;
#define IWL_SCAN_REQ_UMAC_SIZE_V8 sizeof(struct iwl_scan_req_umac)
-#define IWL_SCAN_REQ_UMAC_SIZE_V7 (sizeof(struct iwl_scan_req_umac) - \
- 4 * sizeof(u8))
-#define IWL_SCAN_REQ_UMAC_SIZE_V6 (sizeof(struct iwl_scan_req_umac) - \
- 2 * sizeof(u8) - sizeof(__le16))
-#define IWL_SCAN_REQ_UMAC_SIZE_V1 (sizeof(struct iwl_scan_req_umac) - \
- 2 * sizeof(__le32) - 2 * sizeof(u8) - \
- sizeof(__le16))
+#define IWL_SCAN_REQ_UMAC_SIZE_V7 48
+#define IWL_SCAN_REQ_UMAC_SIZE_V6 44
+#define IWL_SCAN_REQ_UMAC_SIZE_V1 36
/**
* struct iwl_umac_scan_abort
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
IWL_UCODE_TLV_FW_DBG_TRIGGER = 40,
IWL_UCODE_TLV_FW_GSCAN_CAPA = 50,
IWL_UCODE_TLV_FW_MEM_SEG = 51,
+ IWL_UCODE_TLV_IML = 52,
};
struct iwl_ucode_tlv {
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* @ucode_ver: ucode version from the ucode file
* @fw_version: firmware version string
* @img: ucode image like ucode_rt, ucode_init, ucode_wowlan.
+ * @iml_len: length of the image loader image
+ * @iml: image loader fw image
* @ucode_capa: capabilities parsed from the ucode file.
* @enhance_sensitivity_table: device can do enhanced sensitivity.
* @init_evtlog_ptr: event log offset for init ucode.
/* ucode images */
struct fw_img img[IWL_UCODE_TYPE_MAX];
+ size_t iml_len;
+ u8 *iml;
struct iwl_ucode_capabilities ucode_capa;
bool enhance_sensitivity_table;
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
static int iwl_fill_paging_mem(struct iwl_fw_runtime *fwrt,
const struct fw_img *image)
{
- int sec_idx, idx;
+ int sec_idx, idx, ret;
u32 offset = 0;
/*
*/
if (sec_idx >= image->num_sec - 1) {
IWL_ERR(fwrt, "Paging: Missing CSS and/or paging sections\n");
- iwl_free_fw_paging(fwrt);
- return -EINVAL;
+ ret = -EINVAL;
+ goto err;
}
/* copy the CSS block to the dram */
IWL_DEBUG_FW(fwrt, "Paging: load paging CSS to FW, sec = %d\n",
sec_idx);
+ if (image->sec[sec_idx].len > fwrt->fw_paging_db[0].fw_paging_size) {
+ IWL_ERR(fwrt, "CSS block is larger than paging size\n");
+ ret = -EINVAL;
+ goto err;
+ }
+
memcpy(page_address(fwrt->fw_paging_db[0].fw_paging_block),
image->sec[sec_idx].data,
- fwrt->fw_paging_db[0].fw_paging_size);
+ image->sec[sec_idx].len);
dma_sync_single_for_device(fwrt->trans->dev,
fwrt->fw_paging_db[0].fw_paging_phys,
fwrt->fw_paging_db[0].fw_paging_size,
sec_idx++;
/*
- * copy the paging blocks to the dram
- * loop index start from 1 since that CSS block already copied to dram
- * and CSS index is 0.
- * loop stop at num_of_paging_blk since that last block is not full.
+ * Copy the paging blocks to the dram. The loop index starts
+ * from 1 since the CSS block (index 0) was already copied to
+ * dram. We use num_of_paging_blk + 1 to account for that.
*/
- for (idx = 1; idx < fwrt->num_of_paging_blk; idx++) {
+ for (idx = 1; idx < fwrt->num_of_paging_blk + 1; idx++) {
struct iwl_fw_paging *block = &fwrt->fw_paging_db[idx];
+ int remaining = image->sec[sec_idx].len - offset;
+ int len = block->fw_paging_size;
+
+ /*
+ * For the last block, we copy all that is remaining,
+ * for all other blocks, we copy fw_paging_size at a
+ * time. */
+ if (idx == fwrt->num_of_paging_blk) {
+ len = remaining;
+ if (remaining !=
+ fwrt->num_of_pages_in_last_blk * FW_PAGING_SIZE) {
+ IWL_ERR(fwrt,
+ "Paging: last block contains more data than expected %d\n",
+ remaining);
+ ret = -EINVAL;
+ goto err;
+ }
+ } else if (block->fw_paging_size > remaining) {
+ IWL_ERR(fwrt,
+ "Paging: not enough data in other in block %d (%d)\n",
+ idx, remaining);
+ ret = -EINVAL;
+ goto err;
+ }
memcpy(page_address(block->fw_paging_block),
- image->sec[sec_idx].data + offset,
- block->fw_paging_size);
+ image->sec[sec_idx].data + offset, len);
dma_sync_single_for_device(fwrt->trans->dev,
block->fw_paging_phys,
block->fw_paging_size,
IWL_DEBUG_FW(fwrt,
"Paging: copied %d paging bytes to block %d\n",
- fwrt->fw_paging_db[idx].fw_paging_size,
- idx);
-
- offset += fwrt->fw_paging_db[idx].fw_paging_size;
- }
-
- /* copy the last paging block */
- if (fwrt->num_of_pages_in_last_blk > 0) {
- struct iwl_fw_paging *block = &fwrt->fw_paging_db[idx];
+ len, idx);
- memcpy(page_address(block->fw_paging_block),
- image->sec[sec_idx].data + offset,
- FW_PAGING_SIZE * fwrt->num_of_pages_in_last_blk);
- dma_sync_single_for_device(fwrt->trans->dev,
- block->fw_paging_phys,
- block->fw_paging_size,
- DMA_BIDIRECTIONAL);
-
- IWL_DEBUG_FW(fwrt,
- "Paging: copied %d pages in the last block %d\n",
- fwrt->num_of_pages_in_last_blk, idx);
+ offset += block->fw_paging_size;
}
return 0;
+
+err:
+ iwl_free_fw_paging(fwrt);
+ return ret;
}
static int iwl_save_fw_paging(struct iwl_fw_runtime *fwrt,
*
* Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
* Copyright (C) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright (C) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <linux/netdevice.h>
#include <linux/ieee80211.h>
#include <linux/nl80211.h>
+#include "iwl-csr.h"
enum iwl_device_family {
IWL_DEVICE_FAMILY_UNDEFINED,
u32 backoff;
};
+/**
+ * struct iwl_csr_params
+ *
+ * @flag_sw_reset: reset the device
+ * @flag_mac_clock_ready:
+ * Indicates MAC (ucode processor, etc.) is powered up and can run.
+ * Internal resources are accessible.
+ * NOTE: This does not indicate that the processor is actually running.
+ * NOTE: This does not indicate that device has completed
+ * init or post-power-down restore of internal SRAM memory.
+ * Use CSR_UCODE_DRV_GP1_BIT_MAC_SLEEP as indication that
+ * SRAM is restored and uCode is in normal operation mode.
+ * This note is relevant only for pre 5xxx devices.
+ * NOTE: After device reset, this bit remains "0" until host sets
+ * INIT_DONE
+ * @flag_init_done: Host sets this to put device into fully operational
+ * D0 power mode. Host resets this after SW_RESET to put device into
+ * low power mode.
+ * @flag_mac_access_req: Host sets this to request and maintain MAC wakeup,
+ * to allow host access to device-internal resources. Host must wait for
+ * mac_clock_ready (and !GOING_TO_SLEEP) before accessing non-CSR device
+ * registers.
+ * @flag_val_mac_access_en: mac access is enabled
+ * @flag_master_dis: disable master
+ * @flag_stop_master: stop master
+ * @addr_sw_reset: address for resetting the device
+ * @mac_addr0_otp: first part of MAC address from OTP
+ * @mac_addr1_otp: second part of MAC address from OTP
+ * @mac_addr0_strap: first part of MAC address from strap
+ * @mac_addr1_strap: second part of MAC address from strap
+ */
+struct iwl_csr_params {
+ u8 flag_sw_reset;
+ u8 flag_mac_clock_ready;
+ u8 flag_init_done;
+ u8 flag_mac_access_req;
+ u8 flag_val_mac_access_en;
+ u8 flag_master_dis;
+ u8 flag_stop_master;
+ u8 addr_sw_reset;
+ u32 mac_addr0_otp;
+ u32 mac_addr1_otp;
+ u32 mac_addr0_strap;
+ u32 mac_addr1_strap;
+};
+
/**
* struct iwl_cfg
* @name: Official name of the device
* next step. Supported only in integrated solutions.
* @ucode_api_max: Highest version of uCode API supported by driver.
* @ucode_api_min: Lowest version of uCode API supported by driver.
- * @max_inst_size: The maximal length of the fw inst section
- * @max_data_size: The maximal length of the fw data section
+ * @max_inst_size: The maximal length of the fw inst section (only DVM)
+ * @max_data_size: The maximal length of the fw data section (only DVM)
* @valid_tx_ant: valid transmit antenna
* @valid_rx_ant: valid receive antenna
* @non_shared_ant: the antenna that is for WiFi only
* @mac_addr_from_csr: read HW address from CSR registers
* @features: hw features, any combination of feature_whitelist
* @pwr_tx_backoffs: translation table between power limits and backoffs
+ * @csr: csr flags and addresses that are different across devices
* @max_rx_agg_size: max RX aggregation size of the ADDBA request/response
* @max_tx_agg_size: max TX aggregation size of the ADDBA request/response
* @max_ht_ampdu_factor: the exponent of the max length of A-MPDU that the
const struct iwl_pwr_tx_backoff *pwr_tx_backoffs;
const char *default_nvm_file_C_step;
const struct iwl_tt_params *thermal_params;
+ const struct iwl_csr_params *csr;
enum iwl_device_family device_family;
enum iwl_led_mode led_mode;
enum iwl_nvm_type nvm_type;
u32 soc_latency;
u16 nvm_ver;
u16 nvm_calib_ver;
- u16 rx_with_siso_diversity:1,
+ u32 rx_with_siso_diversity:1,
bt_shared_single_ant:1,
internal_wimax_coex:1,
host_interrupt_operation_mode:1,
u32 extra_phy_cfg_flags;
};
+static const struct iwl_csr_params iwl_csr_v1 = {
+ .flag_mac_clock_ready = 0,
+ .flag_val_mac_access_en = 0,
+ .flag_init_done = 2,
+ .flag_mac_access_req = 3,
+ .flag_sw_reset = 7,
+ .flag_master_dis = 8,
+ .flag_stop_master = 9,
+ .addr_sw_reset = (CSR_BASE + 0x020),
+ .mac_addr0_otp = 0x380,
+ .mac_addr1_otp = 0x384,
+ .mac_addr0_strap = 0x388,
+ .mac_addr1_strap = 0x38C
+};
+
+static const struct iwl_csr_params iwl_csr_v2 = {
+ .flag_init_done = 6,
+ .flag_mac_clock_ready = 20,
+ .flag_val_mac_access_en = 20,
+ .flag_mac_access_req = 21,
+ .flag_master_dis = 28,
+ .flag_stop_master = 29,
+ .flag_sw_reset = 31,
+ .addr_sw_reset = (CSR_BASE + 0x024),
+ .mac_addr0_otp = 0x30,
+ .mac_addr1_otp = 0x34,
+ .mac_addr0_strap = 0x38,
+ .mac_addr1_strap = 0x3C
+};
+
/*
* This list declares the config structures for all devices.
*/
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* RESET */
#define CSR_RESET_REG_FLAG_NEVO_RESET (0x00000001)
#define CSR_RESET_REG_FLAG_FORCE_NMI (0x00000002)
-#define CSR_RESET_REG_FLAG_SW_RESET (0x00000080)
#define CSR_RESET_REG_FLAG_MASTER_DISABLED (0x00000100)
#define CSR_RESET_REG_FLAG_STOP_MASTER (0x00000200)
#define CSR_RESET_LINK_PWR_MGMT_DISABLED (0x80000000)
* 4: GOING_TO_SLEEP
* Indicates MAC is entering a power-saving sleep power-down.
* Not a good time to access device-internal resources.
- * 3: MAC_ACCESS_REQ
- * Host sets this to request and maintain MAC wakeup, to allow host
- * access to device-internal resources. Host must wait for
- * MAC_CLOCK_READY (and !GOING_TO_SLEEP) before accessing non-CSR
- * device registers.
- * 2: INIT_DONE
- * Host sets this to put device into fully operational D0 power mode.
- * Host resets this after SW_RESET to put device into low power mode.
- * 0: MAC_CLOCK_READY
- * Indicates MAC (ucode processor, etc.) is powered up and can run.
- * Internal resources are accessible.
- * NOTE: This does not indicate that the processor is actually running.
- * NOTE: This does not indicate that device has completed
- * init or post-power-down restore of internal SRAM memory.
- * Use CSR_UCODE_DRV_GP1_BIT_MAC_SLEEP as indication that
- * SRAM is restored and uCode is in normal operation mode.
- * Later devices (5xxx/6xxx/1xxx) use non-volatile SRAM, and
- * do not need to save/restore it.
- * NOTE: After device reset, this bit remains "0" until host sets
- * INIT_DONE
*/
-#define CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY (0x00000001)
-#define CSR_GP_CNTRL_REG_FLAG_INIT_DONE (0x00000004)
-#define CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ (0x00000008)
#define CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP (0x00000010)
#define CSR_GP_CNTRL_REG_FLAG_XTAL_ON (0x00000400)
-#define CSR_GP_CNTRL_REG_VAL_MAC_ACCESS_EN (0x00000001)
-
#define CSR_GP_CNTRL_REG_MSK_POWER_SAVE_TYPE (0x07000000)
#define CSR_GP_CNTRL_REG_FLAG_RFKILL_WAKE_L1A_EN (0x04000000)
#define CSR_GP_CNTRL_REG_FLAG_HW_RF_KILL_SW (0x08000000)
for (i = 0; i < ARRAY_SIZE(drv->fw.dbg_trigger_tlv); i++)
kfree(drv->fw.dbg_trigger_tlv[i]);
kfree(drv->fw.dbg_mem_tlv);
+ kfree(drv->fw.iml);
for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
iwl_free_fw_img(drv, drv->fw.img + i);
pieces->n_dbg_mem_tlv++;
break;
}
+ case IWL_UCODE_TLV_IML: {
+ drv->fw.iml_len = tlv_len;
+ drv->fw.iml = kmemdup(tlv_data, tlv_len, GFP_KERNEL);
+ if (!drv->fw.iml)
+ return -ENOMEM;
+ break;
+ }
default:
IWL_DEBUG_INFO(drv, "unknown TLV: %d\n", tlv_type);
break;
module_param_named(disable_11ac, iwlwifi_mod_params.disable_11ac, bool, 0444);
MODULE_PARM_DESC(disable_11ac, "Disable VHT capabilities (default: false)");
+
+module_param_named(remove_when_gone,
+ iwlwifi_mod_params.remove_when_gone, bool,
+ 0444);
+MODULE_PARM_DESC(remove_when_gone,
+ "Remove dev from PCIe bus if it is deemed inaccessible (default: false)");
* GPL LICENSE SUMMARY
*
* Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* Enable 40MHz radio clock */
iwl_write32(trans, CSR_GP_CNTRL,
iwl_read32(trans, CSR_GP_CNTRL) |
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
/* wait for clock to be ready */
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
25000);
if (ret < 0) {
IWL_ERR(trans, "Time out access OTP\n");
* @lar_disable: disable LAR (regulatory), default = 0
* @fw_monitor: allow to use firmware monitor
* @disable_11ac: disable VHT capabilities, default = false.
+ * @remove_when_gone: remove an inaccessible device from the PCIe bus.
*/
struct iwl_mod_params {
int swcrypto;
bool lar_disable;
bool fw_monitor;
bool disable_11ac;
+ bool remove_when_gone;
};
#endif /* #__iwl_modparams_h__ */
static void iwl_set_hw_address_from_csr(struct iwl_trans *trans,
struct iwl_nvm_data *data)
{
- __le32 mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_STRAP));
- __le32 mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_STRAP));
+ __le32 mac_addr0 =
+ cpu_to_le32(iwl_read32(trans,
+ trans->cfg->csr->mac_addr0_strap));
+ __le32 mac_addr1 =
+ cpu_to_le32(iwl_read32(trans,
+ trans->cfg->csr->mac_addr1_strap));
iwl_flip_hw_address(mac_addr0, mac_addr1, data->hw_addr);
/*
if (is_valid_ether_addr(data->hw_addr))
return;
- mac_addr0 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR0_OTP));
- mac_addr1 = cpu_to_le32(iwl_read32(trans, CSR_MAC_ADDR1_OTP));
+ mac_addr0 = cpu_to_le32(iwl_read32(trans,
+ trans->cfg->csr->mac_addr0_otp));
+ mac_addr1 = cpu_to_le32(iwl_read32(trans,
+ trans->cfg->csr->mac_addr1_otp));
iwl_flip_hw_address(mac_addr0, mac_addr1, data->hw_addr);
}
return flags;
}
+struct regdb_ptrs {
+ struct ieee80211_wmm_rule *rule;
+ u32 token;
+};
+
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
- int num_of_ch, __le32 *channels, u16 fw_mcc)
+ int num_of_ch, __le32 *channels, u16 fw_mcc,
+ u16 geo_info)
{
int ch_idx;
u16 ch_flags;
u32 reg_rule_flags, prev_reg_rule_flags = 0;
const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ?
iwl_ext_nvm_channels : iwl_nvm_channels;
- struct ieee80211_regdomain *regd;
- int size_of_regd;
+ struct ieee80211_regdomain *regd, *copy_rd;
+ int size_of_regd, regd_to_copy, wmms_to_copy;
+ int size_of_wmms = 0;
struct ieee80211_reg_rule *rule;
+ struct ieee80211_wmm_rule *wmm_rule, *d_wmm, *s_wmm;
+ struct regdb_ptrs *regdb_ptrs;
enum nl80211_band band;
int center_freq, prev_center_freq = 0;
- int valid_rules = 0;
+ int valid_rules = 0, n_wmms = 0;
+ int i;
bool new_rule;
int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ?
IWL_NVM_NUM_CHANNELS_EXT : IWL_NVM_NUM_CHANNELS;
sizeof(struct ieee80211_regdomain) +
num_of_ch * sizeof(struct ieee80211_reg_rule);
- regd = kzalloc(size_of_regd, GFP_KERNEL);
+ if (geo_info & GEO_WMM_ETSI_5GHZ_INFO)
+ size_of_wmms =
+ num_of_ch * sizeof(struct ieee80211_wmm_rule);
+
+ regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL);
if (!regd)
return ERR_PTR(-ENOMEM);
+ regdb_ptrs = kcalloc(num_of_ch, sizeof(*regdb_ptrs), GFP_KERNEL);
+ if (!regdb_ptrs) {
+ copy_rd = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ /* set alpha2 from FW. */
+ regd->alpha2[0] = fw_mcc >> 8;
+ regd->alpha2[1] = fw_mcc & 0xff;
+
+ wmm_rule = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
ch_flags = (u16)__le32_to_cpup(channels + ch_idx);
band = (ch_idx < NUM_2GHZ_CHANNELS) ?
iwl_nvm_print_channel_flags(dev, IWL_DL_LAR,
nvm_chan[ch_idx], ch_flags);
+
+ if (!(geo_info & GEO_WMM_ETSI_5GHZ_INFO) ||
+ band == NL80211_BAND_2GHZ)
+ continue;
+
+ if (!reg_query_regdb_wmm(regd->alpha2, center_freq,
+ ®db_ptrs[n_wmms].token, wmm_rule)) {
+ /* Add only new rules */
+ for (i = 0; i < n_wmms; i++) {
+ if (regdb_ptrs[i].token ==
+ regdb_ptrs[n_wmms].token) {
+ rule->wmm_rule = regdb_ptrs[i].rule;
+ break;
+ }
+ }
+ if (i == n_wmms) {
+ rule->wmm_rule = wmm_rule;
+ regdb_ptrs[n_wmms++].rule = wmm_rule;
+ wmm_rule++;
+ }
+ }
}
regd->n_reg_rules = valid_rules;
+ regd->n_wmm_rules = n_wmms;
- /* set alpha2 from FW. */
- regd->alpha2[0] = fw_mcc >> 8;
- regd->alpha2[1] = fw_mcc & 0xff;
+ /*
+ * Narrow down regdom for unused regulatory rules to prevent hole
+ * between reg rules to wmm rules.
+ */
+ regd_to_copy = sizeof(struct ieee80211_regdomain) +
+ valid_rules * sizeof(struct ieee80211_reg_rule);
+
+ wmms_to_copy = sizeof(struct ieee80211_wmm_rule) * n_wmms;
+
+ copy_rd = kzalloc(regd_to_copy + wmms_to_copy, GFP_KERNEL);
+ if (!copy_rd) {
+ copy_rd = ERR_PTR(-ENOMEM);
+ goto out;
+ }
- return regd;
+ memcpy(copy_rd, regd, regd_to_copy);
+ memcpy((u8 *)copy_rd + regd_to_copy, (u8 *)regd + size_of_regd,
+ wmms_to_copy);
+
+ d_wmm = (struct ieee80211_wmm_rule *)((u8 *)copy_rd + regd_to_copy);
+ s_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
+ for (i = 0; i < regd->n_reg_rules; i++) {
+ if (!regd->reg_rules[i].wmm_rule)
+ continue;
+
+ copy_rd->reg_rules[i].wmm_rule = d_wmm +
+ (regd->reg_rules[i].wmm_rule - s_wmm) /
+ sizeof(struct ieee80211_wmm_rule);
+ }
+
+out:
+ kfree(regdb_ptrs);
+ kfree(regd);
+ return copy_rd;
}
IWL_EXPORT_SYMBOL(iwl_parse_nvm_mcc_info);
*
* This function parses the regulatory channel data received as a
* MCC_UPDATE_CMD command. It returns a newly allocation regulatory domain,
- * to be fed into the regulatory core. An ERR_PTR is returned on error.
+ * to be fed into the regulatory core. In case the geo_info is set handle
+ * accordingly. An ERR_PTR is returned on error.
* If not given to the regulatory core, the user is responsible for freeing
* the regdomain returned here with kfree.
*/
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
- int num_of_ch, __le32 *channels, u16 fw_mcc);
+ int num_of_ch, __le32 *channels, u16 fw_mcc,
+ u16 geo_info);
/**
* struct iwl_nvm_section - describes an NVM section in memory.
* @wide_cmd_header: true when ucode supports wide command header format
* @num_rx_queues: number of RX queues allocated by the transport;
* the transport must set this before calling iwl_drv_start()
+ * @iml_len: the length of the image loader
+ * @iml: a pointer to the image loader itself
* @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
* The user should use iwl_trans_{alloc,free}_tx_cmd.
* @rx_mpdu_cmd: MPDU RX command ID, must be assigned by opmode before
u8 num_rx_queues;
+ size_t iml_len;
+ u8 *iml;
+
/* The following fields are internal only */
struct kmem_cache *dev_cmd_pool;
char dev_cmd_pool_name[50];
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
- *
* The full GNU General Public License is included in this distribution
* in the file called COPYING.
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
IWL_WOWLAN_WAKEUP_LINK_CHANGE);
}
+ if (wowlan->any) {
+ wowlan_config_cmd->wakeup_filter |=
+ cpu_to_le32(IWL_WOWLAN_WAKEUP_BEACON_MISS |
+ IWL_WOWLAN_WAKEUP_LINK_CHANGE |
+ IWL_WOWLAN_WAKEUP_RX_FRAME |
+ IWL_WOWLAN_WAKEUP_BCN_FILTERING);
+ }
+
return 0;
}
regd = iwl_parse_nvm_mcc_info(mvm->trans->dev, mvm->cfg,
__le32_to_cpu(resp->n_channels),
resp->channels,
- __le16_to_cpu(resp->mcc));
+ __le16_to_cpu(resp->mcc),
+ __le16_to_cpu(resp->geo_info));
/* Store the return source id */
src_id = resp->source_id;
kfree(resp);
sizeof(trans->dbg_conf_tlv));
trans->dbg_trigger_tlv = mvm->fw->dbg_trigger_tlv;
+ trans->iml = mvm->fw->iml;
+ trans->iml_len = mvm->fw->iml_len;
+
/* set up notification wait support */
iwl_notification_wait_init(&mvm->notif_wait);
unsigned int hdrlen = ieee80211_hdrlen(hdr->frame_control);
if (desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) {
+ len -= 2;
pad_len = 2;
-
- /*
- * If the device inserted padding it means that (it thought)
- * the 802.11 header wasn't a multiple of 4 bytes long. In
- * this case, reserve two bytes at the start of the SKB to
- * align the payload properly in case we end up copying it.
- */
- skb_reserve(skb, pad_len);
}
- len -= pad_len;
/* If frame is small enough to fit in skb->head, pull it completely.
* If not, only pull ieee80211_hdr (including crypto if present, and
return;
}
+ if (desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) {
+ /*
+ * If the device inserted padding it means that (it thought)
+ * the 802.11 header wasn't a multiple of 4 bytes long. In
+ * this case, reserve two bytes at the start of the SKB to
+ * align the payload properly in case we end up copying it.
+ */
+ skb_reserve(skb, 2);
+ }
+
rx_status = IEEE80211_SKB_RXCB(skb);
if (iwl_mvm_rx_crypto(mvm, hdr, rx_status, desc,
return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb);
if (iwl_mvm_vif_low_latency(iwl_mvm_vif_from_mac80211(mvmsta->vif)) ||
- tid_to_mac80211_ac[tid] < IEEE80211_AC_BE ||
!(mvmsta->amsdu_enabled & BIT(tid)))
return iwl_mvm_tx_tso_segment(skb, 1, netdev_flags, mpdus_skb);
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* set INIT_DONE flag */
iwl_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
/* and wait for clock stabilization */
if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
udelay(2);
err = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
25000);
if (err < 0) {
IWL_DEBUG_INFO(trans,
* @hw_init_mask: initial unmasked hw causes
* @fh_mask: current unmasked fh causes
* @hw_mask: current unmasked hw causes
+ * @in_rescan: true if we have triggered a device rescan
+ * @scheduled_for_removal: true if we have scheduled a device removal
*/
struct iwl_trans_pcie {
struct iwl_rxq *rxq;
u32 fh_mask;
u32 hw_mask;
cpumask_t affinity_mask[IWL_MAX_RX_HW_QUEUES];
+ u16 tx_cmd_queue_size;
+ bool in_rescan;
+ bool scheduled_for_removal;
};
static inline struct iwl_trans_pcie *
* Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* Portions of this file are derived from the ipw3945 project, as well
* as portions of the ieee80211 subsystem header files.
IWL_DEBUG_INFO(trans, "Rx queue requesting wakeup, GP1 = 0x%x\n",
reg);
iwl_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
rxq->need_update = true;
return;
}
* GPL LICENSE SUMMARY
*
* Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* BSD LICENSE
*
* Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* Set "initialization complete" bit to move adapter from
* D0U* --> D0A* (powered-up active) state.
*/
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ iwl_set_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_init_done));
/*
* Wait for clock stabilization; once stabilized, access to
* and accesses to uCode SRAM.
*/
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY, 25000);
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ 25000);
if (ret < 0) {
IWL_DEBUG_INFO(trans, "Failed to init the card\n");
return ret;
* Clear "initialization complete" bit to move adapter from
* D0A* (powered-up Active) --> D0U* (Uninitialized) state.
*/
- iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ iwl_clear_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_init_done));
}
void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power)
/* Make sure (redundant) we've released our request to stay awake */
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
/* Stop the device, and put it in low power state */
iwl_pcie_gen2_apm_stop(trans, false);
* Copyright(c) 2007 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2005 - 2015 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/pm_runtime.h>
+#include <linux/module.h>
#include "iwl-drv.h"
#include "iwl-trans.h"
static void iwl_trans_pcie_sw_reset(struct iwl_trans *trans)
{
/* Reset entire device - do controller reset (results in SHRD_HW_RST) */
- iwl_set_bit(trans, CSR_RESET, CSR_RESET_REG_FLAG_SW_RESET);
+ iwl_set_bit(trans, trans->cfg->csr->addr_sw_reset,
+ BIT(trans->cfg->csr->flag_sw_reset));
usleep_range(5000, 6000);
}
* Set "initialization complete" bit to move adapter from
* D0U* --> D0A* (powered-up active) state.
*/
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ iwl_set_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_init_done));
/*
* Wait for clock stabilization; once stabilized, access to
* and accesses to uCode SRAM.
*/
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY, 25000);
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ 25000);
if (ret < 0) {
IWL_ERR(trans, "Failed to init the card\n");
return ret;
* Set "initialization complete" bit to move adapter from
* D0U* --> D0A* (powered-up active) state.
*/
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ iwl_set_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_init_done));
/*
* Wait for clock stabilization; once stabilized, access to
* device-internal resources is possible.
*/
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
25000);
if (WARN_ON(ret < 0)) {
IWL_ERR(trans, "Access time out - failed to enable LP XTAL\n");
* D0A* (powered-up Active) --> D0U* (Uninitialized) state.
*/
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
/* Activates XTAL resources monitor */
__iwl_trans_pcie_set_bit(trans, CSR_MONITOR_CFG_REG,
int ret;
/* stop device's busmaster DMA activity */
- iwl_set_bit(trans, CSR_RESET, CSR_RESET_REG_FLAG_STOP_MASTER);
+ iwl_set_bit(trans, trans->cfg->csr->addr_sw_reset,
+ BIT(trans->cfg->csr->flag_stop_master));
- ret = iwl_poll_bit(trans, CSR_RESET,
- CSR_RESET_REG_FLAG_MASTER_DISABLED,
- CSR_RESET_REG_FLAG_MASTER_DISABLED, 100);
+ ret = iwl_poll_bit(trans, trans->cfg->csr->addr_sw_reset,
+ BIT(trans->cfg->csr->flag_master_dis),
+ BIT(trans->cfg->csr->flag_master_dis), 100);
if (ret < 0)
IWL_WARN(trans, "Master Disable Timed Out, 100 usec\n");
* D0A* (powered-up Active) --> D0U* (Uninitialized) state.
*/
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
}
static int iwl_pcie_nic_init(struct iwl_trans *trans)
/* Make sure (redundant) we've released our request to stay awake */
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
/* Stop the device, and put it in low power state */
iwl_pcie_apm_stop(trans, false);
iwl_pcie_synchronize_irqs(trans);
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
iwl_pcie_enable_rx_wake(trans, false);
iwl_pcie_reset_ict(trans);
iwl_enable_interrupts(trans);
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ iwl_set_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_mac_access_req));
+ iwl_set_bit(trans, CSR_GP_CNTRL,
+ BIT(trans->cfg->csr->flag_init_done));
if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_8000)
udelay(2);
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
25000);
if (ret < 0) {
IWL_ERR(trans, "Failed to resume the device (mac ready)\n");
if (!reset) {
iwl_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
} else {
iwl_trans_pcie_tx_reset(trans);
clear_bit(STATUS_TPOWER_PMI, &trans->status);
}
+struct iwl_trans_pcie_removal {
+ struct pci_dev *pdev;
+ struct work_struct work;
+};
+
+static void iwl_trans_pcie_removal_wk(struct work_struct *wk)
+{
+ struct iwl_trans_pcie_removal *removal =
+ container_of(wk, struct iwl_trans_pcie_removal, work);
+ struct pci_dev *pdev = removal->pdev;
+ char *prop[] = {"EVENT=INACCESSIBLE", NULL};
+
+ dev_err(&pdev->dev, "Device gone - attempting removal\n");
+ kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, prop);
+ pci_lock_rescan_remove();
+ pci_dev_put(pdev);
+ pci_stop_and_remove_bus_device(pdev);
+ pci_unlock_rescan_remove();
+
+ kfree(removal);
+ module_put(THIS_MODULE);
+}
+
static bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans,
unsigned long *flags)
{
/* this bit wakes up the NIC */
__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_8000)
udelay(2);
* and do not save/restore SRAM when power cycling.
*/
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_VAL_MAC_ACCESS_EN,
- (CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
+ BIT(trans->cfg->csr->flag_val_mac_access_en),
+ (BIT(trans->cfg->csr->flag_mac_clock_ready) |
CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP), 15000);
if (unlikely(ret < 0)) {
- iwl_trans_pcie_dump_regs(trans);
- iwl_write32(trans, CSR_RESET, CSR_RESET_REG_FLAG_FORCE_NMI);
+ u32 cntrl = iwl_read32(trans, CSR_GP_CNTRL);
+
WARN_ONCE(1,
"Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n",
- iwl_read32(trans, CSR_GP_CNTRL));
+ cntrl);
+
+ iwl_trans_pcie_dump_regs(trans);
+
+ if (iwlwifi_mod_params.remove_when_gone && cntrl == ~0U) {
+ struct iwl_trans_pcie_removal *removal;
+
+ if (trans_pcie->scheduled_for_removal)
+ goto err;
+
+ IWL_ERR(trans, "Device gone - scheduling removal!\n");
+
+ /*
+ * get a module reference to avoid doing this
+ * while unloading anyway and to avoid
+ * scheduling a work with code that's being
+ * removed.
+ */
+ if (!try_module_get(THIS_MODULE)) {
+ IWL_ERR(trans,
+ "Module is being unloaded - abort\n");
+ goto err;
+ }
+
+ removal = kzalloc(sizeof(*removal), GFP_ATOMIC);
+ if (!removal) {
+ module_put(THIS_MODULE);
+ goto err;
+ }
+ /*
+ * we don't need to clear this flag, because
+ * the trans will be freed and reallocated.
+ */
+ trans_pcie->scheduled_for_removal = true;
+
+ removal->pdev = to_pci_dev(trans->dev);
+ INIT_WORK(&removal->work, iwl_trans_pcie_removal_wk);
+ pci_dev_get(removal->pdev);
+ schedule_work(&removal->work);
+ } else {
+ iwl_write32(trans, CSR_RESET,
+ CSR_RESET_REG_FLAG_FORCE_NMI);
+ }
+
+err:
spin_unlock_irqrestore(&trans_pcie->reg_lock, *flags);
return false;
}
goto out;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
/*
* Above we read the CSR_GP_CNTRL register, which will flush
* any previous writes, but we need the write that clears the
* id located at the AUX bus MISC address space.
*/
iwl_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+ BIT(trans->cfg->csr->flag_init_done));
udelay(2);
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
- CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY,
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
+ BIT(trans->cfg->csr->flag_mac_clock_ready),
25000);
if (ret < 0) {
IWL_DEBUG_INFO(trans, "Failed to wake up the nic\n");
* Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* Portions of this file are derived from the ipw3945 project, as well
* as portions of the ieee80211 subsystem header files.
IWL_DEBUG_INFO(trans, "Tx queue %d requesting wakeup, GP1 = 0x%x\n",
txq_id, reg);
iwl_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
txq->need_update = true;
return;
}
trans_pcie->cmd_hold_nic_awake = false;
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(trans->cfg->csr->flag_mac_access_req));
}
/*
const struct iwl_host_cmd *cmd)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+ const struct iwl_cfg *cfg = trans->cfg;
int ret;
lockdep_assert_held(&trans_pcie->reg_lock);
* returned. This needs to be done only on NICs that have
* apmg_wake_up_wa set.
*/
- if (trans->cfg->base_params->apmg_wake_up_wa &&
+ if (cfg->base_params->apmg_wake_up_wa &&
!trans_pcie->cmd_hold_nic_awake) {
__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(cfg->csr->flag_mac_access_req));
ret = iwl_poll_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_VAL_MAC_ACCESS_EN,
- (CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY |
+ BIT(cfg->csr->flag_val_mac_access_en),
+ (BIT(cfg->csr->flag_mac_clock_ready) |
CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP),
15000);
if (ret < 0) {
__iwl_trans_pcie_clear_bit(trans, CSR_GP_CNTRL,
- CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+ BIT(cfg->csr->flag_mac_access_req));
IWL_ERR(trans, "Failed to wake NIC for hcmd\n");
return -EIO;
}
goto out_err;
iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, false);
- if (amsdu) {
+ /*
+ * If gso_size wasn't set, don't give the frame "amsdu treatment"
+ * (adding subframes, etc.).
+ * This can happen in some testing flows when the amsdu was already
+ * pre-built, and we just need to send the resulting skb.
+ */
+ if (amsdu && skb_shinfo(skb)->gso_size) {
if (unlikely(iwl_fill_data_tbs_amsdu(trans, skb, txq, hdr_len,
out_meta, dev_cmd,
tb1_len)))
GENL_SET_ERR_MSG(info,"MAC is no valid source addr");
NL_SET_BAD_ATTR(info->extack,
info->attrs[HWSIM_ATTR_PERM_ADDR]);
+ kfree(hwname);
return -EINVAL;
}
adapter->rx_locked = false;
spin_unlock_irqrestore(&adapter->rx_proc_lock, flags);
- mwifiex_set_mac_address(priv, dev);
+ mwifiex_set_mac_address(priv, dev, false, NULL);
return 0;
}
priv->netdev = dev;
if (!adapter->mfg_mode) {
- mwifiex_set_mac_address(priv, dev);
+ mwifiex_set_mac_address(priv, dev, false, NULL);
ret = mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE,
HostCmd_ACT_GEN_SET, 0, NULL, true);
#include "main.h"
#include "wmm.h"
#include "11n.h"
-#include "11ac.h"
static void mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter);
/*
* CFG802.11 network device handler for data transmission.
*/
-static int
+static netdev_tx_t
mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
}
int mwifiex_set_mac_address(struct mwifiex_private *priv,
- struct net_device *dev)
+ struct net_device *dev, bool external,
+ u8 *new_mac)
{
int ret;
u64 mac_addr, old_mac_addr;
- if (priv->bss_type == MWIFIEX_BSS_TYPE_ANY)
- return -ENOTSUPP;
+ old_mac_addr = ether_addr_to_u64(priv->curr_addr);
- mac_addr = ether_addr_to_u64(priv->curr_addr);
- old_mac_addr = mac_addr;
+ if (external) {
+ mac_addr = ether_addr_to_u64(new_mac);
+ } else {
+ /* Internal mac address change */
+ if (priv->bss_type == MWIFIEX_BSS_TYPE_ANY)
+ return -ENOTSUPP;
- if (priv->bss_type == MWIFIEX_BSS_TYPE_P2P)
- mac_addr |= BIT_ULL(MWIFIEX_MAC_LOCAL_ADMIN_BIT);
+ mac_addr = old_mac_addr;
- if (mwifiex_get_intf_num(priv->adapter, priv->bss_type) > 1) {
- /* Set mac address based on bss_type/bss_num */
- mac_addr ^= BIT_ULL(priv->bss_type + 8);
- mac_addr += priv->bss_num;
- }
+ if (priv->bss_type == MWIFIEX_BSS_TYPE_P2P)
+ mac_addr |= BIT_ULL(MWIFIEX_MAC_LOCAL_ADMIN_BIT);
- if (mac_addr == old_mac_addr)
- goto done;
+ if (mwifiex_get_intf_num(priv->adapter, priv->bss_type) > 1) {
+ /* Set mac address based on bss_type/bss_num */
+ mac_addr ^= BIT_ULL(priv->bss_type + 8);
+ mac_addr += priv->bss_num;
+ }
+ }
u64_to_ether_addr(mac_addr, priv->curr_addr);
return ret;
}
-done:
ether_addr_copy(dev->dev_addr, priv->curr_addr);
return 0;
}
struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
struct sockaddr *hw_addr = addr;
- memcpy(priv->curr_addr, hw_addr->sa_data, ETH_ALEN);
- return mwifiex_set_mac_address(priv, dev);
+ return mwifiex_set_mac_address(priv, dev, true, hw_addr->sa_data);
}
/*
priv->assocresp_idx = MWIFIEX_AUTO_IDX_MASK;
priv->gen_idx = MWIFIEX_AUTO_IDX_MASK;
priv->num_tx_timeout = 0;
- ether_addr_copy(priv->curr_addr, priv->adapter->perm_addr);
+ if (is_valid_ether_addr(dev->dev_addr))
+ ether_addr_copy(priv->curr_addr, dev->dev_addr);
+ else
+ ether_addr_copy(priv->curr_addr, priv->adapter->perm_addr);
if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA ||
GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
#define MWIFIEX_TIMER_10S 10000
#define MWIFIEX_TIMER_1S 1000
-#define MAX_TX_PENDING 100
-#define LOW_TX_PENDING 80
+#define MAX_TX_PENDING 400
+#define LOW_TX_PENDING 380
#define HIGH_RX_PENDING 50
#define LOW_RX_PENDING 20
struct sk_buff *event_skb);
void mwifiex_multi_chan_resync(struct mwifiex_adapter *adapter);
int mwifiex_set_mac_address(struct mwifiex_private *priv,
- struct net_device *dev);
+ struct net_device *dev,
+ bool external, u8 *new_mac);
void mwifiex_devdump_tmo_func(unsigned long function_context);
#ifdef CONFIG_DEBUG_FS
struct mwifiex_adapter *adapter = priv->adapter;
int len, i;
u32 eventcause = adapter->event_cause;
- struct station_info sinfo;
+ struct station_info *sinfo;
struct mwifiex_assoc_event *event;
struct mwifiex_sta_node *node;
u8 *deauth_mac;
switch (eventcause) {
case EVENT_UAP_STA_ASSOC:
- memset(&sinfo, 0, sizeof(sinfo));
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo)
+ return -ENOMEM;
+
event = (struct mwifiex_assoc_event *)
(adapter->event_body + MWIFIEX_UAP_EVENT_EXTRA_HEADER);
if (le16_to_cpu(event->type) == TLV_TYPE_UAP_MGMT_FRAME) {
len = ETH_ALEN;
if (len != -1) {
- sinfo.assoc_req_ies = &event->data[len];
- len = (u8 *)sinfo.assoc_req_ies -
+ sinfo->assoc_req_ies = &event->data[len];
+ len = (u8 *)sinfo->assoc_req_ies -
(u8 *)&event->frame_control;
- sinfo.assoc_req_ies_len =
+ sinfo->assoc_req_ies_len =
le16_to_cpu(event->len) - (u16)len;
}
}
- cfg80211_new_sta(priv->netdev, event->sta_addr, &sinfo,
+ cfg80211_new_sta(priv->netdev, event->sta_addr, sinfo,
GFP_KERNEL);
node = mwifiex_add_sta_entry(priv, event->sta_addr);
if (!node) {
mwifiex_dbg(adapter, ERROR,
"could not create station entry!\n");
+ kfree(sinfo);
return -1;
}
- if (!priv->ap_11n_enabled)
+ if (!priv->ap_11n_enabled) {
+ kfree(sinfo);
break;
+ }
- mwifiex_set_sta_ht_cap(priv, sinfo.assoc_req_ies,
- sinfo.assoc_req_ies_len, node);
+ mwifiex_set_sta_ht_cap(priv, sinfo->assoc_req_ies,
+ sinfo->assoc_req_ies_len, node);
for (i = 0; i < MAX_NUM_TID; i++) {
if (node->is_11n_enabled)
node->ampdu_sta[i] = BA_STREAM_NOT_ALLOWED;
}
memset(node->rx_seq, 0xff, sizeof(node->rx_seq));
+ kfree(sinfo);
break;
case EVENT_UAP_STA_DEAUTH:
deauth_mac = adapter->event_body +
__skb_queue_head_init(&frames);
local_bh_disable();
+ rcu_read_lock();
spin_lock(&tid->lock);
mt76_rx_aggr_check_release(tid, &frames);
REORDER_TIMEOUT);
mt76_rx_complete(dev, &frames, -1);
+ rcu_read_unlock();
local_bh_enable();
}
u8 size = tid->size;
int i;
+ cancel_delayed_work(&tid->reorder_work);
+
spin_lock_bh(&tid->lock);
tid->stopped = true;
}
spin_unlock_bh(&tid->lock);
-
- cancel_delayed_work(&tid->reorder_work);
}
void mt76_rx_aggr_stop(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tidno)
if (queue >= 0)
napi = &dev->napi[queue];
+ spin_lock(&dev->rx_lock);
while ((skb = __skb_dequeue(frames)) != NULL) {
if (mt76_check_ccmp_pn(skb)) {
dev_kfree_skb(skb);
sta = mt76_rx_convert(skb);
ieee80211_rx_napi(dev->hw, sta, skb, napi);
}
+ spin_unlock(&dev->rx_lock);
}
void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q)
struct device *dev;
struct net_device napi_dev;
+ spinlock_t rx_lock;
struct napi_struct napi[__MT_RXQ_MAX];
struct sk_buff_head rx_skb[__MT_RXQ_MAX];
u8 beacon_mask;
u8 beacon_data_mask;
- u32 rev;
u32 rxfilter;
u16 chainmask;
static inline bool is_mt7612(struct mt76x2_dev *dev)
{
- return (dev->rev >> 16) == 0x7612;
+ return mt76_chip(&dev->mt76) == 0x7612;
}
void mt76x2_set_irq_mask(struct mt76x2_dev *dev, u32 clear, u32 set);
/* Wait for MAC to become idle */
for (i = 0; i < 300; i++) {
- if (mt76_rr(dev, MT_MAC_STATUS) &
- (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX))
- continue;
-
- if (mt76_rr(dev, MT_BBP(IBI, 12)))
+ if ((mt76_rr(dev, MT_MAC_STATUS) &
+ (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX)) ||
+ mt76_rr(dev, MT_BBP(IBI, 12))) {
+ usleep_range(10, 20);
continue;
+ }
stopped = true;
break;
dev->mt76.drv = &drv_ops;
mutex_init(&dev->mutex);
spin_lock_init(&dev->irq_lock);
+ spin_lock_init(&dev->mt76.rx_lock);
return dev;
}
break;
default:
return -EINVAL;
- break;
}
if (rate & MT_RXWI_RATE_SGI)
u8 gain_delta;
int low_gain;
- dev->cal.avg_rssi[0] = (dev->cal.avg_rssi[0] * 15) / 16 + (rssi0 << 8);
- dev->cal.avg_rssi[1] = (dev->cal.avg_rssi[1] * 15) / 16 + (rssi1 << 8);
+ dev->cal.avg_rssi[0] = (dev->cal.avg_rssi[0] * 15) / 16 +
+ (rssi0 << 8) / 16;
+ dev->cal.avg_rssi[1] = (dev->cal.avg_rssi[1] * 15) / 16 +
+ (rssi1 << 8) / 16;
dev->cal.avg_rssi_all = (dev->cal.avg_rssi[0] +
dev->cal.avg_rssi[1]) / 512;
bool empty = false;
int cur;
+ if (test_bit(MT76_SCANNING, &dev->state) ||
+ test_bit(MT76_RESET, &dev->state))
+ return -EBUSY;
+
mtxq = list_first_entry(&hwq->swq, struct mt76_txq, list);
if (mtxq->send_bar && mtxq->aggr) {
struct ieee80211_txq *txq = mtxq_to_txq(mtxq);
{
int len;
+ rcu_read_lock();
do {
if (hwq->swq_queued >= 4 || list_empty(&hwq->swq))
break;
len = mt76_txq_schedule_list(dev, hwq);
} while (len > 0);
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(mt76_txq_schedule);
/* Netdev handler for data transmission.
*/
-static int
+static netdev_tx_t
qtnf_netdev_hard_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct qtnf_vif *vif;
{
const u8 *sta_addr;
u16 frame_control;
- struct station_info sinfo = { 0 };
+ struct station_info *sinfo;
size_t payload_len;
u16 tlv_type;
u16 tlv_value_len;
size_t tlv_full_len;
const struct qlink_tlv_hdr *tlv;
+ int ret = 0;
if (unlikely(len < sizeof(*sta_assoc))) {
pr_err("VIF%u.%u: payload is too short (%u < %zu)\n",
return -EPROTO;
}
+ sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+ if (!sinfo)
+ return -ENOMEM;
+
sta_addr = sta_assoc->sta_addr;
frame_control = le16_to_cpu(sta_assoc->frame_control);
qtnf_sta_list_add(vif, sta_addr);
- sinfo.assoc_req_ies = NULL;
- sinfo.assoc_req_ies_len = 0;
- sinfo.generation = vif->generation;
+ sinfo->assoc_req_ies = NULL;
+ sinfo->assoc_req_ies_len = 0;
+ sinfo->generation = vif->generation;
payload_len = len - sizeof(*sta_assoc);
tlv = (const struct qlink_tlv_hdr *)sta_assoc->ies;
tlv_value_len = le16_to_cpu(tlv->len);
tlv_full_len = tlv_value_len + sizeof(struct qlink_tlv_hdr);
- if (tlv_full_len > payload_len)
- return -EINVAL;
+ if (tlv_full_len > payload_len) {
+ ret = -EINVAL;
+ goto out;
+ }
if (tlv_type == QTN_TLV_ID_IE_SET) {
const struct qlink_tlv_ie_set *ie_set;
unsigned int ie_len;
- if (payload_len < sizeof(*ie_set))
- return -EINVAL;
+ if (payload_len < sizeof(*ie_set)) {
+ ret = -EINVAL;
+ goto out;
+ }
ie_set = (const struct qlink_tlv_ie_set *)tlv;
ie_len = tlv_value_len -
(sizeof(*ie_set) - sizeof(ie_set->hdr));
if (ie_set->type == QLINK_IE_SET_ASSOC_REQ && ie_len) {
- sinfo.assoc_req_ies = ie_set->ie_data;
- sinfo.assoc_req_ies_len = ie_len;
+ sinfo->assoc_req_ies = ie_set->ie_data;
+ sinfo->assoc_req_ies_len = ie_len;
}
}
tlv = (struct qlink_tlv_hdr *)(tlv->val + tlv_value_len);
}
- if (payload_len)
- return -EINVAL;
+ if (payload_len) {
+ ret = -EINVAL;
+ goto out;
+ }
- cfg80211_new_sta(vif->netdev, sta_assoc->sta_addr, &sinfo,
+ cfg80211_new_sta(vif->netdev, sta_assoc->sta_addr, sinfo,
GFP_KERNEL);
- return 0;
+out:
+ kfree(sinfo);
+ return ret;
}
static int
#define TX_PWR_CFG_3_MCS13 FIELD32(0x000000f0)
#define TX_PWR_CFG_3_MCS14 FIELD32(0x00000f00)
#define TX_PWR_CFG_3_MCS15 FIELD32(0x0000f000)
-#define TX_PWR_CFG_3_UKNOWN1 FIELD32(0x000f0000)
-#define TX_PWR_CFG_3_UKNOWN2 FIELD32(0x00f00000)
-#define TX_PWR_CFG_3_UKNOWN3 FIELD32(0x0f000000)
-#define TX_PWR_CFG_3_UKNOWN4 FIELD32(0xf0000000)
+#define TX_PWR_CFG_3_UNKNOWN1 FIELD32(0x000f0000)
+#define TX_PWR_CFG_3_UNKNOWN2 FIELD32(0x00f00000)
+#define TX_PWR_CFG_3_UNKNOWN3 FIELD32(0x0f000000)
+#define TX_PWR_CFG_3_UNKNOWN4 FIELD32(0xf0000000)
/* bits for 3T devices */
#define TX_PWR_CFG_3_MCS12_CH0 FIELD32(0x0000000f)
#define TX_PWR_CFG_3_MCS12_CH1 FIELD32(0x000000f0)
* TX_PWR_CFG_4:
*/
#define TX_PWR_CFG_4 0x1324
-#define TX_PWR_CFG_4_UKNOWN5 FIELD32(0x0000000f)
-#define TX_PWR_CFG_4_UKNOWN6 FIELD32(0x000000f0)
-#define TX_PWR_CFG_4_UKNOWN7 FIELD32(0x00000f00)
-#define TX_PWR_CFG_4_UKNOWN8 FIELD32(0x0000f000)
+#define TX_PWR_CFG_4_UNKNOWN5 FIELD32(0x0000000f)
+#define TX_PWR_CFG_4_UNKNOWN6 FIELD32(0x000000f0)
+#define TX_PWR_CFG_4_UNKNOWN7 FIELD32(0x00000f00)
+#define TX_PWR_CFG_4_UNKNOWN8 FIELD32(0x0000f000)
/* bits for 3T devices */
#define TX_PWR_CFG_4_STBC4_CH0 FIELD32(0x0000000f)
#define TX_PWR_CFG_4_STBC4_CH1 FIELD32(0x000000f0)
rt2800_register_write(rt2x00dev, MAX_LEN_CFG, reg);
}
-int rt2800_sta_add(struct rt2x00_dev *rt2x00dev, struct ieee80211_vif *vif,
+int rt2800_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
struct ieee80211_sta *sta)
{
- int wcid;
- struct rt2x00_sta *sta_priv = sta_to_rt2x00_sta(sta);
+ struct rt2x00_dev *rt2x00dev = hw->priv;
struct rt2800_drv_data *drv_data = rt2x00dev->drv_data;
+ struct rt2x00_sta *sta_priv = sta_to_rt2x00_sta(sta);
+ int wcid;
/*
* Limit global maximum TX AMPDU length to smallest value of all
}
EXPORT_SYMBOL_GPL(rt2800_sta_add);
-int rt2800_sta_remove(struct rt2x00_dev *rt2x00dev, struct ieee80211_sta *sta)
+int rt2800_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta)
{
+ struct rt2x00_dev *rt2x00dev = hw->priv;
struct rt2800_drv_data *drv_data = rt2x00dev->drv_data;
struct rt2x00_sta *sta_priv = sta_to_rt2x00_sta(sta);
int wcid = sta_priv->wcid;
int rt2800_config_pairwise_key(struct rt2x00_dev *rt2x00dev,
struct rt2x00lib_crypto *crypto,
struct ieee80211_key_conf *key);
-int rt2800_sta_add(struct rt2x00_dev *rt2x00dev, struct ieee80211_vif *vif,
+int rt2800_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
struct ieee80211_sta *sta);
-int rt2800_sta_remove(struct rt2x00_dev *rt2x00dev, struct ieee80211_sta *sta);
+int rt2800_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta);
void rt2800_config_filter(struct rt2x00_dev *rt2x00dev,
const unsigned int filter_flags);
void rt2800_config_intf(struct rt2x00_dev *rt2x00dev, struct rt2x00_intf *intf,
case QID_AC_VI:
case QID_AC_BE:
case QID_AC_BK:
+ WARN_ON_ONCE(rt2x00queue_empty(queue));
entry = rt2x00queue_get_entry(queue, Q_INDEX);
rt2x00mmio_register_write(rt2x00dev, TX_CTX_IDX(queue->qid),
entry->entry_idx);
.get_stats = rt2x00mac_get_stats,
.get_key_seq = rt2800_get_key_seq,
.set_rts_threshold = rt2800_set_rts_threshold,
- .sta_add = rt2x00mac_sta_add,
- .sta_remove = rt2x00mac_sta_remove,
+ .sta_add = rt2800_sta_add,
+ .sta_remove = rt2800_sta_remove,
.bss_info_changed = rt2x00mac_bss_info_changed,
.conf_tx = rt2800_conf_tx,
.get_tsf = rt2800_get_tsf,
.config_erp = rt2800_config_erp,
.config_ant = rt2800_config_ant,
.config = rt2800_config,
- .sta_add = rt2800_sta_add,
- .sta_remove = rt2800_sta_remove,
};
static const struct rt2x00_ops rt2800pci_ops = {
.get_stats = rt2x00mac_get_stats,
.get_key_seq = rt2800_get_key_seq,
.set_rts_threshold = rt2800_set_rts_threshold,
- .sta_add = rt2x00mac_sta_add,
- .sta_remove = rt2x00mac_sta_remove,
+ .sta_add = rt2800_sta_add,
+ .sta_remove = rt2800_sta_remove,
.bss_info_changed = rt2x00mac_bss_info_changed,
.conf_tx = rt2800_conf_tx,
.get_tsf = rt2800_get_tsf,
.config_erp = rt2800_config_erp,
.config_ant = rt2800_config_ant,
.config = rt2800_config,
- .sta_add = rt2800_sta_add,
- .sta_remove = rt2800_sta_remove,
};
static const struct rt2x00_ops rt2800soc_ops = {
.get_stats = rt2x00mac_get_stats,
.get_key_seq = rt2800_get_key_seq,
.set_rts_threshold = rt2800_set_rts_threshold,
- .sta_add = rt2x00mac_sta_add,
- .sta_remove = rt2x00mac_sta_remove,
+ .sta_add = rt2800_sta_add,
+ .sta_remove = rt2800_sta_remove,
.bss_info_changed = rt2x00mac_bss_info_changed,
.conf_tx = rt2800_conf_tx,
.get_tsf = rt2800_get_tsf,
.config_erp = rt2800_config_erp,
.config_ant = rt2800_config_ant,
.config = rt2800_config,
- .sta_add = rt2800_sta_add,
- .sta_remove = rt2800_sta_remove,
};
static void rt2800usb_queue_init(struct data_queue *queue)
#else
#define rt2x00mac_set_key NULL
#endif /* CONFIG_RT2X00_LIB_CRYPTO */
-int rt2x00mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
- struct ieee80211_sta *sta);
-int rt2x00mac_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
- struct ieee80211_sta *sta);
void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
const u8 *mac_addr);
return;
tx_queue_for_each(rt2x00dev, queue)
- if (!rt2x00queue_empty(queue))
- rt2x00queue_flush_queue(queue, drop);
+ rt2x00queue_flush_queue(queue, drop);
}
EXPORT_SYMBOL_GPL(rt2x00mac_flush);
(queue->qid == QID_AC_BE) ||
(queue->qid == QID_AC_BK);
+ if (rt2x00queue_empty(queue))
+ return;
/*
* If we are not supposed to drop any pending
bool scan = false, link = false, roam = false;
RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
- "[BTCoex], PsTdma type dismatch!!!, ");
+ "[BTCoex], PsTdma type mismatch!!!, ");
RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
"curPsTdma=%d, recordPsTdma=%d\n",
coex_dm->cur_ps_tdma, coex_dm->tdma_adj_type);
if (coex_dm->cur_ps_tdma != coex_dm->ps_tdma_du_adj_type) {
bool scan = false, link = false, roam = false;
RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
- "[BTCoex], PsTdma type dismatch!!!, curPsTdma=%d, recordPsTdma=%d\n",
+ "[BTCoex], PsTdma type mismatch!!!, curPsTdma=%d, recordPsTdma=%d\n",
coex_dm->cur_ps_tdma, coex_dm->ps_tdma_du_adj_type);
btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
bool scan = false, link = false, roam = false;
RT_TRACE(rtlpriv, COMP_BT_COEXIST, DBG_LOUD,
- "[BTCoex], PsTdma type dismatch!!!, cur_ps_tdma = %d, recordPsTdma = %d\n",
+ "[BTCoex], PsTdma type mismatch!!!, cur_ps_tdma = %d, recordPsTdma = %d\n",
coex_dm->cur_ps_tdma, coex_dm->ps_tdma_du_adj_type);
btcoexist->btc_get(btcoexist, BTC_GET_BL_WIFI_SCAN, &scan);
static u8 rtl_get_hwpg_single_ant_path(struct rtl_priv *rtlpriv)
{
- struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
-
- /* override ant_num / ant_path */
- if (mod_params->ant_sel) {
- rtlpriv->btcoexist.btc_info.ant_num =
- (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
-
- rtlpriv->btcoexist.btc_info.single_ant_path =
- (mod_params->ant_sel == 1 ? 0 : 1);
- }
return rtlpriv->btcoexist.btc_info.single_ant_path;
}
static u8 rtl_get_hwpg_ant_num(struct rtl_priv *rtlpriv)
{
- struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
u8 num;
if (rtlpriv->btcoexist.btc_info.ant_num == ANT_X2)
else
num = 1;
- /* override ant_num / ant_path */
- if (mod_params->ant_sel)
- num = (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1) + 1;
-
return num;
}
rtlpriv->btcoexist.btc_info.btcoexist = 0;
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8192E;
- rtlpriv->btcoexist.btc_info.ant_num = ANT_TOTAL_X2;
+ rtlpriv->btcoexist.btc_info.ant_num = ANT_X2;
} else {
rtlpriv->btcoexist.btc_info.btcoexist = 1;
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8192E;
- rtlpriv->btcoexist.btc_info.ant_num = ANT_TOTAL_X1;
+ rtlpriv->btcoexist.btc_info.ant_num = ANT_X1;
}
}
return false;
}
+ if (rtlpriv->cfg->ops->get_btc_status())
+ rtlpriv->btcoexist.btc_ops->btc_power_on_setting(rtlpriv);
+
bytetmp = rtl_read_byte(rtlpriv, REG_MULTI_FUNC_CTRL);
rtl_write_byte(rtlpriv, REG_MULTI_FUNC_CTRL, bytetmp | BIT(3));
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
rtlpriv->btcoexist.btc_info.ant_num = (value & 0x1);
rtlpriv->btcoexist.btc_info.single_ant_path =
- (value & 0x40); /*0xc3[6]*/
+ (value & 0x40 ? ANT_AUX : ANT_MAIN); /*0xc3[6]*/
} else {
rtlpriv->btcoexist.btc_info.btcoexist = 0;
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
rtlpriv->btcoexist.btc_info.ant_num = ANT_X2;
- rtlpriv->btcoexist.btc_info.single_ant_path = 0;
+ rtlpriv->btcoexist.btc_info.single_ant_path = ANT_MAIN;
}
/* override ant_num / ant_path */
if (mod_params->ant_sel) {
rtlpriv->btcoexist.btc_info.ant_num =
- (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
+ (mod_params->ant_sel == 1 ? ANT_X1 : ANT_X2);
rtlpriv->btcoexist.btc_info.single_ant_path =
- (mod_params->ant_sel == 1 ? 0 : 1);
+ (mod_params->ant_sel == 1 ? ANT_AUX : ANT_MAIN);
}
}
ANT_X1 = 1,
};
+enum bt_ant_path {
+ ANT_MAIN = 0,
+ ANT_AUX = 1,
+};
+
enum bt_co_type {
BT_2WIRE = 0,
BT_ISSC_3WIRE = 1,
BT_RTL8812A = 11,
};
-enum bt_total_ant_num {
- ANT_TOTAL_X2 = 0,
- ANT_TOTAL_X1 = 1
-};
-
enum bt_cur_state {
BT_OFF = 0,
BT_ON = 1,
switch (msg_type) {
case COMMON_CARD_READY_IND:
rsi_dbg(INFO_ZONE, "common card ready received\n");
+ common->hibernate_resume = false;
rsi_handle_card_ready(common, msg);
break;
case SLEEP_NOTIFY_IND:
}
rsi_core_queue_pkt(common, skb);
- rsi_dbg(DATA_TX_ZONE, "%s: ===> Scheduling TX thead <===\n", __func__);
+ rsi_dbg(DATA_TX_ZONE, "%s: ===> Scheduling TX thread <===\n", __func__);
rsi_set_event(&common->tx_thread.event);
return;
}
}
- return rsi_hal_load_key(adapter->priv,
- key->key,
- key->keylen,
- key_type,
- key->keyidx,
- key->cipher,
- sta_id,
- vif);
+ status = rsi_hal_load_key(adapter->priv,
+ key->key,
+ key->keylen,
+ key_type,
+ key->keyidx,
+ key->cipher,
+ sta_id,
+ vif);
if (status)
return status;
struct rsi_common *common = adapter->priv;
u16 triggers = 0;
u16 rx_filter_word = 0;
- struct ieee80211_bss_conf *bss = &adapter->vifs[0]->bss_conf;
+ struct ieee80211_bss_conf *bss = NULL;
rsi_dbg(INFO_ZONE, "Config WoWLAN to device\n");
+ if (!adapter->vifs[0])
+ return -EINVAL;
+
+ bss = &adapter->vifs[0]->bss_conf;
+
if (WARN_ON(!wowlan)) {
rsi_dbg(ERR_ZONE, "WoW triggers not enabled\n");
return -EINVAL;
}
+ common->wow_flags |= RSI_WOW_ENABLED;
triggers = rsi_wow_map_triggers(common, wowlan);
if (!triggers) {
rsi_dbg(ERR_ZONE, "%s:No valid WoW triggers\n", __func__);
rx_filter_word = (ALLOW_DATA_ASSOC_PEER | DISALLOW_BEACONS);
rsi_send_rx_filter_frame(common, rx_filter_word);
- common->wow_flags |= RSI_WOW_ENABLED;
return 0;
}
*/
msleep(100);
- if (rsi_usb_master_reg_write(adapter, SWBL_REGOUT,
- RSI_FW_WDT_DISABLE_REQ,
- RSI_COMMON_REG_SIZE) < 0) {
+ ret = rsi_usb_master_reg_write(adapter, SWBL_REGOUT,
+ RSI_FW_WDT_DISABLE_REQ,
+ RSI_COMMON_REG_SIZE);
+ if (ret < 0) {
rsi_dbg(ERR_ZONE, "Disabling firmware watchdog timer failed\n");
goto fail;
}
struct mmc_card *card = func->card;
ret = pm_runtime_get_sync(&card->dev);
- if (ret) {
- /*
- * Runtime PM might be temporarily disabled, or the device
- * might have a positive reference counter. Make sure it is
- * really powered on.
- */
- ret = mmc_power_restore_host(card->host);
- if (ret < 0) {
- pm_runtime_put_sync(&card->dev);
- goto out;
- }
+ if (ret < 0) {
+ pm_runtime_put_noidle(&card->dev);
+ dev_err(glue->dev, "%s: failed to get_sync(%d)\n",
+ __func__, ret);
+ goto out;
}
sdio_claim_host(func);
static int wl12xx_sdio_power_off(struct wl12xx_sdio_glue *glue)
{
- int ret;
struct sdio_func *func = dev_to_sdio_func(glue->dev);
struct mmc_card *card = func->card;
sdio_disable_func(func);
sdio_release_host(func);
- /* Power off the card manually in case it wasn't powered off above */
- ret = mmc_power_save_host(card->host);
- if (ret < 0)
- goto out;
-
/* Let runtime PM know the card is powered off */
- pm_runtime_put_sync(&card->dev);
-
-out:
- return ret;
+ return pm_runtime_put_sync(&card->dev);
}
static int wl12xx_sdio_set_power(struct device *child, bool enable)
Select Y if unsure
config OF_PMEM
- # FIXME: make tristate once OF_NUMA dependency removed
- bool "Device-tree support for persistent memory regions"
+ tristate "Device-tree support for persistent memory regions"
depends on OF
default LIBNVDIMM
help
int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+ int rc = validate_dimm(ndd), cmd_rc = 0;
struct nd_cmd_get_config_data_hdr *cmd;
struct nvdimm_bus_descriptor *nd_desc;
- int rc = validate_dimm(ndd);
u32 max_cmd_size, config_size;
size_t offset;
cmd->in_offset = offset;
rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
ND_CMD_GET_CONFIG_DATA, cmd,
- cmd->in_length + sizeof(*cmd), NULL);
- if (rc || cmd->status) {
- rc = -ENXIO;
+ cmd->in_length + sizeof(*cmd), &cmd_rc);
+ if (rc < 0)
+ break;
+ if (cmd_rc < 0) {
+ rc = cmd_rc;
break;
}
memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length);
int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
void *buf, size_t len)
{
- int rc = validate_dimm(ndd);
size_t max_cmd_size, buf_offset;
struct nd_cmd_set_config_hdr *cmd;
+ int rc = validate_dimm(ndd), cmd_rc = 0;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
for (buf_offset = 0; len; len -= cmd->in_length,
buf_offset += cmd->in_length) {
size_t cmd_size;
- u32 *status;
cmd->in_offset = offset + buf_offset;
cmd->in_length = min(max_cmd_size, len);
/* status is output in the last 4-bytes of the command buffer */
cmd_size = sizeof(*cmd) + cmd->in_length + sizeof(u32);
- status = ((void *) cmd) + cmd_size - sizeof(u32);
rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
- ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, NULL);
- if (rc || *status) {
- rc = rc ? rc : -ENXIO;
+ ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, &cmd_rc);
+ if (rc < 0)
+ break;
+ if (cmd_rc < 0) {
+ rc = cmd_rc;
break;
}
}
*/
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
- ndr_desc.numa_node = of_node_to_nid(np);
+ ndr_desc.numa_node = dev_to_node(&pdev->dev);
ndr_desc.res = &pdev->resource[i];
ndr_desc.of_node = np;
set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
config NVME_RDMA
tristate "NVM Express over Fabrics RDMA host driver"
- depends on INFINIBAND && BLOCK
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK
select NVME_CORE
select NVME_FABRICS
select SG_POOL
static void nvme_ns_remove(struct nvme_ns *ns);
static int nvme_revalidate_disk(struct gendisk *disk);
+static void nvme_put_subsystem(struct nvme_subsystem *subsys);
int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
ret = nvme_reset_ctrl(ctrl);
if (!ret) {
flush_work(&ctrl->reset_work);
- if (ctrl->state != NVME_CTRL_LIVE)
+ if (ctrl->state != NVME_CTRL_LIVE &&
+ ctrl->state != NVME_CTRL_ADMIN_ONLY)
ret = -ENETRESET;
}
ida_simple_remove(&head->subsys->ns_ida, head->instance);
list_del_init(&head->entry);
cleanup_srcu_struct(&head->srcu);
+ nvme_put_subsystem(head->subsys);
kfree(head);
}
ret = PTR_ERR(meta);
goto out_unmap;
}
+ req->cmd_flags |= REQ_INTEGRITY;
}
}
goto out_cleanup_srcu;
list_add_tail(&head->entry, &ctrl->subsys->nsheads);
+
+ kref_get(&ctrl->subsys->ref);
+
return head;
out_cleanup_srcu:
cleanup_srcu_struct(&head->srcu);
if (nvme_init_ns_head(ns, nsid, id))
goto out_free_id;
nvme_setup_streams_ns(ctrl, ns);
-
-#ifdef CONFIG_NVME_MULTIPATH
- /*
- * If multipathing is enabled we need to always use the subsystem
- * instance number for numbering our devices to avoid conflicts
- * between subsystems that have multiple controllers and thus use
- * the multipath-aware subsystem node and those that have a single
- * controller and use the controller node directly.
- */
- if (ns->head->disk) {
- sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
- ctrl->cntlid, ns->head->instance);
- flags = GENHD_FL_HIDDEN;
- } else {
- sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
- ns->head->instance);
- }
-#else
- /*
- * But without the multipath code enabled, multiple controller per
- * subsystems are visible as devices and thus we cannot use the
- * subsystem instance.
- */
- sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
-#endif
+ nvme_set_disk_name(disk_name, ns, ctrl, &flags);
if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
if (nvme_nvm_register(ns, disk_name, node)) {
ret = -ENOMEM;
goto out;
}
+ kfree(opts->transport);
opts->transport = p;
break;
case NVMF_OPT_NQN:
ret = -ENOMEM;
goto out;
}
+ kfree(opts->subsysnqn);
opts->subsysnqn = p;
nqnlen = strlen(opts->subsysnqn);
if (nqnlen >= NVMF_NQN_SIZE) {
ret = -ENOMEM;
goto out;
}
+ kfree(opts->traddr);
opts->traddr = p;
break;
case NVMF_OPT_TRSVCID:
ret = -ENOMEM;
goto out;
}
+ kfree(opts->trsvcid);
opts->trsvcid = p;
break;
case NVMF_OPT_QUEUE_SIZE:
ret = -EINVAL;
goto out;
}
+ nvmf_host_put(opts->host);
opts->host = nvmf_host_add(p);
kfree(p);
if (!opts->host) {
ret = -ENOMEM;
goto out;
}
+ kfree(opts->host_traddr);
opts->host_traddr = p;
break;
case NVMF_OPT_HOST_ID:
#include "nvme.h"
static bool multipath = true;
-module_param(multipath, bool, 0644);
+module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
+/*
+ * If multipathing is enabled we need to always use the subsystem instance
+ * number for numbering our devices to avoid conflicts between subsystems that
+ * have multiple controllers and thus use the multipath-aware subsystem node
+ * and those that have a single controller and use the controller node
+ * directly.
+ */
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags)
+{
+ if (!multipath) {
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+ } else if (ns->head->disk) {
+ sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
+ ctrl->cntlid, ns->head->instance);
+ *flags = GENHD_FL_HIDDEN;
+ } else {
+ sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
+ ns->head->instance);
+ }
+}
+
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
* Supports the LighNVM command set if indicated in vs[1].
*/
NVME_QUIRK_LIGHTNVM = (1 << 6),
+
+ /*
+ * Set MEDIUM priority on SQ creation
+ */
+ NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7),
};
/*
extern const struct block_device_operations nvme_ns_head_ops;
#ifdef CONFIG_NVME_MULTIPATH
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
bool nvme_req_needs_failover(struct request *req, blk_status_t error);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
}
#else
+/*
+ * Without the multipath code enabled, multiple controller per subsystems are
+ * visible as devices and thus we cannot use the subsystem instance.
+ */
+static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags)
+{
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+}
+
static inline void nvme_failover_req(struct request *req)
{
}
static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
+ struct nvme_ctrl *ctrl = &dev->ctrl;
struct nvme_command c;
int flags = NVME_QUEUE_PHYS_CONTIG;
+ /*
+ * Some drives have a bug that auto-enables WRRU if MEDIUM isn't
+ * set. Since URGENT priority is zeroes, it makes all queues
+ * URGENT.
+ */
+ if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ)
+ flags |= NVME_SQ_PRIO_MEDIUM;
+
/*
* Note: we (ab)use the fact that the prp fields survive if no data
* is attached to the request.
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */
- .driver_data = NVME_QUIRK_NO_DEEPEST_PS },
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_MEDIUM_PRIO_SQ },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
config NVME_TARGET_RDMA
tristate "NVMe over Fabrics RDMA target support"
- depends on INFINIBAND
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS
depends on NVME_TARGET
select SGL_ALLOC
help
nvme_stop_ctrl(&ctrl->ctrl);
nvme_loop_shutdown_ctrl(ctrl);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+ /* state change failure should never happen */
+ WARN_ON_ONCE(1);
+ return;
+ }
+
ret = nvme_loop_configure_admin_queue(ctrl);
if (ret)
goto out_disable;
int offset;
const char *p, *q, *options = NULL;
int l;
- const struct earlycon_id *match;
+ const struct earlycon_id **p_match;
const void *fdt = initial_boot_params;
offset = fdt_path_offset(fdt, "/chosen");
return 0;
}
- for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+ for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+ p_match++) {
+ const struct earlycon_id *match = *p_match;
+
if (!match->compatible[0])
continue;
bool scanphys = false;
int addr, rc;
+ if (!np)
+ return mdiobus_register(mdio);
+
/* Do not continue if the node is disabled */
if (!of_device_is_available(np))
return -ENODEV;
static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain);
+/**
+ * of_overlay_notifier_register() - Register notifier for overlay operations
+ * @nb: Notifier block to register
+ *
+ * Register for notification on overlay operations on device tree nodes. The
+ * reported actions definied by @of_reconfig_change. The notifier callback
+ * furthermore receives a pointer to the affected device tree node.
+ *
+ * Note that a notifier callback is not supposed to store pointers to a device
+ * tree node or its content beyond @OF_OVERLAY_POST_REMOVE corresponding to the
+ * respective node it received.
+ */
int of_overlay_notifier_register(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&overlay_notify_chain, nb);
}
EXPORT_SYMBOL_GPL(of_overlay_notifier_register);
+/**
+ * of_overlay_notifier_register() - Unregister notifier for overlay operations
+ * @nb: Notifier block to unregister
+ */
int of_overlay_notifier_unregister(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&overlay_notify_chain, nb);
of_node_put(ovcs->fragments[i].overlay);
}
kfree(ovcs->fragments);
-
/*
- * TODO
- *
- * would like to: kfree(ovcs->overlay_tree);
- * but can not since drivers may have pointers into this data
- *
- * would like to: kfree(ovcs->fdt);
- * but can not since drivers may have pointers into this data
+ * There should be no live pointers into ovcs->overlay_tree and
+ * ovcs->fdt due to the policy that overlay notifiers are not allowed
+ * to retain pointers into the overlay devicetree.
*/
-
+ kfree(ovcs->overlay_tree);
+ kfree(ovcs->fdt);
kfree(ovcs);
}
* to/from certain pages. To avoid this happening, we mark these pages
* as `used', and ensure that nothing will try to allocate from them.
*/
-void ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
+void __init ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
{
unsigned int idx;
struct parisc_device *dev = parisc_parent(cujo);
* I/O Page Directory, the resource map, and initalizing the
* U2/Uturn chip into virtual mode.
*/
-static void
+static void __init
ccio_ioc_init(struct ioc *ioc)
{
int i;
return ret;
kirin_pcie->gpio_id_reset = of_get_named_gpio(dev->of_node,
- "reset-gpio", 0);
+ "reset-gpios", 0);
if (kirin_pcie->gpio_id_reset < 0)
return -ENODEV;
#define PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT 5
#define PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE (0 << 11)
#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT 12
+#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ 0x2
#define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0
#define PCIE_CORE_LINK_L0S_ENTRY BIT(0)
#define PCIE_CORE_LINK_TRAINING BIT(5)
#define PCIE_ISR1_MASK_REG (CONTROL_BASE_ADDR + 0x4C)
#define PCIE_ISR1_POWER_STATE_CHANGE BIT(4)
#define PCIE_ISR1_FLUSH BIT(5)
-#define PCIE_ISR1_ALL_MASK GENMASK(5, 4)
+#define PCIE_ISR1_INTX_ASSERT(val) BIT(8 + (val))
+#define PCIE_ISR1_ALL_MASK GENMASK(11, 4)
#define PCIE_MSI_ADDR_LOW_REG (CONTROL_BASE_ADDR + 0x50)
#define PCIE_MSI_ADDR_HIGH_REG (CONTROL_BASE_ADDR + 0x54)
#define PCIE_MSI_STATUS_REG (CONTROL_BASE_ADDR + 0x58)
#define PCIE_CONFIG_WR_TYPE0 0xa
#define PCIE_CONFIG_WR_TYPE1 0xb
-/* PCI_BDF shifts 8bit, so we need extra 4bit shift */
-#define PCIE_BDF(dev) (dev << 4)
#define PCIE_CONF_BUS(bus) (((bus) & 0xff) << 20)
#define PCIE_CONF_DEV(dev) (((dev) & 0x1f) << 15)
#define PCIE_CONF_FUNC(fun) (((fun) & 0x7) << 12)
reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
- PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT;
+ (PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
+ PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
/* Program PCIe Control 2 to disable strict ordering */
u32 reg;
int ret;
- if (PCI_SLOT(devfn) != 0) {
+ if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
*val = 0xffffffff;
return PCIBIOS_DEVICE_NOT_FOUND;
}
advk_writel(pcie, reg, PIO_CTRL);
/* Program the address registers */
- reg = PCIE_BDF(devfn) | PCIE_CONF_REG(where);
+ reg = PCIE_CONF_ADDR(bus->number, devfn, where);
advk_writel(pcie, reg, PIO_ADDR_LS);
advk_writel(pcie, 0, PIO_ADDR_MS);
int offset;
int ret;
- if (PCI_SLOT(devfn) != 0)
+ if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
return PCIBIOS_DEVICE_NOT_FOUND;
if (where % size)
irq_hw_number_t hwirq = irqd_to_hwirq(d);
u32 mask;
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- mask |= PCIE_ISR0_INTX_ASSERT(hwirq);
- advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+ mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ mask |= PCIE_ISR1_INTX_ASSERT(hwirq);
+ advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
}
static void advk_pcie_irq_unmask(struct irq_data *d)
irq_hw_number_t hwirq = irqd_to_hwirq(d);
u32 mask;
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- mask &= ~PCIE_ISR0_INTX_ASSERT(hwirq);
- advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+ mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ mask &= ~PCIE_ISR1_INTX_ASSERT(hwirq);
+ advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
}
static int advk_pcie_irq_map(struct irq_domain *h,
static void advk_pcie_handle_int(struct advk_pcie *pcie)
{
- u32 val, mask, status;
+ u32 isr0_val, isr0_mask, isr0_status;
+ u32 isr1_val, isr1_mask, isr1_status;
int i, virq;
- val = advk_readl(pcie, PCIE_ISR0_REG);
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- status = val & ((~mask) & PCIE_ISR0_ALL_MASK);
+ isr0_val = advk_readl(pcie, PCIE_ISR0_REG);
+ isr0_mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+ isr0_status = isr0_val & ((~isr0_mask) & PCIE_ISR0_ALL_MASK);
+
+ isr1_val = advk_readl(pcie, PCIE_ISR1_REG);
+ isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
- if (!status) {
- advk_writel(pcie, val, PCIE_ISR0_REG);
+ if (!isr0_status && !isr1_status) {
+ advk_writel(pcie, isr0_val, PCIE_ISR0_REG);
+ advk_writel(pcie, isr1_val, PCIE_ISR1_REG);
return;
}
/* Process MSI interrupts */
- if (status & PCIE_ISR0_MSI_INT_PENDING)
+ if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
advk_pcie_handle_msi(pcie);
/* Process legacy interrupts */
for (i = 0; i < PCI_NUM_INTX; i++) {
- if (!(status & PCIE_ISR0_INTX_ASSERT(i)))
+ if (!(isr1_status & PCIE_ISR1_INTX_ASSERT(i)))
continue;
- advk_writel(pcie, PCIE_ISR0_INTX_ASSERT(i),
- PCIE_ISR0_REG);
+ advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i),
+ PCIE_ISR1_REG);
virq = irq_find_mapping(pcie->irq_domain, i);
generic_handle_irq(virq);
* devices should not be touched during freeze/thaw transitions,
* however.
*/
- if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+ if (!dev_pm_smart_suspend_and_suspended(dev)) {
pm_runtime_resume(dev);
+ pci_dev->state_saved = false;
+ }
- pci_dev->state_saved = false;
if (pm->freeze) {
int error;
EXPORT_SYMBOL(pci_pme_active);
/**
- * pci_enable_wake - enable PCI device as wakeup event source
+ * __pci_enable_wake - enable PCI device as wakeup event source
* @dev: PCI device affected
* @state: PCI state from which device will issue wakeup events
* @enable: True to enable event generation; false to disable
* Error code depending on the platform is returned if both the platform and
* the native mechanism fail to enable the generation of wake-up events
*/
-int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
+static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
{
int ret = 0;
return ret;
}
+
+/**
+ * pci_enable_wake - change wakeup settings for a PCI device
+ * @pci_dev: Target device
+ * @state: PCI state from which device will issue wakeup events
+ * @enable: Whether or not to enable event generation
+ *
+ * If @enable is set, check device_may_wakeup() for the device before calling
+ * __pci_enable_wake() for it.
+ */
+int pci_enable_wake(struct pci_dev *pci_dev, pci_power_t state, bool enable)
+{
+ if (enable && !device_may_wakeup(&pci_dev->dev))
+ return -EINVAL;
+
+ return __pci_enable_wake(pci_dev, state, enable);
+}
EXPORT_SYMBOL(pci_enable_wake);
/**
* should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
* ordering constraints.
*
- * This function only returns error code if the device is not capable of
- * generating PME# from both D3_hot and D3_cold, and the platform is unable to
- * enable wake-up power for it.
+ * This function only returns error code if the device is not allowed to wake
+ * up the system from sleep or it is not capable of generating PME# from both
+ * D3_hot and D3_cold and the platform is unable to enable wake-up power for it.
*/
int pci_wake_from_d3(struct pci_dev *dev, bool enable)
{
dev->runtime_d3cold = target_state == PCI_D3cold;
- pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
+ __pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
error = pci_set_power_state(dev, target_state);
{
struct pci_bus *bus = dev->bus;
- if (device_can_wakeup(&dev->dev))
- return true;
-
if (!dev->pme_support)
return false;
/* PME-capable in principle, but not from the target power state */
- if (!pci_pme_capable(dev, pci_target_state(dev, false)))
+ if (!pci_pme_capable(dev, pci_target_state(dev, true)))
return false;
+ if (device_can_wakeup(&dev->dev))
+ return true;
+
while (bus->parent) {
struct pci_dev *bridge = bus->self;
bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
if (bw_avail >= bw_cap)
- pci_info(dev, "%u.%03u Gb/s available bandwidth (%s x%d link)\n",
+ pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
bw_cap / 1000, bw_cap % 1000,
PCIE_SPEED2STR(speed_cap), width_cap);
else
- pci_info(dev, "%u.%03u Gb/s available bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
+ pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
bw_avail / 1000, bw_avail % 1000,
PCIE_SPEED2STR(speed), width,
limiting_dev ? pci_name(limiting_dev) : "<unknown>",
static const struct mvebu_comhy_conf mvebu_comphy_cp110_modes[] = {
/* lane 0 */
MVEBU_COMPHY_CONF(0, 1, PHY_MODE_SGMII, 0x1),
+ MVEBU_COMPHY_CONF(0, 1, PHY_MODE_2500SGMII, 0x1),
/* lane 1 */
MVEBU_COMPHY_CONF(1, 2, PHY_MODE_SGMII, 0x1),
+ MVEBU_COMPHY_CONF(1, 2, PHY_MODE_2500SGMII, 0x1),
/* lane 2 */
MVEBU_COMPHY_CONF(2, 0, PHY_MODE_SGMII, 0x1),
+ MVEBU_COMPHY_CONF(2, 0, PHY_MODE_2500SGMII, 0x1),
MVEBU_COMPHY_CONF(2, 0, PHY_MODE_10GKR, 0x1),
/* lane 3 */
MVEBU_COMPHY_CONF(3, 1, PHY_MODE_SGMII, 0x2),
+ MVEBU_COMPHY_CONF(3, 1, PHY_MODE_2500SGMII, 0x2),
/* lane 4 */
MVEBU_COMPHY_CONF(4, 0, PHY_MODE_SGMII, 0x2),
+ MVEBU_COMPHY_CONF(4, 0, PHY_MODE_2500SGMII, 0x2),
MVEBU_COMPHY_CONF(4, 0, PHY_MODE_10GKR, 0x2),
MVEBU_COMPHY_CONF(4, 1, PHY_MODE_SGMII, 0x1),
/* lane 5 */
MVEBU_COMPHY_CONF(5, 2, PHY_MODE_SGMII, 0x1),
+ MVEBU_COMPHY_CONF(5, 2, PHY_MODE_2500SGMII, 0x1),
};
struct mvebu_comphy_priv {
if (mode == PHY_MODE_10GKR)
val |= MVEBU_COMPHY_SERDES_CFG0_GEN_RX(0xe) |
MVEBU_COMPHY_SERDES_CFG0_GEN_TX(0xe);
+ else if (mode == PHY_MODE_2500SGMII)
+ val |= MVEBU_COMPHY_SERDES_CFG0_GEN_RX(0x8) |
+ MVEBU_COMPHY_SERDES_CFG0_GEN_TX(0x8) |
+ MVEBU_COMPHY_SERDES_CFG0_HALF_BUS;
else if (mode == PHY_MODE_SGMII)
val |= MVEBU_COMPHY_SERDES_CFG0_GEN_RX(0x6) |
MVEBU_COMPHY_SERDES_CFG0_GEN_TX(0x6) |
return 0;
}
-static int mvebu_comphy_set_mode_sgmii(struct phy *phy)
+static int mvebu_comphy_set_mode_sgmii(struct phy *phy, enum phy_mode mode)
{
struct mvebu_comphy_lane *lane = phy_get_drvdata(phy);
struct mvebu_comphy_priv *priv = lane->priv;
u32 val;
- mvebu_comphy_ethernet_init_reset(lane, PHY_MODE_SGMII);
+ mvebu_comphy_ethernet_init_reset(lane, mode);
val = readl(priv->base + MVEBU_COMPHY_RX_CTRL1(lane->id));
val &= ~MVEBU_COMPHY_RX_CTRL1_CLK8T_EN;
switch (lane->mode) {
case PHY_MODE_SGMII:
- ret = mvebu_comphy_set_mode_sgmii(phy);
+ case PHY_MODE_2500SGMII:
+ ret = mvebu_comphy_set_mode_sgmii(phy, lane->mode);
break;
case PHY_MODE_10GKR:
ret = mvebu_comphy_set_mode_10gkr(phy);
if (!need_valid_mask) {
irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0,
- chip->ngpio, NUMA_NO_NODE);
+ community->npins, NUMA_NO_NODE);
if (irq_base < 0) {
dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n");
return irq_base;
}
- } else {
- irq_base = 0;
}
- ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base,
+ ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
handle_bad_irq, IRQ_TYPE_NONE);
if (ret) {
dev_err(pctrl->dev, "failed to add IRQ chip\n");
return ret;
}
+ if (!need_valid_mask) {
+ for (i = 0; i < community->ngpio_ranges; i++) {
+ range = &community->gpio_ranges[i];
+
+ irq_domain_associate_many(chip->irq.domain, irq_base,
+ range->base, range->npins);
+ irq_base += range->npins;
+ }
+ }
+
gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq,
chv_gpio_irq_handler);
return 0;
.npins = ((e) - (s) + 1), \
}
+#define SPTH_GPP(r, s, e, g) \
+ { \
+ .reg_num = (r), \
+ .base = (s), \
+ .size = ((e) - (s) + 1), \
+ .gpio_base = (g), \
+ }
+
+#define SPTH_COMMUNITY(b, s, e, g) \
+ { \
+ .barno = (b), \
+ .padown_offset = SPT_PAD_OWN, \
+ .padcfglock_offset = SPT_PADCFGLOCK, \
+ .hostown_offset = SPT_HOSTSW_OWN, \
+ .ie_offset = SPT_GPI_IE, \
+ .pin_base = (s), \
+ .npins = ((e) - (s) + 1), \
+ .gpps = (g), \
+ .ngpps = ARRAY_SIZE(g), \
+ }
+
/* Sunrisepoint-LP */
static const struct pinctrl_pin_desc sptlp_pins[] = {
/* GPP_A */
FUNCTION("i2c2", spth_i2c2_groups),
};
+static const struct intel_padgroup spth_community0_gpps[] = {
+ SPTH_GPP(0, 0, 23, 0), /* GPP_A */
+ SPTH_GPP(1, 24, 47, 24), /* GPP_B */
+};
+
+static const struct intel_padgroup spth_community1_gpps[] = {
+ SPTH_GPP(0, 48, 71, 48), /* GPP_C */
+ SPTH_GPP(1, 72, 95, 72), /* GPP_D */
+ SPTH_GPP(2, 96, 108, 96), /* GPP_E */
+ SPTH_GPP(3, 109, 132, 120), /* GPP_F */
+ SPTH_GPP(4, 133, 156, 144), /* GPP_G */
+ SPTH_GPP(5, 157, 180, 168), /* GPP_H */
+};
+
+static const struct intel_padgroup spth_community3_gpps[] = {
+ SPTH_GPP(0, 181, 191, 192), /* GPP_I */
+};
+
static const struct intel_community spth_communities[] = {
- SPT_COMMUNITY(0, 0, 47),
- SPT_COMMUNITY(1, 48, 180),
- SPT_COMMUNITY(2, 181, 191),
+ SPTH_COMMUNITY(0, 0, 47, spth_community0_gpps),
+ SPTH_COMMUNITY(1, 48, 180, spth_community1_gpps),
+ SPTH_COMMUNITY(2, 181, 191, spth_community3_gpps),
};
static const struct intel_pinctrl_soc_data spth_soc_data = {
static struct meson_bank meson_axg_aobus_banks[] = {
/* name first last irq pullen pull dir out in */
- BANK("AO", GPIOAO_0, GPIOAO_9, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0),
+ BANK("AO", GPIOAO_0, GPIOAO_13, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0),
};
static struct meson_pmx_bank meson_axg_periphs_pmx_banks[] = {
depends on ACPI_VIDEO || ACPI_VIDEO = n
depends on RFKILL || RFKILL = n
depends on SERIO_I8042
- select DELL_SMBIOS
+ depends on DELL_SMBIOS
select POWER_SUPPLY
select LEDS_CLASS
select NEW_LEDS
depends on DMI
depends on INPUT
depends on ACPI_VIDEO || ACPI_VIDEO = n
+ depends on DELL_SMBIOS
select DELL_WMI_DESCRIPTOR
- select DELL_SMBIOS
select INPUT_SPARSEKMAP
---help---
Say Y here if you want to support WMI-based hotkeys on Dell laptops.
{
struct asus_wireless_data *data = acpi_driver_data(adev);
- if (data->wq)
+ if (data->wq) {
+ devm_led_classdev_unregister(&adev->dev, &data->led);
destroy_workqueue(data->wq);
+ }
return 0;
}
static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
{
u64 ns;
- u32 remainder;
unsigned long flags;
struct pch_dev *pch_dev = container_of(ptp, struct pch_dev, caps);
struct pch_ts_regs __iomem *regs = pch_dev->regs;
ns = pch_systime_read(regs);
spin_unlock_irqrestore(&pch_dev->register_lock, flags);
- ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
- ts->tv_nsec = remainder;
+ *ts = ns_to_timespec64(ns);
return 0;
}
struct pch_dev *pch_dev = container_of(ptp, struct pch_dev, caps);
struct pch_ts_regs __iomem *regs = pch_dev->regs;
- ns = ts->tv_sec * 1000000000ULL;
- ns += ts->tv_nsec;
+ ns = timespec64_to_ns(ts);
spin_lock_irqsave(&pch_dev->register_lock, flags);
pch_systime_write(regs, ns);
tx->callback = dma_xfer_callback;
tx->callback_param = req;
- req->dmach = chan;
- req->sync = sync;
req->status = DMA_IN_PROGRESS;
- init_completion(&req->req_comp);
kref_get(&req->refcount);
cookie = dmaengine_submit(tx);
if (!req)
return -ENOMEM;
- kref_init(&req->refcount);
-
ret = get_dma_channel(priv);
if (ret) {
kfree(req);
return ret;
}
+ chan = priv->dmach;
+
+ kref_init(&req->refcount);
+ init_completion(&req->req_comp);
+ req->dir = dir;
+ req->filp = filp;
+ req->priv = priv;
+ req->dmach = chan;
+ req->sync = sync;
/*
* If parameter loc_addr != NULL, we are transferring data from/to
xfer->offset, xfer->length);
}
- req->dir = dir;
- req->filp = filp;
- req->priv = priv;
- chan = priv->dmach;
-
nents = dma_map_sg(chan->device->dev,
req->sgt.sgl, req->sgt.nents, dir);
if (nents == 0) {
dev_err(qproc->dev, "unable to resolve mba region\n");
return ret;
}
+ of_node_put(node);
qproc->mba_phys = r.start;
qproc->mba_size = resource_size(&r);
dev_err(qproc->dev, "unable to resolve mpss region\n");
return ret;
}
+ of_node_put(node);
qproc->mpss_phys = qproc->mpss_reloc = r.start;
qproc->mpss_size = resource_size(&r);
if (ret)
return ret;
- ret = rproc_stop(rproc, false);
+ ret = rproc_stop(rproc, true);
if (ret)
goto unlock_mutex;
if (!atomic_dec_and_test(&rproc->power))
goto out;
- ret = rproc_stop(rproc, true);
+ ret = rproc_stop(rproc, false);
if (ret) {
atomic_inc(&rproc->power);
goto out;
UNIPHIER_RESETX(4, 0x200c, 2), /* eMMC */
UNIPHIER_RESETX(6, 0x200c, 6), /* Ether */
UNIPHIER_RESETX(8, 0x200c, 8), /* STDMAC (HSC) */
- UNIPHIER_RESETX(12, 0x200c, 5), /* GIO (PCIe, USB3) */
+ UNIPHIER_RESETX(14, 0x200c, 5), /* USB30 */
UNIPHIER_RESETX(16, 0x200c, 12), /* USB30-PHY0 */
UNIPHIER_RESETX(17, 0x200c, 13), /* USB30-PHY1 */
UNIPHIER_RESETX(18, 0x200c, 14), /* USB30-PHY2 */
UNIPHIER_RESETX(6, 0x200c, 9), /* Ether0 */
UNIPHIER_RESETX(7, 0x200c, 10), /* Ether1 */
UNIPHIER_RESETX(8, 0x200c, 12), /* STDMAC */
- UNIPHIER_RESETX(12, 0x200c, 4), /* USB30 link (GIO0) */
- UNIPHIER_RESETX(13, 0x200c, 5), /* USB31 link (GIO1) */
+ UNIPHIER_RESETX(12, 0x200c, 4), /* USB30 link */
+ UNIPHIER_RESETX(13, 0x200c, 5), /* USB31 link */
UNIPHIER_RESETX(16, 0x200c, 16), /* USB30-PHY0 */
UNIPHIER_RESETX(17, 0x200c, 18), /* USB30-PHY1 */
UNIPHIER_RESETX(18, 0x200c, 20), /* USB30-PHY2 */
unregister_chrdev_region(rpmsg_major, RPMSG_DEV_MAX);
}
module_exit(rpmsg_chrdev_exit);
+
+MODULE_ALIAS("rpmsg:rpmsg_chrdev");
MODULE_LICENSE("GPL v2");
static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
{
- long rc = OPAL_BUSY;
+ s64 rc = OPAL_BUSY;
int retries = 10;
u32 y_m_d;
u64 h_m_s_ms;
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (retries-- && (rc == OPAL_HARDWARE
- || rc == OPAL_INTERNAL_ERROR))
- msleep(10);
- else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
- break;
+ } else if (rc == OPAL_BUSY) {
+ msleep(OPAL_BUSY_DELAY_MS);
+ } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+ if (retries--) {
+ msleep(10); /* Wait 10ms before retry */
+ rc = OPAL_BUSY; /* go around again */
+ }
+ }
}
if (rc != OPAL_SUCCESS)
static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
{
- long rc = OPAL_BUSY;
+ s64 rc = OPAL_BUSY;
int retries = 10;
u32 y_m_d = 0;
u64 h_m_s_ms = 0;
tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_write(y_m_d, h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (retries-- && (rc == OPAL_HARDWARE
- || rc == OPAL_INTERNAL_ERROR))
- msleep(10);
- else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
- break;
+ } else if (rc == OPAL_BUSY) {
+ msleep(OPAL_BUSY_DELAY_MS);
+ } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+ if (retries--) {
+ msleep(10); /* Wait 10ms before retry */
+ rc = OPAL_BUSY; /* go around again */
+ }
+ }
}
return rc == OPAL_SUCCESS ? 0 : -EIO;
int dasd_alias_add_device(struct dasd_device *device)
{
struct dasd_eckd_private *private = device->private;
- struct alias_lcu *lcu;
+ __u8 uaddr = private->uid.real_unit_addr;
+ struct alias_lcu *lcu = private->lcu;
unsigned long flags;
int rc;
- lcu = private->lcu;
rc = 0;
spin_lock_irqsave(&lcu->lock, flags);
+ /*
+ * Check if device and lcu type differ. If so, the uac data may be
+ * outdated and needs to be updated.
+ */
+ if (private->uid.type != lcu->uac->unit[uaddr].ua_type) {
+ lcu->flags |= UPDATE_PENDING;
+ DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+ "uid type mismatch - trigger rescan");
+ }
if (!(lcu->flags & UPDATE_PENDING)) {
rc = _add_device_to_lcu(lcu, device, device);
if (rc)
static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
{
+ struct channel_path *chp;
struct chp_link link;
struct chp_id chpid;
int status;
chpid.id = sei_area->rsid;
/* allocate a new channel path structure, if needed */
status = chp_get_status(chpid);
- if (status < 0)
- chp_new(chpid);
- else if (!status)
+ if (!status)
return;
+
+ if (status < 0) {
+ chp_new(chpid);
+ } else {
+ chp = chpid_to_chp(chpid);
+ mutex_lock(&chp->lock);
+ chp_update_desc(chp);
+ mutex_unlock(&chp->lock);
+ }
memset(&link, 0, sizeof(struct chp_link));
link.chpid = chpid;
if ((sei_area->vf & 0xc0) != 0) {
int i;
for (i = 0; i < nr_queues; i++) {
- q = kmem_cache_alloc(qdio_q_cache, GFP_KERNEL);
+ q = kmem_cache_zalloc(qdio_q_cache, GFP_KERNEL);
if (!q)
return -ENOMEM;
{
struct ciw *ciw;
struct qdio_irq *irq_ptr = init_data->cdev->private->qdio_data;
- int rc;
memset(&irq_ptr->qib, 0, sizeof(irq_ptr->qib));
memset(&irq_ptr->siga_flag, 0, sizeof(irq_ptr->siga_flag));
ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE);
if (!ciw) {
DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no);
- rc = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
irq_ptr->equeue = *ciw;
ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE);
if (!ciw) {
DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no);
- rc = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
irq_ptr->aqueue = *ciw;
init_data->cdev->handler = qdio_int_handler;
spin_unlock_irq(get_ccwdev_lock(irq_ptr->cdev));
return 0;
-out_err:
- qdio_release_memory(irq_ptr);
- return rc;
}
void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
* and stores the result to ccwchain list. @cp must have been
* initialized by a previous call with cp_init(). Otherwise, undefined
* behavior occurs.
+ * For each chain composing the channel program:
+ * - On entry ch_len holds the count of CCWs to be translated.
+ * - On exit ch_len is adjusted to the count of successfully translated CCWs.
+ * This allows cp_free to find in ch_len the count of CCWs to free in a chain.
*
* The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
* as helpers to do ccw chain translation inside the kernel. Basically
for (idx = 0; idx < len; idx++) {
ret = ccwchain_fetch_one(chain, idx, cp);
if (ret)
- return ret;
+ goto out_err;
}
}
return 0;
+out_err:
+ /* Only cleanup the chain elements that were actually translated. */
+ chain->ch_len = idx;
+ list_for_each_entry_continue(chain, &cp->ccwchain_list, next) {
+ chain->ch_len = 0;
+ }
+ return ret;
}
/**
int ccode;
__u8 lpm;
unsigned long flags;
+ int ret;
sch = private->sch;
spin_lock_irqsave(sch->lock, flags);
private->state = VFIO_CCW_STATE_BUSY;
- spin_unlock_irqrestore(sch->lock, flags);
orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
* Initialize device status information
*/
sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
- return 0;
+ ret = 0;
+ break;
case 1: /* Status pending */
case 2: /* Busy */
- return -EBUSY;
+ ret = -EBUSY;
+ break;
case 3: /* Device/path not operational */
{
lpm = orb->cmd.lpm;
sch->lpm = 0;
if (cio_update_schib(sch))
- return -ENODEV;
-
- return sch->lpm ? -EACCES : -ENODEV;
+ ret = -ENODEV;
+ else
+ ret = sch->lpm ? -EACCES : -ENODEV;
+ break;
}
default:
- return ccode;
+ ret = ccode;
}
+ spin_unlock_irqrestore(sch->lock, flags);
+ return ret;
}
static void fsm_notoper(struct vfio_ccw_private *private,
return -EINVAL;
/* TODO: sanity checks */
card->portno = value;
+ if (card->dev)
+ card->dev->dev_port = card->portno;
return count;
card->dev = dev;
card->dev->ml_priv = card;
card->dev->netdev_ops = &lcs_netdev_ops;
+ card->dev->dev_port = card->portno;
memcpy(card->dev->dev_addr, card->mac, LCS_MAC_LENGTH);
#ifdef CONFIG_IP_MULTICAST
if (!lcs_check_multicast_support(card))
unsigned int tx_csum;
unsigned int tx_lin;
unsigned int tx_linfail;
+ unsigned int rx_csum;
};
/* Routing stuff */
enum qeth_cmd_buffer_state {
BUF_STATE_FREE,
BUF_STATE_LOCKED,
- BUF_STATE_PROCESSED,
};
enum qeth_cq {
struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
atomic_t irq_pending;
int io_buf_no;
- int buf_no;
};
/**
struct qeth_discipline {
const struct device_type *devtype;
- void (*start_poll)(struct ccw_device *, int, unsigned long);
- qdio_handler_t *input_handler;
- qdio_handler_t *output_handler;
int (*process_rx_buffer)(struct qeth_card *card, int budget, int *done);
int (*recover)(void *ptr);
int (*setup) (struct ccwgroup_device *);
struct qeth_card_options options;
wait_queue_head_t wait_q;
- spinlock_t vlanlock;
spinlock_t mclock;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+ struct mutex vid_list_mutex; /* vid_list */
struct list_head vid_list;
DECLARE_HASHTABLE(mac_htable, 4);
DECLARE_HASHTABLE(ip_htable, 4);
}
}
+static inline void qeth_rx_csum(struct qeth_card *card, struct sk_buff *skb,
+ u8 flags)
+{
+ if ((card->dev->features & NETIF_F_RXCSUM) &&
+ (flags & QETH_HDR_EXT_CSUM_TRANSP_REQ)) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (card->options.performance_stats)
+ card->perf_stats.rx_csum++;
+ } else {
+ skb->ip_summed = CHECKSUM_NONE;
+ }
+}
+
+static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, int ipv)
+{
+ *flags |= QETH_HDR_EXT_CSUM_TRANSP_REQ;
+ if ((ipv == 4 && ip_hdr(skb)->protocol == IPPROTO_UDP) ||
+ (ipv == 6 && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP))
+ *flags |= QETH_HDR_EXT_UDP;
+ if (ipv == 4) {
+ /* some HW requires combined L3+L4 csum offload: */
+ *flags |= QETH_HDR_EXT_CSUM_HDR_REQ;
+ ip_hdr(skb)->check = 0;
+ }
+}
+
static inline void qeth_put_buffer_pool_entry(struct qeth_card *card,
struct qeth_buffer_pool_entry *entry)
{
return card->info.diagass_support & (__u32)cmd;
}
+int qeth_send_simple_setassparms_prot(struct qeth_card *card,
+ enum qeth_ipa_funcs ipa_func,
+ u16 cmd_code, long data,
+ enum qeth_prot_versions prot);
+/* IPv4 variant */
+static inline int qeth_send_simple_setassparms(struct qeth_card *card,
+ enum qeth_ipa_funcs ipa_func,
+ u16 cmd_code, long data)
+{
+ return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code,
+ data, QETH_PROT_IPV4);
+}
+
+static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card,
+ enum qeth_ipa_funcs ipa_func,
+ u16 cmd_code, long data)
+{
+ return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code,
+ data, QETH_PROT_IPV6);
+}
+
extern struct qeth_discipline qeth_l2_discipline;
extern struct qeth_discipline qeth_l3_discipline;
extern const struct attribute_group *qeth_generic_attr_groups[];
struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *,
struct qeth_hdr **);
void qeth_schedule_recovery(struct qeth_card *);
-void qeth_qdio_start_poll(struct ccw_device *, int, unsigned long);
int qeth_poll(struct napi_struct *napi, int budget);
-void qeth_qdio_input_handler(struct ccw_device *,
- unsigned int, unsigned int, int,
- int, unsigned long);
-void qeth_qdio_output_handler(struct ccw_device *, unsigned int,
- int, int, int, unsigned long);
void qeth_clear_ipacmd_list(struct qeth_card *);
int qeth_qdio_clear_card(struct qeth_card *, int);
void qeth_clear_working_pool_list(struct qeth_card *);
int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot);
void qeth_trace_features(struct qeth_card *);
void qeth_close_dev(struct qeth_card *);
-int qeth_send_simple_setassparms(struct qeth_card *, enum qeth_ipa_funcs,
- __u16, long);
int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16,
long,
int (*reply_cb)(struct qeth_card *,
qeth_put_reply(reply);
}
spin_unlock_irqrestore(&card->lock, flags);
- atomic_set(&card->write.irq_pending, 0);
}
EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list);
for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
qeth_release_buffer(channel, &channel->iob[cnt]);
- channel->buf_no = 0;
channel->io_buf_no = 0;
}
EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
kfree(channel->iob[cnt].data);
return -ENOMEM;
}
- channel->buf_no = 0;
channel->io_buf_no = 0;
atomic_set(&channel->irq_pending, 0);
spin_lock_init(&channel->iob_lock);
{
int rc;
int cstat, dstat;
- struct qeth_cmd_buffer *buffer;
+ struct qeth_cmd_buffer *iob = NULL;
struct qeth_channel *channel;
struct qeth_card *card;
- struct qeth_cmd_buffer *iob;
- __u8 index;
-
- if (__qeth_check_irb_error(cdev, intparm, irb))
- return;
- cstat = irb->scsw.cmd.cstat;
- dstat = irb->scsw.cmd.dstat;
card = CARD_FROM_CDEV(cdev);
if (!card)
channel = &card->data;
QETH_CARD_TEXT(card, 5, "data");
}
+
+ if (qeth_intparm_is_iob(intparm))
+ iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+
+ if (__qeth_check_irb_error(cdev, intparm, irb)) {
+ /* IO was terminated, free its resources. */
+ if (iob)
+ qeth_release_buffer(iob->channel, iob);
+ atomic_set(&channel->irq_pending, 0);
+ wake_up(&card->wait_q);
+ return;
+ }
+
atomic_set(&channel->irq_pending, 0);
if (irb->scsw.cmd.fctl & (SCSW_FCTL_CLEAR_FUNC))
/* we don't have to handle this further */
intparm = 0;
}
+
+ cstat = irb->scsw.cmd.cstat;
+ dstat = irb->scsw.cmd.dstat;
+
if ((dstat & DEV_STAT_UNIT_EXCEP) ||
(dstat & DEV_STAT_UNIT_CHECK) ||
(cstat)) {
channel->state = CH_STATE_RCD_DONE;
goto out;
}
- if (intparm) {
- buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
- buffer->state = BUF_STATE_PROCESSED;
- }
if (channel == &card->data)
return;
if (channel == &card->read &&
channel->state == CH_STATE_UP)
__qeth_issue_next_read(card);
- iob = channel->iob;
- index = channel->buf_no;
- while (iob[index].state == BUF_STATE_PROCESSED) {
- if (iob[index].callback != NULL)
- iob[index].callback(channel, iob + index);
+ if (iob && iob->callback)
+ iob->callback(iob->channel, iob);
- index = (index + 1) % QETH_CMD_BUFFER_NO;
- }
- channel->buf_no = index;
out:
wake_up(&card->wait_q);
return;
card->lan_online = 0;
card->read_or_write_problem = 0;
card->dev = NULL;
- spin_lock_init(&card->vlanlock);
spin_lock_init(&card->mclock);
spin_lock_init(&card->lock);
spin_lock_init(&card->ip_lock);
spin_lock_init(&card->thread_mask_lock);
mutex_init(&card->conf_mutex);
mutex_init(&card->discipline_mutex);
+ mutex_init(&card->vid_list_mutex);
card->thread_start_mask = 0;
card->thread_allowed_mask = 0;
card->thread_running_mask = 0;
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
if (channel->state != CH_STATE_UP) {
rc = -ETIME;
QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
- qeth_clear_cmd_buffers(channel);
} else
rc = 0;
return rc;
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n",
dev_name(&channel->ccwdev->dev));
QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME);
- qeth_clear_cmd_buffers(channel);
return -ETIME;
}
return qeth_idx_activate_get_answer(channel, idx_reply_cb);
QETH_CARD_TEXT(card, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, event_timeout);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
}
}
- if (reply->rc == -EIO)
- goto error;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
list_del_init(&reply->list);
spin_unlock_irqrestore(&reply->card->lock, flags);
atomic_inc(&reply->received);
-error:
- atomic_set(&card->write.irq_pending, 0);
- qeth_release_buffer(iob->channel, iob);
- card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
return rc;
}
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
{
- struct qeth_ipa_cmd *cmd;
-
- QETH_CARD_TEXT(card, 4, "defadpcb");
-
- cmd = (struct qeth_ipa_cmd *) data;
- if (cmd->hdr.return_code == 0)
+ if (!cmd->hdr.return_code)
cmd->hdr.return_code =
cmd->data.setadapterparms.hdr.return_code;
- return 0;
+ return cmd->hdr.return_code;
}
static int qeth_query_setadapterparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 3, "quyadpcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
card->info.link_type =
cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
}
card->options.adp.supported_funcs =
cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
- return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+ return 0;
}
static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
static int qeth_query_switch_attributes_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
- struct qeth_switch_info *sw_info;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_query_switch_attributes *attrs;
+ struct qeth_switch_info *sw_info;
QETH_CARD_TEXT(card, 2, "qswiatcb");
- cmd = (struct qeth_ipa_cmd *) data;
- sw_info = (struct qeth_switch_info *)reply->param;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
- sw_info->capabilities = attrs->capabilities;
- sw_info->settings = attrs->settings;
- QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
- sw_info->settings);
- }
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
+ sw_info = (struct qeth_switch_info *)reply->param;
+ attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+ sw_info->capabilities = attrs->capabilities;
+ sw_info->settings = attrs->settings;
+ QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+ sw_info->settings);
return 0;
}
}
}
-void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue,
- unsigned long card_ptr)
+static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue,
+ unsigned long card_ptr)
{
struct qeth_card *card = (struct qeth_card *)card_ptr;
if (card->dev && (card->dev->flags & IFF_UP))
napi_schedule(&card->napi);
}
-EXPORT_SYMBOL_GPL(qeth_qdio_start_poll);
int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq)
{
return;
}
-void qeth_qdio_input_handler(struct ccw_device *ccwdev, unsigned int qdio_err,
- unsigned int queue, int first_elem, int count,
- unsigned long card_ptr)
+static void qeth_qdio_input_handler(struct ccw_device *ccwdev,
+ unsigned int qdio_err, int queue,
+ int first_elem, int count,
+ unsigned long card_ptr)
{
struct qeth_card *card = (struct qeth_card *)card_ptr;
qeth_qdio_cq_handler(card, qdio_err, queue, first_elem, count);
else if (qdio_err)
qeth_schedule_recovery(card);
-
-
}
-EXPORT_SYMBOL_GPL(qeth_qdio_input_handler);
-void qeth_qdio_output_handler(struct ccw_device *ccwdev,
- unsigned int qdio_error, int __queue, int first_element,
- int count, unsigned long card_ptr)
+static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
+ unsigned int qdio_error, int __queue,
+ int first_element, int count,
+ unsigned long card_ptr)
{
struct qeth_card *card = (struct qeth_card *) card_ptr;
struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue];
card->perf_stats.outbound_handler_time += qeth_get_micros() -
card->perf_stats.outbound_handler_start_time;
}
-EXPORT_SYMBOL_GPL(qeth_qdio_output_handler);
/* We cannot use outbound queue 3 for unicast packets on HiperSockets */
static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_ipacmd_setadpparms *setparms;
QETH_CARD_TEXT(card, 4, "prmadpcb");
- cmd = (struct qeth_ipa_cmd *) data;
setparms = &(cmd->data.setadapterparms);
-
- qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
- if (cmd->hdr.return_code) {
+ if (qeth_setadpparms_inspect_rc(cmd)) {
QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
setparms->data.mode = SET_PROMISC_MODE_OFF;
}
static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 4, "chgmaccb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (!card->options.layer2 ||
!(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
ether_addr_copy(card->dev->dev_addr,
cmd->data.setadapterparms.data.change_addr.addr);
card->info.mac_bits |= QETH_LAYER2_MAC_READ;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_set_access_ctrl *access_ctrl_req;
int fallback = *(int *)reply->param;
QETH_CARD_TEXT(card, 4, "setaccb");
+ if (cmd->hdr.return_code)
+ return 0;
+ qeth_setadpparms_inspect_rc(cmd);
- cmd = (struct qeth_ipa_cmd *) data;
access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
QETH_DBF_TEXT_(SETUP, 2, "setaccb");
QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
card->options.isolation = card->options.prev_isolation;
break;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_qoat_priv *priv;
char *resdata;
int resdatalen;
QETH_CARD_TEXT(card, 3, "qoatcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *)data;
priv = (struct qeth_qoat_priv *)reply->param;
resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
resdata = (char *)data + 28;
static int qeth_query_card_info_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_query_card_info *card_info;
- struct carrier_info *carrier_info;
QETH_CARD_TEXT(card, 2, "qcrdincb");
- carrier_info = (struct carrier_info *)reply->param;
- cmd = (struct qeth_ipa_cmd *)data;
- card_info = &cmd->data.setadapterparms.data.card_info;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- carrier_info->card_type = card_info->card_type;
- carrier_info->port_mode = card_info->port_mode;
- carrier_info->port_speed = card_info->port_speed;
- }
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ card_info = &cmd->data.setadapterparms.data.card_info;
+ carrier_info->card_type = card_info->card_type;
+ carrier_info->port_mode = card_info->port_mode;
+ carrier_info->port_speed = card_info->port_speed;
return 0;
}
goto out;
}
- ccw_device_get_id(CARD_DDEV(card), &id);
+ ccw_device_get_id(CARD_RDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
goto out_free_in_sbals;
}
for (i = 0; i < card->qdio.no_in_queues; ++i)
- queue_start_poll[i] = card->discipline->start_poll;
+ queue_start_poll[i] = qeth_qdio_start_poll;
qeth_qdio_establish_cq(card, in_sbal_ptrs, queue_start_poll);
init_data.qib_param_field = qib_param_field;
init_data.no_input_qs = card->qdio.no_in_queues;
init_data.no_output_qs = card->qdio.no_out_queues;
- init_data.input_handler = card->discipline->input_handler;
- init_data.output_handler = card->discipline->output_handler;
+ init_data.input_handler = qeth_qdio_input_handler;
+ init_data.output_handler = qeth_qdio_output_handler;
init_data.queue_start_poll_array = queue_start_poll;
init_data.int_parm = (unsigned long) card;
init_data.input_sbal_addr_array = (void **) in_sbal_ptrs;
rc = qeth_query_ipassists(card, QETH_PROT_IPV4);
if (rc == -ENOMEM)
goto out;
+ if (qeth_is_supported(card, IPA_IPV6)) {
+ rc = qeth_query_ipassists(card, QETH_PROT_IPV6);
+ if (rc == -ENOMEM)
+ goto out;
+ }
if (qeth_is_supported(card, IPA_SETADAPTERPARMS)) {
rc = qeth_query_setadapterparms(card);
if (rc < 0) {
}
EXPORT_SYMBOL_GPL(qeth_send_setassparms);
-int qeth_send_simple_setassparms(struct qeth_card *card,
- enum qeth_ipa_funcs ipa_func,
- __u16 cmd_code, long data)
+int qeth_send_simple_setassparms_prot(struct qeth_card *card,
+ enum qeth_ipa_funcs ipa_func,
+ u16 cmd_code, long data,
+ enum qeth_prot_versions prot)
{
int rc;
int length = 0;
struct qeth_cmd_buffer *iob;
- QETH_CARD_TEXT(card, 4, "simassp4");
+ QETH_CARD_TEXT_(card, 4, "simassp%i", prot);
if (data)
length = sizeof(__u32);
- iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code,
- length, QETH_PROT_IPV4);
+ iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, length, prot);
if (!iob)
return -ENOMEM;
rc = qeth_send_setassparms(card, iob, length, data,
qeth_setassparms_cb, NULL);
return rc;
}
-EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms);
+EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms_prot);
static void qeth_unregister_dbf_views(void)
{
{"tx lin"},
{"tx linfail"},
{"cq handler count"},
- {"cq handler time"}
+ {"cq handler time"},
+ {"rx csum"}
};
int qeth_core_get_sset_count(struct net_device *dev, int stringset)
data[35] = card->perf_stats.tx_linfail;
data[36] = card->perf_stats.cq_cnt;
data[37] = card->perf_stats.cq_time;
+ data[38] = card->perf_stats.rx_csum;
}
EXPORT_SYMBOL_GPL(qeth_core_get_ethtool_stats);
static int qeth_ipa_checksum_run_cmd(struct qeth_card *card,
enum qeth_ipa_funcs ipa_func,
__u16 cmd_code, long data,
- struct qeth_checksum_cmd *chksum_cb)
+ struct qeth_checksum_cmd *chksum_cb,
+ enum qeth_prot_versions prot)
{
struct qeth_cmd_buffer *iob;
int rc = -ENOMEM;
QETH_CARD_TEXT(card, 4, "chkdocmd");
iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code,
- sizeof(__u32), QETH_PROT_IPV4);
+ sizeof(__u32), prot);
if (iob)
rc = qeth_send_setassparms(card, iob, sizeof(__u32), data,
qeth_ipa_checksum_run_cmd_cb,
return rc;
}
-static int qeth_send_checksum_on(struct qeth_card *card, int cstype)
+static int qeth_send_checksum_on(struct qeth_card *card, int cstype,
+ enum qeth_prot_versions prot)
{
- const __u32 required_features = QETH_IPA_CHECKSUM_IP_HDR |
- QETH_IPA_CHECKSUM_UDP |
- QETH_IPA_CHECKSUM_TCP;
+ u32 required_features = QETH_IPA_CHECKSUM_UDP | QETH_IPA_CHECKSUM_TCP;
struct qeth_checksum_cmd chksum_cb;
int rc;
+ if (prot == QETH_PROT_IPV4)
+ required_features |= QETH_IPA_CHECKSUM_IP_HDR;
rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_START, 0,
- &chksum_cb);
+ &chksum_cb, prot);
if (!rc) {
if ((required_features & chksum_cb.supported) !=
required_features)
QETH_CARD_IFNAME(card));
}
if (rc) {
- qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_STOP, 0);
+ qeth_send_simple_setassparms_prot(card, cstype,
+ IPA_CMD_ASS_STOP, 0, prot);
dev_warn(&card->gdev->dev,
- "Starting HW checksumming for %s failed, using SW checksumming\n",
- QETH_CARD_IFNAME(card));
+ "Starting HW IPv%d checksumming for %s failed, using SW checksumming\n",
+ prot, QETH_CARD_IFNAME(card));
return rc;
}
rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_ENABLE,
- chksum_cb.supported, &chksum_cb);
+ chksum_cb.supported, &chksum_cb,
+ prot);
if (!rc) {
if ((required_features & chksum_cb.enabled) !=
required_features)
rc = -EIO;
}
if (rc) {
- qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_STOP, 0);
+ qeth_send_simple_setassparms_prot(card, cstype,
+ IPA_CMD_ASS_STOP, 0, prot);
dev_warn(&card->gdev->dev,
- "Enabling HW checksumming for %s failed, using SW checksumming\n",
- QETH_CARD_IFNAME(card));
+ "Enabling HW IPv%d checksumming for %s failed, using SW checksumming\n",
+ prot, QETH_CARD_IFNAME(card));
return rc;
}
- dev_info(&card->gdev->dev, "HW Checksumming (%sbound) enabled\n",
- cstype == IPA_INBOUND_CHECKSUM ? "in" : "out");
+ dev_info(&card->gdev->dev, "HW Checksumming (%sbound IPv%d) enabled\n",
+ cstype == IPA_INBOUND_CHECKSUM ? "in" : "out", prot);
return 0;
}
-static int qeth_set_ipa_csum(struct qeth_card *card, int on, int cstype)
+static int qeth_set_ipa_csum(struct qeth_card *card, bool on, int cstype,
+ enum qeth_prot_versions prot)
{
- int rc = (on) ? qeth_send_checksum_on(card, cstype)
- : qeth_send_simple_setassparms(card, cstype,
- IPA_CMD_ASS_STOP, 0);
+ int rc = (on) ? qeth_send_checksum_on(card, cstype, prot)
+ : qeth_send_simple_setassparms_prot(card, cstype,
+ IPA_CMD_ASS_STOP, 0,
+ prot);
return rc ? -EIO : 0;
}
return rc;
}
-#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO)
+static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on)
+{
+ int rc_ipv4 = (on) ? -EOPNOTSUPP : 0;
+ int rc_ipv6;
+
+ if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
+ rc_ipv4 = qeth_set_ipa_csum(card, on, IPA_INBOUND_CHECKSUM,
+ QETH_PROT_IPV4);
+ if (!qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6))
+ /* no/one Offload Assist available, so the rc is trivial */
+ return rc_ipv4;
+
+ rc_ipv6 = qeth_set_ipa_csum(card, on, IPA_INBOUND_CHECKSUM,
+ QETH_PROT_IPV6);
+ if (on)
+ /* enable: success if any Assist is active */
+ return (rc_ipv6) ? rc_ipv4 : 0;
+
+ /* disable: failure if any Assist is still active */
+ return (rc_ipv6) ? rc_ipv6 : rc_ipv4;
+}
+
+#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
+ NETIF_F_IPV6_CSUM)
/**
* qeth_recover_features() - Restore device features after recovery
* @dev: the recovering net_device
QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
if ((changed & NETIF_F_IP_CSUM)) {
- rc = qeth_set_ipa_csum(card,
- features & NETIF_F_IP_CSUM ? 1 : 0,
- IPA_OUTBOUND_CHECKSUM);
+ rc = qeth_set_ipa_csum(card, features & NETIF_F_IP_CSUM,
+ IPA_OUTBOUND_CHECKSUM, QETH_PROT_IPV4);
if (rc)
changed ^= NETIF_F_IP_CSUM;
}
- if ((changed & NETIF_F_RXCSUM)) {
- rc = qeth_set_ipa_csum(card,
- features & NETIF_F_RXCSUM ? 1 : 0,
- IPA_INBOUND_CHECKSUM);
+ if (changed & NETIF_F_IPV6_CSUM) {
+ rc = qeth_set_ipa_csum(card, features & NETIF_F_IPV6_CSUM,
+ IPA_OUTBOUND_CHECKSUM, QETH_PROT_IPV6);
+ if (rc)
+ changed ^= NETIF_F_IPV6_CSUM;
+ }
+ if (changed & NETIF_F_RXCSUM) {
+ rc = qeth_set_ipa_rx_csum(card, features & NETIF_F_RXCSUM);
if (rc)
changed ^= NETIF_F_RXCSUM;
}
QETH_DBF_TEXT(SETUP, 2, "fixfeat");
if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
features &= ~NETIF_F_IP_CSUM;
- if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
+ if (!qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6))
+ features &= ~NETIF_F_IPV6_CSUM;
+ if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM) &&
+ !qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6))
features &= ~NETIF_F_RXCSUM;
if (!qeth_is_supported(card, IPA_OUTBOUND_TSO))
features &= ~NETIF_F_TSO;
mutex_init(&qeth_mod_mutex);
qeth_wq = create_singlethread_workqueue("qeth_wq");
+ if (!qeth_wq) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
rc = qeth_register_dbf_views();
if (rc)
- goto out_err;
+ goto dbf_err;
qeth_core_root_dev = root_device_register("qeth");
rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
if (rc)
root_device_unregister(qeth_core_root_dev);
register_err:
qeth_unregister_dbf_views();
+dbf_err:
+ destroy_workqueue(qeth_wq);
out_err:
pr_err("Initializing the qeth device driver failed\n");
return rc;
#define QETH_HALT_CHANNEL_PARM -11
#define QETH_RCD_PARM -12
+static inline bool qeth_intparm_is_iob(unsigned long intparm)
+{
+ switch (intparm) {
+ case QETH_CLEAR_CHANNEL_PARM:
+ case QETH_HALT_CHANNEL_PARM:
+ case QETH_RCD_PARM:
+ case 0:
+ return false;
+ }
+ return true;
+}
+
/*****************************************************************************/
/* IP Assist related definitions */
/*****************************************************************************/
IPA_QUERY_ARP_ASSIST = 0x00040000L,
IPA_INBOUND_TSO = 0x00080000L,
IPA_OUTBOUND_TSO = 0x00100000L,
+ IPA_INBOUND_CHECKSUM_V6 = 0x00400000L,
+ IPA_OUTBOUND_CHECKSUM_V6 = 0x00800000L,
};
/* SETIP/DELIP IPA Command: ***************************************************/
goto out;
}
card->info.portno = portno;
+ if (card->dev)
+ card->dev->dev_port = portno;
out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/etherdevice.h>
-#include <linux/ip.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/hashtable.h>
QETH_CARD_TEXT(card, 2, "L2Setmac");
rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC);
if (rc == 0) {
- card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- ether_addr_copy(card->dev->dev_addr, mac);
dev_info(&card->gdev->dev,
- "MAC address %pM successfully registered on device %s\n",
- card->dev->dev_addr, card->dev->name);
+ "MAC address %pM successfully registered on device %s\n",
+ mac, card->dev->name);
} else {
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
switch (rc) {
case -EEXIST:
dev_warn(&card->gdev->dev,
return rc;
}
-static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac)
-{
- int rc;
-
- QETH_CARD_TEXT(card, 2, "L2Delmac");
- if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
- rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC);
- if (rc == 0)
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
- return rc;
-}
-
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
return RTN_UNSPEC;
}
-static void qeth_l2_hdr_csum(struct qeth_card *card, struct qeth_hdr *hdr,
- struct sk_buff *skb)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- /* tcph->check contains already the pseudo hdr checksum
- * so just set the header flags
- */
- if (iph->protocol == IPPROTO_UDP)
- hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_UDP;
- hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_CSUM_TRANSP_REQ |
- QETH_HDR_EXT_CSUM_HDR_REQ;
- iph->check = 0;
- if (card->options.performance_stats)
- card->perf_stats.tx_csum++;
-}
-
static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb,
int cast_type, unsigned int data_len)
{
static void qeth_l2_process_vlans(struct qeth_card *card)
{
struct qeth_vlan_vid *id;
+
QETH_CARD_TEXT(card, 3, "L2prcvln");
- spin_lock_bh(&card->vlanlock);
+ mutex_lock(&card->vid_list_mutex);
list_for_each_entry(id, &card->vid_list, list) {
qeth_l2_send_setdelvlan(card, id->vid, IPA_CMD_SETVLAN);
}
- spin_unlock_bh(&card->vlanlock);
+ mutex_unlock(&card->vid_list_mutex);
}
static int qeth_l2_vlan_rx_add_vid(struct net_device *dev,
QETH_CARD_TEXT(card, 3, "aidREC");
return 0;
}
- id = kmalloc(sizeof(struct qeth_vlan_vid), GFP_ATOMIC);
+ id = kmalloc(sizeof(*id), GFP_KERNEL);
if (id) {
id->vid = vid;
rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_SETVLAN);
kfree(id);
return rc;
}
- spin_lock_bh(&card->vlanlock);
+ mutex_lock(&card->vid_list_mutex);
list_add_tail(&id->list, &card->vid_list);
- spin_unlock_bh(&card->vlanlock);
+ mutex_unlock(&card->vid_list_mutex);
} else {
return -ENOMEM;
}
QETH_CARD_TEXT(card, 3, "kidREC");
return 0;
}
- spin_lock_bh(&card->vlanlock);
+ mutex_lock(&card->vid_list_mutex);
list_for_each_entry(id, &card->vid_list, list) {
if (id->vid == vid) {
list_del(&id->list);
break;
}
}
- spin_unlock_bh(&card->vlanlock);
+ mutex_unlock(&card->vid_list_mutex);
if (tmpid) {
rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
kfree(tmpid);
switch (hdr->hdr.l2.id) {
case QETH_HEADER_TYPE_LAYER2:
skb->protocol = eth_type_trans(skb, skb->dev);
- if ((card->dev->features & NETIF_F_RXCSUM)
- && ((hdr->hdr.l2.flags[1] &
- (QETH_HDR_EXT_CSUM_HDR_REQ |
- QETH_HDR_EXT_CSUM_TRANSP_REQ)) ==
- (QETH_HDR_EXT_CSUM_HDR_REQ |
- QETH_HDR_EXT_CSUM_TRANSP_REQ)))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- skb->ip_summed = CHECKSUM_NONE;
+ qeth_rx_csum(card, skb, hdr->hdr.l2.flags[1]);
if (skb->protocol == htons(ETH_P_802_2))
*((__u32 *)skb->cb) = ++card->seqno.pkt_seqno;
len = skb->len;
static int qeth_l2_request_initial_mac(struct qeth_card *card)
{
int rc = 0;
- char vendor_pre[] = {0x02, 0x00, 0x00};
QETH_DBF_TEXT(SETUP, 2, "l2reqmac");
QETH_DBF_TEXT_(SETUP, 2, "doL2%s", CARD_BUS_ID(card));
card->info.type == QETH_CARD_TYPE_OSX ||
card->info.guestlan) {
rc = qeth_setadpparms_change_macaddr(card);
- if (rc) {
- QETH_DBF_MESSAGE(2, "couldn't get MAC address on "
- "device %s: x%x\n", CARD_BUS_ID(card), rc);
- QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc);
- return rc;
- }
- } else {
- eth_random_addr(card->dev->dev_addr);
- memcpy(card->dev->dev_addr, vendor_pre, 3);
+ if (!rc)
+ goto out;
+ QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %s: x%x\n",
+ CARD_BUS_ID(card), rc);
+ QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc);
+ /* fall back once more: */
}
+
+ /* some devices don't support a custom MAC address: */
+ if (card->info.type == QETH_CARD_TYPE_OSM ||
+ card->info.type == QETH_CARD_TYPE_OSX)
+ return (rc) ? rc : -EADDRNOTAVAIL;
+ eth_hw_addr_random(card->dev);
+
out:
QETH_DBF_HEX(SETUP, 2, card->dev->dev_addr, card->dev->addr_len);
return 0;
{
struct sockaddr *addr = p;
struct qeth_card *card = dev->ml_priv;
+ u8 old_addr[ETH_ALEN];
int rc = 0;
QETH_CARD_TEXT(card, 3, "setmac");
return -EOPNOTSUPP;
}
QETH_CARD_HEX(card, 3, addr->sa_data, ETH_ALEN);
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "setmcREC");
return -ERESTARTSYS;
}
- rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]);
- if (!rc || (rc == -ENOENT))
- rc = qeth_l2_send_setmac(card, addr->sa_data);
- return rc ? -EINVAL : 0;
+
+ if (!qeth_card_hw_is_reachable(card)) {
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+ return 0;
+ }
+
+ /* don't register the same address twice */
+ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
+ (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
+ return 0;
+
+ /* add the new address, switch over, drop the old */
+ rc = qeth_l2_send_setmac(card, addr->sa_data);
+ if (rc)
+ return rc;
+ ether_addr_copy(old_addr, dev->dev_addr);
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+
+ if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
+ qeth_l2_remove_mac(card, old_addr);
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
+ return 0;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
}
static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
- struct qeth_qdio_out_q *queue, int cast_type)
+ struct qeth_qdio_out_q *queue, int cast_type,
+ int ipv)
{
int push_len = sizeof(struct qeth_hdr);
unsigned int elements, nr_frags;
hdr_elements = 1;
}
qeth_l2_fill_header(hdr, skb, cast_type, skb->len - push_len);
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- qeth_l2_hdr_csum(card, hdr, skb);
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv);
+ if (card->options.performance_stats)
+ card->perf_stats.tx_csum++;
+ }
elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
if (!elements) {
{
struct qeth_card *card = dev->ml_priv;
int cast_type = qeth_l2_get_cast_type(card, skb);
+ int ipv = qeth_get_ip_version(skb);
struct qeth_qdio_out_q *queue;
int tx_bytes = skb->len;
int rc;
if (card->qdio.do_prio_queueing || (cast_type &&
card->info.is_multicast_different))
queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb,
- qeth_get_ip_version(skb), cast_type)];
+ ipv, cast_type)];
else
queue = card->qdio.out_qs[card->qdio.default_out_queue];
rc = qeth_l2_xmit_iqd(card, skb, queue, cast_type);
break;
default:
- rc = qeth_l2_xmit_osa(card, skb, queue, cast_type);
+ rc = qeth_l2_xmit_osa(card, skb, queue, cast_type, ipv);
}
if (!rc) {
card->dev->mtu = card->info.initial_mtu;
card->dev->min_mtu = 64;
card->dev->max_mtu = ETH_MAX_MTU;
+ card->dev->dev_port = card->info.portno;
card->dev->netdev_ops = &qeth_l2_netdev_ops;
if (card->info.type == QETH_CARD_TYPE_OSN) {
card->dev->ethtool_ops = &qeth_l2_osn_ops;
card->dev->hw_features |= NETIF_F_IP_CSUM;
card->dev->vlan_features |= NETIF_F_IP_CSUM;
}
- if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) {
- card->dev->hw_features |= NETIF_F_RXCSUM;
- card->dev->vlan_features |= NETIF_F_RXCSUM;
- }
+ }
+ if (qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) {
+ card->dev->hw_features |= NETIF_F_IPV6_CSUM;
+ card->dev->vlan_features |= NETIF_F_IPV6_CSUM;
+ }
+ if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM) ||
+ qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6)) {
+ card->dev->hw_features |= NETIF_F_RXCSUM;
+ card->dev->vlan_features |= NETIF_F_RXCSUM;
}
card->info.broadcast_capable = 1;
goto out_remove;
}
- if (card->info.type != QETH_CARD_TYPE_OSN)
- qeth_l2_send_setmac(card, &card->dev->dev_addr[0]);
+ if (card->info.type != QETH_CARD_TYPE_OSN &&
+ !qeth_l2_send_setmac(card, card->dev->dev_addr))
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
if (card->info.hwtrap &&
struct qeth_discipline qeth_l2_discipline = {
.devtype = &qeth_l2_devtype,
- .start_poll = qeth_qdio_start_poll,
- .input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
- .output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
.process_rx_buffer = qeth_l2_process_inbound_buffer,
.recover = qeth_l2_recover,
.setup = qeth_l2_probe_device,
qeth_prepare_control_data(card, len, iob);
QETH_CARD_TEXT(card, 6, "osnoirqp");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
return rc;
}
-static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card,
- enum qeth_ipa_funcs ipa_func, __u16 cmd_code)
-{
- int rc;
- struct qeth_cmd_buffer *iob;
-
- QETH_CARD_TEXT(card, 4, "simassp6");
- iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code,
- 0, QETH_PROT_IPV6);
- if (!iob)
- return -ENOMEM;
- rc = qeth_send_setassparms(card, iob, 0, 0,
- qeth_setassparms_cb, NULL);
- return rc;
-}
-
static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card)
{
int rc;
QETH_CARD_TEXT(card, 3, "softipv6");
- rc = qeth_query_ipassists(card, QETH_PROT_IPV6);
- if (rc) {
- dev_err(&card->gdev->dev,
- "Activating IPv6 support for %s failed\n",
- QETH_CARD_IFNAME(card));
- return rc;
- }
-
if (card->info.type == QETH_CARD_TYPE_IQD)
goto out;
QETH_CARD_IFNAME(card));
return rc;
}
- rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_IPV6,
- IPA_CMD_ASS_START);
+ rc = qeth_send_simple_setassparms_v6(card, IPA_IPV6,
+ IPA_CMD_ASS_START, 0);
if (rc) {
dev_err(&card->gdev->dev,
"Activating IPv6 support for %s failed\n",
QETH_CARD_IFNAME(card));
return rc;
}
- rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_PASSTHRU,
- IPA_CMD_ASS_START);
+ rc = qeth_send_simple_setassparms_v6(card, IPA_PASSTHRU,
+ IPA_CMD_ASS_START, 0);
if (rc) {
dev_warn(&card->gdev->dev,
"Enabling the passthrough mode for %s failed\n",
in6_dev_put(in6_dev);
}
-static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
- unsigned short vid)
-{
- struct in_device *in_dev;
- struct in_ifaddr *ifa;
- struct qeth_ipaddr *addr;
- struct net_device *netdev;
-
- QETH_CARD_TEXT(card, 4, "frvaddr4");
-
- netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
- if (!netdev)
- return;
- in_dev = in_dev_get(netdev);
- if (!in_dev)
- return;
-
- addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
- if (!addr)
- goto out;
-
- spin_lock_bh(&card->ip_lock);
-
- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
- addr->u.a4.addr = be32_to_cpu(ifa->ifa_address);
- addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask);
- addr->type = QETH_IP_TYPE_NORMAL;
- qeth_l3_delete_ip(card, addr);
- }
-
- spin_unlock_bh(&card->ip_lock);
-
- kfree(addr);
-out:
- in_dev_put(in_dev);
-}
-
-static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
- unsigned short vid)
-{
- struct inet6_dev *in6_dev;
- struct inet6_ifaddr *ifa;
- struct qeth_ipaddr *addr;
- struct net_device *netdev;
-
- QETH_CARD_TEXT(card, 4, "frvaddr6");
-
- netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
- if (!netdev)
- return;
-
- in6_dev = in6_dev_get(netdev);
- if (!in6_dev)
- return;
-
- addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
- if (!addr)
- goto out;
-
- spin_lock_bh(&card->ip_lock);
-
- list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
- memcpy(&addr->u.a6.addr, &ifa->addr,
- sizeof(struct in6_addr));
- addr->u.a6.pfxlen = ifa->prefix_len;
- addr->type = QETH_IP_TYPE_NORMAL;
- qeth_l3_delete_ip(card, addr);
- }
-
- spin_unlock_bh(&card->ip_lock);
-
- kfree(addr);
-out:
- in6_dev_put(in6_dev);
-}
-
-static void qeth_l3_free_vlan_addresses(struct qeth_card *card,
- unsigned short vid)
-{
- rcu_read_lock();
- qeth_l3_free_vlan_addresses4(card, vid);
- qeth_l3_free_vlan_addresses6(card, vid);
- rcu_read_unlock();
-}
-
static int qeth_l3_vlan_rx_add_vid(struct net_device *dev,
__be16 proto, u16 vid)
{
QETH_CARD_TEXT(card, 3, "kidREC");
return 0;
}
- /* unregister IP addresses of vlan device */
- qeth_l3_free_vlan_addresses(card, vid);
clear_bit(vid, card->active_vlans);
qeth_l3_set_rx_mode(dev);
return 0;
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag);
}
- if (card->dev->features & NETIF_F_RXCSUM) {
- if ((hdr->hdr.l3.ext_flags &
- (QETH_HDR_EXT_CSUM_HDR_REQ |
- QETH_HDR_EXT_CSUM_TRANSP_REQ)) ==
- (QETH_HDR_EXT_CSUM_HDR_REQ |
- QETH_HDR_EXT_CSUM_TRANSP_REQ))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- skb->ip_summed = CHECKSUM_NONE;
- } else
- skb->ip_summed = CHECKSUM_NONE;
+ qeth_rx_csum(card, skb, hdr->hdr.l3.ext_flags);
}
static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
rcu_read_unlock();
}
-static void qeth_l3_hdr_csum(struct qeth_card *card, struct qeth_hdr *hdr,
- struct sk_buff *skb)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- /* tcph->check contains already the pseudo hdr checksum
- * so just set the header flags
- */
- if (iph->protocol == IPPROTO_UDP)
- hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_UDP;
- hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_TRANSP_REQ |
- QETH_HDR_EXT_CSUM_HDR_REQ;
- iph->check = 0;
- if (card->options.performance_stats)
- card->perf_stats.tx_csum++;
-}
-
static void qeth_tso_fill_header(struct qeth_card *card,
struct qeth_hdr *qhdr, struct sk_buff *skb)
{
}
}
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- qeth_l3_hdr_csum(card, hdr, new_skb);
+ if (new_skb->ip_summed == CHECKSUM_PARTIAL) {
+ qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv);
+ if (card->options.performance_stats)
+ card->perf_stats.tx_csum++;
+ }
}
elements = use_tso ?
(card->info.link_type == QETH_LINK_TYPE_HSTR)) {
pr_info("qeth_l3: ignoring TR device\n");
return -ENODEV;
- } else {
- card->dev = alloc_etherdev(0);
- if (!card->dev)
- return -ENODEV;
- card->dev->netdev_ops = &qeth_l3_osa_netdev_ops;
-
- /*IPv6 address autoconfiguration stuff*/
- qeth_l3_get_unique_id(card);
- if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD))
- card->dev->dev_id = card->info.unique_id &
- 0xffff;
-
- card->dev->hw_features |= NETIF_F_SG;
- card->dev->vlan_features |= NETIF_F_SG;
-
- if (!card->info.guestlan) {
- card->dev->features |= NETIF_F_SG;
- card->dev->hw_features |= NETIF_F_TSO |
- NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
- card->dev->vlan_features |= NETIF_F_TSO |
- NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
- }
+ }
+
+ card->dev = alloc_etherdev(0);
+ if (!card->dev)
+ return -ENODEV;
+ card->dev->netdev_ops = &qeth_l3_osa_netdev_ops;
+
+ /*IPv6 address autoconfiguration stuff*/
+ qeth_l3_get_unique_id(card);
+ if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD))
+ card->dev->dev_id = card->info.unique_id & 0xffff;
+
+ card->dev->hw_features |= NETIF_F_SG;
+ card->dev->vlan_features |= NETIF_F_SG;
+
+ if (!card->info.guestlan) {
+ card->dev->features |= NETIF_F_SG;
+ card->dev->hw_features |= NETIF_F_TSO |
+ NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
+ card->dev->vlan_features |= NETIF_F_TSO |
+ NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
+ }
+
+ if (qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) {
+ card->dev->hw_features |= NETIF_F_IPV6_CSUM;
+ card->dev->vlan_features |= NETIF_F_IPV6_CSUM;
}
} else if (card->info.type == QETH_CARD_TYPE_IQD) {
card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN,
card->dev->mtu = card->info.initial_mtu;
card->dev->min_mtu = 64;
card->dev->max_mtu = ETH_MAX_MTU;
+ card->dev->dev_port = card->info.portno;
card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
struct qeth_discipline qeth_l3_discipline = {
.devtype = &qeth_l3_devtype,
- .start_poll = qeth_qdio_start_poll,
- .input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
- .output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
.process_rx_buffer = qeth_l3_process_inbound_buffer,
.recover = qeth_l3_recover,
.setup = qeth_l3_probe_device,
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
int wait;
unsigned long flags = 0;
unsigned long mflags = 0;
+ struct aac_hba_cmd_req *hbacmd = (struct aac_hba_cmd_req *)
+ fibptr->hw_fib_va;
fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA);
if (callback) {
wait = 1;
- if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
- struct aac_hba_cmd_req *hbacmd =
- (struct aac_hba_cmd_req *)fibptr->hw_fib_va;
+ hbacmd->iu_type = command;
- hbacmd->iu_type = command;
+ if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
/* bit1 of request_id must be 0 */
hbacmd->request_id =
cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
"Number of Abort FW Timeouts: %lld\n"
"Number of Abort IO NOT Found: %lld\n"
- "Abord issued times: \n"
+ "Abort issued times: \n"
" < 6 sec : %lld\n"
" 6 sec - 20 sec : %lld\n"
" 20 sec - 30 sec : %lld\n"
* Note: We have not moved the current phy_index so we will actually
* compare the startting phy with itself.
* This is expected and required to add the phy to the port. */
- while (phy_index < SCI_MAX_PHYS) {
+ for (; phy_index < SCI_MAX_PHYS; phy_index++) {
if ((phy_mask & (1 << phy_index)) == 0)
continue;
sci_phy_get_sas_address(&ihost->phys[phy_index],
&ihost->phys[phy_index]);
assigned_phy_mask |= (1 << phy_index);
- phy_index++;
}
}
goto fail_fw_init;
}
- ret = 0;
+ return 0;
fail_fw_init:
dev_err(&instance->pdev->dev,
- "Init cmd return status %s for SCSI host %d\n",
- ret ? "FAILED" : "SUCCESS", instance->host->host_no);
+ "Init cmd return status FAILED for SCSI host %d\n",
+ instance->host->host_no);
return ret;
}
struct fip_vlan *vlan;
#define MY_FIP_ALL_FCF_MACS ((__u8[6]) { 1, 0x10, 0x18, 1, 0, 2 })
static u8 my_fcoe_all_fcfs[ETH_ALEN] = MY_FIP_ALL_FCF_MACS;
+ unsigned long flags = 0;
skb = dev_alloc_skb(sizeof(struct fip_vlan));
if (!skb)
kfree_skb(skb);
return;
}
- qed_ops->ll2->start_xmit(qedf->cdev, skb);
+
+ set_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &flags);
+ qed_ops->ll2->start_xmit(qedf->cdev, skb, flags);
}
static void qedf_fcoe_process_vlan_resp(struct qedf_ctx *qedf,
print_hex_dump(KERN_WARNING, "fip ", DUMP_PREFIX_OFFSET, 16, 1,
skb->data, skb->len, false);
- qed_ops->ll2->start_xmit(qedf->cdev, skb);
+ qed_ops->ll2->start_xmit(qedf->cdev, skb, 0);
}
/* Process incoming FIP frames. */
if (qedf_dump_frames)
print_hex_dump(KERN_WARNING, "fcoe: ", DUMP_PREFIX_OFFSET, 16,
1, skb->data, skb->len, false);
- qed_ops->ll2->start_xmit(qedf->cdev, skb);
+ qed_ops->ll2->start_xmit(qedf->cdev, skb, 0);
return 0;
}
if (vlanid)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid);
- rc = qedi_ops->ll2->start_xmit(cdev, skb);
+ rc = qedi_ops->ll2->start_xmit(cdev, skb, 0);
if (rc) {
QEDI_ERR(&qedi->dbg_ctx, "ll2 start_xmit returned %d\n",
rc);
#define F_INV_OP 0x200
#define F_FAKE_RW 0x400
#define F_M_ACCESS 0x800 /* media access */
-#define F_LONG_DELAY 0x1000
+#define F_SSU_DELAY 0x1000
+#define F_SYNC_DELAY 0x2000
#define FF_RESPOND (F_RL_WLUN_OK | F_SKIP_UA | F_DELAY_OVERR)
#define FF_MEDIA_IO (F_M_ACCESS | F_FAKE_RW)
#define FF_SA (F_SA_HIGH | F_SA_LOW)
+#define F_LONG_DELAY (F_SSU_DELAY | F_SYNC_DELAY)
#define SDEBUG_MAX_PARTS 4
};
static const struct opcode_info_t sync_cache_iarr[] = {
- {0, 0x91, 0, F_LONG_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
+ {0, 0x91, 0, F_SYNC_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
{16, 0x6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0x3f, 0xc7} }, /* SYNC_CACHE (16) */
};
resp_write_dt0, write_iarr, /* WRITE(16) */
{16, 0xfa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0xff, 0xc7} },
- {0, 0x1b, 0, F_LONG_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
+ {0, 0x1b, 0, F_SSU_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
{6, 0x1, 0, 0xf, 0xf7, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
{ARRAY_SIZE(sa_in_16_iarr), 0x9e, 0x10, F_SA_LOW | F_D_IN,
resp_readcap16, sa_in_16_iarr, /* SA_IN(16), READ CAPACITY(16) */
resp_write_same_10, write_same_iarr, /* WRITE SAME(10) */
{10, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0,
0, 0, 0, 0, 0} },
- {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_LONG_DELAY | F_M_ACCESS,
+ {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_SYNC_DELAY | F_M_ACCESS,
resp_sync_cache, sync_cache_iarr,
{10, 0x7, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0, 0,
0, 0, 0, 0} }, /* SYNC_CACHE (10) */
static bool sdebug_any_injecting_opt;
static bool sdebug_verbose;
static bool have_dif_prot;
+static bool write_since_sync;
static bool sdebug_statistics = DEF_STATISTICS;
static unsigned int sdebug_store_sectors;
{
unsigned char *cmd = scp->cmnd;
int power_cond, stop;
+ bool changing;
power_cond = (cmd[4] & 0xf0) >> 4;
if (power_cond) {
return check_condition_result;
}
stop = !(cmd[4] & 1);
+ changing = atomic_read(&devip->stopped) == !stop;
atomic_xchg(&devip->stopped, stop);
- return (cmd[1] & 0x1) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!changing || cmd[1] & 0x1) /* state unchanged or IMMED set */
+ return SDEG_RES_IMMED_MASK;
+ else
+ return 0;
}
static sector_t get_sdebug_capacity(void)
if (do_write) {
sdb = scsi_out(scmd);
dir = DMA_TO_DEVICE;
+ write_since_sync = true;
} else {
sdb = scsi_in(scmd);
dir = DMA_FROM_DEVICE;
static int resp_sync_cache(struct scsi_cmnd *scp,
struct sdebug_dev_info *devip)
{
+ int res = 0;
u64 lba;
u32 num_blocks;
u8 *cmd = scp->cmnd;
mk_sense_buffer(scp, ILLEGAL_REQUEST, LBA_OUT_OF_RANGE, 0);
return check_condition_result;
}
- return (cmd[1] & 0x2) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!write_since_sync || cmd[1] & 0x2)
+ res = SDEG_RES_IMMED_MASK;
+ else /* delay if write_since_sync and IMMED clear */
+ write_since_sync = false;
+ return res;
}
#define RL_BUCKET_ELEMS 8
return schedule_resp(scp, devip, errsts, pfp, 0, 0);
else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
/*
- * If any delay is active, want F_LONG_DELAY to be at least 1
+ * If any delay is active, for F_SSU_DELAY want at least 1
* second and if sdebug_jdelay>0 want a long delay of that
- * many seconds.
+ * many seconds; for F_SYNC_DELAY want 1/20 of that.
*/
int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
+ int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
- jdelay = mult_frac(USER_HZ * jdelay, HZ, USER_HZ);
+ jdelay = mult_frac(USER_HZ * jdelay, HZ, denom * USER_HZ);
return schedule_resp(scp, devip, errsts, pfp, jdelay, 0);
} else
return schedule_resp(scp, devip, errsts, pfp, sdebug_jdelay,
return nlmsg_multicast(nls, skb, 0, group, gfp);
}
+static int
+iscsi_unicast_skb(struct sk_buff *skb, u32 portid)
+{
+ return nlmsg_unicast(nls, skb, portid);
+}
+
int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
char *data, uint32_t data_size)
{
EXPORT_SYMBOL_GPL(iscsi_ping_comp_event);
static int
-iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
- void *payload, int size)
+iscsi_if_send_reply(u32 portid, int type, void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
int len = nlmsg_total_size(size);
- int flags = multi ? NLM_F_MULTI : 0;
- int t = done ? NLMSG_DONE : type;
skb = alloc_skb(len, GFP_ATOMIC);
if (!skb) {
return -ENOMEM;
}
- nlh = __nlmsg_put(skb, 0, 0, t, (len - sizeof(*nlh)), 0);
- nlh->nlmsg_flags = flags;
+ nlh = __nlmsg_put(skb, 0, 0, type, (len - sizeof(*nlh)), 0);
memcpy(nlmsg_data(nlh), payload, size);
- return iscsi_multicast_skb(skb, group, GFP_ATOMIC);
+ return iscsi_unicast_skb(skb, portid);
}
static int
iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
{
int err = 0;
+ u32 portid;
struct iscsi_uevent *ev = nlmsg_data(nlh);
struct iscsi_transport *transport = NULL;
struct iscsi_internal *priv;
if (!try_module_get(transport->owner))
return -EINVAL;
+ portid = NETLINK_CB(skb).portid;
+
switch (nlh->nlmsg_type) {
case ISCSI_UEVENT_CREATE_SESSION:
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_session.initial_cmdsn,
ev->u.c_session.cmds_max,
ev->u.c_session.queue_depth);
}
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_bound_session.initial_cmdsn,
ev->u.c_bound_session.cmds_max,
ev->u.c_bound_session.queue_depth);
static void
iscsi_if_rx(struct sk_buff *skb)
{
+ u32 portid = NETLINK_CB(skb).portid;
+
mutex_lock(&rx_queue_mutex);
while (skb->len >= NLMSG_HDRLEN) {
int err;
break;
if (ev->type == ISCSI_UEVENT_GET_CHAP && !err)
break;
- err = iscsi_if_send_reply(group, nlh->nlmsg_seq,
- nlh->nlmsg_type, 0, 0, ev, sizeof(*ev));
+ err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
+ ev, sizeof(*ev));
} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
skb_pull(skb, rlen);
}
break; /* standby */
if (sshdr.asc == 4 && sshdr.ascq == 0xc)
break; /* unavailable */
+ if (sshdr.asc == 4 && sshdr.ascq == 0x1b)
+ break; /* sanitize in progress */
/*
* Issue command to spin up drive when not ready
*/
*
* Check that all zones of the device are equal. The last zone can however
* be smaller. The zone size must also be a power of two number of LBAs.
+ *
+ * Returns the zone size in bytes upon success or an error code upon failure.
*/
-static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
{
u64 zone_blocks = 0;
sector_t block = 0;
int ret;
u8 same;
- sdkp->zone_blocks = 0;
-
/* Get a buffer */
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
/* Parse zone descriptors */
while (rec < buf + buf_len) {
- zone_blocks = get_unaligned_be64(&rec[8]);
- if (sdkp->zone_blocks == 0) {
- sdkp->zone_blocks = zone_blocks;
- } else if (zone_blocks != sdkp->zone_blocks &&
- (block + zone_blocks < sdkp->capacity
- || zone_blocks > sdkp->zone_blocks)) {
- zone_blocks = 0;
+ u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
+
+ if (zone_blocks == 0) {
+ zone_blocks = this_zone_blocks;
+ } else if (this_zone_blocks != zone_blocks &&
+ (block + this_zone_blocks < sdkp->capacity
+ || this_zone_blocks > zone_blocks)) {
+ this_zone_blocks = 0;
goto out;
}
- block += zone_blocks;
+ block += this_zone_blocks;
rec += 64;
}
} while (block < sdkp->capacity);
- zone_blocks = sdkp->zone_blocks;
-
out:
if (!zone_blocks) {
if (sdkp->first_scan)
"Zone size too large\n");
ret = -ENODEV;
} else {
- sdkp->zone_blocks = zone_blocks;
- sdkp->zone_shift = ilog2(zone_blocks);
+ ret = zone_blocks;
}
out_free:
/**
* sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
- * @sdkp: The disk of the bitmap
+ * @nr_zones: Number of zones to allocate space for.
+ * @numa_node: NUMA node to allocate the memory from.
*/
-static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+static inline unsigned long *
+sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node)
{
- struct request_queue *q = sdkp->disk->queue;
-
- return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
- * sizeof(unsigned long),
- GFP_KERNEL, q->node);
+ return kzalloc_node(BITS_TO_LONGS(nr_zones) * sizeof(unsigned long),
+ GFP_KERNEL, numa_node);
}
/**
* @sdkp: disk used
* @buf: report reply buffer
* @buflen: length of @buf
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
* @seq_zones_bitmap: bitmap of sequential zones to set
*
* Parse reported zone descriptors in @buf to identify sequential zones and
* Return the LBA after the last zone reported.
*/
static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
- unsigned int buflen,
+ unsigned int buflen, u32 zone_shift,
unsigned long *seq_zones_bitmap)
{
sector_t lba, next_lba = sdkp->capacity;
if (type != ZBC_ZONE_TYPE_CONV &&
cond != ZBC_ZONE_COND_READONLY &&
cond != ZBC_ZONE_COND_OFFLINE)
- set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap);
+ set_bit(lba >> zone_shift, seq_zones_bitmap);
next_lba = lba + get_unaligned_be64(&rec[8]);
rec += 64;
}
}
/**
- * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap.
+ * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap.
* @sdkp: target disk
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
+ * @nr_zones: number of zones to set up a seq zone bitmap for
*
* Allocate a zone bitmap and initialize it by identifying sequential zones.
*/
-static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
+static unsigned long *
+sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift,
+ u32 nr_zones)
{
struct request_queue *q = sdkp->disk->queue;
unsigned long *seq_zones_bitmap;
unsigned char *buf;
int ret = -ENOMEM;
- seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp);
+ seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node);
if (!seq_zones_bitmap)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
if (ret)
goto out;
lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
- seq_zones_bitmap);
+ zone_shift, seq_zones_bitmap);
}
if (lba != sdkp->capacity) {
kfree(buf);
if (ret) {
kfree(seq_zones_bitmap);
- return ret;
+ return ERR_PTR(ret);
}
-
- q->seq_zones_bitmap = seq_zones_bitmap;
-
- return 0;
+ return seq_zones_bitmap;
}
static void sd_zbc_cleanup(struct scsi_disk *sdkp)
q->nr_zones = 0;
}
-static int sd_zbc_setup(struct scsi_disk *sdkp)
+static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks)
{
struct request_queue *q = sdkp->disk->queue;
+ u32 zone_shift = ilog2(zone_blocks);
+ u32 nr_zones;
int ret;
- /* READ16/WRITE16 is mandatory for ZBC disks */
- sdkp->device->use_16_for_rw = 1;
- sdkp->device->use_10_for_rw = 0;
-
/* chunk_sectors indicates the zone size */
- blk_queue_chunk_sectors(sdkp->disk->queue,
- logical_to_sectors(sdkp->device, sdkp->zone_blocks));
- sdkp->nr_zones =
- round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
+ blk_queue_chunk_sectors(q,
+ logical_to_sectors(sdkp->device, zone_blocks));
+ nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift;
/*
* Initialize the device request queue information if the number
* of zones changed.
*/
- if (sdkp->nr_zones != q->nr_zones) {
-
- sd_zbc_cleanup(sdkp);
-
- q->nr_zones = sdkp->nr_zones;
- if (sdkp->nr_zones) {
- q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
- if (!q->seq_zones_wlock) {
+ if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) {
+ unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+ size_t zone_bitmap_size;
+
+ if (nr_zones) {
+ seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones,
+ q->node);
+ if (!seq_zones_wlock) {
ret = -ENOMEM;
goto err;
}
- ret = sd_zbc_setup_seq_zones_bitmap(sdkp);
- if (ret) {
- sd_zbc_cleanup(sdkp);
+ seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp,
+ zone_shift, nr_zones);
+ if (IS_ERR(seq_zones_bitmap)) {
+ ret = PTR_ERR(seq_zones_bitmap);
+ kfree(seq_zones_wlock);
goto err;
}
}
-
+ zone_bitmap_size = BITS_TO_LONGS(nr_zones) *
+ sizeof(unsigned long);
+ blk_mq_freeze_queue(q);
+ if (q->nr_zones != nr_zones) {
+ /* READ16/WRITE16 is mandatory for ZBC disks */
+ sdkp->device->use_16_for_rw = 1;
+ sdkp->device->use_10_for_rw = 0;
+
+ sdkp->zone_blocks = zone_blocks;
+ sdkp->zone_shift = zone_shift;
+ sdkp->nr_zones = nr_zones;
+ q->nr_zones = nr_zones;
+ swap(q->seq_zones_wlock, seq_zones_wlock);
+ swap(q->seq_zones_bitmap, seq_zones_bitmap);
+ } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size) != 0) {
+ memcpy(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size);
+ }
+ blk_mq_unfreeze_queue(q);
+ kfree(seq_zones_wlock);
+ kfree(seq_zones_bitmap);
}
return 0;
int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
{
+ int64_t zone_blocks;
int ret;
if (!sd_is_zoned(sdkp))
* Check zone size: only devices with a constant zone size (except
* an eventual last runt zone) that is a power of 2 are supported.
*/
- ret = sd_zbc_check_zone_size(sdkp);
- if (ret)
+ zone_blocks = sd_zbc_check_zone_size(sdkp);
+ ret = -EFBIG;
+ if (zone_blocks != (u32)zone_blocks)
+ goto err;
+ ret = zone_blocks;
+ if (ret < 0)
goto err;
/* The drive satisfies the kernel restrictions: set it up */
- ret = sd_zbc_setup(sdkp);
+ ret = sd_zbc_setup(sdkp, zone_blocks);
if (ret)
goto err;
max_targets = STORVSC_MAX_TARGETS;
max_channels = STORVSC_MAX_CHANNELS;
/*
- * On Windows8 and above, we support sub-channels for storage.
+ * On Windows8 and above, we support sub-channels for storage
+ * on SCSI and FC controllers.
* The number of sub-channels offerred is based on the number of
* VCPUs in the guest.
*/
- max_sub_channels = (num_cpus / storvsc_vcpus_per_sub_channel);
+ if (!dev_is_ide)
+ max_sub_channels =
+ (num_cpus - 1) / storvsc_vcpus_per_sub_channel;
}
scsi_driver.can_queue = (max_outstanding_req_per_channel *
*val = ' ';
}
+static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb);
+}
+
+static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr);
+}
+
+static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_task_req_desc *descp;
+ struct utp_upiu_task_req *task_req;
+ int off = (int)tag - hba->nutrs;
+
+ descp = &hba->utmrdl_base_addr[off];
+ task_req = (struct utp_upiu_task_req *)descp->task_req_upiu;
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &task_req->header,
+ &task_req->input_param1);
+}
+
static void ufshcd_add_command_trace(struct ufs_hba *hba,
unsigned int tag, const char *str)
{
struct ufshcd_lrb *lrbp;
int transfer_len = -1;
+ /* trace UPIU also */
+ ufshcd_add_cmd_upiu_trace(hba, tag, str);
+
if (!trace_ufshcd_command_enabled())
return;
hba->dev_cmd.complete = &wait;
+ ufshcd_add_query_upiu_trace(hba, tag, "query_send");
/* Make sure descriptors are ready before ringing the doorbell */
wmb();
spin_lock_irqsave(hba->host->host_lock, flags);
err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
+ ufshcd_add_query_upiu_trace(hba, tag,
+ err ? "query_complete_err" : "query_complete");
+
out_put_tag:
ufshcd_put_dev_cmd_tag(hba, tag);
wake_up(&hba->dev_cmd.tag_wq);
spin_unlock_irqrestore(host->host_lock, flags);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send");
+
/* wait until the task management command is completed */
err = wait_event_timeout(hba->tm_wq,
test_bit(free_slot, &hba->tm_condition),
msecs_to_jiffies(TM_CMD_TIMEOUT));
if (!err) {
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err");
dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
__func__, tm_function);
if (ufshcd_clear_tm_cmd(hba, free_slot))
err = -ETIMEDOUT;
} else {
err = ufshcd_task_req_compl(hba, free_slot, tm_response);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete");
}
clear_bit(free_slot, &hba->tm_condition);
break;
case BTSTAT_ABORTQUEUE:
- cmd->result = (DID_ABORT << 16);
+ cmd->result = (DID_BUS_BUSY << 16);
break;
case BTSTAT_SCSIPARITY:
0, 1, 2, 3, 3, 4, 4, 5, 5, 5, 5, 6, 6, 6, 6, 7
};
- clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
+ code = clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
return sizetocode[code - 1];
}
struct rpi_power_domain_packet {
u32 domain;
u32 on;
-} __packet;
+};
/*
* Asks the firmware to enable or disable power on a specific power
static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)
{
- if (!has_bspi(qspi) || (qspi->bspi_enabled))
+ if (!has_bspi(qspi))
return;
qspi->bspi_enabled = 1;
static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)
{
- if (!has_bspi(qspi) || (!qspi->bspi_enabled))
+ if (!has_bspi(qspi))
return;
qspi->bspi_enabled = 0;
static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs)
{
- u32 data = 0;
+ u32 rd = 0;
+ u32 wr = 0;
- if (qspi->curr_cs == cs)
- return;
if (qspi->base[CHIP_SELECT]) {
- data = bcm_qspi_read(qspi, CHIP_SELECT, 0);
- data = (data & ~0xff) | (1 << cs);
- bcm_qspi_write(qspi, CHIP_SELECT, 0, data);
+ rd = bcm_qspi_read(qspi, CHIP_SELECT, 0);
+ wr = (rd & ~0xff) | (1 << cs);
+ if (rd == wr)
+ return;
+ bcm_qspi_write(qspi, CHIP_SELECT, 0, wr);
usleep_range(10, 20);
}
+
+ dev_dbg(&qspi->pdev->dev, "using cs:%d\n", cs);
qspi->curr_cs = cs;
}
dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
}
mspi_cdram = MSPI_CDRAM_CONT_BIT;
- mspi_cdram |= (~(1 << spi->chip_select) &
- MSPI_CDRAM_PCS);
+
+ if (has_bspi(qspi))
+ mspi_cdram &= ~1;
+ else
+ mspi_cdram |= (~(1 << spi->chip_select) &
+ MSPI_CDRAM_PCS);
+
mspi_cdram |= ((tp.trans->bits_per_word <= 8) ? 0 :
MSPI_CDRAM_BITSE_BIT);
struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
irqreturn_t ret = IRQ_NONE;
+ /* IRQ may be shared, so return if our interrupts are disabled */
+ if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) &
+ (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE)))
+ return ret;
+
/* check if we have data to read */
while (bs->rx_len &&
(!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
while ((trans_cnt < CDNS_SPI_FIFO_DEPTH) &&
(xspi->tx_bytes > 0)) {
+
+ /* When xspi in busy condition, bytes may send failed,
+ * then spi control did't work thoroughly, add one byte delay
+ */
+ if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
+ CDNS_SPI_IXR_TXFULL)
+ usleep_range(10, 20);
+
if (xspi->txbuf)
cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
else
};
module_platform_driver(spi_imx_driver);
-MODULE_DESCRIPTION("SPI Master Controller driver");
+MODULE_DESCRIPTION("SPI Controller driver");
MODULE_AUTHOR("Sascha Hauer, Pengutronix");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:" DRIVER_NAME);
/* SSP register addresses */
void __iomem *ioaddr;
- u32 ssdr_physical;
+ phys_addr_t ssdr_physical;
/* SSP masks*/
u32 dma_cr1;
}
k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1);
+ brps = min_t(int, brps, 32);
scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps);
sh_msiof_write(p, TSCR, scr);
priv->dev->of_node = pdata->of_node;
pinctrl = devm_pinctrl_get_select_default(priv->dev);
if (IS_ERR(pinctrl)) {
- ret = PTR_ERR(priv->vdev);
+ ret = PTR_ERR(pinctrl);
dev_dbg(priv->dev,
"devm_pinctrl_get_select_default() failed: %d\n", ret);
if (ret != -ENODEV)
}
if (hif_drv->usr_conn_req.ies) {
- conn_info.req_ies = kmemdup(conn_info.req_ies,
+ conn_info.req_ies = kmemdup(hif_drv->usr_conn_req.ies,
hif_drv->usr_conn_req.ies_len,
GFP_KERNEL);
if (conn_info.req_ies)
{
struct se_device *dev = cmd->se_dev;
struct scatterlist *sg = &cmd->t_data_sg[0];
- unsigned char *buf, zero = 0x00, *p = &zero;
- int rc, ret;
+ unsigned char *buf, *not_zero;
+ int ret;
buf = kmap(sg_page(sg)) + sg->offset;
if (!buf)
* Fall back to block_execute_write_same() slow-path if
* incoming WRITE_SAME payload does not contain zeros.
*/
- rc = memcmp(buf, p, cmd->data_length);
+ not_zero = memchr_inv(buf, 0x00, cmd->data_length);
kunmap(sg_page(sg));
- if (rc)
+ if (not_zero)
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
ret = blkdev_issue_zeroout(bdev,
bytes = min(bytes, data_len);
if (!bio) {
+new_bio:
nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
nr_pages -= nr_vecs;
/*
* be allocated with pscsi_get_bio() above.
*/
bio = NULL;
+ goto new_bio;
}
data_len -= bytes;
if (IS_ERR(shm))
return PTR_ERR(shm);
+ /*
+ * Ensure offset + size does not overflow offset
+ * and does not overflow the size of the referred
+ * shared memory object.
+ */
+ if ((ip.a + ip.b) < ip.a ||
+ (ip.a + ip.b) > shm->size) {
+ tee_shm_put(shm);
+ return -EINVAL;
+ }
+
params[n].u.memref.shm_offs = ip.a;
params[n].u.memref.size = ip.b;
params[n].u.memref.shm = shm;
if (!(shm->flags & TEE_SHM_DMA_BUF))
return -EINVAL;
+ get_dma_buf(shm->dmabuf);
fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
- if (fd >= 0)
- get_dma_buf(shm->dmabuf);
+ if (fd < 0)
+ dma_buf_put(shm->dmabuf);
return fd;
}
return -EFAULT;
}
+ priv->priv = obj;
obj->max_state = p->package.count - 1;
obj->cdev =
thermal_cooling_device_register(acpi_device_bid(priv->adev),
if (IS_ERR(obj->cdev))
result = PTR_ERR(obj->cdev);
- priv->priv = obj;
-
kfree(buf.pointer);
/* TODO: add ACPI notification support */
* @regulator: pointer to the TMU regulator structure.
* @reg_conf: pointer to structure to register with core thermal.
* @ntrip: number of supported trip points.
+ * @enabled: current status of TMU device
* @tmu_initialize: SoC specific TMU initialization method
* @tmu_control: SoC specific TMU control method
* @tmu_read: SoC specific TMU temperature read method
struct regulator *regulator;
struct thermal_zone_device *tzd;
unsigned int ntrip;
+ bool enabled;
int (*tmu_initialize)(struct platform_device *pdev);
void (*tmu_control)(struct platform_device *pdev, bool on);
mutex_lock(&data->lock);
clk_enable(data->clk);
data->tmu_control(pdev, on);
+ data->enabled = on;
clk_disable(data->clk);
mutex_unlock(&data->lock);
}
static int exynos_get_temp(void *p, int *temp)
{
struct exynos_tmu_data *data = p;
+ int value, ret = 0;
- if (!data || !data->tmu_read)
+ if (!data || !data->tmu_read || !data->enabled)
return -EINVAL;
mutex_lock(&data->lock);
clk_enable(data->clk);
- *temp = code_to_temp(data, data->tmu_read(data)) * MCELSIUS;
+ value = data->tmu_read(data);
+ if (value < 0)
+ ret = value;
+ else
+ *temp = code_to_temp(data, value) * MCELSIUS;
clk_disable(data->clk);
mutex_unlock(&data->lock);
- return 0;
+ return ret;
}
#ifdef CONFIG_THERMAL_EMULATION
struct mutex mutex;
/* Link layer */
+ int mode;
+#define DLCI_MODE_ABM 0 /* Normal Asynchronous Balanced Mode */
+#define DLCI_MODE_ADM 1 /* Asynchronous Disconnected Mode */
spinlock_t lock; /* Protects the internal state */
struct timer_list t1; /* Retransmit timer for SABM and UA */
int retries;
ctrl->data = data;
ctrl->len = clen;
gsm->pending_cmd = ctrl;
- gsm->cretries = gsm->n2;
+
+ /* If DLCI0 is in ADM mode skip retries, it won't respond */
+ if (gsm->dlci[0]->mode == DLCI_MODE_ADM)
+ gsm->cretries = 1;
+ else
+ gsm->cretries = gsm->n2;
+
mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100);
gsm_control_transmit(gsm, ctrl);
spin_unlock_irqrestore(&gsm->control_lock, flags);
if (debug & 8)
pr_info("DLCI %d opening in ADM mode.\n",
dlci->addr);
+ dlci->mode = DLCI_MODE_ADM;
gsm_dlci_open(dlci);
} else {
gsm_dlci_close(dlci);
static int gsm_carrier_raised(struct tty_port *port)
{
struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port);
+ struct gsm_mux *gsm = dlci->gsm;
+
/* Not yet open so no carrier info */
if (dlci->state != DLCI_OPEN)
return 0;
if (debug & 2)
return 1;
+
+ /*
+ * Basic mode with control channel in ADM mode may not respond
+ * to CMD_MSC at all and modem_rx is empty.
+ */
+ if (gsm->encoding == 0 && gsm->dlci[0]->mode == DLCI_MODE_ADM &&
+ !dlci->modem_rx)
+ return 1;
+
return dlci->modem_rx & TIOCM_CD;
}
*/
int __init setup_earlycon(char *buf)
{
- const struct earlycon_id *match;
+ const struct earlycon_id **p_match;
if (!buf || !buf[0])
return -EINVAL;
if (early_con.flags & CON_ENABLED)
return -EALREADY;
- for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+ for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+ p_match++) {
+ const struct earlycon_id *match = *p_match;
size_t len = strlen(match->name);
if (strncmp(buf, match->name, len))
* differ from the value that was last written. As it only
* clears after being set, reread conditionally.
*/
- if (sport->ucr2 & UCR2_SRST)
+ if (!(sport->ucr2 & UCR2_SRST))
sport->ucr2 = readl(sport->port.membase + offset);
return sport->ucr2;
break;
rs485conf->flags &= ~SER_RS485_ENABLED;
if (rs485conf->flags & SER_RS485_ENABLED) {
+ /* Enable receiver if low-active RTS signal is requested */
+ if (sport->have_rtscts && !sport->have_rtsgpio &&
+ !(rs485conf->flags & SER_RS485_RTS_ON_SEND))
+ rs485conf->flags |= SER_RS485_RX_DURING_TX;
+
/* disable transmitter */
ucr2 = imx_uart_readl(sport, UCR2);
if (rs485conf->flags & SER_RS485_RTS_AFTER_SEND)
(!sport->have_rtscts && !sport->have_rtsgpio))
dev_err(&pdev->dev, "no RTS control, disabling rs485\n");
+ /*
+ * If using the i.MX UART RTS/CTS control then the RTS (CTS_B)
+ * signal cannot be set low during transmission in case the
+ * receiver is off (limitation of the i.MX UART IP).
+ */
+ if (sport->port.rs485.flags & SER_RS485_ENABLED &&
+ sport->have_rtscts && !sport->have_rtsgpio &&
+ (!(sport->port.rs485.flags & SER_RS485_RTS_ON_SEND) &&
+ !(sport->port.rs485.flags & SER_RS485_RX_DURING_TX)))
+ dev_err(&pdev->dev,
+ "low-active RTS not possible when receiver is off, enabling receiver\n");
+
imx_uart_rs485_config(&sport->port, &sport->port.rs485);
/* Disable interrupts before requesting them */
termios->c_iflag |= old->c_iflag & ~(INPCK | IGNPAR);
termios->c_cflag &= CREAD | CBAUD;
termios->c_cflag |= old->c_cflag & ~(CREAD | CBAUD);
- termios->c_lflag = old->c_lflag;
}
spin_unlock_irqrestore(&port->lock, flags);
struct qcom_geni_serial_port *port;
struct uart_port *uport;
struct resource *res;
+ int irq;
if (pdev->dev.of_node)
line = of_alias_get_id(pdev->dev.of_node, "serial");
port->rx_fifo_depth = DEF_FIFO_DEPTH_WORDS;
port->tx_fifo_width = DEF_FIFO_WIDTH_BITS;
- uport->irq = platform_get_irq(pdev, 0);
- if (uport->irq < 0) {
- dev_err(&pdev->dev, "Failed to get IRQ %d\n", uport->irq);
- return uport->irq;
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "Failed to get IRQ %d\n", irq);
+ return irq;
}
+ uport->irq = irq;
uport->private_data = &qcom_geni_console_driver;
platform_set_drvdata(pdev, port);
/* only set baud if specified on command line - otherwise
* assume it has been initialized by a boot loader.
*/
- if (device->baud) {
+ if (port->uartclk && device->baud) {
u32 cd = 0, bdiv = 0;
u32 mr;
int div8;
kref_init(&tty->kref);
tty->magic = TTY_MAGIC;
- tty_ldisc_init(tty);
+ if (tty_ldisc_init(tty)) {
+ kfree(tty);
+ return NULL;
+ }
tty->session = NULL;
tty->pgrp = NULL;
mutex_init(&tty->legacy_mutex);
return ERR_CAST(ldops);
}
- ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL);
- if (ld == NULL) {
- put_ldops(ldops);
- return ERR_PTR(-ENOMEM);
- }
-
+ /*
+ * There is no way to handle allocation failure of only 16 bytes.
+ * Let's simplify error handling and save more memory.
+ */
+ ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL | __GFP_NOFAIL);
ld->ops = ldops;
ld->tty = tty;
static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
{
/* There is an outstanding reference here so this is safe */
- old = tty_ldisc_get(tty, old->ops->num);
- WARN_ON(IS_ERR(old));
- tty->ldisc = old;
- tty_set_termios_ldisc(tty, old->ops->num);
- if (tty_ldisc_open(tty, old) < 0) {
- tty_ldisc_put(old);
+ if (tty_ldisc_failto(tty, old->ops->num) < 0) {
+ const char *name = tty_name(tty);
+
+ pr_warn("Falling back ldisc for %s.\n", name);
/* The traditional behaviour is to fall back to N_TTY, we
want to avoid falling back to N_NULL unless we have no
choice to avoid the risk of breaking anything */
if (tty_ldisc_failto(tty, N_TTY) < 0 &&
tty_ldisc_failto(tty, N_NULL) < 0)
- panic("Couldn't open N_NULL ldisc for %s.",
- tty_name(tty));
+ panic("Couldn't open N_NULL ldisc for %s.", name);
}
}
* the tty structure is not completely set up when this call is made.
*/
-void tty_ldisc_init(struct tty_struct *tty)
+int tty_ldisc_init(struct tty_struct *tty)
{
struct tty_ldisc *ld = tty_ldisc_get(tty, N_TTY);
if (IS_ERR(ld))
- panic("n_tty: init_tty");
+ return PTR_ERR(ld);
tty->ldisc = ld;
+ return 0;
}
/**
* # echo -n "ed963694-e847-4b2a-85af-bc9cfc11d6f3" \
* > /sys/bus/vmbus/drivers/uio_hv_generic/bind
*/
-
+#define DEBUG 1
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/device.h>
*/
static void hv_uio_channel_cb(void *context)
{
- struct hv_uio_private_data *pdata = context;
- struct hv_device *dev = pdata->device;
+ struct vmbus_channel *chan = context;
+ struct hv_device *hv_dev = chan->device_obj;
+ struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
- dev->channel->inbound.ring_buffer->interrupt_mask = 1;
+ chan->inbound.ring_buffer->interrupt_mask = 1;
virt_mb();
uio_event_notify(&pdata->info);
uio_event_notify(&pdata->info);
}
-/*
- * Handle fault when looking for sub channel ring buffer
- * Subchannel ring buffer is same as resource 0 which is main ring buffer
- * This is derived from uio_vma_fault
+/* Sysfs API to allow mmap of the ring buffers
+ * The ring buffer is allocated as contiguous memory by vmbus_open
*/
-static int hv_uio_vma_fault(struct vm_fault *vmf)
-{
- struct vm_area_struct *vma = vmf->vma;
- void *ring_buffer = vma->vm_private_data;
- struct page *page;
- void *addr;
-
- addr = ring_buffer + (vmf->pgoff << PAGE_SHIFT);
- page = virt_to_page(addr);
- get_page(page);
- vmf->page = page;
- return 0;
-}
-
-static const struct vm_operations_struct hv_uio_vm_ops = {
- .fault = hv_uio_vma_fault,
-};
-
-/* Sysfs API to allow mmap of the ring buffers */
static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr,
struct vm_area_struct *vma)
{
struct vmbus_channel *channel
= container_of(kobj, struct vmbus_channel, kobj);
- unsigned long requested_pages, actual_pages;
-
- if (vma->vm_end < vma->vm_start)
- return -EINVAL;
-
- /* only allow 0 for now */
- if (vma->vm_pgoff > 0)
- return -EINVAL;
+ struct hv_device *dev = channel->primary_channel->device_obj;
+ u16 q_idx = channel->offermsg.offer.sub_channel_index;
- requested_pages = vma_pages(vma);
- actual_pages = 2 * HV_RING_SIZE;
- if (requested_pages > actual_pages)
- return -EINVAL;
+ dev_dbg(&dev->device, "mmap channel %u pages %#lx at %#lx\n",
+ q_idx, vma_pages(vma), vma->vm_pgoff);
- vma->vm_private_data = channel->ringbuffer_pages;
- vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
- vma->vm_ops = &hv_uio_vm_ops;
- return 0;
+ return vm_iomap_memory(vma, virt_to_phys(channel->ringbuffer_pages),
+ channel->ringbuffer_pagecount << PAGE_SHIFT);
}
-static struct bin_attribute ring_buffer_bin_attr __ro_after_init = {
+static const struct bin_attribute ring_buffer_bin_attr = {
.attr = {
.name = "ring",
.mode = 0600,
- /* size is set at init time */
},
+ .size = 2 * HV_RING_SIZE * PAGE_SIZE,
.mmap = hv_uio_ring_mmap,
};
-/* Callback from VMBUS subystem when new channel created. */
+/* Callback from VMBUS subsystem when new channel created. */
static void
hv_uio_new_channel(struct vmbus_channel *new_sc)
{
struct hv_device *hv_dev = new_sc->primary_channel->device_obj;
struct device *device = &hv_dev->device;
- struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
const size_t ring_bytes = HV_RING_SIZE * PAGE_SIZE;
int ret;
/* Create host communication ring */
ret = vmbus_open(new_sc, ring_bytes, ring_bytes, NULL, 0,
- hv_uio_channel_cb, pdata);
+ hv_uio_channel_cb, new_sc);
if (ret) {
dev_err(device, "vmbus_open subchannel failed: %d\n", ret);
return;
ret = vmbus_open(dev->channel, HV_RING_SIZE * PAGE_SIZE,
HV_RING_SIZE * PAGE_SIZE, NULL, 0,
- hv_uio_channel_cb, pdata);
+ hv_uio_channel_cb, dev->channel);
if (ret)
goto fail;
vmbus_set_chn_rescind_callback(dev->channel, hv_uio_rescind);
vmbus_set_sc_create_callback(dev->channel, hv_uio_new_channel);
+ ret = sysfs_create_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+ if (ret)
+ dev_notice(&dev->device,
+ "sysfs create ring bin file failed; %d\n", ret);
+
hv_set_drvdata(dev, pdata);
return 0;
config USB_ROLE_SWITCH
tristate
+ select USB_COMMON
endif # USB_SUPPORT
static const unsigned short high_speed_maxpacket_maxes[4] = {
[USB_ENDPOINT_XFER_CONTROL] = 64,
[USB_ENDPOINT_XFER_ISOC] = 1024,
- [USB_ENDPOINT_XFER_BULK] = 512,
+
+ /* Bulk should be 512, but some devices use 1024: we will warn below */
+ [USB_ENDPOINT_XFER_BULK] = 1024,
[USB_ENDPOINT_XFER_INT] = 1024,
};
static const unsigned short super_speed_maxpacket_maxes[4] = {
hcd->state = HC_STATE_SUSPENDED;
if (!PMSG_IS_AUTO(msg))
- usb_phy_roothub_power_off(hcd->phy_roothub);
+ usb_phy_roothub_suspend(hcd->self.sysdev,
+ hcd->phy_roothub);
/* Did we race with a root-hub wakeup event? */
if (rhdev->do_remote_wakeup) {
}
if (!PMSG_IS_AUTO(msg)) {
- status = usb_phy_roothub_power_on(hcd->phy_roothub);
+ status = usb_phy_roothub_resume(hcd->self.sysdev,
+ hcd->phy_roothub);
if (status)
return status;
}
}
} else {
hcd->state = old_state;
- usb_phy_roothub_power_off(hcd->phy_roothub);
+ usb_phy_roothub_suspend(hcd->self.sysdev, hcd->phy_roothub);
dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
"resume", status);
if (status != -ESHUTDOWN)
spin_lock_irqsave (&hcd_root_hub_lock, flags);
if (hcd->rh_registered) {
+ pm_wakeup_event(&hcd->self.root_hub->dev, 0);
set_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
queue_work(pm_wq, &hcd->wakeup_work);
}
}
if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) {
- hcd->phy_roothub = usb_phy_roothub_init(hcd->self.sysdev);
+ hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev);
if (IS_ERR(hcd->phy_roothub)) {
retval = PTR_ERR(hcd->phy_roothub);
- goto err_phy_roothub_init;
+ goto err_phy_roothub_alloc;
}
+ retval = usb_phy_roothub_init(hcd->phy_roothub);
+ if (retval)
+ goto err_phy_roothub_alloc;
+
retval = usb_phy_roothub_power_on(hcd->phy_roothub);
if (retval)
goto err_usb_phy_roothub_power_on;
usb_phy_roothub_power_off(hcd->phy_roothub);
err_usb_phy_roothub_power_on:
usb_phy_roothub_exit(hcd->phy_roothub);
-err_phy_roothub_init:
+err_phy_roothub_alloc:
if (hcd->remove_phy && hcd->usb_phy) {
usb_phy_shutdown(hcd->usb_phy);
usb_put_phy(hcd->usb_phy);
unsigned int portnum)
{
struct usb_hub *hub;
+ struct usb_port *port_dev;
if (!hdev)
return;
hub = usb_hub_to_struct_hub(hdev);
if (hub) {
+ port_dev = hub->ports[portnum - 1];
+ if (port_dev && port_dev->child)
+ pm_wakeup_event(&port_dev->child->dev, 0);
+
set_bit(portnum, hub->wakeup_bits);
kick_hub_wq(hub);
}
/* Skip the initial Clear-Suspend step for a remote wakeup */
status = hub_port_status(hub, port1, &portstatus, &portchange);
- if (status == 0 && !port_is_suspended(hub, portstatus))
+ if (status == 0 && !port_is_suspended(hub, portstatus)) {
+ if (portchange & USB_PORT_STAT_C_SUSPEND)
+ pm_wakeup_event(&udev->dev, 0);
goto SuspendCleared;
+ }
/* see 7.1.7.7; affects power usage, but not budgeting */
if (hub_is_superspeed(hub->hdev))
struct list_head list;
};
-static struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
-{
- struct usb_phy_roothub *roothub_entry;
-
- roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
- if (!roothub_entry)
- return ERR_PTR(-ENOMEM);
-
- INIT_LIST_HEAD(&roothub_entry->list);
-
- return roothub_entry;
-}
-
static int usb_phy_roothub_add_phy(struct device *dev, int index,
struct list_head *list)
{
return PTR_ERR(phy);
}
- roothub_entry = usb_phy_roothub_alloc(dev);
- if (IS_ERR(roothub_entry))
- return PTR_ERR(roothub_entry);
+ roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
+ if (!roothub_entry)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&roothub_entry->list);
roothub_entry->phy = phy;
return 0;
}
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev)
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
{
struct usb_phy_roothub *phy_roothub;
- struct usb_phy_roothub *roothub_entry;
- struct list_head *head;
int i, num_phys, err;
+ if (!IS_ENABLED(CONFIG_GENERIC_PHY))
+ return NULL;
+
num_phys = of_count_phandle_with_args(dev->of_node, "phys",
"#phy-cells");
if (num_phys <= 0)
return NULL;
- phy_roothub = usb_phy_roothub_alloc(dev);
- if (IS_ERR(phy_roothub))
- return phy_roothub;
+ phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL);
+ if (!phy_roothub)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&phy_roothub->list);
for (i = 0; i < num_phys; i++) {
err = usb_phy_roothub_add_phy(dev, i, &phy_roothub->list);
if (err)
- goto err_out;
+ return ERR_PTR(err);
}
+ return phy_roothub;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub)
+{
+ struct usb_phy_roothub *roothub_entry;
+ struct list_head *head;
+ int err;
+
+ if (!phy_roothub)
+ return 0;
+
head = &phy_roothub->list;
list_for_each_entry(roothub_entry, head, list) {
goto err_exit_phys;
}
- return phy_roothub;
+ return 0;
err_exit_phys:
list_for_each_entry_continue_reverse(roothub_entry, head, list)
phy_exit(roothub_entry->phy);
-err_out:
- return ERR_PTR(err);
+ return err;
}
EXPORT_SYMBOL_GPL(usb_phy_roothub_init);
list_for_each_entry(roothub_entry, head, list) {
err = phy_exit(roothub_entry->phy);
if (err)
- ret = ret;
+ ret = err;
}
return ret;
phy_power_off(roothub_entry->phy);
}
EXPORT_SYMBOL_GPL(usb_phy_roothub_power_off);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub)
+{
+ usb_phy_roothub_power_off(phy_roothub);
+
+ /* keep the PHYs initialized so the device can wake up the system */
+ if (device_may_wakeup(controller_dev))
+ return 0;
+
+ return usb_phy_roothub_exit(phy_roothub);
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_suspend);
+
+int usb_phy_roothub_resume(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub)
+{
+ int err;
+
+ /* if the device can't wake up the system _exit was called */
+ if (!device_may_wakeup(controller_dev)) {
+ err = usb_phy_roothub_init(phy_roothub);
+ if (err)
+ return err;
+ }
+
+ err = usb_phy_roothub_power_on(phy_roothub);
+
+ /* undo _init if _power_on failed */
+ if (err && !device_may_wakeup(controller_dev))
+ usb_phy_roothub_exit(phy_roothub);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_resume);
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * USB roothub wrapper
+ *
+ * Copyright (C) 2018 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+ */
+
+#ifndef __USB_CORE_PHY_H_
+#define __USB_CORE_PHY_H_
+
+struct device;
struct usb_phy_roothub;
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev);
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub);
int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub);
int usb_phy_roothub_power_on(struct usb_phy_roothub *phy_roothub);
void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub);
+int usb_phy_roothub_resume(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub);
+
+#endif /* __USB_CORE_PHY_H_ */
{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
+ /* HP v222w 16GB Mini USB Drive */
+ { USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Creative SB Audigy 2 NX */
{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
/* DWC OTG HW Release versions */
#define DWC2_CORE_REV_2_71a 0x4f54271a
+#define DWC2_CORE_REV_2_72a 0x4f54272a
#define DWC2_CORE_REV_2_80a 0x4f54280a
#define DWC2_CORE_REV_2_90a 0x4f54290a
#define DWC2_CORE_REV_2_91a 0x4f54291a
#define DWC2_CORE_REV_2_94a 0x4f54294a
#define DWC2_CORE_REV_3_00a 0x4f54300a
#define DWC2_CORE_REV_3_10a 0x4f54310a
+#define DWC2_CORE_REV_4_00a 0x4f54400a
#define DWC2_FS_IOT_REV_1_00a 0x5531100a
#define DWC2_HS_IOT_REV_1_00a 0x5532100a
if (index && !hs_ep->isochronous)
epctrl |= DXEPCTL_SETD0PID;
+ /* WA for Full speed ISOC IN in DDMA mode.
+ * By Clear NAK status of EP, core will send ZLP
+ * to IN token and assert NAK interrupt relying
+ * on TxFIFO status only
+ */
+
+ if (hsotg->gadget.speed == USB_SPEED_FULL &&
+ hs_ep->isochronous && dir_in) {
+ /* The WA applies only to core versions from 2.72a
+ * to 4.00a (including both). Also for FS_IOT_1.00a
+ * and HS_IOT_1.00a.
+ */
+ u32 gsnpsid = dwc2_readl(hsotg->regs + GSNPSID);
+
+ if ((gsnpsid >= DWC2_CORE_REV_2_72a &&
+ gsnpsid <= DWC2_CORE_REV_4_00a) ||
+ gsnpsid == DWC2_FS_IOT_REV_1_00a ||
+ gsnpsid == DWC2_HS_IOT_REV_1_00a)
+ epctrl |= DXEPCTL_CNAK;
+ }
+
dev_dbg(hsotg->dev, "%s: write DxEPCTL=0x%08x\n",
__func__, epctrl);
static int dwc2_vbus_supply_init(struct dwc2_hsotg *hsotg)
{
+ int ret;
+
hsotg->vbus_supply = devm_regulator_get_optional(hsotg->dev, "vbus");
- if (IS_ERR(hsotg->vbus_supply))
- return 0;
+ if (IS_ERR(hsotg->vbus_supply)) {
+ ret = PTR_ERR(hsotg->vbus_supply);
+ hsotg->vbus_supply = NULL;
+ return ret == -ENODEV ? 0 : ret;
+ }
return regulator_enable(hsotg->vbus_supply);
}
spin_unlock_irqrestore(&hsotg->lock, flags);
- dwc2_vbus_supply_init(hsotg);
-
- return 0;
+ return dwc2_vbus_supply_init(hsotg);
}
/*
goto err;
glue = devm_kzalloc(dev, sizeof(*glue), GFP_KERNEL);
- if (!glue)
+ if (!glue) {
+ ret = -ENOMEM;
goto err;
+ }
ret = platform_device_add(dwc2);
if (ret) {
dwc3_ep_inc_trb(&dep->trb_dequeue);
}
-void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
+static void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
struct dwc3_request *req, int status)
{
struct dwc3 *dwc = dep->dwc;
dwc->lock);
if (!r->trb)
- goto out1;
+ goto out0;
if (r->num_pending_sgs) {
struct dwc3_trb *trb;
netif_wake_queue(dev);
}
-static int pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct phonet_port *port = netdev_priv(dev);
struct f_phonet *fp;
if (!qh)
goto done;
qh->hw = (struct ehci_qh_hw *)
- dma_pool_zalloc(ehci->qh_pool, flags, &dma);
+ dma_pool_alloc(ehci->qh_pool, flags, &dma);
if (!qh->hw)
goto fail;
+ memset(qh->hw, 0, sizeof *qh->hw);
qh->qh_dma = dma;
// INIT_LIST_HEAD (&qh->qh_list);
INIT_LIST_HEAD (&qh->qtd_list);
} else {
alloc_itd:
spin_unlock_irqrestore(&ehci->lock, flags);
- itd = dma_pool_zalloc(ehci->itd_pool, mem_flags,
+ itd = dma_pool_alloc(ehci->itd_pool, mem_flags,
&itd_dma);
spin_lock_irqsave(&ehci->lock, flags);
if (!itd) {
}
}
+ memset(itd, 0, sizeof(*itd));
itd->itd_dma = itd_dma;
itd->frame = NO_FRAME;
list_add(&itd->itd_list, &sched->td_list);
} else {
alloc_sitd:
spin_unlock_irqrestore(&ehci->lock, flags);
- sitd = dma_pool_zalloc(ehci->sitd_pool, mem_flags,
+ sitd = dma_pool_alloc(ehci->sitd_pool, mem_flags,
&sitd_dma);
spin_lock_irqsave(&ehci->lock, flags);
if (!sitd) {
}
}
+ memset(sitd, 0, sizeof(*sitd));
sitd->sitd_dma = sitd_dma;
sitd->frame = NO_FRAME;
list_add(&sitd->sitd_list, &iso_sched->td_list);
void xhci_dbc_tty_unregister_driver(void)
{
- tty_unregister_driver(dbc_tty_driver);
- put_tty_driver(dbc_tty_driver);
- dbc_tty_driver = NULL;
+ if (dbc_tty_driver) {
+ tty_unregister_driver(dbc_tty_driver);
+ put_tty_driver(dbc_tty_driver);
+ dbc_tty_driver = NULL;
+ }
}
static void dbc_rx_push(unsigned long _port)
slot_id = 0;
for (i = 0; i < MAX_HC_SLOTS; i++) {
- if (!xhci->devs[i])
+ if (!xhci->devs[i] || !xhci->devs[i]->udev)
continue;
speed = xhci->devs[i]->udev->speed;
if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3))
if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
xhci->quirks |= XHCI_AMD_PLL_FIX;
- if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x43bb)
+ if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+ (pdev->device == 0x15e0 ||
+ pdev->device == 0x15e1 ||
+ pdev->device == 0x43bb))
xhci->quirks |= XHCI_SUSPEND_DELAY;
if (pdev->vendor == PCI_VENDOR_ID_AMD)
struct resource *res;
struct usb_hcd *hcd;
struct clk *clk;
+ struct clk *reg_clk;
int ret;
int irq;
hcd->rsrc_len = resource_size(res);
/*
- * Not all platforms have a clk so it is not an error if the
- * clock does not exists.
+ * Not all platforms have clks so it is not an error if the
+ * clock do not exist.
*/
+ reg_clk = devm_clk_get(&pdev->dev, "reg");
+ if (!IS_ERR(reg_clk)) {
+ ret = clk_prepare_enable(reg_clk);
+ if (ret)
+ goto put_hcd;
+ } else if (PTR_ERR(reg_clk) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto put_hcd;
+ }
+
clk = devm_clk_get(&pdev->dev, NULL);
if (!IS_ERR(clk)) {
ret = clk_prepare_enable(clk);
if (ret)
- goto put_hcd;
+ goto disable_reg_clk;
} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
ret = -EPROBE_DEFER;
- goto put_hcd;
+ goto disable_reg_clk;
}
xhci = hcd_to_xhci(hcd);
device_wakeup_enable(hcd->self.controller);
xhci->clk = clk;
+ xhci->reg_clk = reg_clk;
xhci->main_hcd = hcd;
xhci->shared_hcd = __usb_create_hcd(driver, sysdev, &pdev->dev,
dev_name(&pdev->dev), hcd);
usb_put_hcd(xhci->shared_hcd);
disable_clk:
- if (!IS_ERR(clk))
- clk_disable_unprepare(clk);
+ clk_disable_unprepare(clk);
+
+disable_reg_clk:
+ clk_disable_unprepare(reg_clk);
put_hcd:
usb_put_hcd(hcd);
struct usb_hcd *hcd = platform_get_drvdata(dev);
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct clk *clk = xhci->clk;
+ struct clk *reg_clk = xhci->reg_clk;
xhci->xhc_state |= XHCI_STATE_REMOVING;
usb_remove_hcd(hcd);
usb_put_hcd(xhci->shared_hcd);
- if (!IS_ERR(clk))
- clk_disable_unprepare(clk);
+ clk_disable_unprepare(clk);
+ clk_disable_unprepare(reg_clk);
usb_put_hcd(hcd);
pm_runtime_set_suspended(&dev->dev);
static struct platform_driver usb_xhci_driver = {
.probe = xhci_plat_probe,
.remove = xhci_plat_remove,
- .shutdown = usb_hcd_platform_shutdown,
.driver = {
.name = "xhci-hcd",
.pm = &xhci_plat_pm_ops,
del_timer_sync(&virt_dev->eps[i].stop_cmd_timer);
}
xhci_debugfs_remove_slot(xhci, udev->slot_id);
+ virt_dev->udev = NULL;
ret = xhci_disable_slot(xhci, udev->slot_id);
if (ret)
xhci_free_virt_device(xhci, udev->slot_id);
int page_shift;
/* msi-x vectors */
int msix_count;
- /* optional clock */
+ /* optional clocks */
struct clk *clk;
+ struct clk *reg_clk;
/* data structures */
struct xhci_device_context_array *dcbaa;
struct xhci_ring *cmd_ring;
if (!rev)
return -ENODEV;
- usb_phy_init(musb->xceiv);
if (IS_ERR(musb->phy)) {
musb->phy = NULL;
} else {
struct dsps_glue *glue = dev_get_drvdata(dev->parent);
del_timer_sync(&musb->dev_timer);
- usb_phy_shutdown(musb->xceiv);
phy_power_off(musb->phy);
phy_exit(musb->phy);
debugfs_remove_recursive(glue->dbgfs_root);
req = next_request(musb_ep);
request = &req->request;
- trace_musb_req_tx(req);
csr = musb_readw(epio, MUSB_TXCSR);
musb_dbg(musb, "<== %s, txcsr %04x", musb_ep->end_point.name, csr);
u8 is_dma = 0;
bool short_packet = false;
+ trace_musb_req_tx(req);
+
if (dma && (csr & MUSB_TXCSR_DMAENAB)) {
is_dma = 1;
csr |= MUSB_TXCSR_P_WZC_BITS;
/* set tx_reinit and schedule the next qh */
ep->tx_reinit = 1;
}
- musb_start_urb(musb, is_in, next_qh);
+
+ if (next_qh)
+ musb_start_urb(musb, is_in, next_qh);
}
}
{
struct musb *musb = hcd_to_musb(hcd);
u8 devctl;
+ int ret;
- musb_port_suspend(musb, true);
+ ret = musb_port_suspend(musb, true);
+ if (ret)
+ return ret;
if (!is_host_active(musb))
return 0;
hcd->self.otg_port = 1;
musb->xceiv->otg->host = &hcd->self;
hcd->power_budget = 2 * (power_budget ? : 250);
+ hcd->skip_phy_initialization = 1;
ret = usb_add_hcd(hcd, 0, 0);
if (ret < 0)
extern void musb_root_disconnect(struct musb *musb);
extern void musb_host_resume_root_hub(struct musb *musb);
extern void musb_host_poke_root_hub(struct musb *musb);
-extern void musb_port_suspend(struct musb *musb, bool do_suspend);
+extern int musb_port_suspend(struct musb *musb, bool do_suspend);
extern void musb_port_reset(struct musb *musb, bool do_reset);
extern void musb_host_finish_resume(struct work_struct *work);
#else
static inline void musb_host_resume_root_hub(struct musb *musb) {}
static inline void musb_host_poll_rh_status(struct musb *musb) {}
static inline void musb_host_poke_root_hub(struct musb *musb) {}
-static inline void musb_port_suspend(struct musb *musb, bool do_suspend) {}
+static inline int musb_port_suspend(struct musb *musb, bool do_suspend)
+{
+ return 0;
+}
static inline void musb_port_reset(struct musb *musb, bool do_reset) {}
static inline void musb_host_finish_resume(struct work_struct *work) {}
#endif
spin_unlock_irqrestore(&musb->lock, flags);
}
-void musb_port_suspend(struct musb *musb, bool do_suspend)
+int musb_port_suspend(struct musb *musb, bool do_suspend)
{
struct usb_otg *otg = musb->xceiv->otg;
u8 power;
void __iomem *mbase = musb->mregs;
if (!is_host_active(musb))
- return;
+ return 0;
/* NOTE: this doesn't necessarily put PHY into low power mode,
* turning off its clock; that's a function of PHY integration and
if (do_suspend) {
int retries = 10000;
- power &= ~MUSB_POWER_RESUME;
- power |= MUSB_POWER_SUSPENDM;
- musb_writeb(mbase, MUSB_POWER, power);
+ if (power & MUSB_POWER_RESUME)
+ return -EBUSY;
- /* Needed for OPT A tests */
- power = musb_readb(mbase, MUSB_POWER);
- while (power & MUSB_POWER_SUSPENDM) {
+ if (!(power & MUSB_POWER_SUSPENDM)) {
+ power |= MUSB_POWER_SUSPENDM;
+ musb_writeb(mbase, MUSB_POWER, power);
+
+ /* Needed for OPT A tests */
power = musb_readb(mbase, MUSB_POWER);
- if (retries-- < 1)
- break;
+ while (power & MUSB_POWER_SUSPENDM) {
+ power = musb_readb(mbase, MUSB_POWER);
+ if (retries-- < 1)
+ break;
+ }
}
musb_dbg(musb, "Root port suspended, power %02x", power);
schedule_delayed_work(&musb->finish_resume_work,
msecs_to_jiffies(USB_RESUME_TIMEOUT));
}
+ return 0;
}
void musb_port_reset(struct musb *musb, bool do_reset)
- Fundamental Software dongle.
- Google USB serial devices
- HP4x calculators
+ - Libtransistor USB console
- a number of Motorola phones
- Motorola Tetra devices
- Novatel Wireless GPS receivers
{ USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */
{ USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */
{ USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */
+ { USB_DEVICE(0x3923, 0x7A0B) }, /* National Instruments USB Serial Console */
{ USB_DEVICE(0x413C, 0x9500) }, /* DW700 GPS USB interface */
{ } /* Terminating Entry */
};
return ftdi_jtag_probe(serial);
if (udev->product &&
- (!strcmp(udev->product, "BeagleBone/XDS100V2") ||
+ (!strcmp(udev->product, "Arrow USB Blaster") ||
+ !strcmp(udev->product, "BeagleBone/XDS100V2") ||
!strcmp(udev->product, "SNAP Connect E10")))
return ftdi_jtag_probe(serial);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These u-blox products use Qualcomm's vendor ID */
+#define UBLOX_PRODUCT_R410M 0x90b2
/* These Yuga products use Qualcomm's vendor ID */
#define YUGA_PRODUCT_CLM920_NC5 0x9625
/* Yuga products use Qualcomm vendor ID */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
.driver_info = RSVD(1) | RSVD(4) },
+ /* u-blox products using Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
+ .driver_info = RSVD(1) | RSVD(3) },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = RSVD(4) },
0x01) }
DEVICE(google, GOOGLE_IDS);
+/* Libtransistor USB console */
+#define LIBTRANSISTOR_IDS() \
+ { USB_DEVICE(0x1209, 0x8b00) }
+DEVICE(libtransistor, LIBTRANSISTOR_IDS);
+
/* ViVOpay USB Serial Driver */
#define VIVOPAY_IDS() \
{ USB_DEVICE(0x1d5f, 0x1004) } /* ViVOpay 8800 */
&funsoft_device,
&flashloader_device,
&google_device,
+ &libtransistor_device,
&vivopay_device,
&moto_modem_device,
&motorola_tetra_device,
FUNSOFT_IDS(),
FLASHLOADER_IDS(),
GOOGLE_IDS(),
+ LIBTRANSISTOR_IDS(),
VIVOPAY_IDS(),
MOTO_IDS(),
MOTOROLA_TETRA_IDS(),
goto exit;
}
- if (retval == sizeof(*connection_info)) {
- connection_info = (struct visor_connection_info *)
- transfer_buffer;
-
- num_ports = le16_to_cpu(connection_info->num_ports);
- for (i = 0; i < num_ports; ++i) {
- switch (
- connection_info->connections[i].port_function_id) {
- case VISOR_FUNCTION_GENERIC:
- string = "Generic";
- break;
- case VISOR_FUNCTION_DEBUGGER:
- string = "Debugger";
- break;
- case VISOR_FUNCTION_HOTSYNC:
- string = "HotSync";
- break;
- case VISOR_FUNCTION_CONSOLE:
- string = "Console";
- break;
- case VISOR_FUNCTION_REMOTE_FILE_SYS:
- string = "Remote File System";
- break;
- default:
- string = "unknown";
- break;
- }
- dev_info(dev, "%s: port %d, is for %s use\n",
- serial->type->description,
- connection_info->connections[i].port, string);
- }
+ if (retval != sizeof(*connection_info)) {
+ dev_err(dev, "Invalid connection information received from device\n");
+ retval = -ENODEV;
+ goto exit;
}
- /*
- * Handle devices that report invalid stuff here.
- */
+
+ connection_info = (struct visor_connection_info *)transfer_buffer;
+
+ num_ports = le16_to_cpu(connection_info->num_ports);
+
+ /* Handle devices that report invalid stuff here. */
if (num_ports == 0 || num_ports > 2) {
dev_warn(dev, "%s: No valid connect info available\n",
serial->type->description);
num_ports = 2;
}
+ for (i = 0; i < num_ports; ++i) {
+ switch (connection_info->connections[i].port_function_id) {
+ case VISOR_FUNCTION_GENERIC:
+ string = "Generic";
+ break;
+ case VISOR_FUNCTION_DEBUGGER:
+ string = "Debugger";
+ break;
+ case VISOR_FUNCTION_HOTSYNC:
+ string = "HotSync";
+ break;
+ case VISOR_FUNCTION_CONSOLE:
+ string = "Console";
+ break;
+ case VISOR_FUNCTION_REMOTE_FILE_SYS:
+ string = "Remote File System";
+ break;
+ default:
+ string = "unknown";
+ break;
+ }
+ dev_info(dev, "%s: port %d, is for %s use\n",
+ serial->type->description,
+ connection_info->connections[i].port, string);
+ }
dev_info(dev, "%s: Number of ports: %d\n", serial->type->description,
num_ports);
for (i = 0; i < ARRAY_SIZE(port->port_altmode); i++)
typec_unregister_altmode(port->port_altmode[i]);
typec_unregister_port(port->typec_port);
+ usb_role_switch_put(port->role_sw);
tcpm_debugfs_exit(port);
destroy_workqueue(port->wq);
}
struct device *dev;
struct regmap *regmap;
struct mutex lock; /* device lock */
+ u8 i2c_protocol:1;
struct typec_port *port;
struct typec_partner *partner;
struct typec_capability typec_cap;
};
+static int
+tps6598x_block_read(struct tps6598x *tps, u8 reg, void *val, size_t len)
+{
+ u8 data[len + 1];
+ int ret;
+
+ if (!tps->i2c_protocol)
+ return regmap_raw_read(tps->regmap, reg, val, len);
+
+ ret = regmap_raw_read(tps->regmap, reg, data, sizeof(data));
+ if (ret)
+ return ret;
+
+ if (data[0] < len)
+ return -EIO;
+
+ memcpy(val, &data[1], len);
+ return 0;
+}
+
static inline int tps6598x_read16(struct tps6598x *tps, u8 reg, u16 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u16));
+ return tps6598x_block_read(tps, reg, val, sizeof(u16));
}
static inline int tps6598x_read32(struct tps6598x *tps, u8 reg, u32 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u32));
+ return tps6598x_block_read(tps, reg, val, sizeof(u32));
}
static inline int tps6598x_read64(struct tps6598x *tps, u8 reg, u64 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u64));
+ return tps6598x_block_read(tps, reg, val, sizeof(u64));
}
static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val)
struct tps6598x_rx_identity_reg id;
int ret;
- ret = regmap_raw_read(tps->regmap, TPS_REG_RX_IDENTITY_SOP,
- &id, sizeof(id));
+ ret = tps6598x_block_read(tps, TPS_REG_RX_IDENTITY_SOP,
+ &id, sizeof(id));
if (ret)
return ret;
} while (val);
if (out_len) {
- ret = regmap_raw_read(tps->regmap, TPS_REG_DATA1,
- out_data, out_len);
+ ret = tps6598x_block_read(tps, TPS_REG_DATA1,
+ out_data, out_len);
if (ret)
return ret;
val = out_data[0];
} else {
- ret = regmap_read(tps->regmap, TPS_REG_DATA1, &val);
+ ret = tps6598x_block_read(tps, TPS_REG_DATA1, &val, sizeof(u8));
if (ret)
return ret;
}
if (!vid)
return -ENODEV;
+ /*
+ * Checking can the adapter handle SMBus protocol. If it can not, the
+ * driver needs to take care of block reads separately.
+ *
+ * FIXME: Testing with I2C_FUNC_I2C. regmap-i2c uses I2C protocol
+ * unconditionally if the adapter has I2C_FUNC_I2C set.
+ */
+ if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+ tps->i2c_protocol = true;
+
ret = tps6598x_read32(tps, TPS_REG_STATUS, &status);
if (ret < 0)
return ret;
typec_ucsi-y := ucsi.o
-typec_ucsi-$(CONFIG_FTRACE) += trace.o
+typec_ucsi-$(CONFIG_TRACING) += trace.o
obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o
* difficult to estimate the time it takes for the system to process the command
* before it is actually passed to the PPM.
*/
-#define UCSI_TIMEOUT_MS 1000
+#define UCSI_TIMEOUT_MS 5000
/*
* UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests
struct stub_device *sdev;
struct usb_device *udev;
char shutdown_busid;
+ spinlock_t busid_lock;
};
/* stub_priv is allocated from stub_priv_cache */
/* stub_main.c */
struct bus_id_priv *get_busid_priv(const char *busid);
+void put_busid_priv(struct bus_id_priv *bid);
int del_match_busid(char *busid);
void stub_device_cleanup_urbs(struct stub_device *sdev);
struct stub_device *sdev = NULL;
const char *udev_busid = dev_name(&udev->dev);
struct bus_id_priv *busid_priv;
- int rc;
+ int rc = 0;
- dev_dbg(&udev->dev, "Enter\n");
+ dev_dbg(&udev->dev, "Enter probe\n");
/* check we should claim or not by busid_table */
busid_priv = get_busid_priv(udev_busid);
* other matched drivers by the driver core.
* See driver_probe_device() in driver/base/dd.c
*/
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) {
dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n",
udev_busid);
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
if (!strcmp(udev->bus->bus_name, "vhci_hcd")) {
"%s is attached on vhci_hcd... skip!\n",
udev_busid);
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
/* ok, this is my device */
sdev = stub_device_alloc(udev);
- if (!sdev)
- return -ENOMEM;
+ if (!sdev) {
+ rc = -ENOMEM;
+ goto call_put_busid_priv;
+ }
dev_info(&udev->dev,
"usbip-host: register new device (bus %u dev %u)\n",
}
busid_priv->status = STUB_BUSID_ALLOC;
- return 0;
+ rc = 0;
+ goto call_put_busid_priv;
+
err_files:
usb_hub_release_port(udev->parent, udev->portnum,
(struct usb_dev_state *) udev);
busid_priv->sdev = NULL;
stub_device_free(sdev);
+
+call_put_busid_priv:
+ put_busid_priv(busid_priv);
return rc;
}
struct bus_id_priv *busid_priv;
int rc;
- dev_dbg(&udev->dev, "Enter\n");
+ dev_dbg(&udev->dev, "Enter disconnect\n");
busid_priv = get_busid_priv(udev_busid);
if (!busid_priv) {
/* get stub_device */
if (!sdev) {
dev_err(&udev->dev, "could not get device");
- return;
+ goto call_put_busid_priv;
}
dev_set_drvdata(&udev->dev, NULL);
(struct usb_dev_state *) udev);
if (rc) {
dev_dbg(&udev->dev, "unable to release port\n");
- return;
+ goto call_put_busid_priv;
}
/* If usb reset is called from event handler */
if (usbip_in_eh(current))
- return;
+ goto call_put_busid_priv;
/* shutdown the current connection */
shutdown_busid(busid_priv);
busid_priv->sdev = NULL;
stub_device_free(sdev);
- if (busid_priv->status == STUB_BUSID_ALLOC) {
+ if (busid_priv->status == STUB_BUSID_ALLOC)
busid_priv->status = STUB_BUSID_ADDED;
- } else {
- busid_priv->status = STUB_BUSID_OTHER;
- del_match_busid((char *)udev_busid);
- }
+
+call_put_busid_priv:
+ put_busid_priv(busid_priv);
}
#ifdef CONFIG_PM
#define DRIVER_DESC "USB/IP Host Driver"
struct kmem_cache *stub_priv_cache;
+
/*
* busid_tables defines matching busids that usbip can grab. A user can change
* dynamically what device is locally used and what device is exported to a
static void init_busid_table(void)
{
+ int i;
+
/*
* This also sets the bus_table[i].status to
* STUB_BUSID_OTHER, which is 0.
memset(busid_table, 0, sizeof(busid_table));
spin_lock_init(&busid_table_lock);
+
+ for (i = 0; i < MAX_BUSID; i++)
+ spin_lock_init(&busid_table[i].busid_lock);
}
/*
int i;
int idx = -1;
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (busid_table[i].name[0])
if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) {
idx = i;
+ spin_unlock(&busid_table[i].busid_lock);
break;
}
+ spin_unlock(&busid_table[i].busid_lock);
+ }
return idx;
}
+/* Returns holding busid_lock. Should call put_busid_priv() to unlock */
struct bus_id_priv *get_busid_priv(const char *busid)
{
int idx;
spin_lock(&busid_table_lock);
idx = get_busid_idx(busid);
- if (idx >= 0)
+ if (idx >= 0) {
bid = &(busid_table[idx]);
+ /* get busid_lock before returning */
+ spin_lock(&bid->busid_lock);
+ }
spin_unlock(&busid_table_lock);
return bid;
}
+void put_busid_priv(struct bus_id_priv *bid)
+{
+ if (bid)
+ spin_unlock(&bid->busid_lock);
+}
+
static int add_match_busid(char *busid)
{
int i;
goto out;
}
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (!busid_table[i].name[0]) {
strlcpy(busid_table[i].name, busid, BUSID_SIZE);
if ((busid_table[i].status != STUB_BUSID_ALLOC) &&
(busid_table[i].status != STUB_BUSID_REMOV))
busid_table[i].status = STUB_BUSID_ADDED;
ret = 0;
+ spin_unlock(&busid_table[i].busid_lock);
break;
}
+ spin_unlock(&busid_table[i].busid_lock);
+ }
out:
spin_unlock(&busid_table_lock);
/* found */
ret = 0;
+ spin_lock(&busid_table[idx].busid_lock);
+
if (busid_table[idx].status == STUB_BUSID_OTHER)
memset(busid_table[idx].name, 0, BUSID_SIZE);
(busid_table[idx].status != STUB_BUSID_ADDED))
busid_table[idx].status = STUB_BUSID_REMOV;
+ spin_unlock(&busid_table[idx].busid_lock);
out:
spin_unlock(&busid_table_lock);
char *out = buf;
spin_lock(&busid_table_lock);
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (busid_table[i].name[0])
out += sprintf(out, "%s ", busid_table[i].name);
+ spin_unlock(&busid_table[i].busid_lock);
+ }
spin_unlock(&busid_table_lock);
out += sprintf(out, "\n");
}
static DRIVER_ATTR_RW(match_busid);
+static int do_rebind(char *busid, struct bus_id_priv *busid_priv)
+{
+ int ret;
+
+ /* device_attach() callers should hold parent lock for USB */
+ if (busid_priv->udev->dev.parent)
+ device_lock(busid_priv->udev->dev.parent);
+ ret = device_attach(&busid_priv->udev->dev);
+ if (busid_priv->udev->dev.parent)
+ device_unlock(busid_priv->udev->dev.parent);
+ if (ret < 0) {
+ dev_err(&busid_priv->udev->dev, "rebind failed\n");
+ return ret;
+ }
+ return 0;
+}
+
+static void stub_device_rebind(void)
+{
+#if IS_MODULE(CONFIG_USBIP_HOST)
+ struct bus_id_priv *busid_priv;
+ int i;
+
+ /* update status to STUB_BUSID_OTHER so probe ignores the device */
+ spin_lock(&busid_table_lock);
+ for (i = 0; i < MAX_BUSID; i++) {
+ if (busid_table[i].name[0] &&
+ busid_table[i].shutdown_busid) {
+ busid_priv = &(busid_table[i]);
+ busid_priv->status = STUB_BUSID_OTHER;
+ }
+ }
+ spin_unlock(&busid_table_lock);
+
+ /* now run rebind - no need to hold locks. driver files are removed */
+ for (i = 0; i < MAX_BUSID; i++) {
+ if (busid_table[i].name[0] &&
+ busid_table[i].shutdown_busid) {
+ busid_priv = &(busid_table[i]);
+ do_rebind(busid_table[i].name, busid_priv);
+ }
+ }
+#endif
+}
+
static ssize_t rebind_store(struct device_driver *dev, const char *buf,
size_t count)
{
if (!bid)
return -ENODEV;
- ret = device_attach(&bid->udev->dev);
- if (ret < 0) {
- dev_err(&bid->udev->dev, "rebind failed\n");
+ /* mark the device for deletion so probe ignores it during rescan */
+ bid->status = STUB_BUSID_OTHER;
+ /* release the busid lock */
+ put_busid_priv(bid);
+
+ ret = do_rebind((char *) buf, bid);
+ if (ret < 0)
return ret;
- }
+
+ /* delete device from busid_table */
+ del_match_busid((char *) buf);
return count;
}
*/
usb_deregister_device_driver(&stub_driver);
+ /* initiate scan to attach devices */
+ stub_device_rebind();
+
kmem_cache_destroy(stub_priv_cache);
}
#define VUDC_EVENT_ERROR_USB (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
#define VUDC_EVENT_ERROR_MALLOC (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
-#define VDEV_EVENT_REMOVED (USBIP_EH_SHUTDOWN | USBIP_EH_BYE)
+#define VDEV_EVENT_REMOVED (USBIP_EH_SHUTDOWN | USBIP_EH_RESET | USBIP_EH_BYE)
#define VDEV_EVENT_DOWN (USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
#define VDEV_EVENT_ERROR_TCP (USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
#define VDEV_EVENT_ERROR_MALLOC (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
unset_event(ud, USBIP_EH_UNUSABLE);
}
- /* Stop the error handler. */
- if (ud->event & USBIP_EH_BYE)
- usbip_dbg_eh("removed %p\n", ud);
-
wake_up(&ud->eh_waitq);
}
}
usbip_dbg_vhci_rh(" ClearHubFeature\n");
break;
case ClearPortFeature:
+ if (rhport < 0)
+ goto error;
switch (wValue) {
case USB_PORT_FEAT_SUSPEND:
if (hcd->speed == HCD_USB3) {
goto error;
}
+ if (rhport < 0)
+ goto error;
+
vhci_hcd->port_status[rhport] |= USB_PORT_STAT_SUSPEND;
break;
case USB_PORT_FEAT_POWER:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_POWER\n");
+ if (rhport < 0)
+ goto error;
if (hcd->speed == HCD_USB3)
vhci_hcd->port_status[rhport] |= USB_SS_PORT_STAT_POWER;
else
case USB_PORT_FEAT_BH_PORT_RESET:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_BH_PORT_RESET\n");
+ if (rhport < 0)
+ goto error;
/* Applicable only for USB3.0 hub */
if (hcd->speed != HCD_USB3) {
pr_err("USB_PORT_FEAT_BH_PORT_RESET req not "
case USB_PORT_FEAT_RESET:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_RESET\n");
+ if (rhport < 0)
+ goto error;
/* if it's already enabled, disable */
if (hcd->speed == HCD_USB3) {
vhci_hcd->port_status[rhport] = 0;
default:
usbip_dbg_vhci_rh(" SetPortFeature: default %d\n",
wValue);
+ if (rhport < 0)
+ goto error;
if (hcd->speed == HCD_USB3) {
if ((vhci_hcd->port_status[rhport] &
USB_SS_PORT_STAT_POWER) != 0) {
#define VHOST_NET_WEIGHT 0x80000
/* Max number of packets transferred before requeueing the job.
- * Using this limit prevents one virtqueue from starving rx. */
-#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2)
+ * Using this limit prevents one virtqueue from starving others with small
+ * pkts.
+ */
+#define VHOST_NET_PKT_WEIGHT 256
/* MAX number of TX used buffers for outstanding zerocopy */
#define VHOST_MAX_PEND 128
vhost_zerocopy_signal_used(net, vq);
vhost_net_tx_packet(net);
if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
- unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) {
+ unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
struct socket *sock;
struct iov_iter fixup;
__virtio16 num_buffers;
+ int recv_pkts = 0;
mutex_lock_nested(&vq->mutex, 0);
sock = vq->private_data;
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
- if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+ if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
+ unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
vhost_poll_queue(&vq->poll);
goto out;
}
}
out:
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
kfree(pages);
}
rc = vbg_req_perform(gdev, req);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
if (rc < 0) {
vbg_err("%s error: %d\n", __func__, rc);
ret = vbg_status_code_to_errno(rc);
out_free:
- kfree(req2);
- kfree(req1);
+ vbg_req_free(req2, sizeof(*req2));
+ vbg_req_free(req1, sizeof(*req1));
return ret;
}
if (rc == VERR_NOT_IMPLEMENTED) /* Compatibility with older hosts. */
rc = VINF_SUCCESS;
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
rc = vbg_req_perform(gdev, req);
do_div(req->interval_ns, 1000000); /* ns -> ms */
gdev->heartbeat_interval_ms = req->interval_ns;
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
if (ret < 0)
return ret;
- /*
- * Preallocate the request to use it from the timer callback because:
- * 1) on Windows vbg_req_alloc must be called at IRQL <= APC_LEVEL
- * and the timer callback runs at DISPATCH_LEVEL;
- * 2) avoid repeated allocations.
- */
gdev->guest_heartbeat_req = vbg_req_alloc(
sizeof(*gdev->guest_heartbeat_req),
VMMDEVREQ_GUEST_HEARTBEAT);
{
del_timer_sync(&gdev->heartbeat_timer);
vbg_heartbeat_host_config(gdev, false);
- kfree(gdev->guest_heartbeat_req);
-
+ vbg_req_free(gdev->guest_heartbeat_req,
+ sizeof(*gdev->guest_heartbeat_req));
}
/**
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
out:
mutex_unlock(&gdev->session_mutex);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
out:
mutex_unlock(&gdev->session_mutex);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
rc = vbg_req_perform(gdev, req);
ret = vbg_status_code_to_errno(rc);
- if (ret)
+ if (ret) {
+ vbg_err("%s error: %d\n", __func__, rc);
goto out;
+ }
snprintf(gdev->host_version, sizeof(gdev->host_version), "%u.%u.%ur%u",
req->major, req->minor, req->build, req->revision);
}
out:
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
return 0;
err_free_reqs:
- kfree(gdev->mouse_status_req);
- kfree(gdev->ack_events_req);
- kfree(gdev->cancel_req);
- kfree(gdev->mem_balloon.change_req);
- kfree(gdev->mem_balloon.get_req);
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
return ret;
}
vbg_reset_host_capabilities(gdev);
vbg_core_set_mouse_status(gdev, 0);
- kfree(gdev->mouse_status_req);
- kfree(gdev->ack_events_req);
- kfree(gdev->cancel_req);
- kfree(gdev->mem_balloon.change_req);
- kfree(gdev->mem_balloon.get_req);
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
}
/**
req->flags = dump->u.in.flags;
dump->hdr.rc = vbg_req_perform(gdev, req);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return 0;
}
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
void vbg_linux_mouse_event(struct vbg_dev *gdev);
+/* Private (non exported) functions form vboxguest_utils.c */
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
+void vbg_req_free(void *req, size_t len);
+int vbg_req_perform(struct vbg_dev *gdev, void *req);
+int vbg_hgcm_call32(
+ struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
+ struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
+ int *vbox_status);
+
#endif
struct vbg_session *session = filp->private_data;
size_t returned_size, size;
struct vbg_ioctl_hdr hdr;
+ bool is_vmmdev_req;
int ret = 0;
void *buf;
if (size > SZ_16M)
return -E2BIG;
- /* __GFP_DMA32 because IOCTL_VMMDEV_REQUEST passes this to the host */
- buf = kmalloc(size, GFP_KERNEL | __GFP_DMA32);
+ /*
+ * IOCTL_VMMDEV_REQUEST needs the buffer to be below 4G to avoid
+ * the need for a bounce-buffer and another copy later on.
+ */
+ is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) ||
+ req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
+
+ if (is_vmmdev_req)
+ buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT);
+ else
+ buf = kmalloc(size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
ret = -EFAULT;
out:
- kfree(buf);
+ if (is_vmmdev_req)
+ vbg_req_free(buf, size);
+ else
+ kfree(buf);
return ret;
}
void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
{
struct vmmdev_request_header *req;
+ int order = get_order(PAGE_ALIGN(len));
- req = kmalloc(len, GFP_KERNEL | __GFP_DMA32);
+ req = (void *)__get_free_pages(GFP_KERNEL | GFP_DMA32, order);
if (!req)
return NULL;
return req;
}
+void vbg_req_free(void *req, size_t len)
+{
+ if (!req)
+ return;
+
+ free_pages((unsigned long)req, get_order(PAGE_ALIGN(len)));
+}
+
/* Note this function returns a VBox status code, not a negative errno!! */
int vbg_req_perform(struct vbg_dev *gdev, void *req)
{
rc = hgcm_connect->header.result;
}
- kfree(hgcm_connect);
+ vbg_req_free(hgcm_connect, sizeof(*hgcm_connect));
*vbox_status = rc;
return 0;
if (rc >= 0)
rc = hgcm_disconnect->header.result;
- kfree(hgcm_disconnect);
+ vbg_req_free(hgcm_disconnect, sizeof(*hgcm_disconnect));
*vbox_status = rc;
return 0;
}
if (!leak_it)
- kfree(call);
+ vbg_req_free(call, size);
free_bounce_bufs:
if (bounce_bufs) {
#define WDT_CTRL_WDT_INTR BIT(2)
#define WDT_CTRL_RESET_SYSTEM BIT(1)
#define WDT_CTRL_ENABLE BIT(0)
+#define WDT_TIMEOUT_STATUS 0x10
+#define WDT_TIMEOUT_STATUS_BOOT_SECONDARY BIT(1)
/*
* WDT_RESET_WIDTH controls the characteristics of the external pulse (if
struct device_node *np;
const char *reset_type;
u32 duration;
+ u32 status;
int ret;
wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
writel(duration - 1, wdt->base + WDT_RESET_WIDTH);
}
+ status = readl(wdt->base + WDT_TIMEOUT_STATUS);
+ if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY)
+ wdt->wdd.bootstatus = WDIOF_CARDRESET;
+
ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdd);
if (ret) {
dev_err(&pdev->dev, "failed to register\n");
}
static const struct watchdog_info rwdt_ident = {
- .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
+ .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+ WDIOF_CARDRESET,
.identity = "Renesas WDT Watchdog",
};
return PTR_ERR(clk);
pm_runtime_enable(&pdev->dev);
-
pm_runtime_get_sync(&pdev->dev);
priv->clk_rate = clk_get_rate(clk);
+ priv->wdev.bootstatus = (readb_relaxed(priv->base + RWTCSRA) &
+ RWTCSRA_WOVF) ? WDIOF_CARDRESET : 0;
pm_runtime_put(&pdev->dev);
if (!priv->clk_rate) {
if (sch311x_wdt_set_heartbeat(new_timeout))
return -EINVAL;
sch311x_wdt_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, p);
default:
return -EINVAL;
wdt_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, uarg.i);
timeout = new_timeout;
wafwdt_stop();
wafwdt_start();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, p);
p = text;
do {
struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs];
- char tdelim = delim;
+ const char *q, *stop;
if (*p == delim) {
p++;
if (*p == '[') {
p++;
- tdelim = ']';
+ q = memchr(p, ']', end - p);
+ } else {
+ for (q = p; q < end; q++)
+ if (*q == '+' || *q == delim)
+ break;
}
- if (in4_pton(p, end - p,
+ if (in4_pton(p, q - p,
(u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
- tdelim, &p)) {
+ -1, &stop)) {
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- } else if (in6_pton(p, end - p,
+ } else if (in6_pton(p, q - p,
srx->transport.sin6.sin6_addr.s6_addr,
- tdelim, &p)) {
+ -1, &stop)) {
/* Nothing to do */
} else {
goto bad_address;
}
- if (tdelim == ']') {
- if (p == end || *p != ']')
- goto bad_address;
+ if (stop != q)
+ goto bad_address;
+
+ p = q;
+ if (q < end && *q == ']')
p++;
- }
if (p < end) {
if (*p == '+') {
/*
* Set up an interest-in-callbacks record for a volume on a server and
* register it with the server.
- * - Called with volume->server_sem held.
+ * - Called with vnode->io_lock held.
*/
int afs_register_server_cb_interest(struct afs_vnode *vnode,
- struct afs_server_entry *entry)
+ struct afs_server_list *slist,
+ unsigned int index)
{
- struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x;
+ struct afs_server_entry *entry = &slist->servers[index];
+ struct afs_cb_interest *cbi, *vcbi, *new, *old;
struct afs_server *server = entry->server;
again:
+ if (vnode->cb_interest &&
+ likely(vnode->cb_interest == entry->cb_interest))
+ return 0;
+
+ read_lock(&slist->lock);
+ cbi = afs_get_cb_interest(entry->cb_interest);
+ read_unlock(&slist->lock);
+
vcbi = vnode->cb_interest;
if (vcbi) {
- if (vcbi == cbi)
+ if (vcbi == cbi) {
+ afs_put_cb_interest(afs_v2net(vnode), cbi);
return 0;
+ }
+ /* Use a new interest in the server list for the same server
+ * rather than an old one that's still attached to a vnode.
+ */
if (cbi && vcbi->server == cbi->server) {
write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
write_sequnlock(&vnode->cb_lock);
- afs_put_cb_interest(afs_v2net(vnode), cbi);
+ afs_put_cb_interest(afs_v2net(vnode), old);
return 0;
}
+ /* Re-use the one attached to the vnode. */
if (!cbi && vcbi->server == server) {
- afs_get_cb_interest(vcbi);
- x = cmpxchg(&entry->cb_interest, cbi, vcbi);
- if (x != cbi) {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), vcbi);
+ write_lock(&slist->lock);
+ if (entry->cb_interest) {
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), cbi);
goto again;
}
+
+ entry->cb_interest = cbi;
+ write_unlock(&slist->lock);
return 0;
}
}
list_add_tail(&new->cb_link, &server->cb_interests);
write_unlock(&server->cb_break_lock);
- x = cmpxchg(&entry->cb_interest, cbi, new);
- if (x == cbi) {
+ write_lock(&slist->lock);
+ if (!entry->cb_interest) {
+ entry->cb_interest = afs_get_cb_interest(new);
cbi = new;
+ new = NULL;
} else {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), new);
+ cbi = afs_get_cb_interest(entry->cb_interest);
}
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), new);
}
ASSERT(cbi);
*/
write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
vnode->cb_s_break = cbi->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
write_sequnlock(&vnode->cb_lock);
+ afs_put_cb_interest(afs_v2net(vnode), old);
return 0;
}
if (cbi->vid != fid->vid)
continue;
- data.volume = NULL;
- data.fid = *fid;
- inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data);
- if (inode) {
- vnode = AFS_FS_I(inode);
- afs_break_callback(vnode);
- iput(inode);
+ if (fid->vnode == 0 && fid->unique == 0) {
+ /* The callback break applies to an entire volume. */
+ struct afs_super_info *as = AFS_FS_S(cbi->sb);
+ struct afs_volume *volume = as->volume;
+
+ write_lock(&volume->cb_break_lock);
+ volume->cb_v_break++;
+ write_unlock(&volume->cb_break_lock);
+ } else {
+ data.volume = NULL;
+ data.fid = *fid;
+ inode = ilookup5_nowait(cbi->sb, fid->vnode,
+ afs_iget5_test, &data);
+ if (inode) {
+ vnode = AFS_FS_I(inode);
+ afs_break_callback(vnode);
+ iput(inode);
+ }
}
}
ASSERT(server != NULL);
ASSERTCMP(count, <=, AFSCBMAX);
+ /* TODO: Sort the callback break list by volume ID */
+
for (; count > 0; callbacks++, count--) {
_debug("- Fid { vl=%08x n=%u u=%u } CB { v=%u x=%u t=%u }",
callbacks->fid.vid,
}
/*
- * clean up a cache manager call
+ * Clean up a cache manager call.
*/
static void afs_cm_destructor(struct afs_call *call)
{
- _enter("");
-
- /* Break the callbacks here so that we do it after the final ACK is
- * received. The step number here must match the final number in
- * afs_deliver_cb_callback().
- */
- if (call->unmarshall == 5) {
- ASSERT(call->cm_server && call->count && call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
- }
-
kfree(call->buffer);
call->buffer = NULL;
}
_enter("");
- /* be sure to send the reply *before* attempting to spam the AFS server
- * with FSFetchStatus requests on the vnodes with broken callbacks lest
- * the AFS server get into a vicious cycle of trying to break further
- * callbacks because it hadn't received completion of the CBCallBack op
- * yet */
- afs_send_empty_reply(call);
+ /* We need to break the callbacks before sending the reply as the
+ * server holds up change visibility till it receives our reply so as
+ * to maintain cache coherency.
+ */
+ if (call->cm_server)
+ afs_break_callbacks(call->cm_server, call->count, call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
+ afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
}
{
struct afs_callback_break *cb;
struct sockaddr_rxrpc srx;
- struct afs_server *server;
__be32 *bp;
int ret, loop;
call->offset = 0;
call->unmarshall++;
-
- /* Record that the message was unmarshalled successfully so
- * that the call destructor can know do the callback breaking
- * work, even if the final ACK isn't received.
- *
- * If the step number changes, then afs_cm_destructor() must be
- * updated also.
- */
- call->unmarshall++;
case 5:
break;
}
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
_enter("{%p}", call->cm_server);
- afs_init_callback_state(call->cm_server);
+ if (call->cm_server)
+ afs_init_callback_state(call->cm_server);
afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
{
struct sockaddr_rxrpc srx;
- struct afs_server *server;
int ret;
_enter("");
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
*/
static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
{
- struct sockaddr_rxrpc srx;
- struct afs_server *server;
struct afs_uuid *r;
unsigned loop;
__be32 *b;
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ rcu_read_lock();
+ call->cm_server = afs_find_server_by_uuid(call->net, call->request);
+ rcu_read_unlock();
+ if (!call->cm_server)
+ trace_afs_cm_no_server_u(call, call->request);
return afs_queue_call_work(call);
}
* get reclaimed during the iteration.
*/
static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
+ __acquires(&dvnode->validate_lock)
{
struct afs_read *req;
loff_t i_size;
/* If we're going to reload, we need to lock all the pages to prevent
* races.
*/
- if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
- ret = -ERESTARTSYS;
- for (i = 0; i < req->nr_pages; i++)
- if (lock_page_killable(req->pages[i]) < 0)
- goto error_unlock;
+ ret = -ERESTARTSYS;
+ if (down_read_killable(&dvnode->validate_lock) < 0)
+ goto error;
- if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
- goto success;
+ if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+ goto success;
+
+ up_read(&dvnode->validate_lock);
+ if (down_write_killable(&dvnode->validate_lock) < 0)
+ goto error;
+ if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
ret = afs_fetch_data(dvnode, key, req);
if (ret < 0)
- goto error_unlock_all;
+ goto error_unlock;
task_io_account_read(PAGE_SIZE * req->nr_pages);
for (i = 0; i < req->nr_pages; i++)
if (!afs_dir_check_page(dvnode, req->pages[i],
req->actual_len))
- goto error_unlock_all;
+ goto error_unlock;
// TODO: Trim excess pages
set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags);
}
+ downgrade_write(&dvnode->validate_lock);
success:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
return req;
-error_unlock_all:
- i = req->nr_pages;
error_unlock:
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
error:
afs_put_read(req);
_leave(" = %d", ret);
return ERR_PTR(ret);
content_has_grown:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
afs_put_read(req);
goto retry;
}
}
out:
+ up_read(&dvnode->validate_lock);
afs_put_read(req);
_leave(" = %d", ret);
return ret;
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, true,
data_version);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, false,
data_version);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
- fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(vnode);
afs_fs_link(&fc, vnode, dentry->d_name.name, data_version);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_symlink(&fc, dentry->d_name.name,
content, data_version,
&newfid, &newstatus);
}
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;
- fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
afs_fs_rename(&fc, old_dentry->d_name.name,
new_dvnode, new_dentry->d_name.name,
orig_data_version, new_data_version);
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_data(&fc, desc);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_set_lock(&fc, type);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_extend_lock(&fc);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_release_lock(&fc);
}
struct afs_read *read_req)
{
const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp;
+ bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus);
u64 data_version, size;
u32 type, abort_code;
u8 flags = 0;
if (vnode)
write_seqlock(&vnode->cb_lock);
+ abort_code = ntohl(xdr->abort_code);
+
if (xdr->if_version != htonl(AFS_FSTATUS_VERSION)) {
+ if (xdr->if_version == htonl(0) &&
+ abort_code != 0 &&
+ inline_error) {
+ /* The OpenAFS fileserver has a bug in FS.InlineBulkStatus
+ * whereby it doesn't set the interface version in the error
+ * case.
+ */
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
goto bad;
}
+ if (abort_code != 0 && inline_error) {
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
type = ntohl(xdr->type);
- abort_code = ntohl(xdr->abort_code);
switch (type) {
case AFS_FTYPE_FILE:
case AFS_FTYPE_DIR:
}
status->type = type;
break;
- case AFS_FTYPE_INVALID:
- if (abort_code != 0) {
- status->abort_code = abort_code;
- ret = 0;
- goto out;
- }
- /* Fall through */
default:
goto bad;
}
write_seqlock(&vnode->cb_lock);
- if (call->cb_break == (vnode->cb_break + cbi->server->cb_s_break)) {
+ if (call->cb_break == afs_cb_break_sum(vnode, cbi)) {
vnode->cb_version = ntohl(*bp++);
cb_expiry = ntohl(*bp++);
vnode->cb_type = ntohl(*bp++);
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_file_status(&fc, NULL, new_inode);
}
read_seqlock_excl(&vnode->cb_lock);
if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
- if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) {
+ if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break ||
+ vnode->cb_v_break != vnode->volume->cb_v_break) {
vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
+ valid = false;
} else if (vnode->status.type == AFS_FTYPE_DIR &&
test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
} else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
}
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
if (valid)
goto valid;
- mutex_lock(&vnode->validate_lock);
+ down_write(&vnode->validate_lock);
/* if the promise has expired, we need to check the server again to get
* a new promise - note that if the (parent) directory's metadata was
* different */
if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
afs_zap_data(vnode);
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
valid:
_leave(" = 0");
return 0;
error_unlock:
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_setattr(&fc, attr);
}
#define AFS_SERVER_FL_PROBED 5 /* The fileserver has been probed */
#define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */
#define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */
+#define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */
atomic_t usage;
u32 addr_version; /* Address list version */
unsigned short index; /* Server currently in use */
unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */
unsigned int seq; /* Set to ->servers_seq when installed */
+ rwlock_t lock;
struct afs_server_entry servers[];
};
rwlock_t servers_lock; /* Lock for ->servers */
unsigned int servers_seq; /* Incremented each time ->servers changes */
+ unsigned cb_v_break; /* Break-everything counter. */
+ rwlock_t cb_break_lock;
+
afs_voltype_t type; /* type of volume */
short error;
char type_force; /* force volume type (suppress R/O -> R/W) */
#endif
struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */
struct mutex io_lock; /* Lock for serialising I/O on this mutex */
- struct mutex validate_lock; /* lock for validating this vnode */
+ struct rw_semaphore validate_lock; /* lock for validating this vnode */
spinlock_t wb_lock; /* lock for wb_keys */
spinlock_t lock; /* waitqueue/flags lock */
unsigned long flags;
/* outstanding callback notification on this file */
struct afs_cb_interest *cb_interest; /* Server on which this resides */
unsigned int cb_s_break; /* Mass break counter on ->server */
+ unsigned int cb_v_break; /* Mass break counter on ->volume */
unsigned int cb_break; /* Break counter on vnode */
seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */
extern void afs_break_callback(struct afs_vnode *);
extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*);
-extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_entry *);
+extern int afs_register_server_cb_interest(struct afs_vnode *,
+ struct afs_server_list *, unsigned int);
extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *);
extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *);
static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi)
{
- refcount_inc(&cbi->usage);
+ if (cbi)
+ refcount_inc(&cbi->usage);
return cbi;
}
+static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
+{
+ return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+}
+
+static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode,
+ struct afs_cb_interest *cbi)
+{
+ return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break;
+}
+
/*
* cell.c
*/
*/
if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
write_lock(&vnode->volume->servers_lock);
*/
if (vnode->volume->servers == fc->server_list) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
/* Try again */
* break request before we've finished decoding the reply and
* installing the vnode.
*/
- fc->ac.error = afs_register_server_cb_interest(
- vnode, &fc->server_list->servers[fc->index]);
+ fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list,
+ fc->index);
if (fc->ac.error < 0)
goto failed;
if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
fc->ac.alist = afs_get_addrlist(alist);
- if (!afs_probe_fileserver(fc))
- goto failed;
+ if (!afs_probe_fileserver(fc)) {
+ switch (fc->ac.error) {
+ case -ENOMEM:
+ case -ERESTARTSYS:
+ case -EINTR:
+ goto failed;
+ default:
+ goto next_server;
+ }
+ }
}
if (!fc->ac.alist)
{
struct sockaddr_rxrpc srx;
struct socket *socket;
+ unsigned int min_level;
int ret;
_enter("");
srx.transport.sin6.sin6_family = AF_INET6;
srx.transport.sin6.sin6_port = htons(AFS_CM_PORT);
+ min_level = RXRPC_SECURITY_ENCRYPT;
+ ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
+ (void *)&min_level, sizeof(min_level));
+ if (ret < 0)
+ goto error_2;
+
ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
if (ret == -EADDRINUSE) {
srx.transport.sin6.sin6_port = 0;
state = READ_ONCE(call->state);
switch (ret) {
case 0:
- if (state == AFS_CALL_CL_PROC_REPLY)
+ if (state == AFS_CALL_CL_PROC_REPLY) {
+ if (call->cbi)
+ set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
+ &call->cbi->server->flags);
goto call_complete;
+ }
ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY);
goto done;
case -EINPROGRESS:
case -ECONNABORTED:
ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
goto done;
- case -ENOTCONN:
- abort_code = RX_CALL_DEAD;
- rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KNC");
- goto local_abort;
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
break;
}
- if (cb_break != (vnode->cb_break +
- vnode->cb_interest->server->cb_s_break)) {
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) {
changed = true;
break;
}
}
}
- if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break))
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest))
goto someone_else_changed_it;
/* We need a ref on any permits list we want to copy as we'll have to
spin_lock(&vnode->lock);
zap = rcu_access_pointer(vnode->permit_cache);
- if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) &&
+ if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) &&
zap == permits)
rcu_assign_pointer(vnode->permit_cache, replacement);
else
sizeof(struct in6_addr));
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == alist->nr_ipv4)
- // goto not_found;
- break;
- }
}
}
} else {
(u32 __force)b->sin6_addr.s6_addr32[3]);
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == 0)
- // goto not_found;
- break;
- }
}
}
}
- //not_found:
server = NULL;
found:
if (server && !atomic_inc_not_zero(&server->usage))
struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
struct afs_addr_cursor ac = {
.alist = alist,
- .addr = &alist->addrs[0],
.start = alist->index,
- .index = alist->index,
+ .index = 0,
+ .addr = &alist->addrs[alist->index],
.error = 0,
};
_enter("%p", server);
- afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+ if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
+ afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+
call_rcu(&server->rcu, afs_server_rcu);
afs_dec_servers_outstanding(net);
}
goto error;
refcount_set(&slist->usage, 1);
+ rwlock_init(&slist->lock);
/* Make sure a records exists for each server in the list. */
for (i = 0; i < vldb->nr_servers; i++) {
goto error_2;
}
- /* Insertion-sort by server pointer */
+ /* Insertion-sort by UUID */
for (j = 0; j < slist->nr_servers; j++)
- if (slist->servers[j].server >= server)
+ if (memcmp(&slist->servers[j].server->uuid,
+ &server->uuid,
+ sizeof(server->uuid)) >= 0)
break;
if (j < slist->nr_servers) {
if (slist->servers[j].server == server) {
memset(vnode, 0, sizeof(*vnode));
inode_init_once(&vnode->vfs_inode);
mutex_init(&vnode->io_lock);
- mutex_init(&vnode->validate_lock);
+ init_rwsem(&vnode->validate_lock);
spin_lock_init(&vnode->wb_lock);
spin_lock_init(&vnode->lock);
INIT_LIST_HEAD(&vnode->wb_keys);
if (afs_begin_vnode_operation(&fc, vnode, key)) {
fc.flags |= AFS_FS_CURSOR_NO_VSLEEP;
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_get_volume_status(&fc, &vs);
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_store_data(&fc, mapping, first, last, offset, to);
}
autofs4_del_active(dentry);
- inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+ inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode);
if (!inode)
return -ENOMEM;
d_add(dentry, inode);
} else
map_addr = vm_mmap(filep, addr, size, prot, type, off);
- if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr))
- pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n",
- task_pid_nr(current), current->comm,
- (void *)addr);
+ if ((type & MAP_FIXED_NOREPLACE) &&
+ PTR_ERR((void *)map_addr) == -EEXIST)
+ pr_info("%d (%s): Uhuuh, elf segment at %px requested but the memory is mapped already\n",
+ task_pid_nr(current), current->comm, (void *)addr);
return(map_addr);
}
if (p->reada != READA_NONE)
reada_for_search(fs_info, p, level, slot, key->objectid);
- btrfs_release_path(p);
-
ret = -EAGAIN;
- tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+ tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
&first_key);
if (!IS_ERR(tmp)) {
/*
} else {
ret = PTR_ERR(tmp);
}
+
+ btrfs_release_path(p);
return ret;
}
down_read(&fs_info->commit_root_sem);
left_level = btrfs_header_level(left_root->commit_root);
left_root_level = left_level;
- left_path->nodes[left_level] = left_root->commit_root;
+ left_path->nodes[left_level] =
+ btrfs_clone_extent_buffer(left_root->commit_root);
+ if (!left_path->nodes[left_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(left_path->nodes[left_level]);
right_level = btrfs_header_level(right_root->commit_root);
right_root_level = right_level;
- right_path->nodes[right_level] = right_root->commit_root;
+ right_path->nodes[right_level] =
+ btrfs_clone_extent_buffer(right_root->commit_root);
+ if (!right_path->nodes[right_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(right_path->nodes[right_level]);
up_read(&fs_info->commit_root_sem);
unsigned short full;
unsigned short type;
unsigned short failfast;
+
+ /*
+ * Qgroup equivalent for @size @reserved
+ *
+ * Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
+ * about things like csum size nor how many tree blocks it will need to
+ * reserve.
+ *
+ * Qgroup cares more about net change of the extent usage.
+ *
+ * So for one newly inserted file extent, in worst case it will cause
+ * leaf split and level increase, nodesize for each file extent is
+ * already too much.
+ *
+ * In short, qgroup_size/reserved is the upper limit of possible needed
+ * qgroup metadata reservation.
+ */
+ u64 qgroup_rsv_size;
+ u64 qgroup_rsv_reserved;
};
/*
*/
#define BTRFS_FS_EXCL_OP 16
+/*
+ * To info transaction_kthread we need an immediate commit so it doesn't
+ * need to wait for commit_interval
+ */
+#define BTRFS_FS_NEED_ASYNC_COMMIT 17
+
struct btrfs_fs_info {
u8 fsid[BTRFS_FSID_SIZE];
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes);
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode);
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
dst_rsv = &fs_info->delayed_block_rsv;
num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+
+ /*
+ * Here we migrate space rsv from transaction rsv, since have already
+ * reserved space when starting a transaction. So no need to reserve
+ * qgroup space here.
+ */
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
if (!ret) {
trace_btrfs_space_reservation(fs_info, "delayed_item",
return;
rsv = &fs_info->delayed_block_rsv;
- btrfs_qgroup_convert_reserved_meta(root, item->bytes_reserved);
+ /*
+ * Check btrfs_delayed_item_reserve_metadata() to see why we don't need
+ * to release/reserve qgroup space.
+ */
trace_btrfs_space_reservation(fs_info, "delayed_item",
item->key.objectid, item->bytes_reserved,
0);
num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
- ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
- if (ret < 0)
- return ret;
/*
* btrfs_dirty_inode will update the inode under btrfs_join_transaction
* which doesn't reserve space for speed. This is a problem since we
*/
if (!src_rsv || (!trans->bytes_reserved &&
src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
+ ret = btrfs_qgroup_reserve_meta_prealloc(root,
+ fs_info->nodesize, true);
+ if (ret < 0)
+ return ret;
ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
BTRFS_RESERVE_NO_FLUSH);
/*
"delayed_inode",
btrfs_ino(inode),
num_bytes, 1);
+ } else {
+ btrfs_qgroup_free_meta_prealloc(root, fs_info->nodesize);
}
return ret;
}
struct btrfs_delayed_ref_head *head_ref,
struct btrfs_qgroup_extent_record *qrecord,
u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
- int action, int is_data, int *qrecord_inserted_ret,
+ int action, int is_data, int is_system,
+ int *qrecord_inserted_ret,
int *old_ref_mod, int *new_ref_mod)
+
{
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_root *delayed_refs;
head_ref->ref_mod = count_mod;
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
+ head_ref->is_system = is_system;
head_ref->ref_tree = RB_ROOT;
INIT_LIST_HEAD(&head_ref->ref_add_list);
RB_CLEAR_NODE(&head_ref->href_node);
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
int qrecord_inserted;
+ int is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
BUG_ON(extent_op && extent_op->is_data);
ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
*/
head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
bytenr, num_bytes, 0, 0, action, 0,
- &qrecord_inserted, old_ref_mod,
- new_ref_mod);
+ is_system, &qrecord_inserted,
+ old_ref_mod, new_ref_mod);
add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, level, action);
*/
head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
bytenr, num_bytes, ref_root, reserved,
- action, 1, &qrecord_inserted,
+ action, 1, 0, &qrecord_inserted,
old_ref_mod, new_ref_mod);
add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
+ /*
+ * extent_ops just modify the flags of an extent and they don't result
+ * in ref count changes, hence it's safe to pass false/0 for is_system
+ * argument
+ */
add_delayed_ref_head(fs_info, trans, head_ref, NULL, bytenr,
num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
- extent_op->is_data, NULL, NULL, NULL);
+ extent_op->is_data, 0, NULL, NULL, NULL);
spin_unlock(&delayed_refs->lock);
return 0;
*/
unsigned int must_insert_reserved:1;
unsigned int is_data:1;
+ unsigned int is_system:1;
unsigned int processing:1;
};
now = get_seconds();
if (cur->state < TRANS_STATE_BLOCKED &&
+ !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
(now < cur->start_time ||
now - cur->start_time < fs_info->commit_interval)) {
spin_unlock(&fs_info->trans_lock);
set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
btrfs_free_qgroup_config(fs_info);
+ ASSERT(list_empty(&fs_info->delalloc_roots));
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
btrfs_info(fs_info, "at unmount delalloc count %lld",
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
{
+ /* cleanup FS via transaction */
+ btrfs_cleanup_transaction(fs_info);
+
mutex_lock(&fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
down_write(&fs_info->cleanup_work_sem);
up_write(&fs_info->cleanup_work_sem);
-
- /* cleanup FS via transaction */
- btrfs_cleanup_transaction(fs_info);
}
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
list_splice_init(&root->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
+ struct inode *inode = NULL;
btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
delalloc_inodes);
-
- list_del_init(&btrfs_inode->delalloc_inodes);
- clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
- &btrfs_inode->runtime_flags);
+ __btrfs_del_delalloc_inode(root, btrfs_inode);
spin_unlock(&root->delalloc_lock);
- btrfs_invalidate_inodes(btrfs_inode->root);
-
+ /*
+ * Make sure we get a live inode and that it'll not disappear
+ * meanwhile.
+ */
+ inode = igrab(&btrfs_inode->vfs_inode);
+ if (inode) {
+ invalidate_inode_pages2(inode->i_mapping);
+ iput(inode);
+ }
spin_lock(&root->delalloc_lock);
}
-
spin_unlock(&root->delalloc_lock);
}
while (!list_empty(&splice)) {
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
- list_del_init(&root->delalloc_root);
root = btrfs_grab_fs_root(root);
BUG_ON(!root);
spin_unlock(&fs_info->delalloc_root_lock);
trace_run_delayed_ref_head(fs_info, head, 0);
if (head->total_ref_mod < 0) {
- struct btrfs_block_group_cache *cache;
+ struct btrfs_space_info *space_info;
+ u64 flags;
- cache = btrfs_lookup_block_group(fs_info, head->bytenr);
- ASSERT(cache);
- percpu_counter_add(&cache->space_info->total_bytes_pinned,
+ if (head->is_data)
+ flags = BTRFS_BLOCK_GROUP_DATA;
+ else if (head->is_system)
+ flags = BTRFS_BLOCK_GROUP_SYSTEM;
+ else
+ flags = BTRFS_BLOCK_GROUP_METADATA;
+ space_info = __find_space_info(fs_info, flags);
+ ASSERT(space_info);
+ percpu_counter_add(&space_info->total_bytes_pinned,
-head->num_bytes);
- btrfs_put_block_group(cache);
if (head->is_data) {
spin_lock(&delayed_refs->lock);
struct rb_node *node;
int ret = 0;
+ spin_lock(&root->fs_info->trans_lock);
cur_trans = root->fs_info->running_transaction;
+ if (cur_trans)
+ refcount_inc(&cur_trans->use_count);
+ spin_unlock(&root->fs_info->trans_lock);
if (!cur_trans)
return 0;
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (!head) {
spin_unlock(&delayed_refs->lock);
+ btrfs_put_transaction(cur_trans);
return 0;
}
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref_head(head);
+ btrfs_put_transaction(cur_trans);
return -EAGAIN;
}
spin_unlock(&delayed_refs->lock);
}
spin_unlock(&head->lock);
mutex_unlock(&head->mutex);
+ btrfs_put_transaction(cur_trans);
return ret;
}
static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv,
- struct btrfs_block_rsv *dest, u64 num_bytes)
+ struct btrfs_block_rsv *dest, u64 num_bytes,
+ u64 *qgroup_to_release_ret)
{
struct btrfs_space_info *space_info = block_rsv->space_info;
+ u64 qgroup_to_release = 0;
u64 ret;
spin_lock(&block_rsv->lock);
- if (num_bytes == (u64)-1)
+ if (num_bytes == (u64)-1) {
num_bytes = block_rsv->size;
+ qgroup_to_release = block_rsv->qgroup_rsv_size;
+ }
block_rsv->size -= num_bytes;
if (block_rsv->reserved >= block_rsv->size) {
num_bytes = block_rsv->reserved - block_rsv->size;
} else {
num_bytes = 0;
}
+ if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
+ qgroup_to_release = block_rsv->qgroup_rsv_reserved -
+ block_rsv->qgroup_rsv_size;
+ block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
+ } else {
+ qgroup_to_release = 0;
+ }
spin_unlock(&block_rsv->lock);
ret = num_bytes;
space_info_add_old_bytes(fs_info, space_info,
num_bytes);
}
+ if (qgroup_to_release_ret)
+ *qgroup_to_release_ret = qgroup_to_release;
return ret;
}
struct btrfs_root *root = inode->root;
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 num_bytes = 0;
+ u64 qgroup_num_bytes = 0;
int ret = -ENOSPC;
spin_lock(&block_rsv->lock);
if (block_rsv->reserved < block_rsv->size)
num_bytes = block_rsv->size - block_rsv->reserved;
+ if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+ qgroup_num_bytes = block_rsv->qgroup_rsv_size -
+ block_rsv->qgroup_rsv_reserved;
spin_unlock(&block_rsv->lock);
if (num_bytes == 0)
return 0;
- ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
+ ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
if (ret)
return ret;
ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
block_rsv_add_bytes(block_rsv, num_bytes, 0);
trace_btrfs_space_reservation(root->fs_info, "delalloc",
btrfs_ino(inode), num_bytes, 1);
- }
+
+ /* Don't forget to increase qgroup_rsv_reserved */
+ spin_lock(&block_rsv->lock);
+ block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
+ spin_unlock(&block_rsv->lock);
+ } else
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
return ret;
}
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 released = 0;
+ u64 qgroup_to_release = 0;
/*
* Since we statically set the block_rsv->size we just want to say we
* are releasing 0 bytes, and then we'll just get the reservation over
* the size free'd.
*/
- released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0);
+ released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0,
+ &qgroup_to_release);
if (released > 0)
trace_btrfs_space_reservation(fs_info, "delalloc",
btrfs_ino(inode), released, 0);
if (qgroup_free)
- btrfs_qgroup_free_meta_prealloc(inode->root, released);
+ btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
else
- btrfs_qgroup_convert_reserved_meta(inode->root, released);
+ btrfs_qgroup_convert_reserved_meta(inode->root,
+ qgroup_to_release);
}
void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
if (global_rsv == block_rsv ||
block_rsv->space_info != global_rsv->space_info)
global_rsv = NULL;
- block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes);
+ block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes, NULL);
}
static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
{
block_rsv_release_bytes(fs_info, &fs_info->global_block_rsv, NULL,
- (u64)-1);
+ (u64)-1, NULL);
WARN_ON(fs_info->trans_block_rsv.size > 0);
WARN_ON(fs_info->trans_block_rsv.reserved > 0);
WARN_ON(fs_info->chunk_block_rsv.size > 0);
WARN_ON_ONCE(!list_empty(&trans->new_bgs));
block_rsv_release_bytes(fs_info, &fs_info->chunk_block_rsv, NULL,
- trans->chunk_bytes_reserved);
+ trans->chunk_bytes_reserved, NULL);
trans->chunk_bytes_reserved = 0;
}
{
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 reserve_size = 0;
+ u64 qgroup_rsv_size = 0;
u64 csum_leaves;
unsigned outstanding_extents;
inode->csum_bytes);
reserve_size += btrfs_calc_trans_metadata_size(fs_info,
csum_leaves);
+ /*
+ * For qgroup rsv, the calculation is very simple:
+ * account one nodesize for each outstanding extent
+ *
+ * This is overestimating in most cases.
+ */
+ qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
spin_lock(&block_rsv->lock);
block_rsv->size = reserve_size;
+ block_rsv->qgroup_rsv_size = qgroup_rsv_size;
spin_unlock(&block_rsv->lock);
}
struct btrfs_block_rsv *block_rsv, u32 blocksize)
{
block_rsv_add_bytes(block_rsv, blocksize, 0);
- block_rsv_release_bytes(fs_info, block_rsv, NULL, 0);
+ block_rsv_release_bytes(fs_info, block_rsv, NULL, 0, NULL);
}
/*
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
lockstart, lockend, &cached_state);
btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
- (ret != 0));
+ true);
if (ret) {
btrfs_drop_pages(pages, num_pages);
break;
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
+#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
spin_unlock(&root->delalloc_lock);
}
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
- struct btrfs_inode *inode)
+
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- spin_lock(&root->delalloc_lock);
if (!list_empty(&inode->delalloc_inodes)) {
list_del_init(&inode->delalloc_inodes);
clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
spin_unlock(&fs_info->delalloc_root_lock);
}
}
+}
+
+static void btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
+{
+ spin_lock(&root->delalloc_lock);
+ __btrfs_del_delalloc_inode(root, inode);
spin_unlock(&root->delalloc_lock);
}
struct dir_entry *entry = addr;
char *name = (char *)(entry + 1);
- ctx->pos = entry->offset;
- if (!dir_emit(ctx, name, entry->name_len, entry->ino,
- entry->type))
+ ctx->pos = get_unaligned(&entry->offset);
+ if (!dir_emit(ctx, name, get_unaligned(&entry->name_len),
+ get_unaligned(&entry->ino),
+ get_unaligned(&entry->type)))
return 1;
- addr += sizeof(struct dir_entry) + entry->name_len;
+ addr += sizeof(struct dir_entry) +
+ get_unaligned(&entry->name_len);
ctx->pos++;
}
return 0;
}
entry = addr;
- entry->name_len = name_len;
+ put_unaligned(name_len, &entry->name_len);
name_ptr = (char *)(entry + 1);
read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1),
name_len);
- entry->type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
+ put_unaligned(btrfs_filetype_table[btrfs_dir_type(leaf, di)],
+ &entry->type);
btrfs_dir_item_key_to_cpu(leaf, di, &location);
- entry->ino = location.objectid;
- entry->offset = found_key.offset;
+ put_unaligned(location.objectid, &entry->ino);
+ put_unaligned(found_key.offset, &entry->offset);
entries++;
addr += sizeof(struct dir_entry) + name_len;
total_len += sizeof(struct dir_entry) + name_len;
fs_info = l->fs_info;
nr = btrfs_header_nritems(l);
- btrfs_info(fs_info, "leaf %llu total ptrs %d free space %d",
- btrfs_header_bytenr(l), nr,
- btrfs_leaf_free_space(fs_info, l));
+ btrfs_info(fs_info,
+ "leaf %llu gen %llu total ptrs %d free space %d owner %llu",
+ btrfs_header_bytenr(l), btrfs_header_generation(l), nr,
+ btrfs_leaf_free_space(fs_info, l), btrfs_header_owner(l));
for (i = 0 ; i < nr ; i++) {
item = btrfs_item_nr(i);
btrfs_item_key_to_cpu(l, &key, i);
}
}
-void btrfs_print_tree(struct extent_buffer *c)
+void btrfs_print_tree(struct extent_buffer *c, bool follow)
{
struct btrfs_fs_info *fs_info;
int i; u32 nr;
return;
}
btrfs_info(fs_info,
- "node %llu level %d total ptrs %d free spc %u",
- btrfs_header_bytenr(c), level, nr,
- (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr);
+ "node %llu level %d gen %llu total ptrs %d free spc %u owner %llu",
+ btrfs_header_bytenr(c), level, btrfs_header_generation(c),
+ nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr,
+ btrfs_header_owner(c));
for (i = 0; i < nr; i++) {
btrfs_node_key_to_cpu(c, &key, i);
- pr_info("\tkey %d (%llu %u %llu) block %llu\n",
+ pr_info("\tkey %d (%llu %u %llu) block %llu gen %llu\n",
i, key.objectid, key.type, key.offset,
- btrfs_node_blockptr(c, i));
+ btrfs_node_blockptr(c, i),
+ btrfs_node_ptr_generation(c, i));
}
+ if (!follow)
+ return;
for (i = 0; i < nr; i++) {
struct btrfs_key first_key;
struct extent_buffer *next;
if (btrfs_header_level(next) !=
level - 1)
BUG();
- btrfs_print_tree(next);
+ btrfs_print_tree(next, follow);
free_extent_buffer(next);
}
}
#define BTRFS_PRINT_TREE_H
void btrfs_print_leaf(struct extent_buffer *l);
-void btrfs_print_tree(struct extent_buffer *c);
+void btrfs_print_tree(struct extent_buffer *c, bool follow);
#endif
const char *value,
size_t len)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int type;
if (len == 0) {
return 0;
}
- if (!strncmp("lzo", value, 3))
+ if (!strncmp("lzo", value, 3)) {
type = BTRFS_COMPRESS_LZO;
- else if (!strncmp("zlib", value, 4))
+ btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (!strncmp("zlib", value, 4)) {
type = BTRFS_COMPRESS_ZLIB;
- else if (!strncmp("zstd", value, len))
+ } else if (!strncmp("zstd", value, len)) {
type = BTRFS_COMPRESS_ZSTD;
- else
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
+ } else {
return -EINVAL;
+ }
BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/btrfs.h>
+#include <linux/sizes.h>
#include "ctree.h"
#include "transaction.h"
return ret;
}
-static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
+/*
+ * Two limits to commit transaction in advance.
+ *
+ * For RATIO, it will be 1/RATIO of the remaining limit
+ * (excluding data and prealloc meta) as threshold.
+ * For SIZE, it will be in byte unit as threshold.
+ */
+#define QGROUP_PERTRANS_RATIO 32
+#define QGROUP_PERTRANS_SIZE SZ_32M
+static bool qgroup_check_limits(struct btrfs_fs_info *fs_info,
+ const struct btrfs_qgroup *qg, u64 num_bytes)
{
+ u64 limit;
+ u64 threshold;
+
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
return false;
qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
return false;
+ /*
+ * Even if we passed the check, it's better to check if reservation
+ * for meta_pertrans is pushing us near limit.
+ * If there is too much pertrans reservation or it's near the limit,
+ * let's try commit transaction to free some, using transaction_kthread
+ */
+ if ((qg->lim_flags & (BTRFS_QGROUP_LIMIT_MAX_RFER |
+ BTRFS_QGROUP_LIMIT_MAX_EXCL))) {
+ if (qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL)
+ limit = qg->max_excl;
+ else
+ limit = qg->max_rfer;
+ threshold = (limit - qg->rsv.values[BTRFS_QGROUP_RSV_DATA] -
+ qg->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC]) /
+ QGROUP_PERTRANS_RATIO;
+ threshold = min_t(u64, threshold, QGROUP_PERTRANS_SIZE);
+
+ /*
+ * Use transaction_kthread to commit transaction, so we no
+ * longer need to bother nested transaction nor lock context.
+ */
+ if (qg->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > threshold)
+ btrfs_commit_transaction_locksafe(fs_info);
+ }
+
return true;
}
qg = unode_aux_to_qgroup(unode);
- if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+ if (enforce && !qgroup_check_limits(fs_info, qg, num_bytes)) {
ret = -EDQUOT;
goto out;
}
old_bytenr = btrfs_node_blockptr(parent, slot);
blocksize = fs_info->nodesize;
old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
- btrfs_node_key_to_cpu(parent, &key, slot);
+ btrfs_node_key_to_cpu(parent, &first_key, slot);
if (level <= max_level) {
eb = path->nodes[level];
len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
}
+ if (offset >= sctx->cur_inode_size) {
+ ret = 0;
+ goto out;
+ }
if (offset + len > sctx->cur_inode_size)
len = sctx->cur_inode_size - offset;
if (len == 0) {
*/
cur_trans->state = TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
+ clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
spin_lock(&fs_info->trans_lock);
list_del_init(&cur_trans->list);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
int wait_for_unblock);
+
+/*
+ * Try to commit transaction asynchronously, so this is safe to call
+ * even holding a spinlock.
+ *
+ * It's done by informing transaction_kthread to commit transaction without
+ * waiting for commit interval.
+ */
+static inline void btrfs_commit_transaction_locksafe(
+ struct btrfs_fs_info *fs_info)
+{
+ set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
+ wake_up_process(fs_info->transaction_kthread);
+}
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
void btrfs_throttle(struct btrfs_fs_info *fs_info);
return ret;
}
+/*
+ * Log all prealloc extents beyond the inode's i_size to make sure we do not
+ * lose them after doing a fast fsync and replaying the log. We scan the
+ * subvolume's root instead of iterating the inode's extent map tree because
+ * otherwise we can log incorrect extent items based on extent map conversion.
+ * That can happen due to the fact that extent maps are merged when they
+ * are not in the extent map tree's list of modified extents.
+ */
+static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct btrfs_path *path)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_key key;
+ const u64 i_size = i_size_read(&inode->vfs_inode);
+ const u64 ino = btrfs_ino(inode);
+ struct btrfs_path *dst_path = NULL;
+ u64 last_extent = (u64)-1;
+ int ins_nr = 0;
+ int start_slot;
+ int ret;
+
+ if (!(inode->flags & BTRFS_INODE_PREALLOC))
+ return 0;
+
+ key.objectid = ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = i_size;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, start_slot,
+ ins_nr, 1, 0);
+ if (ret < 0)
+ goto out;
+ ins_nr = 0;
+ }
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid > ino)
+ break;
+ if (WARN_ON_ONCE(key.objectid < ino) ||
+ key.type < BTRFS_EXTENT_DATA_KEY ||
+ key.offset < i_size) {
+ path->slots[0]++;
+ continue;
+ }
+ if (last_extent == (u64)-1) {
+ last_extent = key.offset;
+ /*
+ * Avoid logging extent items logged in past fsync calls
+ * and leading to duplicate keys in the log tree.
+ */
+ do {
+ ret = btrfs_truncate_inode_items(trans,
+ root->log_root,
+ &inode->vfs_inode,
+ i_size,
+ BTRFS_EXTENT_DATA_KEY);
+ } while (ret == -EAGAIN);
+ if (ret)
+ goto out;
+ }
+ if (ins_nr == 0)
+ start_slot = slot;
+ ins_nr++;
+ path->slots[0]++;
+ if (!dst_path) {
+ dst_path = btrfs_alloc_path();
+ if (!dst_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ }
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path, &last_extent,
+ start_slot, ins_nr, 1, 0);
+ if (ret > 0)
+ ret = 0;
+ }
+out:
+ btrfs_release_path(path);
+ btrfs_free_path(dst_path);
+ return ret;
+}
+
static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_inode *inode,
if (em->generation <= test_gen)
continue;
+ /* We log prealloc extents beyond eof later. */
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+ em->start >= i_size_read(&inode->vfs_inode))
+ continue;
+
if (em->start < logged_start)
logged_start = em->start;
if ((em->start + em->len - 1) > logged_end)
num++;
}
- /*
- * Add all prealloc extents beyond the inode's i_size to make sure we
- * don't lose them after doing a fast fsync and replaying the log.
- */
- if (inode->flags & BTRFS_INODE_PREALLOC) {
- struct rb_node *node;
-
- for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
- em = rb_entry(node, struct extent_map, rb_node);
- if (em->start < i_size_read(&inode->vfs_inode))
- break;
- if (!list_empty(&em->list))
- continue;
- /* Same as above loop. */
- if (++num > 32768) {
- list_del_init(&tree->modified_extents);
- ret = -EFBIG;
- goto process;
- }
- refcount_inc(&em->refs);
- set_bit(EXTENT_FLAG_LOGGING, &em->flags);
- list_add_tail(&em->list, &extents);
- }
- }
-
list_sort(NULL, &extents, extent_cmp);
btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
/*
up_write(&inode->dio_sem);
btrfs_release_path(path);
+ if (!ret)
+ ret = btrfs_log_prealloc_extents(trans, inode, path);
+
return ret;
}
struct extent_map_tree *em_tree = &inode->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
+ bool xattrs_logged = false;
path = btrfs_alloc_path();
if (!path)
err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
if (err)
goto out_unlock;
+ xattrs_logged = true;
if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
btrfs_release_path(path);
btrfs_release_path(dst_path);
btrfs_release_path(dst_path);
if (need_log_inode_item) {
err = log_inode_item(trans, log, dst_path, inode);
+ if (!err && !xattrs_logged) {
+ err = btrfs_log_all_xattrs(trans, root, inode, path,
+ dst_path);
+ btrfs_release_path(path);
+ }
if (err)
goto out_unlock;
}
return 0;
}
+ /*
+ * A ro->rw remount sequence should continue with the paused balance
+ * regardless of who pauses it, system or the user as of now, so set
+ * the resume flag.
+ */
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
return PTR_ERR_OR_ZERO(tsk);
}
*/
/*
- * Calculate the length sum of direct io vectors that can
- * be combined into one page vector.
+ * How many pages to get in one call to iov_iter_get_pages(). This
+ * determines the size of the on-stack array used as a buffer.
*/
-static size_t dio_get_pagev_size(const struct iov_iter *it)
+#define ITER_GET_BVECS_PAGES 64
+
+static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
+ struct bio_vec *bvecs)
{
- const struct iovec *iov = it->iov;
- const struct iovec *iovend = iov + it->nr_segs;
- size_t size;
-
- size = iov->iov_len - it->iov_offset;
- /*
- * An iov can be page vectored when both the current tail
- * and the next base are page aligned.
- */
- while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) &&
- (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) {
- size += iov->iov_len;
- }
- dout("dio_get_pagevlen len = %zu\n", size);
- return size;
+ size_t size = 0;
+ int bvec_idx = 0;
+
+ if (maxsize > iov_iter_count(iter))
+ maxsize = iov_iter_count(iter);
+
+ while (size < maxsize) {
+ struct page *pages[ITER_GET_BVECS_PAGES];
+ ssize_t bytes;
+ size_t start;
+ int idx = 0;
+
+ bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+ ITER_GET_BVECS_PAGES, &start);
+ if (bytes < 0)
+ return size ?: bytes;
+
+ iov_iter_advance(iter, bytes);
+ size += bytes;
+
+ for ( ; bytes; idx++, bvec_idx++) {
+ struct bio_vec bv = {
+ .bv_page = pages[idx],
+ .bv_len = min_t(int, bytes, PAGE_SIZE - start),
+ .bv_offset = start,
+ };
+
+ bvecs[bvec_idx] = bv;
+ bytes -= bv.bv_len;
+ start = 0;
+ }
+ }
+
+ return size;
}
/*
- * Allocate a page vector based on (@it, @nbytes).
- * The return value is the tuple describing a page vector,
- * that is (@pages, @page_align, @num_pages).
+ * iov_iter_get_pages() only considers one iov_iter segment, no matter
+ * what maxsize or maxpages are given. For ITER_BVEC that is a single
+ * page.
+ *
+ * Attempt to get up to @maxsize bytes worth of pages from @iter.
+ * Return the number of bytes in the created bio_vec array, or an error.
*/
-static struct page **
-dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes,
- size_t *page_align, int *num_pages)
+static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
+ struct bio_vec **bvecs, int *num_bvecs)
{
- struct iov_iter tmp_it = *it;
- size_t align;
- struct page **pages;
- int ret = 0, idx, npages;
+ struct bio_vec *bv;
+ size_t orig_count = iov_iter_count(iter);
+ ssize_t bytes;
+ int npages;
- align = (unsigned long)(it->iov->iov_base + it->iov_offset) &
- (PAGE_SIZE - 1);
- npages = calc_pages_for(align, nbytes);
- pages = kvmalloc(sizeof(*pages) * npages, GFP_KERNEL);
- if (!pages)
- return ERR_PTR(-ENOMEM);
+ iov_iter_truncate(iter, maxsize);
+ npages = iov_iter_npages(iter, INT_MAX);
+ iov_iter_reexpand(iter, orig_count);
- for (idx = 0; idx < npages; ) {
- size_t start;
- ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes,
- npages - idx, &start);
- if (ret < 0)
- goto fail;
+ /*
+ * __iter_get_bvecs() may populate only part of the array -- zero it
+ * out.
+ */
+ bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
+ if (!bv)
+ return -ENOMEM;
- iov_iter_advance(&tmp_it, ret);
- nbytes -= ret;
- idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE;
+ bytes = __iter_get_bvecs(iter, maxsize, bv);
+ if (bytes < 0) {
+ /*
+ * No pages were pinned -- just free the array.
+ */
+ kvfree(bv);
+ return bytes;
}
- BUG_ON(nbytes != 0);
- *num_pages = npages;
- *page_align = align;
- dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align);
- return pages;
-fail:
- ceph_put_page_vector(pages, idx, false);
- return ERR_PTR(ret);
+ *bvecs = bv;
+ *num_bvecs = npages;
+ return bytes;
+}
+
+static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
+{
+ int i;
+
+ for (i = 0; i < num_bvecs; i++) {
+ if (bvecs[i].bv_page) {
+ if (should_dirty)
+ set_page_dirty_lock(bvecs[i].bv_page);
+ put_page(bvecs[i].bv_page);
+ }
+ }
+ kvfree(bvecs);
}
/*
struct inode *inode = req->r_inode;
struct ceph_aio_request *aio_req = req->r_priv;
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
- int num_pages = calc_pages_for((u64)osd_data->alignment,
- osd_data->length);
- dout("ceph_aio_complete_req %p rc %d bytes %llu\n",
- inode, rc, osd_data->length);
+ BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
+ BUG_ON(!osd_data->num_bvecs);
+
+ dout("ceph_aio_complete_req %p rc %d bytes %u\n",
+ inode, rc, osd_data->bvec_pos.iter.bi_size);
if (rc == -EOLDSNAPC) {
struct ceph_aio_work *aio_work;
} else if (!aio_req->write) {
if (rc == -ENOENT)
rc = 0;
- if (rc >= 0 && osd_data->length > rc) {
- int zoff = osd_data->alignment + rc;
- int zlen = osd_data->length - rc;
+ if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) {
+ struct iov_iter i;
+ int zlen = osd_data->bvec_pos.iter.bi_size - rc;
+
/*
* If read is satisfied by single OSD request,
* it can pass EOF. Otherwise read is within
aio_req->total_len = rc + zlen;
}
- if (zlen > 0)
- ceph_zero_page_vector_range(zoff, zlen,
- osd_data->pages);
+ iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs,
+ osd_data->num_bvecs,
+ osd_data->bvec_pos.iter.bi_size);
+ iov_iter_advance(&i, rc);
+ iov_iter_zero(zlen, &i);
}
}
- ceph_put_page_vector(osd_data->pages, num_pages, aio_req->should_dirty);
+ put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
+ aio_req->should_dirty);
ceph_osdc_put_request(req);
if (rc < 0)
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_vino vino;
struct ceph_osd_request *req;
- struct page **pages;
+ struct bio_vec *bvecs;
struct ceph_aio_request *aio_req = NULL;
int num_pages = 0;
int flags;
}
while (iov_iter_count(iter) > 0) {
- u64 size = dio_get_pagev_size(iter);
- size_t start = 0;
+ u64 size = iov_iter_count(iter);
ssize_t len;
+ if (write)
+ size = min_t(u64, size, fsc->mount_options->wsize);
+ else
+ size = min_t(u64, size, fsc->mount_options->rsize);
+
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, pos, &size, 0,
break;
}
- if (write)
- size = min_t(u64, size, fsc->mount_options->wsize);
- else
- size = min_t(u64, size, fsc->mount_options->rsize);
-
- len = size;
- pages = dio_get_pages_alloc(iter, len, &start, &num_pages);
- if (IS_ERR(pages)) {
+ len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
+ if (len < 0) {
ceph_osdc_put_request(req);
- ret = PTR_ERR(pages);
+ ret = len;
break;
}
+ if (len != size)
+ osd_req_op_extent_update(req, 0, len);
/*
* To simplify error handling, allow AIO when IO within i_size
req->r_mtime = mtime;
}
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, start,
- false, false);
+ osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
if (aio_req) {
aio_req->total_len += len;
list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
pos += len;
- iov_iter_advance(iter, len);
continue;
}
if (ret == -ENOENT)
ret = 0;
if (ret >= 0 && ret < len && pos + ret < size) {
+ struct iov_iter i;
int zlen = min_t(size_t, len - ret,
size - pos - ret);
- ceph_zero_page_vector_range(start + ret, zlen,
- pages);
+
+ iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages,
+ len);
+ iov_iter_advance(&i, ret);
+ iov_iter_zero(zlen, &i);
ret += zlen;
}
if (ret >= 0)
len = ret;
}
- ceph_put_page_vector(pages, num_pages, should_dirty);
-
+ put_bvecs(bvecs, num_pages, should_dirty);
ceph_osdc_put_request(req);
if (ret < 0)
break;
pos += len;
- iov_iter_advance(iter, len);
-
if (!write && pos >= size)
break;
static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci)
{
- return (ci->i_max_files || ci->i_max_bytes);
+ bool ret = false;
+ spin_lock(&ci->i_ceph_lock);
+ if ((ci->i_max_files || ci->i_max_bytes) &&
+ ci->i_vino.snap == CEPH_NOSNAP &&
+ ci->i_snap_realm &&
+ ci->i_snap_realm->ino == ci->i_vino.ino)
+ ret = true;
+ spin_unlock(&ci->i_ceph_lock);
+ return ret;
}
static size_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val,
char *newval = NULL;
struct ceph_inode_xattr *xattr = NULL;
int required_blob_size;
+ bool check_realm = false;
bool lock_snap_rwsem = false;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
vxattr = ceph_match_vxattr(inode, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
+ if (vxattr) {
+ if (vxattr->readonly)
+ return -EOPNOTSUPP;
+ if (value && !strncmp(vxattr->name, "ceph.quota", 10))
+ check_realm = true;
+ }
/* pass any unhandled ceph.* xattrs through to the MDS */
if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
err = -EBUSY;
} else {
err = ceph_sync_setxattr(inode, name, value, size, flags);
+ if (err >= 0 && check_realm) {
+ /* check if snaprealm was created for quota inode */
+ spin_lock(&ci->i_ceph_lock);
+ if ((ci->i_max_files || ci->i_max_bytes) &&
+ !(ci->i_snap_realm &&
+ ci->i_snap_realm->ino == ci->i_vino.ino))
+ err = -EOPNOTSUPP;
+ spin_unlock(&ci->i_ceph_lock);
+ }
}
out:
ceph_free_cap_flush(prealloc_cf);
config CIFS_SMB_DIRECT
bool "SMB Direct support (Experimental)"
- depends on CIFS=m && INFINIBAND || CIFS=y && INFINIBAND=y
+ depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
help
Enables SMB Direct experimental support for SMB 3.0, 3.02 and 3.1.1.
SMB Direct allows transferring SMB packets over RDMA. If unsure,
pr_debug_ ## ratefunc("%s: " \
fmt, __FILE__, ##__VA_ARGS__); \
} else if ((type) & VFS) { \
- pr_err_ ## ratefunc("CuIFS VFS: " \
+ pr_err_ ## ratefunc("CIFS VFS: " \
fmt, ##__VA_ARGS__); \
} else if ((type) & NOISY && (NOISY != 0)) { \
pr_debug_ ## ratefunc(fmt, ##__VA_ARGS__); \
return rc;
}
+/*
+ * Directory operations under CIFS/SMB2/SMB3 are synchronous, so fsync()
+ * is a dummy operation.
+ */
+static int cifs_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ cifs_dbg(FYI, "Sync directory - name: %pD datasync: 0x%x\n",
+ file, datasync);
+
+ return 0;
+}
+
static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff,
size_t len, unsigned int flags)
.copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = generic_file_llseek,
+ .fsync = cifs_dir_fsync,
};
static void
server->sign = true;
}
+ if (cifs_rdma_enabled(server) && server->sign)
+ cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled");
+
return 0;
}
goto cifs_parse_mount_err;
}
-#ifdef CONFIG_CIFS_SMB_DIRECT
- if (vol->rdma && vol->sign) {
- cifs_dbg(VFS, "Currently SMB direct doesn't support signing."
- " This is being fixed\n");
- goto cifs_parse_mount_err;
- }
-#endif
-
#ifndef CONFIG_KEYS
/* Muliuser mounts require CONFIG_KEYS support */
if (vol->multiuser) {
}
}
+ if (volume_info->seal) {
+ if (ses->server->vals->protocol_id == 0) {
+ cifs_dbg(VFS,
+ "SMB3 or later required for encryption\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
+ } else if (tcon->ses->server->capabilities &
+ SMB2_GLOBAL_CAP_ENCRYPTION)
+ tcon->seal = true;
+ else {
+ cifs_dbg(VFS, "Encryption is not supported on share\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
+ }
+ }
+
/*
* BB Do we need to wrap session_mutex around this TCon call and Unix
* SetFS as we do on SessSetup and reconnect?
tcon->use_resilient = true;
}
- if (volume_info->seal) {
- if (ses->server->vals->protocol_id == 0) {
- cifs_dbg(VFS,
- "SMB3 or later required for encryption\n");
- rc = -EOPNOTSUPP;
- goto out_fail;
- } else if (tcon->ses->server->capabilities &
- SMB2_GLOBAL_CAP_ENCRYPTION)
- tcon->seal = true;
- else {
- cifs_dbg(VFS, "Encryption is not supported on share\n");
- rc = -EOPNOTSUPP;
- goto out_fail;
- }
- }
-
/*
* We can have only one retry value for a connection to a share so for
* resources mounted more than once to the same server share the last
goto mknod_out;
}
+ if (!S_ISCHR(mode) && !S_ISBLK(mode))
+ goto mknod_out;
+
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
goto mknod_out;
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
- kfree(full_path);
rc = -ENOMEM;
- free_xid(xid);
- return rc;
+ goto mknod_out;
}
if (backup_cred(cifs_sb))
pdev->minor = cpu_to_le64(MINOR(device_number));
rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
&bytes_written, iov, 1);
- } /* else if (S_ISFIFO) */
+ }
tcon->ses->server->ops->close(xid, tcon, &fid);
d_drop(direntry);
* If the page is mmap'ed into a process' page tables, then we need to make
* sure that it doesn't change while being written back.
*/
-static int
+static vm_fault_t
cifs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
wsize = min_t(unsigned int, wsize, server->max_write);
#ifdef CONFIG_CIFS_SMB_DIRECT
- if (server->rdma)
- wsize = min_t(unsigned int,
+ if (server->rdma) {
+ if (server->sign)
+ wsize = min_t(unsigned int,
+ wsize, server->smbd_conn->max_fragmented_send_size);
+ else
+ wsize = min_t(unsigned int,
wsize, server->smbd_conn->max_readwrite_size);
+ }
#endif
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
rsize = min_t(unsigned int, rsize, server->max_read);
#ifdef CONFIG_CIFS_SMB_DIRECT
- if (server->rdma)
- rsize = min_t(unsigned int,
+ if (server->rdma) {
+ if (server->sign)
+ rsize = min_t(unsigned int,
+ rsize, server->smbd_conn->max_fragmented_recv_size);
+ else
+ rsize = min_t(unsigned int,
rsize, server->smbd_conn->max_readwrite_size);
+ }
#endif
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+ /*
+ * If ea_name is NULL (listxattr) and there are no EAs, return 0 as it's
+ * not an error. Otherwise, the specified ea_name was not found.
+ */
if (!rc)
rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data,
SMB2_MAX_EA_BUF, ea_name);
+ else if (!ea_name && rc == -ENODATA)
+ rc = 0;
kfree(smb2_data);
return rc;
struct cifs_open_parms oparms;
struct cifs_fid fid;
struct kvec err_iov = {NULL, 0};
- struct smb2_err_rsp *err_buf = NULL;
+ struct smb2_err_rsp *err_buf;
struct smb2_symlink_err_rsp *symlink;
unsigned int sub_len;
unsigned int sub_offset;
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov);
- if (!rc || !err_buf) {
+ if (!rc || !err_iov.iov_base) {
kfree(utf16_path);
return -ENOENT;
}
build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt)
{
pneg_ctxt->ContextType = SMB2_ENCRYPTION_CAPABILITIES;
- pneg_ctxt->DataLength = cpu_to_le16(6);
- pneg_ctxt->CipherCount = cpu_to_le16(2);
- pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;
- pneg_ctxt->Ciphers[1] = SMB2_ENCRYPTION_AES128_CCM;
+ pneg_ctxt->DataLength = cpu_to_le16(4); /* Cipher Count + le16 cipher */
+ pneg_ctxt->CipherCount = cpu_to_le16(1);
+/* pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;*/ /* not supported yet */
+ pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_CCM;
}
static void
return -EINVAL;
}
server->cipher_type = ctxt->Ciphers[0];
+ server->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
return 0;
}
int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
{
- int rc = 0;
- struct validate_negotiate_info_req vneg_inbuf;
+ int rc;
+ struct validate_negotiate_info_req *pneg_inbuf;
struct validate_negotiate_info_rsp *pneg_rsp = NULL;
u32 rsplen;
u32 inbuflen; /* max of 4 dialects */
cifs_dbg(FYI, "validate negotiate\n");
-#ifdef CONFIG_CIFS_SMB_DIRECT
- if (tcon->ses->server->rdma)
- return 0;
-#endif
-
/* In SMB3.11 preauth integrity supersedes validate negotiate */
if (tcon->ses->server->dialect == SMB311_PROT_ID)
return 0;
if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
- vneg_inbuf.Capabilities =
+ pneg_inbuf = kmalloc(sizeof(*pneg_inbuf), GFP_NOFS);
+ if (!pneg_inbuf)
+ return -ENOMEM;
+
+ pneg_inbuf->Capabilities =
cpu_to_le32(tcon->ses->server->vals->req_capabilities);
- memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
+ memcpy(pneg_inbuf->Guid, tcon->ses->server->client_guid,
SMB2_CLIENT_GUID_SIZE);
if (tcon->ses->sign)
- vneg_inbuf.SecurityMode =
+ pneg_inbuf->SecurityMode =
cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED);
else if (global_secflags & CIFSSEC_MAY_SIGN)
- vneg_inbuf.SecurityMode =
+ pneg_inbuf->SecurityMode =
cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED);
else
- vneg_inbuf.SecurityMode = 0;
+ pneg_inbuf->SecurityMode = 0;
if (strcmp(tcon->ses->server->vals->version_string,
SMB3ANY_VERSION_STRING) == 0) {
- vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
- vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
- vneg_inbuf.DialectCount = cpu_to_le16(2);
+ pneg_inbuf->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+ pneg_inbuf->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+ pneg_inbuf->DialectCount = cpu_to_le16(2);
/* structure is big enough for 3 dialects, sending only 2 */
- inbuflen = sizeof(struct validate_negotiate_info_req) - 2;
+ inbuflen = sizeof(*pneg_inbuf) -
+ sizeof(pneg_inbuf->Dialects[0]);
} else if (strcmp(tcon->ses->server->vals->version_string,
SMBDEFAULT_VERSION_STRING) == 0) {
- vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
- vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
- vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
- vneg_inbuf.DialectCount = cpu_to_le16(3);
+ pneg_inbuf->Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+ pneg_inbuf->Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+ pneg_inbuf->Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+ pneg_inbuf->DialectCount = cpu_to_le16(3);
/* structure is big enough for 3 dialects */
- inbuflen = sizeof(struct validate_negotiate_info_req);
+ inbuflen = sizeof(*pneg_inbuf);
} else {
/* otherwise specific dialect was requested */
- vneg_inbuf.Dialects[0] =
+ pneg_inbuf->Dialects[0] =
cpu_to_le16(tcon->ses->server->vals->protocol_id);
- vneg_inbuf.DialectCount = cpu_to_le16(1);
+ pneg_inbuf->DialectCount = cpu_to_le16(1);
/* structure is big enough for 3 dialects, sending only 1 */
- inbuflen = sizeof(struct validate_negotiate_info_req) - 4;
+ inbuflen = sizeof(*pneg_inbuf) -
+ sizeof(pneg_inbuf->Dialects[0]) * 2;
}
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
- (char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
- (char **)&pneg_rsp, &rsplen);
+ (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen);
if (rc != 0) {
cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc);
- return -EIO;
+ rc = -EIO;
+ goto out_free_inbuf;
}
- if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
+ rc = -EIO;
+ if (rsplen != sizeof(*pneg_rsp)) {
cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
rsplen);
/* relax check since Mac returns max bufsize allowed on ioctl */
- if ((rsplen > CIFSMaxBufSize)
- || (rsplen < sizeof(struct validate_negotiate_info_rsp)))
- goto err_rsp_free;
+ if (rsplen > CIFSMaxBufSize || rsplen < sizeof(*pneg_rsp))
+ goto out_free_rsp;
}
/* check validate negotiate info response matches what we got earlier */
goto vneg_out;
/* validate negotiate successful */
+ rc = 0;
cifs_dbg(FYI, "validate negotiate info successful\n");
- kfree(pneg_rsp);
- return 0;
+ goto out_free_rsp;
vneg_out:
cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
-err_rsp_free:
+out_free_rsp:
kfree(pneg_rsp);
- return -EIO;
+out_free_inbuf:
+ kfree(pneg_inbuf);
+ return rc;
}
enum securityEnum
* If we want to do a RDMA write, fill in and append
* smbd_buffer_descriptor_v1 to the end of read request
*/
- if (server->rdma && rdata &&
+ if (server->rdma && rdata && !server->sign &&
rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) {
struct smbd_buffer_descriptor_v1 *v1;
* If we want to do a server RDMA read, fill in and append
* smbd_buffer_descriptor_v1 to the end of write request
*/
- if (server->rdma && wdata->bytes >=
+ if (server->rdma && !server->sign && wdata->bytes >=
server->smbd_conn->rdma_readwrite_threshold) {
struct smbd_buffer_descriptor_v1 *v1;
__le16 DataLength;
__le32 Reserved;
__le16 CipherCount; /* AES-128-GCM and AES-128-CCM */
- __le16 Ciphers[2]; /* Ciphers[0] since only one used now */
+ __le16 Ciphers[1]; /* Ciphers[0] since only one used now */
} __packed;
struct smb2_negotiate_rsp {
for (i = 0; i < request->num_sge; i++) {
log_rdma_send(INFO,
"rdma_request sge[%d] addr=%llu length=%u\n",
- i, request->sge[0].addr, request->sge[0].length);
+ i, request->sge[i].addr, request->sge[i].length);
ib_dma_sync_single_for_device(
info->id->device,
request->sge[i].addr,
int start, i, j;
int max_iov_size =
info->max_send_size - sizeof(struct smbd_data_transfer);
- struct kvec iov[SMBDIRECT_MAX_SGE];
+ struct kvec *iov;
int rc;
info->smbd_send_pending++;
}
/*
- * This usually means a configuration error
- * We use RDMA read/write for packet size > rdma_readwrite_threshold
- * as long as it's properly configured we should never get into this
- * situation
- */
- if (rqst->rq_nvec + rqst->rq_npages > SMBDIRECT_MAX_SGE) {
- log_write(ERR, "maximum send segment %x exceeding %x\n",
- rqst->rq_nvec + rqst->rq_npages, SMBDIRECT_MAX_SGE);
- rc = -EINVAL;
- goto done;
- }
-
- /*
- * Remove the RFC1002 length defined in MS-SMB2 section 2.1
- * It is used only for TCP transport
+ * Skip the RFC1002 length defined in MS-SMB2 section 2.1
+ * It is used only for TCP transport in the iov[0]
* In future we may want to add a transport layer under protocol
* layer so this will only be issued to TCP transport
*/
- iov[0].iov_base = (char *)rqst->rq_iov[0].iov_base + 4;
- iov[0].iov_len = rqst->rq_iov[0].iov_len - 4;
- buflen += iov[0].iov_len;
+
+ if (rqst->rq_iov[0].iov_len != 4) {
+ log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len);
+ return -EINVAL;
+ }
+ iov = &rqst->rq_iov[1];
/* total up iov array first */
- for (i = 1; i < rqst->rq_nvec; i++) {
- iov[i].iov_base = rqst->rq_iov[i].iov_base;
- iov[i].iov_len = rqst->rq_iov[i].iov_len;
+ for (i = 0; i < rqst->rq_nvec-1; i++) {
buflen += iov[i].iov_len;
}
goto done;
}
+ cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen);
+ for (i = 0; i < rqst->rq_nvec-1; i++)
+ dump_smb(iov[i].iov_base, iov[i].iov_len);
+
remaining_data_length = buflen;
log_write(INFO, "rqst->rq_nvec=%d rqst->rq_npages=%d rq_pagesz=%d "
goto done;
}
i++;
+ if (i == rqst->rq_nvec-1)
+ break;
}
start = i;
buflen = 0;
} else {
i++;
- if (i == rqst->rq_nvec) {
+ if (i == rqst->rq_nvec-1) {
/* send out all remaining vecs */
remaining_data_length -= buflen;
log_write(INFO,
goto out;
#ifdef CONFIG_CIFS_SMB311
- if (ses->status == CifsNew)
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
smb311_update_preauth_hash(ses, rqst->rq_iov+1,
rqst->rq_nvec-1);
#endif
*resp_buf_type = CIFS_SMALL_BUFFER;
#ifdef CONFIG_CIFS_SMB311
- if (ses->status == CifsNew) {
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
struct kvec iov = {
.iov_base = buf + 4,
.iov_len = get_rfc1002_length(buf)
if (n_vec + 1 > CIFS_MAX_IOV_SIZE) {
new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1),
GFP_KERNEL);
- if (!new_iov)
+ if (!new_iov) {
+ /* otherwise cifs_send_recv below sets resp_buf_type */
+ *resp_buf_type = CIFS_NO_BUFFER;
return -ENOMEM;
+ }
} else
new_iov = s_iov;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
+ ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_fsblk_t blk;
ext4_fsblk_t group_first_block;
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode table block number is set */
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
- EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= sb->s_blocksize)
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+ EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
return blk;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
EXT4_B2C(sbi, offset + sbi->s_itb_per_group),
stop = le32_to_cpu(extent->ee_block);
/*
- * In case of left shift, Don't start shifting extents until we make
- * sure the hole is big enough to accommodate the shift.
+ * For left shifts, make sure the hole on the left is big enough to
+ * accommodate the shift. For right shifts, make sure the last extent
+ * won't be shifted beyond EXT_MAX_BLOCKS.
*/
if (SHIFT == SHIFT_LEFT) {
path = ext4_find_extent(inode, start - 1, &path,
if ((start == ex_start && shift > ex_start) ||
(shift > start - ex_end)) {
- ext4_ext_drop_refs(path);
- kfree(path);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
+ }
+ } else {
+ if (shift > EXT_MAX_BLOCKS -
+ (stop + ext4_ext_get_actual_len(extent))) {
+ ret = -EINVAL;
+ goto out;
}
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: crc32c");
module_init(ext4_init_fs)
module_exit(ext4_exit_fs)
*/
if (inode && inode_to_wb_is_valid(inode)) {
struct bdi_writeback *wb;
- bool locked, congested;
+ struct wb_lock_cookie lock_cookie = {};
+ bool congested;
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &lock_cookie);
congested = wb_congested(wb, cong_bits);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &lock_cookie);
return congested;
}
}
if (!list_empty(&wb->work_list))
- mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ wb_wakeup(wb);
else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
wb_wakeup_delayed(wb);
return 0;
out_put_hidden_dir:
+ cancel_delayed_work_sync(&sbi->sync_work);
iput(sbi->hidden_dir);
out_put_root:
dput(sb->s_root);
*/
ret = start_this_handle(journal, handle, GFP_NOFS);
if (ret < 0) {
+ handle->h_journal = journal;
jbd2_journal_free_reserved(handle);
return ret;
}
static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry, bool preserve)
{
- int error;
+ int error, had_lock;
struct inode *inode = d_inode(old_dentry);
struct buffer_head *old_bh = NULL;
struct inode *new_orphan_inode = NULL;
+ struct ocfs2_lock_holder oh;
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
return -EOPNOTSUPP;
goto out;
}
+ had_lock = ocfs2_inode_lock_tracker(new_orphan_inode, NULL, 1,
+ &oh);
+ if (had_lock < 0) {
+ error = had_lock;
+ mlog_errno(error);
+ goto out;
+ }
+
/* If the security isn't preserved, we need to re-initialize them. */
if (!preserve) {
error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
if (error)
mlog_errno(error);
}
-out:
if (!error) {
error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode,
new_dentry);
if (error)
mlog_errno(error);
}
+ ocfs2_inode_unlock_tracker(new_orphan_inode, 1, &oh, had_lock);
+out:
if (new_orphan_inode) {
/*
* We need to open_unlock the inode no matter whether we
help
Exports the dump image of crashed kernel in ELF format.
+config PROC_VMCORE_DEVICE_DUMP
+ bool "Device Hardware/Firmware Log Collection"
+ depends on PROC_VMCORE
+ default n
+ help
+ After kernel panic, device drivers can collect the device
+ specific snapshot of their hardware or firmware before the
+ underlying devices are initialized in crash recovery kernel.
+ Note that the device driver must be present in the crash
+ recovery kernel's initramfs to collect its underlying device
+ snapshot.
+
+ If you say Y here, the collected device dumps will be added
+ as ELF notes to /proc/vmcore.
+
config PROC_SYSCTL
bool "Sysctl support (/proc/sys)" if EXPERT
depends on PROC_FS
* Inherently racy -- command line shares address space
* with code and data.
*/
- rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
if (rv <= 0)
goto out_free_page;
int nr_read;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
bool final;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
+ retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
if (retval <= 0) {
ret = retval;
kuid_t uid;
kgid_t gid;
+ if (unlikely(task->flags & PF_KTHREAD)) {
+ *ruid = GLOBAL_ROOT_UID;
+ *rgid = GLOBAL_ROOT_GID;
+ return;
+ }
+
/* Default to the tasks effective ownership */
rcu_read_lock();
cred = __task_cred(task);
{
struct list_head *head = (struct list_head *)arg;
struct kcore_list *ent;
+ struct page *p;
+
+ if (!pfn_valid(pfn))
+ return 1;
+
+ p = pfn_to_page(pfn);
+ if (!memmap_valid_within(pfn, p, page_zone(p)))
+ return 1;
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
if (!ent)
return -ENOMEM;
- ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT));
+ ent->addr = (unsigned long)page_to_virt(p);
ent->size = nr_pages << PAGE_SHIFT;
- /* Sanity check: Can happen in 32bit arch...maybe */
- if (ent->addr < (unsigned long) __va(0))
+ if (!virt_addr_valid(ent->addr))
goto free_out;
/* cut not-mapped area. ....from ppc-32 code. */
if (ULONG_MAX - ent->addr < ent->size)
ent->size = ULONG_MAX - ent->addr;
- /* cut when vmalloc() area is higher than direct-map area */
- if (VMALLOC_START > (unsigned long)__va(0)) {
- if (ent->addr > VMALLOC_START)
- goto free_out;
+ /*
+ * We've already checked virt_addr_valid so we know this address
+ * is a valid pointer, therefore we can check against it to determine
+ * if we need to trim
+ */
+ if (VMALLOC_START > ent->addr) {
if (VMALLOC_START - ent->addr < ent->size)
ent->size = VMALLOC_START - ent->addr;
}
LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
nr_running(), nr_threads,
- idr_get_cursor(&task_active_pid_ns(current)->idr));
+ idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
return 0;
}
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
else if (is_swap_pmd(pmd)) {
swp_entry_t entry = pmd_to_swp_entry(pmd);
+ unsigned long offset = swp_offset(entry);
+ offset += (addr & ~PMD_MASK) >> PAGE_SHIFT;
frame = swp_type(entry) |
- (swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+ (offset << MAX_SWAPFILES_SHIFT);
flags |= PM_SWAP;
if (pmd_swp_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
break;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
+ else if (flags & PM_SWAP)
+ frame += (1 << MAX_SWAPFILES_SHIFT);
}
spin_unlock(ptl);
return err;
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/list.h>
+#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
static char *elfnotes_buf;
static size_t elfnotes_sz;
+/* Size of all notes minus the device dump notes */
+static size_t elfnotes_orig_sz;
/* Total size of vmcore file. */
static u64 vmcore_size;
static struct proc_dir_entry *proc_vmcore;
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+/* Device Dump list and mutex to synchronize access to list */
+static LIST_HEAD(vmcoredd_list);
+static DEFINE_MUTEX(vmcoredd_mutex);
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+/* Device Dump Size */
+static size_t vmcoredd_orig_sz;
+
/*
* Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
* The called function has to take care of module refcounting.
return 0;
}
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf)
+{
+ struct vmcoredd_node *dump;
+ u64 offset = 0;
+ int ret = 0;
+ size_t tsz;
+ char *buf;
+
+ mutex_lock(&vmcoredd_mutex);
+ list_for_each_entry(dump, &vmcoredd_list, list) {
+ if (start < offset + dump->size) {
+ tsz = min(offset + (u64)dump->size - start, (u64)size);
+ buf = dump->buf + start - offset;
+ if (copy_to(dst, buf, tsz, userbuf)) {
+ ret = -EFAULT;
+ goto out_unlock;
+ }
+
+ size -= tsz;
+ start += tsz;
+ dst += tsz;
+
+ /* Leave now if buffer filled already */
+ if (!size)
+ goto out_unlock;
+ }
+ offset += dump->size;
+ }
+
+out_unlock:
+ mutex_unlock(&vmcoredd_mutex);
+ return ret;
+}
+
+static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
+ u64 start, size_t size)
+{
+ struct vmcoredd_node *dump;
+ u64 offset = 0;
+ int ret = 0;
+ size_t tsz;
+ char *buf;
+
+ mutex_lock(&vmcoredd_mutex);
+ list_for_each_entry(dump, &vmcoredd_list, list) {
+ if (start < offset + dump->size) {
+ tsz = min(offset + (u64)dump->size - start, (u64)size);
+ buf = dump->buf + start - offset;
+ if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) {
+ ret = -EFAULT;
+ goto out_unlock;
+ }
+
+ size -= tsz;
+ start += tsz;
+ dst += tsz;
+
+ /* Leave now if buffer filled already */
+ if (!size)
+ goto out_unlock;
+ }
+ offset += dump->size;
+ }
+
+out_unlock:
+ mutex_unlock(&vmcoredd_mutex);
+ return ret;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
/* Read from the ELF header and then the crash dump. On error, negative value is
* returned otherwise number of bytes read are returned.
*/
if (*fpos < elfcorebuf_sz + elfnotes_sz) {
void *kaddr;
+ /* We add device dumps before other elf notes because the
+ * other elf notes may not fill the elf notes buffer
+ * completely and we will end up with zero-filled data
+ * between the elf notes and the device dumps. Tools will
+ * then try to decode this zero-filled data as valid notes
+ * and we don't want that. Hence, adding device dumps before
+ * the other elf notes ensure that zero-filled data can be
+ * avoided.
+ */
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+ /* Read device dumps */
+ if (*fpos < elfcorebuf_sz + vmcoredd_orig_sz) {
+ tsz = min(elfcorebuf_sz + vmcoredd_orig_sz -
+ (size_t)*fpos, buflen);
+ start = *fpos - elfcorebuf_sz;
+ if (vmcoredd_copy_dumps(buffer, start, tsz, userbuf))
+ return -EFAULT;
+
+ buflen -= tsz;
+ *fpos += tsz;
+ buffer += tsz;
+ acc += tsz;
+
+ /* leave now if filled buffer already */
+ if (!buflen)
+ return acc;
+ }
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+ /* Read remaining elf notes */
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
- kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
+ kaddr = elfnotes_buf + *fpos - elfcorebuf_sz - vmcoredd_orig_sz;
if (copy_to(buffer, kaddr, tsz, userbuf))
return -EFAULT;
+
buflen -= tsz;
*fpos += tsz;
buffer += tsz;
};
/**
- * alloc_elfnotes_buf - allocate buffer for ELF note segment in
- * vmalloc memory
- *
- * @notes_sz: size of buffer
+ * vmcore_alloc_buf - allocate buffer in vmalloc memory
+ * @sizez: size of buffer
*
* If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
* the buffer to user-space by means of remap_vmalloc_range().
* If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
* disabled and there's no need to allow users to mmap the buffer.
*/
-static inline char *alloc_elfnotes_buf(size_t notes_sz)
+static inline char *vmcore_alloc_buf(size_t size)
{
#ifdef CONFIG_MMU
- return vmalloc_user(notes_sz);
+ return vmalloc_user(size);
#else
- return vzalloc(notes_sz);
+ return vzalloc(size);
#endif
}
if (start < elfcorebuf_sz + elfnotes_sz) {
void *kaddr;
+ /* We add device dumps before other elf notes because the
+ * other elf notes may not fill the elf notes buffer
+ * completely and we will end up with zero-filled data
+ * between the elf notes and the device dumps. Tools will
+ * then try to decode this zero-filled data as valid notes
+ * and we don't want that. Hence, adding device dumps before
+ * the other elf notes ensure that zero-filled data can be
+ * avoided. This also ensures that the device dumps and
+ * other elf notes can be properly mmaped at page aligned
+ * address.
+ */
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+ /* Read device dumps */
+ if (start < elfcorebuf_sz + vmcoredd_orig_sz) {
+ u64 start_off;
+
+ tsz = min(elfcorebuf_sz + vmcoredd_orig_sz -
+ (size_t)start, size);
+ start_off = start - elfcorebuf_sz;
+ if (vmcoredd_mmap_dumps(vma, vma->vm_start + len,
+ start_off, tsz))
+ goto fail;
+
+ size -= tsz;
+ start += tsz;
+ len += tsz;
+
+ /* leave now if filled buffer already */
+ if (!size)
+ return 0;
+ }
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+ /* Read remaining elf notes */
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
- kaddr = elfnotes_buf + start - elfcorebuf_sz;
+ kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz;
if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
kaddr, tsz))
goto fail;
+
size -= tsz;
start += tsz;
len += tsz;
return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
}
-static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
- struct list_head *vc_list)
+static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
+ struct list_head *vc_list)
{
u64 size;
struct vmcore *m;
return rc;
*notes_sz = roundup(phdr_sz, PAGE_SIZE);
- *notes_buf = alloc_elfnotes_buf(*notes_sz);
+ *notes_buf = vmcore_alloc_buf(*notes_sz);
if (!*notes_buf)
return -ENOMEM;
/* Modify e_phnum to reflect merged headers. */
ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
+ /* Store the size of all notes. We need this to update the note
+ * header when the device dumps will be added.
+ */
+ elfnotes_orig_sz = phdr.p_memsz;
+
return 0;
}
return rc;
*notes_sz = roundup(phdr_sz, PAGE_SIZE);
- *notes_buf = alloc_elfnotes_buf(*notes_sz);
+ *notes_buf = vmcore_alloc_buf(*notes_sz);
if (!*notes_buf)
return -ENOMEM;
/* Modify e_phnum to reflect merged headers. */
ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
+ /* Store the size of all notes. We need this to update the note
+ * header when the device dumps will be added.
+ */
+ elfnotes_orig_sz = phdr.p_memsz;
+
return 0;
}
}
/* Sets offset fields of vmcore elements. */
-static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
- struct list_head *vc_list)
+static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
+ struct list_head *vc_list)
{
loff_t vmcore_off;
struct vmcore *m;
return 0;
}
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+/**
+ * vmcoredd_write_header - Write vmcore device dump header at the
+ * beginning of the dump's buffer.
+ * @buf: Output buffer where the note is written
+ * @data: Dump info
+ * @size: Size of the dump
+ *
+ * Fills beginning of the dump's buffer with vmcore device dump header.
+ */
+static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data,
+ u32 size)
+{
+ struct vmcoredd_header *vdd_hdr = (struct vmcoredd_header *)buf;
+
+ vdd_hdr->n_namesz = sizeof(vdd_hdr->name);
+ vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name);
+ vdd_hdr->n_type = NT_VMCOREDD;
+
+ strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME,
+ sizeof(vdd_hdr->name));
+ memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_name));
+}
+
+/**
+ * vmcoredd_update_program_headers - Update all Elf program headers
+ * @elfptr: Pointer to elf header
+ * @elfnotesz: Size of elf notes aligned to page size
+ * @vmcoreddsz: Size of device dumps to be added to elf note header
+ *
+ * Determine type of Elf header (Elf64 or Elf32) and update the elf note size.
+ * Also update the offsets of all the program headers after the elf note header.
+ */
+static void vmcoredd_update_program_headers(char *elfptr, size_t elfnotesz,
+ size_t vmcoreddsz)
+{
+ unsigned char *e_ident = (unsigned char *)elfptr;
+ u64 start, end, size;
+ loff_t vmcore_off;
+ u32 i;
+
+ vmcore_off = elfcorebuf_sz + elfnotesz;
+
+ if (e_ident[EI_CLASS] == ELFCLASS64) {
+ Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfptr;
+ Elf64_Phdr *phdr = (Elf64_Phdr *)(elfptr + sizeof(Elf64_Ehdr));
+
+ /* Update all program headers */
+ for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+ if (phdr->p_type == PT_NOTE) {
+ /* Update note size */
+ phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz;
+ phdr->p_filesz = phdr->p_memsz;
+ continue;
+ }
+
+ start = rounddown(phdr->p_offset, PAGE_SIZE);
+ end = roundup(phdr->p_offset + phdr->p_memsz,
+ PAGE_SIZE);
+ size = end - start;
+ phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+ vmcore_off += size;
+ }
+ } else {
+ Elf32_Ehdr *ehdr = (Elf32_Ehdr *)elfptr;
+ Elf32_Phdr *phdr = (Elf32_Phdr *)(elfptr + sizeof(Elf32_Ehdr));
+
+ /* Update all program headers */
+ for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+ if (phdr->p_type == PT_NOTE) {
+ /* Update note size */
+ phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz;
+ phdr->p_filesz = phdr->p_memsz;
+ continue;
+ }
+
+ start = rounddown(phdr->p_offset, PAGE_SIZE);
+ end = roundup(phdr->p_offset + phdr->p_memsz,
+ PAGE_SIZE);
+ size = end - start;
+ phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+ vmcore_off += size;
+ }
+ }
+}
+
+/**
+ * vmcoredd_update_size - Update the total size of the device dumps and update
+ * Elf header
+ * @dump_size: Size of the current device dump to be added to total size
+ *
+ * Update the total size of all the device dumps and update the Elf program
+ * headers. Calculate the new offsets for the vmcore list and update the
+ * total vmcore size.
+ */
+static void vmcoredd_update_size(size_t dump_size)
+{
+ vmcoredd_orig_sz += dump_size;
+ elfnotes_sz = roundup(elfnotes_orig_sz, PAGE_SIZE) + vmcoredd_orig_sz;
+ vmcoredd_update_program_headers(elfcorebuf, elfnotes_sz,
+ vmcoredd_orig_sz);
+
+ /* Update vmcore list offsets */
+ set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+
+ vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+ &vmcore_list);
+ proc_vmcore->size = vmcore_size;
+}
+
+/**
+ * vmcore_add_device_dump - Add a buffer containing device dump to vmcore
+ * @data: dump info.
+ *
+ * Allocate a buffer and invoke the calling driver's dump collect routine.
+ * Write Elf note at the beginning of the buffer to indicate vmcore device
+ * dump and add the dump to global list.
+ */
+int vmcore_add_device_dump(struct vmcoredd_data *data)
+{
+ struct vmcoredd_node *dump;
+ void *buf = NULL;
+ size_t data_size;
+ int ret;
+
+ if (!data || !strlen(data->dump_name) ||
+ !data->vmcoredd_callback || !data->size)
+ return -EINVAL;
+
+ dump = vzalloc(sizeof(*dump));
+ if (!dump) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ /* Keep size of the buffer page aligned so that it can be mmaped */
+ data_size = roundup(sizeof(struct vmcoredd_header) + data->size,
+ PAGE_SIZE);
+
+ /* Allocate buffer for driver's to write their dumps */
+ buf = vmcore_alloc_buf(data_size);
+ if (!buf) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ vmcoredd_write_header(buf, data, data_size -
+ sizeof(struct vmcoredd_header));
+
+ /* Invoke the driver's dump collection routing */
+ ret = data->vmcoredd_callback(data, buf +
+ sizeof(struct vmcoredd_header));
+ if (ret)
+ goto out_err;
+
+ dump->buf = buf;
+ dump->size = data_size;
+
+ /* Add the dump to driver sysfs list */
+ mutex_lock(&vmcoredd_mutex);
+ list_add_tail(&dump->list, &vmcoredd_list);
+ mutex_unlock(&vmcoredd_mutex);
+
+ vmcoredd_update_size(data_size);
+ return 0;
+
+out_err:
+ if (buf)
+ vfree(buf);
+
+ if (dump)
+ vfree(dump);
+
+ return ret;
+}
+EXPORT_SYMBOL(vmcore_add_device_dump);
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+
+/* Free all dumps in vmcore device dump list */
+static void vmcore_free_device_dumps(void)
+{
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+ mutex_lock(&vmcoredd_mutex);
+ while (!list_empty(&vmcoredd_list)) {
+ struct vmcoredd_node *dump;
+
+ dump = list_first_entry(&vmcoredd_list, struct vmcoredd_node,
+ list);
+ list_del(&dump->list);
+ vfree(dump->buf);
+ vfree(dump);
+ }
+ mutex_unlock(&vmcoredd_mutex);
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
+}
+
/* Init function for vmcore module. */
static int __init vmcore_init(void)
{
kfree(m);
}
free_elfcorebuf();
+
+ /* clear vmcore device dump list */
+ vmcore_free_device_dumps();
}
if (args->flags & ATTR_CREATE)
return retval;
retval = xfs_attr_shortform_remove(args);
- ASSERT(retval == 0);
+ if (retval)
+ return retval;
+ /*
+ * Since we have removed the old attr, clear ATTR_REPLACE so
+ * that the leaf format add routine won't trip over the attr
+ * not being around.
+ */
+ args->flags &= ~ATTR_REPLACE;
}
if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
*logflagsp = 0;
if ((error = xfs_alloc_vextent(&args))) {
xfs_iroot_realloc(ip, -1, whichfork);
+ ASSERT(ifp->if_broot == NULL);
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
xfs_iroot_realloc(ip, -1, whichfork);
+ ASSERT(ifp->if_broot == NULL);
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return -ENOSPC;
}
return __this_address;
if (di_size > XFS_DFORK_DSIZE(dip, mp))
return __this_address;
+ if (dip->di_nextents)
+ return __this_address;
/* fall through */
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
if (XFS_DFORK_Q(dip)) {
switch (dip->di_aformat) {
case XFS_DINODE_FMT_LOCAL:
+ if (dip->di_anextents)
+ return __this_address;
+ /* fall through */
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
break;
default:
return __this_address;
}
+ } else {
+ /*
+ * If there is no fork offset, this may be a freshly-made inode
+ * in a new disk cluster, in which case di_aformat is zeroed.
+ * Otherwise, such an inode must be in EXTENTS format; this goes
+ * for freed inodes as well.
+ */
+ switch (dip->di_aformat) {
+ case 0:
+ case XFS_DINODE_FMT_EXTENTS:
+ break;
+ default:
+ return __this_address;
+ }
+ if (dip->di_anextents)
+ return __this_address;
}
/* only version 3 or greater inodes are extensively verified here */
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
- unsigned int blksize_mask = i_blocksize(inode) - 1;
+ unsigned int blksize_mask = i_blocksize(inode) - 1;
+ loff_t isize = i_size_read(inode);
- new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
- /* check the new inode size does not wrap through zero */
- if (new_size > inode->i_sb->s_maxbytes) {
+ /*
+ * New inode size must not exceed ->s_maxbytes, accounting for
+ * possible signed overflow.
+ */
+ if (inode->i_sb->s_maxbytes - isize < len) {
error = -EFBIG;
goto out_unlock;
}
+ new_size = isize + len;
/* Offset should be less than i_size */
- if (offset >= i_size_read(inode)) {
+ if (offset >= isize) {
error = -EINVAL;
goto out_unlock;
}
struct file *dst_file,
u64 dst_loff)
{
+ struct inode *srci = file_inode(src_file);
+ u64 max_dedupe;
int error;
+ /*
+ * Since we have to read all these pages in to compare them, cut
+ * it off at MAX_RW_COUNT/2 rounded down to the nearest block.
+ * That means we won't do more than MAX_RW_COUNT IO per request.
+ */
+ max_dedupe = (MAX_RW_COUNT >> 1) & ~(i_blocksize(srci) - 1);
+ if (len > max_dedupe)
+ len = max_dedupe;
error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
len, true);
if (error)
#endif
#ifdef CONFIG_SERIAL_EARLYCON
-#define EARLYCON_TABLE() STRUCT_ALIGN(); \
+#define EARLYCON_TABLE() . = ALIGN(8); \
VMLINUX_SYMBOL(__earlycon_table) = .; \
KEEP(*(__earlycon_table)) \
VMLINUX_SYMBOL(__earlycon_table_end) = .;
#define DRM_HDCP_RI_LEN 2
#define DRM_HDCP_V_PRIME_PART_LEN 4
#define DRM_HDCP_V_PRIME_NUM_PARTS 5
-#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x3f)
+#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x7f)
#define DRM_HDCP_MAX_CASCADE_EXCEEDED(x) (x & BIT(3))
#define DRM_HDCP_MAX_DEVICE_EXCEEDED(x) (x & BIT(7))
#define I2C6 63
#define USART1 64
#define RTCAPB 65
-#define TZC 66
+#define TZC1 66
#define TZPC 67
#define IWDG1 68
#define BSEC 69
#define CRC1 110
#define USBH 111
#define ETHSTP 112
+#define TZC2 113
/* Kernel clocks */
#define SDMMC1_K 118
#define CK_MCO2 212
/* TRACE & DEBUG clocks */
-#define DBG 213
#define CK_DBG 214
#define CK_TRACE 215
* Our PSCI implementation stays the same across versions from
* v0.2 onward, only adding the few mandatory functions (such
* as FEATURES with 1.0) that are required by newer
- * revisions. It is thus safe to return the latest.
+ * revisions. It is thus safe to return the latest, unless
+ * userspace has instructed us otherwise.
*/
- if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) {
+ if (vcpu->kvm->arch.psci_version)
+ return vcpu->kvm->arch.psci_version;
+
return KVM_ARM_PSCI_LATEST;
+ }
return KVM_ARM_PSCI_0_1;
}
int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+struct kvm_one_reg;
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
#endif /* __KVM_ARM_PSCI_H__ */
u32 mpidr; /* GICv3 target VCPU */
};
u8 source; /* GICv2 SGIs only */
+ u8 active_source; /* GICv2 SGIs only */
u8 priority;
enum vgic_irq_config config; /* Level or edge */
struct virtchnl_rss_lut {
u16 vsi_id;
u16 lut_entries;
- u8 lut[1]; /* RSS lookup table*/
+ u8 lut[1]; /* RSS lookup table */
};
VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);
return VIRTCHNL_ERR_PARAM;
}
/* few more checks */
- if ((valid_len != msglen) || (err_msg_format))
+ if (err_msg_format || valid_len != msglen)
return VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH;
return 0;
set_wb_congested(bdi->wb.congested, sync);
}
+struct wb_lock_cookie {
+ bool locked;
+ unsigned long flags;
+};
+
#ifdef CONFIG_CGROUP_WRITEBACK
/**
/**
* unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
* @inode: target inode
- * @lockedp: temp bool output param, to be passed to the end function
+ * @cookie: output param, to be passed to the end function
*
* The caller wants to access the wb associated with @inode but isn't
* holding inode->i_lock, the i_pages lock or wb->list_lock. This
* association doesn't change until the transaction is finished with
* unlocked_inode_to_wb_end().
*
- * The caller must call unlocked_inode_to_wb_end() with *@lockdep
- * afterwards and can't sleep during transaction. IRQ may or may not be
- * disabled on return.
+ * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
+ * can't sleep during the transaction. IRQs may or may not be disabled on
+ * return.
*/
static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
rcu_read_lock();
* Paired with store_release in inode_switch_wb_work_fn() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
- *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
- if (unlikely(*lockedp))
- xa_lock_irq(&inode->i_mapping->i_pages);
+ if (unlikely(cookie->locked))
+ xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
/*
* Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages
/**
* unlocked_inode_to_wb_end - end inode wb access transaction
* @inode: target inode
- * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ * @cookie: @cookie from unlocked_inode_to_wb_begin()
*/
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+ struct wb_lock_cookie *cookie)
{
- if (unlikely(locked))
- xa_unlock_irq(&inode->i_mapping->i_pages);
+ if (unlikely(cookie->locked))
+ xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags);
rcu_read_unlock();
}
}
static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
return inode_to_wb(inode);
}
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+ struct wb_lock_cookie *cookie)
{
}
struct blk_mq_tags;
struct blk_flush_queue;
+/**
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ */
struct blk_mq_hw_ctx {
struct {
spinlock_t lock;
* initialized by the low level device driver (e.g. scsi/sd.c).
* Stacking drivers (device mappers) may or may not initialize
* these fields.
+ *
+ * Reads of this information must be protected with blk_queue_enter() /
+ * blk_queue_exit(). Modifying this information is only allowed while
+ * no requests are being processed. See also blk_mq_freeze_queue() and
+ * blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
unsigned long *seq_zones_bitmap;
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_preempt_only(q) \
test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
extern int blk_set_preempt_only(struct request_queue *q);
extern void blk_clear_preempt_only(struct request_queue *q);
void (*map_release)(struct bpf_map *map, struct file *map_file);
void (*map_free)(struct bpf_map *map);
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+ void (*map_release_uref)(struct bpf_map *map);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
return container_of(map, struct bpf_offloaded_map, map);
}
+static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
+{
+ return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return map->ops->map_seq_show_elem && map->ops->map_check_btf;
struct bpf_insn_access_aux *info);
int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
const struct bpf_prog *prog);
+ int (*gen_ld_abs)(const struct bpf_insn *orig,
+ struct bpf_insn *insn_buf);
u32 (*convert_ctx_access)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt);
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
struct bpf_prog **_prog, *__prog; \
struct bpf_prog_array *_array; \
u32 _ret = 1; \
+ preempt_disable(); \
rcu_read_lock(); \
_array = rcu_dereference(array); \
if (unlikely(check_non_null && !_array))\
} \
_out: \
rcu_read_unlock(); \
+ preempt_enable_no_resched(); \
_ret; \
})
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
-void bpf_fd_array_map_clear(struct bpf_map *map);
int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
-static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
{
return aux->offload_requested;
}
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET)
struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
+struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
#else
static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
return NULL;
}
+static inline struct sock *__sock_hash_lookup_elem(struct bpf_map *map,
+ void *key)
+{
+ return NULL;
+}
+
static inline int sock_map_prog(struct bpf_map *map,
struct bpf_prog *prog,
u32 type)
}
#endif
+#if defined(CONFIG_XDP_SOCKETS)
+struct xdp_sock;
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs);
+void __xsk_map_flush(struct bpf_map *map);
+#else
+struct xdp_sock;
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+ u32 key)
+{
+ return NULL;
+}
+
+static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void __xsk_map_flush(struct bpf_map *map)
+{
+}
+#endif
+
/* verifier prototypes for helper functions called from eBPF programs */
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
-extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
-extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto;
+extern const struct bpf_func_proto bpf_get_stack_proto;
extern const struct bpf_func_proto bpf_sock_map_update_proto;
+extern const struct bpf_func_proto bpf_sock_hash_update_proto;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
#ifndef __LINUX_BPF_TRACE_H__
#define __LINUX_BPF_TRACE_H__
-#include <trace/events/bpf.h>
#include <trace/events/xdp.h>
#endif /* __LINUX_BPF_TRACE_H__ */
BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET)
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
+#if defined(CONFIG_XDP_SOCKETS)
+BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
+#endif
#endif
#define BPF_MAX_SUBPROGS 256
+struct bpf_subprog_info {
+ u32 start; /* insn idx of function entry point */
+ u16 stack_depth; /* max. stack depth used by this function */
+};
+
/* single container for all structs
* one verifier_env per bpf_check() call
*/
bool seen_direct_write;
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
struct bpf_verifier_log log;
- u32 subprog_starts[BPF_MAX_SUBPROGS];
- /* computes the stack depth of each bpf function */
- u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1];
+ struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
u32 subprog_cnt;
};
-void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
- va_list args);
+__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
+ const char *fmt, va_list args);
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
const char *fmt, ...);
#define PHY_ID_BCM54612E 0x03625e60
#define PHY_ID_BCM54616S 0x03625d10
#define PHY_ID_BCM57780 0x03625d90
+#define PHY_ID_BCM89610 0x03625cd0
#define PHY_ID_BCM7250 0xae025280
#define PHY_ID_BCM7260 0xae025190
u32 *ret_size);
void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
struct seq_file *m);
+int btf_get_fd_by_id(u32 id);
+u32 btf_id(const struct btf *btf);
#endif
u32 bio_length;
};
#endif /* CONFIG_BLOCK */
- struct ceph_bvec_iter bvec_pos;
+ struct {
+ struct ceph_bvec_iter bvec_pos;
+ u32 num_bvecs;
+ };
};
};
struct ceph_bio_iter *bio_pos,
u32 bio_length);
#endif /* CONFIG_BLOCK */
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes);
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
unsigned int which,
struct ceph_bvec_iter *bvec_pos);
bool own_pages);
void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
unsigned int which,
- struct bio_vec *bvecs, u32 bytes);
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes);
extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
int __clk_determine_rate(struct clk_hw *core, struct clk_rate_request *req);
int __clk_mux_determine_rate_closest(struct clk_hw *hw,
struct clk_rate_request *req);
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+ struct clk_rate_request *req,
+ unsigned long flags);
void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent);
void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate,
unsigned long max_rate);
#define __SANITIZE_ADDRESS__
#endif
+#undef __no_sanitize_address
+#define __no_sanitize_address __attribute__((no_sanitize("address")))
+
/* Clang doesn't have a way to turn it off per-function, yet. */
#ifdef __noretpoline
#undef __noretpoline
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef _LINUX_CORESIGHT_PMU_H
#include <linux/kexec.h>
#include <linux/proc_fs.h>
#include <linux/elf.h>
+#include <uapi/linux/vmcore.h>
#include <asm/pgtable.h> /* for pgprot_t */
#endif /* CONFIG_CRASH_DUMP */
extern unsigned long saved_max_pfn;
+
+/* Device Dump information to be filled by drivers */
+struct vmcoredd_data {
+ char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */
+ unsigned int size; /* Size of the dump */
+ /* Driver's registered callback to be invoked to collect dump */
+ int (*vmcoredd_callback)(struct vmcoredd_data *data, void *buf);
+};
+
+#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+int vmcore_add_device_dump(struct vmcoredd_data *data);
+#else
+static inline int vmcore_add_device_dump(struct vmcoredd_data *data)
+{
+ return -EOPNOTSUPP;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
#endif /* LINUX_CRASHDUMP_H */
* automatically.
* @pm: Power management operations of the device which matched
* this driver.
- * @coredump: Called through sysfs to initiate a device coredump.
+ * @coredump: Called when sysfs entry is written to. The device driver
+ * is expected to call the dev_coredump API resulting in a
+ * uevent.
* @p: Driver core's private data, no one other than the driver
* core can touch this.
*
const struct attribute_group **groups;
const struct dev_pm_ops *pm;
- int (*coredump) (struct device *dev);
+ void (*coredump) (struct device *dev);
struct driver_private *p;
};
u32 attributes;
u32 get_bar_attributes;
u32 set_bar_attributes;
- uint64_t romsize;
- void *romimage;
+ u64 romsize;
+ u32 romimage;
} efi_pci_io_protocol_32;
typedef struct {
u64 attributes;
u64 get_bar_attributes;
u64 set_bar_attributes;
- uint64_t romsize;
- void *romimage;
+ u64 romsize;
+ u64 romimage;
} efi_pci_io_protocol_64;
typedef struct {
* fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS
* instead of the latter), any change to them will be overwritten
* by kernel. Returns a negative error code or zero.
+ * @get_fecparam: Get the network device Forward Error Correction parameters.
+ * @set_fecparam: Set the network device Forward Error Correction parameters.
+ * @get_ethtool_phy_stats: Return extended statistics about the PHY device.
+ * This is only useful if the device maintains PHY statistics and
+ * cannot use the standard PHY library helpers.
*
* All operations are optional (i.e. the function pointer may be set
* to %NULL) and callers must take this into account. Callers must
struct ethtool_fecparam *);
int (*set_fecparam)(struct net_device *,
struct ethtool_fecparam *);
+ void (*get_ethtool_phy_stats)(struct net_device *,
+ struct ethtool_stats *, u64 *);
};
#endif /* _LINUX_ETHTOOL_H */
/* Additional register mappings for converted user programs. */
#define BPF_REG_A BPF_REG_0
#define BPF_REG_X BPF_REG_7
-#define BPF_REG_TMP BPF_REG_8
+#define BPF_REG_TMP BPF_REG_2 /* scratch reg */
+#define BPF_REG_D BPF_REG_8 /* data, callee-saved */
+#define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */
/* Kernel hidden auxiliary/helper register for hardening step.
* Only used by eBPF JITs. It's nothing more than a temporary
dst_needed:1, /* Do we need dst entry? */
blinded:1, /* Was blinded */
is_func:1, /* program is a bpf function */
- kprobe_override:1; /* Do we override a kprobe? */
+ kprobe_override:1, /* Do we override a kprobe? */
+ has_callchain_buf:1; /* callchain buffer allocated? */
enum bpf_prog_type type; /* Type of BPF program */
enum bpf_attach_type expected_attach_type; /* For some prog types */
u32 len; /* Number of filter blocks */
int sg_end;
struct scatterlist sg_data[MAX_SKB_FRAGS];
bool sg_copy[MAX_SKB_FRAGS];
- __u32 key;
__u32 flags;
- struct bpf_map *map;
+ struct sock *sk_redir;
struct sk_buff *skb;
struct list_head list;
};
* This does not appear to be a real limitation for existing software.
*/
int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *prog);
+ struct xdp_buff *xdp, struct bpf_prog *prog);
int xdp_do_redirect(struct net_device *dev,
struct xdp_buff *xdp,
struct bpf_prog *prog);
union { /* Object pointer [lock] */
struct inode *inode;
struct vfsmount *mnt;
- };
- union {
- struct hlist_head list;
/* Used listing heads to free after srcu period expires */
struct fsnotify_mark_connector *destroy_next;
};
+ struct hlist_head list;
};
/*
part_stat_add(cpu, gendiskp, field, -subnd)
void part_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
+ unsigned int inflight[2]);
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2]);
void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
int rw);
void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
HRTIMER_BASE_REALTIME,
+ HRTIMER_BASE_BOOTTIME,
HRTIMER_BASE_TAI,
HRTIMER_BASE_MONOTONIC_SOFT,
HRTIMER_BASE_REALTIME_SOFT,
+ HRTIMER_BASE_BOOTTIME_SOFT,
HRTIMER_BASE_TAI_SOFT,
HRTIMER_MAX_CLOCK_BASES,
};
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING)
bool br_vlan_enabled(const struct net_device *dev);
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid);
+int br_vlan_get_info(const struct net_device *dev, u16 vid,
+ struct bridge_vlan_info *p_vinfo);
#else
static inline bool br_vlan_enabled(const struct net_device *dev)
{
return false;
}
+
+static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
+{
+ return -1;
+}
+
+static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
+ struct bridge_vlan_info *p_vinfo)
+{
+ return -1;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_BRIDGE)
+struct net_device *br_fdb_find_port(const struct net_device *br_dev,
+ const unsigned char *addr,
+ __u16 vid);
+#else
+static inline struct net_device *
+br_fdb_find_port(const struct net_device *br_dev,
+ const unsigned char *addr,
+ __u16 vid)
+{
+ return NULL;
+}
#endif
#endif
struct hlist_node hlist;
struct macvlan_port *port;
struct net_device *lowerdev;
- void *fwd_priv;
+ void *accel_priv;
struct vlan_pcpu_stats __percpu *pcpu_stats;
DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ);
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack);
-extern void macvlan_count_rx(const struct macvlan_dev *vlan,
- unsigned int len, bool success,
- bool multicast);
-
extern void macvlan_dellink(struct net_device *dev, struct list_head *head);
extern int macvlan_link_register(struct rtnl_link_ops *ops);
}
#endif
+static inline void *macvlan_accel_priv(struct net_device *dev)
+{
+ struct macvlan_dev *macvlan = netdev_priv(dev);
+
+ return macvlan->accel_priv;
+}
+
+static inline bool macvlan_supports_dest_filter(struct net_device *dev)
+{
+ struct macvlan_dev *macvlan = netdev_priv(dev);
+
+ return macvlan->mode == MACVLAN_MODE_PRIVATE ||
+ macvlan->mode == MACVLAN_MODE_VEPA ||
+ macvlan->mode == MACVLAN_MODE_BRIDGE;
+}
+
+static inline int macvlan_release_l2fw_offload(struct net_device *dev)
+{
+ struct macvlan_dev *macvlan = netdev_priv(dev);
+
+ macvlan->accel_priv = NULL;
+ return dev_uc_add(macvlan->lowerdev, dev->dev_addr);
+}
#endif /* _LINUX_IF_MACVLAN_H */
loff_t offset;
};
+struct vmcoredd_node {
+ struct list_head list; /* List of dumps */
+ void *buf; /* Buffer containing device's dump */
+ unsigned int size; /* Size of the buffer */
+};
+
#ifdef CONFIG_PROC_KCORE
extern void kclist_add(struct kcore_list *, void *, size_t, int type);
#else
int kthread_park(struct task_struct *k);
void kthread_unpark(struct task_struct *k);
void kthread_parkme(void);
+void kthread_park_complete(struct task_struct *k);
int kthreadd(void *unused);
extern struct task_struct *kthreadd_task;
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-#ifdef CONFIG_S390
-#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
-#elif defined(CONFIG_ARM64)
-#define KVM_MAX_IRQ_ROUTES 4096
-#else
-#define KVM_MAX_IRQ_ROUTES 1024
-#endif
+#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36,
MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37,
MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38,
+ MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39,
};
enum {
};
static inline const struct cpumask *
-mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
+mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
{
- const struct cpumask *mask;
- struct irq_desc *desc;
- unsigned int irq;
- int eqn;
- int err;
-
- err = mlx5_vector2eqn(dev, MLX5_EQ_VEC_COMP_BASE + vector, &eqn, &irq);
- if (err)
- return NULL;
-
- desc = irq_to_desc(irq);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
- mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
-#else
- mask = desc->irq_common_data.affinity;
-#endif
- return mask;
+ return dev->priv.irq_info[vector].mask;
}
#endif /* MLX5_DRIVER_H */
union {
u32 tir_num;
struct mlx5_flow_table *ft;
- u32 vport_num;
struct mlx5_fc *counter;
+ struct {
+ u16 num;
+ u16 vhca_id;
+ bool vhca_id_valid;
+ } vport;
};
};
u8 reserved_at_6[0x1a];
};
-struct mlx5_ifc_ipv4_layout_bits {
- u8 reserved_at_0[0x60];
-
- u8 ipv4[0x20];
-};
-
-struct mlx5_ifc_ipv6_layout_bits {
- u8 ipv6[16][0x8];
-};
-
-union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
- struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
- struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
- u8 reserved_at_0[0x80];
-};
-
struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
u8 smac_47_16[0x20];
u8 reserved_at_0[0x8];
u8 source_sqn[0x18];
- u8 reserved_at_20[0x10];
+ u8 source_eswitch_owner_vhca_id[0x10];
u8 source_port[0x10];
u8 outer_second_prio[0x3];
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x19];
+ u8 reserved_at_5[0x18];
+ u8 merged_eswitch[0x1];
u8 nic_vport_node_guid_modify[0x1];
u8 nic_vport_port_guid_modify[0x1];
struct mlx5_ifc_dest_format_struct_bits {
u8 destination_type[0x8];
u8 destination_id[0x18];
-
- u8 reserved_at_20[0x20];
+ u8 destination_eswitch_owner_vhca_id_valid[0x1];
+ u8 reserved_at_21[0xf];
+ u8 destination_eswitch_owner_vhca_id[0x10];
};
struct mlx5_ifc_flow_counter_list_bits {
u8 reserved_at_a0[0x8];
u8 table_id[0x18];
- u8 reserved_at_c0[0x20];
+ u8 source_eswitch_owner_vhca_id_valid[0x1];
+
+ u8 reserved_at_c1[0x1f];
u8 start_flow_index[0x20];
#ifndef MLX5_IFC_FPGA_H
#define MLX5_IFC_FPGA_H
+struct mlx5_ifc_ipv4_layout_bits {
+ u8 reserved_at_0[0x60];
+
+ u8 ipv4[0x20];
+};
+
+struct mlx5_ifc_ipv6_layout_bits {
+ u8 ipv6[16][0x8];
+};
+
+union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
+ struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
+ struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
+ u8 reserved_at_0[0x80];
+};
+
enum {
MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9,
};
enum {
MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2,
+ MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3,
};
struct mlx5_ifc_fpga_shell_caps_bits {
u8 reserved_at_40[0x40];
};
+struct mlx5_ifc_tls_extended_cap_bits {
+ u8 aes_gcm_128[0x1];
+ u8 aes_gcm_256[0x1];
+ u8 reserved_at_2[0x1e];
+ u8 reserved_at_20[0x20];
+ u8 context_capacity_total[0x20];
+ u8 context_capacity_rx[0x20];
+ u8 context_capacity_tx[0x20];
+ u8 reserved_at_a0[0x10];
+ u8 tls_counter_size[0x10];
+ u8 tls_counters_addr_low[0x20];
+ u8 tls_counters_addr_high[0x20];
+ u8 rx[0x1];
+ u8 tx[0x1];
+ u8 tls_v12[0x1];
+ u8 tls_v13[0x1];
+ u8 lro[0x1];
+ u8 ipv6[0x1];
+ u8 reserved_at_106[0x1a];
+};
+
struct mlx5_ifc_ipsec_extended_cap_bits {
u8 encapsulation[0x20];
__be16 reserved2;
} __packed;
+enum fpga_tls_cmds {
+ CMD_SETUP_STREAM = 0x1001,
+ CMD_TEARDOWN_STREAM = 0x1002,
+};
+
+#define MLX5_TLS_1_2 (0)
+
+#define MLX5_TLS_ALG_AES_GCM_128 (0)
+#define MLX5_TLS_ALG_AES_GCM_256 (1)
+
+struct mlx5_ifc_tls_cmd_bits {
+ u8 command_type[0x20];
+ u8 ipv6[0x1];
+ u8 direction_sx[0x1];
+ u8 tls_version[0x2];
+ u8 reserved[0x1c];
+ u8 swid[0x20];
+ u8 src_port[0x10];
+ u8 dst_port[0x10];
+ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6;
+ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
+ u8 tls_rcd_sn[0x40];
+ u8 tcp_sn[0x20];
+ u8 tls_implicit_iv[0x20];
+ u8 tls_xor_iv[0x40];
+ u8 encryption_key[0x100];
+ u8 alg[4];
+ u8 reserved2[0x1c];
+ u8 reserved3[0x4a0];
+};
+
+struct mlx5_ifc_tls_resp_bits {
+ u8 syndrome[0x20];
+ u8 stream_id[0x20];
+ u8 reserverd[0x40];
+};
+
+#define MLX5_TLS_COMMAND_SIZE (0x100)
+
#endif /* MLX5_IFC_FPGA_H */
return VM_FAULT_NOPAGE;
}
+static inline vm_fault_t vmf_error(int err)
+{
+ if (err == -ENOMEM)
+ return VM_FAULT_OOM;
+ return VM_FAULT_SIGBUS;
+}
+
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int foll_flags,
unsigned int *page_mask);
#define FOLL_MLOCK 0x1000 /* lock present pages */
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
#define FOLL_COW 0x4000 /* internal GUP flag */
+#define FOLL_ANON 0x8000 /* don't do file mappings */
static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
{
#define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335
#define SDIO_DEVICE_ID_BROADCOM_4339 0x4339
#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962
+#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4
#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6
#define SDIO_DEVICE_ID_BROADCOM_4345 0x4345
#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf
unsigned int write_suspended:1;
unsigned int erase_suspended:1;
unsigned long in_progress_block_addr;
+ unsigned long in_progress_block_mask;
struct mutex mutex;
wait_queue_head_t wq; /* Wait on here when we're waiting for the chip
({ \
int i, ret = 1; \
for (i = 0; i < map_words(map); i++) { \
- if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) { \
+ if (((val1).x[i] & (val2).x[i]) != (val3).x[i]) { \
ret = 0; \
break; \
} \
* tBERS (during an erase) which all of them are u64 values that cannot be
* divided by usual kernel macros and must be handled with the special
* DIV_ROUND_UP_ULL() macro.
+ *
+ * Cast to type of dividend is needed here to guarantee that the result won't
+ * be an unsigned long long when the dividend is an unsigned long (or smaller),
+ * which is what the compiler does when it sees ternary operator with 2
+ * different return types (picks the largest type to make sure there's no
+ * loss).
*/
-#define __DIVIDE(dividend, divisor) ({ \
- sizeof(dividend) == sizeof(u32) ? \
- DIV_ROUND_UP(dividend, divisor) : \
- DIV_ROUND_UP_ULL(dividend, divisor); \
- })
+#define __DIVIDE(dividend, divisor) ({ \
+ (__typeof__(dividend))(sizeof(dividend) <= sizeof(unsigned long) ? \
+ DIV_ROUND_UP(dividend, divisor) : \
+ DIV_ROUND_UP_ULL(dividend, divisor)); \
+ })
#define PSEC_TO_NSEC(x) __DIVIDE(x, 1000)
#define PSEC_TO_MSEC(x) __DIVIDE(x, 1000000000)
#define NET_DIM_PARAMS_NUM_PROFILES 5
/* Adaptive moderation profiles */
#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128
#define NET_DIM_DEF_PROFILE_CQE 1
#define NET_DIM_DEF_PROFILE_EQE 1
/* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */
-#define NET_DIM_EQE_PROFILES { \
+#define NET_DIM_RX_EQE_PROFILES { \
{1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
{8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
{64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
{256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
}
-#define NET_DIM_CQE_PROFILES { \
+#define NET_DIM_RX_CQE_PROFILES { \
{2, 256}, \
{8, 128}, \
{16, 64}, \
{64, 64} \
}
+#define NET_DIM_TX_EQE_PROFILES { \
+ {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \
+}
+
+#define NET_DIM_TX_CQE_PROFILES { \
+ {5, 128}, \
+ {8, 64}, \
+ {16, 32}, \
+ {32, 32}, \
+ {64, 32} \
+}
+
static const struct net_dim_cq_moder
-profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
- NET_DIM_EQE_PROFILES,
- NET_DIM_CQE_PROFILES,
+rx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+ NET_DIM_RX_EQE_PROFILES,
+ NET_DIM_RX_CQE_PROFILES,
};
-static inline struct net_dim_cq_moder net_dim_get_profile(u8 cq_period_mode,
- int ix)
+static const struct net_dim_cq_moder
+tx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+ NET_DIM_TX_EQE_PROFILES,
+ NET_DIM_TX_CQE_PROFILES,
+};
+
+static inline struct net_dim_cq_moder
+net_dim_get_rx_moderation(u8 cq_period_mode, int ix)
{
- struct net_dim_cq_moder cq_moder;
+ struct net_dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix];
- cq_moder = profile[cq_period_mode][ix];
cq_moder.cq_period_mode = cq_period_mode;
return cq_moder;
}
-static inline struct net_dim_cq_moder net_dim_get_def_profile(u8 rx_cq_period_mode)
+static inline struct net_dim_cq_moder
+net_dim_get_def_rx_moderation(u8 cq_period_mode)
+{
+ u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+ NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
+
+ return net_dim_get_rx_moderation(cq_period_mode, profile_ix);
+}
+
+static inline struct net_dim_cq_moder
+net_dim_get_tx_moderation(u8 cq_period_mode, int ix)
{
- int default_profile_ix;
+ struct net_dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix];
+
+ cq_moder.cq_period_mode = cq_period_mode;
+ return cq_moder;
+}
- if (rx_cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE)
- default_profile_ix = NET_DIM_DEF_PROFILE_CQE;
- else /* NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE */
- default_profile_ix = NET_DIM_DEF_PROFILE_EQE;
+static inline struct net_dim_cq_moder
+net_dim_get_def_tx_moderation(u8 cq_period_mode)
+{
+ u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+ NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
- return net_dim_get_profile(rx_cq_period_mode, default_profile_ix);
+ return net_dim_get_tx_moderation(cq_period_mode, profile_ix);
}
static inline bool net_dim_on_top(struct net_dim *dim)
NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */
NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */
NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */
+ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */
/**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */
- NETIF_F_GSO_UDP_BIT,
+ NETIF_F_GSO_UDP_L4_BIT,
NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */
NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */
NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */
NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */
NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
+ NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */
NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */
#define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM)
#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT)
#define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD)
+#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
+#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX)
#define for_each_netdev_feature(mask_addr, bit) \
for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
NETIF_F_GSO_GRE_CSUM | \
NETIF_F_GSO_IPXIP4 | \
NETIF_F_GSO_IPXIP6 | \
+ NETIF_F_GSO_UDP_L4 | \
NETIF_F_GSO_UDP_TUNNEL | \
NETIF_F_GSO_UDP_TUNNEL_CSUM)
};
#endif
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+enum tls_offload_ctx_dir {
+ TLS_OFFLOAD_CTX_DIR_RX,
+ TLS_OFFLOAD_CTX_DIR_TX,
+};
+
+struct tls_crypto_info;
+struct tls_context;
+
+struct tlsdev_ops {
+ int (*tls_dev_add)(struct net_device *netdev, struct sock *sk,
+ enum tls_offload_ctx_dir direction,
+ struct tls_crypto_info *crypto_info,
+ u32 start_offload_tcp_sn);
+ void (*tls_dev_del)(struct net_device *netdev,
+ struct tls_context *ctx,
+ enum tls_offload_ctx_dir direction);
+};
+#endif
+
struct dev_ifalias {
struct rcu_head rcuhead;
char ifalias[];
const struct xfrmdev_ops *xfrmdev_ops;
#endif
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+ const struct tlsdev_ops *tlsdev_ops;
+#endif
+
const struct header_ops *header_ops;
unsigned int flags;
int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
int dev_queue_xmit(struct sk_buff *skb);
int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
+int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
}
#endif
-u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
- unsigned int num_tx_queues);
-
-/*
- * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used
- * as a distribution range limit for the returned value.
- */
-static inline u16 skb_tx_hash(const struct net_device *dev,
- struct sk_buff *skb)
-{
- return __skb_tx_hash(dev, skb, dev->real_num_tx_queues);
-}
-
/**
* netif_is_multiqueue - test if device has multiple transmit queues
* @dev: network device
BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
return (features & feature) == feature;
}
--- /dev/null
+#include <uapi/linux/netfilter/nf_osf.h>
+
+/* Initial window size option state machine: multiple of mss, mtu or
+ * plain numeric value. Can also be made as plain numeric value which
+ * is not a multiple of specified value.
+ */
+enum nf_osf_window_size_options {
+ OSF_WSS_PLAIN = 0,
+ OSF_WSS_MSS,
+ OSF_WSS_MTU,
+ OSF_WSS_MODULO,
+ OSF_WSS_MAX,
+};
+
+enum osf_fmatch_states {
+ /* Packet does not match the fingerprint */
+ FMATCH_WRONG = 0,
+ /* Packet matches the fingerprint */
+ FMATCH_OK,
+ /* Options do not match the fingerprint, but header does */
+ FMATCH_OPT_WRONG,
+};
+
+bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
+ int hooknum, struct net_device *in, struct net_device *out,
+ const struct nf_osf_info *info, struct net *net,
+ const struct list_head *nf_osf_fingers);
#include <linux/if_ether.h>
#include <uapi/linux/netfilter_bridge/ebtables.h>
-/* return values for match() functions */
-#define EBT_MATCH 0
-#define EBT_NOMATCH 1
-
struct ebt_match {
struct list_head list;
const char name[EBT_FUNCTION_MAXNAMELEN];
return 0;
}
+void __oom_reap_task_mm(struct mm_struct *mm);
+
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
lock_release(&sem->rw_sem.dep_map, 1, ip);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
if (!read)
- sem->rw_sem.owner = NULL;
+ sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN;
#endif
}
bool read, unsigned long ip)
{
lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+ if (!read)
+ sem->rw_sem.owner = current;
+#endif
}
#endif
void mdio_bus_exit(void);
#endif
+/* Inline function for use within net/core/ethtool.c (built-in) */
+static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
+{
+ if (!phydev->drv)
+ return -EIO;
+
+ mutex_lock(&phydev->lock);
+ phydev->drv->get_strings(phydev, data);
+ mutex_unlock(&phydev->lock);
+
+ return 0;
+}
+
+static inline int phy_ethtool_get_sset_count(struct phy_device *phydev)
+{
+ int ret;
+
+ if (!phydev->drv)
+ return -EIO;
+
+ if (phydev->drv->get_sset_count &&
+ phydev->drv->get_strings &&
+ phydev->drv->get_stats) {
+ mutex_lock(&phydev->lock);
+ ret = phydev->drv->get_sset_count(phydev);
+ mutex_unlock(&phydev->lock);
+
+ return ret;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static inline int phy_ethtool_get_stats(struct phy_device *phydev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ if (!phydev->drv)
+ return -EIO;
+
+ mutex_lock(&phydev->lock);
+ phydev->drv->get_stats(phydev, stats, data);
+ mutex_unlock(&phydev->lock);
+
+ return 0;
+}
+
extern struct bus_type mdio_bus_type;
struct mdio_board_info {
PHY_MODE_USB_DEVICE_SS,
PHY_MODE_USB_OTG,
PHY_MODE_SGMII,
+ PHY_MODE_2500SGMII,
PHY_MODE_10GKR,
PHY_MODE_UFS_HS_A,
PHY_MODE_UFS_HS_B,
#define __B53_H
#include <linux/kernel.h>
+#include <net/dsa.h>
struct b53_platform_data {
+ /* Must be first such that dsa_register_switch() can access it */
+ struct dsa_chip_data cd;
+
u32 chip_id;
u16 enabled_ports;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DSA_MV88E6XXX_H
+#define __DSA_MV88E6XXX_H
+
+#include <net/dsa.h>
+
+struct dsa_mv88e6xxx_pdata {
+ /* Must be first, such that dsa_register_switch() can access this
+ * without gory pointer manipulations
+ */
+ struct dsa_chip_data cd;
+ const char *compatible;
+ unsigned int enabled_ports;
+ struct net_device *netdev;
+ u32 eeprom_len;
+};
+
+#endif
u8 num_hwfns;
u8 hw_mac[ETH_ALEN];
- bool is_mf_default;
/* FW version */
u16 fw_major;
#define QED_MFW_VERSION_3_OFFSET 24
u32 flash_size;
- u8 mf_mode;
+ bool b_inter_pf_switch;
bool tx_switching;
bool rdma_supported;
u16 mtu;
bool enable_ip_cksum;
bool enable_l4_cksum;
bool calc_ip_len;
+ bool remove_stag;
};
#define QED_LL2_UNUSED_HANDLE (0xff)
u8 ll2_mac_address[ETH_ALEN];
};
+enum qed_ll2_xmit_flags {
+ /* FIP discovery packet */
+ QED_LL2_XMIT_FLAGS_FIP_DISCOVERY
+};
+
struct qed_ll2_ops {
/**
* @brief start - initializes ll2
*
* @param cdev
* @param skb
+ * @param xmit_flags - Transmit options defined by the enum qed_ll2_xmit_flags.
*
* @return 0 on success, otherwise error value.
*/
- int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb);
+ int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb,
+ unsigned long xmit_flags);
/**
* @brief register_cb_ops - protocol driver register the callback for Rx/Tx
#include <linux/compiler.h>
#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
/*
* Please note - only struct rb_augment_callbacks and the prototypes for
#include <linux/rbtree.h>
#include <linux/seqlock.h>
+#include <linux/rcupdate.h>
struct latch_tree_node {
struct rb_node node[2];
void rproc_add_subdev(struct rproc *rproc,
struct rproc_subdev *subdev,
int (*probe)(struct rproc_subdev *subdev),
- void (*remove)(struct rproc_subdev *subdev, bool graceful));
+ void (*remove)(struct rproc_subdev *subdev, bool crashed));
void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev);
*
* It is safe to call this function from atomic context.
*
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
*/
static inline int rhashtable_insert_fast(
struct rhashtable *ht, struct rhash_head *obj,
*
* It is safe to call this function from atomic context.
*
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
*/
static inline int rhltable_insert_key(
struct rhltable *hlt, const void *key, struct rhlist_head *list,
*
* It is safe to call this function from atomic context.
*
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
*/
static inline int rhltable_insert(
struct rhltable *hlt, struct rhlist_head *list,
*
* It is safe to call this function from atomic context.
*
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
*/
static inline int rhashtable_lookup_insert_fast(
struct rhashtable *ht, struct rhash_head *obj,
*
* Lookups may occur in parallel with hashtable mutations and resizing.
*
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
*
* Returns zero on success.
*/
* walk the bucket chain upon removal. The removal operation is thus
* considerable slow if the hash table is not correctly sized.
*
- * Will automatically shrink the table via rhashtable_expand() if the
- * shrink_decision function specified at rhashtable_init() returns true.
+ * Will automatically shrink the table if permitted when residency drops
+ * below 30%.
*
* Returns zero on success, -ENOENT if the entry could not be found.
*/
* walk the bucket chain upon removal. The removal operation is thus
* considerable slow if the hash table is not correctly sized.
*
- * Will automatically shrink the table via rhashtable_expand() if the
- * shrink_decision function specified at rhashtable_init() returns true.
+ * Will automatically shrink the table if permitted when residency drops
+ * below 30%
*
* Returns zero on success, -ENOENT if the entry could not be found.
*/
* For a completely stable walk you should construct your own data
* structure outside the hash table.
*
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
*
* You must call rhashtable_walk_exit after this function returns.
*/
#endif
};
+/*
+ * Setting bit 0 of the owner field with other non-zero bits will indicate
+ * that the rwsem is writer-owned with an unknown owner.
+ */
+#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-1L)
+
extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+/*
+ * Special states are those that do not use the normal wait-loop pattern. See
+ * the comment with set_special_state().
+ */
+#define is_special_task_state(state) \
+ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+
#define __set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
current->state = (state_value); \
} while (0)
+
#define set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
smp_store_mb(current->state, (state_value)); \
} while (0)
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ WARN_ON_ONCE(!is_special_task_state(state_value)); \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->task_state_change = _THIS_IP_; \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
#else
/*
* set_current_state() includes a barrier so that the write of current->state
*
* The above is typically ordered against the wakeup, which does:
*
- * need_sleep = false;
- * wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ * need_sleep = false;
+ * wake_up_state(p, TASK_UNINTERRUPTIBLE);
*
* Where wake_up_state() (and all other wakeup primitives) imply enough
* barriers to order the store of the variable against wakeup.
* once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
* TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
*
- * This is obviously fine, since they both store the exact same value.
+ * However, with slightly different timing the wakeup TASK_RUNNING store can
+ * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * a problem either because that will result in one extra go around the loop
+ * and our @cond test will save the day.
*
* Also see the comments of try_to_wake_up().
*/
-#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
-#define set_current_state(state_value) smp_store_mb(current->state, (state_value))
+#define __set_current_state(state_value) \
+ current->state = (state_value)
+
+#define set_current_state(state_value) \
+ smp_store_mb(current->state, (state_value))
+
+/*
+ * set_special_state() should be used for those states when the blocking task
+ * can not use the regular condition based wait-loop. In that case we must
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
+ * will not collide with our state change.
+ */
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
+
#endif
/* Task command name length: */
{
spin_lock_irq(¤t->sighand->siglock);
if (current->jobctl & JOBCTL_STOP_DEQUEUED)
- __set_current_state(TASK_STOPPED);
+ set_special_state(TASK_STOPPED);
spin_unlock_irq(¤t->sighand->siglock);
schedule();
char name[16];
char compatible[128];
int (*setup)(struct earlycon_device *, const char *options);
-} __aligned(32);
+};
-extern const struct earlycon_id __earlycon_table[];
-extern const struct earlycon_id __earlycon_table_end[];
+extern const struct earlycon_id *__earlycon_table[];
+extern const struct earlycon_id *__earlycon_table_end[];
#if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE)
#define EARLYCON_USED_OR_UNUSED __used
#define EARLYCON_USED_OR_UNUSED __maybe_unused
#endif
-#define OF_EARLYCON_DECLARE(_name, compat, fn) \
- static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \
- EARLYCON_USED_OR_UNUSED __section(__earlycon_table) \
+#define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id) \
+ static const struct earlycon_id unique_id \
+ EARLYCON_USED_OR_UNUSED __initconst \
= { .name = __stringify(_name), \
.compatible = compat, \
- .setup = fn }
+ .setup = fn }; \
+ static const struct earlycon_id EARLYCON_USED_OR_UNUSED \
+ __section(__earlycon_table) \
+ * const __PASTE(__p, unique_id) = &unique_id
+
+#define OF_EARLYCON_DECLARE(_name, compat, fn) \
+ _OF_EARLYCON_DECLARE(_name, compat, fn, \
+ __UNIQUE_ID(__earlycon_##_name))
#define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn)
return ptr_ring_empty_any(&a->ring);
}
+static inline struct sk_buff *__skb_array_consume(struct skb_array *a)
+{
+ return __ptr_ring_consume(&a->ring);
+}
+
static inline struct sk_buff *skb_array_consume(struct skb_array *a)
{
return ptr_ring_consume(&a->ring);
SKB_GSO_ESP = 1 << 15,
SKB_GSO_UDP = 1 << 16,
+
+ SKB_GSO_UDP_L4 = 1 << 17,
};
#if BITS_PER_LONG > 32
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
+void skb_copy_header(struct sk_buff *new, const struct sk_buff *old);
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority);
struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
gfp_t gfp_mask, bool fclone);
u32 __skb_get_hash_symmetric(const struct sk_buff *skb);
u32 skb_get_poff(const struct sk_buff *skb);
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
- const struct flow_keys *keys, int hlen);
+ const struct flow_keys_basic *keys, int hlen);
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
void *data, int hlen_proto);
NULL, 0, 0, 0, flags);
}
-static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
- void *data, __be16 proto,
- int nhoff, int hlen,
- unsigned int flags)
+static inline bool
+skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb,
+ struct flow_keys_basic *flow, void *data,
+ __be16 proto, int nhoff, int hlen,
+ unsigned int flags)
{
memset(flow, 0, sizeof(*flow));
- return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
+ return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow,
data, proto, nhoff, hlen, flags);
}
static inline void skb_probe_transport_header(struct sk_buff *skb,
const int offset_hint)
{
- struct flow_keys keys;
+ struct flow_keys_basic keys;
if (skb_transport_header_was_set(skb))
return;
- else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
+
+ if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0))
skb_set_transport_header(skb, keys.control.thoff);
else
skb_set_transport_header(skb, offset_hint);
void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
-static inline
-void sock_init_cookie(struct sock *sk)
-{
- u64 res;
-
- res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
- atomic64_set(&sk->sk_cookie, res);
-}
-
u64 sock_gen_cookie(struct sock *sk);
int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
* PF_SMC protocol family that
* reuses AF_INET address family
*/
+#define AF_XDP 44 /* XDP sockets */
-#define AF_MAX 44 /* For now.. */
+#define AF_MAX 45 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
#define PF_KCM AF_KCM
#define PF_QIPCRTR AF_QIPCRTR
#define PF_SMC AF_SMC
+#define PF_XDP AF_XDP
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
#define SOL_NFC 280
#define SOL_KCM 281
#define SOL_TLS 282
+#define SOL_XDP 283
/* IPX options */
#define IPX_TYPE 1
* losing bits). This also has the property (wanted by the dcache)
* that the msbits make a good hash table index.
*/
-static inline unsigned long end_name_hash(unsigned long hash)
+static inline unsigned int end_name_hash(unsigned long hash)
{
- return __hash_32((unsigned int)hash);
+ return hash_long(hash, 32);
}
/*
reord:1; /* reordering detected */
} rack;
u16 advmss; /* Advertised MSS */
+ u8 compressed_ack;
u32 chrono_start; /* Start time in jiffies of a TCP chrono */
u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
u8 chrono_type:2, /* current chronograph type */
unused:2;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
- unused1 : 1,
+ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
repair : 1,
frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
u8 repair_queue;
u32 sacked_out; /* SACK'd packets */
struct hrtimer pacing_timer;
+ struct hrtimer compressed_ack_timer;
/* from STCP, retrans queue hinting */
struct sk_buff* lost_skb_hint;
#define THREAD_ALIGN THREAD_SIZE
#endif
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO)
-#else
-# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT)
-#endif
+#define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO)
/*
* flag set/clear/test wrappers
u32 abort_sr;
} __packed __aligned(8);
+static inline void ti_emif_asm_offsets(void)
+{
+ DEFINE(EMIF_SDCFG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_sdcfg_val));
+ DEFINE(EMIF_TIMING1_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing1_val));
+ DEFINE(EMIF_TIMING2_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing2_val));
+ DEFINE(EMIF_TIMING3_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing3_val));
+ DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
+ DEFINE(EMIF_ZQCFG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_zqcfg_val));
+ DEFINE(EMIF_PMCR_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_pmcr_val));
+ DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
+ DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
+ DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
+ DEFINE(EMIF_COS_CONFIG_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_cos_config));
+ DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
+ DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
+ DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
+ DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ocp_config_val));
+ DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
+ DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
+ DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
+ DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
+ DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
+ DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
+ DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
+
+ BLANK();
+
+ DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
+ DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
+ DEFINE(EMIF_PM_CONFIG_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
+ DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
+ offsetof(struct ti_emif_pm_data, regs_virt));
+ DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
+ offsetof(struct ti_emif_pm_data, regs_phys));
+ DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
+
+ BLANK();
+
+ DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
+ offsetof(struct ti_emif_pm_functions, save_context));
+ DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
+ offsetof(struct ti_emif_pm_functions, restore_context));
+ DEFINE(EMIF_PM_ENTER_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, enter_sr));
+ DEFINE(EMIF_PM_EXIT_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, exit_sr));
+ DEFINE(EMIF_PM_ABORT_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, abort_sr));
+ DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+}
+
struct gen_pool;
int ti_emif_copy_pm_function_table(struct gen_pool *sram_pool, void *dst);
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
- * @time_suspended: Accumulated suspend time
* @tai_offset: The current UTC to TAI offset in seconds
* @clock_was_set_seq: The sequence number of clock was set events
* @cs_was_changed_seq: The sequence number of clocksource change events
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
- ktime_t time_suspended;
s32 tai_offset;
unsigned int clock_was_set_seq;
u8 cs_was_changed_seq;
extern time64_t ktime_get_seconds(void);
extern time64_t __ktime_get_real_seconds(void);
extern time64_t ktime_get_real_seconds(void);
-extern void ktime_get_active_ts64(struct timespec64 *ts);
extern int __getnstimeofday64(struct timespec64 *tv);
extern void getnstimeofday64(struct timespec64 *tv);
extern void getboottime64(struct timespec64 *ts);
-#define ktime_get_real_ts64(ts) getnstimeofday64(ts)
-
-/* Clock BOOTTIME compatibility wrappers */
-static inline void get_monotonic_boottime64(struct timespec64 *ts)
-{
- ktime_get_ts64(ts);
-}
+#define ktime_get_real_ts64(ts) getnstimeofday64(ts)
/*
* ktime_t based interfaces
*/
+
enum tk_offsets {
TK_OFFS_REAL,
+ TK_OFFS_BOOT,
TK_OFFS_TAI,
TK_OFFS_MAX,
};
extern ktime_t ktime_get_raw(void);
extern u32 ktime_get_resolution_ns(void);
-/* Clock BOOTTIME compatibility wrappers */
-static inline ktime_t ktime_get_boottime(void) { return ktime_get(); }
-static inline u64 ktime_get_boot_ns(void) { return ktime_get(); }
-
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
*/
return ktime_get_with_offset(TK_OFFS_REAL);
}
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in ktime_t format
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the
+ * time spent in suspend.
+ */
+static inline ktime_t ktime_get_boottime(void)
+{
+ return ktime_get_with_offset(TK_OFFS_BOOT);
+}
+
/**
* ktime_get_clocktai - Returns the TAI time of day in ktime_t format
*/
return ktime_to_ns(ktime_get_real());
}
+static inline u64 ktime_get_boot_ns(void)
+{
+ return ktime_to_ns(ktime_get_boottime());
+}
+
static inline u64 ktime_get_tai_ns(void)
{
return ktime_to_ns(ktime_get_clocktai());
extern u64 ktime_get_mono_fast_ns(void);
extern u64 ktime_get_raw_fast_ns(void);
+extern u64 ktime_get_boot_fast_ns(void);
extern u64 ktime_get_real_fast_ns(void);
/*
* timespec64 interfaces utilizing the ktime based ones
*/
+static inline void get_monotonic_boottime64(struct timespec64 *ts)
+{
+ *ts = ktime_to_timespec64(ktime_get_boottime());
+}
+
static inline void timekeeping_clocktai64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_clocktai());
extern void do_gettimeofday(struct timeval *tv);
unsigned long get_seconds(void);
-/* does not take xtime_lock */
-struct timespec __current_kernel_time(void);
-
static inline struct timespec current_kernel_time(void)
{
struct timespec64 now = current_kernel_time64();
#include <linux/debugobjects.h>
#include <linux/stringify.h>
-struct tvec_base;
-
struct timer_list {
/*
* All fields that change during normal runtime grouped to the
/* Arithmetic and logical ops */
/* Shift a tnum left (by a fixed shift) */
struct tnum tnum_lshift(struct tnum a, u8 shift);
-/* Shift a tnum right (by a fixed shift) */
+/* Shift (rsh) a tnum right (by a fixed shift) */
struct tnum tnum_rshift(struct tnum a, u8 shift);
+/* Shift (arsh) a tnum right (by a fixed min_shift) */
+struct tnum tnum_arshift(struct tnum a, u8 min_shift);
/* Add two tnums, return @a + @b */
struct tnum tnum_add(struct tnum a, struct tnum b);
/* Subtract two tnums, return @a - @b */
extern int tty_set_ldisc(struct tty_struct *tty, int disc);
extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty);
extern void tty_ldisc_release(struct tty_struct *tty);
-extern void tty_ldisc_init(struct tty_struct *tty);
+extern int __must_check tty_ldisc_init(struct tty_struct *tty);
extern void tty_ldisc_deinit(struct tty_struct *tty);
extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
char *f, int count);
#endif
}
-static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
- raw_write_seqcount_begin(&syncp->seq);
-#endif
-}
-
-static inline void u64_stats_update_end_raw(struct u64_stats_sync *syncp)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
- raw_write_seqcount_end(&syncp->seq);
-#endif
-}
-
static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
* when the socket is uncorked.
*/
__u16 len; /* total length of pending frames */
+ __u16 gso_size;
/*
* Fields specific to UDP-Lite.
*/
int forward_deficit;
};
+#define UDP_MAX_SEGMENTS (1 << 6UL)
+
static inline struct udp_sock *udp_sk(const struct sock *sk)
{
return (struct udp_sock *)sk;
#define USB_GADGET_DELAYED_STATUS 0x7fff /* Impossibly large value */
/* big enough to hold our biggest descriptor */
-#define USB_COMP_EP0_BUFSIZ 1024
+#define USB_COMP_EP0_BUFSIZ 4096
/* OS feature descriptor length <= 4kB */
#define USB_COMP_EP0_OS_DESC_BUFSIZ 4096
#define vbg_debug pr_debug
#endif
-/**
- * Allocate memory for generic request and initialize the request header.
- *
- * Return: the allocated memory
- * @len: Size of memory block required for the request.
- * @req_type: The generic request type.
- */
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
-
-/**
- * Perform a generic request.
- *
- * Return: VBox status code
- * @gdev: The Guest extension device.
- * @req: Pointer to the request structure.
- */
-int vbg_req_perform(struct vbg_dev *gdev, void *req);
-
int vbg_hgcm_connect(struct vbg_dev *gdev,
struct vmmdev_hgcm_service_location *loc,
u32 *client_id, int *vbox_status);
u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
u32 parm_count, int *vbox_status);
-int vbg_hgcm_call32(
- struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
- struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
- int *vbox_status);
-
/**
* Convert a VirtualBox status code to a standard Linux kernel return value.
* Return: 0 or negative errno value.
int virtio_device_restore(struct virtio_device *dev);
#endif
+#define virtio_device_for_each_vq(vdev, vq) \
+ list_for_each_entry(vq, &vdev->vqs, list)
+
/**
* virtio_driver - operations for a virtio I/O driver
* @driver: underlying device driver (populate name and owner).
__ret; \
})
+/**
+ * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit
+ *
+ * @bit: the bit of the word being waited on
+ * @word: the word being waited on, a kernel virtual address
+ *
+ * You can use this helper if bitflags are manipulated atomically rather than
+ * non-atomically under a lock.
+ */
+static inline void clear_and_wake_up_bit(int bit, void *word)
+{
+ clear_bit_unlock(bit, word);
+ /* See wake_up_bit() for which memory barrier you need to use. */
+ smp_mb__after_atomic();
+ wake_up_bit(word, bit);
+}
+
#endif /* _LINUX_WAIT_BIT_H */
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14
*
/*
* generic helper functions for handling video4linux capture buffers
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
const struct in6_addr *addr);
int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6);
+
+ struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
+ struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
+ struct flowi6 *fl6, int flags);
+ struct fib6_info *(*fib6_table_lookup)(struct net *net,
+ struct fib6_table *table,
+ int oif, struct flowi6 *fl6,
+ int flags);
+ struct fib6_info *(*fib6_multipath_select)(const struct net *net,
+ struct fib6_info *f6i,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb,
+ int strict);
+
void (*udpv6_encap_enable)(void);
void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
const void *param, u32 timeout);
struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
const void *param, u8 event, u32 timeout);
+int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen,
+ const void *param);
int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
const void *param);
struct slave __rcu *primary_slave;
struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
bool force_primary;
+ u32 nest_level;
s32 slave_cnt; /* never change this value outside the attach/detach wrappers */
int (*recv_probe)(const struct sk_buff *, struct bonding *,
struct slave *);
static inline bool bond_is_nondyn_tlb(const struct bonding *bond)
{
- return (BOND_MODE(bond) == BOND_MODE_TLB) &&
- (bond->params.tlb_dynamic_lb == 0);
+ return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0);
+}
+
+static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond)
+{
+ return (BOND_MODE(bond) == BOND_MODE_8023AD ||
+ BOND_MODE(bond) == BOND_MODE_XOR ||
+ BOND_MODE(bond) == BOND_MODE_TLB ||
+ BOND_MODE(bond) == BOND_MODE_ALB);
}
static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond)
char priv[0] __aligned(NETDEV_ALIGN);
};
+struct devlink_port_attrs {
+ bool set;
+ enum devlink_port_flavour flavour;
+ u32 port_number; /* same value as "split group" */
+ bool split;
+ u32 split_subport_number;
+};
+
struct devlink_port {
struct list_head list;
struct devlink *devlink;
enum devlink_port_type type;
enum devlink_port_type desired_type;
void *type_dev;
- bool split;
- u32 split_group;
+ struct devlink_port_attrs attrs;
};
struct devlink_sb_pool_info {
void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev);
void devlink_port_type_clear(struct devlink_port *devlink_port);
-void devlink_port_split_set(struct devlink_port *devlink_port,
- u32 split_group);
+void devlink_port_attrs_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 port_number, bool split,
+ u32 split_subport_number);
+int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
+ char *name, size_t len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
{
}
-static inline void devlink_port_split_set(struct devlink_port *devlink_port,
- u32 split_group)
+static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 port_number, bool split,
+ u32 split_subport_number)
{
}
+static inline int
+devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
+ char *name, size_t len)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int devlink_sb_register(struct devlink *devlink,
unsigned int sb_index, u32 size,
u16 ingress_pools_count,
#include <linux/of.h>
#include <linux/ethtool.h>
#include <linux/net_tstamp.h>
+#include <linux/phy.h>
#include <net/devlink.h>
#include <net/switchdev.h>
struct tc_action;
struct phy_device;
struct fixed_phy_status;
+struct phylink_link_state;
enum dsa_tag_protocol {
DSA_TAG_PROTO_NONE = 0,
u8 stp_state;
struct net_device *bridge_dev;
struct devlink_port devlink_port;
+ struct phylink *pl;
/*
* Original copy of the master netdev ethtool_ops
*/
void (*fixed_link_update)(struct dsa_switch *ds, int port,
struct fixed_phy_status *st);
+ /*
+ * PHYLINK integration
+ */
+ void (*phylink_validate)(struct dsa_switch *ds, int port,
+ unsigned long *supported,
+ struct phylink_link_state *state);
+ int (*phylink_mac_link_state)(struct dsa_switch *ds, int port,
+ struct phylink_link_state *state);
+ void (*phylink_mac_config)(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ const struct phylink_link_state *state);
+ void (*phylink_mac_an_restart)(struct dsa_switch *ds, int port);
+ void (*phylink_mac_link_down)(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ phy_interface_t interface);
+ void (*phylink_mac_link_up)(struct dsa_switch *ds, int port,
+ unsigned int mode,
+ phy_interface_t interface,
+ struct phy_device *phydev);
+ void (*phylink_fixed_state)(struct dsa_switch *ds, int port,
+ struct phylink_link_state *state);
/*
* ethtool hardware statistics.
*/
- void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
+ void (*get_strings)(struct dsa_switch *ds, int port,
+ u32 stringset, uint8_t *data);
void (*get_ethtool_stats)(struct dsa_switch *ds,
int port, uint64_t *data);
- int (*get_sset_count)(struct dsa_switch *ds, int port);
+ int (*get_sset_count)(struct dsa_switch *ds, int port, int sset);
+ void (*get_ethtool_phy_stats)(struct dsa_switch *ds,
+ int port, uint64_t *data);
/*
* ethtool Wake-on-LAN
#define BRCM_TAG_GET_PORT(v) ((v) >> 8)
#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff)
+
+int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data);
+int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data);
+int dsa_port_get_phy_sset_count(struct dsa_port *dp);
+void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up);
+
#endif
return htonl((u32)h_usecs);
}
+/* ERSPAN BSO (Bad/Short/Oversized), see RFC1757
+ * 00b --> Good frame with no error, or unknown integrity
+ * 01b --> Payload is a Short Frame
+ * 10b --> Payload is an Oversized Frame
+ * 11b --> Payload is a Bad Frame with CRC or Alignment Error
+ */
+enum erspan_bso {
+ BSO_NOERROR = 0x0,
+ BSO_SHORT = 0x1,
+ BSO_OVERSIZED = 0x2,
+ BSO_BAD = 0x3,
+};
+
+static inline u8 erspan_detect_bso(struct sk_buff *skb)
+{
+ /* BSO_BAD is not handled because the frame CRC
+ * or alignment error information is in FCS.
+ */
+ if (skb->len < ETH_ZLEN)
+ return BSO_SHORT;
+
+ if (skb->len > ETH_FRAME_LEN)
+ return BSO_OVERSIZED;
+
+ return BSO_NOERROR;
+}
+
static inline void erspan_build_header_v2(struct sk_buff *skb,
u32 id, u8 direction, u16 hwid,
bool truncate, bool is_ipv4)
vlan_tci = ntohs(qp->tci);
}
+ bso = erspan_detect_bso(skb);
skb_push(skb, sizeof(*ershdr) + ERSPAN_V2_MDSIZE);
ershdr = (struct erspan_base_hdr *)skb->data;
memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V2_MDSIZE);
unsigned short int offset[FLOW_DISSECTOR_KEY_MAX];
};
+struct flow_keys_basic {
+ struct flow_dissector_key_control control;
+ struct flow_dissector_key_basic basic;
+};
+
struct flow_keys {
struct flow_dissector_key_control control;
#define FLOW_KEYS_HASH_START_FIELD basic
__be32 flow_get_u32_dst(const struct flow_keys *flow);
extern struct flow_dissector flow_keys_dissector;
-extern struct flow_dissector flow_keys_buf_dissector;
+extern struct flow_dissector flow_keys_basic_dissector;
/* struct flow_keys_digest:
*
* This structure is used to hold a digest of the full flow keys. This is a
* larger "hash" of a flow to allow definitively matching specific flows where
* the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
- * that it can by used in CB of skb (see sch_choke for an example).
+ * that it can be used in CB of skb (see sch_choke for an example).
*/
#define FLOW_KEYS_DIGEST_LEN 16
struct flow_keys_digest {
void *ife_encode(struct sk_buff *skb, u16 metalen);
void *ife_decode(struct sk_buff *skb, u16 *metalen);
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
#include <net/inet_sock.h>
#include <net/request_sock.h>
-#define INET_CSK_DEBUG 1
-
/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS
* @icsk_af_ops Operations which are AF_INET{4,6} specific
* @icsk_ulp_ops Pluggable ULP control hook
* @icsk_ulp_data ULP private data
+ * @icsk_clean_acked Clean acked data hook
* @icsk_listen_portaddr_node hash to the portaddr listener hashtable
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
const struct inet_connection_sock_af_ops *icsk_af_ops;
const struct tcp_ulp_ops *icsk_ulp_ops;
void *icsk_ulp_data;
+ void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
struct hlist_node icsk_listen_portaddr_node;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:6,
void inet_csk_delete_keepalive_timer(struct sock *sk);
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
-#ifdef INET_CSK_DEBUG
-extern const char inet_csk_timer_bug_msg[];
-#endif
-
static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
struct inet_connection_sock *icsk = inet_csk(sk);
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
+ } else {
+ pr_debug("inet_csk BUG: unknown timer value\n");
}
-#ifdef INET_CSK_DEBUG
- else {
- pr_debug("%s", inet_csk_timer_bug_msg);
- }
-#endif
}
/*
struct inet_connection_sock *icsk = inet_csk(sk);
if (when > max_when) {
-#ifdef INET_CSK_DEBUG
pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
sk, what, when, current_text_addr());
-#endif
when = max_when;
}
icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
+ } else {
+ pr_debug("inet_csk BUG: unknown timer value\n");
}
-#ifdef INET_CSK_DEBUG
- else {
- pr_debug("%s", inet_csk_timer_bug_msg);
- }
-#endif
}
static inline unsigned long
__u8 ttl;
__s16 tos;
char priority;
+ __u16 gso_size;
};
struct inet_cork_full {
#define tw_dr __tw_common.skc_tw_dr
int tw_timeout;
+ __u32 tw_mark;
volatile unsigned char tw_substate;
unsigned char tw_rcv_wscale;
__u8 ttl;
__s16 tos;
char priority;
+ __u16 gso_size;
};
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
- unsigned int flags);
+ struct inet_cork *cork, unsigned int flags);
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
struct fib6_info {
struct fib6_table *fib6_table;
- struct fib6_info __rcu *rt6_next;
+ struct fib6_info __rcu *fib6_next;
struct fib6_node __rcu *fib6_node;
/* Multipath routes:
#define for_each_fib6_node_rt_rcu(fn) \
for (rt = rcu_dereference((fn)->leaf); rt; \
- rt = rcu_dereference(rt->rt6_next))
+ rt = rcu_dereference(rt->fib6_next))
#define for_each_fib6_walker_rt(w) \
for (rt = (w)->leaf; rt; \
- rt = rcu_dereference_protected(rt->rt6_next, 1))
+ rt = rcu_dereference_protected(rt->fib6_next, 1))
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
{
const struct sk_buff *skb,
int flags, pol_lookup_t lookup);
-struct fib6_node *fib6_lookup(struct fib6_node *root,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr);
+/* called with rcu lock held; can return error pointer
+ * caller needs to select path
+ */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ int flags);
+
+/* called with rcu lock held; caller needs to select path */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int strict);
+
+struct fib6_info *fib6_multipath_select(const struct net *net,
+ struct fib6_info *match,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb, int strict);
+
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr);
struct fib6_node *fib6_locate(struct fib6_node *root,
const struct in6_addr *daddr, int dst_len,
!lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
}
+static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+ struct inet6_dev *idev;
+ unsigned int mtu;
+
+ if (dst_metric_locked(dst, RTAX_MTU)) {
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ return mtu;
+ }
+
+ mtu = IPV6_MIN_MTU;
+ rcu_read_lock();
+ idev = __in6_dev_get(dst->dev);
+ if (idev)
+ mtu = idev->cnf.mtu6;
+ rcu_read_unlock();
+
+ return mtu;
+}
+
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev, struct sk_buff *skb,
const void *daddr);
return (struct ip_tunnel_info *)lwtstate->data;
}
-extern struct static_key ip_tunnel_metadata_cnt;
+DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
/* Returns > 0 if metadata should be collected */
static inline int ip_tunnel_collect_metadata(void)
{
- return static_key_false(&ip_tunnel_metadata_cnt);
+ return static_branch_unlikely(&ip_tunnel_metadata_cnt);
}
void __init ip_tunnel_core_init(void);
volatile unsigned int flags; /* dest status flags */
atomic_t conn_flags; /* flags to copy to conn */
atomic_t weight; /* server weight */
+ atomic_t last_weight; /* server latest weight */
refcount_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
__s16 tclass;
__s8 dontfrag;
struct ipv6_txoptions *opt;
+ __u16 gso_size;
};
static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
+ struct inet_cork_full *cork,
const struct sockcm_cookie *sockc);
static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
&inet6_sk(sk)->cork);
}
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst);
-
int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
struct flowi6 *fl6);
struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
* virtual interface might not be given air time for the transmission of
* the frame, as it is not synced with the AP/P2P GO yet, and thus the
* deauthentication frame might not be transmitted.
- >
+ *
* @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't
* support QoS NDP for AP probing - that's most likely a driver bug.
*
#define NEIGH_UPDATE_F_OVERRIDE 0x00000001
#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002
#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004
+#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000
#define NEIGH_UPDATE_F_ISROUTER 0x40000000
#define NEIGH_UPDATE_F_ADMIN 0x80000000
} while (read_seqretry(&n->ha_lock, seq));
}
-
+static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
+ int *notify)
+{
+ u8 ndm_flags = 0;
+
+ if (!(flags & NEIGH_UPDATE_F_ADMIN))
+ return;
+
+ ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
+ if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
+ if (ndm_flags & NTF_EXT_LEARNED)
+ neigh->flags |= NTF_EXT_LEARNED;
+ else
+ neigh->flags &= ~NTF_EXT_LEARNED;
+ *notify = 1;
+ }
+}
#endif
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
const struct net_device *out);
void nf_nat_masquerade_ipv4_register_notifier(void);
#define _NF_NAT_MASQUERADE_IPV6_H_
unsigned int
-nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
const struct net_device *out);
void nf_nat_masquerade_ipv6_register_notifier(void);
void nf_nat_masquerade_ipv6_unregister_notifier(void);
#include <linux/netdevice.h>
#include <linux/rhashtable.h>
#include <linux/rcupdate.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
#include <net/dst.h>
struct nf_flowtable;
struct nf_flowtable_type {
struct list_head list;
int family;
- void (*gc)(struct work_struct *work);
+ int (*init)(struct nf_flowtable *ft);
void (*free)(struct nf_flowtable *ft);
- const struct rhashtable_params *params;
nf_hookfn *hook;
struct module *owner;
};
struct nf_flowtable {
+ struct list_head list;
struct rhashtable rhashtable;
const struct nf_flowtable_type *type;
struct delayed_work gc_work;
};
enum flow_offload_tuple_dir {
- FLOW_OFFLOAD_DIR_ORIGINAL,
- FLOW_OFFLOAD_DIR_REPLY,
- __FLOW_OFFLOAD_DIR_MAX = FLOW_OFFLOAD_DIR_REPLY,
+ FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
+ FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
+ FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
};
-#define FLOW_OFFLOAD_DIR_MAX (__FLOW_OFFLOAD_DIR_MAX + 1)
struct flow_offload_tuple {
union {
int oifidx;
+ u16 mtu;
+
struct dst_entry *dst_cache;
};
#define FLOW_OFFLOAD_SNAT 0x1
#define FLOW_OFFLOAD_DNAT 0x2
#define FLOW_OFFLOAD_DYING 0x4
+#define FLOW_OFFLOAD_TEARDOWN 0x8
struct flow_offload {
struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX];
void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
+int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
-void nf_flow_offload_work_gc(struct work_struct *work);
-extern const struct rhashtable_params nf_flow_offload_rhash_params;
-void flow_offload_dead(struct flow_offload *flow);
+void flow_offload_teardown(struct flow_offload *flow);
+static inline void flow_offload_dead(struct flow_offload *flow)
+{
+ flow->flags |= FLOW_OFFLOAD_DYING;
+}
int nf_flow_snat_port(const struct flow_offload *flow,
struct sk_buff *skb, unsigned int thoff,
/* Set up the info structure to map into this range. */
unsigned int nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype);
extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct,
u8 l3proto;
bool (*in_range)(const struct nf_conntrack_tuple *t,
- const struct nf_nat_range *range);
+ const struct nf_nat_range2 *range);
u32 (*secure_port)(const struct nf_conntrack_tuple *t, __be16);
struct flowi *fl);
int (*nlattr_to_range)(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_range2 *range);
};
int nf_nat_l3proto_register(const struct nf_nat_l3proto *);
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv4_local_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv6_local_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct));
+ const struct nf_hook_state *state));
#endif /* _NF_NAT_L3PROTO_H */
*/
void (*unique_tuple)(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct);
int (*nlattr_to_range)(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_range2 *range);
};
/* Protocol registration. */
void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct, u16 *rover);
int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range);
+ struct nf_nat_range2 *range);
#endif /*_NF_NAT_L4PROTO_H*/
const struct nf_nat_ipv4_multi_range_compat *mr,
unsigned int hooknum);
unsigned int
-nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
unsigned int hooknum);
#endif /* _NF_NAT_REDIRECT_H_ */
int nft_data_init(const struct nft_ctx *ctx,
struct nft_data *data, unsigned int size,
struct nft_data_desc *desc, const struct nlattr *nla);
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
void nft_data_release(const struct nft_data *data, enum nft_data_types type);
int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
enum nft_data_types type, unsigned int len);
enum nft_set_class space;
};
-/**
- * struct nft_set_type - nf_tables set type
- *
- * @select_ops: function to select nft_set_ops
- * @ops: default ops, used when no select_ops functions is present
- * @list: used internally
- * @owner: module reference
- */
-struct nft_set_type {
- const struct nft_set_ops *(*select_ops)(const struct nft_ctx *,
- const struct nft_set_desc *desc,
- u32 flags);
- const struct nft_set_ops *ops;
- struct list_head list;
- struct module *owner;
-};
-
struct nft_set_ext;
struct nft_expr;
* @init: initialize private data of new set instance
* @destroy: destroy private data of set instance
* @elemsize: element private size
- * @features: features supported by the implementation
*/
struct nft_set_ops {
bool (*lookup)(const struct net *net,
void (*destroy)(const struct nft_set *set);
unsigned int elemsize;
+};
+
+/**
+ * struct nft_set_type - nf_tables set type
+ *
+ * @ops: set ops for this type
+ * @list: used internally
+ * @owner: module reference
+ * @features: features supported by the implementation
+ */
+struct nft_set_type {
+ const struct nft_set_ops ops;
+ struct list_head list;
+ struct module *owner;
u32 features;
- const struct nft_set_type *type;
};
+#define to_set_type(o) container_of(o, struct nft_set_type, ops)
int nft_register_set(struct nft_set_type *type);
void nft_unregister_set(struct nft_set_type *type);
return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
}
-static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext)
+static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext)
{
return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
}
static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
{
return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
- time_is_before_eq_jiffies(*nft_set_ext_expiration(ext));
+ time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
}
static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
int (*init)(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[]);
+ void (*activate)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr);
+ void (*deactivate)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr);
void (*destroy)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
int (*dump)(struct sk_buff *skb,
#define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr))
-struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
- const struct nlattr *nla, u32 objtype,
- u8 genmask);
+struct nft_object *nft_obj_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u32 objtype,
+ u8 genmask);
void nft_obj_notify(struct net *net, struct nft_table *table,
struct nft_object *obj, u32 portid, u32 seq,
struct nf_flowtable data;
};
-struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
- const struct nlattr *nla,
- u8 genmask);
-void nft_flow_table_iterate(struct net *net,
- void (*iter)(struct nf_flowtable *flowtable, void *data),
- void *data);
+struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
+ const struct nlattr *nla,
+ u8 genmask);
void nft_register_flowtable_type(struct nf_flowtable_type *type);
void nft_unregister_flowtable_type(struct nf_flowtable_type *type);
extern struct nft_expr_type nft_payload_type;
extern struct nft_expr_type nft_dynset_type;
extern struct nft_expr_type nft_range_type;
+extern struct nft_expr_type nft_meta_type;
+extern struct nft_expr_type nft_rt_type;
+extern struct nft_expr_type nft_exthdr_type;
int nf_tables_core_module_init(void);
void nf_tables_core_module_exit(void);
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _KER_NFNETLINK_LOG_H
-#define _KER_NFNETLINK_LOG_H
-
-void
-nfulnl_log_packet(struct net *net,
- u_int8_t pf,
- unsigned int hooknum,
- const struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- const struct nf_loginfo *li_user,
- const char *prefix);
-
-#define NFULNL_COPY_DISABLED 0xff
-
-#endif /* _KER_NFNETLINK_LOG_H */
-
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_META_H_
-#define _NFT_META_H_
-
-struct nft_meta {
- enum nft_meta_keys key:8;
- union {
- enum nft_registers dreg:8;
- enum nft_registers sreg:8;
- };
-};
-
-extern const struct nla_policy nft_meta_policy[];
-
-int nft_meta_get_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[]);
-
-int nft_meta_set_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[]);
-
-int nft_meta_get_dump(struct sk_buff *skb,
- const struct nft_expr *expr);
-
-int nft_meta_set_dump(struct sk_buff *skb,
- const struct nft_expr *expr);
-
-void nft_meta_get_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt);
-
-void nft_meta_set_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt);
-
-void nft_meta_set_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr);
-
-int nft_meta_set_validate(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nft_data **data);
-
-#endif
int sysctl_tcp_pacing_ca_ratio;
int sysctl_tcp_wmem[3];
int sysctl_tcp_rmem[3];
+ int sysctl_tcp_comp_sack_nr;
+ unsigned long sysctl_tcp_comp_sack_delay_ns;
struct inet_timewait_death_row tcp_death_row;
int sysctl_max_syn_backlog;
int sysctl_tcp_fastopen;
int max_hbh_opts_cnt;
int max_dst_opts_len;
int max_hbh_opts_len;
+ int seg6_flowlabel;
};
struct netns_ipv6 {
/* SKIP_HW and SKIP_SW are mutually exclusive flags. */
static inline bool tc_flags_valid(u32 flags)
{
- if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW))
+ if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW |
+ TCA_CLS_FLAGS_VERBOSE))
return false;
+ flags &= TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW;
if (!(flags ^ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW)))
return false;
cls_common->chain_index = tp->chain->index;
cls_common->protocol = tp->protocol;
cls_common->prio = tp->prio;
- if (tc_skip_sw(flags))
+ if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
cls_common->extack = extack;
}
enum qdisc_state_t {
__QDISC_STATE_SCHED,
__QDISC_STATE_DEACTIVATED,
- __QDISC_STATE_RUNNING,
};
struct qdisc_size_table {
refcount_t refcnt;
spinlock_t busylock ____cacheline_aligned_in_smp;
+ spinlock_t seqlock;
};
static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
refcount_inc(&qdisc->refcnt);
}
-static inline bool qdisc_is_running(const struct Qdisc *qdisc)
+static inline bool qdisc_is_running(struct Qdisc *qdisc)
{
+ if (qdisc->flags & TCQ_F_NOLOCK)
+ return spin_is_locked(&qdisc->seqlock);
return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
}
static inline bool qdisc_run_begin(struct Qdisc *qdisc)
{
- if (qdisc_is_running(qdisc))
+ if (qdisc->flags & TCQ_F_NOLOCK) {
+ if (!spin_trylock(&qdisc->seqlock))
+ return false;
+ } else if (qdisc_is_running(qdisc)) {
return false;
+ }
/* Variant of write_seqcount_begin() telling lockdep a trylock
* was attempted.
*/
static inline void qdisc_run_end(struct Qdisc *qdisc)
{
write_seqcount_end(&qdisc->running);
+ if (qdisc->flags & TCQ_F_NOLOCK)
+ spin_unlock(&qdisc->seqlock);
}
static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
#define SCTP_TSN_MAP_SIZE 4096
/* We will not record more than this many duplicate TSNs between two
- * SACKs. The minimum PMTU is 576. Remove all the headers and there
- * is enough room for 131 duplicate reports. Round down to the
+ * SACKs. The minimum PMTU is 512. Remove all the headers and there
+ * is enough room for 117 duplicate reports. Round down to the
* nearest power of 2.
*/
-enum { SCTP_MIN_PMTU = 576 };
enum { SCTP_MAX_DUP_TSNS = 16 };
enum { SCTP_MAX_GABS = 16 };
return (head->next != head) && (head->next == head->prev);
}
-/* Break down data chunks at this point. */
-static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
-{
- struct sctp_sock *sp = sctp_sk(asoc->base.sk);
- struct sctp_af *af = sp->pf->af;
- int frag = pmtu;
-
- frag -= af->ip_options_len(asoc->base.sk);
- frag -= af->net_header_len;
- frag -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream);
-
- if (asoc->user_frag)
- frag = min_t(int, frag, asoc->user_frag);
-
- frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN -
- sctp_datachk_len(&asoc->stream)));
-
- return frag;
-}
-
-static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
-{
- sctp_assoc_sync_pmtu(asoc);
- asoc->pmtu_pending = 0;
-}
-
static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
{
return !list_empty(&chunk->list);
return t->dst;
}
-static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+/* Calculate max payload size given a MTU, or the total overhead if
+ * given MTU is zero
+ */
+static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp,
+ __u32 mtu, __u32 extra)
{
- __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
- SCTP_DEFAULT_MINSEGMENT);
+ __u32 overhead = sizeof(struct sctphdr) + extra;
- if (t->pathmtu == pmtu)
- return true;
+ if (sp)
+ overhead += sp->pf->af->net_header_len;
+ else
+ overhead += sizeof(struct ipv6hdr);
- t->pathmtu = pmtu;
+ if (WARN_ON_ONCE(mtu && mtu <= overhead))
+ mtu = overhead;
- return false;
+ return mtu ? mtu - overhead : overhead;
+}
+
+static inline __u32 sctp_dst_mtu(const struct dst_entry *dst)
+{
+ return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst),
+ SCTP_DEFAULT_MINSEGMENT));
}
#endif /* __net_sctp_h__ */
int len, __u8 flags, gfp_t gfp);
struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc,
const __u32 lowest_tsn);
-struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc);
+struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc);
struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc,
const struct sctp_chunk *chunk);
struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc,
struct sctp_chunk *sctp_make_shutdown_complete(
const struct sctp_association *asoc,
const struct sctp_chunk *chunk);
-void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen);
+int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen);
struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc,
const struct sctp_chunk *chunk,
const size_t hint);
enum sctp_transport_cmd command,
sctp_sn_error_t error);
struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32);
-struct sctp_transport *sctp_assoc_is_match(struct sctp_association *,
- struct net *,
- const union sctp_addr *,
- const union sctp_addr *);
void sctp_assoc_migrate(struct sctp_association *, struct sock *);
int sctp_assoc_update(struct sctp_association *old,
struct sctp_association *new);
__u32 sctp_association_get_next_tsn(struct sctp_association *);
+void sctp_assoc_update_frag_point(struct sctp_association *asoc);
+void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu);
void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk,
struct sk_buff *skb);
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+ struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk,
+ struct net_device *dev,
+ struct sk_buff *skb);
+#endif
void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb;
struct rcu_head sk_rcu;
}
#ifdef CONFIG_NET
-extern struct static_key memalloc_socks;
+DECLARE_STATIC_KEY_FALSE(memalloc_socks_key);
static inline int sk_memalloc_socks(void)
{
- return static_key_false(&memalloc_socks);
+ return static_branch_unlikely(&memalloc_socks_key);
}
#else
return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
}
+/* Checks if this SKB belongs to an HW offloaded socket
+ * and whether any SW fallbacks are required based on dev.
+ */
+static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
+ struct net_device *dev)
+{
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+ struct sock *sk = skb->sk;
+
+ if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb)
+ skb = sk->sk_validate_xmit_skb(sk, dev, skb);
+#endif
+
+ return skb;
+}
+
/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
* SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
*/
struct switchdev_notifier_info info; /* must be first */
const unsigned char *addr;
u16 vid;
+ bool added_by_user;
};
static inline struct net_device *
#define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */
#define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */
+#define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
void tcp_init_xmit_timers(struct sock *);
static inline void tcp_clear_xmit_timers(struct sock *sk)
{
- hrtimer_cancel(&tcp_sk(sk)->pacing_timer);
+ if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1)
+ __sock_put(sk);
+
+ if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1)
+ __sock_put(sk);
+
inet_csk_clear_xmit_timers(sk);
}
#endif
} header; /* For incoming skbs */
struct {
- __u32 key;
__u32 flags;
- struct bpf_map *map;
+ struct sock *sk_redir;
void *data_end;
} bpf;
};
void tcp_init(void);
/* tcp_recovery.c */
+void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb);
+void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced);
+extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb,
+ u32 reo_wnd);
extern void tcp_rack_mark_lost(struct sock *sk);
extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
u64 xmit_time);
#if IS_ENABLED(CONFIG_SMC)
extern struct static_key_false tcp_have_smc;
#endif
+
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+void clean_acked_data_enable(struct inet_connection_sock *icsk,
+ void (*cad)(struct sock *sk, u32 ack_seq));
+void clean_acked_data_disable(struct inet_connection_sock *icsk);
+
+#endif
+
#endif /* _TCP_H */
__be32 w[4];
};
-static inline u32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
+static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
{
u32 w0 = ntohl(hdr->w[0]);
bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK;
- int key;
+ __be32 key;
/* Return source node identity as key */
if (likely(!keepalive_msg))
void (*unhash)(struct tls_device *device, struct sock *sk);
};
-struct tls_sw_context {
+struct tls_sw_context_tx {
struct crypto_aead *aead_send;
- struct crypto_aead *aead_recv;
struct crypto_wait async_wait;
- /* Receive context */
- struct strparser strp;
- void (*saved_data_ready)(struct sock *sk);
- unsigned int (*sk_poll)(struct file *file, struct socket *sock,
- struct poll_table_struct *wait);
- struct sk_buff *recv_pkt;
- u8 control;
- bool decrypted;
-
- /* Sending context */
char aad_space[TLS_AAD_SPACE_SIZE];
unsigned int sg_plaintext_size;
struct scatterlist sg_aead_out[2];
};
+struct tls_sw_context_rx {
+ struct crypto_aead *aead_recv;
+ struct crypto_wait async_wait;
+
+ struct strparser strp;
+ void (*saved_data_ready)(struct sock *sk);
+ unsigned int (*sk_poll)(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait);
+ struct sk_buff *recv_pkt;
+ u8 control;
+ bool decrypted;
+
+ char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
+ char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
+
+};
+
+struct tls_record_info {
+ struct list_head list;
+ u32 end_seq;
+ int len;
+ int num_frags;
+ skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+struct tls_offload_context {
+ struct crypto_aead *aead_send;
+ spinlock_t lock; /* protects records list */
+ struct list_head records_list;
+ struct tls_record_info *open_record;
+ struct tls_record_info *retransmit_hint;
+ u64 hint_record_sn;
+ u64 unacked_record_sn;
+
+ struct scatterlist sg_tx_data[MAX_SKB_FRAGS];
+ void (*sk_destruct)(struct sock *sk);
+ u8 driver_state[];
+ /* The TLS layer reserves room for driver specific state
+ * Currently the belief is that there is not enough
+ * driver specific state to justify another layer of indirection
+ */
+#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *)))
+};
+
+#define TLS_OFFLOAD_CONTEXT_SIZE \
+ (ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) + \
+ TLS_DRIVER_STATE_SIZE)
+
enum {
TLS_PENDING_CLOSED_RECORD
};
struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128;
};
- void *priv_ctx;
+ struct list_head list;
+ struct net_device *netdev;
+ refcount_t refcount;
+
+ void *priv_ctx_tx;
+ void *priv_ctx_rx;
- u8 conf:3;
+ u8 tx_conf:3;
+ u8 rx_conf:3;
struct cipher_context tx;
struct cipher_context rx;
struct scatterlist *partially_sent_record;
u16 partially_sent_offset;
unsigned long flags;
+ bool in_tcp_sendpages;
u16 pending_open_record_frags;
int (*push_pending_record)(struct sock *sk, int flags);
int tls_sw_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_sw_close(struct sock *sk, long timeout);
-void tls_sw_free_resources(struct sock *sk);
+void tls_sw_free_resources_tx(struct sock *sk);
+void tls_sw_free_resources_rx(struct sock *sk);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
unsigned int tls_sw_poll(struct file *file, struct socket *sock,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
-void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
-void tls_icsk_clean_acked(struct sock *sk);
+int tls_set_device_offload(struct sock *sk, struct tls_context *ctx);
+int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+int tls_device_sendpage(struct sock *sk, struct page *page,
+ int offset, size_t size, int flags);
+void tls_device_sk_destruct(struct sock *sk);
+void tls_device_init(void);
+void tls_device_cleanup(void);
+
+struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+ u32 seq, u64 *p_record_sn);
+
+static inline bool tls_record_is_start_marker(struct tls_record_info *rec)
+{
+ return rec->len == 0;
+}
+
+static inline u32 tls_record_start_seq(struct tls_record_info *rec)
+{
+ return rec->end_seq - rec->len;
+}
+void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
int tls_push_sg(struct sock *sk, struct tls_context *ctx,
struct scatterlist *sg, u16 first_offset,
int flags);
return tls_ctx->pending_open_record_frags;
}
+static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
+{
+ return sk_fullsock(sk) &&
+ /* matches smp_store_release in tls_set_device_offload */
+ smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct;
+}
+
static inline void tls_err_abort(struct sock *sk, int err)
{
sk->sk_err = err;
return icsk->icsk_ulp_data;
}
-static inline struct tls_sw_context *tls_sw_ctx(
+static inline struct tls_sw_context_rx *tls_sw_ctx_rx(
const struct tls_context *tls_ctx)
{
- return (struct tls_sw_context *)tls_ctx->priv_ctx;
+ return (struct tls_sw_context_rx *)tls_ctx->priv_ctx_rx;
+}
+
+static inline struct tls_sw_context_tx *tls_sw_ctx_tx(
+ const struct tls_context *tls_ctx)
+{
+ return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx;
}
static inline struct tls_offload_context *tls_offload_ctx(
const struct tls_context *tls_ctx)
{
- return (struct tls_offload_context *)tls_ctx->priv_ctx;
+ return (struct tls_offload_context *)tls_ctx->priv_ctx_tx;
}
int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
void tls_register_device(struct tls_device *device);
void tls_unregister_device(struct tls_device *device);
+struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
+ struct net_device *dev,
+ struct sk_buff *skb);
+
+int tls_sw_fallback_init(struct sock *sk,
+ struct tls_offload_context *offload_ctx,
+ struct tls_crypto_info *crypto_info);
+
#endif /* _TLS_OFFLOAD_H */
struct udphdr *uh, udp_lookup_t lookup);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
+struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features);
+
static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
{
struct udphdr *uh;
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udp_push_pending_frames(struct sock *sk);
void udp_flush_pending_frames(struct sock *sk);
+int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
int udp_rcv(struct sk_buff *skb);
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
}
void xdp_return_frame(struct xdp_frame *xdpf);
+void xdp_return_buff(struct xdp_buff *xdp);
int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
struct net_device *dev, u32 queue_index);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * AF_XDP internal functions
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _LINUX_XDP_SOCK_H
+#define _LINUX_XDP_SOCK_H
+
+#include <linux/mutex.h>
+#include <net/sock.h>
+
+struct net_device;
+struct xsk_queue;
+struct xdp_umem;
+
+struct xdp_sock {
+ /* struct sock must be the first member of struct xdp_sock */
+ struct sock sk;
+ struct xsk_queue *rx;
+ struct net_device *dev;
+ struct xdp_umem *umem;
+ struct list_head flush_node;
+ u16 queue_id;
+ struct xsk_queue *tx ____cacheline_aligned_in_smp;
+ /* Protects multiple processes in the control path */
+ struct mutex mutex;
+ u64 rx_dropped;
+};
+
+struct xdp_buff;
+#ifdef CONFIG_XDP_SOCKETS
+int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
+int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
+void xsk_flush(struct xdp_sock *xs);
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
+#else
+static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ return -ENOTSUPP;
+}
+
+static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ return -ENOTSUPP;
+}
+
+static inline void xsk_flush(struct xdp_sock *xs)
+{
+}
+
+static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+ return false;
+}
+#endif /* CONFIG_XDP_SOCKETS */
+
+#endif /* _LINUX_XDP_SOCK_H */
int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo);
int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo);
+void xfrm_flush_gc(void);
void xfrm_state_delete_tunnel(struct xfrm_state *x);
struct xfrm_type {
extern void scsi_print_command(struct scsi_cmnd *);
extern size_t __scsi_format_command(char *, size_t,
const unsigned char *, size_t);
-extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
- unsigned char, unsigned char);
extern void scsi_print_sense_hdr(const struct scsi_device *, const char *,
const struct scsi_sense_hdr *);
extern void scsi_print_sense(const struct scsi_cmnd *);
static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag,
void *data, size_t len)
{
- return 0;
+ return -ENOSYS;
}
static inline int rpi_firmware_property_list(struct rpi_firmware *fw,
void *data, size_t tag_size)
{
- return 0;
+ return -ENOSYS;
}
static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node)
*/
#include <linux/wait.h>
+#include <linux/nospec.h>
#include <sound/asound.h>
#define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data)
static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
{
- return id->numid - kctl->id.numid;
+ unsigned int ioff = id->numid - kctl->id.numid;
+ return array_index_nospec(ioff, kctl->count);
}
static inline unsigned int snd_ctl_get_ioffidx(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
{
- return id->index - kctl->id.index;
+ unsigned int ioff = id->index - kctl->id.index;
+ return array_index_nospec(ioff, kctl->count);
}
static inline unsigned int snd_ctl_get_ioff(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
__entry->call, __entry->error, __entry->where)
);
+TRACE_EVENT(afs_cm_no_server,
+ TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
+
+ TP_ARGS(call, srx),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, call )
+ __field(unsigned int, op_id )
+ __field_struct(struct sockaddr_rxrpc, srx )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call->debug_id;
+ __entry->op_id = call->operation_ID;
+ memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+ ),
+
+ TP_printk("c=%08x op=%u %pISpc",
+ __entry->call, __entry->op_id, &__entry->srx.transport)
+ );
+
+TRACE_EVENT(afs_cm_no_server_u,
+ TP_PROTO(struct afs_call *call, const uuid_t *uuid),
+
+ TP_ARGS(call, uuid),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, call )
+ __field(unsigned int, op_id )
+ __field_struct(uuid_t, uuid )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call->debug_id;
+ __entry->op_id = call->operation_ID;
+ memcpy(&__entry->uuid, uuid, sizeof(__entry->uuid));
+ ),
+
+ TP_printk("c=%08x op=%u %pU",
+ __entry->call, __entry->op_id, &__entry->uuid)
+ );
+
#endif /* _TRACE_AFS_H */
/* This part must be outside protection */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM bpf
-
-#if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_BPF_H
-
-/* These are only used within the BPF_SYSCALL code */
-#ifdef CONFIG_BPF_SYSCALL
-
-#include <linux/filter.h>
-#include <linux/bpf.h>
-#include <linux/fs.h>
-#include <linux/tracepoint.h>
-
-#define __PROG_TYPE_MAP(FN) \
- FN(SOCKET_FILTER) \
- FN(KPROBE) \
- FN(SCHED_CLS) \
- FN(SCHED_ACT) \
- FN(TRACEPOINT) \
- FN(XDP) \
- FN(PERF_EVENT) \
- FN(CGROUP_SKB) \
- FN(CGROUP_SOCK) \
- FN(LWT_IN) \
- FN(LWT_OUT) \
- FN(LWT_XMIT)
-
-#define __MAP_TYPE_MAP(FN) \
- FN(HASH) \
- FN(ARRAY) \
- FN(PROG_ARRAY) \
- FN(PERF_EVENT_ARRAY) \
- FN(PERCPU_HASH) \
- FN(PERCPU_ARRAY) \
- FN(STACK_TRACE) \
- FN(CGROUP_ARRAY) \
- FN(LRU_HASH) \
- FN(LRU_PERCPU_HASH) \
- FN(LPM_TRIE)
-
-#define __PROG_TYPE_TP_FN(x) \
- TRACE_DEFINE_ENUM(BPF_PROG_TYPE_##x);
-#define __PROG_TYPE_SYM_FN(x) \
- { BPF_PROG_TYPE_##x, #x },
-#define __PROG_TYPE_SYM_TAB \
- __PROG_TYPE_MAP(__PROG_TYPE_SYM_FN) { -1, 0 }
-__PROG_TYPE_MAP(__PROG_TYPE_TP_FN)
-
-#define __MAP_TYPE_TP_FN(x) \
- TRACE_DEFINE_ENUM(BPF_MAP_TYPE_##x);
-#define __MAP_TYPE_SYM_FN(x) \
- { BPF_MAP_TYPE_##x, #x },
-#define __MAP_TYPE_SYM_TAB \
- __MAP_TYPE_MAP(__MAP_TYPE_SYM_FN) { -1, 0 }
-__MAP_TYPE_MAP(__MAP_TYPE_TP_FN)
-
-DECLARE_EVENT_CLASS(bpf_prog_event,
-
- TP_PROTO(const struct bpf_prog *prg),
-
- TP_ARGS(prg),
-
- TP_STRUCT__entry(
- __array(u8, prog_tag, 8)
- __field(u32, type)
- ),
-
- TP_fast_assign(
- BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag));
- memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag));
- __entry->type = prg->type;
- ),
-
- TP_printk("prog=%s type=%s",
- __print_hex_str(__entry->prog_tag, 8),
- __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB))
-);
-
-DEFINE_EVENT(bpf_prog_event, bpf_prog_get_type,
-
- TP_PROTO(const struct bpf_prog *prg),
-
- TP_ARGS(prg)
-);
-
-DEFINE_EVENT(bpf_prog_event, bpf_prog_put_rcu,
-
- TP_PROTO(const struct bpf_prog *prg),
-
- TP_ARGS(prg)
-);
-
-TRACE_EVENT(bpf_prog_load,
-
- TP_PROTO(const struct bpf_prog *prg, int ufd),
-
- TP_ARGS(prg, ufd),
-
- TP_STRUCT__entry(
- __array(u8, prog_tag, 8)
- __field(u32, type)
- __field(int, ufd)
- ),
-
- TP_fast_assign(
- BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag));
- memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag));
- __entry->type = prg->type;
- __entry->ufd = ufd;
- ),
-
- TP_printk("prog=%s type=%s ufd=%d",
- __print_hex_str(__entry->prog_tag, 8),
- __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB),
- __entry->ufd)
-);
-
-TRACE_EVENT(bpf_map_create,
-
- TP_PROTO(const struct bpf_map *map, int ufd),
-
- TP_ARGS(map, ufd),
-
- TP_STRUCT__entry(
- __field(u32, type)
- __field(u32, size_key)
- __field(u32, size_value)
- __field(u32, max_entries)
- __field(u32, flags)
- __field(int, ufd)
- ),
-
- TP_fast_assign(
- __entry->type = map->map_type;
- __entry->size_key = map->key_size;
- __entry->size_value = map->value_size;
- __entry->max_entries = map->max_entries;
- __entry->flags = map->map_flags;
- __entry->ufd = ufd;
- ),
-
- TP_printk("map type=%s ufd=%d key=%u val=%u max=%u flags=%x",
- __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
- __entry->ufd, __entry->size_key, __entry->size_value,
- __entry->max_entries, __entry->flags)
-);
-
-DECLARE_EVENT_CLASS(bpf_obj_prog,
-
- TP_PROTO(const struct bpf_prog *prg, int ufd,
- const struct filename *pname),
-
- TP_ARGS(prg, ufd, pname),
-
- TP_STRUCT__entry(
- __array(u8, prog_tag, 8)
- __field(int, ufd)
- __string(path, pname->name)
- ),
-
- TP_fast_assign(
- BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag));
- memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag));
- __assign_str(path, pname->name);
- __entry->ufd = ufd;
- ),
-
- TP_printk("prog=%s path=%s ufd=%d",
- __print_hex_str(__entry->prog_tag, 8),
- __get_str(path), __entry->ufd)
-);
-
-DEFINE_EVENT(bpf_obj_prog, bpf_obj_pin_prog,
-
- TP_PROTO(const struct bpf_prog *prg, int ufd,
- const struct filename *pname),
-
- TP_ARGS(prg, ufd, pname)
-);
-
-DEFINE_EVENT(bpf_obj_prog, bpf_obj_get_prog,
-
- TP_PROTO(const struct bpf_prog *prg, int ufd,
- const struct filename *pname),
-
- TP_ARGS(prg, ufd, pname)
-);
-
-DECLARE_EVENT_CLASS(bpf_obj_map,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const struct filename *pname),
-
- TP_ARGS(map, ufd, pname),
-
- TP_STRUCT__entry(
- __field(u32, type)
- __field(int, ufd)
- __string(path, pname->name)
- ),
-
- TP_fast_assign(
- __assign_str(path, pname->name);
- __entry->type = map->map_type;
- __entry->ufd = ufd;
- ),
-
- TP_printk("map type=%s ufd=%d path=%s",
- __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
- __entry->ufd, __get_str(path))
-);
-
-DEFINE_EVENT(bpf_obj_map, bpf_obj_pin_map,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const struct filename *pname),
-
- TP_ARGS(map, ufd, pname)
-);
-
-DEFINE_EVENT(bpf_obj_map, bpf_obj_get_map,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const struct filename *pname),
-
- TP_ARGS(map, ufd, pname)
-);
-
-DECLARE_EVENT_CLASS(bpf_map_keyval,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const void *key, const void *val),
-
- TP_ARGS(map, ufd, key, val),
-
- TP_STRUCT__entry(
- __field(u32, type)
- __field(u32, key_len)
- __dynamic_array(u8, key, map->key_size)
- __field(bool, key_trunc)
- __field(u32, val_len)
- __dynamic_array(u8, val, map->value_size)
- __field(bool, val_trunc)
- __field(int, ufd)
- ),
-
- TP_fast_assign(
- memcpy(__get_dynamic_array(key), key, map->key_size);
- memcpy(__get_dynamic_array(val), val, map->value_size);
- __entry->type = map->map_type;
- __entry->key_len = min(map->key_size, 16U);
- __entry->key_trunc = map->key_size != __entry->key_len;
- __entry->val_len = min(map->value_size, 16U);
- __entry->val_trunc = map->value_size != __entry->val_len;
- __entry->ufd = ufd;
- ),
-
- TP_printk("map type=%s ufd=%d key=[%s%s] val=[%s%s]",
- __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
- __entry->ufd,
- __print_hex(__get_dynamic_array(key), __entry->key_len),
- __entry->key_trunc ? " ..." : "",
- __print_hex(__get_dynamic_array(val), __entry->val_len),
- __entry->val_trunc ? " ..." : "")
-);
-
-DEFINE_EVENT(bpf_map_keyval, bpf_map_lookup_elem,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const void *key, const void *val),
-
- TP_ARGS(map, ufd, key, val)
-);
-
-DEFINE_EVENT(bpf_map_keyval, bpf_map_update_elem,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const void *key, const void *val),
-
- TP_ARGS(map, ufd, key, val)
-);
-
-TRACE_EVENT(bpf_map_delete_elem,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const void *key),
-
- TP_ARGS(map, ufd, key),
-
- TP_STRUCT__entry(
- __field(u32, type)
- __field(u32, key_len)
- __dynamic_array(u8, key, map->key_size)
- __field(bool, key_trunc)
- __field(int, ufd)
- ),
-
- TP_fast_assign(
- memcpy(__get_dynamic_array(key), key, map->key_size);
- __entry->type = map->map_type;
- __entry->key_len = min(map->key_size, 16U);
- __entry->key_trunc = map->key_size != __entry->key_len;
- __entry->ufd = ufd;
- ),
-
- TP_printk("map type=%s ufd=%d key=[%s%s]",
- __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
- __entry->ufd,
- __print_hex(__get_dynamic_array(key), __entry->key_len),
- __entry->key_trunc ? " ..." : "")
-);
-
-TRACE_EVENT(bpf_map_next_key,
-
- TP_PROTO(const struct bpf_map *map, int ufd,
- const void *key, const void *key_next),
-
- TP_ARGS(map, ufd, key, key_next),
-
- TP_STRUCT__entry(
- __field(u32, type)
- __field(u32, key_len)
- __dynamic_array(u8, key, map->key_size)
- __dynamic_array(u8, nxt, map->key_size)
- __field(bool, key_trunc)
- __field(bool, key_null)
- __field(int, ufd)
- ),
-
- TP_fast_assign(
- if (key)
- memcpy(__get_dynamic_array(key), key, map->key_size);
- __entry->key_null = !key;
- memcpy(__get_dynamic_array(nxt), key_next, map->key_size);
- __entry->type = map->map_type;
- __entry->key_len = min(map->key_size, 16U);
- __entry->key_trunc = map->key_size != __entry->key_len;
- __entry->ufd = ufd;
- ),
-
- TP_printk("map type=%s ufd=%d key=[%s%s] next=[%s%s]",
- __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB),
- __entry->ufd,
- __entry->key_null ? "NULL" : __print_hex(__get_dynamic_array(key),
- __entry->key_len),
- __entry->key_trunc && !__entry->key_null ? " ..." : "",
- __print_hex(__get_dynamic_array(nxt), __entry->key_len),
- __entry->key_trunc ? " ..." : "")
-);
-#endif /* CONFIG_BPF_SYSCALL */
-#endif /* _TRACE_BPF_H */
-
-#include <trace/define_trace.h>
TRACE_EVENT(fib6_table_lookup,
- TP_PROTO(const struct net *net, const struct rt6_info *rt,
+ TP_PROTO(const struct net *net, const struct fib6_info *f6i,
struct fib6_table *table, const struct flowi6 *flp),
- TP_ARGS(net, rt, table, flp),
+ TP_ARGS(net, f6i, table, flp),
TP_STRUCT__entry(
__field( u32, tb_id )
in6 = (struct in6_addr *)__entry->dst;
*in6 = flp->daddr;
- if (rt->rt6i_idev) {
- __assign_str(name, rt->rt6i_idev->dev->name);
+ if (f6i->fib6_nh.nh_dev) {
+ __assign_str(name, f6i->fib6_nh.nh_dev);
} else {
__assign_str(name, "");
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
struct in6_addr in6_zero = {};
in6 = (struct in6_addr *)__entry->gw;
*in6 = in6_zero;
- } else if (rt) {
+ } else if (f6i) {
in6 = (struct in6_addr *)__entry->gw;
- *in6 = rt->rt6i_gateway;
+ *in6 = f6i->fib6_nh.nh_gw;
}
),
TP_ARGS(func),
TP_STRUCT__entry(
- __field(initcall_t, func)
+ /*
+ * Use field_struct to avoid is_signed_type()
+ * comparison of a function pointer
+ */
+ __field_struct(initcall_t, func)
),
TP_fast_assign(
TP_ARGS(func, ret),
TP_STRUCT__entry(
- __field(initcall_t, func)
- __field(int, ret)
+ /*
+ * Use field_struct to avoid is_signed_type()
+ * comparison of a function pointer
+ */
+ __field_struct(initcall_t, func)
+ __field(int, ret)
),
TP_fast_assign(
#define _TRACE_RXRPC_H
#include <linux/tracepoint.h>
+#include <linux/errqueue.h>
/*
* Define enums for tracing information.
rxrpc_cong_saw_nack,
};
+enum rxrpc_tx_fail_trace {
+ rxrpc_tx_fail_call_abort,
+ rxrpc_tx_fail_call_ack,
+ rxrpc_tx_fail_call_data_frag,
+ rxrpc_tx_fail_call_data_nofrag,
+ rxrpc_tx_fail_call_final_resend,
+ rxrpc_tx_fail_conn_abort,
+ rxrpc_tx_fail_conn_challenge,
+ rxrpc_tx_fail_conn_response,
+ rxrpc_tx_fail_reject,
+ rxrpc_tx_fail_version_keepalive,
+ rxrpc_tx_fail_version_reply,
+};
+
#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
/*
EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \
E_(RXRPC_CALL_NETWORK_ERROR, "NetError")
+#define rxrpc_tx_fail_traces \
+ EM(rxrpc_tx_fail_call_abort, "CallAbort") \
+ EM(rxrpc_tx_fail_call_ack, "CallAck") \
+ EM(rxrpc_tx_fail_call_data_frag, "CallDataFrag") \
+ EM(rxrpc_tx_fail_call_data_nofrag, "CallDataNofrag") \
+ EM(rxrpc_tx_fail_call_final_resend, "CallFinalResend") \
+ EM(rxrpc_tx_fail_conn_abort, "ConnAbort") \
+ EM(rxrpc_tx_fail_conn_challenge, "ConnChall") \
+ EM(rxrpc_tx_fail_conn_response, "ConnResp") \
+ EM(rxrpc_tx_fail_reject, "Reject") \
+ EM(rxrpc_tx_fail_version_keepalive, "VerKeepalive") \
+ E_(rxrpc_tx_fail_version_reply, "VerReply")
+
/*
* Export enum symbols via userspace.
*/
rxrpc_propose_ack_outcomes;
rxrpc_congest_modes;
rxrpc_congest_changes;
+rxrpc_tx_fail_traces;
/*
* Now redefine the EM() and E_() macros to map the enums to the strings that
__entry->anno)
);
+TRACE_EVENT(rxrpc_rx_icmp,
+ TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee,
+ struct sockaddr_rxrpc *srx),
+
+ TP_ARGS(peer, ee, srx),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, peer )
+ __field_struct(struct sock_extended_err, ee )
+ __field_struct(struct sockaddr_rxrpc, srx )
+ ),
+
+ TP_fast_assign(
+ __entry->peer = peer->debug_id;
+ memcpy(&__entry->ee, ee, sizeof(__entry->ee));
+ memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+ ),
+
+ TP_printk("P=%08x o=%u t=%u c=%u i=%u d=%u e=%d %pISp",
+ __entry->peer,
+ __entry->ee.ee_origin,
+ __entry->ee.ee_type,
+ __entry->ee.ee_code,
+ __entry->ee.ee_info,
+ __entry->ee.ee_data,
+ __entry->ee.ee_errno,
+ &__entry->srx.transport)
+ );
+
+TRACE_EVENT(rxrpc_tx_fail,
+ TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret,
+ enum rxrpc_tx_fail_trace what),
+
+ TP_ARGS(debug_id, serial, ret, what),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, debug_id )
+ __field(rxrpc_serial_t, serial )
+ __field(int, ret )
+ __field(enum rxrpc_tx_fail_trace, what )
+ ),
+
+ TP_fast_assign(
+ __entry->debug_id = debug_id;
+ __entry->serial = serial;
+ __entry->ret = ret;
+ __entry->what = what;
+ ),
+
+ TP_printk("c=%08x r=%x ret=%d %s",
+ __entry->debug_id,
+ __entry->serial,
+ __entry->ret,
+ __print_symbolic(__entry->what, rxrpc_tx_fail_traces))
+ );
+
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
TP_ARGS(task, backlog, rtt, execute),
TP_STRUCT__entry(
+ __field(unsigned int, task_id)
+ __field(unsigned int, client_id)
__field(u32, xid)
__field(int, version)
__string(progname, task->tk_client->cl_program->name)
__field(unsigned long, backlog)
__field(unsigned long, rtt)
__field(unsigned long, execute)
- __string(addr,
- task->tk_xprt->address_strings[RPC_DISPLAY_ADDR])
- __string(port,
- task->tk_xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
+ __entry->client_id = task->tk_client->cl_clid;
+ __entry->task_id = task->tk_pid;
__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
__entry->version = task->tk_client->cl_vers;
__assign_str(progname, task->tk_client->cl_program->name)
__entry->backlog = ktime_to_us(backlog);
__entry->rtt = ktime_to_us(rtt);
__entry->execute = ktime_to_us(execute);
- __assign_str(addr,
- task->tk_xprt->address_strings[RPC_DISPLAY_ADDR]);
- __assign_str(port,
- task->tk_xprt->address_strings[RPC_DISPLAY_PORT]);
),
- TP_printk("peer=[%s]:%s xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
- __get_str(addr), __get_str(port), __entry->xid,
+ TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
+ __entry->task_id, __entry->client_id, __entry->xid,
__get_str(progname), __entry->version, __get_str(procname),
__entry->backlog, __entry->rtt, __entry->execute)
);
)
);
+TRACE_EVENT(ufshcd_upiu,
+ TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf),
+
+ TP_ARGS(dev_name, str, hdr, tsf),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev_name)
+ __string(str, str)
+ __array(unsigned char, hdr, 12)
+ __array(unsigned char, tsf, 16)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev_name);
+ __assign_str(str, str);
+ memcpy(__entry->hdr, hdr, sizeof(__entry->hdr));
+ memcpy(__entry->tsf, tsf, sizeof(__entry->tsf));
+ ),
+
+ TP_printk(
+ "%s: %s: HDR:%s, CDB:%s",
+ __get_str(str), __get_str(dev_name),
+ __print_hex(__entry->hdr, sizeof(__entry->hdr)),
+ __print_hex(__entry->tsf, sizeof(__entry->tsf))
+ )
+);
+
#endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
/* This part must be outside protection */
TP_printk("work struct %p", __entry->work)
);
+struct pool_workqueue;
+
/**
* workqueue_queue_work - called when a work gets queued
* @req_cpu: the requested cpu
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
-TRACE_EVENT(xen_mmu_flush_tlb_all,
- TP_PROTO(int x),
- TP_ARGS(x),
- TP_STRUCT__entry(__array(char, x, 0)),
- TP_fast_assign((void)x),
- TP_printk("%s", "")
- );
-
-TRACE_EVENT(xen_mmu_flush_tlb,
- TP_PROTO(int x),
- TP_ARGS(x),
- TP_STRUCT__entry(__array(char, x, 0)),
- TP_fast_assign((void)x),
- TP_printk("%s", "")
- );
-
TRACE_EVENT(xen_mmu_flush_tlb_one_user,
TP_PROTO(unsigned long addr),
TP_ARGS(addr),
BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
+ BPF_BTF_GET_FD_BY_ID,
};
enum bpf_map_type {
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
BPF_MAP_TYPE_CPUMAP,
+ BPF_MAP_TYPE_XSKMAP,
+ BPF_MAP_TYPE_SOCKHASH,
};
enum bpf_prog_type {
__u32 start_id;
__u32 prog_id;
__u32 map_id;
+ __u32 btf_id;
};
__u32 next_id;
__u32 open_flags;
};
} __attribute__((aligned(8)));
-/* BPF helper function descriptions:
- *
- * void *bpf_map_lookup_elem(&map, &key)
- * Return: Map value or NULL
- *
- * int bpf_map_update_elem(&map, &key, &value, flags)
- * Return: 0 on success or negative error
- *
- * int bpf_map_delete_elem(&map, &key)
- * Return: 0 on success or negative error
- *
- * int bpf_probe_read(void *dst, int size, void *src)
- * Return: 0 on success or negative error
+/* The description below is an attempt at providing documentation to eBPF
+ * developers about the multiple available eBPF helper functions. It can be
+ * parsed and used to produce a manual page. The workflow is the following,
+ * and requires the rst2man utility:
+ *
+ * $ ./scripts/bpf_helpers_doc.py \
+ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
+ * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
+ * $ man /tmp/bpf-helpers.7
+ *
+ * Note that in order to produce this external documentation, some RST
+ * formatting is used in the descriptions to get "bold" and "italics" in
+ * manual pages. Also note that the few trailing white spaces are
+ * intentional, removing them would break paragraphs for rst2man.
+ *
+ * Start of BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Perform a lookup in *map* for an entry associated to *key*.
+ * Return
+ * Map value associated to *key*, or **NULL** if no entry was
+ * found.
+ *
+ * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+ * Description
+ * Add or update the value of the entry associated to *key* in
+ * *map* with *value*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * Flag value **BPF_NOEXIST** cannot be used for maps of types
+ * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all
+ * elements always exist), the helper would return an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_delete_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Delete entry with *key* from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * Description
+ * For tracing programs, safely attempt to read *size* bytes from
+ * address *src* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* u64 bpf_ktime_get_ns(void)
- * Return: current ktime
- *
- * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
- * Return: length of buffer written or negative error
- *
- * u32 bpf_prandom_u32(void)
- * Return: random value
- *
- * u32 bpf_raw_smp_processor_id(void)
- * Return: SMP processor ID
- *
- * int bpf_skb_store_bytes(skb, offset, from, len, flags)
- * store bytes into packet
- * @skb: pointer to skb
- * @offset: offset within packet from skb->mac_header
- * @from: pointer where to copy bytes from
- * @len: number of bytes to store into packet
- * @flags: bit 0 - if true, recompute skb->csum
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_l3_csum_replace(skb, offset, from, to, flags)
- * recompute IP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where IP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_l4_csum_replace(skb, offset, from, to, flags)
- * recompute TCP/UDP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where TCP/UDP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * bit 4 - is pseudo header
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_tail_call(ctx, prog_array_map, index)
- * jump into another BPF program
- * @ctx: context pointer passed to next program
- * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- * @index: 32-bit index inside array that selects specific program to run
- * Return: 0 on success or negative error
- *
- * int bpf_clone_redirect(skb, ifindex, flags)
- * redirect to another netdev
- * @skb: pointer to skb
- * @ifindex: ifindex of the net device
- * @flags: bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * Return: 0 on success or negative error
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Return
+ * Current *ktime*.
+ *
+ * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
+ * Description
+ * This helper is a "printk()-like" facility for debugging. It
+ * prints a message defined by format *fmt* (of size *fmt_size*)
+ * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if
+ * available. It can take up to three additional **u64**
+ * arguments (as an eBPF helpers, the total number of arguments is
+ * limited to five).
+ *
+ * Each time the helper is called, it appends a line to the trace.
+ * The format of the trace is customizable, and the exact output
+ * one will get depends on the options set in
+ * *\/sys/kernel/debug/tracing/trace_options* (see also the
+ * *README* file under the same directory). However, it usually
+ * defaults to something like:
+ *
+ * ::
+ *
+ * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg>
+ *
+ * In the above:
+ *
+ * * ``telnet`` is the name of the current task.
+ * * ``470`` is the PID of the current task.
+ * * ``001`` is the CPU number on which the task is
+ * running.
+ * * In ``.N..``, each character refers to a set of
+ * options (whether irqs are enabled, scheduling
+ * options, whether hard/softirqs are running, level of
+ * preempt_disabled respectively). **N** means that
+ * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED**
+ * are set.
+ * * ``419421.045894`` is a timestamp.
+ * * ``0x00000001`` is a fake value used by BPF for the
+ * instruction pointer register.
+ * * ``<formatted msg>`` is the message formatted with
+ * *fmt*.
+ *
+ * The conversion specifiers supported by *fmt* are similar, but
+ * more limited than for printk(). They are **%d**, **%i**,
+ * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**,
+ * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size
+ * of field, padding with zeroes, etc.) is available, and the
+ * helper will return **-EINVAL** (but print nothing) if it
+ * encounters an unknown specifier.
+ *
+ * Also, note that **bpf_trace_printk**\ () is slow, and should
+ * only be used for debugging purposes. For this reason, a notice
+ * bloc (spanning several lines) is printed to kernel logs and
+ * states that the helper should not be used "for production use"
+ * the first time this helper is used (or more precisely, when
+ * **trace_printk**\ () buffers are allocated). For passing values
+ * to user space, perf events should be preferred.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * u32 bpf_get_prandom_u32(void)
+ * Description
+ * Get a pseudo-random number.
+ *
+ * From a security point of view, this helper uses its own
+ * pseudo-random internal state, and cannot be used to infer the
+ * seed of other random functions in the kernel. However, it is
+ * essential to note that the generator used by the helper is not
+ * cryptographically secure.
+ * Return
+ * A random 32-bit unsigned value.
+ *
+ * u32 bpf_get_smp_processor_id(void)
+ * Description
+ * Get the SMP (symmetric multiprocessing) processor id. Note that
+ * all programs run with preemption disabled, which means that the
+ * SMP processor id is stable during all the execution of the
+ * program.
+ * Return
+ * The SMP id of the processor running the program.
+ *
+ * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. *flags* are a combination of
+ * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * checksum for the packet after storing the bytes) and
+ * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
+ * **->swhash** and *skb*\ **->l4hash** to 0).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
+ * Description
+ * Recompute the layer 3 (e.g. IP) checksum for the packet
+ * associated to *skb*. Computation is incremental, so the helper
+ * must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored in *size*.
+ * Alternatively, it is possible to store the difference between
+ * the previous and the new values of the header field in *to*, by
+ * setting *from* and *size* to 0. For both methods, *offset*
+ * indicates the location of the IP checksum within the packet.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
+ * Description
+ * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
+ * packet associated to *skb*. Computation is incremental, so the
+ * helper must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored on the lowest
+ * four bits of *flags*. Alternatively, it is possible to store
+ * the difference between the previous and the new values of the
+ * header field in *to*, by setting *from* and the four lowest
+ * bits of *flags* to 0. For both methods, *offset* indicates the
+ * location of the IP checksum within the packet. In addition to
+ * the size of the field, *flags* can be added (bitwise OR) actual
+ * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
+ * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
+ * for updates resulting in a null checksum the value is set to
+ * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
+ * the checksum is to be computed against a pseudo-header.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
+ * Description
+ * This special helper is used to trigger a "tail call", or in
+ * other words, to jump into another eBPF program. The same stack
+ * frame is used (but values on stack and in registers for the
+ * caller are not accessible to the callee). This mechanism allows
+ * for program chaining, either for raising the maximum number of
+ * available eBPF instructions, or to execute given programs in
+ * conditional blocks. For security reasons, there is an upper
+ * limit to the number of successive tail calls that can be
+ * performed.
+ *
+ * Upon call of this helper, the program attempts to jump into a
+ * program referenced at index *index* in *prog_array_map*, a
+ * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
+ * *ctx*, a pointer to the context.
+ *
+ * If the call succeeds, the kernel immediately runs the first
+ * instruction of the new program. This is not a function call,
+ * and it never returns to the previous program. If the call
+ * fails, then the helper has no effect, and the caller continues
+ * to run its subsequent instructions. A call can fail if the
+ * destination program for the jump does not exist (i.e. *index*
+ * is superior to the number of entries in *prog_array_map*), or
+ * if the maximum number of tail calls has been reached for this
+ * chain of programs. This limit is defined in the kernel by the
+ * macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
+ * which is currently set to 32.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
+ * Description
+ * Clone and redirect the packet associated to *skb* to another
+ * net device of index *ifindex*. Both ingress and egress
+ * interfaces can be used for redirection. The **BPF_F_INGRESS**
+ * value in *flags* is used to make the distinction (ingress path
+ * is selected if the flag is present, egress path otherwise).
+ * This is the only flag supported for now.
+ *
+ * In comparison with **bpf_redirect**\ () helper,
+ * **bpf_clone_redirect**\ () has the associated cost of
+ * duplicating the packet buffer, but this can be executed out of
+ * the eBPF program. Conversely, **bpf_redirect**\ () is more
+ * efficient, but it is handled through an action code where the
+ * redirection happens only after the eBPF program has returned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* u64 bpf_get_current_pid_tgid(void)
- * Return: current->tgid << 32 | current->pid
+ * Return
+ * A 64-bit integer containing the current tgid and pid, and
+ * created as such:
+ * *current_task*\ **->tgid << 32 \|**
+ * *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
- * Return: current_gid << 32 | current_uid
- *
- * int bpf_get_current_comm(char *buf, int size_of_buf)
- * stores current->comm into buf
- * Return: 0 on success or negative error
- *
- * u32 bpf_get_cgroup_classid(skb)
- * retrieve a proc's classid
- * @skb: pointer to skb
- * Return: classid if != 0
- *
- * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
- * Return: 0 on success or negative error
- *
- * int bpf_skb_vlan_pop(skb)
- * Return: 0 on success or negative error
- *
- * int bpf_skb_get_tunnel_key(skb, key, size, flags)
- * int bpf_skb_set_tunnel_key(skb, key, size, flags)
- * retrieve or populate tunnel metadata
- * @skb: pointer to skb
- * @key: pointer to 'struct bpf_tunnel_key'
- * @size: size of 'struct bpf_tunnel_key'
- * @flags: room for future extensions
- * Return: 0 on success or negative error
- *
- * u64 bpf_perf_event_read(map, flags)
- * read perf event counter value
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * Return: value of perf event counter read or error code
- *
- * int bpf_redirect(ifindex, flags)
- * redirect to another netdev
- * @ifindex: ifindex of the net device
- * @flags:
- * cls_bpf:
- * bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * xdp_bpf:
- * all bits - reserved
- * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
- * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
- * int bpf_redirect_map(map, key, flags)
- * redirect to endpoint in map
- * @map: pointer to dev map
- * @key: index in map to lookup
- * @flags: --
- * Return: XDP_REDIRECT on success or XDP_ABORT on error
- *
- * u32 bpf_get_route_realm(skb)
- * retrieve a dst's tclassid
- * @skb: pointer to skb
- * Return: realm if != 0
- *
- * int bpf_perf_event_output(ctx, map, flags, data, size)
- * output perf raw sample
- * @ctx: struct pt_regs*
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * @data: data on stack to be output as raw data
- * @size: size of data
- * Return: 0 on success or negative error
- *
- * int bpf_get_stackid(ctx, map, flags)
- * walk user or kernel stack and return id
- * @ctx: struct pt_regs*
- * @map: pointer to stack_trace map
- * @flags: bits 0-7 - numer of stack frames to skip
- * bit 8 - collect user stack instead of kernel
- * bit 9 - compare stacks by hash only
- * bit 10 - if two different stacks hash into the same stackid
- * discard old
- * other bits - reserved
- * Return: >= 0 stackid on success or negative error
- *
- * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
- * calculate csum diff
- * @from: raw from buffer
- * @from_size: length of from buffer
- * @to: raw to buffer
- * @to_size: length of to buffer
- * @seed: optional seed
- * Return: csum result or negative error code
- *
- * int bpf_skb_get_tunnel_opt(skb, opt, size)
- * retrieve tunnel options metadata
- * @skb: pointer to skb
- * @opt: pointer to raw tunnel option data
- * @size: size of @opt
- * Return: option size
- *
- * int bpf_skb_set_tunnel_opt(skb, opt, size)
- * populate tunnel options metadata
- * @skb: pointer to skb
- * @opt: pointer to raw tunnel option data
- * @size: size of @opt
- * Return: 0 on success or negative error
- *
- * int bpf_skb_change_proto(skb, proto, flags)
- * Change protocol of the skb. Currently supported is v4 -> v6,
- * v6 -> v4 transitions. The helper will also resize the skb. eBPF
- * program is expected to fill the new headers via skb_store_bytes
- * and lX_csum_replace.
- * @skb: pointer to skb
- * @proto: new skb->protocol type
- * @flags: reserved
- * Return: 0 on success or negative error
- *
- * int bpf_skb_change_type(skb, type)
- * Change packet type of skb.
- * @skb: pointer to skb
- * @type: new skb->pkt_type type
- * Return: 0 on success or negative error
- *
- * int bpf_skb_under_cgroup(skb, map, index)
- * Check cgroup2 membership of skb
- * @skb: pointer to skb
- * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
- * @index: index of the cgroup in the bpf_map
- * Return:
- * == 0 skb failed the cgroup2 descendant test
- * == 1 skb succeeded the cgroup2 descendant test
- * < 0 error
- *
- * u32 bpf_get_hash_recalc(skb)
- * Retrieve and possibly recalculate skb->hash.
- * @skb: pointer to skb
- * Return: hash
+ * Return
+ * A 64-bit integer containing the current GID and UID, and
+ * created as such: *current_gid* **<< 32 \|** *current_uid*.
+ *
+ * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * Description
+ * Copy the **comm** attribute of the current task into *buf* of
+ * *size_of_buf*. The **comm** attribute contains the name of
+ * the executable (excluding the path) for the current task. The
+ * *size_of_buf* must be strictly positive. On success, the
+ * helper makes sure that the *buf* is NUL-terminated. On failure,
+ * it is filled with zeroes.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u32 bpf_get_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * Retrieve the classid for the current task, i.e. for the net_cls
+ * cgroup to which *skb* belongs.
+ *
+ * This helper can be used on TC egress path, but not on ingress.
+ *
+ * The net_cls cgroup provides an interface to tag network packets
+ * based on a user-provided identifier for all traffic coming from
+ * the tasks belonging to the related cgroup. See also the related
+ * kernel documentation, available from the Linux sources in file
+ * *Documentation/cgroup-v1/net_cls.txt*.
+ *
+ * The Linux kernel has two versions for cgroups: there are
+ * cgroups v1 and cgroups v2. Both are available to users, who can
+ * use a mixture of them, but note that the net_cls cgroup is for
+ * cgroup v1 only. This makes it incompatible with BPF programs
+ * run on cgroups, which is a cgroup-v2-only feature (a socket can
+ * only hold data for one version of cgroups at a time).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to
+ * "**y**" or to "**m**".
+ * Return
+ * The classid, or 0 for the default unconfigured classid.
+ *
+ * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+ * Description
+ * Push a *vlan_tci* (VLAN tag control information) of protocol
+ * *vlan_proto* to the packet associated to *skb*, then update
+ * the checksum. Note that if *vlan_proto* is different from
+ * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
+ * be **ETH_P_8021Q**.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_vlan_pop(struct sk_buff *skb)
+ * Description
+ * Pop a VLAN header from the packet associated to *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Get tunnel metadata. This helper takes a pointer *key* to an
+ * empty **struct bpf_tunnel_key** of **size**, that will be
+ * filled with tunnel metadata for the packet associated to *skb*.
+ * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
+ * indicates that the tunnel is based on IPv6 protocol instead of
+ * IPv4.
+ *
+ * The **struct bpf_tunnel_key** is an object that generalizes the
+ * principal parameters used by various tunneling protocols into a
+ * single struct. This way, it can be used to easily make a
+ * decision based on the contents of the encapsulation header,
+ * "summarized" in this struct. In particular, it holds the IP
+ * address of the remote end (IPv4 or IPv6, depending on the case)
+ * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
+ * this struct exposes the *key*\ **->tunnel_id**, which is
+ * generally mapped to a VNI (Virtual Network Identifier), making
+ * it programmable together with the **bpf_skb_set_tunnel_key**\
+ * () helper.
+ *
+ * Let's imagine that the following code is part of a program
+ * attached to the TC ingress interface, on one end of a GRE
+ * tunnel, and is supposed to filter out all messages coming from
+ * remote ends with IPv4 address other than 10.0.0.1:
+ *
+ * ::
+ *
+ * int ret;
+ * struct bpf_tunnel_key key = {};
+ *
+ * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ * if (ret < 0)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * if (key.remote_ipv4 != 0x0a000001)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * return TC_ACT_OK; // accept packet
+ *
+ * This interface can also be used with all encapsulation devices
+ * that can operate in "collect metadata" mode: instead of having
+ * one network device per specific configuration, the "collect
+ * metadata" mode only requires a single device where the
+ * configuration can be extracted from this helper.
+ *
+ * This can be used together with various tunnels such as VXLan,
+ * Geneve, GRE or IP in IP (IPIP).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Populate tunnel metadata for packet associated to *skb.* The
+ * tunnel metadata is set to the contents of *key*, of *size*. The
+ * *flags* can be set to a combination of the following values:
+ *
+ * **BPF_F_TUNINFO_IPV6**
+ * Indicate that the tunnel is based on IPv6 protocol
+ * instead of IPv4.
+ * **BPF_F_ZERO_CSUM_TX**
+ * For IPv4 packets, add a flag to tunnel metadata
+ * indicating that checksum computation should be skipped
+ * and checksum set to zeroes.
+ * **BPF_F_DONT_FRAGMENT**
+ * Add a flag to tunnel metadata indicating that the
+ * packet should not be fragmented.
+ * **BPF_F_SEQ_NUMBER**
+ * Add a flag to tunnel metadata indicating that a
+ * sequence number should be added to tunnel header before
+ * sending the packet. This flag was added for GRE
+ * encapsulation, but might be used with other protocols
+ * as well in the future.
+ *
+ * Here is a typical usage on the transmit path:
+ *
+ * ::
+ *
+ * struct bpf_tunnel_key key;
+ * populate key ...
+ * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
+ *
+ * See also the description of the **bpf_skb_get_tunnel_key**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags)
+ * Description
+ * Read the value of a perf event counter. This helper relies on a
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of
+ * the perf event counter is selected when *map* is updated with
+ * perf event file descriptors. The *map* is an array whose size
+ * is the number of available CPUs, and each cell contains a value
+ * relative to one CPU. The value to retrieve is indicated by
+ * *flags*, that contains the index of the CPU to look up, masked
+ * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * Note that before Linux 4.13, only hardware perf event can be
+ * retrieved.
+ *
+ * Also, be aware that the newer helper
+ * **bpf_perf_event_read_value**\ () is recommended over
+ * **bpf_perf_event_read**\ () in general. The latter has some ABI
+ * quirks where error and counter value are used as a return code
+ * (which is wrong to do since ranges may overlap). This issue is
+ * fixed with **bpf_perf_event_read_value**\ (), which at the same
+ * time provides more features over the **bpf_perf_event_read**\
+ * () interface. Please refer to the description of
+ * **bpf_perf_event_read_value**\ () for details.
+ * Return
+ * The value of the perf event counter read from the map, or a
+ * negative error code in case of failure.
+ *
+ * int bpf_redirect(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_clone_redirect**\
+ * (), except that the packet is not cloned, which provides
+ * increased performance.
+ *
+ * Except for XDP, both ingress and egress interfaces can be used
+ * for redirection. The **BPF_F_INGRESS** value in *flags* is used
+ * to make the distinction (ingress path is selected if the flag
+ * is present, egress path otherwise). Currently, XDP only
+ * supports redirection to the egress interface, and accepts no
+ * flag at all.
+ *
+ * The same effect can be attained with the more generic
+ * **bpf_redirect_map**\ (), which requires specific maps to be
+ * used but offers better performance.
+ * Return
+ * For XDP, the helper returns **XDP_REDIRECT** on success or
+ * **XDP_ABORTED** on error. For other program types, the values
+ * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on
+ * error.
+ *
+ * u32 bpf_get_route_realm(struct sk_buff *skb)
+ * Description
+ * Retrieve the realm or the route, that is to say the
+ * **tclassid** field of the destination for the *skb*. The
+ * indentifier retrieved is a user-provided tag, similar to the
+ * one used with the net_cls cgroup (see description for
+ * **bpf_get_cgroup_classid**\ () helper), but here this tag is
+ * held by a route (a destination entry), not by a task.
+ *
+ * Retrieving this identifier works with the clsact TC egress hook
+ * (see also **tc-bpf(8)**), or alternatively on conventional
+ * classful egress qdiscs, but not on TC ingress path. In case of
+ * clsact TC egress hook, this has the advantage that, internally,
+ * the destination entry has not been dropped yet in the transmit
+ * path. Therefore, the destination entry does not need to be
+ * artificially held via **netif_keep_dst**\ () for a classful
+ * qdisc until the *skb* is freed.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_IP_ROUTE_CLASSID** configuration option.
+ * Return
+ * The realm of the route for the packet associated to *skb*, or 0
+ * if none was found.
+ *
+ * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * The context of the program *ctx* needs also be passed to the
+ * helper.
+ *
+ * On user space, a program willing to read the values needs to
+ * call **perf_event_open**\ () on the perf event (either for
+ * one or for all CPUs) and to store the file descriptor into the
+ * *map*. This must be done before the eBPF program can send data
+ * into it. An example is available in file
+ * *samples/bpf/trace_output_user.c* in the Linux kernel source
+ * tree (the eBPF program counterpart is in
+ * *samples/bpf/trace_output_kern.c*).
+ *
+ * **bpf_perf_event_output**\ () achieves better performance
+ * than **bpf_trace_printk**\ () for sharing data with user
+ * space, and is much better suitable for streaming data from eBPF
+ * programs.
+ *
+ * Note that this helper is not restricted to tracing use cases
+ * and can be used with programs attached to TC or XDP as well,
+ * where it allows for passing data to user space listeners. Data
+ * can be:
+ *
+ * * Only custom structs,
+ * * Only the packet payload, or
+ * * A combination of both.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * Description
+ * This helper was provided as an easy way to load data from a
+ * packet. It can be used to load *len* bytes from *offset* from
+ * the packet associated to *skb*, into the buffer pointed by
+ * *to*.
+ *
+ * Since Linux 4.7, usage of this helper has mostly been replaced
+ * by "direct packet access", enabling packet data to be
+ * manipulated with *skb*\ **->data** and *skb*\ **->data_end**
+ * pointing respectively to the first byte of packet data and to
+ * the byte after the last byte of packet data. However, it
+ * remains useful if one wishes to read large quantities of data
+ * at once from a packet into the eBPF stack.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
+ * Description
+ * Walk a user or a kernel stack and return its id. To achieve
+ * this, the helper needs *ctx*, which is a pointer to the context
+ * on which the tracing program is executed, and a pointer to a
+ * *map* of type **BPF_MAP_TYPE_STACK_TRACE**.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * a combination of the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_FAST_STACK_CMP**
+ * Compare stacks by hash only.
+ * **BPF_F_REUSE_STACKID**
+ * If two different stacks hash into the same *stackid*,
+ * discard the old one.
+ *
+ * The stack id retrieved is a 32 bit long integer handle which
+ * can be further combined with other data (including other stack
+ * ids) and used as a key into maps. This can be useful for
+ * generating a variety of graphs (such as flame graphs or off-cpu
+ * graphs).
+ *
+ * For walking a stack, this helper is an improvement over
+ * **bpf_probe_read**\ (), which can be used with unrolled loops
+ * but is not efficient and consumes a lot of eBPF instructions.
+ * Instead, **bpf_get_stackid**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * Return
+ * The positive or null stack id on success, or a negative error
+ * in case of failure.
+ *
+ * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed)
+ * Description
+ * Compute a checksum difference, from the raw buffer pointed by
+ * *from*, of length *from_size* (that must be a multiple of 4),
+ * towards the raw buffer pointed by *to*, of size *to_size*
+ * (same remark). An optional *seed* can be added to the value
+ * (this can be cascaded, the seed may come from a previous call
+ * to the helper).
+ *
+ * This is flexible enough to be used in several ways:
+ *
+ * * With *from_size* == 0, *to_size* > 0 and *seed* set to
+ * checksum, it can be used when pushing new data.
+ * * With *from_size* > 0, *to_size* == 0 and *seed* set to
+ * checksum, it can be used when removing data from a packet.
+ * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it
+ * can be used to compute a diff. Note that *from_size* and
+ * *to_size* do not need to be equal.
+ *
+ * This helper can be used in combination with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to
+ * which one can feed in the difference computed with
+ * **bpf_csum_diff**\ ().
+ * Return
+ * The checksum result, or a negative error code in case of
+ * failure.
+ *
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Retrieve tunnel options metadata for the packet associated to
+ * *skb*, and store the raw tunnel option data to the buffer *opt*
+ * of *size*.
+ *
+ * This helper can be used with encapsulation devices that can
+ * operate in "collect metadata" mode (please refer to the related
+ * note in the description of **bpf_skb_get_tunnel_key**\ () for
+ * more details). A particular example where this can be used is
+ * in combination with the Geneve encapsulation protocol, where it
+ * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper)
+ * and retrieving arbitrary TLVs (Type-Length-Value headers) from
+ * the eBPF program. This allows for full customization of these
+ * headers.
+ * Return
+ * The size of the option data retrieved.
+ *
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Set tunnel options metadata for the packet associated to *skb*
+ * to the option data contained in the raw buffer *opt* of *size*.
+ *
+ * See also the description of the **bpf_skb_get_tunnel_opt**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
+ * Description
+ * Change the protocol of the *skb* to *proto*. Currently
+ * supported are transition from IPv4 to IPv6, and from IPv6 to
+ * IPv4. The helper takes care of the groundwork for the
+ * transition, including resizing the socket buffer. The eBPF
+ * program is expected to fill the new headers, if any, via
+ * **skb_store_bytes**\ () and to recompute the checksums with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\
+ * (). The main case for this helper is to perform NAT64
+ * operations out of an eBPF program.
+ *
+ * Internally, the GSO type is marked as dodgy so that headers are
+ * checked and segments are recalculated by the GSO/GRO engine.
+ * The size for GSO target is adapted as well.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_type(struct sk_buff *skb, u32 type)
+ * Description
+ * Change the packet type for the packet associated to *skb*. This
+ * comes down to setting *skb*\ **->pkt_type** to *type*, except
+ * the eBPF program does not have a write access to *skb*\
+ * **->pkt_type** beside this helper. Using a helper here allows
+ * for graceful handling of errors.
+ *
+ * The major use case is to change incoming *skb*s to
+ * **PACKET_HOST** in a programmatic way instead of having to
+ * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for
+ * example.
+ *
+ * Note that *type* only allows certain values. At this time, they
+ * are:
+ *
+ * **PACKET_HOST**
+ * Packet is for us.
+ * **PACKET_BROADCAST**
+ * Send packet to all.
+ * **PACKET_MULTICAST**
+ * Send packet to group.
+ * **PACKET_OTHERHOST**
+ * Send packet to someone else.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
+ * Description
+ * Check whether *skb* is a descendant of the cgroup2 held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* failed the cgroup2 descendant test.
+ * * 1, if the *skb* succeeded the cgroup2 descendant test.
+ * * A negative error code, if an error occurred.
+ *
+ * u32 bpf_get_hash_recalc(struct sk_buff *skb)
+ * Description
+ * Retrieve the hash of the packet, *skb*\ **->hash**. If it is
+ * not set, in particular if the hash was cleared due to mangling,
+ * recompute this hash. Later accesses to the hash can be done
+ * directly with *skb*\ **->hash**.
+ *
+ * Calling **bpf_set_hash_invalid**\ (), changing a packet
+ * prototype with **bpf_skb_change_proto**\ (), or calling
+ * **bpf_skb_store_bytes**\ () with the
+ * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear
+ * the hash and to trigger a new computation for the next call to
+ * **bpf_get_hash_recalc**\ ().
+ * Return
+ * The 32-bit hash.
*
* u64 bpf_get_current_task(void)
- * Returns current task_struct
- * Return: current
- *
- * int bpf_probe_write_user(void *dst, void *src, int len)
- * safely attempt to write to a location
- * @dst: destination address in userspace
- * @src: source address on stack
- * @len: number of bytes to copy
- * Return: 0 on success or negative error
- *
- * int bpf_current_task_under_cgroup(map, index)
- * Check cgroup2 membership of current task
- * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
- * @index: index of the cgroup in the bpf_map
- * Return:
- * == 0 current failed the cgroup2 descendant test
- * == 1 current succeeded the cgroup2 descendant test
- * < 0 error
- *
- * int bpf_skb_change_tail(skb, len, flags)
- * The helper will resize the skb to the given new size, to be used f.e.
- * with control messages.
- * @skb: pointer to skb
- * @len: new skb length
- * @flags: reserved
- * Return: 0 on success or negative error
- *
- * int bpf_skb_pull_data(skb, len)
- * The helper will pull in non-linear data in case the skb is non-linear
- * and not all of len are part of the linear section. Only needed for
- * read/write with direct packet access.
- * @skb: pointer to skb
- * @len: len to make read/writeable
- * Return: 0 on success or negative error
- *
- * s64 bpf_csum_update(skb, csum)
- * Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
- * @skb: pointer to skb
- * @csum: csum to add
- * Return: csum on success or negative error
- *
- * void bpf_set_hash_invalid(skb)
- * Invalidate current skb->hash.
- * @skb: pointer to skb
- *
- * int bpf_get_numa_node_id()
- * Return: Id of current NUMA node.
- *
- * int bpf_skb_change_head()
- * Grows headroom of skb and adjusts MAC header offset accordingly.
- * Will extends/reallocae as required automatically.
- * May change skb data pointer and will thus invalidate any check
- * performed for direct packet access.
- * @skb: pointer to skb
- * @len: length of header to be pushed in front
- * @flags: Flags (unused for now)
- * Return: 0 on success or negative error
- *
- * int bpf_xdp_adjust_head(xdp_md, delta)
- * Adjust the xdp_md.data by delta
- * @xdp_md: pointer to xdp_md
- * @delta: An positive/negative integer to be added to xdp_md.data
- * Return: 0 on success or negative on error
+ * Return
+ * A pointer to the current task struct.
+ *
+ * int bpf_probe_write_user(void *dst, const void *src, u32 len)
+ * Description
+ * Attempt in a safe way to write *len* bytes from the buffer
+ * *src* to *dst* in memory. It only works for threads that are in
+ * user context, and *dst* must be a valid user space address.
+ *
+ * This helper should not be used to implement any kind of
+ * security mechanism because of TOC-TOU attacks, but rather to
+ * debug, divert, and manipulate execution of semi-cooperative
+ * processes.
+ *
+ * Keep in mind that this feature is meant for experiments, and it
+ * has a risk of crashing the system and running programs.
+ * Therefore, when an eBPF program using this helper is attached,
+ * a warning including PID and process name is printed to kernel
+ * logs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
+ * Description
+ * Check whether the probe is being run is the context of a given
+ * subset of the cgroup2 hierarchy. The cgroup2 to test is held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* task belongs to the cgroup2.
+ * * 1, if the *skb* task does not belong to the cgroup2.
+ * * A negative error code, if an error occurred.
+ *
+ * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Resize (trim or grow) the packet associated to *skb* to the
+ * new *len*. The *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * The basic idea is that the helper performs the needed work to
+ * change the size of the packet, then the eBPF program rewrites
+ * the rest via helpers like **bpf_skb_store_bytes**\ (),
+ * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ ()
+ * and others. This helper is a slow path utility intended for
+ * replies with control messages. And because it is targeted for
+ * slow path, the helper itself can afford to be slow: it
+ * implicitly linearizes, unclones and drops offloads from the
+ * *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_pull_data(struct sk_buff *skb, u32 len)
+ * Description
+ * Pull in non-linear data in case the *skb* is non-linear and not
+ * all of *len* are part of the linear section. Make *len* bytes
+ * from *skb* readable and writable. If a zero value is passed for
+ * *len*, then the whole length of the *skb* is pulled.
+ *
+ * This helper is only needed for reading and writing with direct
+ * packet access.
+ *
+ * For direct packet access, testing that offsets to access
+ * are within packet boundaries (test on *skb*\ **->data_end**) is
+ * susceptible to fail if offsets are invalid, or if the requested
+ * data is in non-linear parts of the *skb*. On failure the
+ * program can just bail out, or in the case of a non-linear
+ * buffer, use a helper to make the data available. The
+ * **bpf_skb_load_bytes**\ () helper is a first solution to access
+ * the data. Another one consists in using **bpf_skb_pull_data**
+ * to pull in once the non-linear parts, then retesting and
+ * eventually access the data.
+ *
+ * At the same time, this also makes sure the *skb* is uncloned,
+ * which is a necessary condition for direct write. As this needs
+ * to be an invariant for the write part only, the verifier
+ * detects writes and adds a prologue that is calling
+ * **bpf_skb_pull_data()** to effectively unclone the *skb* from
+ * the very beginning in case it is indeed cloned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum)
+ * Description
+ * Add the checksum *csum* into *skb*\ **->csum** in case the
+ * driver has supplied a checksum for the entire packet into that
+ * field. Return an error otherwise. This helper is intended to be
+ * used in combination with **bpf_csum_diff**\ (), in particular
+ * when the checksum needs to be updated after data has been
+ * written into the packet through direct packet access.
+ * Return
+ * The checksum on success, or a negative error code in case of
+ * failure.
+ *
+ * void bpf_set_hash_invalid(struct sk_buff *skb)
+ * Description
+ * Invalidate the current *skb*\ **->hash**. It can be used after
+ * mangling on headers through direct packet access, in order to
+ * indicate that the hash is outdated and to trigger a
+ * recalculation the next time the kernel tries to access this
+ * hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ *
+ * int bpf_get_numa_node_id(void)
+ * Description
+ * Return the id of the current NUMA node. The primary use case
+ * for this helper is the selection of sockets for the local NUMA
+ * node, when the program is attached to sockets using the
+ * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**),
+ * but the helper is also available to other eBPF program types,
+ * similarly to **bpf_get_smp_processor_id**\ ().
+ * Return
+ * The id of current NUMA node.
+ *
+ * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Grows headroom of packet associated to *skb* and adjusts the
+ * offset of the MAC header accordingly, adding *len* bytes of
+ * space. It automatically extends and reallocates memory as
+ * required.
+ *
+ * This helper can be used on a layer 3 *skb* to push a MAC header
+ * for redirection into a layer 2 device.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that
+ * it is possible to use a negative value for *delta*. This helper
+ * can be used to prepare the packet for pushing or popping
+ * headers.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
- * Copy a NUL terminated string from unsafe address. In case the string
- * length is smaller than size, the target is not padded with further NUL
- * bytes. In case the string length is larger than size, just count-1
- * bytes are copied and the last byte is set to NUL.
- * @dst: destination address
- * @size: maximum number of bytes to copy, including the trailing NUL
- * @unsafe_ptr: unsafe address
- * Return:
- * > 0 length of the string including the trailing NUL on success
- * < 0 error
- *
- * u64 bpf_get_socket_cookie(skb)
- * Get the cookie for the socket stored inside sk_buff.
- * @skb: pointer to skb
- * Return: 8 Bytes non-decreasing number on success or 0 if the socket
- * field is missing inside sk_buff
- *
- * u32 bpf_get_socket_uid(skb)
- * Get the owner uid of the socket stored inside sk_buff.
- * @skb: pointer to skb
- * Return: uid of the socket owner on success or overflowuid if failed.
- *
- * u32 bpf_set_hash(skb, hash)
- * Set full skb->hash.
- * @skb: pointer to skb
- * @hash: hash to set
- *
- * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
- * Calls setsockopt. Not all opts are available, only those with
- * integer optvals plus TCP_CONGESTION.
- * Supported levels: SOL_SOCKET and IPPROTO_TCP
- * @bpf_socket: pointer to bpf_socket
- * @level: SOL_SOCKET or IPPROTO_TCP
- * @optname: option name
- * @optval: pointer to option value
- * @optlen: length of optval in bytes
- * Return: 0 or negative error
- *
- * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
- * Calls getsockopt. Not all opts are available.
- * Supported levels: IPPROTO_TCP
- * @bpf_socket: pointer to bpf_socket
- * @level: IPPROTO_TCP
- * @optname: option name
- * @optval: pointer to option value
- * @optlen: length of optval in bytes
- * Return: 0 or negative error
- *
- * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
- * Set callback flags for sock_ops
- * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
- * @flags: flags value
- * Return: 0 for no error
- * -EINVAL if there is no full tcp socket
- * bits in flags that are not supported by current kernel
- *
- * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
- * Grow or shrink room in sk_buff.
- * @skb: pointer to skb
- * @len_diff: (signed) amount of room to grow/shrink
- * @mode: operation mode (enum bpf_adj_room_mode)
- * @flags: reserved for future use
- * Return: 0 on success or negative error code
- *
- * int bpf_sk_redirect_map(map, key, flags)
- * Redirect skb to a sock in map using key as a lookup key for the
- * sock in map.
- * @map: pointer to sockmap
- * @key: key to lookup sock in map
- * @flags: reserved for future use
- * Return: SK_PASS
- *
- * int bpf_sock_map_update(skops, map, key, flags)
- * @skops: pointer to bpf_sock_ops
- * @map: pointer to sockmap to update
- * @key: key to insert/update sock in map
- * @flags: same flags as map update elem
- *
- * int bpf_xdp_adjust_meta(xdp_md, delta)
- * Adjust the xdp_md.data_meta by delta
- * @xdp_md: pointer to xdp_md
- * @delta: An positive/negative integer to be added to xdp_md.data_meta
- * Return: 0 on success or negative on error
- *
- * int bpf_perf_event_read_value(map, flags, buf, buf_size)
- * read perf event counter value and perf event enabled/running time
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * @buf: buf to fill
- * @buf_size: size of the buf
- * Return: 0 on success or negative error code
- *
- * int bpf_perf_prog_read_value(ctx, buf, buf_size)
- * read perf prog attached perf event counter and enabled/running time
- * @ctx: pointer to ctx
- * @buf: buf to fill
- * @buf_size: size of the buf
- * Return : 0 on success or negative error code
- *
- * int bpf_override_return(pt_regs, rc)
- * @pt_regs: pointer to struct pt_regs
- * @rc: the return value to set
- *
- * int bpf_msg_redirect_map(map, key, flags)
- * Redirect msg to a sock in map using key as a lookup key for the
- * sock in map.
- * @map: pointer to sockmap
- * @key: key to lookup sock in map
- * @flags: reserved for future use
- * Return: SK_PASS
- *
- * int bpf_bind(ctx, addr, addr_len)
- * Bind socket to address. Only binding to IP is supported, no port can be
- * set in addr.
- * @ctx: pointer to context of type bpf_sock_addr
- * @addr: pointer to struct sockaddr to bind socket to
- * @addr_len: length of sockaddr structure
- * Return: 0 on success or negative error code
- *
- * int bpf_xdp_adjust_tail(xdp_md, delta)
- * Adjust the xdp_md.data_end by delta. Only shrinking of packet's
- * size is supported.
- * @xdp_md: pointer to xdp_md
- * @delta: A negative integer to be added to xdp_md.data_end
- * Return: 0 on success or negative on error
+ * Description
+ * Copy a NUL terminated string from an unsafe address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read()** helper here instead
+ * to read the string would require to estimate the length at
+ * compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * u64 bpf_get_socket_cookie(struct sk_buff *skb)
+ * Description
+ * If the **struct sk_buff** pointed by *skb* has a known socket,
+ * retrieve the cookie (generated by the kernel) of this socket.
+ * If no cookie has been set yet, generate a new cookie. Once
+ * generated, the socket cookie remains stable for the life of the
+ * socket. This helper can be useful for monitoring per socket
+ * networking traffic statistics as it provides a unique socket
+ * identifier per namespace.
+ * Return
+ * A 8-byte long non-decreasing number on success, or 0 if the
+ * socket field is missing inside *skb*.
+ *
+ * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Return
+ * The owner UID of the socket associated to *skb*. If the socket
+ * is **NULL**, or if it is not a full socket (i.e. if it is a
+ * time-wait or a request socket instead), **overflowuid** value
+ * is returned (note that **overflowuid** might also be the actual
+ * UID value for the socket).
+ *
+ * u32 bpf_set_hash(struct sk_buff *skb, u32 hash)
+ * Description
+ * Set the full hash for *skb* (set the field *skb*\ **->hash**)
+ * to value *hash*.
+ * Return
+ * 0
+ *
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **setsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **setsockopt(2)** for more information.
+ * The option value of length *optlen* is pointed by *optval*.
+ *
+ * This helper actually implements a subset of **setsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **SOL_SOCKET**, which supports the following *optname*\ s:
+ * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
+ * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**.
+ * * **IPPROTO_TCP**, which supports the following *optname*\ s:
+ * **TCP_CONGESTION**, **TCP_BPF_IW**,
+ * **TCP_BPF_SNDCWND_CLAMP**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * Description
+ * Grow or shrink the room for data in the packet associated to
+ * *skb* by *len_diff*, and according to the selected *mode*.
+ *
+ * There is a single supported mode at this time:
+ *
+ * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
+ * (room space is added or removed below the layer 3 header).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the endpoint referenced by *map* at
+ * index *key*. Depending on its type, this *map* can contain
+ * references to net devices (for forwarding packets through other
+ * ports), or to CPUs (for redirecting XDP frames to another CPU;
+ * but this is only implemented for native XDP (with driver
+ * support) as of this writing).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * When used to redirect packets to net devices, this helper
+ * provides a high performance increase over **bpf_redirect**\ ().
+ * This is due to various implementation details of the underlying
+ * mechanisms, one of which is the fact that **bpf_redirect_map**\
+ * () tries to send packet as a "bulk" to the device.
+ * Return
+ * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ *
+ * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a *map* referencing sockets. The
+ * *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust the address pointed by *xdp_md*\ **->data_meta** by
+ * *delta* (which can be positive or negative). Note that this
+ * operation modifies the address stored in *xdp_md*\ **->data**,
+ * so the latter must be loaded only after the helper has been
+ * called.
+ *
+ * The use of *xdp_md*\ **->data_meta** is optional and programs
+ * are not required to use it. The rationale is that when the
+ * packet is processed with XDP (e.g. as DoS filter), it is
+ * possible to push further meta data along with it before passing
+ * to the stack, and to give the guarantee that an ingress eBPF
+ * program attached as a TC classifier on the same device can pick
+ * this up for further post-processing. Since TC works with socket
+ * buffers, it remains possible to set from XDP the **mark** or
+ * **priority** pointers, or other pointers for the socket buffer.
+ * Having this scratch space generic and programmable allows for
+ * more flexibility as the user is free to store whatever meta
+ * data they need.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * Read the value of a perf event counter, and store it into *buf*
+ * of size *buf_size*. This helper relies on a *map* of type
+ * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event
+ * counter is selected when *map* is updated with perf event file
+ * descriptors. The *map* is an array whose size is the number of
+ * available CPUs, and each cell contains a value relative to one
+ * CPU. The value to retrieve is indicated by *flags*, that
+ * contains the index of the CPU to look up, masked with
+ * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * This helper behaves in a way close to
+ * **bpf_perf_event_read**\ () helper, save that instead of
+ * just returning the value observed, it fills the *buf*
+ * structure. This allows for additional data to be retrieved: in
+ * particular, the enabled and running times (in *buf*\
+ * **->enabled** and *buf*\ **->running**, respectively) are
+ * copied. In general, **bpf_perf_event_read_value**\ () is
+ * recommended over **bpf_perf_event_read**\ (), which has some
+ * ABI issues and provides fewer functionalities.
+ *
+ * These values are interesting, because hardware PMU (Performance
+ * Monitoring Unit) counters are limited resources. When there are
+ * more PMU based perf events opened than available counters,
+ * kernel will multiplex these events so each event gets certain
+ * percentage (but not all) of the PMU time. In case that
+ * multiplexing happens, the number of samples or counter value
+ * will not reflect the case compared to when no multiplexing
+ * occurs. This makes comparison between different runs difficult.
+ * Typically, the counter value should be normalized before
+ * comparing to other experiments. The usual normalization is done
+ * as follows.
+ *
+ * ::
+ *
+ * normalized_counter = counter * t_enabled / t_running
+ *
+ * Where t_enabled is the time enabled for event and t_running is
+ * the time running for event since last normalization. The
+ * enabled and running times are accumulated since the perf event
+ * open. To achieve scaling factor between two invocations of an
+ * eBPF program, users can can use CPU id as the key (which is
+ * typical for perf array usage model) to remember the previous
+ * value and do the calculation inside the eBPF program.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * For en eBPF program attached to a perf event, retrieve the
+ * value of the event counter associated to *ctx* and store it in
+ * the structure pointed by *buf* and of size *buf_size*. Enabled
+ * and running times are also stored in the structure (see
+ * description of helper **bpf_perf_event_read_value**\ () for
+ * more details).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **getsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **getsockopt(2)** for more information.
+ * The retrieved value is stored in the structure pointed by
+ * *opval* and of length *optlen*.
+ *
+ * This helper actually implements a subset of **getsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **IPPROTO_TCP**, which supports *optname*
+ * **TCP_CONGESTION**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_override_return(struct pt_reg *regs, u64 rc)
+ * Description
+ * Used for error injection, this helper uses kprobes to override
+ * the return value of the probed function, and to set it to *rc*.
+ * The first argument is the context *regs* on which the kprobe
+ * works.
+ *
+ * This helper works by setting setting the PC (program counter)
+ * to an override function which is run in place of the original
+ * probed function. This means the probed function is not run at
+ * all. The replacement function just returns with the required
+ * value.
+ *
+ * This helper has security implications, and thus is subject to
+ * restrictions. It is only available if the kernel was compiled
+ * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
+ * option, and in this case it only works on functions tagged with
+ * **ALLOW_ERROR_INJECTION** in the kernel code.
+ *
+ * Also, the helper is only available for the architectures having
+ * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
+ * x86 architecture is the only one to support this feature.
+ * Return
+ * 0
+ *
+ * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
+ * Description
+ * Attempt to set the value of the **bpf_sock_ops_cb_flags** field
+ * for the full TCP socket associated to *bpf_sock_ops* to
+ * *argval*.
+ *
+ * The primary use of this field is to determine if there should
+ * be calls to eBPF programs of type
+ * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP
+ * code. A program of the same type can change its value, per
+ * connection and as necessary, when the connection is
+ * established. This field is directly accessible for reading, but
+ * this helper must be used for updates in order to return an
+ * error if an eBPF program tries to set a callback that is not
+ * supported in the current kernel.
+ *
+ * The supported callback values that *argval* can combine are:
+ *
+ * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
+ * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
+ * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ *
+ * Here are some examples of where one could call such eBPF
+ * program:
+ *
+ * * When RTO fires.
+ * * When a packet is retransmitted.
+ * * When the connection terminates.
+ * * When a packet is sent.
+ * * When a packet is received.
+ * Return
+ * Code **-EINVAL** if the socket is not a full TCP socket;
+ * otherwise, a positive number containing the bits that could not
+ * be set is returned (which comes down to 0 if all bits were set
+ * as required).
+ *
+ * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, apply the verdict of the eBPF program to
+ * the next *bytes* (number of bytes) of message *msg*.
+ *
+ * For example, this helper can be used in the following cases:
+ *
+ * * A single **sendmsg**\ () or **sendfile**\ () system call
+ * contains multiple logical messages that the eBPF program is
+ * supposed to read and for which it should apply a verdict.
+ * * An eBPF program only cares to read the first *bytes* of a
+ * *msg*. If the message has a large payload, then setting up
+ * and calling the eBPF program repeatedly for all bytes, even
+ * though the verdict is already known, would create unnecessary
+ * overhead.
+ *
+ * When called from within an eBPF program, the helper sets a
+ * counter internal to the BPF infrastructure, that is used to
+ * apply the last verdict to the next *bytes*. If *bytes* is
+ * smaller than the current data being processed from a
+ * **sendmsg**\ () or **sendfile**\ () system call, the first
+ * *bytes* will be sent and the eBPF program will be re-run with
+ * the pointer for start of data pointing to byte number *bytes*
+ * **+ 1**. If *bytes* is larger than the current data being
+ * processed, then the eBPF verdict will be applied to multiple
+ * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are
+ * consumed.
+ *
+ * Note that if a socket closes with the internal counter holding
+ * a non-zero value, this is not a problem because data is not
+ * being buffered for *bytes* and is sent as it is received.
+ * Return
+ * 0
+ *
+ * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, prevent the execution of the verdict eBPF
+ * program for message *msg* until *bytes* (byte number) have been
+ * accumulated.
+ *
+ * This can be used when one needs a specific number of bytes
+ * before a verdict can be assigned, even if the data spans
+ * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme
+ * case would be a user calling **sendmsg**\ () repeatedly with
+ * 1-byte long message segments. Obviously, this is bad for
+ * performance, but it is still valid. If the eBPF program needs
+ * *bytes* bytes to validate a header, this helper can be used to
+ * prevent the eBPF program to be called again until *bytes* have
+ * been accumulated.
+ * Return
+ * 0
+ *
+ * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+ * Description
+ * For socket policies, pull in non-linear data from user space
+ * for *msg* and set pointers *msg*\ **->data** and *msg*\
+ * **->data_end** to *start* and *end* bytes offsets into *msg*,
+ * respectively.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it can only parse data that the (**data**, **data_end**)
+ * pointers have already consumed. For **sendmsg**\ () hooks this
+ * is likely the first scatterlist element. But for calls relying
+ * on the **sendpage** handler (e.g. **sendfile**\ ()) this will
+ * be the range (**0**, **0**) because the data is shared with
+ * user space and by default the objective is to avoid allowing
+ * user space to modify data while (or after) eBPF verdict is
+ * being decided. This helper can be used to pull in data and to
+ * set the start and end pointer to given values. Data will be
+ * copied if necessary (i.e. if data was not linear and if start
+ * and end pointers do not point to the same chunk).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
+ * Description
+ * Bind the socket associated to *ctx* to the address pointed by
+ * *addr*, of length *addr_len*. This allows for making outgoing
+ * connection from the desired IP address, which can be useful for
+ * example when all processes inside a cgroup should use one
+ * single IP address on a host that has multiple IP configured.
+ *
+ * This helper works for IPv4 and IPv6, TCP and UDP sockets. The
+ * domain (*addr*\ **->sa_family**) must be **AF_INET** (or
+ * **AF_INET6**). Looking for a free port to bind to can be
+ * expensive, therefore binding to port is not permitted by the
+ * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
+ * must be set to zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
+ * only possible to shrink the packet as of this writing,
+ * therefore *delta* must be a negative integer.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
+ * Description
+ * Retrieve the XFRM state (IP transform framework, see also
+ * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*.
+ *
+ * The retrieved value is stored in the **struct bpf_xfrm_state**
+ * pointed by *xfrm_state* and of length *size*.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_XFRM** configuration option.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * To achieve this, the helper needs *ctx*, which is a pointer
+ * to the context on which the tracing program is executed.
+ * To store the stacktrace, the bpf program provides *buf* with
+ * a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect buildid+offset instead of ips for user stack,
+ * only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * **bpf_get_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * Return
+ * a non-negative value equal to or less than size on success, or
+ * a negative error in case of failure.
+ *
+ * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * Description
+ * This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * it provides an easy way to load *len* bytes from *offset*
+ * from the packet associated to *skb*, into the buffer pointed
+ * by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * a fifth argument *start_header* exists in order to select a
+ * base offset to start from. *start_header* can be one of:
+ *
+ * **BPF_HDR_START_MAC**
+ * Base offset to load data from is *skb*'s mac header.
+ * **BPF_HDR_START_NET**
+ * Base offset to load data from is *skb*'s network header.
+ *
+ * In general, "direct packet access" is the preferred method to
+ * access packet data, however, this helper is in particular useful
+ * in socket filters where *skb*\ **->data** does not always point
+ * to the start of the mac header and where "direct packet access"
+ * is not available.
+ *
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ * Description
+ * Do FIB lookup in kernel tables using parameters in *params*.
+ * If lookup is successful and result shows packet is to be
+ * forwarded, the neighbor tables are searched for the nexthop.
+ * If successful (ie., FIB lookup shows forwarding and nexthop
+ * is resolved), the nexthop address is returned in ipv4_dst,
+ * ipv6_dst or mpls_out based on family, smac is set to mac
+ * address of egress device, dmac is set to nexthop mac address,
+ * rt_metric is set to metric from route.
+ *
+ * *plen* argument is the size of the passed in struct.
+ * *flags* argument can be one or more BPF_FIB_LOOKUP_ flags:
+ *
+ * **BPF_FIB_LOOKUP_DIRECT** means do a direct table lookup vs
+ * full lookup using FIB rules
+ * **BPF_FIB_LOOKUP_OUTPUT** means do lookup from an egress
+ * perspective (default is ingress)
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ *
+ * Return
+ * Egress device index on success, 0 if packet needs to continue
+ * up the stack for further processing or a negative error in case
+ * of failure.
+ *
+ * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a sockhash *map* referencing sockets.
+ * The *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ * if the verdeict eBPF program returns **SK_PASS**), redirect it
+ * to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(msg_cork_bytes), \
FN(msg_pull_data), \
FN(bind), \
- FN(xdp_adjust_tail),
+ FN(xdp_adjust_tail), \
+ FN(skb_get_xfrm_state), \
+ FN(get_stack), \
+ FN(skb_load_bytes_relative), \
+ FN(fib_lookup), \
+ FN(sock_hash_update), \
+ FN(msg_redirect_hash), \
+ FN(sk_redirect_hash),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
#define BPF_F_TUNINFO_IPV6 (1ULL << 0)
-/* BPF_FUNC_get_stackid flags. */
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
#define BPF_F_SKIP_FIELD_MASK 0xffULL
#define BPF_F_USER_STACK (1ULL << 8)
+/* flags used by BPF_FUNC_get_stackid only. */
#define BPF_F_FAST_STACK_CMP (1ULL << 9)
#define BPF_F_REUSE_STACKID (1ULL << 10)
+/* flags used by BPF_FUNC_get_stack only. */
+#define BPF_F_USER_BUILD_ID (1ULL << 11)
/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
BPF_ADJ_ROOM_NET,
};
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+ BPF_HDR_START_MAC,
+ BPF_HDR_START_NET,
+};
+
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
*/
__u32 tunnel_label;
};
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+ __u32 reqid;
+ __u32 spi; /* Stored in network byte order */
+ __u16 family;
+ union {
+ __u32 remote_ipv4; /* Stored in network byte order */
+ __u32 remote_ipv6[4]; /* Stored in network byte order */
+ };
+};
+
/* Generic BPF return codes which all BPF program types may support.
* The values are binary compatible with their TC_ACT_* counter-part to
* provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 gpl_compatible:1;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
__u32 ifindex;
__u64 netns_dev;
__u64 netns_ino;
+ __u32 btf_id;
+ __u32 btf_key_id;
+ __u32 btf_value_id;
+} __attribute__((aligned(8)));
+
+struct bpf_btf_info {
+ __aligned_u64 btf;
+ __u32 btf_size;
+ __u32 id;
} __attribute__((aligned(8)));
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
__u64 args[0];
};
+/* DIRECT: Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT: Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+
+struct bpf_fib_lookup {
+ /* input */
+ __u8 family; /* network family, AF_INET, AF_INET6, AF_MPLS */
+
+ /* set if lookup is to consider L4 data - e.g., FIB rules */
+ __u8 l4_protocol;
+ __be16 sport;
+ __be16 dport;
+
+ /* total length of packet from network header - used for MTU check */
+ __u16 tot_len;
+ __u32 ifindex; /* L3 device index for lookup */
+
+ union {
+ /* inputs to lookup */
+ __u8 tos; /* AF_INET */
+ __be32 flowlabel; /* AF_INET6 */
+
+ /* output: metric of fib result */
+ __u32 rt_metric;
+ };
+
+ union {
+ __be32 mpls_in;
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ };
+
+ /* input to bpf_fib_lookup, *dst is destination address.
+ * output: bpf_fib_lookup sets to gateway address
+ */
+ union {
+ /* return for MPLS lookups */
+ __be32 mpls_out[4]; /* support up to 4 labels */
+ __be32 ipv4_dst;
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
-#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
-#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
- __u32 name;
+ __u32 name_off;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* info in "struct btf_type").
*/
struct btf_enum {
- __u32 name;
+ __u32 name_off;
__s32 val;
};
* "struct btf_type").
*/
struct btf_member {
- __u32 name;
+ __u32 name_off;
__u32 type;
__u32 offset; /* offset in bits */
};
struct coredump_proc_event {
__kernel_pid_t process_pid;
__kernel_pid_t process_tgid;
+ __kernel_pid_t parent_pid;
+ __kernel_pid_t parent_tgid;
} coredump;
struct exit_proc_event {
__kernel_pid_t process_pid;
__kernel_pid_t process_tgid;
__u32 exit_code, exit_signal;
+ __kernel_pid_t parent_pid;
+ __kernel_pid_t parent_tgid;
} exit;
} event_data;
DEVLINK_ESWITCH_ENCAP_MODE_BASIC,
};
+enum devlink_port_flavour {
+ DEVLINK_PORT_FLAVOUR_PHYSICAL, /* Any kind of a port physically
+ * facing the user.
+ */
+ DEVLINK_PORT_FLAVOUR_CPU, /* CPU port */
+ DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture
+ * interconnect port.
+ */
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, /* u64 */
DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,/* u64 */
+ DEVLINK_ATTR_PORT_FLAVOUR, /* u16 */
+ DEVLINK_ATTR_PORT_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, /* u32 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
#define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */
#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */
#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */
+#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */
/* Note header in a PT_NOTE section */
typedef struct elf32_note {
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
/*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+ *
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ * Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* Options for the sxdp_flags field */
+#define XDP_SHARED_UMEM 1
+
+struct sockaddr_xdp {
+ __u16 sxdp_family;
+ __u32 sxdp_ifindex;
+ __u32 sxdp_queue_id;
+ __u32 sxdp_shared_umem_fd;
+ __u16 sxdp_flags;
+};
+
+/* XDP socket options */
+#define XDP_RX_RING 1
+#define XDP_TX_RING 2
+#define XDP_UMEM_REG 3
+#define XDP_UMEM_FILL_RING 4
+#define XDP_UMEM_COMPLETION_RING 5
+#define XDP_STATISTICS 6
+
+struct xdp_umem_reg {
+ __u64 addr; /* Start of packet data area */
+ __u64 len; /* Length of packet data area */
+ __u32 frame_size; /* Frame size */
+ __u32 frame_headroom; /* Frame head room */
+};
+
+struct xdp_statistics {
+ __u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+ __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
+ __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+};
+
+/* Pgoff for mmaping the rings */
+#define XDP_PGOFF_RX_RING 0
+#define XDP_PGOFF_TX_RING 0x80000000
+#define XDP_UMEM_PGOFF_FILL_RING 0x100000000
+#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000
+
+struct xdp_desc {
+ __u32 idx;
+ __u32 len;
+ __u16 offset;
+ __u8 flags;
+ __u8 padding[5];
+};
+
+struct xdp_ring {
+ __u32 producer __attribute__((aligned(64)));
+ __u32 consumer __attribute__((aligned(64)));
+};
+
+/* Used for the RX and TX queues for packets */
+struct xdp_rxtx_ring {
+ struct xdp_ring ptrs;
+ struct xdp_desc desc[0] __attribute__((aligned(64)));
+};
+
+/* Used for the fill and completion queues for buffers */
+struct xdp_umem_ring {
+ struct xdp_ring ptrs;
+ __u32 desc[0] __attribute__((aligned(64)));
+};
+
+#endif /* _LINUX_IF_XDP_H */
__u8 pad[36];
};
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HTL | \
+ KVM_X86_DISABLE_EXITS_PAUSE)
+
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
/* in */
/* Marks possibility for expected RFC5961 challenge ACK */
#define IP_CT_EXP_CHALLENGE_ACK 0x40
+/* Simultaneous open initialized */
+#define IP_CT_TCP_SIMULTANEOUS_OPEN 0x80
+
struct nf_ct_tcp_flags {
__u8 flags;
__u8 mask;
#define NF_NAT_RANGE_PROTO_RANDOM (1 << 2)
#define NF_NAT_RANGE_PERSISTENT (1 << 3)
#define NF_NAT_RANGE_PROTO_RANDOM_FULLY (1 << 4)
+#define NF_NAT_RANGE_PROTO_OFFSET (1 << 5)
#define NF_NAT_RANGE_PROTO_RANDOM_ALL \
(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
#define NF_NAT_RANGE_MASK \
(NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED | \
NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT | \
- NF_NAT_RANGE_PROTO_RANDOM_FULLY)
+ NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET)
struct nf_nat_ipv4_range {
unsigned int flags;
union nf_conntrack_man_proto max_proto;
};
+struct nf_nat_range2 {
+ unsigned int flags;
+ union nf_inet_addr min_addr;
+ union nf_inet_addr max_addr;
+ union nf_conntrack_man_proto min_proto;
+ union nf_conntrack_man_proto max_proto;
+ union nf_conntrack_man_proto base_proto;
+};
+
#endif /* _NETFILTER_NF_NAT_H */
--- /dev/null
+#ifndef _NF_OSF_H
+#define _NF_OSF_H
+
+#define MAXGENRELEN 32
+
+#define NF_OSF_GENRE (1 << 0)
+#define NF_OSF_TTL (1 << 1)
+#define NF_OSF_LOG (1 << 2)
+#define NF_OSF_INVERT (1 << 3)
+
+#define NF_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */
+#define NF_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */
+#define NF_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */
+
+#define NF_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */
+
+/* Do not compare ip and fingerprint TTL at all */
+#define NF_OSF_TTL_NOCHECK 2
+
+/* Wildcard MSS (kind of).
+ * It is used to implement a state machine for the different wildcard values
+ * of the MSS and window sizes.
+ */
+struct nf_osf_wc {
+ __u32 wc;
+ __u32 val;
+};
+
+/* This struct represents IANA options
+ * http://www.iana.org/assignments/tcp-parameters
+ */
+struct nf_osf_opt {
+ __u16 kind, length;
+ struct nf_osf_wc wc;
+};
+
+struct nf_osf_info {
+ char genre[MAXGENRELEN];
+ __u32 len;
+ __u32 flags;
+ __u32 loglevel;
+ __u32 ttl;
+};
+
+struct nf_osf_user_finger {
+ struct nf_osf_wc wss;
+
+ __u8 ttl, df;
+ __u16 ss, mss;
+ __u16 opt_num;
+
+ char genre[MAXGENRELEN];
+ char version[MAXGENRELEN];
+ char subtype[MAXGENRELEN];
+
+ /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */
+ struct nf_osf_opt opt[MAX_IPOPTLEN];
+};
+
+struct nf_osf_finger {
+ struct rcu_head rcu_head;
+ struct list_head finger_entry;
+ struct nf_osf_user_finger finger;
+};
+
+struct nf_osf_nlmsg {
+ struct nf_osf_user_finger f;
+ struct iphdr ip;
+ struct tcphdr tcp;
+};
+
+/* Defines for IANA option kinds */
+enum iana_options {
+ OSFOPT_EOL = 0, /* End of options */
+ OSFOPT_NOP, /* NOP */
+ OSFOPT_MSS, /* Maximum segment size */
+ OSFOPT_WSO, /* Window scale option */
+ OSFOPT_SACKP, /* SACK permitted */
+ OSFOPT_SACK, /* SACK */
+ OSFOPT_ECHO,
+ OSFOPT_ECHOREPLY,
+ OSFOPT_TS, /* Timestamp option */
+ OSFOPT_POCP, /* Partial Order Connection Permitted */
+ OSFOPT_POSP, /* Partial Order Service Profile */
+
+ /* Others are not used in the current OSF */
+ OSFOPT_EMPTY = 255,
+};
+
+#endif /* _NF_OSF_H */
NFT_RT_NEXTHOP4,
NFT_RT_NEXTHOP6,
NFT_RT_TCPMSS,
+ __NFT_RT_MAX
};
+#define NFT_RT_MAX (__NFT_RT_MAX - 1)
/**
* enum nft_hash_types - nf_tables hash expression types
NFT_CT_DST_IP,
NFT_CT_SRC_IP6,
NFT_CT_DST_IP6,
+ __NFT_CT_MAX
};
+#define NFT_CT_MAX (__NFT_CT_MAX - 1)
/**
* enum nft_ct_attributes - nf_tables ct expression netlink attributes
* @NFTA_NG_MODULUS: maximum counter value (NLA_U32)
* @NFTA_NG_TYPE: operation type (NLA_U32)
* @NFTA_NG_OFFSET: offset to be added to the counter (NLA_U32)
+ * @NFTA_NG_SET_NAME: name of the map to lookup (NLA_STRING)
+ * @NFTA_NG_SET_ID: id of the map (NLA_U32)
*/
enum nft_ng_attributes {
NFTA_NG_UNSPEC,
NFTA_NG_MODULUS,
NFTA_NG_TYPE,
NFTA_NG_OFFSET,
+ NFTA_NG_SET_NAME,
+ NFTA_NG_SET_ID,
__NFTA_NG_MAX
};
#define NFTA_NG_MAX (__NFTA_NG_MAX - 1)
enum ctattr_stats_global {
CTA_STATS_GLOBAL_UNSPEC,
CTA_STATS_GLOBAL_ENTRIES,
+ CTA_STATS_GLOBAL_MAX_ENTRIES,
__CTA_STATS_GLOBAL_MAX,
};
#define CTA_STATS_GLOBAL_MAX (__CTA_STATS_GLOBAL_MAX - 1)
#include <linux/types.h>
#include <linux/ip.h>
#include <linux/tcp.h>
+#include <linux/netfilter/nf_osf.h>
-#define MAXGENRELEN 32
+#define XT_OSF_GENRE NF_OSF_GENRE
+#define XT_OSF_INVERT NF_OSF_INVERT
-#define XT_OSF_GENRE (1<<0)
-#define XT_OSF_TTL (1<<1)
-#define XT_OSF_LOG (1<<2)
-#define XT_OSF_INVERT (1<<3)
+#define XT_OSF_TTL NF_OSF_TTL
+#define XT_OSF_LOG NF_OSF_LOG
-#define XT_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */
-#define XT_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */
-#define XT_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */
+#define XT_OSF_LOGLEVEL_ALL NF_OSF_LOGLEVEL_ALL
+#define XT_OSF_LOGLEVEL_FIRST NF_OSF_LOGLEVEL_FIRST
+#define XT_OSF_LOGLEVEL_ALL_KNOWN NF_OSF_LOGLEVEL_ALL_KNOWN
-#define XT_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */
-#define XT_OSF_TTL_LESS 1 /* Check if ip TTL is less than fingerprint one */
-#define XT_OSF_TTL_NOCHECK 2 /* Do not compare ip and fingerprint TTL at all */
+#define XT_OSF_TTL_TRUE NF_OSF_TTL_TRUE
+#define XT_OSF_TTL_NOCHECK NF_OSF_TTL_NOCHECK
-struct xt_osf_info {
- char genre[MAXGENRELEN];
- __u32 len;
- __u32 flags;
- __u32 loglevel;
- __u32 ttl;
-};
-
-/*
- * Wildcard MSS (kind of).
- * It is used to implement a state machine for the different wildcard values
- * of the MSS and window sizes.
- */
-struct xt_osf_wc {
- __u32 wc;
- __u32 val;
-};
-
-/*
- * This struct represents IANA options
- * http://www.iana.org/assignments/tcp-parameters
- */
-struct xt_osf_opt {
- __u16 kind, length;
- struct xt_osf_wc wc;
-};
-
-struct xt_osf_user_finger {
- struct xt_osf_wc wss;
-
- __u8 ttl, df;
- __u16 ss, mss;
- __u16 opt_num;
-
- char genre[MAXGENRELEN];
- char version[MAXGENRELEN];
- char subtype[MAXGENRELEN];
+#define XT_OSF_TTL_LESS 1 /* Check if ip TTL is less than fingerprint one */
- /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */
- struct xt_osf_opt opt[MAX_IPOPTLEN];
-};
-
-struct xt_osf_nlmsg {
- struct xt_osf_user_finger f;
- struct iphdr ip;
- struct tcphdr tcp;
-};
-
-/* Defines for IANA option kinds */
-
-enum iana_options {
- OSFOPT_EOL = 0, /* End of options */
- OSFOPT_NOP, /* NOP */
- OSFOPT_MSS, /* Maximum segment size */
- OSFOPT_WSO, /* Window scale option */
- OSFOPT_SACKP, /* SACK permitted */
- OSFOPT_SACK, /* SACK */
- OSFOPT_ECHO,
- OSFOPT_ECHOREPLY,
- OSFOPT_TS, /* Timestamp option */
- OSFOPT_POCP, /* Partial Order Connection Permitted */
- OSFOPT_POSP, /* Partial Order Service Profile */
-
- /* Others are not used in the current OSF */
- OSFOPT_EMPTY = 255,
-};
-
-/*
- * Initial window size option state machine: multiple of mss, mtu or
- * plain numeric value. Can also be made as plain numeric value which
- * is not a multiple of specified value.
- */
-enum xt_osf_window_size_options {
- OSF_WSS_PLAIN = 0,
- OSF_WSS_MSS,
- OSF_WSS_MTU,
- OSF_WSS_MODULO,
- OSF_WSS_MAX,
-};
+#define xt_osf_wc nf_osf_wc
+#define xt_osf_opt nf_osf_opt
+#define xt_osf_info nf_osf_info
+#define xt_osf_user_finger nf_osf_user_finger
+#define xt_osf_finger nf_osf_finger
+#define xt_osf_nlmsg nf_osf_nlmsg
/*
* Add/remove fingerprint from the kernel.
unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace))));
};
+static __inline__ struct ebt_entry_target *
+ebt_get_target(struct ebt_entry *e)
+{
+ return (void *)e + e->target_offset;
+}
+
/* {g,s}etsockopt numbers */
#define EBT_BASE_CTL 128
#define IP6T_SRH_LAST_GT 0x0100
#define IP6T_SRH_LAST_LT 0x0200
#define IP6T_SRH_TAG 0x0400
-#define IP6T_SRH_MASK 0x07FF
+#define IP6T_SRH_PSID 0x0800
+#define IP6T_SRH_NSID 0x1000
+#define IP6T_SRH_LSID 0x2000
+#define IP6T_SRH_MASK 0x3FFF
/* Values for "mt_invflags" field in struct ip6t_srh */
#define IP6T_SRH_INV_NEXTHDR 0x0001
#define IP6T_SRH_INV_LAST_GT 0x0100
#define IP6T_SRH_INV_LAST_LT 0x0200
#define IP6T_SRH_INV_TAG 0x0400
-#define IP6T_SRH_INV_MASK 0x07FF
+#define IP6T_SRH_INV_PSID 0x0800
+#define IP6T_SRH_INV_NSID 0x1000
+#define IP6T_SRH_INV_LSID 0x2000
+#define IP6T_SRH_INV_MASK 0x3FFF
/**
* struct ip6t_srh - SRH match options
__u16 mt_invflags;
};
+/**
+ * struct ip6t_srh1 - SRH match options (revision 1)
+ * @ next_hdr: Next header field of SRH
+ * @ hdr_len: Extension header length field of SRH
+ * @ segs_left: Segments left field of SRH
+ * @ last_entry: Last entry field of SRH
+ * @ tag: Tag field of SRH
+ * @ psid_addr: Address of previous SID in SRH SID list
+ * @ nsid_addr: Address of NEXT SID in SRH SID list
+ * @ lsid_addr: Address of LAST SID in SRH SID list
+ * @ psid_msk: Mask of previous SID in SRH SID list
+ * @ nsid_msk: Mask of next SID in SRH SID list
+ * @ lsid_msk: MAsk of last SID in SRH SID list
+ * @ mt_flags: match options
+ * @ mt_invflags: Invert the sense of match options
+ */
+
+struct ip6t_srh1 {
+ __u8 next_hdr;
+ __u8 hdr_len;
+ __u8 segs_left;
+ __u8 last_entry;
+ __u16 tag;
+ struct in6_addr psid_addr;
+ struct in6_addr nsid_addr;
+ struct in6_addr lsid_addr;
+ struct in6_addr psid_msk;
+ struct in6_addr nsid_msk;
+ struct in6_addr lsid_msk;
+ __u16 mt_flags;
+ __u16 mt_invflags;
+};
+
#endif /*_IP6T_SRH_H*/
#define NL80211_ATTR_KEYS NL80211_ATTR_KEYS
#define NL80211_ATTR_FEATURE_FLAGS NL80211_ATTR_FEATURE_FLAGS
+#define NL80211_WIPHY_NAME_MAXLEN 128
+
#define NL80211_MAX_SUPP_RATES 32
#define NL80211_MAX_SUPP_HT_RATES 77
#define NL80211_MAX_SUPP_REG_RULES 64
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ * Indicates that thread was preempted in TASK_RUNNING state.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */
#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */
#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */
/* U32 filters */
/* Clear the entropy pool and associated counters. (Superuser only.) */
#define RNDCLEARPOOL _IO( 'R', 0x06 )
+/* Reseed CRNG. (Superuser only.) */
+#define RNDRESEEDCRNG _IO( 'R', 0x07 )
+
struct rand_pool_info {
int entropy_count;
int buf_size;
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2008 Oracle. All rights reserved.
*
LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */
LINUX_MIB_TCPDELIVERED, /* TCPDelivered */
LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */
+ LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */
__LINUX_MIB_MAX
};
NET_BRIDGE_NF_FILTER_PPPOE_TAGGED = 5,
};
-/* proc/sys/net/irda */
-enum {
- NET_IRDA_DISCOVERY=1,
- NET_IRDA_DEVNAME=2,
- NET_IRDA_DEBUG=3,
- NET_IRDA_FAST_POLL=4,
- NET_IRDA_DISCOVERY_SLOTS=5,
- NET_IRDA_DISCOVERY_TIMEOUT=6,
- NET_IRDA_SLOT_TIMEOUT=7,
- NET_IRDA_MAX_BAUD_RATE=8,
- NET_IRDA_MIN_TX_TURN_TIME=9,
- NET_IRDA_MAX_TX_DATA_SIZE=10,
- NET_IRDA_MAX_TX_WINDOW=11,
- NET_IRDA_MAX_NOREPLY_TIME=12,
- NET_IRDA_WARN_NOREPLY_TIME=13,
- NET_IRDA_LAP_KEEPALIVE_TIME=14,
-};
-
/* CTL_FS names: */
enum
#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
+#define TCP_ZEROCOPY_RECEIVE 35
+#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */
+
+#define TCP_CM_INQ TCP_INQ
struct tcp_repair_opt {
__u32 opt_code;
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN];
};
+/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
+
+struct tcp_zerocopy_receive {
+ __u64 address; /* in: address of mapping */
+ __u32 length; /* in/out: number of bytes to map/mapped */
+ __u32 recv_skip_hint; /* out: amount of bytes to skip */
+};
#endif /* _UAPI_LINUX_TCP_H */
*/
#define CLOCK_SGI_CYCLE 10
#define CLOCK_TAI 11
-#define CLOCK_MONOTONIC_ACTIVE 12
#define MAX_CLOCKS 16
#define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC)
* The string formatting for each name element is:
* media: media
* interface: media:interface name
- * link: Z.C.N:interface-Z.C.N:interface
- *
+ * link: node:interface-node:interface
*/
-
+#define TIPC_NODEID_LEN 16
#define TIPC_MAX_MEDIA_NAME 16
#define TIPC_MAX_IF_NAME 16
#define TIPC_MAX_BEARER_NAME 32
#define TIPC_MAX_LINK_NAME 68
-#define SIOCGETLINKNAME SIOCPROTOPRIVATE
+#define SIOCGETLINKNAME SIOCPROTOPRIVATE
+#define SIOCGETNODEID (SIOCPROTOPRIVATE + 1)
struct tipc_sioc_ln_req {
__u32 peer;
char linkname[TIPC_MAX_LINK_NAME];
};
+struct tipc_sioc_nodeid_req {
+ __u32 peer;
+ char node_id[TIPC_NODEID_LEN];
+};
/* The macros and functions below are deprecated:
*/
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
*
#define UDP_ENCAP 100 /* Set the socket to accept encapsulated packets */
#define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */
#define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */
+#define UDP_SEGMENT 103 /* Set GSO segmentation size */
/* UDP encapsulation types */
#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
#define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */
#define VIRTIO_BALLOON_S_NR 10
+#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \
+ VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \
+ VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \
+ VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \
+ VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \
+ VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \
+ VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \
+ VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \
+}
+
+#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("")
+
/*
* Memory statistics structure.
* Driver fills an array of these structures and passes to device.
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI_VMCORE_H
+#define _UAPI_VMCORE_H
+
+#include <linux/types.h>
+
+#define VMCOREDD_NOTE_NAME "LINUX"
+#define VMCOREDD_MAX_NAME_BYTES 44
+
+struct vmcoredd_header {
+ __u32 n_namesz; /* Name size */
+ __u32 n_descsz; /* Content size */
+ __u32 n_type; /* NT_VMCOREDD */
+ __u8 name[8]; /* LINUX\0\0\0 */
+ __u8 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Device dump's name */
+};
+
+#endif /* _UAPI_VMCORE_H */
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2006 Chelsio, Inc. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Hisilicon Limited.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Intel Corporation. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2017-2018, Mellanox Technologies inc. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Voltaire, Inc. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Intel Corporation. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2006 - 2011 Intel Corporation. All rights reserved.
* Copyright (c) 2005 Topspin Communications. All rights reserved.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/* QLogic qedr NIC Driver
* Copyright (c) 2015-2016 QLogic Corporation
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005-2006 Intel Corporation. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Mellanox Technologies, LTD. All rights reserved.
*
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
*
tasks running within the fair group scheduler. Groups with no limit
set are considered to be unconstrained and will run with no
restriction.
- See tip/Documentation/scheduler/sched-bwc.txt for more information.
+ See Documentation/scheduler/sched-bwc.txt for more information.
config RT_GROUP_SCHED
bool "Group scheduling for SCHED_RR/FIFO"
bool "Enable bpf() system call"
select ANON_INODES
select BPF
+ select IRQ_WORK
default n
help
Enable the bpf() system call that allows to manipulate eBPF
/*
* Enable might_sleep() and smp_processor_id() checks.
- * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+ * They cannot be enabled earlier because with CONFIG_PREEMPT=y
* kernel_thread() would trigger might_sleep() splats. With
* CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
* already, but it's stuck on the kthreadd_done completion.
static void mark_readonly(void)
{
if (rodata_enabled) {
+ /*
+ * load_module() results in W+X mappings, which are cleaned up
+ * with call_rcu_sched(). Let's make sure that queued work is
+ * flushed so that we don't hit false positives looking for
+ * insecure pages which are W+X.
+ */
+ rcu_barrier_sched();
mark_rodata_ro();
rodata_test();
} else
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+ifeq ($(CONFIG_XDP_SOCKETS),y)
+obj-$(CONFIG_BPF_SYSCALL) += xskmap.o
+endif
obj-$(CONFIG_BPF_SYSCALL) += offload.o
ifeq ($(CONFIG_STREAM_PARSER),y)
ifeq ($(CONFIG_INET),y)
}
/* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
.map_fd_get_ptr = prog_fd_array_get_ptr,
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+ .map_release_uref = bpf_fd_array_map_clear,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
+#include <linux/idr.h>
#include <linux/bpf_verifier.h>
#include <linux/btf.h>
i < btf_type_vlen(struct_type); \
i++, member++)
+static DEFINE_IDR(btf_idr);
+static DEFINE_SPINLOCK(btf_idr_lock);
+
struct btf {
union {
struct btf_header *hdr;
u32 types_size;
u32 data_size;
refcount_t refcnt;
+ u32 id;
+ struct rcu_head rcu;
};
enum verifier_phase {
__btf_verifier_log(log, "[%u] %s %s%s",
env->log_type_id,
btf_kind_str[kind],
- btf_name_by_offset(btf, t->name),
+ btf_name_by_offset(btf, t->name_off),
log_details ? " " : "");
if (log_details)
btf_verifier_log_type(env, struct_type, NULL);
__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
- btf_name_by_offset(btf, member->name),
+ btf_name_by_offset(btf, member->name_off),
member->type, member->offset);
if (fmt && *fmt) {
return 0;
}
+static int btf_alloc_id(struct btf *btf)
+{
+ int id;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_bh(&btf_idr_lock);
+ id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ btf->id = id;
+ spin_unlock_bh(&btf_idr_lock);
+ idr_preload_end();
+
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void btf_free_id(struct btf *btf)
+{
+ unsigned long flags;
+
+ /*
+ * In map-in-map, calling map_delete_elem() on outer
+ * map will call bpf_map_put on the inner map.
+ * It will then eventually call btf_free_id()
+ * on the inner map. Some of the map_delete_elem()
+ * implementation may have irq disabled, so
+ * we need to use the _irqsave() version instead
+ * of the _bh() version.
+ */
+ spin_lock_irqsave(&btf_idr_lock, flags);
+ idr_remove(&btf_idr, btf->id);
+ spin_unlock_irqrestore(&btf_idr_lock, flags);
+}
+
static void btf_free(struct btf *btf)
{
kvfree(btf->types);
kfree(btf);
}
-static void btf_get(struct btf *btf)
+static void btf_free_rcu(struct rcu_head *rcu)
{
- refcount_inc(&btf->refcnt);
+ struct btf *btf = container_of(rcu, struct btf, rcu);
+
+ btf_free(btf);
}
void btf_put(struct btf *btf)
{
- if (btf && refcount_dec_and_test(&btf->refcnt))
- btf_free(btf);
+ if (btf && refcount_dec_and_test(&btf->refcnt)) {
+ btf_free_id(btf);
+ call_rcu(&btf->rcu, btf_free_rcu);
+ }
}
static int env_resolve_init(struct btf_verifier_env *env)
btf_verifier_log_type(env, t, NULL);
for_each_member(i, t, member) {
- if (!btf_name_offset_valid(btf, member->name)) {
+ if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
"Invalid member name_offset:%u",
- member->name);
+ member->name_off);
return -EINVAL;
}
btf_verifier_log_type(env, t, NULL);
for (i = 0; i < nr_enums; i++) {
- if (!btf_name_offset_valid(btf, enums[i].name)) {
+ if (!btf_name_offset_valid(btf, enums[i].name_off)) {
btf_verifier_log(env, "\tInvalid name_offset:%u",
- enums[i].name);
+ enums[i].name_off);
return -EINVAL;
}
btf_verifier_log(env, "\t%s val=%d\n",
- btf_name_by_offset(btf, enums[i].name),
+ btf_name_by_offset(btf, enums[i].name_off),
enums[i].val);
}
for (i = 0; i < nr_enums; i++) {
if (v == enums[i].val) {
seq_printf(m, "%s",
- btf_name_by_offset(btf, enums[i].name));
+ btf_name_by_offset(btf, enums[i].name_off));
return;
}
}
return -EINVAL;
}
- if (!btf_name_offset_valid(env->btf, t->name)) {
+ if (!btf_name_offset_valid(env->btf, t->name_off)) {
btf_verifier_log(env, "[%u] Invalid name_offset:%u",
- env->log_type_id, t->name);
+ env->log_type_id, t->name_off);
return -EINVAL;
}
if (!err) {
btf_verifier_env_free(env);
- btf_get(btf);
+ refcount_set(&btf->refcnt, 1);
return btf;
}
.release = btf_release,
};
+static int __btf_new_fd(struct btf *btf)
+{
+ return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC);
+}
+
int btf_new_fd(const union bpf_attr *attr)
{
struct btf *btf;
- int fd;
+ int ret;
btf = btf_parse(u64_to_user_ptr(attr->btf),
attr->btf_size, attr->btf_log_level,
if (IS_ERR(btf))
return PTR_ERR(btf);
- fd = anon_inode_getfd("btf", &btf_fops, btf,
- O_RDONLY | O_CLOEXEC);
- if (fd < 0)
+ ret = btf_alloc_id(btf);
+ if (ret) {
+ btf_free(btf);
+ return ret;
+ }
+
+ /*
+ * The BTF ID is published to the userspace.
+ * All BTF free must go through call_rcu() from
+ * now on (i.e. free by calling btf_put()).
+ */
+
+ ret = __btf_new_fd(btf);
+ if (ret < 0)
btf_put(btf);
- return fd;
+ return ret;
}
struct btf *btf_get_by_fd(int fd)
}
btf = f.file->private_data;
- btf_get(btf);
+ refcount_inc(&btf->refcnt);
fdput(f);
return btf;
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- void __user *udata = u64_to_user_ptr(attr->info.info);
- u32 copy_len = min_t(u32, btf->data_size,
- attr->info.info_len);
+ struct bpf_btf_info __user *uinfo;
+ struct bpf_btf_info info = {};
+ u32 info_copy, btf_copy;
+ void __user *ubtf;
+ u32 uinfo_len;
+
+ uinfo = u64_to_user_ptr(attr->info.info);
+ uinfo_len = attr->info.info_len;
- if (copy_to_user(udata, btf->data, copy_len) ||
- put_user(btf->data_size, &uattr->info.info_len))
+ info_copy = min_t(u32, uinfo_len, sizeof(info));
+ if (copy_from_user(&info, uinfo, info_copy))
+ return -EFAULT;
+
+ info.id = btf->id;
+ ubtf = u64_to_user_ptr(info.btf);
+ btf_copy = min_t(u32, btf->data_size, info.btf_size);
+ if (copy_to_user(ubtf, btf->data, btf_copy))
+ return -EFAULT;
+ info.btf_size = btf->data_size;
+
+ if (copy_to_user(uinfo, &info, info_copy) ||
+ put_user(info_copy, &uattr->info.info_len))
return -EFAULT;
return 0;
}
+
+int btf_get_fd_by_id(u32 id)
+{
+ struct btf *btf;
+ int fd;
+
+ rcu_read_lock();
+ btf = idr_find(&btf_idr, id);
+ if (!btf || !refcount_inc_not_zero(&btf->refcnt))
+ btf = ERR_PTR(-ENOENT);
+ rcu_read_unlock();
+
+ if (IS_ERR(btf))
+ return PTR_ERR(btf);
+
+ fd = __btf_new_fd(btf);
+ if (fd < 0)
+ btf_put(btf);
+
+ return fd;
+}
+
+u32 btf_id(const struct btf *btf)
+{
+ return btf->id;
+}
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
+#include <linux/perf_event.h>
#include <asm/unaligned.h>
return 0;
}
-static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
{
+ const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+ s64 imm = insn->imm;
+
+ if (curr < pos && curr + imm + 1 > pos)
+ imm += delta;
+ else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+ imm -= delta;
+ if (imm < imm_min || imm > imm_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->imm = imm;
+ return 0;
+}
+
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
+{
+ const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s32 off = insn->off;
+
+ if (curr < pos && curr + off + 1 > pos)
+ off += delta;
+ else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+ off -= delta;
+ if (off < off_min || off > off_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->off = off;
+ return 0;
+}
+
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
+ const bool probe_pass)
+{
+ u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
struct bpf_insn *insn = prog->insnsi;
- u32 i, insn_cnt = prog->len;
- bool pseudo_call;
- u8 code;
- int off;
+ int ret = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
+ u8 code;
+
+ /* In the probing pass we still operate on the original,
+ * unpatched image in order to check overflows before we
+ * do any other adjustments. Therefore skip the patchlet.
+ */
+ if (probe_pass && i == pos) {
+ i += delta + 1;
+ insn++;
+ }
code = insn->code;
- if (BPF_CLASS(code) != BPF_JMP)
- continue;
- if (BPF_OP(code) == BPF_EXIT)
+ if (BPF_CLASS(code) != BPF_JMP ||
+ BPF_OP(code) == BPF_EXIT)
continue;
+ /* Adjust offset of jmps if we cross patch boundaries. */
if (BPF_OP(code) == BPF_CALL) {
- if (insn->src_reg == BPF_PSEUDO_CALL)
- pseudo_call = true;
- else
+ if (insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
+ probe_pass);
} else {
- pseudo_call = false;
+ ret = bpf_adj_delta_to_off(insn, pos, delta, i,
+ probe_pass);
}
- off = pseudo_call ? insn->imm : insn->off;
-
- /* Adjust offset of jmps if we cross boundaries. */
- if (i < pos && i + off + 1 > pos)
- off += delta;
- else if (i > pos + delta && i + off + 1 <= pos + delta)
- off -= delta;
-
- if (pseudo_call)
- insn->imm = off;
- else
- insn->off = off;
+ if (ret)
+ break;
}
+
+ return ret;
}
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len)
{
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+ const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
/* Since our patchlet doesn't expand the image, we're done. */
insn_adj_cnt = prog->len + insn_delta;
+ /* Reject anything that would potentially let the insn->off
+ * target overflow when we have excessive program expansions.
+ * We need to probe here before we do any reallocation where
+ * we afterwards may not fail anymore.
+ */
+ if (insn_adj_cnt > cnt_max &&
+ bpf_adj_branches(prog, off, insn_delta, true))
+ return NULL;
+
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
* last page could have large enough tailroom.
sizeof(*patch) * insn_rest);
memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
- bpf_adj_branches(prog_adj, off, insn_delta);
+ /* We are guaranteed to not fail at this point, otherwise
+ * the ship has sailed to reverse to the original state. An
+ * overflow cannot happen at this point.
+ */
+ BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
return prog_adj;
}
*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
break;
- case BPF_LD | BPF_ABS | BPF_W:
- case BPF_LD | BPF_ABS | BPF_H:
- case BPF_LD | BPF_ABS | BPF_B:
- *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
- *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
- break;
-
- case BPF_LD | BPF_IND | BPF_W:
- case BPF_LD | BPF_IND | BPF_H:
- case BPF_LD | BPF_IND | BPF_B:
- *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
- *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
- *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg);
- *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
- break;
-
case BPF_LD | BPF_IMM | BPF_DW:
*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
INSN_3(LDX, MEM, W), \
INSN_3(LDX, MEM, DW), \
/* Immediate based. */ \
- INSN_3(LD, IMM, DW), \
- /* Misc (old cBPF carry-over). */ \
- INSN_3(LD, ABS, B), \
- INSN_3(LD, ABS, H), \
- INSN_3(LD, ABS, W), \
- INSN_3(LD, IND, B), \
- INSN_3(LD, IND, H), \
- INSN_3(LD, IND, W)
+ INSN_3(LD, IMM, DW)
bool bpf_opcode_in_insntable(u8 code)
{
[0 ... 255] = false,
/* Now overwrite non-defaults ... */
BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+ /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
+ [BPF_LD | BPF_ABS | BPF_B] = true,
+ [BPF_LD | BPF_ABS | BPF_H] = true,
+ [BPF_LD | BPF_ABS | BPF_W] = true,
+ [BPF_LD | BPF_IND | BPF_B] = true,
+ [BPF_LD | BPF_IND | BPF_H] = true,
+ [BPF_LD | BPF_IND | BPF_W] = true,
};
#undef BPF_INSN_3_TBL
#undef BPF_INSN_2_TBL
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
u32 tail_call_cnt = 0;
- void *ptr;
- int off;
#define CONT ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })
atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
(DST + insn->off));
CONT;
- LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
- off = IMM;
-load_word:
- /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
- * appearing in the programs where ctx == skb
- * (see may_access_skb() in the verifier). All programs
- * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
- * bpf_convert_filter() saves it in BPF_R6, internal BPF
- * verifier will check that BPF_R6 == ctx.
- *
- * BPF_ABS and BPF_IND are wrappers of function calls,
- * so they scratch BPF_R1-BPF_R5 registers, preserve
- * BPF_R6-BPF_R9, and store return value into BPF_R0.
- *
- * Implicit input:
- * ctx == skb == BPF_R6 == CTX
- *
- * Explicit input:
- * SRC == any register
- * IMM == 32-bit immediate
- *
- * Output:
- * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
- */
-
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = get_unaligned_be32(ptr);
- CONT;
- }
-
- return 0;
- LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
- off = IMM;
-load_half:
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = get_unaligned_be16(ptr);
- CONT;
- }
-
- return 0;
- LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
- off = IMM;
-load_byte:
- ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
- if (likely(ptr != NULL)) {
- BPF_R0 = *(u8 *)ptr;
- CONT;
- }
-
- return 0;
- LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
- off = IMM + SRC;
- goto load_word;
- LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
- off = IMM + SRC;
- goto load_half;
- LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
- off = IMM + SRC;
- goto load_byte;
default_label:
/* If we ever reach this, we have a bug somewhere. Die hard here
return cnt;
}
+static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+ u32 *prog_ids,
+ u32 request_cnt)
+{
+ int i = 0;
+
+ for (; *prog; prog++) {
+ if (*prog == &dummy_bpf_prog.prog)
+ continue;
+ prog_ids[i] = (*prog)->aux->id;
+ if (++i == request_cnt) {
+ prog++;
+ break;
+ }
+ }
+
+ return !!(*prog);
+}
+
int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
__u32 __user *prog_ids, u32 cnt)
{
struct bpf_prog **prog;
unsigned long err = 0;
- u32 i = 0, *ids;
bool nospc;
+ u32 *ids;
/* users of this function are doing:
* cnt = bpf_prog_array_length();
return -ENOMEM;
rcu_read_lock();
prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
- continue;
- ids[i] = (*prog)->aux->id;
- if (++i == cnt) {
- prog++;
- break;
- }
- }
- nospc = !!(*prog);
+ nospc = bpf_prog_array_copy_core(prog, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
}
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt)
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt)
{
+ struct bpf_prog **prog;
u32 cnt = 0;
if (array)
cnt = bpf_prog_array_length(array);
- if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
- return -EFAULT;
+ *prog_cnt = cnt;
/* return early if user requested only program count or nothing to copy */
if (!request_cnt || !cnt)
return 0;
- return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+ /* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+ prog = rcu_dereference_check(array, 1)->progs;
+ return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ : 0;
}
static void bpf_prog_free_deferred(struct work_struct *work)
aux = container_of(work, struct bpf_prog_aux, work);
if (bpf_prog_is_dev_bound(aux))
bpf_prog_offload_destroy(aux->prog);
+#ifdef CONFIG_PERF_EVENTS
+ if (aux->prog->has_callchain_buf)
+ put_callchain_buffers();
+#endif
for (i = 0; i < aux->func_cnt; i++)
bpf_jit_free(aux->func[i]);
if (aux->func_cnt) {
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto bpf_sock_map_update_proto __weak;
+const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
{
return -ENOTSUPP;
}
+EXPORT_SYMBOL_GPL(bpf_event_output);
/* Always built-in helper functions. */
const struct bpf_func_proto bpf_tail_call_proto = {
#include <linux/bpf_trace.h>
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
-
-/* These are only used within the BPF_SYSCALL code */
-#ifdef CONFIG_BPF_SYSCALL
-EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type);
-EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu);
-#endif
ret = bpf_obj_do_pin(pname, raw, type);
if (ret != 0)
bpf_any_put(raw, type);
- if ((trace_bpf_obj_pin_prog_enabled() ||
- trace_bpf_obj_pin_map_enabled()) && !ret) {
- if (type == BPF_TYPE_PROG)
- trace_bpf_obj_pin_prog(raw, ufd, pname);
- if (type == BPF_TYPE_MAP)
- trace_bpf_obj_pin_map(raw, ufd, pname);
- }
out:
putname(pname);
return ret;
else
goto out;
- if (ret < 0) {
+ if (ret < 0)
bpf_any_put(raw, type);
- } else if (trace_bpf_obj_get_prog_enabled() ||
- trace_bpf_obj_get_map_enabled()) {
- if (type == BPF_TYPE_PROG)
- trace_bpf_obj_get_prog(raw, ret, pname);
- if (type == BPF_TYPE_MAP)
- trace_bpf_obj_get_map(raw, ret, pname);
- }
out:
putname(pname);
return ret;
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
struct bpf_prog_offload *offload;
bool ret;
- if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map))
+ if (!bpf_prog_is_dev_bound(prog->aux))
return false;
+ if (!bpf_map_is_dev_bound(map))
+ return bpf_map_offload_neutral(map);
down_read(&bpf_devs_lock);
offload = prog->aux->offload;
#include <net/tcp.h>
#include <linux/ptr_ring.h>
#include <net/inet_common.h>
+#include <linux/sched/signal.h>
#define SOCK_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
-struct bpf_stab {
- struct bpf_map map;
- struct sock **sock_map;
+struct bpf_sock_progs {
struct bpf_prog *bpf_tx_msg;
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
};
+struct bpf_stab {
+ struct bpf_map map;
+ struct sock **sock_map;
+ struct bpf_sock_progs progs;
+};
+
+struct bucket {
+ struct hlist_head head;
+ raw_spinlock_t lock;
+};
+
+struct bpf_htab {
+ struct bpf_map map;
+ struct bucket *buckets;
+ atomic_t count;
+ u32 n_buckets;
+ u32 elem_size;
+ struct bpf_sock_progs progs;
+};
+
+struct htab_elem {
+ struct rcu_head rcu;
+ struct hlist_node hash_node;
+ u32 hash;
+ struct sock *sk;
+ char key[0];
+};
+
enum smap_psock_state {
SMAP_TX_RUNNING,
};
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
+ struct htab_elem *hash_link;
+ struct bpf_htab *htab;
};
struct smap_psock {
rcu_read_unlock();
}
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+ atomic_dec(&htab->count);
+ kfree_rcu(l, rcu);
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
}
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- osk = cmpxchg(e->entry, sk, NULL);
- if (osk == sk) {
- list_del(&e->list);
- smap_release_sock(psock, sk);
+ if (e->entry) {
+ osk = cmpxchg(e->entry, sk, NULL);
+ if (osk == sk) {
+ list_del(&e->list);
+ smap_release_sock(psock, sk);
+ }
+ } else {
+ hlist_del_rcu(&e->hash_link->hash_node);
+ smap_release_sock(psock, e->hash_link->sk);
+ free_htab_elem(e->htab, e->hash_link);
}
}
write_unlock_bh(&sk->sk_callback_lock);
if (ret > 0) {
if (apply)
apply_bytes -= ret;
+
+ sg->offset += ret;
+ sg->length -= ret;
size -= ret;
offset += ret;
if (uncharge)
goto retry;
}
- sg->length = size;
- sg->offset = offset;
return ret;
}
} while (i != md->sg_end);
}
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+ struct sk_msg_buff *md, bool charge)
{
struct scatterlist *sg = md->sg_data;
int i = md->sg_start, free;
if (bytes < free) {
sg[i].length -= bytes;
sg[i].offset += bytes;
- sk_mem_uncharge(sk, bytes);
+ if (charge)
+ sk_mem_uncharge(sk, bytes);
break;
}
- sk_mem_uncharge(sk, sg[i].length);
+ if (charge)
+ sk_mem_uncharge(sk, sg[i].length);
put_page(sg_page(&sg[i]));
bytes -= sg[i].length;
sg[i].length = 0;
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ md->sg_start = i;
}
static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
{
return ((_rc == SK_PASS) ?
- (md->map ? __SK_REDIRECT : __SK_PASS) :
+ (md->sk_redir ? __SK_REDIRECT : __SK_PASS) :
__SK_DROP);
}
i = md->sg_start;
do {
- r->sg_data[i] = md->sg_data[i];
-
size = (apply && apply_bytes < md->sg_data[i].length) ?
apply_bytes : md->sg_data[i].length;
}
sk_mem_charge(sk, size);
+ r->sg_data[i] = md->sg_data[i];
r->sg_data[i].length = size;
md->sg_data[i].length -= size;
md->sg_data[i].offset += size;
struct sk_msg_buff *md,
int flags)
{
+ bool ingress = !!(md->flags & BPF_F_INGRESS);
struct smap_psock *psock;
struct scatterlist *sg;
- int i, err, free = 0;
- bool ingress = !!(md->flags & BPF_F_INGRESS);
+ int err = 0;
sg = md->sg_data;
out_rcu:
rcu_read_unlock();
out:
- i = md->sg_start;
- while (sg[i].length) {
- free += sg[i].length;
- put_page(sg_page(&sg[i]));
- sg[i].length = 0;
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
- }
- return free;
+ free_bytes_sg(NULL, send, md, false);
+ return err;
}
static inline void bpf_md_init(struct smap_psock *psock)
err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
lock_sock(sk);
+ if (unlikely(err < 0)) {
+ free_start_sg(sk, m);
+ psock->sg_size = 0;
+ if (!cork)
+ *copied -= send;
+ } else {
+ psock->sg_size -= send;
+ }
+
if (cork) {
free_start_sg(sk, m);
+ psock->sg_size = 0;
kfree(m);
m = NULL;
+ err = 0;
}
- if (unlikely(err))
- *copied -= err;
- else
- psock->sg_size -= send;
break;
case __SK_DROP:
default:
- free_bytes_sg(sk, send, m);
+ free_bytes_sg(sk, send, m, true);
apply_bytes_dec(psock, send);
*copied -= send;
psock->sg_size -= send;
return err;
}
+static int bpf_wait_data(struct sock *sk,
+ struct smap_psock *psk, int flags,
+ long timeo, int *err)
+{
+ int rc;
+
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ rc = sk_wait_event(sk, &timeo,
+ !list_empty(&psk->ingress) ||
+ !skb_queue_empty(&sk->sk_receive_queue),
+ &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+
+ return rc;
+}
+
static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
lock_sock(sk);
+bytes_ready:
while (copied != len) {
struct scatterlist *sg;
struct sk_msg_buff *md;
}
}
+ if (!copied) {
+ long timeo;
+ int data;
+ int err = 0;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+ data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+ if (data) {
+ if (!skb_queue_empty(&sk->sk_receive_queue)) {
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ return copied;
+ }
+ goto bytes_ready;
+ }
+
+ if (err)
+ copied = err;
+ }
+
release_sock(sk);
smap_release_sock(psock, sk);
return copied;
* when we orphan the skb so that we don't have the possibility
* to reference a stale map.
*/
- TCP_SKB_CB(skb)->bpf.map = NULL;
+ TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
bpf_compute_data_pointers(skb);
preempt_disable();
/* Moving return codes from UAPI namespace into internal namespace */
return rc == SK_PASS ?
- (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+ (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) :
__SK_DROP;
}
}
static void smap_init_progs(struct smap_psock *psock,
- struct bpf_stab *stab,
struct bpf_prog *verdict,
struct bpf_prog *parse)
{
kfree(psock);
}
-static struct smap_psock *smap_init_psock(struct sock *sock,
- struct bpf_stab *stab)
+static struct smap_psock *smap_init_psock(struct sock *sock, int node)
{
struct smap_psock *psock;
psock = kzalloc_node(sizeof(struct smap_psock),
GFP_ATOMIC | __GFP_NOWARN,
- stab->map.numa_node);
+ node);
if (!psock)
return ERR_PTR(-ENOMEM);
attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
- if (attr->value_size > KMALLOC_MAX_SIZE)
- return ERR_PTR(-E2BIG);
-
err = bpf_tcp_ulp_register();
if (err && err != -EEXIST)
return ERR_PTR(err);
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock, struct sock **entry)
+static void smap_list_remove(struct smap_psock *psock,
+ struct sock **entry,
+ struct htab_elem *hash_link)
{
struct smap_psock_map_entry *e, *tmp;
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry) {
+ if (e->entry == entry || e->hash_link == hash_link) {
list_del(&e->list);
break;
}
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i]);
+ smap_list_remove(psock, &stab->sock_map[i], NULL);
smap_release_sock(psock, sock);
}
write_unlock_bh(&sock->sk_callback_lock);
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k]);
+ smap_list_remove(psock, &stab->sock_map[k], NULL);
smap_release_sock(psock, sock);
out:
write_unlock_bh(&sock->sk_callback_lock);
* - sock_map must use READ_ONCE and (cmp)xchg operations
* - BPF verdict/parse programs must use READ_ONCE and xchg operations
*/
-static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
- struct bpf_map *map,
- void *key, u64 flags)
+
+static int __sock_map_ctx_update_elem(struct bpf_map *map,
+ struct bpf_sock_progs *progs,
+ struct sock *sock,
+ struct sock **map_link,
+ void *key)
{
- struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
- struct smap_psock_map_entry *e = NULL;
struct bpf_prog *verdict, *parse, *tx_msg;
- struct sock *osock, *sock;
+ struct smap_psock_map_entry *e = NULL;
struct smap_psock *psock;
- u32 i = *(u32 *)key;
bool new = false;
int err;
- if (unlikely(flags > BPF_EXIST))
- return -EINVAL;
-
- if (unlikely(i >= stab->map.max_entries))
- return -E2BIG;
-
- sock = READ_ONCE(stab->sock_map[i]);
- if (flags == BPF_EXIST && !sock)
- return -ENOENT;
- else if (flags == BPF_NOEXIST && sock)
- return -EEXIST;
-
- sock = skops->sk;
-
/* 1. If sock map has BPF programs those will be inherited by the
* sock being added. If the sock is already attached to BPF programs
* this results in an error.
*/
- verdict = READ_ONCE(stab->bpf_verdict);
- parse = READ_ONCE(stab->bpf_parse);
- tx_msg = READ_ONCE(stab->bpf_tx_msg);
+ verdict = READ_ONCE(progs->bpf_verdict);
+ parse = READ_ONCE(progs->bpf_parse);
+ tx_msg = READ_ONCE(progs->bpf_tx_msg);
if (parse && verdict) {
/* bpf prog refcnt may be zero if a concurrent attach operation
* we increment the refcnt. If this is the case abort with an
* error.
*/
- verdict = bpf_prog_inc_not_zero(stab->bpf_verdict);
+ verdict = bpf_prog_inc_not_zero(verdict);
if (IS_ERR(verdict))
return PTR_ERR(verdict);
- parse = bpf_prog_inc_not_zero(stab->bpf_parse);
+ parse = bpf_prog_inc_not_zero(parse);
if (IS_ERR(parse)) {
bpf_prog_put(verdict);
return PTR_ERR(parse);
}
if (tx_msg) {
- tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg);
+ tx_msg = bpf_prog_inc_not_zero(tx_msg);
if (IS_ERR(tx_msg)) {
- if (verdict)
- bpf_prog_put(verdict);
- if (parse)
+ if (parse && verdict) {
bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
return PTR_ERR(tx_msg);
}
}
goto out_progs;
}
} else {
- psock = smap_init_psock(sock, stab);
+ psock = smap_init_psock(sock, map->numa_node);
if (IS_ERR(psock)) {
err = PTR_ERR(psock);
goto out_progs;
new = true;
}
- e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
- if (!e) {
- err = -ENOMEM;
- goto out_progs;
+ if (map_link) {
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e) {
+ err = -ENOMEM;
+ goto out_progs;
+ }
}
- e->entry = &stab->sock_map[i];
/* 3. At this point we have a reference to a valid psock that is
* running. Attach any BPF programs needed.
err = smap_init_sock(psock, sock);
if (err)
goto out_free;
- smap_init_progs(psock, stab, verdict, parse);
+ smap_init_progs(psock, verdict, parse);
smap_start_sock(psock, sock);
}
* it with. Because we can only have a single set of programs if
* old_sock has a strp we can stop it.
*/
- list_add_tail(&e->list, &psock->maps);
+ if (map_link) {
+ e->entry = map_link;
+ list_add_tail(&e->list, &psock->maps);
+ }
+ write_unlock_bh(&sock->sk_callback_lock);
+ return err;
+out_free:
+ kfree(e);
+ smap_release_sock(psock, sock);
+out_progs:
+ if (parse && verdict) {
+ bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
+ if (tx_msg)
+ bpf_prog_put(tx_msg);
write_unlock_bh(&sock->sk_callback_lock);
+ kfree(e);
+ return err;
+}
+
+static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+ struct bpf_map *map,
+ void *key, u64 flags)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_sock_progs *progs = &stab->progs;
+ struct sock *osock, *sock;
+ u32 i = *(u32 *)key;
+ int err;
+
+ if (unlikely(flags > BPF_EXIST))
+ return -EINVAL;
+
+ if (unlikely(i >= stab->map.max_entries))
+ return -E2BIG;
+
+ sock = READ_ONCE(stab->sock_map[i]);
+ if (flags == BPF_EXIST && !sock)
+ return -ENOENT;
+ else if (flags == BPF_NOEXIST && sock)
+ return -EEXIST;
+
+ sock = skops->sk;
+ err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i],
+ key);
+ if (err)
+ goto out;
osock = xchg(&stab->sock_map[i], sock);
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i]);
+ smap_list_remove(opsock, &stab->sock_map[i], NULL);
smap_release_sock(opsock, osock);
write_unlock_bh(&osock->sk_callback_lock);
}
- return 0;
-out_free:
- smap_release_sock(psock, sock);
-out_progs:
- if (verdict)
- bpf_prog_put(verdict);
- if (parse)
- bpf_prog_put(parse);
- if (tx_msg)
- bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(e);
+out:
return err;
}
int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
{
- struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_sock_progs *progs;
struct bpf_prog *orig;
- if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP))
+ if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+ progs = &stab->progs;
+ } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ progs = &htab->progs;
+ } else {
return -EINVAL;
+ }
switch (type) {
case BPF_SK_MSG_VERDICT:
- orig = xchg(&stab->bpf_tx_msg, prog);
+ orig = xchg(&progs->bpf_tx_msg, prog);
break;
case BPF_SK_SKB_STREAM_PARSER:
- orig = xchg(&stab->bpf_parse, prog);
+ orig = xchg(&progs->bpf_parse, prog);
break;
case BPF_SK_SKB_STREAM_VERDICT:
- orig = xchg(&stab->bpf_verdict, prog);
+ orig = xchg(&progs->bpf_verdict, prog);
break;
default:
return -EOPNOTSUPP;
return err;
}
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
{
- struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_sock_progs *progs;
struct bpf_prog *orig;
- orig = xchg(&stab->bpf_parse, NULL);
+ if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+ progs = &stab->progs;
+ } else {
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ progs = &htab->progs;
+ }
+
+ orig = xchg(&progs->bpf_parse, NULL);
if (orig)
bpf_prog_put(orig);
- orig = xchg(&stab->bpf_verdict, NULL);
+ orig = xchg(&progs->bpf_verdict, NULL);
if (orig)
bpf_prog_put(orig);
- orig = xchg(&stab->bpf_tx_msg, NULL);
+ orig = xchg(&progs->bpf_tx_msg, NULL);
if (orig)
bpf_prog_put(orig);
}
+static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
+{
+ struct bpf_htab *htab;
+ int i, err;
+ u64 cost;
+
+ if (!capable(CAP_NET_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ /* check sanity of attributes */
+ if (attr->max_entries == 0 || attr->value_size != 4 ||
+ attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
+ return ERR_PTR(-EINVAL);
+
+ if (attr->key_size > MAX_BPF_STACK)
+ /* eBPF programs initialize keys on stack, so they cannot be
+ * larger than max stack size
+ */
+ return ERR_PTR(-E2BIG);
+
+ err = bpf_tcp_ulp_register();
+ if (err && err != -EEXIST)
+ return ERR_PTR(err);
+
+ htab = kzalloc(sizeof(*htab), GFP_USER);
+ if (!htab)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&htab->map, attr);
+
+ htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+ htab->elem_size = sizeof(struct htab_elem) +
+ round_up(htab->map.key_size, 8);
+ err = -EINVAL;
+ if (htab->n_buckets == 0 ||
+ htab->n_buckets > U32_MAX / sizeof(struct bucket))
+ goto free_htab;
+
+ cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+ (u64) htab->elem_size * htab->map.max_entries;
+
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_htab;
+
+ htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+ err = bpf_map_precharge_memlock(htab->map.pages);
+ if (err)
+ goto free_htab;
+
+ err = -ENOMEM;
+ htab->buckets = bpf_map_area_alloc(
+ htab->n_buckets * sizeof(struct bucket),
+ htab->map.numa_node);
+ if (!htab->buckets)
+ goto free_htab;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ INIT_HLIST_HEAD(&htab->buckets[i].head);
+ raw_spin_lock_init(&htab->buckets[i].lock);
+ }
+
+ return &htab->map;
+free_htab:
+ kfree(htab);
+ return ERR_PTR(err);
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
+static void sock_hash_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ int i;
+
+ synchronize_rcu();
+
+ /* At this point no update, lookup or delete operations can happen.
+ * However, be aware we can still get a socket state event updates,
+ * and data ready callabacks that reference the psock from sk_user_data
+ * Also psock worker threads are still in-flight. So smap_release_sock
+ * will only free the psock after cancel_sync on the worker threads
+ * and a grace period expire to ensure psock is really safe to remove.
+ */
+ rcu_read_lock();
+ for (i = 0; i < htab->n_buckets; i++) {
+ struct hlist_head *head = select_bucket(htab, i);
+ struct hlist_node *n;
+ struct htab_elem *l;
+
+ hlist_for_each_entry_safe(l, n, head, hash_node) {
+ struct sock *sock = l->sk;
+ struct smap_psock *psock;
+
+ hlist_del_rcu(&l->hash_node);
+ write_lock_bh(&sock->sk_callback_lock);
+ psock = smap_psock_sk(sock);
+ /* This check handles a racing sock event that can get
+ * the sk_callback_lock before this case but after xchg
+ * causing the refcnt to hit zero and sock user data
+ * (psock) to be null and queued for garbage collection.
+ */
+ if (likely(psock)) {
+ smap_list_remove(psock, NULL, l);
+ smap_release_sock(psock, sock);
+ }
+ write_unlock_bh(&sock->sk_callback_lock);
+ kfree(l);
+ }
+ }
+ rcu_read_unlock();
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
+}
+
+static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
+ void *key, u32 key_size, u32 hash,
+ struct sock *sk,
+ struct htab_elem *old_elem)
+{
+ struct htab_elem *l_new;
+
+ if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+ if (!old_elem) {
+ atomic_dec(&htab->count);
+ return ERR_PTR(-E2BIG);
+ }
+ }
+ l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+ htab->map.numa_node);
+ if (!l_new)
+ return ERR_PTR(-ENOMEM);
+
+ memcpy(l_new->key, key, key_size);
+ l_new->sk = sk;
+ l_new->hash = hash;
+ return l_new;
+}
+
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len)
+{
+ return jhash(key, key_len, 0);
+}
+
+static int sock_hash_get_next_key(struct bpf_map *map,
+ void *key, void *next_key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l, *next_l;
+ struct hlist_head *h;
+ u32 hash, key_size;
+ int i = 0;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+ if (!key)
+ goto find_first_elem;
+ hash = htab_map_hash(key, key_size);
+ h = select_bucket(htab, hash);
+
+ l = lookup_elem_raw(h, hash, key, key_size);
+ if (!l)
+ goto find_first_elem;
+ next_l = hlist_entry_safe(
+ rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+ struct htab_elem, hash_node);
+ if (next_l) {
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+
+ /* no more elements in this hash list, go to the next bucket */
+ i = hash & (htab->n_buckets - 1);
+ i++;
+
+find_first_elem:
+ /* iterate over buckets */
+ for (; i < htab->n_buckets; i++) {
+ h = select_bucket(htab, i);
+
+ /* pick first element in the bucket */
+ next_l = hlist_entry_safe(
+ rcu_dereference_raw(hlist_first_rcu(h)),
+ struct htab_elem, hash_node);
+ if (next_l) {
+ /* if it's not empty, just return it */
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+ }
+
+ /* iterated over all buckets and all elements */
+ return -ENOENT;
+}
+
+static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+ struct bpf_map *map,
+ void *key, u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct bpf_sock_progs *progs = &htab->progs;
+ struct htab_elem *l_new = NULL, *l_old;
+ struct smap_psock_map_entry *e = NULL;
+ struct hlist_head *head;
+ struct smap_psock *psock;
+ u32 key_size, hash;
+ struct sock *sock;
+ struct bucket *b;
+ int err;
+
+ sock = skops->sk;
+
+ if (sock->sk_type != SOCK_STREAM ||
+ sock->sk_protocol != IPPROTO_TCP)
+ return -EOPNOTSUPP;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e)
+ return -ENOMEM;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key);
+ if (err)
+ goto err;
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_bh(&b->lock);
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+ if (l_old && map_flags == BPF_NOEXIST) {
+ err = -EEXIST;
+ goto bucket_err;
+ }
+ if (!l_old && map_flags == BPF_EXIST) {
+ err = -ENOENT;
+ goto bucket_err;
+ }
+
+ l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old);
+ if (IS_ERR(l_new)) {
+ err = PTR_ERR(l_new);
+ goto bucket_err;
+ }
+
+ psock = smap_psock_sk(sock);
+ if (unlikely(!psock)) {
+ err = -EINVAL;
+ goto bucket_err;
+ }
+
+ e->hash_link = l_new;
+ e->htab = container_of(map, struct bpf_htab, map);
+ list_add_tail(&e->list, &psock->maps);
+
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
+ */
+ hlist_add_head_rcu(&l_new->hash_node, head);
+ if (l_old) {
+ psock = smap_psock_sk(l_old->sk);
+
+ hlist_del_rcu(&l_old->hash_node);
+ smap_list_remove(psock, NULL, l_old);
+ smap_release_sock(psock, l_old->sk);
+ free_htab_elem(htab, l_old);
+ }
+ raw_spin_unlock_bh(&b->lock);
+ return 0;
+bucket_err:
+ raw_spin_unlock_bh(&b->lock);
+err:
+ kfree(e);
+ psock = smap_psock_sk(sock);
+ if (psock)
+ smap_release_sock(psock, sock);
+ return err;
+}
+
+static int sock_hash_update_elem(struct bpf_map *map,
+ void *key, void *value, u64 flags)
+{
+ struct bpf_sock_ops_kern skops;
+ u32 fd = *(u32 *)value;
+ struct socket *socket;
+ int err;
+
+ socket = sockfd_lookup(fd, &err);
+ if (!socket)
+ return err;
+
+ skops.sk = socket->sk;
+ if (!skops.sk) {
+ fput(socket->file);
+ return -EINVAL;
+ }
+
+ err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ fput(socket->file);
+ return err;
+}
+
+static int sock_hash_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct bucket *b;
+ struct htab_elem *l;
+ u32 hash, key_size;
+ int ret = -ENOENT;
+
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head, hash, key, key_size);
+ if (l) {
+ struct sock *sock = l->sk;
+ struct smap_psock *psock;
+
+ hlist_del_rcu(&l->hash_node);
+ write_lock_bh(&sock->sk_callback_lock);
+ psock = smap_psock_sk(sock);
+ /* This check handles a racing sock event that can get the
+ * sk_callback_lock before this case but after xchg happens
+ * causing the refcnt to hit zero and sock user data (psock)
+ * to be null and queued for garbage collection.
+ */
+ if (likely(psock)) {
+ smap_list_remove(psock, NULL, l);
+ smap_release_sock(psock, sock);
+ }
+ write_unlock_bh(&sock->sk_callback_lock);
+ free_htab_elem(htab, l);
+ ret = 0;
+ }
+ raw_spin_unlock_bh(&b->lock);
+ return ret;
+}
+
+struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ u32 key_size, hash;
+ struct bucket *b;
+ struct sock *sk;
+
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head, hash, key, key_size);
+ sk = l ? l->sk : NULL;
+ raw_spin_unlock_bh(&b->lock);
+ return sk;
+}
+
const struct bpf_map_ops sock_map_ops = {
.map_alloc = sock_map_alloc,
.map_free = sock_map_free,
.map_get_next_key = sock_map_get_next_key,
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
- .map_release = sock_map_release,
+ .map_release_uref = sock_map_release,
+};
+
+const struct bpf_map_ops sock_hash_ops = {
+ .map_alloc = sock_hash_alloc,
+ .map_free = sock_hash_free,
+ .map_lookup_elem = sock_map_lookup,
+ .map_get_next_key = sock_hash_get_next_key,
+ .map_update_elem = sock_hash_update_elem,
+ .map_delete_elem = sock_hash_delete_elem,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
.arg3_type = ARG_PTR_TO_MAP_KEY,
.arg4_type = ARG_ANYTHING,
};
+
+BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
+ struct bpf_map *, map, void *, key, u64, flags)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
+}
+
+const struct bpf_func_proto bpf_sock_hash_update_proto = {
+ .func = bpf_sock_hash_update,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_PTR_TO_MAP_KEY,
+ .arg4_type = ARG_ANYTHING,
+};
#include <linux/perf_event.h>
#include <linux/elf.h>
#include <linux/pagemap.h>
+#include <linux/irq_work.h>
#include "percpu_freelist.h"
#define STACK_CREATE_FLAG_MASK \
struct stack_map_bucket *buckets[];
};
+/* irq_work to run up_read() for build_id lookup in nmi context */
+struct stack_map_irq_work {
+ struct irq_work irq_work;
+ struct rw_semaphore *sem;
+};
+
+static void do_up_read(struct irq_work *entry)
+{
+ struct stack_map_irq_work *work;
+
+ work = container_of(entry, struct stack_map_irq_work, irq_work);
+ up_read(work->sem);
+ work->sem = NULL;
+}
+
+static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
+
static inline bool stack_map_use_build_id(struct bpf_map *map)
{
return (map->map_flags & BPF_F_STACK_BUILD_ID);
return ret;
}
-static void stack_map_get_build_id_offset(struct bpf_map *map,
- struct stack_map_bucket *bucket,
+static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
u64 *ips, u32 trace_nr, bool user)
{
int i;
struct vm_area_struct *vma;
- struct bpf_stack_build_id *id_offs;
-
- bucket->nr = trace_nr;
- id_offs = (struct bpf_stack_build_id *)bucket->data;
+ bool in_nmi_ctx = in_nmi();
+ bool irq_work_busy = false;
+ struct stack_map_irq_work *work;
+
+ if (in_nmi_ctx) {
+ work = this_cpu_ptr(&up_read_work);
+ if (work->irq_work.flags & IRQ_WORK_BUSY)
+ /* cannot queue more up_read, fallback */
+ irq_work_busy = true;
+ }
/*
- * We cannot do up_read() in nmi context, so build_id lookup is
- * only supported for non-nmi events. If at some point, it is
- * possible to run find_vma() without taking the semaphore, we
- * would like to allow build_id lookup in nmi context.
+ * We cannot do up_read() in nmi context. To do build_id lookup
+ * in nmi context, we need to run up_read() in irq_work. We use
+ * a percpu variable to do the irq_work. If the irq_work is
+ * already used by another lookup, we fall back to report ips.
*
* Same fallback is used for kernel stack (!user) on a stackmap
* with build_id.
*/
- if (!user || !current || !current->mm || in_nmi() ||
+ if (!user || !current || !current->mm || irq_work_busy ||
down_read_trylock(¤t->mm->mmap_sem) == 0) {
/* cannot access current->mm, fall back to ips */
for (i = 0; i < trace_nr; i++) {
- vma->vm_start;
id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
}
- up_read(¤t->mm->mmap_sem);
+
+ if (!in_nmi_ctx) {
+ up_read(¤t->mm->mmap_sem);
+ } else {
+ work->sem = ¤t->mm->mmap_sem;
+ irq_work_queue(&work->irq_work);
+ }
}
BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
pcpu_freelist_pop(&smap->freelist);
if (unlikely(!new_bucket))
return -ENOMEM;
- stack_map_get_build_id_offset(map, new_bucket, ips,
- trace_nr, user);
+ new_bucket->nr = trace_nr;
+ stack_map_get_build_id_offset(
+ (struct bpf_stack_build_id *)new_bucket->data,
+ ips, trace_nr, user);
trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
if (hash_matches && bucket->nr == trace_nr &&
memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+ u64, flags)
+{
+ u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
+ bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+ u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+ bool user = flags & BPF_F_USER_STACK;
+ struct perf_callchain_entry *trace;
+ bool kernel = !user;
+ int err = -EINVAL;
+ u64 *ips;
+
+ if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+ BPF_F_USER_BUILD_ID)))
+ goto clear;
+ if (kernel && user_build_id)
+ goto clear;
+
+ elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
+ : sizeof(u64);
+ if (unlikely(size % elem_size))
+ goto clear;
+
+ num_elem = size / elem_size;
+ if (sysctl_perf_event_max_stack < num_elem)
+ init_nr = 0;
+ else
+ init_nr = sysctl_perf_event_max_stack - num_elem;
+ trace = get_perf_callchain(regs, init_nr, kernel, user,
+ sysctl_perf_event_max_stack, false, false);
+ if (unlikely(!trace))
+ goto err_fault;
+
+ trace_nr = trace->nr - init_nr;
+ if (trace_nr < skip)
+ goto err_fault;
+
+ trace_nr -= skip;
+ trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
+ copy_len = trace_nr * elem_size;
+ ips = trace->ip + skip + init_nr;
+ if (user && user_build_id)
+ stack_map_get_build_id_offset(buf, ips, trace_nr, user);
+ else
+ memcpy(buf, ips, copy_len);
+
+ if (size > copy_len)
+ memset(buf + copy_len, 0, size - copy_len);
+ return copy_len;
+
+err_fault:
+ err = -EFAULT;
+clear:
+ memset(buf, 0, size);
+ return err;
+}
+
+const struct bpf_func_proto bpf_get_stack_proto = {
+ .func = bpf_get_stack,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg4_type = ARG_ANYTHING,
+};
+
/* Called from eBPF program */
static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
{
.map_update_elem = stack_map_update_elem,
.map_delete_elem = stack_map_delete_elem,
};
+
+static int __init stack_map_init(void)
+{
+ int cpu;
+ struct stack_map_irq_work *work;
+
+ for_each_possible_cpu(cpu) {
+ work = per_cpu_ptr(&up_read_work, cpu);
+ init_irq_work(&work->irq_work, do_up_read);
+ }
+ return 0;
+}
+subsys_initcall(stack_map_init);
#include <linux/timekeeping.h>
#include <linux/ctype.h>
#include <linux/btf.h>
+#include <linux/nospec.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
const struct bpf_map_ops *ops;
+ u32 type = attr->map_type;
struct bpf_map *map;
int err;
- if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+ if (type >= ARRAY_SIZE(bpf_map_types))
return ERR_PTR(-EINVAL);
- ops = bpf_map_types[attr->map_type];
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+ ops = bpf_map_types[type];
if (!ops)
return ERR_PTR(-EINVAL);
if (IS_ERR(map))
return map;
map->ops = ops;
- map->map_type = attr->map_type;
+ map->map_type = type;
return map;
}
bpf_map_uncharge_memlock(map);
security_bpf_map_free(map);
- btf_put(map->btf);
/* implementation dependent freeing */
map->ops->map_free(map);
}
static void bpf_map_put_uref(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->usercnt)) {
- if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
- bpf_fd_array_map_clear(map);
+ if (map->ops->map_release_uref)
+ map->ops->map_release_uref(map);
}
}
if (atomic_dec_and_test(&map->refcnt)) {
/* bpf_map_free_id() must be called first */
bpf_map_free_id(map, do_idr_lock);
+ btf_put(map->btf);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
{
__bpf_map_put(map, true);
}
+EXPORT_SYMBOL_GPL(bpf_map_put);
void bpf_map_put_with_uref(struct bpf_map *map)
{
return err;
}
- trace_bpf_map_create(map, err);
return err;
free_map:
atomic_inc(&map->usercnt);
return map;
}
+EXPORT_SYMBOL_GPL(bpf_map_inc);
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
if (copy_to_user(uvalue, value, value_size) != 0)
goto free_value;
- trace_bpf_map_lookup_elem(map, ufd, key, value);
err = 0;
free_value:
__this_cpu_dec(bpf_prog_active);
preempt_enable();
out:
- if (!err)
- trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
kfree(value);
free_key:
__this_cpu_dec(bpf_prog_active);
preempt_enable();
out:
- if (!err)
- trace_bpf_map_delete_elem(map, ufd, key);
kfree(key);
err_put:
fdput(f);
if (copy_to_user(unext_key, next_key, map->key_size) != 0)
goto free_next_key;
- trace_bpf_map_next_key(map, ufd, key, next_key);
err = 0;
free_next_key:
static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
- if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+ const struct bpf_prog_ops *ops;
+
+ if (type >= ARRAY_SIZE(bpf_prog_types))
+ return -EINVAL;
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+ ops = bpf_prog_types[type];
+ if (!ops)
return -EINVAL;
if (!bpf_prog_is_dev_bound(prog->aux))
- prog->aux->ops = bpf_prog_types[type];
+ prog->aux->ops = ops;
else
prog->aux->ops = &bpf_offload_prog_ops;
prog->type = type;
if (atomic_dec_and_test(&prog->aux->refcnt)) {
int i;
- trace_bpf_prog_put_rcu(prog);
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
bool attach_drv)
{
- struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv);
-
- if (!IS_ERR(prog))
- trace_bpf_prog_get_type(prog);
- return prog;
+ return __bpf_prog_get(ufd, &type, attach_drv);
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
}
bpf_prog_kallsyms_add(prog);
- trace_bpf_prog_load(prog, err);
return err;
free_used_maps:
info.load_time = prog->aux->load_time;
info.created_by_uid = from_kuid_munged(current_user_ns(),
prog->aux->user->uid);
+ info.gpl_compatible = prog->gpl_compatible;
memcpy(info.tag, prog->tag, sizeof(prog->tag));
memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
info.map_flags = map->map_flags;
memcpy(info.name, map->name, sizeof(map->name));
+ if (map->btf) {
+ info.btf_id = btf_id(map->btf);
+ info.btf_key_id = map->btf_key_id;
+ info.btf_value_id = map->btf_value_id;
+ }
+
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_info_fill(&info, map);
if (err)
return 0;
}
+static int bpf_btf_get_info_by_fd(struct btf *btf,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+ if (err)
+ return err;
+
+ return btf_get_info_by_fd(btf, attr, uattr);
+}
+
#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
err = bpf_map_get_info_by_fd(f.file->private_data, attr,
uattr);
else if (f.file->f_op == &btf_fops)
- err = btf_get_info_by_fd(f.file->private_data, attr, uattr);
+ err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
else
err = -EINVAL;
return btf_new_fd(attr);
}
+#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
+
+static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
+{
+ if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return btf_get_fd_by_id(attr->btf_id);
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
case BPF_BTF_LOAD:
err = bpf_btf_load(&attr);
break;
+ case BPF_BTF_GET_FD_BY_ID:
+ err = bpf_btf_get_fd_by_id(&attr);
+ break;
default:
err = -EINVAL;
break;
return TNUM(a.value >> shift, a.mask >> shift);
}
+struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+{
+ /* if a.value is negative, arithmetic shifting by minimum shift
+ * will have larger negative offset compared to more shifting.
+ * If a.value is nonnegative, arithmetic shifting by minimum shift
+ * will have larger positive offset compare to more shifting.
+ */
+ return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+}
+
struct tnum tnum_add(struct tnum a, struct tnum b)
{
u64 sm, sv, sigma, chi, mu;
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
+#include <linux/perf_event.h>
#include "disasm.h"
bool pkt_access;
int regno;
int access_size;
+ s64 msize_smax_value;
+ u64 msize_umax_value;
};
static DEFINE_MUTEX(bpf_verifier_lock);
static int cmp_subprogs(const void *a, const void *b)
{
- return *(int *)a - *(int *)b;
+ return ((struct bpf_subprog_info *)a)->start -
+ ((struct bpf_subprog_info *)b)->start;
}
static int find_subprog(struct bpf_verifier_env *env, int off)
{
- u32 *p;
+ struct bpf_subprog_info *p;
- p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
- sizeof(env->subprog_starts[0]), cmp_subprogs);
+ p = bsearch(&off, env->subprog_info, env->subprog_cnt,
+ sizeof(env->subprog_info[0]), cmp_subprogs);
if (!p)
return -ENOENT;
- return p - env->subprog_starts;
+ return p - env->subprog_info;
}
verbose(env, "too many subprograms\n");
return -E2BIG;
}
- env->subprog_starts[env->subprog_cnt++] = off;
- sort(env->subprog_starts, env->subprog_cnt,
- sizeof(env->subprog_starts[0]), cmp_subprogs, NULL);
+ env->subprog_info[env->subprog_cnt++].start = off;
+ sort(env->subprog_info, env->subprog_cnt,
+ sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
return 0;
}
static int check_subprogs(struct bpf_verifier_env *env)
{
int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
+ struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
+ /* Add entry function. */
+ ret = add_subprog(env, 0);
+ if (ret < 0)
+ return ret;
+
/* determine subprog starts. The end is one before the next starts */
for (i = 0; i < insn_cnt; i++) {
if (insn[i].code != (BPF_JMP | BPF_CALL))
return ret;
}
+ /* Add a fake 'exit' subprog which could simplify subprog iteration
+ * logic. 'subprog_cnt' should not be increased.
+ */
+ subprog[env->subprog_cnt].start = insn_cnt;
+
if (env->log.level > 1)
for (i = 0; i < env->subprog_cnt; i++)
- verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);
+ verbose(env, "func#%d @%d\n", i, subprog[i].start);
/* now check that all jumps are within the same subprog */
- subprog_start = 0;
- if (env->subprog_cnt == cur_subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[cur_subprog++];
+ subprog_start = subprog[cur_subprog].start;
+ subprog_end = subprog[cur_subprog + 1].start;
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
return -EINVAL;
}
subprog_start = subprog_end;
- if (env->subprog_cnt == cur_subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[cur_subprog++];
+ cur_subprog++;
+ if (cur_subprog < env->subprog_cnt)
+ subprog_end = subprog[cur_subprog + 1].start;
}
}
return 0;
const struct bpf_func_state *func,
int off)
{
- u16 stack = env->subprog_stack_depth[func->subprogno];
+ u16 stack = env->subprog_info[func->subprogno].stack_depth;
if (stack >= -off)
return 0;
/* update known max for given subprogram */
- env->subprog_stack_depth[func->subprogno] = -off;
+ env->subprog_info[func->subprogno].stack_depth = -off;
return 0;
}
*/
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
- int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
+ int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
+ struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
- int insn_cnt = env->prog->len;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
/* round up to 32-bytes, since this is granularity
* of interpreter stack size
*/
- depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
if (depth > MAX_BPF_STACK) {
verbose(env, "combined stack size of %d calls is %d. Too large\n",
frame + 1, depth);
return -EACCES;
}
continue_func:
- if (env->subprog_cnt == subprog)
- subprog_end = insn_cnt;
- else
- subprog_end = env->subprog_starts[subprog];
+ subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
if (insn[i].code != (BPF_JMP | BPF_CALL))
continue;
continue;
/* remember insn and function to return to */
ret_insn[frame] = i + 1;
- ret_prog[frame] = subprog;
+ ret_prog[frame] = idx;
/* find the callee */
i = i + insn[i].imm + 1;
- subprog = find_subprog(env, i);
- if (subprog < 0) {
+ idx = find_subprog(env, i);
+ if (idx < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
i);
return -EFAULT;
}
- subprog++;
frame++;
if (frame >= MAX_CALL_FRAMES) {
WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
*/
if (frame == 0)
return 0;
- depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
frame--;
i = ret_insn[frame];
- subprog = ret_prog[frame];
+ idx = ret_prog[frame];
goto continue_func;
}
start);
return -EFAULT;
}
- subprog++;
- return env->subprog_stack_depth[subprog];
+ return env->subprog_info[subprog].stack_depth;
}
#endif
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
- if (!type_is_pkt_pointer(type) &&
+ if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
verbose(env, "invalid map_ptr to access map->key\n");
return -EACCES;
}
- if (type_is_pkt_pointer(type))
- err = check_packet_access(env, regno, reg->off,
- meta->map_ptr->key_size,
- false);
- else
- err = check_stack_boundary(env, regno,
- meta->map_ptr->key_size,
- false, NULL);
+ err = check_helper_mem_access(env, regno,
+ meta->map_ptr->key_size, false,
+ NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
- if (type_is_pkt_pointer(type))
- err = check_packet_access(env, regno, reg->off,
- meta->map_ptr->value_size,
- false);
- else
- err = check_stack_boundary(env, regno,
- meta->map_ptr->value_size,
- false, NULL);
+ err = check_helper_mem_access(env, regno,
+ meta->map_ptr->value_size, false,
+ NULL);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
+ /* remember the mem_size which may be used later
+ * to refine return values.
+ */
+ meta->msize_smax_value = reg->smax_value;
+ meta->msize_umax_value = reg->umax_value;
+
/* The register is SCALAR_VALUE; the access check
* happens using its boundaries.
*/
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
- /* Restrict bpf side of cpumap, open when use-cases appear */
+ /* Restrict bpf side of cpumap and xskmap, open when use-cases
+ * appear.
+ */
case BPF_MAP_TYPE_CPUMAP:
+ case BPF_MAP_TYPE_XSKMAP:
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
func_id != BPF_FUNC_msg_redirect_map)
goto error;
break;
+ case BPF_MAP_TYPE_SOCKHASH:
+ if (func_id != BPF_FUNC_sk_redirect_hash &&
+ func_id != BPF_FUNC_sock_hash_update &&
+ func_id != BPF_FUNC_map_delete_elem &&
+ func_id != BPF_FUNC_msg_redirect_hash)
+ goto error;
+ break;
default:
break;
}
case BPF_FUNC_tail_call:
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
goto error;
- if (env->subprog_cnt) {
+ if (env->subprog_cnt > 1) {
verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
return -EINVAL;
}
break;
case BPF_FUNC_redirect_map:
if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
- map->map_type != BPF_MAP_TYPE_CPUMAP)
+ map->map_type != BPF_MAP_TYPE_CPUMAP &&
+ map->map_type != BPF_MAP_TYPE_XSKMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
case BPF_FUNC_msg_redirect_map:
+ case BPF_FUNC_sock_map_update:
if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
goto error;
break;
- case BPF_FUNC_sock_map_update:
- if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
+ case BPF_FUNC_sk_redirect_hash:
+ case BPF_FUNC_msg_redirect_hash:
+ case BPF_FUNC_sock_hash_update:
+ if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
default:
/* remember the callsite, it will be used by bpf_exit */
*insn_idx /* callsite */,
state->curframe + 1 /* frameno within this callchain */,
- subprog + 1 /* subprog number within this prog */);
+ subprog /* subprog number within this prog */);
/* copy r1 - r5 args that callee can access */
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
return 0;
}
+static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
+ int func_id,
+ struct bpf_call_arg_meta *meta)
+{
+ struct bpf_reg_state *ret_reg = ®s[BPF_REG_0];
+
+ if (ret_type != RET_INTEGER ||
+ (func_id != BPF_FUNC_get_stack &&
+ func_id != BPF_FUNC_probe_read_str))
+ return;
+
+ ret_reg->smax_value = meta->msize_smax_value;
+ ret_reg->umax_value = meta->msize_umax_value;
+ __reg_deduce_bounds(ret_reg);
+ __reg_bound_offset(ret_reg);
+}
+
static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
const struct bpf_func_proto *fn = NULL;
return -EINVAL;
}
+ do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
return err;
+ if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+ const char *err_str;
+
+#ifdef CONFIG_PERF_EVENTS
+ err = get_callchain_buffers(sysctl_perf_event_max_stack);
+ err_str = "cannot get callchain buffer for func %s#%d\n";
+#else
+ err = -ENOTSUPP;
+ err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
+#endif
+ if (err) {
+ verbose(env, err_str, func_id_name(func_id), func_id);
+ return err;
+ }
+
+ env->prog->has_callchain_buf = true;
+ }
+
if (changes_data)
clear_all_pkt_pointers(env);
return 0;
dst_reg->umin_value <<= umin_val;
dst_reg->umax_value <<= umax_val;
}
- if (src_known)
- dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
- else
- dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val);
+ dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
*/
dst_reg->smin_value = S64_MIN;
dst_reg->smax_value = S64_MAX;
- if (src_known)
- dst_reg->var_off = tnum_rshift(dst_reg->var_off,
- umin_val);
- else
- dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val);
+ dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
dst_reg->umin_value >>= umax_val;
dst_reg->umax_value >>= umin_val;
/* We may learn something more from the var_off */
__update_reg_bounds(dst_reg);
break;
+ case BPF_ARSH:
+ if (umax_val >= insn_bitness) {
+ /* Shifts greater than 31 or 63 are undefined.
+ * This includes shifts by a negative number.
+ */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ break;
+ }
+
+ /* Upon reaching here, src_known is true and
+ * umax_val is equal to umin_val.
+ */
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+
+ /* blow away the dst_reg umin_value/umax_value and rely on
+ * dst_reg var_off to refine the result.
+ */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ __update_reg_bounds(dst_reg);
+ break;
default:
mark_reg_unknown(env, regs, insn->dst_reg);
break;
return -EINVAL;
}
- if (env->subprog_cnt) {
+ if (!env->ops->gen_ld_abs) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ if (env->subprog_cnt > 1) {
/* when program has LD_ABS insn JITs and interpreter assume
* that r1 == ctx == skb which is not the case for callees
* that can have arbitrary arguments. It's problematic
verbose(env, "processed %d insns (limit %d), stack depth ",
insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
- for (i = 0; i < env->subprog_cnt + 1; i++) {
- u32 depth = env->subprog_stack_depth[i];
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
verbose(env, "%d", depth);
- if (i + 1 < env->subprog_cnt + 1)
+ if (i + 1 < env->subprog_cnt)
verbose(env, "+");
}
verbose(env, "\n");
- env->prog->aux->stack_depth = env->subprog_stack_depth[0];
+ env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
- * and all maps are released in free_bpf_prog_info()
+ * and all maps are released in free_used_maps()
*/
map = bpf_map_inc(map, false);
if (IS_ERR(map)) {
if (len == 1)
return;
- for (i = 0; i < env->subprog_cnt; i++) {
- if (env->subprog_starts[i] < off)
+ /* NOTE: fake 'exit' subprog should be updated as well. */
+ for (i = 0; i <= env->subprog_cnt; i++) {
+ if (env->subprog_info[i].start < off)
continue;
- env->subprog_starts[i] += len - 1;
+ env->subprog_info[i].start += len - 1;
}
}
}
}
- if (!ops->convert_ctx_access)
+ if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux))
return 0;
insn = env->prog->insnsi + delta;
void *old_bpf_func;
int err = -ENOMEM;
- if (env->subprog_cnt == 0)
+ if (env->subprog_cnt <= 1)
return 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
/* temporarily remember subprog id inside insn instead of
* aux_data, since next loop will split up all insns into funcs
*/
- insn->off = subprog + 1;
+ insn->off = subprog;
/* remember original imm in case JIT fails and fallback
* to interpreter will be needed
*/
insn->imm = 1;
}
- func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL);
+ func = kzalloc(sizeof(prog) * env->subprog_cnt, GFP_KERNEL);
if (!func)
return -ENOMEM;
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
- if (env->subprog_cnt == i)
- subprog_end = prog->len;
- else
- subprog_end = env->subprog_starts[i];
+ subprog_end = env->subprog_info[i + 1].start;
len = subprog_end - subprog_start;
func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
* Long term would need debug info to populate names
*/
func[i]->aux->name[0] = 'F';
- func[i]->aux->stack_depth = env->subprog_stack_depth[i];
+ func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
func[i]->jit_requested = 1;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
*/
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
__bpf_call_base;
}
}
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
/* finally lock prog and jit images for all functions and
* populate kallsysm
*/
- for (i = 0; i <= env->subprog_cnt; i++) {
+ for (i = 0; i < env->subprog_cnt; i++) {
bpf_prog_lock_ro(func[i]);
bpf_prog_kallsyms_add(func[i]);
}
continue;
insn->off = env->insn_aux_data[i].call_imm;
subprog = find_subprog(env, i + insn->off + 1);
- addr = (unsigned long)func[subprog + 1]->bpf_func;
+ addr = (unsigned long)func[subprog]->bpf_func;
addr &= PAGE_MASK;
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
addr - __bpf_call_base;
prog->jited = 1;
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
- prog->aux->func_cnt = env->subprog_cnt + 1;
+ prog->aux->func_cnt = env->subprog_cnt;
return 0;
out_free:
- for (i = 0; i <= env->subprog_cnt; i++)
+ for (i = 0; i < env->subprog_cnt; i++)
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
continue;
}
+ if (BPF_CLASS(insn->code) == BPF_LD &&
+ (BPF_MODE(insn->code) == BPF_ABS ||
+ BPF_MODE(insn->code) == BPF_IND)) {
+ cnt = env->ops->gen_ld_abs(insn, insn_buf);
+ if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
if (insn->code != (BPF_JMP | BPF_CALL))
continue;
if (insn->src_reg == BPF_PSEUDO_CALL)
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
+ ret = replace_map_fd_with_map_ptr(env);
+ if (ret < 0)
+ goto skip_full_check;
+
if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env);
if (ret)
- goto err_unlock;
+ goto skip_full_check;
}
- ret = replace_map_fd_with_map_ptr(env);
- if (ret < 0)
- goto skip_full_check;
-
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
err_release_maps:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
- * them now. Otherwise free_bpf_prog_info() will release them.
+ * them now. Otherwise free_used_maps() will release them.
*/
release_maps(env);
*prog = env->prog;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* XSKMAP used for AF_XDP sockets
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/capability.h>
+#include <net/xdp_sock.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+struct xsk_map {
+ struct bpf_map map;
+ struct xdp_sock **xsk_map;
+ struct list_head __percpu *flush_list;
+};
+
+static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
+{
+ int cpu, err = -EINVAL;
+ struct xsk_map *m;
+ u64 cost;
+
+ if (!capable(CAP_NET_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ if (attr->max_entries == 0 || attr->key_size != 4 ||
+ attr->value_size != 4 ||
+ attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
+ return ERR_PTR(-EINVAL);
+
+ m = kzalloc(sizeof(*m), GFP_USER);
+ if (!m)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&m->map, attr);
+
+ cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
+ cost += sizeof(struct list_head) * num_possible_cpus();
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_m;
+
+ m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* Notice returns -EPERM on if map size is larger than memlock limit */
+ err = bpf_map_precharge_memlock(m->map.pages);
+ if (err)
+ goto free_m;
+
+ err = -ENOMEM;
+
+ m->flush_list = alloc_percpu(struct list_head);
+ if (!m->flush_list)
+ goto free_m;
+
+ for_each_possible_cpu(cpu)
+ INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
+
+ m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
+ sizeof(struct xdp_sock *),
+ m->map.numa_node);
+ if (!m->xsk_map)
+ goto free_percpu;
+ return &m->map;
+
+free_percpu:
+ free_percpu(m->flush_list);
+free_m:
+ kfree(m);
+ return ERR_PTR(err);
+}
+
+static void xsk_map_free(struct bpf_map *map)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ int i;
+
+ synchronize_net();
+
+ for (i = 0; i < map->max_entries; i++) {
+ struct xdp_sock *xs;
+
+ xs = m->xsk_map[i];
+ if (!xs)
+ continue;
+
+ sock_put((struct sock *)xs);
+ }
+
+ free_percpu(m->flush_list);
+ bpf_map_area_free(m->xsk_map);
+ kfree(m);
+}
+
+static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = next_key;
+
+ if (index >= m->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == m->map.max_entries - 1)
+ return -ENOENT;
+ *next = index + 1;
+ return 0;
+}
+
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct xdp_sock *xs;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ xs = READ_ONCE(m->xsk_map[key]);
+ return xs;
+}
+
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+ struct xdp_sock *xs)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+ int err;
+
+ err = xsk_rcv(xs, xdp);
+ if (err)
+ return err;
+
+ if (!xs->flush_node.prev)
+ list_add(&xs->flush_node, flush_list);
+
+ return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+ struct xdp_sock *xs, *tmp;
+
+ list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
+ xsk_flush(xs);
+ __list_del(xs->flush_node.prev, xs->flush_node.next);
+ xs->flush_node.prev = NULL;
+ }
+}
+
+static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ return NULL;
+}
+
+static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ u32 i = *(u32 *)key, fd = *(u32 *)value;
+ struct xdp_sock *xs, *old_xs;
+ struct socket *sock;
+ int err;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(i >= m->map.max_entries))
+ return -E2BIG;
+ if (unlikely(map_flags == BPF_NOEXIST))
+ return -EEXIST;
+
+ sock = sockfd_lookup(fd, &err);
+ if (!sock)
+ return err;
+
+ if (sock->sk->sk_family != PF_XDP) {
+ sockfd_put(sock);
+ return -EOPNOTSUPP;
+ }
+
+ xs = (struct xdp_sock *)sock->sk;
+
+ if (!xsk_is_setup_for_bpf_map(xs)) {
+ sockfd_put(sock);
+ return -EOPNOTSUPP;
+ }
+
+ sock_hold(sock->sk);
+
+ old_xs = xchg(&m->xsk_map[i], xs);
+ if (old_xs) {
+ /* Make sure we've flushed everything. */
+ synchronize_net();
+ sock_put((struct sock *)old_xs);
+ }
+
+ sockfd_put(sock);
+ return 0;
+}
+
+static int xsk_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+ struct xdp_sock *old_xs;
+ int k = *(u32 *)key;
+
+ if (k >= map->max_entries)
+ return -EINVAL;
+
+ old_xs = xchg(&m->xsk_map[k], NULL);
+ if (old_xs) {
+ /* Make sure we've flushed everything. */
+ synchronize_net();
+ sock_put((struct sock *)old_xs);
+ }
+
+ return 0;
+}
+
+const struct bpf_map_ops xsk_map_ops = {
+ .map_alloc = xsk_map_alloc,
+ .map_free = xsk_map_free,
+ .map_get_next_key = xsk_map_get_next_key,
+ .map_lookup_elem = xsk_map_lookup_elem,
+ .map_update_elem = xsk_map_update_elem,
+ .map_delete_elem = xsk_map_delete_elem,
+};
+
+
{
struct compat_timex tx32;
+ memset(txc, 0, sizeof(struct timex));
if (copy_from_user(&tx32, utp, sizeof(struct compat_timex)))
return -EFAULT;
goto exit;
}
- if (count > 1) {
- /* If the allocation failed, give up */
- if (!callchain_cpus_entries)
- err = -ENOMEM;
- /*
- * If requesting per event more than the global cap,
- * return a different error to help userspace figure
- * this out.
- *
- * And also do it here so that we have &callchain_mutex held.
- */
- if (event_max_stack > sysctl_perf_event_max_stack)
- err = -EOVERFLOW;
+ /*
+ * If requesting per event more than the global cap,
+ * return a different error to help userspace figure
+ * this out.
+ *
+ * And also do it here so that we have &callchain_mutex held.
+ */
+ if (event_max_stack > sysctl_perf_event_max_stack) {
+ err = -EOVERFLOW;
goto exit;
}
- err = alloc_callchain_buffers();
+ if (count == 1)
+ err = alloc_callchain_buffers();
exit:
if (err)
atomic_dec(&nr_callchain_events);
},
};
+ if (!sched_in && task->state == TASK_RUNNING)
+ switch_event.event_id.header.misc |=
+ PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+
perf_iterate_sb(perf_event_switch_output,
&switch_event,
NULL);
* __u16 sample size limit.
*/
if (attr->sample_stack_user >= USHRT_MAX)
- ret = -EINVAL;
+ return -EINVAL;
else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
- ret = -EINVAL;
+ return -EINVAL;
}
if (!attr->sample_max_stack)
#include <linux/slab.h>
#include <linux/circ_buf.h>
#include <linux/poll.h>
+#include <linux/nospec.h>
#include "internal.h"
return NULL;
/* AUX space */
- if (pgoff >= rb->aux_pgoff)
- return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+ if (pgoff >= rb->aux_pgoff) {
+ int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
+ return virt_to_page(rb->aux_pages[aux_pgoff]);
+ }
}
return __perf_mmap_to_page(rb, pgoff);
if (!uprobe)
return NULL;
- uprobe->inode = igrab(inode);
+ uprobe->inode = inode;
uprobe->offset = offset;
init_rwsem(&uprobe->register_rwsem);
init_rwsem(&uprobe->consumer_rwsem);
if (cur_uprobe) {
kfree(uprobe);
uprobe = cur_uprobe;
- iput(inode);
}
return uprobe;
rb_erase(&uprobe->rb_node, &uprobes_tree);
spin_unlock(&uprobes_treelock);
RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
- iput(uprobe->inode);
put_uprobe(uprobe);
}
* tuple). Creation refcount stops uprobe_unregister from freeing the
* @uprobe even before the register operation is complete. Creation
* refcount is released when the last @uc for the @uprobe
- * unregisters.
+ * unregisters. Caller of uprobe_register() is required to keep @inode
+ * (and the containing mount) referenced.
*
* Return errno if it cannot successully install probes
* else return 0 (success)
if (!s)
continue;
-#ifdef CONFIG_DEBUG_KMEMLEAK
/* Clear stale pointers from reused stack. */
memset(s->addr, 0, THREAD_SIZE);
-#endif
+
tsk->stack_vm_area = s;
return s->addr;
}
struct kprobe_blacklist_entry *ent =
list_entry(v, struct kprobe_blacklist_entry, list);
- seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr,
+ seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
(void *)ent->end_addr, (void *)ent->start_addr);
return 0;
}
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
- KTHREAD_IS_PARKED,
};
static inline void set_kthread_struct(void *kthread)
static void __kthread_parkme(struct kthread *self)
{
- __set_current_state(TASK_PARKED);
- while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
- if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
- complete(&self->parked);
+ for (;;) {
+ set_current_state(TASK_PARKED);
+ if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
+ break;
schedule();
- __set_current_state(TASK_PARKED);
}
- clear_bit(KTHREAD_IS_PARKED, &self->flags);
__set_current_state(TASK_RUNNING);
}
}
EXPORT_SYMBOL_GPL(kthread_parkme);
+void kthread_park_complete(struct task_struct *k)
+{
+ complete(&to_kthread(k)->parked);
+}
+
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
{
struct kthread *kthread = to_kthread(k);
- clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
- * We clear the IS_PARKED bit here as we don't wait
- * until the task has left the park code. So if we'd
- * park before that happens we'd see the IS_PARKED bit
- * which might be about to be cleared.
+ * Newly created kthread was parked when the CPU was offline.
+ * The binding was lost and we need to set it again.
*/
- if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
- /*
- * Newly created kthread was parked when the CPU was offline.
- * The binding was lost and we need to set it again.
- */
- if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
- __kthread_bind(k, kthread->cpu, TASK_PARKED);
- wake_up_state(k, TASK_PARKED);
- }
+ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+ __kthread_bind(k, kthread->cpu, TASK_PARKED);
+
+ clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
- if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
- set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
- if (k != current) {
- wake_up_process(k);
- wait_for_completion(&kthread->parked);
- }
+ if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+ return -EBUSY;
+
+ set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ if (k != current) {
+ wake_up_process(k);
+ wait_for_completion(&kthread->parked);
}
return 0;
struct task_struct *owner;
bool ret = true;
+ BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
+
if (need_resched())
return false;
rcu_read_lock();
owner = READ_ONCE(sem->owner);
- if (!rwsem_owner_is_writer(owner)) {
- /*
- * Don't spin if the rwsem is readers owned.
- */
- ret = !rwsem_owner_is_reader(owner);
+ if (!owner || !is_rwsem_owner_spinnable(owner)) {
+ ret = !owner; /* !owner is spinnable */
goto done;
}
{
struct task_struct *owner = READ_ONCE(sem->owner);
- if (!rwsem_owner_is_writer(owner))
- goto out;
+ if (!is_rwsem_owner_spinnable(owner))
+ return false;
rcu_read_lock();
- while (sem->owner == owner) {
+ while (owner && (READ_ONCE(sem->owner) == owner)) {
/*
* Ensure we emit the owner->on_cpu, dereference _after_
* checking sem->owner still matches owner, if that fails,
cpu_relax();
}
rcu_read_unlock();
-out:
+
/*
* If there is a new owner or the owner is not set, we continue
* spinning.
*/
- return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
+ return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
}
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
EXPORT_SYMBOL(up_read_non_owner);
#endif
-
-
/* SPDX-License-Identifier: GPL-2.0 */
/*
* The owner field of the rw_semaphore structure will be set to
- * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
* the owner field when it unlocks. A reader, on the other hand, will
* not touch the owner field when it unlocks.
*
- * In essence, the owner field now has the following 3 states:
+ * In essence, the owner field now has the following 4 states:
* 1) 0
* - lock is free or the owner hasn't set the field yet
* 2) RWSEM_READER_OWNED
* - lock is currently or previously owned by readers (lock is free
* or not set by owner yet)
- * 3) Other non-zero value
- * - a writer owns the lock
+ * 3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
+ * - lock is owned by an anonymous writer, so spinning on the lock
+ * owner should be disabled.
+ * 4) Other non-zero value
+ * - a writer owns the lock and other writers can spin on the lock owner.
*/
-#define RWSEM_READER_OWNED ((struct task_struct *)1UL)
+#define RWSEM_ANONYMOUSLY_OWNED (1UL << 0)
+#define RWSEM_READER_OWNED ((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
#ifdef CONFIG_DEBUG_RWSEMS
# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c)
WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
}
-static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+/*
+ * Return true if the a rwsem waiter can spin on the rwsem's owner
+ * and steal the lock, i.e. the lock is not anonymously owned.
+ * N.B. !owner is considered spinnable.
+ */
+static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
{
- return owner && owner != RWSEM_READER_OWNED;
+ return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
}
-static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+/*
+ * Return true if rwsem is owned by an anonymous writer or readers.
+ */
+static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
{
- return owner == RWSEM_READER_OWNED;
+ return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
}
#else
static inline void rwsem_set_owner(struct rw_semaphore *sem)
{
struct module_sect_attr *sattr =
container_of(mattr, struct module_sect_attr, mattr);
- return sprintf(buf, "0x%pK\n", (void *)sattr->address);
+ return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
+ (void *)sattr->address : NULL);
}
static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
* walking this with preempt disabled. In all the failure paths, we
* call synchronize_sched(), but we don't want to slow down the success
* path, so use actual RCU here.
+ * Note that module_alloc() on most architectures creates W+X page
+ * mappings which won't be cleaned up until do_free_init() runs. Any
+ * code such as mark_rodata_ro() which depends on those mappings to
+ * be cleaned up needs to sync with the queued work - ie
+ * rcu_barrier_sched()
*/
call_rcu_sched(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
/*
* Auto-group scheduling implementation:
*/
+#include <linux/nospec.h>
#include "sched.h"
unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
static unsigned long next = INITIAL_JIFFIES;
struct autogroup *ag;
unsigned long shares;
- int err;
+ int err, idx;
if (nice < MIN_NICE || nice > MAX_NICE)
return -EINVAL;
next = HZ / 10 + jiffies;
ag = autogroup_task_get(p);
- shares = scale_load(sched_prio_to_weight[nice + 20]);
+
+ idx = array_index_nospec(nice + 20, 40);
+ shares = scale_load(sched_prio_to_weight[idx]);
down_write(&ag->lock);
err = sched_group_set_shares(ag->tg, shares);
*/
#include "sched.h"
+#include <linux/kthread.h>
+#include <linux/nospec.h>
+
#include <asm/switch_to.h>
#include <asm/tlb.h>
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
- if (unlikely(prev_state == TASK_DEAD)) {
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
+ if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
+ switch (prev_state) {
+ case TASK_DEAD:
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
+
+ /* Task is done with its stack. */
+ put_task_stack(prev);
- /* Task is done with its stack. */
- put_task_stack(prev);
+ put_task_struct(prev);
+ break;
- put_task_struct(prev);
+ case TASK_PARKED:
+ kthread_park_complete(prev);
+ break;
+ }
}
tick_nohz_task_switch();
void __noreturn do_task_dead(void)
{
- /*
- * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
- * when the following two conditions become true.
- * - There is race condition of mmap_sem (It is acquired by
- * exit_mm()), and
- * - SMI occurs before setting TASK_RUNINNG.
- * (or hypervisor of virtual machine switches to other guest)
- * As a result, we may become TASK_RUNNING after becoming TASK_DEAD
- *
- * To avoid it, we have to wait for releasing tsk->pi_lock which
- * is held by try_to_wake_up()
- */
- raw_spin_lock_irq(¤t->pi_lock);
- raw_spin_unlock_irq(¤t->pi_lock);
-
/* Causes final put_task_struct in finish_task_switch(): */
- __set_current_state(TASK_DEAD);
+ set_special_state(TASK_DEAD);
/* Tell freezer to ignore us: */
current->flags |= PF_NOFREEZE;
struct cftype *cft, s64 nice)
{
unsigned long weight;
+ int idx;
if (nice < MIN_NICE || nice > MAX_NICE)
return -ERANGE;
- weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+ idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+ idx = array_index_nospec(idx, 40);
+ weight = sched_prio_to_weight[idx];
+
return sched_group_set_shares(css_tg(css), scale_load(weight));
}
#endif
* Do not reduce the frequency if the CPU has not been idle
* recently, as the reduction is likely to be premature then.
*/
- if (busy && next_f < sg_policy->next_freq) {
+ if (busy && next_f < sg_policy->next_freq &&
+ sg_policy->next_freq != UINT_MAX) {
next_f = sg_policy->next_freq;
/* Reset cached freq as next_freq has changed */
sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
- /*
- * For RT tasks, the schedutil governor shoots the frequency to maximum.
- * Special care must be taken to ensure that this kthread doesn't result
- * in the same behavior.
- *
- * This is (mostly) guaranteed by the work_in_progress flag. The flag is
- * updated only at the end of the sugov_work() function and before that
- * the schedutil governor rejects all other frequency scaling requests.
- *
- * There is a very rare case though, where the RT thread yields right
- * after the work_in_progress flag is cleared. The effects of that are
- * neglected for now.
- */
kthread_queue_work(&sg_policy->worker, &sg_policy->work);
}
* should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
* So, overflow is not an issue here.
*/
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
{
u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
u64 u_act;
#endif
#ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
void print_dl_stats(struct seq_file *m, int cpu)
{
print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
static void numa_migrate_preferred(struct task_struct *p)
{
unsigned long interval = HZ;
- unsigned long numa_migrate_retry;
/* This task has no NUMA fault statistics yet */
if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
/* Periodically retry migrating the task to the preferred node */
interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
- numa_migrate_retry = jiffies + interval;
-
- /*
- * Check that the new retry threshold is after the current one. If
- * the retry is in the future, it implies that wake_affine has
- * temporarily asked NUMA balancing to backoff from placement.
- */
- if (numa_migrate_retry > p->numa_migrate_retry)
- return;
-
- /* Safe to try placing the task on the preferred node */
- p->numa_migrate_retry = numa_migrate_retry;
+ p->numa_migrate_retry = jiffies + interval;
/* Success if task is already running on preferred CPU */
if (task_node(p) == p->numa_preferred_nid)
return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
}
-#ifdef CONFIG_NUMA_BALANCING
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
- unsigned long interval;
-
- if (!static_branch_likely(&sched_numa_balancing))
- return;
-
- /* If balancing has no preference then continue gathering data */
- if (p->numa_preferred_nid == -1)
- return;
-
- /*
- * If the wakeup is not affecting locality then it is neutral from
- * the perspective of NUMA balacing so continue gathering data.
- */
- if (cpu_to_node(prev_cpu) == cpu_to_node(target))
- return;
-
- /*
- * Temporarily prevent NUMA balancing trying to place waker/wakee after
- * wakee has been moved by wake_affine. This will potentially allow
- * related tasks to converge and update their data placement. The
- * 4 * numa_scan_period is to allow the two-pass filter to migrate
- * hot data to the wakers node.
- */
- interval = max(sysctl_numa_balancing_scan_delay,
- p->numa_scan_period << 2);
- p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-
- interval = max(sysctl_numa_balancing_scan_delay,
- current->numa_scan_period << 2);
- current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-}
-#else
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-}
-#endif
-
static int wake_affine(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int prev_cpu, int sync)
{
if (target == nr_cpumask_bits)
return prev_cpu;
- update_wa_numa_placement(p, prev_cpu, target);
schedstat_inc(sd->ttwu_move_affine);
schedstat_inc(p->se.statistics.nr_wakeups_affine);
return target;
if (curr_cost > this_rq->max_idle_balance_cost)
this_rq->max_idle_balance_cost = curr_cost;
+out:
/*
* While browsing the domains, we released the rq lock, a task could
* have been enqueued in the meantime. Since we're not going idle,
if (this_rq->cfs.h_nr_running && !pulled_task)
pulled_task = 1;
-out:
/* Move the next balance forward */
if (time_after(this_rq->next_balance, next_balance))
this_rq->next_balance = next_balance;
}
#ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
void print_rt_stats(struct seq_file *m, int cpu)
{
rt_rq_iter_t iter;
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
#ifdef CONFIG_NUMA_BALANCING
extern void
show_numa_stats(struct task_struct *p, struct seq_file *m);
return;
}
+ set_special_state(TASK_TRACED);
+
/*
* We're committing to trapping. TRACED should be visible before
* TRAPPING is cleared; otherwise, the tracer might fail do_wait().
* Also, transition to TRACED and updates to ->jobctl should be
* atomic with respect to siglock and should be done after the arch
* hook as siglock is released and regrabbed across it.
+ *
+ * TRACER TRACEE
+ *
+ * ptrace_attach()
+ * [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED)
+ * do_wait()
+ * set_current_state() smp_wmb();
+ * ptrace_do_wait()
+ * wait_task_stopped()
+ * task_stopped_code()
+ * [L] task_is_traced() [S] task_clear_jobctl_trapping();
*/
- set_current_state(TASK_TRACED);
+ smp_wmb();
current->last_siginfo = info;
current->exit_code = exit_code;
if (task_participate_group_stop(current))
notify = CLD_STOPPED;
- __set_current_state(TASK_STOPPED);
+ set_special_state(TASK_STOPPED);
spin_unlock_irq(¤t->sighand->siglock);
/*
#include <linux/smpboot.h>
#include <linux/atomic.h>
#include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
/*
* Structure to determine completion condition and record errors. May
}
static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
- struct cpu_stop_work *work)
+ struct cpu_stop_work *work,
+ struct wake_q_head *wakeq)
{
list_add_tail(&work->list, &stopper->works);
- wake_up_process(stopper->thread);
+ wake_q_add(wakeq, stopper->thread);
}
/* queue @work to @stopper. if offline, @work is completed immediately */
static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
{
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+ DEFINE_WAKE_Q(wakeq);
unsigned long flags;
bool enabled;
spin_lock_irqsave(&stopper->lock, flags);
enabled = stopper->enabled;
if (enabled)
- __cpu_stop_queue_work(stopper, work);
+ __cpu_stop_queue_work(stopper, work, &wakeq);
else if (work->done)
cpu_stop_signal_done(work->done);
spin_unlock_irqrestore(&stopper->lock, flags);
+ wake_up_q(&wakeq);
+
return enabled;
}
{
struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+ DEFINE_WAKE_Q(wakeq);
int err;
retry:
spin_lock_irq(&stopper1->lock);
goto unlock;
err = 0;
- __cpu_stop_queue_work(stopper1, work1);
- __cpu_stop_queue_work(stopper2, work2);
+ __cpu_stop_queue_work(stopper1, work1, &wakeq);
+ __cpu_stop_queue_work(stopper2, work2, &wakeq);
unlock:
spin_unlock(&stopper2->lock);
spin_unlock_irq(&stopper1->lock);
cpu_relax();
goto retry;
}
+
+ wake_up_q(&wakeq);
+
return err;
}
/**
{}
};
-static const struct bin_table bin_net_irda_table[] = {
- { CTL_INT, NET_IRDA_DISCOVERY, "discovery" },
- { CTL_STR, NET_IRDA_DEVNAME, "devname" },
- { CTL_INT, NET_IRDA_DEBUG, "debug" },
- { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" },
- { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" },
- { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" },
- { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" },
- { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" },
- { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" },
- { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" },
- { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" },
- { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" },
- { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" },
- { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" },
- {}
-};
-
static const struct bin_table bin_net_table[] = {
{ CTL_DIR, NET_CORE, "core", bin_net_core_table },
/* NET_ETHER not used */
{ CTL_DIR, NET_LLC, "llc", bin_net_llc_table },
{ CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table },
/* NET_DCCP "dccp" no longer used */
- { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table },
+ /* NET_IRDA "irda" no longer used */
{ CTL_INT, 2089, "nf_conntrack_max" },
{}
};
static int watchdog_running;
static atomic_t watchdog_reset_pending;
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+ spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+ spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
+
static int clocksource_watchdog_kthread(void *data);
static void __clocksource_change_rating(struct clocksource *cs, int rating);
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
+ /*
+ * If the clocksource is registered clocksource_watchdog_kthread() will
+ * re-rate and re-select.
+ */
+ if (list_empty(&cs->list)) {
+ cs->rating = 0;
+ return;
+ }
+
if (cs->mark_unstable)
cs->mark_unstable(cs);
+ /* kick clocksource_watchdog_kthread() */
if (finished_booting)
schedule_work(&watchdog_work);
}
* clocksource_mark_unstable - mark clocksource unstable via watchdog
* @cs: clocksource to be marked unstable
*
- * This function is called instead of clocksource_change_rating from
- * cpu hotplug code to avoid a deadlock between the clocksource mutex
- * and the cpu hotplug mutex. It defers the update of the clocksource
- * to the watchdog thread.
+ * This function is called by the x86 TSC code to mark clocksources as unstable;
+ * it defers demotion and re-selection to a kthread.
*/
void clocksource_mark_unstable(struct clocksource *cs)
{
spin_lock_irqsave(&watchdog_lock, flags);
if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
- if (list_empty(&cs->wd_list))
+ if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
list_add(&cs->wd_list, &watchdog_list);
__clocksource_unstable(cs);
}
static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
- unsigned long flags;
+ INIT_LIST_HEAD(&cs->wd_list);
- spin_lock_irqsave(&watchdog_lock, flags);
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a clocksource to be watched. */
list_add(&cs->wd_list, &watchdog_list);
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
- spin_unlock_irqrestore(&watchdog_lock, flags);
}
static void clocksource_select_watchdog(bool fallback)
static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
- unsigned long flags;
-
- spin_lock_irqsave(&watchdog_lock, flags);
if (cs != watchdog) {
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a watched clocksource. */
clocksource_stop_watchdog();
}
}
- spin_unlock_irqrestore(&watchdog_lock, flags);
}
static int __clocksource_watchdog_kthread(void)
{
struct clocksource *cs, *tmp;
unsigned long flags;
- LIST_HEAD(unstable);
int select = 0;
spin_lock_irqsave(&watchdog_lock, flags);
list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
list_del_init(&cs->wd_list);
- list_add(&cs->wd_list, &unstable);
+ __clocksource_change_rating(cs, 0);
select = 1;
}
if (cs->flags & CLOCK_SOURCE_RESELECT) {
clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
- /* Needs to be done outside of watchdog lock */
- list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
- list_del_init(&cs->wd_list);
- __clocksource_change_rating(cs, 0);
- }
return select;
}
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
void clocksource_mark_unstable(struct clocksource *cs) { }
+static void inline clocksource_watchdog_lock(unsigned long *flags) { }
+static void inline clocksource_watchdog_unlock(unsigned long *flags) { }
+
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
/**
*/
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{
+ unsigned long flags;
/* Initialize mult/shift and max_idle_ns */
__clocksource_update_freq_scale(cs, scale, freq);
/* Add clocksource to the clocksource list */
mutex_lock(&clocksource_mutex);
+
+ clocksource_watchdog_lock(&flags);
clocksource_enqueue(cs);
clocksource_enqueue_watchdog(cs);
+ clocksource_watchdog_unlock(&flags);
+
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
+ unsigned long flags;
+
mutex_lock(&clocksource_mutex);
+ clocksource_watchdog_lock(&flags);
__clocksource_change_rating(cs, rating);
+ clocksource_watchdog_unlock(&flags);
+
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
*/
static int clocksource_unbind(struct clocksource *cs)
{
+ unsigned long flags;
+
if (clocksource_is_watchdog(cs)) {
/* Select and try to install a replacement watchdog. */
clocksource_select_watchdog(true);
if (curr_clocksource == cs)
return -EBUSY;
}
+
+ clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
+ clocksource_watchdog_unlock(&flags);
+
return 0;
}
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
+ {
+ .index = HRTIMER_BASE_BOOTTIME,
+ .clockid = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ },
{
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
.clockid = CLOCK_REALTIME,
.get_time = &ktime_get_real,
},
+ {
+ .index = HRTIMER_BASE_BOOTTIME_SOFT,
+ .clockid = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ },
{
.index = HRTIMER_BASE_TAI_SOFT,
.clockid = CLOCK_TAI,
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
- [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC,
+ [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
- offs_real, offs_tai);
+ offs_real, offs_boot, offs_tai);
base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+ base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
return now;
u64 *newval, u64 *oldval)
{
u64 now;
+ int ret;
WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
+ ret = cpu_timer_sample_group(clock_idx, tsk, &now);
- if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) {
+ if (oldval && ret != -EINVAL) {
/*
* We are setting itimer. The *oldval is absolute and we update
* it to be relative, *newval argument is relative and we update
case CLOCK_BOOTTIME:
get_monotonic_boottime64(tp);
break;
- case CLOCK_MONOTONIC_ACTIVE:
- ktime_get_active_ts64(tp);
default:
return -EINVAL;
}
return 0;
}
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
- timekeeping_clocktai64(tp);
+ get_monotonic_boottime64(tp);
return 0;
}
-static int posix_get_monotonic_active(clockid_t which_clock,
- struct timespec64 *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
- ktime_get_active_ts64(tp);
+ timekeeping_clocktai64(tp);
return 0;
}
.timer_arm = common_hrtimer_arm,
};
-static const struct k_clock clock_monotonic_active = {
+static const struct k_clock clock_boottime = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_get_monotonic_active,
+ .clock_get = posix_get_boottime,
+ .nsleep = common_nsleep,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ .timer_rearm = common_hrtimer_rearm,
+ .timer_forward = common_hrtimer_forward,
+ .timer_remaining = common_hrtimer_remaining,
+ .timer_try_to_cancel = common_hrtimer_try_to_cancel,
+ .timer_arm = common_hrtimer_arm,
};
static const struct k_clock * const posix_clocks[] = {
[CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw,
[CLOCK_REALTIME_COARSE] = &clock_realtime_coarse,
[CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse,
- [CLOCK_BOOTTIME] = &clock_monotonic,
+ [CLOCK_BOOTTIME] = &clock_boottime,
[CLOCK_REALTIME_ALARM] = &alarm_clock,
[CLOCK_BOOTTIME_ALARM] = &alarm_clock,
[CLOCK_TAI] = &clock_tai,
- [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active,
};
static const struct k_clock *clockid_to_kclock(const clockid_t id)
now = ktime_get();
/* Find all expired events */
for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
+ /*
+ * Required for !SMP because for_each_cpu() reports
+ * unconditionally CPU0 as set on UP kernels.
+ */
+ if (!IS_ENABLED(CONFIG_SMP) &&
+ cpumask_empty(tick_broadcast_oneshot_mask))
+ break;
+
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event <= now) {
cpumask_set_cpu(cpu, tmpmask);
clockevents_shutdown(td->evtdev);
}
-static void tick_forward_next_period(void)
-{
- ktime_t delta, now = ktime_get();
- u64 n;
-
- delta = ktime_sub(now, tick_next_period);
- n = ktime_divns(delta, tick_period);
- tick_next_period += n * tick_period;
- if (tick_next_period < now)
- tick_next_period += tick_period;
- tick_sched_forward_next_period();
-}
-
/**
* tick_resume_local - Resume the local tick device
*
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
bool broadcast = tick_resume_check_broadcast();
- tick_forward_next_period();
-
clockevents_tick_resume(td->evtdev);
if (!broadcast) {
if (td->mode == TICKDEV_MODE_PERIODIC)
static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
#endif /* !(BROADCAST && ONESHOT) */
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-extern void tick_sched_forward_next_period(void);
-#else
-static inline void tick_sched_forward_next_period(void) { }
-#endif
-
/* NO_HZ_FULL internal */
#ifdef CONFIG_NO_HZ_FULL
extern void tick_nohz_init(void);
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
!tick_device_is_functional(dev)) {
- printk(KERN_INFO "Clockevents: "
- "could not switch to one-shot mode:");
+ pr_info("Clockevents: could not switch to one-shot mode:");
if (!dev) {
- printk(" no tick device\n");
+ pr_cont(" no tick device\n");
} else {
if (!tick_device_is_functional(dev))
- printk(" %s is not functional.\n", dev->name);
+ pr_cont(" %s is not functional.\n", dev->name);
else
- printk(" %s does not support one-shot mode.\n",
- dev->name);
+ pr_cont(" %s does not support one-shot mode.\n",
+ dev->name);
}
return -EINVAL;
}
*/
static ktime_t last_jiffies_update;
-/*
- * Called after resume. Make sure that jiffies are not fast forwarded due to
- * clock monotonic being forwarded by the suspended time.
- */
-void tick_sched_forward_next_period(void)
-{
- last_jiffies_update = tick_next_period;
-}
-
/*
* Must be called with interrupts disabled !
*/
return;
}
- hrtimer_set_expires(&ts->sched_timer, tick);
-
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
- hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
- else
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+ hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+ } else {
+ hrtimer_set_expires(&ts->sched_timer, tick);
tick_program_event(tick, 1);
+ }
}
static void tick_nohz_retain_tick(struct tick_sched *ts)
static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
- /* Update both bases so mono and raw stay coupled. */
- tk->tkr_mono.base += delta;
- tk->tkr_raw.base += delta;
-
- /* Accumulate time spent in suspend */
- tk->time_suspended += delta;
+ tk->offs_boot = ktime_add(tk->offs_boot, delta);
}
/*
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ * CPU 0 CPU 1
+ * timekeeping_inject_sleeptime64()
+ * __timekeeping_inject_sleeptime(tk, delta);
+ * timestamp();
+ * timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated. Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+
+ return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
+
/*
* See comment for __ktime_get_fast_ns() vs. timestamp ordering
*/
static ktime_t *offsets[TK_OFFS_MAX] = {
[TK_OFFS_REAL] = &tk_core.timekeeper.offs_real,
+ [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot,
[TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai,
};
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);
-/**
- * ktime_get_active_ts64 - Get the active non-suspended monotonic clock
- * @ts: pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime clock and
- * the wall_to_monotonic offset, subtracts the accumulated suspend time and
- * stores the result in normalized timespec64 format in the variable
- * pointed to by @ts.
- */
-void ktime_get_active_ts64(struct timespec64 *ts)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- struct timespec64 tomono, tsusp;
- u64 nsec, nssusp;
- unsigned int seq;
-
- WARN_ON(timekeeping_suspended);
-
- do {
- seq = read_seqcount_begin(&tk_core.seq);
- ts->tv_sec = tk->xtime_sec;
- nsec = timekeeping_get_ns(&tk->tkr_mono);
- tomono = tk->wall_to_monotonic;
- nssusp = tk->time_suspended;
- } while (read_seqcount_retry(&tk_core.seq, seq));
-
- ts->tv_sec += tomono.tv_sec;
- ts->tv_nsec = 0;
- timespec64_add_ns(ts, nsec + tomono.tv_nsec);
- tsusp = ns_to_timespec64(nssusp);
- *ts = timespec64_sub(*ts, tsusp);
-}
-
/**
* ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
*
return;
}
tk_xtime_add(tk, delta);
+ tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
tk_debug_account_sleep_time(delta);
}
void getboottime64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended);
+ ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
*ts = ktime_to_timespec64(t);
}
}
EXPORT_SYMBOL(get_seconds);
-struct timespec __current_kernel_time(void)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
-
- return timespec64_to_timespec(tk_xtime(tk));
-}
-
struct timespec64 current_kernel_time64(void)
{
struct timekeeper *tk = &tk_core.timekeeper;
* ktime_get_update_offsets_now - hrtimer helper
* @cwsseq: pointer to check and store the clock was set sequence number
* @offs_real: pointer to storage for monotonic -> realtime offset
+ * @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets if the
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
- ktime_t *offs_tai)
+ ktime_t *offs_boot, ktime_t *offs_tai)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
if (*cwsseq != tk->clock_was_set_seq) {
*cwsseq = tk->clock_was_set_seq;
*offs_real = tk->offs_real;
+ *offs_boot = tk->offs_boot;
*offs_tai = tk->offs_tai;
}
*/
extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
ktime_t *offs_real,
+ ktime_t *offs_boot,
ktime_t *offs_tai);
extern int timekeeping_valid_for_hres(void);
#include "trace.h"
u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
/**
* trace_call_bpf - invoke BPF program
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct cgroup *cgrp;
- if (unlikely(in_interrupt()))
- return -EINVAL;
if (unlikely(idx >= array->map.max_entries))
return -E2BIG;
return &bpf_perf_event_output_proto;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto;
+ case BPF_FUNC_get_stack:
+ return &bpf_get_stack_proto;
case BPF_FUNC_perf_event_read_value:
return &bpf_perf_event_read_value_proto;
#ifdef CONFIG_BPF_KPROBE_OVERRIDE
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size,
+ u64, flags)
+{
+ struct pt_regs *regs = *(struct pt_regs **)tp_buff;
+
+ return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+ (unsigned long) size, flags, 0);
+}
+
+static const struct bpf_func_proto bpf_get_stack_proto_tp = {
+ .func = bpf_get_stack_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg4_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
return &bpf_perf_event_output_proto_tp;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_tp;
+ case BPF_FUNC_get_stack:
+ return &bpf_get_stack_proto_tp;
default:
return tracing_func_proto(func_id, prog);
}
return &bpf_perf_event_output_proto_tp;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_tp;
+ case BPF_FUNC_get_stack:
+ return &bpf_get_stack_proto_tp;
case BPF_FUNC_perf_prog_read_value:
return &bpf_perf_prog_read_value_proto;
default:
/*
* bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
* to avoid potential recursive reuse issue when/if tracepoints are added
- * inside bpf_*_event_output and/or bpf_get_stack_id
+ * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack
*/
static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
.arg3_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
+ void *, buf, u32, size, u64, flags)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+ perf_fetch_caller_regs(regs);
+ return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+ (unsigned long) size, flags, 0);
+}
+
+static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
+ .func = bpf_get_stack_raw_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg4_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
return &bpf_perf_event_output_proto_raw_tp;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_raw_tp;
+ case BPF_FUNC_get_stack:
+ return &bpf_get_stack_proto_raw_tp;
default:
return tracing_func_proto(func_id, prog);
}
{
struct perf_event_query_bpf __user *uquery = info;
struct perf_event_query_bpf query = {};
+ u32 *ids, prog_cnt, ids_len;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EINVAL;
if (copy_from_user(&query, uquery, sizeof(query)))
return -EFAULT;
- if (query.ids_len > BPF_TRACE_MAX_PROGS)
+
+ ids_len = query.ids_len;
+ if (ids_len > BPF_TRACE_MAX_PROGS)
return -E2BIG;
+ ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
+ if (!ids)
+ return -ENOMEM;
+ /*
+ * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
+ * is required when user only wants to check for uquery->prog_cnt.
+ * There is no need to check for it since the case is handled
+ * gracefully in bpf_prog_array_copy_info.
+ */
mutex_lock(&bpf_event_mutex);
ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
- uquery->ids,
- query.ids_len,
- &uquery->prog_cnt);
+ ids,
+ ids_len,
+ &prog_cnt);
mutex_unlock(&bpf_event_mutex);
+ if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
+ copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
+ ret = -EFAULT;
+
+ kfree(ids);
return ret;
}
ftrace_create_filter_files(&global_ops, d_tracer);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- trace_create_file("set_graph_function", 0444, d_tracer,
+ trace_create_file("set_graph_function", 0644, d_tracer,
NULL,
&ftrace_graph_fops);
- trace_create_file("set_graph_notrace", 0444, d_tracer,
+ trace_create_file("set_graph_notrace", 0644, d_tracer,
NULL,
&ftrace_graph_notrace_fops);
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
- { ktime_get_mono_fast_ns, "boot", 1 },
+ { ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};
__field( unsigned int, seqnum )
),
- F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
+ F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
__entry->seqnum,
__entry->tv_sec,
__entry->tv_nsec,
static int regex_match_front(char *str, struct regex *r, int len)
{
+ if (len < r->len)
+ return 0;
+
if (strncmp(str, r->pattern, r->len) == 0)
return 1;
return 0;
return ret;
}
- if (!nr_preds) {
- prog = NULL;
- } else {
- prog = predicate_parse(filter_string, nr_parens, nr_preds,
+ if (!nr_preds)
+ return -EINVAL;
+
+ prog = predicate_parse(filter_string, nr_parens, nr_preds,
parse_pred, call, pe);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
- }
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
rcu_assign_pointer(filter->prog, prog);
return 0;
}
else if (strcmp(modifier, "usecs") == 0)
*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
else {
+ hist_err("Invalid field modifier: ", modifier);
field = ERR_PTR(-EINVAL);
goto out;
}
else {
field = trace_find_event_field(file->event_call, field_name);
if (!field || !field->size) {
+ hist_err("Couldn't find field: ", field_name);
field = ERR_PTR(-EINVAL);
goto out;
}
seq_printf(m, "%s", field_name);
} else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
seq_puts(m, "common_timestamp");
+
+ if (hist_field->flags) {
+ if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
+ !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+ const char *flags = get_hist_field_flags(hist_field);
+
+ if (flags)
+ seq_printf(m, ".%s", flags);
+ }
+ }
}
static int event_hist_trigger_print(struct seq_file *m,
if (ret == 0)
tk->tp.flags |= TP_FLAG_REGISTERED;
else {
- pr_warn("Could not insert probe at %s+%lu: %d\n",
- trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
NULL, &stack_trace_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
- trace_create_file("stack_trace_filter", 0444, d_tracer,
+ trace_create_file("stack_trace_filter", 0644, d_tracer,
&trace_ops, &stack_trace_filter_fops);
#endif
struct list_head list;
struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
+ struct path path;
struct inode *inode;
char *filename;
unsigned long offset;
for (i = 0; i < tu->tp.nr_args; i++)
traceprobe_free_probe_arg(&tu->tp.args[i]);
- iput(tu->inode);
+ path_put(&tu->path);
kfree(tu->tp.call.class->system);
kfree(tu->tp.call.name);
kfree(tu->filename);
static int create_trace_uprobe(int argc, char **argv)
{
struct trace_uprobe *tu;
- struct inode *inode;
char *arg, *event, *group, *filename;
char buf[MAX_EVENT_NAME_LEN];
struct path path;
bool is_delete, is_return;
int i, ret;
- inode = NULL;
ret = 0;
is_delete = false;
is_return = false;
}
/* Find the last occurrence, in case the path contains ':' too. */
arg = strrchr(argv[1], ':');
- if (!arg) {
- ret = -EINVAL;
- goto fail_address_parse;
- }
+ if (!arg)
+ return -EINVAL;
*arg++ = '\0';
filename = argv[1];
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret)
- goto fail_address_parse;
-
- inode = igrab(d_real_inode(path.dentry));
- path_put(&path);
+ return ret;
- if (!inode || !S_ISREG(inode->i_mode)) {
+ if (!d_is_reg(path.dentry)) {
ret = -EINVAL;
goto fail_address_parse;
}
goto fail_address_parse;
}
tu->offset = offset;
- tu->inode = inode;
+ tu->path = path;
tu->filename = kstrdup(filename, GFP_KERNEL);
if (!tu->filename) {
return ret;
fail_address_parse:
- iput(inode);
+ path_put(&path);
pr_info("Failed to parse address or file.\n");
goto err_flags;
tu->consumer.filter = filter;
+ tu->inode = d_real_inode(tu->path.dentry);
ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
if (ret)
goto err_buffer;
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+ tu->inode = NULL;
tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
uprobe_buffer_disable();
create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
{
struct trace_uprobe *tu;
- struct inode *inode;
struct path path;
int ret;
if (ret)
return ERR_PTR(ret);
- inode = igrab(d_inode(path.dentry));
- path_put(&path);
-
- if (!inode || !S_ISREG(inode->i_mode)) {
- iput(inode);
+ if (!d_is_reg(path.dentry)) {
+ path_put(&path);
return ERR_PTR(-EINVAL);
}
if (IS_ERR(tu)) {
pr_info("Failed to allocate trace_uprobe.(%d)\n",
(int)PTR_ERR(tu));
+ path_put(&path);
return ERR_CAST(tu);
}
tu->offset = offs;
- tu->inode = inode;
+ tu->path = path;
tu->filename = kstrdup(name, GFP_KERNEL);
init_trace_event_call(tu, &tu->tp.call);
lockdep_is_held(&tracepoints_mutex));
old = func_add(&tp_funcs, func, prio);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
lockdep_is_held(&tracepoints_mutex));
old = func_remove(&tp_funcs, func);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
__free_pages(page, page_order);
page = NULL;
- if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
!(gfp & GFP_DMA)) {
gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
goto again;
* errseq_sample() - Grab current errseq_t value.
* @eseq: Pointer to errseq_t to be sampled.
*
- * This function allows callers to sample an errseq_t value, marking it as
- * "seen" if required.
+ * This function allows callers to initialise their errseq_t variable.
+ * If the error has been "seen", new callers will not see an old error.
+ * If there is an unseen error in @eseq, the caller of this function will
+ * see it the next time it checks for an error.
*
+ * Context: Any context.
* Return: The current errseq value.
*/
errseq_t errseq_sample(errseq_t *eseq)
{
errseq_t old = READ_ONCE(*eseq);
- errseq_t new = old;
- /*
- * For the common case of no errors ever having been set, we can skip
- * marking the SEEN bit. Once an error has been set, the value will
- * never go back to zero.
- */
- if (old != 0) {
- new |= ERRSEQ_SEEN;
- if (old != new)
- cmpxchg(eseq, old, new);
- }
- return new;
+ /* If nobody has seen this error yet, then we can be the first. */
+ if (!(old & ERRSEQ_SEEN))
+ old = 0;
+ return old;
}
EXPORT_SYMBOL(errseq_sample);
test_find_next_bit(bitmap, BITMAP_LEN);
test_find_next_zero_bit(bitmap, BITMAP_LEN);
test_find_last_bit(bitmap, BITMAP_LEN);
- test_find_first_bit(bitmap, BITMAP_LEN);
+
+ /*
+ * test_find_first_bit() may take some time, so
+ * traverse only part of bitmap to avoid soft lockup.
+ */
+ test_find_first_bit(bitmap, BITMAP_LEN / 10);
test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
pr_err("\nStart testing find_bit() with sparse bitmap\n");
/* be noisy on error issues */
if (error == -EEXIST)
- WARN(1,
- "%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
- __func__, kobject_name(kobj));
+ pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
+ __func__, kobject_name(kobj));
else
- WARN(1, "%s failed for %s (error: %d parent: %s)\n",
- __func__, kobject_name(kobj), error,
- parent ? kobject_name(parent) : "'none'");
+ pr_err("%s failed for %s (error: %d parent: %s)\n",
+ __func__, kobject_name(kobj), error,
+ parent ? kobject_name(parent) : "'none'");
} else
kobj->state_in_sysfs = 1;
#include <linux/socket.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
+#include <linux/uidgid.h>
#include <linux/uuid.h>
#include <linux/ctype.h>
#include <net/sock.h>
return r;
}
-#ifdef CONFIG_NET
-static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data)
-{
- struct kobject *kobj = data, *ksobj;
- const struct kobj_ns_type_operations *ops;
-
- ops = kobj_ns_ops(kobj);
- if (!ops && kobj->kset) {
- ksobj = &kobj->kset->kobj;
- if (ksobj->parent != NULL)
- ops = kobj_ns_ops(ksobj->parent);
- }
-
- if (ops && ops->netlink_ns && kobj->ktype->namespace) {
- const void *sock_ns, *ns;
- ns = kobj->ktype->namespace(kobj);
- sock_ns = ops->netlink_ns(dsk);
- return sock_ns != ns;
- }
-
- return 0;
-}
-#endif
-
#ifdef CONFIG_UEVENT_HELPER
static int kobj_usermode_filter(struct kobject *kobj)
{
}
#endif
-static int kobject_uevent_net_broadcast(struct kobject *kobj,
- struct kobj_uevent_env *env,
+#ifdef CONFIG_NET
+static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env,
const char *action_string,
const char *devpath)
{
- int retval = 0;
-#if defined(CONFIG_NET)
+ struct netlink_skb_parms *parms;
+ struct sk_buff *skb = NULL;
+ char *scratch;
+ size_t len;
+
+ /* allocate message with maximum possible size */
+ len = strlen(action_string) + strlen(devpath) + 2;
+ skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ /* add header */
+ scratch = skb_put(skb, len);
+ sprintf(scratch, "%s@%s", action_string, devpath);
+
+ skb_put_data(skb, env->buf, env->buflen);
+
+ parms = &NETLINK_CB(skb);
+ parms->creds.uid = GLOBAL_ROOT_UID;
+ parms->creds.gid = GLOBAL_ROOT_GID;
+ parms->dst_group = 1;
+ parms->portid = 0;
+
+ return skb;
+}
+
+static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env,
+ const char *action_string,
+ const char *devpath)
+{
struct sk_buff *skb = NULL;
struct uevent_sock *ue_sk;
+ int retval = 0;
/* send netlink message */
list_for_each_entry(ue_sk, &uevent_sock_list, list) {
continue;
if (!skb) {
- /* allocate message with the maximum possible size */
- size_t len = strlen(action_string) + strlen(devpath) + 2;
- char *scratch;
-
retval = -ENOMEM;
- skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+ skb = alloc_uevent_skb(env, action_string, devpath);
if (!skb)
continue;
-
- /* add header */
- scratch = skb_put(skb, len);
- sprintf(scratch, "%s@%s", action_string, devpath);
-
- skb_put_data(skb, env->buf, env->buflen);
-
- NETLINK_CB(skb).dst_group = 1;
}
- retval = netlink_broadcast_filtered(uevent_sock, skb_get(skb),
- 0, 1, GFP_KERNEL,
- kobj_bcast_filter,
- kobj);
+ retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1,
+ GFP_KERNEL);
/* ENOBUFS should be handled in userspace */
if (retval == -ENOBUFS || retval == -ESRCH)
retval = 0;
}
consume_skb(skb);
-#endif
+
return retval;
}
+static int uevent_net_broadcast_tagged(struct sock *usk,
+ struct kobj_uevent_env *env,
+ const char *action_string,
+ const char *devpath)
+{
+ struct user_namespace *owning_user_ns = sock_net(usk)->user_ns;
+ struct sk_buff *skb = NULL;
+ int ret = 0;
+
+ skb = alloc_uevent_skb(env, action_string, devpath);
+ if (!skb)
+ return -ENOMEM;
+
+ /* fix credentials */
+ if (owning_user_ns != &init_user_ns) {
+ struct netlink_skb_parms *parms = &NETLINK_CB(skb);
+ kuid_t root_uid;
+ kgid_t root_gid;
+
+ /* fix uid */
+ root_uid = make_kuid(owning_user_ns, 0);
+ if (uid_valid(root_uid))
+ parms->creds.uid = root_uid;
+
+ /* fix gid */
+ root_gid = make_kgid(owning_user_ns, 0);
+ if (gid_valid(root_gid))
+ parms->creds.gid = root_gid;
+ }
+
+ ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL);
+ /* ENOBUFS should be handled in userspace */
+ if (ret == -ENOBUFS || ret == -ESRCH)
+ ret = 0;
+
+ return ret;
+}
+#endif
+
+static int kobject_uevent_net_broadcast(struct kobject *kobj,
+ struct kobj_uevent_env *env,
+ const char *action_string,
+ const char *devpath)
+{
+ int ret = 0;
+
+#ifdef CONFIG_NET
+ const struct kobj_ns_type_operations *ops;
+ const struct net *net = NULL;
+
+ ops = kobj_ns_ops(kobj);
+ if (!ops && kobj->kset) {
+ struct kobject *ksobj = &kobj->kset->kobj;
+ if (ksobj->parent != NULL)
+ ops = kobj_ns_ops(ksobj->parent);
+ }
+
+ /* kobjects currently only carry network namespace tags and they
+ * are the only tag relevant here since we want to decide which
+ * network namespaces to broadcast the uevent into.
+ */
+ if (ops && ops->netlink_ns && kobj->ktype->namespace)
+ if (ops->type == KOBJ_NS_TYPE_NET)
+ net = kobj->ktype->namespace(kobj);
+
+ if (!net)
+ ret = uevent_net_broadcast_untagged(env, action_string,
+ devpath);
+ else
+ ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env,
+ action_string, devpath);
+#endif
+
+ return ret;
+}
+
static void zap_modalias_env(struct kobj_uevent_env *env)
{
static const char modalias_prefix[] = "MODALIAS=";
net->uevent_sock = ue_sk;
- mutex_lock(&uevent_sock_mutex);
- list_add_tail(&ue_sk->list, &uevent_sock_list);
- mutex_unlock(&uevent_sock_mutex);
+ /* Restrict uevents to initial user namespace. */
+ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+ mutex_lock(&uevent_sock_mutex);
+ list_add_tail(&ue_sk->list, &uevent_sock_list);
+ mutex_unlock(&uevent_sock_mutex);
+ }
+
return 0;
}
{
struct uevent_sock *ue_sk = net->uevent_sock;
- mutex_lock(&uevent_sock_mutex);
- list_del(&ue_sk->list);
- mutex_unlock(&uevent_sock_mutex);
+ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+ mutex_lock(&uevent_sock_mutex);
+ list_del(&ue_sk->list);
+ mutex_unlock(&uevent_sock_mutex);
+ }
netlink_kernel_release(ue_sk->sk);
kfree(ue_sk);
static void __rcu **skip_siblings(struct radix_tree_node **nodep,
void __rcu **slot, struct radix_tree_iter *iter)
{
- void *sib = node_to_entry(slot - 1);
-
while (iter->index < iter->next_index) {
*nodep = rcu_dereference_raw(*slot);
- if (*nodep && *nodep != sib)
+ if (*nodep && !is_sibling_entry(iter->node, *nodep))
return slot;
slot++;
iter->index = __radix_tree_iter_add(iter, 1);
struct radix_tree_iter *iter, unsigned flags)
{
unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
- struct radix_tree_node *node = rcu_dereference_raw(*slot);
+ struct radix_tree_node *node;
slot = skip_siblings(&node, slot, iter);
* For a completely stable walk you should construct your own data
* structure outside the hash table.
*
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
*
* You must call rhashtable_walk_exit after this function returns.
*/
__acquires(RCU)
{
struct rhashtable *ht = iter->ht;
+ bool rhlist = ht->rhlist;
rcu_read_lock();
list_del(&iter->walker.list);
spin_unlock(&ht->lock);
- if (!iter->walker.tbl && !iter->end_of_table) {
+ if (iter->end_of_table)
+ return 0;
+ if (!iter->walker.tbl) {
iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht);
+ iter->slot = 0;
+ iter->skip = 0;
return -EAGAIN;
}
+ if (iter->p && !rhlist) {
+ /*
+ * We need to validate that 'p' is still in the table, and
+ * if so, update 'skip'
+ */
+ struct rhash_head *p;
+ int skip = 0;
+ rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+ skip++;
+ if (p == iter->p) {
+ iter->skip = skip;
+ goto found;
+ }
+ }
+ iter->p = NULL;
+ } else if (iter->p && rhlist) {
+ /* Need to validate that 'list' is still in the table, and
+ * if so, update 'skip' and 'p'.
+ */
+ struct rhash_head *p;
+ struct rhlist_head *list;
+ int skip = 0;
+ rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+ for (list = container_of(p, struct rhlist_head, rhead);
+ list;
+ list = rcu_dereference(list->next)) {
+ skip++;
+ if (list == iter->list) {
+ iter->p = p;
+ skip = skip;
+ goto found;
+ }
+ }
+ }
+ iter->p = NULL;
+ }
+found:
return 0;
}
EXPORT_SYMBOL_GPL(rhashtable_walk_start_check);
iter->walker.tbl = NULL;
spin_unlock(&ht->lock);
- iter->p = NULL;
-
out:
rcu_read_unlock();
}
phys_addr = swiotlb_tbl_map_single(dev,
__phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, 0);
+ 0, size, DMA_FROM_DEVICE, attrs);
if (phys_addr == SWIOTLB_MAP_ERROR)
goto out_warn;
swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
DMA_ATTR_SKIP_CPU_SYNC);
out_warn:
- if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
dev_warn(dev,
"swiotlb: coherent allocation failed, size=%zu\n",
size);
unsigned int start, nbits;
for (start = 0; start < 1024; start += 8) {
- memset(bmap1, 0x5a, sizeof(bmap1));
- memset(bmap2, 0x5a, sizeof(bmap2));
for (nbits = 0; nbits < 1024 - start; nbits += 8) {
+ memset(bmap1, 0x5a, sizeof(bmap1));
+ memset(bmap2, 0x5a, sizeof(bmap2));
+
bitmap_set(bmap1, start, nbits);
__bitmap_set(bmap2, start, nbits);
- if (!bitmap_equal(bmap1, bmap2, 1024))
+ if (!bitmap_equal(bmap1, bmap2, 1024)) {
printk("set not equal %d %d\n", start, nbits);
- if (!__bitmap_equal(bmap1, bmap2, 1024))
+ failed_tests++;
+ }
+ if (!__bitmap_equal(bmap1, bmap2, 1024)) {
printk("set not __equal %d %d\n", start, nbits);
+ failed_tests++;
+ }
bitmap_clear(bmap1, start, nbits);
__bitmap_clear(bmap2, start, nbits);
- if (!bitmap_equal(bmap1, bmap2, 1024))
+ if (!bitmap_equal(bmap1, bmap2, 1024)) {
printk("clear not equal %d %d\n", start, nbits);
- if (!__bitmap_equal(bmap1, bmap2, 1024))
+ failed_tests++;
+ }
+ if (!__bitmap_equal(bmap1, bmap2, 1024)) {
printk("clear not __equal %d %d\n", start,
nbits);
+ failed_tests++;
+ }
}
}
}
return 0;
}
-#define PUSH_CNT 68
-/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
-static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
-{
- unsigned int len = BPF_MAXINSNS;
- struct bpf_insn *insn;
- int i = 0, j, k = 0;
-
- insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
- if (!insn)
- return -ENOMEM;
-
- insn[i++] = BPF_MOV64_REG(R6, R1);
-loop:
- for (j = 0; j < PUSH_CNT; j++) {
- insn[i++] = BPF_LD_ABS(BPF_B, 0);
- insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
- i++;
- insn[i++] = BPF_MOV64_REG(R1, R6);
- insn[i++] = BPF_MOV64_IMM(R2, 1);
- insn[i++] = BPF_MOV64_IMM(R3, 2);
- insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
- bpf_skb_vlan_push_proto.func - __bpf_call_base);
- insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
- i++;
- }
-
- for (j = 0; j < PUSH_CNT; j++) {
- insn[i++] = BPF_LD_ABS(BPF_B, 0);
- insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
- i++;
- insn[i++] = BPF_MOV64_REG(R1, R6);
- insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
- bpf_skb_vlan_pop_proto.func - __bpf_call_base);
- insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
- i++;
- }
- if (++k < 5)
- goto loop;
-
- for (; i < len - 1; i++)
- insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef);
-
- insn[len - 1] = BPF_EXIT_INSN();
-
- self->u.ptr.insns = insn;
- self->u.ptr.len = len;
-
- return 0;
-}
-
-static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self)
-{
- struct bpf_insn *insn;
-
- insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL);
- if (!insn)
- return -ENOMEM;
-
- /* Due to func address being non-const, we need to
- * assemble this here.
- */
- insn[0] = BPF_MOV64_REG(R6, R1);
- insn[1] = BPF_LD_ABS(BPF_B, 0);
- insn[2] = BPF_LD_ABS(BPF_H, 0);
- insn[3] = BPF_LD_ABS(BPF_W, 0);
- insn[4] = BPF_MOV64_REG(R7, R6);
- insn[5] = BPF_MOV64_IMM(R6, 0);
- insn[6] = BPF_MOV64_REG(R1, R7);
- insn[7] = BPF_MOV64_IMM(R2, 1);
- insn[8] = BPF_MOV64_IMM(R3, 2);
- insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
- bpf_skb_vlan_push_proto.func - __bpf_call_base);
- insn[10] = BPF_MOV64_REG(R6, R7);
- insn[11] = BPF_LD_ABS(BPF_B, 0);
- insn[12] = BPF_LD_ABS(BPF_H, 0);
- insn[13] = BPF_LD_ABS(BPF_W, 0);
- insn[14] = BPF_MOV64_IMM(R0, 42);
- insn[15] = BPF_EXIT_INSN();
-
- self->u.ptr.insns = insn;
- self->u.ptr.len = 16;
-
- return 0;
-}
-
-static int bpf_fill_jump_around_ld_abs(struct bpf_test *self)
-{
- unsigned int len = BPF_MAXINSNS;
- struct bpf_insn *insn;
- int i = 0;
-
- insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
- if (!insn)
- return -ENOMEM;
-
- insn[i++] = BPF_MOV64_REG(R6, R1);
- insn[i++] = BPF_LD_ABS(BPF_B, 0);
- insn[i] = BPF_JMP_IMM(BPF_JEQ, R0, 10, len - i - 2);
- i++;
- while (i < len - 1)
- insn[i++] = BPF_LD_ABS(BPF_B, 1);
- insn[i] = BPF_EXIT_INSN();
-
- self->u.ptr.insns = insn;
- self->u.ptr.len = len;
-
- return 0;
-}
-
static int __bpf_fill_stxdw(struct bpf_test *self, int size)
{
unsigned int len = BPF_MAXINSNS;
{ },
{ { 0, -1 } }
},
- {
- "INT: DIV + ABS",
- .u.insns_int = {
- BPF_ALU64_REG(BPF_MOV, R6, R1),
- BPF_LD_ABS(BPF_B, 3),
- BPF_ALU64_IMM(BPF_MOV, R2, 2),
- BPF_ALU32_REG(BPF_DIV, R0, R2),
- BPF_ALU64_REG(BPF_MOV, R8, R0),
- BPF_LD_ABS(BPF_B, 4),
- BPF_ALU64_REG(BPF_ADD, R8, R0),
- BPF_LD_IND(BPF_B, R8, -70),
- BPF_EXIT_INSN(),
- },
- INTERNAL,
- { 10, 20, 30, 40, 50 },
- { { 4, 0 }, { 5, 10 } }
- },
- {
- /* This one doesn't go through verifier, but is just raw insn
- * as opposed to cBPF tests from here. Thus div by 0 tests are
- * done in test_verifier in BPF kselftests.
- */
- "INT: DIV by -1",
- .u.insns_int = {
- BPF_ALU64_REG(BPF_MOV, R6, R1),
- BPF_ALU64_IMM(BPF_MOV, R7, -1),
- BPF_LD_ABS(BPF_B, 3),
- BPF_ALU32_REG(BPF_DIV, R0, R7),
- BPF_EXIT_INSN(),
- },
- INTERNAL,
- { 10, 20, 30, 40, 50 },
- { { 3, 0 }, { 4, 0 } }
- },
{
"check: missing ret",
.u.insns = {
{ },
{ { 0, 1 } }
},
- {
- "nmap reduced",
- .u.insns_int = {
- BPF_MOV64_REG(R6, R1),
- BPF_LD_ABS(BPF_H, 12),
- BPF_JMP_IMM(BPF_JNE, R0, 0x806, 28),
- BPF_LD_ABS(BPF_H, 12),
- BPF_JMP_IMM(BPF_JNE, R0, 0x806, 26),
- BPF_MOV32_IMM(R0, 18),
- BPF_STX_MEM(BPF_W, R10, R0, -64),
- BPF_LDX_MEM(BPF_W, R7, R10, -64),
- BPF_LD_IND(BPF_W, R7, 14),
- BPF_STX_MEM(BPF_W, R10, R0, -60),
- BPF_MOV32_IMM(R0, 280971478),
- BPF_STX_MEM(BPF_W, R10, R0, -56),
- BPF_LDX_MEM(BPF_W, R7, R10, -56),
- BPF_LDX_MEM(BPF_W, R0, R10, -60),
- BPF_ALU32_REG(BPF_SUB, R0, R7),
- BPF_JMP_IMM(BPF_JNE, R0, 0, 15),
- BPF_LD_ABS(BPF_H, 12),
- BPF_JMP_IMM(BPF_JNE, R0, 0x806, 13),
- BPF_MOV32_IMM(R0, 22),
- BPF_STX_MEM(BPF_W, R10, R0, -56),
- BPF_LDX_MEM(BPF_W, R7, R10, -56),
- BPF_LD_IND(BPF_H, R7, 14),
- BPF_STX_MEM(BPF_W, R10, R0, -52),
- BPF_MOV32_IMM(R0, 17366),
- BPF_STX_MEM(BPF_W, R10, R0, -48),
- BPF_LDX_MEM(BPF_W, R7, R10, -48),
- BPF_LDX_MEM(BPF_W, R0, R10, -52),
- BPF_ALU32_REG(BPF_SUB, R0, R7),
- BPF_JMP_IMM(BPF_JNE, R0, 0, 2),
- BPF_MOV32_IMM(R0, 256),
- BPF_EXIT_INSN(),
- BPF_MOV32_IMM(R0, 0),
- BPF_EXIT_INSN(),
- },
- INTERNAL,
- { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6},
- { { 38, 256 } },
- .stack_depth = 64,
- },
/* BPF_ALU | BPF_MOV | BPF_X */
{
"ALU_MOV_X: dst = 2",
{ { 1, 0xbee } },
.fill_helper = bpf_fill_ld_abs_get_processor_id,
},
- {
- "BPF_MAXINSNS: ld_abs+vlan_push/pop",
- { },
- INTERNAL,
- { 0x34 },
- { { ETH_HLEN, 0xbef } },
- .fill_helper = bpf_fill_ld_abs_vlan_push_pop,
- },
- {
- "BPF_MAXINSNS: jump around ld_abs",
- { },
- INTERNAL,
- { 10, 11 },
- { { 2, 10 } },
- .fill_helper = bpf_fill_jump_around_ld_abs,
- },
/*
* LD_IND / LD_ABS on fragmented SKBs
*/
{ [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
{ {0x40, 0x05 } },
},
+ {
+ "LD_IND byte positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xff } },
+ },
+ {
+ "LD_IND byte positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_IND byte negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 } },
+ },
+ {
+ "LD_IND byte negative offset, multiple calls",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 1),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 2),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 3),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 4),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x82 }, },
+ },
{
"LD_IND halfword positive offset",
.u.insns = {
},
{ {0x40, 0x66cc } },
},
+ {
+ "LD_IND halfword positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3d),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xffff } },
+ },
+ {
+ "LD_IND halfword positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_IND halfword negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 } },
+ },
{
"LD_IND word positive offset",
.u.insns = {
},
{ {0x40, 0x66cc77dd } },
},
+ {
+ "LD_IND word positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xffffffff } },
+ },
+ {
+ "LD_IND word positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_IND word negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+ BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 } },
+ },
{
"LD_ABS byte",
.u.insns = {
},
{ {0x40, 0xcc } },
},
+ {
+ "LD_ABS byte positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xff } },
+ },
+ {
+ "LD_ABS byte positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_ABS byte negative offset, out of bounds load",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, -1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC | FLAG_EXPECTED_FAIL,
+ .expected_errcode = -EINVAL,
+ },
+ {
+ "LD_ABS byte negative offset, in bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x82 }, },
+ },
+ {
+ "LD_ABS byte negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_ABS byte negative offset, multiple calls",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3c),
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3d),
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3e),
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x82 }, },
+ },
{
"LD_ABS halfword",
.u.insns = {
},
{ {0x40, 0x99ff } },
},
+ {
+ "LD_ABS halfword positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3e),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xffff } },
+ },
+ {
+ "LD_ABS halfword positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_ABS halfword negative offset, out of bounds load",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_H, -1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC | FLAG_EXPECTED_FAIL,
+ .expected_errcode = -EINVAL,
+ },
+ {
+ "LD_ABS halfword negative offset, in bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x1982 }, },
+ },
+ {
+ "LD_ABS halfword negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
{
"LD_ABS word",
.u.insns = {
},
{ {0x40, 0x88ee99ff } },
},
+ {
+ "LD_ABS word positive offset, all ff",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3c),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff },
+ { {0x40, 0xffffffff } },
+ },
+ {
+ "LD_ABS word positive offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LD_ABS word negative offset, out of bounds load",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_W, -1),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC | FLAG_EXPECTED_FAIL,
+ .expected_errcode = -EINVAL,
+ },
+ {
+ "LD_ABS word negative offset, in bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x25051982 }, },
+ },
+ {
+ "LD_ABS word negative offset, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x3f, 0 }, },
+ },
+ {
+ "LDX_MSH standalone, preserved A",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0xffeebbaa }, },
+ },
+ {
+ "LDX_MSH standalone, preserved A 2",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0x175e9d63),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3d),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3f),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x175e9d63 }, },
+ },
+ {
+ "LDX_MSH standalone, test result 1",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+ BPF_STMT(BPF_MISC | BPF_TXA, 0),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x14 }, },
+ },
+ {
+ "LDX_MSH standalone, test result 2",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+ BPF_STMT(BPF_MISC | BPF_TXA, 0),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x24 }, },
+ },
+ {
+ "LDX_MSH standalone, negative offset",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, -1),
+ BPF_STMT(BPF_MISC | BPF_TXA, 0),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0 }, },
+ },
+ {
+ "LDX_MSH standalone, negative offset 2",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, SKF_LL_OFF + 0x3e),
+ BPF_STMT(BPF_MISC | BPF_TXA, 0),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0x24 }, },
+ },
+ {
+ "LDX_MSH standalone, out of bounds",
+ .u.insns = {
+ BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+ BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x40),
+ BPF_STMT(BPF_MISC | BPF_TXA, 0),
+ BPF_STMT(BPF_RET | BPF_A, 0x0),
+ },
+ CLASSIC,
+ { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 },
+ { {0x40, 0 }, },
+ },
/*
* verify that the interpreter or JIT correctly sets A and X
* to 0.
{},
{ {0x1, 0x42 } },
},
- {
- "LD_ABS with helper changing skb data",
- { },
- INTERNAL,
- { 0x34 },
- { { ETH_HLEN, 42 } },
- .fill_helper = bpf_fill_ld_abs_vlan_push_pop2,
- },
/* Checking interpreter vs JIT wrt signed extended imms. */
{
"JNE signed compare, test 1",
return number(buf, end, (unsigned long int)ptr, spec);
}
-static bool have_filled_random_ptr_key __read_mostly;
+static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
static siphash_key_t ptr_key __read_mostly;
-static void fill_random_ptr_key(struct random_ready_callback *unused)
+static void enable_ptr_key_workfn(struct work_struct *work)
{
get_random_bytes(&ptr_key, sizeof(ptr_key));
- /*
- * have_filled_random_ptr_key==true is dependent on get_random_bytes().
- * ptr_to_id() needs to see have_filled_random_ptr_key==true
- * after get_random_bytes() returns.
- */
- smp_mb();
- WRITE_ONCE(have_filled_random_ptr_key, true);
+ /* Needs to run from preemptible context */
+ static_branch_disable(¬_filled_random_ptr_key);
+}
+
+static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
+
+static void fill_random_ptr_key(struct random_ready_callback *unused)
+{
+ /* This may be in an interrupt handler. */
+ queue_work(system_unbound_wq, &enable_ptr_key_work);
}
static struct random_ready_callback random_ready = {
if (!ret) {
return 0;
} else if (ret == -EALREADY) {
- fill_random_ptr_key(&random_ready);
+ /* This is in preemptible context */
+ enable_ptr_key_workfn(&enable_ptr_key_work);
return 0;
}
unsigned long hashval;
const int default_width = 2 * sizeof(ptr);
- if (unlikely(!have_filled_random_ptr_key)) {
+ if (static_branch_unlikely(¬_filled_random_ptr_key)) {
spec.field_width = default_width;
/* string length must be less than default_width */
return string(buf, end, "(ptrval)", spec);
default n
depends on NO_BOOTMEM
depends on !FLATMEM
+ depends on !NEED_PER_CPU_KM
help
Ordinarily all struct pages are initialised during early boot in a
single thread. On very large machines this can take a considerable
bdi, &bdi_debug_stats_fops);
if (!bdi->debug_stats) {
debugfs_remove(bdi->debug_dir);
+ bdi->debug_dir = NULL;
return -ENOMEM;
}
* the barrier provided by test_and_clear_bit() above.
*/
smp_wmb();
- clear_bit(WB_shutting_down, &wb->state);
+ clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
return error;
}
- error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
if (error) {
if (!huge)
mem_cgroup_cancel_charge(page, memcg, false);
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, offset,
- gfp_mask & GFP_RECLAIM_MASK);
+ err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (unlikely(err)) {
put_page(page);
page = NULL;
if (!page)
return -ENOMEM;
- ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
+ ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
if (vm_flags & (VM_IO | VM_PFNMAP))
return -EFAULT;
+ if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+ return -EFAULT;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
pmde = maybe_pmd_mkwrite(pmde, vma);
flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
- page_add_anon_rmap(new, vma, mmun_start, true);
+ if (PageAnon(new))
+ page_add_anon_rmap(new, vma, mmun_start, true);
+ else
+ page_add_file_rmap(new, true);
set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
if (vma->vm_flags & VM_LOCKED)
mlock_vma_page(new);
{
struct memcg_kmem_cache_create_work *cw;
- cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
+ cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
if (!cw)
return;
pslot = radix_tree_lookup_slot(&mapping->i_pages,
page_index(page));
- expected_count += 1 + page_has_private(page);
+ expected_count += hpage_nr_pages(page) + page_has_private(page);
if (page_count(page) != expected_count ||
radix_tree_deref_slot_protected(pslot,
&mapping->i_pages.xa_lock) != page) {
*/
newpage->index = page->index;
newpage->mapping = page->mapping;
- get_page(newpage); /* add cache reference */
+ page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
if (PageSwapBacked(page)) {
__SetPageSwapBacked(newpage);
if (PageSwapCache(page)) {
}
radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+ if (PageTransHuge(page)) {
+ int i;
+ int index = page_index(page);
+
+ for (i = 1; i < HPAGE_PMD_NR; i++) {
+ pslot = radix_tree_lookup_slot(&mapping->i_pages,
+ index + i);
+ radix_tree_replace_slot(&mapping->i_pages, pslot,
+ newpage + i);
+ }
+ }
/*
* Drop cache reference from old page by unfreezing
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - 1);
+ page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
xa_unlock(&mapping->i_pages);
/* Leave irq disabled to prevent preemption while updating stats */
current_node = NUMA_NO_NODE;
}
out_flush:
+ if (list_empty(&pagelist))
+ return err;
+
/* Make sure we do not overwrite the existing error */
err1 = do_move_pages_to_node(mm, &pagelist, current_node);
if (!err1)
__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};
+#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ return prot;
+}
+#endif
+
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
- return __pgprot(pgprot_val(protection_map[vm_flags &
+ pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
pgprot_val(arch_vm_get_page_prot(vm_flags)));
+
+ return arch_filter_pgprot(ret);
}
EXPORT_SYMBOL(vm_get_page_prot);
return 0;
}
+static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
+{
+ if (S_ISREG(inode->i_mode))
+ return MAX_LFS_FILESIZE;
+
+ if (S_ISBLK(inode->i_mode))
+ return MAX_LFS_FILESIZE;
+
+ /* Special "we do even unsigned file positions" case */
+ if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+ return 0;
+
+ /* Yes, random drivers might want more. But I'm tired of buggy drivers */
+ return ULONG_MAX;
+}
+
+static inline bool file_mmap_ok(struct file *file, struct inode *inode,
+ unsigned long pgoff, unsigned long len)
+{
+ u64 maxsize = file_mmap_size_max(file, inode);
+
+ if (maxsize && len > maxsize)
+ return false;
+ maxsize -= len;
+ if (pgoff > maxsize >> PAGE_SHIFT)
+ return false;
+ return true;
+}
+
/*
* The caller must hold down_write(¤t->mm->mmap_sem).
*/
struct inode *inode = file_inode(file);
unsigned long flags_mask;
+ if (!file_mmap_ok(file, inode, pgoff, len))
+ return -EOVERFLOW;
+
flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
switch (flags & MAP_TYPE) {
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
+ if (unlikely(mm_is_oom_victim(mm))) {
+ /*
+ * Manually reap the mm to free as much memory as possible.
+ * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
+ * this mm from further consideration. Taking mm->mmap_sem for
+ * write after setting MMF_OOM_SKIP will guarantee that the oom
+ * reaper will not run on this mm again after mmap_sem is
+ * dropped.
+ *
+ * Nothing can be holding mm->mmap_sem here and the above call
+ * to mmu_notifier_release(mm) ensures mmu notifier callbacks in
+ * __oom_reap_task_mm() will not block.
+ *
+ * This needs to be done before calling munlock_vma_pages_all(),
+ * which clears VM_LOCKED, otherwise the oom reaper cannot
+ * reliably test it.
+ */
+ mutex_lock(&oom_lock);
+ __oom_reap_task_mm(mm);
+ mutex_unlock(&oom_lock);
+
+ set_bit(MMF_OOM_SKIP, &mm->flags);
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ }
+
if (mm->locked_vm) {
vma = mm->mmap;
while (vma) {
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
-
- if (unlikely(mm_is_oom_victim(mm))) {
- /*
- * Wait for oom_reap_task() to stop working on this
- * mm. Because MMF_OOM_SKIP is already set before
- * calling down_read(), oom_reap_task() will not run
- * on this "mm" post up_write().
- *
- * mm_is_oom_victim() cannot be set from under us
- * either because victim->mm is already set to NULL
- * under task_lock before calling mmput and oom_mm is
- * set not NULL by the OOM killer only if victim->mm
- * is found not NULL while holding the task_lock.
- */
- set_bit(MMF_OOM_SKIP, &mm->flags);
- down_write(&mm->mmap_sem);
- up_write(&mm->mmap_sem);
- }
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb, 0, -1);
return false;
}
-
#ifdef CONFIG_MMU
/*
* OOM Reaper kernel thread which tries to reap the memory used by the OOM
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);
-static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+void __oom_reap_task_mm(struct mm_struct *mm)
{
- struct mmu_gather tlb;
struct vm_area_struct *vma;
+
+ /*
+ * Tell all users of get_user/copy_from_user etc... that the content
+ * is no longer stable. No barriers really needed because unmapping
+ * should imply barriers already and the reader would hit a page fault
+ * if it stumbled over a reaped memory.
+ */
+ set_bit(MMF_UNSTABLE, &mm->flags);
+
+ for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+ if (!can_madv_dontneed_vma(vma))
+ continue;
+
+ /*
+ * Only anonymous pages have a good chance to be dropped
+ * without additional steps which we cannot afford as we
+ * are OOM already.
+ *
+ * We do not even care about fs backed pages because all
+ * which are reclaimable have already been reclaimed and
+ * we do not want to block exit_mmap by keeping mm ref
+ * count elevated without a good reason.
+ */
+ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+ const unsigned long start = vma->vm_start;
+ const unsigned long end = vma->vm_end;
+ struct mmu_gather tlb;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ unmap_page_range(&tlb, vma, start, end, NULL);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+ }
+ }
+}
+
+static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
bool ret = true;
/*
* We have to make sure to not race with the victim exit path
* and cause premature new oom victim selection:
- * __oom_reap_task_mm exit_mm
+ * oom_reap_task_mm exit_mm
* mmget_not_zero
* mmput
* atomic_dec_and_test
trace_start_task_reaping(tsk->pid);
- /*
- * Tell all users of get_user/copy_from_user etc... that the content
- * is no longer stable. No barriers really needed because unmapping
- * should imply barriers already and the reader would hit a page fault
- * if it stumbled over a reaped memory.
- */
- set_bit(MMF_UNSTABLE, &mm->flags);
-
- for (vma = mm->mmap ; vma; vma = vma->vm_next) {
- if (!can_madv_dontneed_vma(vma))
- continue;
+ __oom_reap_task_mm(mm);
- /*
- * Only anonymous pages have a good chance to be dropped
- * without additional steps which we cannot afford as we
- * are OOM already.
- *
- * We do not even care about fs backed pages because all
- * which are reclaimable have already been reclaimed and
- * we do not want to block exit_mmap by keeping mm ref
- * count elevated without a good reason.
- */
- if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
- const unsigned long start = vma->vm_start;
- const unsigned long end = vma->vm_end;
-
- tlb_gather_mmu(&tlb, mm, start, end);
- mmu_notifier_invalidate_range_start(mm, start, end);
- unmap_page_range(&tlb, vma, start, end, NULL);
- mmu_notifier_invalidate_range_end(mm, start, end);
- tlb_finish_mmu(&tlb, start, end);
- }
- }
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
struct mm_struct *mm = tsk->signal->oom_mm;
/* Retry the down_read_trylock(mmap_sem) a few times */
- while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
+ while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
if (attempts <= MAX_OOM_REAP_RETRIES ||
test_bit(MMF_OOM_SKIP, &mm->flags))
goto done;
-
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
current->nr_dirtied--;
dec_node_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
}
}
EXPORT_SYMBOL(account_page_redirty);
if (mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
lock_page_memcg(page);
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page))
account_page_cleaned(page, mapping, wb);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
unlock_page_memcg(page);
} else {
ClearPageDirty(page);
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
/*
* Yes, Virginia, this is indeed insane.
* always locked coming in here, so we get the desired
* exclusion.
*/
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page)) {
dec_lruvec_page_state(page, NR_FILE_DIRTY);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
return TestClearPageDirty(page);
if (!pvmw.pte && (flags & TTU_MIGRATION)) {
VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
- if (!PageAnon(page))
- continue;
-
set_pmd_migration_entry(&pvmw, page);
continue;
}
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ unsigned long section_nr = pfn_to_section_nr(pfn);
struct mem_section *ms;
/*
"nr_vmscan_immediate_reclaim",
"nr_dirtied",
"nr_written",
- "nr_indirectly_reclaimable",
+ "", /* nr_indirectly_reclaimable */
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
unsigned long *l = arg;
unsigned long off = l - (unsigned long *)m->private;
+ /* Skip hidden vmstat items. */
+ if (*vmstat_text[off] == '\0')
+ return 0;
+
seq_puts(m, vmstat_text[off]);
seq_put_decimal_ull(m, " ", *l);
seq_putc(m, '\n');
PAGE_HEADLESS = 0,
MIDDLE_CHUNK_MAPPED,
NEEDS_COMPACTING,
- PAGE_STALE
+ PAGE_STALE,
+ UNDER_RECLAIM
};
/*****************
clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
clear_bit(NEEDS_COMPACTING, &page->private);
clear_bit(PAGE_STALE, &page->private);
+ clear_bit(UNDER_RECLAIM, &page->private);
spin_lock_init(&zhdr->page_lock);
kref_init(&zhdr->refcount);
atomic64_dec(&pool->pages_nr);
return;
}
+ if (test_bit(UNDER_RECLAIM, &page->private)) {
+ z3fold_page_unlock(zhdr);
+ return;
+ }
if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
z3fold_page_unlock(zhdr);
return;
kref_get(&zhdr->refcount);
list_del_init(&zhdr->buddy);
zhdr->cpu = -1;
+ set_bit(UNDER_RECLAIM, &page->private);
+ break;
}
list_del_init(&page->lru);
goto next;
}
next:
- spin_lock(&pool->lock);
if (test_bit(PAGE_HEADLESS, &page->private)) {
if (ret == 0) {
- spin_unlock(&pool->lock);
free_z3fold_page(page);
return 0;
}
- } else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
- atomic64_dec(&pool->pages_nr);
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
+ spin_unlock(&pool->lock);
+ } else {
+ z3fold_page_lock(zhdr);
+ clear_bit(UNDER_RECLAIM, &page->private);
+ if (kref_put(&zhdr->refcount,
+ release_z3fold_page_locked)) {
+ atomic64_dec(&pool->pages_nr);
+ return 0;
+ }
+ /*
+ * if we are here, the page is still not completely
+ * free. Take the global pool lock then to be able
+ * to add it back to the lru list
+ */
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
spin_unlock(&pool->lock);
- return 0;
+ z3fold_page_unlock(zhdr);
}
- /*
- * Add to the beginning of LRU.
- * Pool lock has to be kept here to ensure the page has
- * not already been released
- */
- list_add(&page->lru, &pool->lru);
+ /* We started off locked to we need to lock the pool back */
+ spin_lock(&pool->lock);
}
spin_unlock(&pool->lock);
return -EAGAIN;
}
int vlan_check_real_dev(struct net_device *real_dev,
- __be16 protocol, u16 vlan_id)
+ __be16 protocol, u16 vlan_id,
+ struct netlink_ext_ack *extack)
{
const char *name = real_dev->name;
if (real_dev->features & NETIF_F_VLAN_CHALLENGED) {
pr_info("VLANs not supported on %s\n", name);
+ NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device");
return -EOPNOTSUPP;
}
- if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL)
+ if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists");
return -EEXIST;
+ }
return 0;
}
if (vlan_id >= VLAN_VID_MASK)
return -ERANGE;
- err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id);
+ err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id,
+ NULL);
if (err < 0)
return err;
void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
int vlan_check_real_dev(struct net_device *real_dev,
- __be16 protocol, u16 vlan_id);
+ __be16 protocol, u16 vlan_id,
+ struct netlink_ext_ack *extack);
void vlan_setup(struct net_device *dev);
int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
return 0;
}
-/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */
+/* Flags are defined in the vlan_flags enum in
+ * include/uapi/linux/if_vlan.h file.
+ */
int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
int err;
if (tb[IFLA_ADDRESS]) {
- if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid link address");
return -EINVAL;
- if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ }
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid link address");
return -EADDRNOTAVAIL;
+ }
}
- if (!data)
+ if (!data) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN properties not specified");
return -EINVAL;
+ }
if (data[IFLA_VLAN_PROTOCOL]) {
switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) {
case htons(ETH_P_8021AD):
break;
default:
+ NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN protocol");
return -EPROTONOSUPPORT;
}
}
if (data[IFLA_VLAN_ID]) {
id = nla_get_u16(data[IFLA_VLAN_ID]);
- if (id >= VLAN_VID_MASK)
+ if (id >= VLAN_VID_MASK) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN id");
return -ERANGE;
+ }
}
if (data[IFLA_VLAN_FLAGS]) {
flags = nla_data(data[IFLA_VLAN_FLAGS]);
if ((flags->flags & flags->mask) &
~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
- VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
+ VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN flags");
return -EINVAL;
+ }
}
err = vlan_validate_qos_map(data[IFLA_VLAN_INGRESS_QOS]);
- if (err < 0)
+ if (err < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid ingress QOS map");
return err;
+ }
err = vlan_validate_qos_map(data[IFLA_VLAN_EGRESS_QOS]);
- if (err < 0)
+ if (err < 0) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid egress QOS map");
return err;
+ }
return 0;
}
__be16 proto;
int err;
- if (!data[IFLA_VLAN_ID])
+ if (!data[IFLA_VLAN_ID]) {
+ NL_SET_ERR_MSG_MOD(extack, "VLAN id not specified");
return -EINVAL;
+ }
- if (!tb[IFLA_LINK])
+ if (!tb[IFLA_LINK]) {
+ NL_SET_ERR_MSG_MOD(extack, "link not specified");
return -EINVAL;
+ }
+
real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
- if (!real_dev)
+ if (!real_dev) {
+ NL_SET_ERR_MSG_MOD(extack, "link does not exist");
return -ENODEV;
+ }
if (data[IFLA_VLAN_PROTOCOL])
proto = nla_get_be16(data[IFLA_VLAN_PROTOCOL]);
dev->priv_flags |= (real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
vlan->flags = VLAN_FLAG_REORDER_HDR;
- err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id);
+ err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id,
+ extack);
if (err < 0)
return err;
/**
* v9fs_get_trans_by_name - get transport with the matching name
- * @name: string identifying transport
+ * @s: string identifying transport
*
*/
struct p9_trans_module *v9fs_get_trans_by_name(char *s)
#include <linux/module.h>
/**
- * p9_release_req_pages - Release pages after the transaction.
+ * p9_release_pages - Release pages after the transaction.
*/
void p9_release_pages(struct page **pages, int nr_pages)
{
};
/**
- * p9_poll_proc - poll worker thread
- * @a: thread state and arguments
+ * p9_poll_workfn - poll worker thread
+ * @work: work queue
*
* polls all v9fs transports for new events and queues the appropriate
* work to the work queue
* @pd: Protection Domain pointer
* @qp: Queue Pair pointer
* @cq: Completion Queue pointer
- * @dm_mr: DMA Memory Region pointer
- * @lkey: The local access only memory region key
* @timeout: Number of uSecs to wait for connection management events
* @privport: Whether a privileged port may be used
* @port: The port to use
}
/**
- * trans_create_rdma - Transport method for creating atransport instance
+ * rdma_create_trans - Transport method for creating a transport instance
* @client: client instance
* @addr: IP address string
* @args: Mount options string
/**
* struct virtio_chan - per-instance transport information
- * @initialized: whether the channel is initialized
* @inuse: whether the channel is in use
* @lock: protects multiple elements within this structure
* @client: client instance
* @uidata: user bffer that should be ued for zero copy read
* @uodata: user buffer that shoud be user for zero copy write
* @inlen: read buffer size
- * @olen: write buffer size
- * @hdrlen: reader header size, This is the size of response protocol data
+ * @outlen: write buffer size
+ * @in_hdr_len: reader header size, This is the size of response protocol data
*
*/
static int
static int xen_9pfs_front_resume(struct xenbus_device *dev)
{
- dev_warn(&dev->dev, "suspsend/resume unsupported\n");
+ dev_warn(&dev->dev, "suspend/resume unsupported\n");
return 0;
}
source "net/xfrm/Kconfig"
source "net/iucv/Kconfig"
source "net/smc/Kconfig"
+source "net/xdp/Kconfig"
config INET
bool "TCP/IP networking"
bool
default n
+config SOCK_VALIDATE_XMIT
+ bool
+
config NET_DEVLINK
tristate "Network physical/parent device Netlink interface"
help
endif
obj-$(CONFIG_QRTR) += qrtr/
obj-$(CONFIG_NET_NCSI) += ncsi/
+obj-$(CONFIG_XDP_SOCKETS) += xdp/
#include <linux/module.h>
#include <linux/init.h>
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
#include "lec.h"
#include "lec_arpc.h"
#include "resources.h"
bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
if (bytes_left != 0)
pr_info("copy from user failed for %d bytes\n", bytes_left);
- if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF ||
- !dev_lec[ioc_data.dev_num])
+ if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF)
+ return -EINVAL;
+ ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF);
+ if (!dev_lec[ioc_data.dev_num])
return -EINVAL;
vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL);
if (!vpriv)
return 0;
}
+int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen,
+ const void *param)
+{
+ struct sk_buff *skb;
+
+ if (hci_opcode_ogf(opcode) != 0x3f) {
+ /* A controller receiving a command shall respond with either
+ * a Command Status Event or a Command Complete Event.
+ * Therefore, all standard HCI commands must be sent via the
+ * standard API, using hci_send_cmd or hci_cmd_sync helpers.
+ * Some vendors do not comply with this rule for vendor-specific
+ * commands and do not return any event. We want to support
+ * unresponded commands for such cases only.
+ */
+ bt_dev_err(hdev, "unresponded command not supported");
+ return -EINVAL;
+ }
+
+ skb = hci_prepare_cmd(hdev, opcode, plen, param);
+ if (!skb) {
+ bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)",
+ opcode);
+ return -ENOMEM;
+ }
+
+ hci_send_frame(hdev, skb);
+
+ return 0;
+}
+EXPORT_SYMBOL(__hci_cmd_send);
+
/* Get data from the previously sent command */
void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode)
{
struct hci_ev_le_advertising_info *ev = ptr;
s8 rssi;
- rssi = ev->data[ev->length];
- process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
- ev->bdaddr_type, NULL, 0, rssi,
- ev->data, ev->length);
+ if (ev->length <= HCI_MAX_AD_LENGTH) {
+ rssi = ev->data[ev->length];
+ process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
+ ev->bdaddr_type, NULL, 0, rssi,
+ ev->data, ev->length);
+ } else {
+ bt_dev_err(hdev, "Dropping invalid advertising data");
+ }
ptr += sizeof(*ev) + ev->length + 1;
}
struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
const void *param, u8 event, u32 timeout)
{
- DECLARE_WAITQUEUE(wait, current);
struct hci_request req;
struct sk_buff *skb;
int err = 0;
hdev->req_status = HCI_REQ_PEND;
- add_wait_queue(&hdev->req_wait_q, &wait);
- set_current_state(TASK_INTERRUPTIBLE);
-
err = hci_req_run_skb(&req, hci_req_sync_complete);
- if (err < 0) {
- remove_wait_queue(&hdev->req_wait_q, &wait);
- set_current_state(TASK_RUNNING);
+ if (err < 0)
return ERR_PTR(err);
- }
- schedule_timeout(timeout);
+ err = wait_event_interruptible_timeout(hdev->req_wait_q,
+ hdev->req_status != HCI_REQ_PEND, timeout);
- remove_wait_queue(&hdev->req_wait_q, &wait);
-
- if (signal_pending(current))
+ if (err == -ERESTARTSYS)
return ERR_PTR(-EINTR);
switch (hdev->req_status) {
unsigned long opt, u32 timeout, u8 *hci_status)
{
struct hci_request req;
- DECLARE_WAITQUEUE(wait, current);
int err = 0;
BT_DBG("%s start", hdev->name);
return err;
}
- add_wait_queue(&hdev->req_wait_q, &wait);
- set_current_state(TASK_INTERRUPTIBLE);
-
err = hci_req_run_skb(&req, hci_req_sync_complete);
if (err < 0) {
hdev->req_status = 0;
- remove_wait_queue(&hdev->req_wait_q, &wait);
- set_current_state(TASK_RUNNING);
-
/* ENODATA means the HCI request command queue is empty.
* This can happen when a request with conditionals doesn't
* trigger any commands to be sent. This is normal behavior
return err;
}
- schedule_timeout(timeout);
-
- remove_wait_queue(&hdev->req_wait_q, &wait);
+ err = wait_event_interruptible_timeout(hdev->req_wait_q,
+ hdev->req_status != HCI_REQ_PEND, timeout);
- if (signal_pending(current))
+ if (err == -ERESTARTSYS)
return -EINTR;
switch (hdev->req_status) {
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net_bridge_port *p;
struct net_bridge *br;
+ bool notified = false;
bool changed_addr;
int err;
break;
case NETDEV_CHANGE:
- br_port_carrier_check(p);
+ br_port_carrier_check(p, ¬ified);
break;
case NETDEV_FEAT_CHANGE:
case NETDEV_DOWN:
spin_lock_bh(&br->lock);
- if (br->dev->flags & IFF_UP)
+ if (br->dev->flags & IFF_UP) {
br_stp_disable_port(p);
+ notified = true;
+ }
spin_unlock_bh(&br->lock);
break;
if (netif_running(br->dev) && netif_oper_up(dev)) {
spin_lock_bh(&br->lock);
br_stp_enable_port(p);
+ notified = true;
spin_unlock_bh(&br->lock);
}
break;
}
/* Events that may cause spanning tree to refresh */
- if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
- event == NETDEV_CHANGE || event == NETDEV_DOWN)
+ if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
+ event == NETDEV_CHANGE || event == NETDEV_DOWN))
br_ifinfo_notify(RTM_NEWLINK, NULL, p);
return NOTIFY_DONE;
case SWITCHDEV_FDB_ADD_TO_BRIDGE:
fdb_info = ptr;
err = br_fdb_external_learn_add(br, p, fdb_info->addr,
- fdb_info->vid);
+ fdb_info->vid, false);
if (err) {
err = notifier_from_errno(err);
break;
case SWITCHDEV_FDB_DEL_TO_BRIDGE:
fdb_info = ptr;
err = br_fdb_external_learn_del(br, p, fdb_info->addr,
- fdb_info->vid);
+ fdb_info->vid, false);
if (err)
err = notifier_from_errno(err);
break;
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
static void fdb_notify(struct net_bridge *br,
- const struct net_bridge_fdb_entry *, int);
+ const struct net_bridge_fdb_entry *, int, bool);
int __init br_fdb_init(void)
{
return fdb;
}
+struct net_device *br_fdb_find_port(const struct net_device *br_dev,
+ const unsigned char *addr,
+ __u16 vid)
+{
+ struct net_bridge_fdb_entry *f;
+ struct net_device *dev = NULL;
+ struct net_bridge *br;
+
+ ASSERT_RTNL();
+
+ if (!netif_is_bridge_master(br_dev))
+ return NULL;
+
+ br = netdev_priv(br_dev);
+ f = br_fdb_find(br, addr, vid);
+ if (f && f->dst)
+ dev = f->dst->dev;
+
+ return dev;
+}
+EXPORT_SYMBOL_GPL(br_fdb_find_port);
+
struct net_bridge_fdb_entry *br_fdb_find_rcu(struct net_bridge *br,
const unsigned char *addr,
__u16 vid)
}
}
-static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
+static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f,
+ bool swdev_notify)
{
trace_fdb_delete(br, f);
hlist_del_init_rcu(&f->fdb_node);
rhashtable_remove_fast(&br->fdb_hash_tbl, &f->rhnode,
br_fdb_rht_params);
- fdb_notify(br, f, RTM_DELNEIGH);
+ fdb_notify(br, f, RTM_DELNEIGH, swdev_notify);
call_rcu(&f->rcu, fdb_rcu_free);
}
return;
}
- fdb_delete(br, f);
+ fdb_delete(br, f, true);
}
void br_fdb_find_delete_local(struct net_bridge *br,
} else {
spin_lock_bh(&br->hash_lock);
if (!hlist_unhashed(&f->fdb_node))
- fdb_delete(br, f);
+ fdb_delete(br, f, true);
spin_unlock_bh(&br->hash_lock);
}
}
spin_lock_bh(&br->hash_lock);
hlist_for_each_entry_safe(f, tmp, &br->fdb_list, fdb_node) {
if (!f->is_static)
- fdb_delete(br, f);
+ fdb_delete(br, f, true);
}
spin_unlock_bh(&br->hash_lock);
}
if (f->is_local)
fdb_delete_local(br, p, f);
else
- fdb_delete(br, f);
+ fdb_delete(br, f, true);
}
spin_unlock_bh(&br->hash_lock);
}
return 0;
br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n",
source ? source->dev->name : br->dev->name, addr, vid);
- fdb_delete(br, fdb);
+ fdb_delete(br, fdb, true);
}
fdb = fdb_create(br, source, addr, vid, 1, 1);
return -ENOMEM;
fdb_add_hw_addr(br, addr);
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, true);
return 0;
}
fdb->added_by_user = 1;
if (unlikely(fdb_modified)) {
trace_br_fdb_update(br, source, addr, vid, added_by_user);
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, true);
}
}
} else {
fdb->added_by_user = 1;
trace_br_fdb_update(br, source, addr, vid,
added_by_user);
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, true);
}
/* else we lose race and someone else inserts
* it first, don't bother updating
}
static void fdb_notify(struct net_bridge *br,
- const struct net_bridge_fdb_entry *fdb, int type)
+ const struct net_bridge_fdb_entry *fdb, int type,
+ bool swdev_notify)
{
struct net *net = dev_net(br->dev);
struct sk_buff *skb;
int err = -ENOBUFS;
- br_switchdev_fdb_notify(fdb, type);
+ if (swdev_notify)
+ br_switchdev_fdb_notify(fdb, type);
skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC);
if (skb == NULL)
fdb->used = jiffies;
if (modified) {
fdb->updated = jiffies;
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, true);
}
return 0;
rcu_read_unlock();
local_bh_enable();
} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
- err = br_fdb_external_learn_add(br, p, addr, vid);
+ err = br_fdb_external_learn_add(br, p, addr, vid, true);
} else {
spin_lock_bh(&br->hash_lock);
err = fdb_add_entry(br, p, addr, ndm->ndm_state,
if (!fdb || fdb->dst != p)
return -ENOENT;
- fdb_delete(br, fdb);
+ fdb_delete(br, fdb, true);
return 0;
}
}
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid)
+ const unsigned char *addr, u16 vid,
+ bool swdev_notify)
{
struct net_bridge_fdb_entry *fdb;
bool modified = false;
goto err_unlock;
}
fdb->added_by_external_learn = 1;
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
} else {
fdb->updated = jiffies;
}
if (modified)
- fdb_notify(br, fdb, RTM_NEWNEIGH);
+ fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
}
err_unlock:
}
int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid)
+ const unsigned char *addr, u16 vid,
+ bool swdev_notify)
{
struct net_bridge_fdb_entry *fdb;
int err = 0;
fdb = br_fdb_find(br, addr, vid);
if (fdb && fdb->added_by_external_learn)
- fdb_delete(br, fdb);
+ fdb_delete(br, fdb, swdev_notify);
else
err = -ENOENT;
struct net_bridge_port *port, *lport, *rport;
lport = p ? p->port : NULL;
- rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) :
- NULL;
+ rport = hlist_entry_safe(rp, struct net_bridge_port, rlist);
if ((unsigned long)lport > (unsigned long)rport) {
port = lport;
/* Check for port carrier transitions. */
-void br_port_carrier_check(struct net_bridge_port *p)
+void br_port_carrier_check(struct net_bridge_port *p, bool *notified)
{
struct net_device *dev = p->dev;
struct net_bridge *br = p->br;
netif_running(dev) && netif_oper_up(dev))
p->path_cost = port_cost(dev);
+ *notified = false;
if (!netif_running(br->dev))
return;
spin_lock_bh(&br->lock);
if (netif_running(dev) && netif_oper_up(dev)) {
- if (p->state == BR_STATE_DISABLED)
+ if (p->state == BR_STATE_DISABLED) {
br_stp_enable_port(p);
+ *notified = true;
+ }
} else {
- if (p->state != BR_STATE_DISABLED)
+ if (p->state != BR_STATE_DISABLED) {
br_stp_disable_port(p);
+ *notified = true;
+ }
}
spin_unlock_bh(&br->lock);
}
return -ELOOP;
}
- /* Device is already being bridged */
- if (br_port_exists(dev))
+ /* Device has master upper dev */
+ if (netdev_master_upper_dev_get(dev))
return -EBUSY;
/* No bridging devices that dislike that (e.g. wireless) */
int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid);
+ const unsigned char *addr, u16 vid,
+ bool swdev_notify);
int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid);
+ const unsigned char *addr, u16 vid,
+ bool swdev_notify);
void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid);
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig);
/* br_if.c */
-void br_port_carrier_check(struct net_bridge_port *p);
+void br_port_carrier_check(struct net_bridge_port *p, bool *notified);
int br_add_bridge(struct net *net, const char *name);
int br_del_bridge(struct net *net, const char *name);
int br_add_if(struct net_bridge *br, struct net_device *dev,
return rcu_dereference(dev->rx_handler) == br_handle_frame;
}
+static inline bool br_rx_handler_check_rtnl(const struct net_device *dev)
+{
+ return rcu_dereference_rtnl(dev->rx_handler) == br_handle_frame;
+}
+
static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev)
{
return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL;
}
+static inline struct net_bridge_port *
+br_port_get_check_rtnl(const struct net_device *dev)
+{
+ return br_rx_handler_check_rtnl(dev) ? br_port_get_rtnl_rcu(dev) : NULL;
+}
+
/* br_ioctl.c */
int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd,
static void
br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac,
- u16 vid, struct net_device *dev)
+ u16 vid, struct net_device *dev,
+ bool added_by_user)
{
struct switchdev_notifier_fdb_info info;
unsigned long notifier_type;
info.addr = mac;
info.vid = vid;
+ info.added_by_user = added_by_user;
notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE;
call_switchdev_notifiers(notifier_type, dev, &info.info);
}
void
br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
{
- if (!fdb->added_by_user || !fdb->dst)
+ if (!fdb->dst)
return;
switch (type) {
case RTM_DELNEIGH:
br_switchdev_fdb_call_notifiers(false, fdb->key.addr.addr,
fdb->key.vlan_id,
- fdb->dst->dev);
+ fdb->dst->dev,
+ fdb->added_by_user);
break;
case RTM_NEWNEIGH:
br_switchdev_fdb_call_notifiers(true, fdb->key.addr.addr,
fdb->key.vlan_id,
- fdb->dst->dev);
+ fdb->dst->dev,
+ fdb->added_by_user);
break;
}
}
stats->tx_packets += txpackets;
}
}
+
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
+{
+ struct net_bridge_vlan_group *vg;
+
+ ASSERT_RTNL();
+ if (netif_is_bridge_master(dev))
+ vg = br_vlan_group(netdev_priv(dev));
+ else
+ return -EINVAL;
+
+ *p_pvid = br_get_pvid(vg);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
+
+int br_vlan_get_info(const struct net_device *dev, u16 vid,
+ struct bridge_vlan_info *p_vinfo)
+{
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_vlan *v;
+ struct net_bridge_port *p;
+
+ ASSERT_RTNL();
+ p = br_port_get_check_rtnl(dev);
+ if (p)
+ vg = nbp_vlan_group(p);
+ else if (netif_is_bridge_master(dev))
+ vg = br_vlan_group(netdev_priv(dev));
+ else
+ return -EINVAL;
+
+ v = br_vlan_find(vg, vid);
+ if (!v)
+ return -ENOENT;
+
+ p_vinfo->vid = vid;
+ p_vinfo->flags = v->flags;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(br_vlan_get_info);
bool "Ethernet Bridge nf_tables support"
if NF_TABLES_BRIDGE
-
-config NFT_BRIDGE_META
- tristate "Netfilter nf_table bridge meta support"
- depends on NFT_META
- help
- Add support for bridge dedicated meta key.
-
config NFT_BRIDGE_REJECT
tristate "Netfilter nf_tables bridge reject support"
depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6
# Makefile for the netfilter modules for Link Layer filtering on a bridge.
#
-obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o
obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o
# packet logging
/* Make sure the match only receives stp frames */
if (!par->nft_compat &&
(!ether_addr_equal(e->destmac, eth_stp_addr) ||
- !is_broadcast_ether_addr(e->destmsk) ||
- !(e->bitmask & EBT_DESTMAC)))
+ !(e->bitmask & EBT_DESTMAC) ||
+ !is_broadcast_ether_addr(e->destmsk)))
return -EINVAL;
return 0;
{
par->match = m->u.match;
par->matchinfo = m->data;
- return m->u.match->match(skb, par) ? EBT_MATCH : EBT_NOMATCH;
+ return !m->u.match->match(skb, par);
}
static inline int
return (void *)entry + entry->next_offset;
}
+static inline const struct ebt_entry_target *
+ebt_get_target_c(const struct ebt_entry *e)
+{
+ return ebt_get_target((struct ebt_entry *)e);
+}
+
/* Do some firewalling */
unsigned int ebt_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
*/
EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &acpar);
- t = (struct ebt_entry_target *)
- (((char *)point) + point->target_offset);
+ t = ebt_get_target_c(point);
/* standard target */
if (!t->u.target->target)
verdict = ((struct ebt_standard_target *)t)->verdict;
"ebtable_", error, mutex);
}
+static inline void ebt_free_table_info(struct ebt_table_info *info)
+{
+ int i;
+
+ if (info->chainstack) {
+ for_each_possible_cpu(i)
+ vfree(info->chainstack[i]);
+ vfree(info->chainstack);
+ }
+}
static inline int
ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par,
unsigned int *cnt)
return 1;
EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, NULL);
EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL);
- t = (struct ebt_entry_target *)(((char *)e) + e->target_offset);
+ t = ebt_get_target(e);
par.net = net;
par.target = t->u.target;
ret = EBT_WATCHER_ITERATE(e, ebt_check_watcher, &tgpar, &j);
if (ret != 0)
goto cleanup_watchers;
- t = (struct ebt_entry_target *)(((char *)e) + e->target_offset);
+ t = ebt_get_target(e);
gap = e->next_offset - e->target_offset;
target = xt_request_find_target(NFPROTO_BRIDGE, t->u.name, 0);
if (pos == nentries)
continue;
}
- t = (struct ebt_entry_target *)
- (((char *)e) + e->target_offset);
+ t = ebt_get_target_c(e);
if (strcmp(t->u.name, EBT_STANDARD_TARGET))
goto letscontinue;
if (e->target_offset + sizeof(struct ebt_standard_target) >
static int do_replace_finish(struct net *net, struct ebt_replace *repl,
struct ebt_table_info *newinfo)
{
- int ret, i;
+ int ret;
struct ebt_counter *counterstmp = NULL;
/* used to be able to unlock earlier */
struct ebt_table_info *table;
ebt_cleanup_entry, net, NULL);
vfree(table->entries);
- if (table->chainstack) {
- for_each_possible_cpu(i)
- vfree(table->chainstack[i]);
- vfree(table->chainstack);
- }
+ ebt_free_table_info(table);
vfree(table);
-
vfree(counterstmp);
#ifdef CONFIG_AUDIT
free_counterstmp:
vfree(counterstmp);
/* can be initialized in translate_table() */
- if (newinfo->chainstack) {
- for_each_possible_cpu(i)
- vfree(newinfo->chainstack[i]);
- vfree(newinfo->chainstack);
- }
+ ebt_free_table_info(newinfo);
return ret;
}
static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
{
- int i;
-
mutex_lock(&ebt_mutex);
list_del(&table->list);
mutex_unlock(&ebt_mutex);
if (table->private->nentries)
module_put(table->me);
vfree(table->private->entries);
- if (table->private->chainstack) {
- for_each_possible_cpu(i)
- vfree(table->private->chainstack[i]);
- vfree(table->private->chainstack);
- }
+ ebt_free_table_info(table->private);
vfree(table->private);
kfree(table);
}
free_unlock:
mutex_unlock(&ebt_mutex);
free_chainstack:
- if (newinfo->chainstack) {
- for_each_possible_cpu(i)
- vfree(newinfo->chainstack[i]);
- vfree(newinfo->chainstack);
- }
+ ebt_free_table_info(newinfo);
vfree(newinfo->entries);
free_newinfo:
vfree(newinfo);
return -EFAULT;
hlp = ubase + (((char *)e + e->target_offset) - base);
- t = (struct ebt_entry_target *)(((char *)e) + e->target_offset);
+ t = ebt_get_target_c(e);
ret = EBT_MATCH_ITERATE(e, ebt_match_to_user, base, ubase);
if (ret != 0)
return ret;
target_offset = e->target_offset - (origsize - *size);
- t = (struct ebt_entry_target *) ((char *) e + e->target_offset);
+ t = ebt_get_target(e);
ret = compat_target_to_user(t, dstptr, size);
if (ret)
EBT_MATCH_ITERATE(e, compat_calc_match, &off);
EBT_WATCHER_ITERATE(e, compat_calc_watcher, &off);
- t = (const struct ebt_entry_target *) ((char *) e + e->target_offset);
+ t = ebt_get_target_c(e);
off += xt_compat_target_offset(t->u.target);
off += ebt_compat_entry_padsize();
{
unsigned int size = info->entries_size;
const void *entries = info->entries;
- int ret;
newinfo->entries_size = size;
-
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
- if (ret)
- return ret;
+ if (info->nentries) {
+ int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+ info->nentries);
+ if (ret)
+ return ret;
+ }
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
+++ /dev/null
-/*
- * Copyright (c) 2014 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nft_meta.h>
-
-#include "../br_private.h"
-
-static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
-{
- const struct nft_meta *priv = nft_expr_priv(expr);
- const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
- u32 *dest = ®s->data[priv->dreg];
- const struct net_bridge_port *p;
-
- switch (priv->key) {
- case NFT_META_BRI_IIFNAME:
- if (in == NULL || (p = br_port_get_rcu(in)) == NULL)
- goto err;
- break;
- case NFT_META_BRI_OIFNAME:
- if (out == NULL || (p = br_port_get_rcu(out)) == NULL)
- goto err;
- break;
- default:
- goto out;
- }
-
- strncpy((char *)dest, p->br->dev->name, IFNAMSIZ);
- return;
-out:
- return nft_meta_get_eval(expr, regs, pkt);
-err:
- regs->verdict.code = NFT_BREAK;
-}
-
-static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
-{
- struct nft_meta *priv = nft_expr_priv(expr);
- unsigned int len;
-
- priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
- switch (priv->key) {
- case NFT_META_BRI_IIFNAME:
- case NFT_META_BRI_OIFNAME:
- len = IFNAMSIZ;
- break;
- default:
- return nft_meta_get_init(ctx, expr, tb);
- }
-
- priv->dreg = nft_parse_register(tb[NFTA_META_DREG]);
- return nft_validate_register_store(ctx, priv->dreg, NULL,
- NFT_DATA_VALUE, len);
-}
-
-static struct nft_expr_type nft_meta_bridge_type;
-static const struct nft_expr_ops nft_meta_bridge_get_ops = {
- .type = &nft_meta_bridge_type,
- .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)),
- .eval = nft_meta_bridge_get_eval,
- .init = nft_meta_bridge_get_init,
- .dump = nft_meta_get_dump,
-};
-
-static const struct nft_expr_ops nft_meta_bridge_set_ops = {
- .type = &nft_meta_bridge_type,
- .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)),
- .eval = nft_meta_set_eval,
- .init = nft_meta_set_init,
- .destroy = nft_meta_set_destroy,
- .dump = nft_meta_set_dump,
- .validate = nft_meta_set_validate,
-};
-
-static const struct nft_expr_ops *
-nft_meta_bridge_select_ops(const struct nft_ctx *ctx,
- const struct nlattr * const tb[])
-{
- if (tb[NFTA_META_KEY] == NULL)
- return ERR_PTR(-EINVAL);
-
- if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
- return ERR_PTR(-EINVAL);
-
- if (tb[NFTA_META_DREG])
- return &nft_meta_bridge_get_ops;
-
- if (tb[NFTA_META_SREG])
- return &nft_meta_bridge_set_ops;
-
- return ERR_PTR(-EINVAL);
-}
-
-static struct nft_expr_type nft_meta_bridge_type __read_mostly = {
- .family = NFPROTO_BRIDGE,
- .name = "meta",
- .select_ops = nft_meta_bridge_select_ops,
- .policy = nft_meta_policy,
- .maxattr = NFTA_META_MAX,
- .owner = THIS_MODULE,
-};
-
-static int __init nft_meta_bridge_module_init(void)
-{
- return nft_register_expr(&nft_meta_bridge_type);
-}
-
-static void __exit nft_meta_bridge_module_exit(void)
-{
- nft_unregister_expr(&nft_meta_bridge_type);
-}
-
-module_init(nft_meta_bridge_module_init);
-module_exit(nft_meta_bridge_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
-MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta");
int ret = 1;
dout("try_write start %p state %lu\n", con, con->state);
+ if (con->state != CON_STATE_PREOPEN &&
+ con->state != CON_STATE_CONNECTING &&
+ con->state != CON_STATE_NEGOTIATING &&
+ con->state != CON_STATE_OPEN)
+ return 0;
more:
dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
}
more_kvec:
+ BUG_ON(!con->sock);
+
/* kvec data queued? */
if (con->out_kvec_left) {
ret = write_partial_kvec(con);
__open_session(monc);
}
+static void un_backoff(struct ceph_mon_client *monc)
+{
+ monc->hunt_mult /= 2; /* reduce by 50% */
+ if (monc->hunt_mult < 1)
+ monc->hunt_mult = 1;
+ dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult);
+}
+
/*
* Reschedule delayed work timer.
*/
if (!monc->hunting) {
ceph_con_keepalive(&monc->con);
__validate_auth(monc);
+ un_backoff(monc);
}
if (is_auth &&
dout("%s found mon%d\n", __func__, monc->cur_mon);
monc->hunting = false;
monc->had_a_connection = true;
- monc->hunt_mult /= 2; /* reduce by 50% */
- if (monc->hunt_mult < 1)
- monc->hunt_mult = 1;
+ un_backoff(monc);
+ __schedule_delayed(monc);
}
}
#endif /* CONFIG_BLOCK */
static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
- struct ceph_bvec_iter *bvec_pos)
+ struct ceph_bvec_iter *bvec_pos,
+ u32 num_bvecs)
{
osd_data->type = CEPH_OSD_DATA_TYPE_BVECS;
osd_data->bvec_pos = *bvec_pos;
+ osd_data->num_bvecs = num_bvecs;
}
#define osd_req_op_data(oreq, whch, typ, fld) \
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
#endif /* CONFIG_BLOCK */
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes)
+{
+ struct ceph_osd_data *osd_data;
+ struct ceph_bvec_iter it = {
+ .bvecs = bvecs,
+ .iter = { .bi_size = bytes },
+ };
+
+ osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
+ ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
+}
+EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs);
+
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
unsigned int which,
struct ceph_bvec_iter *bvec_pos)
struct ceph_osd_data *osd_data;
osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
- ceph_osd_data_bvecs_init(osd_data, bvec_pos);
+ ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);
void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
unsigned int which,
- struct bio_vec *bvecs, u32 bytes)
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes)
{
struct ceph_osd_data *osd_data;
struct ceph_bvec_iter it = {
};
osd_data = osd_req_op_data(osd_req, which, cls, request_data);
- ceph_osd_data_bvecs_init(osd_data, &it);
+ ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
osd_req->r_ops[which].cls.indata_len += bytes;
osd_req->r_ops[which].indata_len += bytes;
}
optname == SO_ATTACH_REUSEPORT_CBPF)
return do_set_attach_filter(sock, level, optname,
optval, optlen);
- if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+ if (!COMPAT_USE_64BIT_TIME &&
+ (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
return do_set_sock_timeout(sock, level, optname, optval, optlen);
return sock_setsockopt(sock, level, optname, optval, optlen);
static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
- if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+ if (!COMPAT_USE_64BIT_TIME &&
+ (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
return do_get_sock_timeout(sock, level, optname, optval, optlen);
return sock_getsockopt(sock, level, optname, optval, optlen);
}
N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
- };
+ }
#undef N
return "UNKNOWN_NETDEV_EVENT";
}
EXPORT_SYMBOL(call_netdevice_notifiers);
#ifdef CONFIG_NET_INGRESS
-static struct static_key ingress_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);
void net_inc_ingress_queue(void)
{
- static_key_slow_inc(&ingress_needed);
+ static_branch_inc(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
void net_dec_ingress_queue(void)
{
- static_key_slow_dec(&ingress_needed);
+ static_branch_dec(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
#endif
#ifdef CONFIG_NET_EGRESS
-static struct static_key egress_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(egress_needed_key);
void net_inc_egress_queue(void)
{
- static_key_slow_inc(&egress_needed);
+ static_branch_inc(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_egress_queue);
void net_dec_egress_queue(void)
{
- static_key_slow_dec(&egress_needed);
+ static_branch_dec(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_egress_queue);
#endif
-static struct static_key netstamp_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
#ifdef HAVE_JUMP_LABEL
static atomic_t netstamp_needed_deferred;
static atomic_t netstamp_wanted;
wanted = atomic_add_return(deferred, &netstamp_wanted);
if (wanted > 0)
- static_key_enable(&netstamp_needed);
+ static_branch_enable(&netstamp_needed_key);
else
- static_key_disable(&netstamp_needed);
+ static_branch_disable(&netstamp_needed_key);
}
static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif
atomic_inc(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
- static_key_slow_inc(&netstamp_needed);
+ static_branch_inc(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_enable_timestamp);
atomic_dec(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
- static_key_slow_dec(&netstamp_needed);
+ static_branch_dec(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp_set(struct sk_buff *skb)
{
skb->tstamp = 0;
- if (static_key_false(&netstamp_needed))
+ if (static_branch_unlikely(&netstamp_needed_key))
__net_timestamp(skb);
}
-#define net_timestamp_check(COND, SKB) \
- if (static_key_false(&netstamp_needed)) { \
- if ((COND) && !(SKB)->tstamp) \
- __net_timestamp(SKB); \
- } \
+#define net_timestamp_check(COND, SKB) \
+ if (static_branch_unlikely(&netstamp_needed_key)) { \
+ if ((COND) && !(SKB)->tstamp) \
+ __net_timestamp(SKB); \
+ } \
bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
{
int i, j;
for (i = count, j = offset; i--; j++) {
- if (!remove_xps_queue(dev_maps, cpu, j))
+ if (!remove_xps_queue(dev_maps, tci, j))
break;
}
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
* to be used as a distribution range.
*/
-u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
- unsigned int num_tx_queues)
+static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
{
u32 hash;
u16 qoffset = 0;
- u16 qcount = num_tx_queues;
+ u16 qcount = dev->real_num_tx_queues;
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
- while (unlikely(hash >= num_tx_queues))
- hash -= num_tx_queues;
+ while (unlikely(hash >= qcount))
+ hash -= qcount;
return hash;
}
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
-EXPORT_SYMBOL(__skb_tx_hash);
static void skb_warn_bad_offload(const struct sk_buff *skb)
{
if (unlikely(!skb))
goto out_null;
+ skb = sk_validate_xmit_skb(skb, dev);
+ if (unlikely(!skb))
+ goto out_null;
+
if (netif_needs_gso(skb, features)) {
struct sk_buff *segs;
rc = NET_XMIT_DROP;
} else {
rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
- __qdisc_run(q);
+ qdisc_run(q);
}
if (unlikely(to_free))
#ifdef CONFIG_NET_CLS_ACT
skb->tc_at_ingress = 0;
# ifdef CONFIG_NET_EGRESS
- if (static_key_false(&egress_needed)) {
+ if (static_branch_unlikely(&egress_needed_key)) {
skb = sch_handle_egress(skb, &rc, dev);
if (!skb)
goto out;
}
EXPORT_SYMBOL(dev_queue_xmit_accel);
+int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+ struct net_device *dev = skb->dev;
+ struct sk_buff *orig_skb = skb;
+ struct netdev_queue *txq;
+ int ret = NETDEV_TX_BUSY;
+ bool again = false;
+
+ if (unlikely(!netif_running(dev) ||
+ !netif_carrier_ok(dev)))
+ goto drop;
+
+ skb = validate_xmit_skb_list(skb, dev, &again);
+ if (skb != orig_skb)
+ goto drop;
+
+ skb_set_queue_mapping(skb, queue_id);
+ txq = skb_get_tx_queue(dev, skb);
+
+ local_bh_disable();
+
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_xmit_frozen_or_drv_stopped(txq))
+ ret = netdev_start_xmit(skb, dev, txq, false);
+ HARD_TX_UNLOCK(dev, txq);
+
+ local_bh_enable();
+
+ if (!dev_xmit_complete(ret))
+ kfree_skb(skb);
+
+ return ret;
+drop:
+ atomic_long_inc(&dev->tx_dropped);
+ kfree_skb_list(skb);
+ return NET_XMIT_DROP;
+}
+EXPORT_SYMBOL(dev_direct_xmit);
/*************************************************************************
* Receiver routines
}
static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+ struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct netdev_rx_queue *rxqueue;
void *orig_data, *orig_data_end;
u32 metalen, act = XDP_DROP;
- struct xdp_buff xdp;
int hlen, off;
u32 mac_len;
*/
mac_len = skb->data - skb_mac_header(skb);
hlen = skb_headlen(skb) + mac_len;
- xdp.data = skb->data - mac_len;
- xdp.data_meta = xdp.data;
- xdp.data_end = xdp.data + hlen;
- xdp.data_hard_start = skb->data - skb_headroom(skb);
- orig_data_end = xdp.data_end;
- orig_data = xdp.data;
+ xdp->data = skb->data - mac_len;
+ xdp->data_meta = xdp->data;
+ xdp->data_end = xdp->data + hlen;
+ xdp->data_hard_start = skb->data - skb_headroom(skb);
+ orig_data_end = xdp->data_end;
+ orig_data = xdp->data;
rxqueue = netif_get_rxqueue(skb);
- xdp.rxq = &rxqueue->xdp_rxq;
+ xdp->rxq = &rxqueue->xdp_rxq;
- act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
- off = xdp.data - orig_data;
+ off = xdp->data - orig_data;
if (off > 0)
__skb_pull(skb, off);
else if (off < 0)
/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
* pckt.
*/
- off = orig_data_end - xdp.data_end;
- if (off != 0)
- skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
+ off = orig_data_end - xdp->data_end;
+ if (off != 0) {
+ skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
+ skb->len -= off;
+
+ }
switch (act) {
case XDP_REDIRECT:
__skb_push(skb, mac_len);
break;
case XDP_PASS:
- metalen = xdp.data - xdp.data_meta;
+ metalen = xdp->data - xdp->data_meta;
if (metalen)
skb_metadata_set(skb, metalen);
break;
}
EXPORT_SYMBOL_GPL(generic_xdp_tx);
-static struct static_key generic_xdp_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
{
if (xdp_prog) {
- u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+ struct xdp_buff xdp;
+ u32 act;
int err;
+ act = netif_receive_generic_xdp(skb, &xdp, xdp_prog);
if (act != XDP_PASS) {
switch (act) {
case XDP_REDIRECT:
err = xdp_do_generic_redirect(skb->dev, skb,
- xdp_prog);
+ &xdp, xdp_prog);
if (err)
goto out_redir;
- /* fallthru to submit skb */
+ break;
case XDP_TX:
generic_xdp_tx(skb, xdp_prog);
break;
trace_netif_rx(skb);
- if (static_key_false(&generic_xdp_needed)) {
+ if (static_branch_unlikely(&generic_xdp_needed_key)) {
int ret;
preempt_disable();
skip_taps:
#ifdef CONFIG_NET_INGRESS
- if (static_key_false(&ingress_needed)) {
+ if (static_branch_unlikely(&ingress_needed_key)) {
skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto out;
bpf_prog_put(old);
if (old && !new) {
- static_key_slow_dec(&generic_xdp_needed);
+ static_branch_dec(&generic_xdp_needed_key);
} else if (new && !old) {
- static_key_slow_inc(&generic_xdp_needed);
+ static_branch_inc(&generic_xdp_needed_key);
dev_disable_lro(dev);
dev_disable_gro_hw(dev);
}
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
- if (static_key_false(&generic_xdp_needed)) {
+ if (static_branch_unlikely(&generic_xdp_needed_key)) {
int ret;
preempt_disable();
int ret;
struct net *net = dev_net(dev);
+ BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE <
+ NETDEV_FEATURE_COUNT);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
}
+static int devlink_nl_port_attrs_put(struct sk_buff *msg,
+ struct devlink_port *devlink_port)
+{
+ struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+ if (!attrs->set)
+ return 0;
+ if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
+ return -EMSGSIZE;
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->port_number))
+ return -EMSGSIZE;
+ if (!attrs->split)
+ return 0;
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->port_number))
+ return -EMSGSIZE;
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
+ attrs->split_subport_number))
+ return -EMSGSIZE;
+ return 0;
+}
+
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_port *devlink_port,
enum devlink_command cmd, u32 portid,
ibdev->name))
goto nla_put_failure;
}
- if (devlink_port->split &&
- nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
- devlink_port->split_group))
+ if (devlink_nl_port_attrs_put(msg, devlink_port))
goto nla_put_failure;
genlmsg_end(msg, hdr);
EXPORT_SYMBOL_GPL(devlink_port_type_clear);
/**
- * devlink_port_split_set - Set port is split
+ * devlink_port_attrs_set - Set port attributes
*
* @devlink_port: devlink port
- * @split_group: split group - identifies group split port is part of
+ * @flavour: flavour of the port
+ * @port_number: number of the port that is facing user, for example
+ * the front panel port number
+ * @split: indicates if this is split port
+ * @split_subport_number: if the port is split, this is the number
+ * of subport.
*/
-void devlink_port_split_set(struct devlink_port *devlink_port,
- u32 split_group)
-{
- devlink_port->split = true;
- devlink_port->split_group = split_group;
+void devlink_port_attrs_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 port_number, bool split,
+ u32 split_subport_number)
+{
+ struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+ attrs->set = true;
+ attrs->flavour = flavour;
+ attrs->port_number = port_number;
+ attrs->split = split;
+ attrs->split_subport_number = split_subport_number;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
-EXPORT_SYMBOL_GPL(devlink_port_split_set);
+EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
+
+int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
+ char *name, size_t len)
+{
+ struct devlink_port_attrs *attrs = &devlink_port->attrs;
+ int n = 0;
+
+ if (!attrs->set)
+ return -EOPNOTSUPP;
+
+ switch (attrs->flavour) {
+ case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+ if (!attrs->split)
+ n = snprintf(name, len, "p%u", attrs->port_number);
+ else
+ n = snprintf(name, len, "p%us%u", attrs->port_number,
+ attrs->split_subport_number);
+ break;
+ case DEVLINK_PORT_FLAVOUR_CPU:
+ case DEVLINK_PORT_FLAVOUR_DSA:
+ /* As CPU and DSA ports do not have a netdevice associated
+ * case should not ever happen.
+ */
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ if (n >= len)
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_port_get_phys_port_name);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
[NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial",
[NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation",
[NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation",
+ [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp",
[NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload",
[NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload",
[NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record",
+ [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload",
};
static const char
return ret;
}
-static int phy_get_sset_count(struct phy_device *phydev)
-{
- int ret;
-
- if (phydev->drv->get_sset_count &&
- phydev->drv->get_strings &&
- phydev->drv->get_stats) {
- mutex_lock(&phydev->lock);
- ret = phydev->drv->get_sset_count(phydev);
- mutex_unlock(&phydev->lock);
-
- return ret;
- }
-
- return -EOPNOTSUPP;
-}
-
static int __ethtool_get_sset_count(struct net_device *dev, int sset)
{
const struct ethtool_ops *ops = dev->ethtool_ops;
if (sset == ETH_SS_PHY_TUNABLES)
return ARRAY_SIZE(phy_tunable_strings);
- if (sset == ETH_SS_PHY_STATS) {
- if (dev->phydev)
- return phy_get_sset_count(dev->phydev);
- else
- return -EOPNOTSUPP;
- }
+ if (sset == ETH_SS_PHY_STATS && dev->phydev &&
+ !ops->get_ethtool_phy_stats)
+ return phy_ethtool_get_sset_count(dev->phydev);
if (ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
memcpy(data, tunable_strings, sizeof(tunable_strings));
else if (stringset == ETH_SS_PHY_TUNABLES)
memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings));
- else if (stringset == ETH_SS_PHY_STATS) {
- struct phy_device *phydev = dev->phydev;
-
- if (phydev) {
- mutex_lock(&phydev->lock);
- phydev->drv->get_strings(phydev, data);
- mutex_unlock(&phydev->lock);
- } else {
- return;
- }
- } else
+ else if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
+ !ops->get_ethtool_phy_stats)
+ phy_ethtool_get_strings(dev->phydev, data);
+ else
/* ops->get_strings is valid because checked earlier */
ops->get_strings(dev, stringset, data);
}
info_size = sizeof(info);
if (copy_from_user(&info, useraddr, info_size))
return -EFAULT;
+ /* Since malicious users may modify the original data,
+ * we need to check whether FLOW_RSS is still requested.
+ */
+ if (!(info.flow_type & FLOW_RSS))
+ return -EINVAL;
}
if (info.cmd == ETHTOOL_GRXCLSRLALL) {
static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
{
- struct ethtool_stats stats;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
struct phy_device *phydev = dev->phydev;
+ struct ethtool_stats stats;
u64 *data;
int ret, n_stats;
- if (!phydev)
+ if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
return -EOPNOTSUPP;
- n_stats = phy_get_sset_count(phydev);
+ if (dev->phydev && !ops->get_ethtool_phy_stats)
+ n_stats = phy_ethtool_get_sset_count(dev->phydev);
+ else
+ n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
if (n_stats < 0)
return n_stats;
if (n_stats > S32_MAX / sizeof(u64))
if (n_stats && !data)
return -ENOMEM;
- mutex_lock(&phydev->lock);
- phydev->drv->get_stats(phydev, &stats, data);
- mutex_unlock(&phydev->lock);
+ if (dev->phydev && !ops->get_ethtool_phy_stats) {
+ ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+ if (ret < 0)
+ return ret;
+ } else {
+ ops->get_ethtool_phy_stats(dev, &stats, data);
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
return NULL;
}
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
+ struct netlink_ext_ack *extack)
+{
+ nlrule->l3mdev = nla_get_u8(nla);
+ if (nlrule->l3mdev != 1) {
+ NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute");
+ return -1;
+ }
+
+ return 0;
+}
+#else
+static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
+ struct netlink_ext_ack *extack)
+{
+ NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel");
+ return -1;
+}
+#endif
+
static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack,
struct fib_rules_ops *ops,
nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
err = -EINVAL;
- if (tb[FRA_L3MDEV]) {
-#ifdef CONFIG_NET_L3_MASTER_DEV
- nlrule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
- if (nlrule->l3mdev != 1)
-#endif
- {
- NL_SET_ERR_MSG(extack, "Invalid l3mdev");
- goto errout_free;
- }
- }
+ if (tb[FRA_L3MDEV] &&
+ fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0)
+ goto errout_free;
nlrule->action = frh->action;
nlrule->flags = frh->flags;
#include <net/sock_reuseport.h>
#include <net/busy_poll.h>
#include <net/tcp.h>
+#include <net/xfrm.h>
#include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
+#include <linux/inetdevice.h>
+#include <net/ip_fib.h>
+#include <net/flow.h>
+#include <net/arp.h>
/**
* sk_filter_trim_cap - run a packet through a socket filter
}
EXPORT_SYMBOL(sk_filter_trim_cap);
-BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb)
+BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb)
{
return skb_get_poff(skb);
}
-BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
return 0;
}
-BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
{
struct nlattr *nla;
return 0;
}
-BPF_CALL_0(__get_raw_cpu_id)
+BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u8 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (offset >= 0) {
+ if (headlen - offset >= len)
+ return *(u8 *)(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return tmp;
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return *(u8 *)ptr;
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u16 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (offset >= 0) {
+ if (headlen - offset >= len)
+ return get_unaligned_be16(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be16_to_cpu(tmp);
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return get_unaligned_be16(ptr);
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
+ data, int, headlen, int, offset)
+{
+ u32 tmp, *ptr;
+ const int len = sizeof(tmp);
+
+ if (likely(offset >= 0)) {
+ if (headlen - offset >= len)
+ return get_unaligned_be32(data + offset);
+ if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+ return be32_to_cpu(tmp);
+ } else {
+ ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+ if (likely(ptr))
+ return get_unaligned_be32(ptr);
+ }
+
+ return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
+ int, offset)
+{
+ return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len,
+ offset);
+}
+
+BPF_CALL_0(bpf_get_raw_cpu_id)
{
return raw_smp_processor_id();
}
static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
- .func = __get_raw_cpu_id,
+ .func = bpf_get_raw_cpu_id,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
/* Emit call(arg1=CTX, arg2=A, arg3=X) */
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
- *insn = BPF_EMIT_CALL(__skb_get_pay_offset);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset);
break;
case SKF_AD_OFF + SKF_AD_NLATTR:
- *insn = BPF_EMIT_CALL(__skb_get_nlattr);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr);
break;
case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
- *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
+ *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest);
break;
case SKF_AD_OFF + SKF_AD_CPU:
- *insn = BPF_EMIT_CALL(__get_raw_cpu_id);
+ *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
*insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
return true;
}
+static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
+{
+ const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS);
+ int size = bpf_size_to_bytes(BPF_SIZE(fp->code));
+ bool endian = BPF_SIZE(fp->code) == BPF_H ||
+ BPF_SIZE(fp->code) == BPF_W;
+ bool indirect = BPF_MODE(fp->code) == BPF_IND;
+ const int ip_align = NET_IP_ALIGN;
+ struct bpf_insn *insn = *insnp;
+ int offset = fp->k;
+
+ if (!indirect &&
+ ((unaligned_ok && offset >= 0) ||
+ (!unaligned_ok && offset >= 0 &&
+ offset + ip_align >= 0 &&
+ offset + ip_align % size == 0))) {
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
+ *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+ *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
+ *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
+ offset);
+ if (endian)
+ *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
+ *insn++ = BPF_JMP_A(8);
+ }
+
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D);
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H);
+ if (!indirect) {
+ *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X);
+ if (fp->k)
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset);
+ }
+
+ switch (BPF_SIZE(fp->code)) {
+ case BPF_B:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8);
+ break;
+ case BPF_H:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16);
+ break;
+ case BPF_W:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32);
+ break;
+ default:
+ return false;
+ }
+
+ *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2);
+ *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
+ *insn = BPF_EXIT_INSN();
+
+ *insnp = insn;
+ return true;
+}
+
/**
* bpf_convert_filter - convert filter program
* @prog: the user passed filter program
* @len: the length of the user passed filter program
* @new_prog: allocated 'struct bpf_prog' or NULL
* @new_len: pointer to store length of converted program
+ * @seen_ld_abs: bool whether we've seen ld_abs/ind
*
* Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
* style extended BPF (eBPF).
* Conversion workflow:
*
* 1) First pass for calculating the new program length:
- * bpf_convert_filter(old_prog, old_len, NULL, &new_len)
+ * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs)
*
* 2) 2nd pass to remap in two passes: 1st pass finds new
* jump offsets, 2nd pass remapping:
- * bpf_convert_filter(old_prog, old_len, new_prog, &new_len);
+ * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs)
*/
static int bpf_convert_filter(struct sock_filter *prog, int len,
- struct bpf_prog *new_prog, int *new_len)
+ struct bpf_prog *new_prog, int *new_len,
+ bool *seen_ld_abs)
{
int new_flen = 0, pass = 0, target, i, stack_off;
struct bpf_insn *new_insn, *first_insn = NULL;
* do this ourself. Initial CTX is present in BPF_REG_ARG1.
*/
*new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
+ if (*seen_ld_abs) {
+ /* For packet access in classic BPF, cache skb->data
+ * in callee-saved BPF R8 and skb->len - skb->data_len
+ * (headlen) in BPF R9. Since classic BPF is read-only
+ * on CTX, we only need to cache it once.
+ */
+ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+ BPF_REG_D, BPF_REG_CTX,
+ offsetof(struct sk_buff, data));
+ *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX,
+ offsetof(struct sk_buff, len));
+ *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX,
+ offsetof(struct sk_buff, data_len));
+ *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP);
+ }
} else {
new_insn += 3;
}
for (i = 0; i < len; fp++, i++) {
- struct bpf_insn tmp_insns[6] = { };
+ struct bpf_insn tmp_insns[32] = { };
struct bpf_insn *insn = tmp_insns;
if (addrs)
BPF_MODE(fp->code) == BPF_ABS &&
convert_bpf_extensions(fp, &insn))
break;
+ if (BPF_CLASS(fp->code) == BPF_LD &&
+ convert_bpf_ld_abs(fp, &insn)) {
+ *seen_ld_abs = true;
+ break;
+ }
if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) ||
fp->code == (BPF_ALU | BPF_MOD | BPF_X)) {
#define BPF_EMIT_JMP \
do { \
+ const s32 off_min = S16_MIN, off_max = S16_MAX; \
+ s32 off; \
+ \
if (target >= len || target < 0) \
goto err; \
- insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
+ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
/* Adjust pc relative offset for 2nd or 3rd insn. */ \
- insn->off -= insn - tmp_insns; \
+ off -= insn - tmp_insns; \
+ /* Reject anything not fitting into insn->off. */ \
+ if (off < off_min || off > off_max) \
+ goto err; \
+ insn->off = off; \
} while (0)
case BPF_JMP | BPF_JA:
break;
/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
- case BPF_LDX | BPF_MSH | BPF_B:
- /* tmp = A */
- *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
+ case BPF_LDX | BPF_MSH | BPF_B: {
+ struct sock_filter tmp = {
+ .code = BPF_LD | BPF_ABS | BPF_B,
+ .k = fp->k,
+ };
+
+ *seen_ld_abs = true;
+
+ /* X = A */
+ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = BPF_R0 = *(u8 *) (skb->data + K) */
- *insn++ = BPF_LD_ABS(BPF_B, fp->k);
+ convert_bpf_ld_abs(&tmp, &insn);
+ insn++;
/* A &= 0xf */
*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
/* A <<= 2 */
*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
+ /* tmp = X */
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X);
/* X = A */
*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = tmp */
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
-
+ }
/* RET_K is remaped into 2 insns. RET_A case doesn't need an
* extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
*/
if (!new_prog) {
/* Only calculating new length. */
*new_len = new_insn - first_insn;
+ if (*seen_ld_abs)
+ *new_len += 4; /* Prologue bits. */
return 0;
}
struct sock_filter *old_prog;
struct bpf_prog *old_fp;
int err, new_len, old_len = fp->len;
+ bool seen_ld_abs = false;
/* We are free to overwrite insns et al right here as it
* won't be used at this point in time anymore internally
}
/* 1st pass: calculate the new program length. */
- err = bpf_convert_filter(old_prog, old_len, NULL, &new_len);
+ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len,
+ &seen_ld_abs);
if (err)
goto out_err_free;
fp->len = new_len;
/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
- err = bpf_convert_filter(old_prog, old_len, fp, &new_len);
+ err = bpf_convert_filter(old_prog, old_len, fp, &new_len,
+ &seen_ld_abs);
if (err)
/* 2nd bpf_convert_filter() can fail only if it fails
* to allocate memory, remapping must succeed. Note,
.arg4_type = ARG_CONST_SIZE,
};
+BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
+ u32, offset, void *, to, u32, len, u32, start_header)
+{
+ u8 *ptr;
+
+ if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+ goto err_clear;
+
+ switch (start_header) {
+ case BPF_HDR_START_MAC:
+ ptr = skb_mac_header(skb) + offset;
+ break;
+ case BPF_HDR_START_NET:
+ ptr = skb_network_header(skb) + offset;
+ break;
+ default:
+ goto err_clear;
+ }
+
+ if (likely(ptr >= skb_mac_header(skb) &&
+ ptr + len <= skb_tail_pointer(skb))) {
+ memcpy(to, ptr, len);
+ return 0;
+ }
+
+err_clear:
+ memset(to, 0, len);
+ return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = {
+ .func = bpf_skb_load_bytes_relative,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
{
/* Idea is the following: should the needed direct read/write
.arg2_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
+ struct bpf_map *, map, void *, key, u64, flags)
+{
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+
+ /* If user passes invalid input drop the packet. */
+ if (unlikely(flags & ~(BPF_F_INGRESS)))
+ return SK_DROP;
+
+ tcb->bpf.flags = flags;
+ tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key);
+ if (!tcb->bpf.sk_redir)
+ return SK_DROP;
+
+ return SK_PASS;
+}
+
+static const struct bpf_func_proto bpf_sk_redirect_hash_proto = {
+ .func = bpf_sk_redirect_hash,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_PTR_TO_MAP_KEY,
+ .arg4_type = ARG_ANYTHING,
+};
+
BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
struct bpf_map *, map, u32, key, u64, flags)
{
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- tcb->bpf.key = key;
tcb->bpf.flags = flags;
- tcb->bpf.map = map;
+ tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key);
+ if (!tcb->bpf.sk_redir)
+ return SK_DROP;
return SK_PASS;
}
struct sock *do_sk_redirect_map(struct sk_buff *skb)
{
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
- struct sock *sk = NULL;
- if (tcb->bpf.map) {
- sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key);
-
- tcb->bpf.key = 0;
- tcb->bpf.map = NULL;
- }
-
- return sk;
+ return tcb->bpf.sk_redir;
}
static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
.arg4_type = ARG_ANYTHING,
};
-BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
- struct bpf_map *, map, u32, key, u64, flags)
+BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg_buff *, msg,
+ struct bpf_map *, map, void *, key, u64, flags)
{
/* If user passes invalid input drop the packet. */
if (unlikely(flags & ~(BPF_F_INGRESS)))
return SK_DROP;
- msg->key = key;
msg->flags = flags;
- msg->map = map;
+ msg->sk_redir = __sock_hash_lookup_elem(map, key);
+ if (!msg->sk_redir)
+ return SK_DROP;
return SK_PASS;
}
-struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+static const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
+ .func = bpf_msg_redirect_hash,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_PTR_TO_MAP_KEY,
+ .arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
+ struct bpf_map *, map, u32, key, u64, flags)
{
- struct sock *sk = NULL;
+ /* If user passes invalid input drop the packet. */
+ if (unlikely(flags & ~(BPF_F_INGRESS)))
+ return SK_DROP;
- if (msg->map) {
- sk = __sock_map_lookup_elem(msg->map, msg->key);
+ msg->flags = flags;
+ msg->sk_redir = __sock_map_lookup_elem(map, key);
+ if (!msg->sk_redir)
+ return SK_DROP;
- msg->key = 0;
- msg->map = NULL;
- }
+ return SK_PASS;
+}
- return sk;
+struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+{
+ return msg->sk_redir;
}
static const struct bpf_func_proto bpf_msg_redirect_map_proto = {
return ret;
}
-const struct bpf_func_proto bpf_skb_vlan_push_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_push_proto = {
.func = bpf_skb_vlan_push,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto);
BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
{
return ret;
}
-const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
.func = bpf_skb_vlan_pop,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
};
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
{
{
int err;
- if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP: {
struct net_device *dev = fwd;
struct xdp_frame *xdpf;
if (err)
return err;
__dev_map_insert_ctx(map, index);
-
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ break;
+ }
+ case BPF_MAP_TYPE_CPUMAP: {
struct bpf_cpu_map_entry *rcpu = fwd;
err = cpu_map_enqueue(rcpu, xdp, dev_rx);
if (err)
return err;
__cpu_map_insert_ctx(map, index);
+ break;
+ }
+ case BPF_MAP_TYPE_XSKMAP: {
+ struct xdp_sock *xs = fwd;
+
+ err = __xsk_map_redirect(map, xdp, xs);
+ return err;
+ }
+ default:
+ break;
}
return 0;
}
case BPF_MAP_TYPE_CPUMAP:
__cpu_map_flush(map);
break;
+ case BPF_MAP_TYPE_XSKMAP:
+ __xsk_map_flush(map);
+ break;
default:
break;
}
return __dev_map_lookup_elem(map, index);
case BPF_MAP_TYPE_CPUMAP:
return __cpu_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_XSKMAP:
+ return __xsk_map_lookup_elem(map, index);
default:
return NULL;
}
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
+ struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err = 0;
ri->ifindex = 0;
if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
goto err;
skb->dev = fwd;
+ generic_xdp_tx(skb, xdp_prog);
+ } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+ struct xdp_sock *xs = fwd;
+
+ err = xsk_generic_rcv(xs, xdp);
+ if (err)
+ goto err;
+ consume_skb(skb);
} else {
/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
err = -EBADRQC;
}
int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+ struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
u32 index = ri->ifindex;
int err = 0;
if (ri->map)
- return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+ return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog);
ri->ifindex = 0;
fwd = dev_get_by_index_rcu(dev_net(dev), index);
skb->dev = fwd;
_trace_xdp_redirect(dev, xdp_prog, index);
+ generic_xdp_tx(skb, xdp_prog);
return 0;
err:
_trace_xdp_redirect_err(dev, xdp_prog, index, err);
skb_dst_set(skb, (struct dst_entry *) md);
info = &md->u.tun_info;
+ memset(info, 0, sizeof(*info));
info->mode = IP_TUNNEL_INFO_TX;
info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
.arg3_type = ARG_CONST_SIZE,
};
+#ifdef CONFIG_XFRM
+BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index,
+ struct bpf_xfrm_state *, to, u32, size, u64, flags)
+{
+ const struct sec_path *sp = skb_sec_path(skb);
+ const struct xfrm_state *x;
+
+ if (!sp || unlikely(index >= sp->len || flags))
+ goto err_clear;
+
+ x = sp->xvec[index];
+
+ if (unlikely(size != sizeof(struct bpf_xfrm_state)))
+ goto err_clear;
+
+ to->reqid = x->props.reqid;
+ to->spi = x->id.spi;
+ to->family = x->props.family;
+ if (to->family == AF_INET6) {
+ memcpy(to->remote_ipv6, x->props.saddr.a6,
+ sizeof(to->remote_ipv6));
+ } else {
+ to->remote_ipv4 = x->props.saddr.a4;
+ }
+
+ return 0;
+err_clear:
+ memset(to, 0, size);
+ return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
+ .func = bpf_skb_get_xfrm_state,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+ .arg5_type = ARG_ANYTHING,
+};
+#endif
+
+#if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
+static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
+ const struct neighbour *neigh,
+ const struct net_device *dev)
+{
+ memcpy(params->dmac, neigh->ha, ETH_ALEN);
+ memcpy(params->smac, dev->dev_addr, ETH_ALEN);
+ params->h_vlan_TCI = 0;
+ params->h_vlan_proto = 0;
+
+ return dev->ifindex;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
+ u32 flags)
+{
+ struct in_device *in_dev;
+ struct neighbour *neigh;
+ struct net_device *dev;
+ struct fib_result res;
+ struct fib_nh *nh;
+ struct flowi4 fl4;
+ int err;
+
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ /* verify forwarding is enabled on this interface */
+ in_dev = __in_dev_get_rcu(dev);
+ if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
+ return 0;
+
+ if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+ fl4.flowi4_iif = 1;
+ fl4.flowi4_oif = params->ifindex;
+ } else {
+ fl4.flowi4_iif = params->ifindex;
+ fl4.flowi4_oif = 0;
+ }
+ fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+ fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+ fl4.flowi4_flags = 0;
+
+ fl4.flowi4_proto = params->l4_protocol;
+ fl4.daddr = params->ipv4_dst;
+ fl4.saddr = params->ipv4_src;
+ fl4.fl4_sport = params->sport;
+ fl4.fl4_dport = params->dport;
+
+ if (flags & BPF_FIB_LOOKUP_DIRECT) {
+ u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+ struct fib_table *tb;
+
+ tb = fib_get_table(net, tbid);
+ if (unlikely(!tb))
+ return 0;
+
+ err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
+ } else {
+ fl4.flowi4_mark = 0;
+ fl4.flowi4_secid = 0;
+ fl4.flowi4_tun_key.tun_id = 0;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+ err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
+ }
+
+ if (err || res.type != RTN_UNICAST)
+ return 0;
+
+ if (res.fi->fib_nhs > 1)
+ fib_select_path(net, &res, &fl4, NULL);
+
+ nh = &res.fi->fib_nh[res.nh_sel];
+
+ /* do not handle lwt encaps right now */
+ if (nh->nh_lwtstate)
+ return 0;
+
+ dev = nh->nh_dev;
+ if (unlikely(!dev))
+ return 0;
+
+ if (nh->nh_gw)
+ params->ipv4_dst = nh->nh_gw;
+
+ params->rt_metric = res.fi->fib_priority;
+
+ /* xdp and cls_bpf programs are run in RCU-bh so
+ * rcu_read_lock_bh is not needed here
+ */
+ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
+ if (neigh)
+ return bpf_fib_set_fwd_params(params, neigh, dev);
+
+ return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
+ u32 flags)
+{
+ struct in6_addr *src = (struct in6_addr *) params->ipv6_src;
+ struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst;
+ struct neighbour *neigh;
+ struct net_device *dev;
+ struct inet6_dev *idev;
+ struct fib6_info *f6i;
+ struct flowi6 fl6;
+ int strict = 0;
+ int oif;
+
+ /* link local addresses are never forwarded */
+ if (rt6_need_strict(dst) || rt6_need_strict(src))
+ return 0;
+
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ idev = __in6_dev_get_safely(dev);
+ if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
+ return 0;
+
+ if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+ fl6.flowi6_iif = 1;
+ oif = fl6.flowi6_oif = params->ifindex;
+ } else {
+ oif = fl6.flowi6_iif = params->ifindex;
+ fl6.flowi6_oif = 0;
+ strict = RT6_LOOKUP_F_HAS_SADDR;
+ }
+ fl6.flowlabel = params->flowlabel;
+ fl6.flowi6_scope = 0;
+ fl6.flowi6_flags = 0;
+ fl6.mp_hash = 0;
+
+ fl6.flowi6_proto = params->l4_protocol;
+ fl6.daddr = *dst;
+ fl6.saddr = *src;
+ fl6.fl6_sport = params->sport;
+ fl6.fl6_dport = params->dport;
+
+ if (flags & BPF_FIB_LOOKUP_DIRECT) {
+ u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+ struct fib6_table *tb;
+
+ tb = ipv6_stub->fib6_get_table(net, tbid);
+ if (unlikely(!tb))
+ return 0;
+
+ f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+ } else {
+ fl6.flowi6_mark = 0;
+ fl6.flowi6_secid = 0;
+ fl6.flowi6_tun_key.tun_id = 0;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
+
+ f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+ }
+
+ if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+ return 0;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT ||
+ f6i->fib6_type != RTN_UNICAST))
+ return 0;
+
+ if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
+ f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
+ fl6.flowi6_oif, NULL,
+ strict);
+
+ if (f6i->fib6_nh.nh_lwtstate)
+ return 0;
+
+ if (f6i->fib6_flags & RTF_GATEWAY)
+ *dst = f6i->fib6_nh.nh_gw;
+
+ dev = f6i->fib6_nh.nh_dev;
+ params->rt_metric = f6i->fib6_metric;
+
+ /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
+ * not needed here. Can not use __ipv6_neigh_lookup_noref here
+ * because we need to get nd_tbl via the stub
+ */
+ neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+ ndisc_hashfn, dst, dev);
+ if (neigh)
+ return bpf_fib_set_fwd_params(params, neigh, dev);
+
+ return 0;
+}
+#endif
+
+BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
+ struct bpf_fib_lookup *, params, int, plen, u32, flags)
+{
+ if (plen < sizeof(*params))
+ return -EINVAL;
+
+ switch (params->family) {
+#if IS_ENABLED(CONFIG_INET)
+ case AF_INET:
+ return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params,
+ flags);
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params,
+ flags);
+#endif
+ }
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = {
+ .func = bpf_xdp_fib_lookup,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
+ struct bpf_fib_lookup *, params, int, plen, u32, flags)
+{
+ if (plen < sizeof(*params))
+ return -EINVAL;
+
+ switch (params->family) {
+#if IS_ENABLED(CONFIG_INET)
+ case AF_INET:
+ return bpf_ipv4_fib_lookup(dev_net(skb->dev), params, flags);
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ return bpf_ipv6_fib_lookup(dev_net(skb->dev), params, flags);
+#endif
+ }
+ return -ENOTSUPP;
+}
+
+static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
+ .func = bpf_skb_fib_lookup,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_skb_load_bytes_relative:
+ return &bpf_skb_load_bytes_relative_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
return &bpf_skb_store_bytes_proto;
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_skb_load_bytes_relative:
+ return &bpf_skb_load_bytes_relative_proto;
case BPF_FUNC_skb_pull_data:
return &bpf_skb_pull_data_proto;
case BPF_FUNC_csum_diff:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
return &bpf_get_socket_uid_proto;
+#ifdef CONFIG_XFRM
+ case BPF_FUNC_skb_get_xfrm_state:
+ return &bpf_skb_get_xfrm_state_proto;
+#endif
+ case BPF_FUNC_fib_lookup:
+ return &bpf_skb_fib_lookup_proto;
default:
return bpf_base_func_proto(func_id);
}
return &bpf_xdp_redirect_map_proto;
case BPF_FUNC_xdp_adjust_tail:
return &bpf_xdp_adjust_tail_proto;
+ case BPF_FUNC_fib_lookup:
+ return &bpf_xdp_fib_lookup_proto;
default:
return bpf_base_func_proto(func_id);
}
return &bpf_sock_ops_cb_flags_set_proto;
case BPF_FUNC_sock_map_update:
return &bpf_sock_map_update_proto;
+ case BPF_FUNC_sock_hash_update:
+ return &bpf_sock_hash_update_proto;
default:
return bpf_base_func_proto(func_id);
}
switch (func_id) {
case BPF_FUNC_msg_redirect_map:
return &bpf_msg_redirect_map_proto;
+ case BPF_FUNC_msg_redirect_hash:
+ return &bpf_msg_redirect_hash_proto;
case BPF_FUNC_msg_apply_bytes:
return &bpf_msg_apply_bytes_proto;
case BPF_FUNC_msg_cork_bytes:
return &bpf_get_socket_uid_proto;
case BPF_FUNC_sk_redirect_map:
return &bpf_sk_redirect_map_proto;
+ case BPF_FUNC_sk_redirect_hash:
+ return &bpf_sk_redirect_hash_proto;
default:
return bpf_base_func_proto(func_id);
}
return insn - insn_buf;
}
+static int bpf_gen_ld_abs(const struct bpf_insn *orig,
+ struct bpf_insn *insn_buf)
+{
+ bool indirect = BPF_MODE(orig->code) == BPF_IND;
+ struct bpf_insn *insn = insn_buf;
+
+ /* We're guaranteed here that CTX is in R6. */
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX);
+ if (!indirect) {
+ *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm);
+ } else {
+ *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg);
+ if (orig->imm)
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm);
+ }
+
+ switch (BPF_SIZE(orig->code)) {
+ case BPF_B:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache);
+ break;
+ case BPF_H:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache);
+ break;
+ case BPF_W:
+ *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache);
+ break;
+ }
+
+ *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2);
+ *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0);
+ *insn++ = BPF_EXIT_INSN();
+
+ return insn - insn_buf;
+}
+
static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
const struct bpf_prog *prog)
{
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
- if (type == BPF_WRITE)
+ if (type == BPF_WRITE) {
+ if (bpf_prog_is_dev_bound(prog->aux)) {
+ switch (off) {
+ case offsetof(struct xdp_md, rx_queue_index):
+ return __is_valid_xdp_access(off, size);
+ }
+ }
return false;
+ }
switch (off) {
case offsetof(struct xdp_md, data):
.get_func_proto = sk_filter_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+ .gen_ld_abs = bpf_gen_ld_abs,
};
const struct bpf_prog_ops sk_filter_prog_ops = {
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+ .gen_ld_abs = bpf_gen_ld_abs,
};
const struct bpf_prog_ops tc_cls_act_prog_ops = {
EXPORT_SYMBOL(skb_get_hash_perturb);
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
- const struct flow_keys *keys, int hlen)
+ const struct flow_keys_basic *keys, int hlen)
{
u32 poff = keys->control.thoff;
*/
u32 skb_get_poff(const struct sk_buff *skb)
{
- struct flow_keys keys;
+ struct flow_keys_basic keys;
- if (!skb_flow_dissect_flow_keys(skb, &keys, 0))
+ if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
return 0;
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
},
};
-static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
+static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = {
{
.key_id = FLOW_DISSECTOR_KEY_CONTROL,
.offset = offsetof(struct flow_keys, control),
struct flow_dissector flow_keys_dissector __read_mostly;
EXPORT_SYMBOL(flow_keys_dissector);
-struct flow_dissector flow_keys_buf_dissector __read_mostly;
+struct flow_dissector flow_keys_basic_dissector __read_mostly;
+EXPORT_SYMBOL(flow_keys_basic_dissector);
static int __init init_default_flow_dissectors(void)
{
skb_flow_dissector_init(&flow_keys_dissector_symmetric,
flow_keys_dissector_symmetric_keys,
ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
- skb_flow_dissector_init(&flow_keys_buf_dissector,
- flow_keys_buf_dissector_keys,
- ARRAY_SIZE(flow_keys_buf_dissector_keys));
+ skb_flow_dissector_init(&flow_keys_basic_dissector,
+ flow_keys_basic_dissector_keys,
+ ARRAY_SIZE(flow_keys_basic_dissector_keys));
return 0;
}
write_lock(&n->lock);
state = n->nud_state;
- if (state & (NUD_PERMANENT | NUD_IN_TIMER)) {
+ if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) ||
+ (n->flags & NTF_EXT_LEARNED)) {
write_unlock(&n->lock);
goto next_elt;
}
if (neigh->dead)
goto out;
+ neigh_update_ext_learned(neigh, flags, ¬ify);
+
if (!(new & NUD_VALID)) {
neigh_del_timer(neigh);
if (old & NUD_CONNECTED)
flags &= ~NEIGH_UPDATE_F_OVERRIDE;
}
+ if (ndm->ndm_flags & NTF_EXT_LEARNED)
+ flags |= NEIGH_UPDATE_F_EXT_LEARNED;
+
if (ndm->ndm_flags & NTF_USE) {
neigh_event_send(neigh, NULL);
err = 0;
skb->inner_mac_header += off;
}
-static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
+void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
{
__copy_skb_header(new, old);
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
+EXPORT_SYMBOL(skb_copy_header);
static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
{
BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
- copy_skb_header(n, skb);
+ skb_copy_header(n, skb);
return n;
}
EXPORT_SYMBOL(skb_copy);
skb_clone_fraglist(n);
}
- copy_skb_header(n, skb);
+ skb_copy_header(n, skb);
out:
return n;
}
BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
skb->len + head_copy_len));
- copy_skb_header(n, skb);
+ skb_copy_header(n, skb);
skb_headers_offset_update(n, newheadroom - oldheadroom);
thlen = tcp_hdrlen(skb);
} else if (unlikely(skb_is_gso_sctp(skb))) {
thlen = sizeof(struct sctphdr);
+ } else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
+ thlen = sizeof(struct udphdr);
}
/* UFO sets gso_size to the size of the fragmentation
* payload, i.e. the size of the L4 (UDP) header is already
x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \
x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \
x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \
- x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX"
+ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \
+ x "AF_MAX"
static const char *const af_family_key_strings[AF_MAX+1] = {
_sock_locks("sk_lock-")
"rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" ,
"rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" ,
"rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" ,
- "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX"
+ "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" ,
+ "rlock-AF_MAX"
};
static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
"wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" ,
"wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" ,
"wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" ,
"wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" ,
- "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX"
+ "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" ,
+ "wlock-AF_MAX"
};
static const char *const af_family_elock_key_strings[AF_MAX+1] = {
"elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" ,
"elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" ,
"elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" ,
"elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" ,
- "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX"
+ "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" ,
+ "elock-AF_MAX"
};
/*
int sysctl_tstamp_allow_data __read_mostly = 1;
-struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
-EXPORT_SYMBOL_GPL(memalloc_socks);
+DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
+EXPORT_SYMBOL_GPL(memalloc_socks_key);
/**
* sk_set_memalloc - sets %SOCK_MEMALLOC
{
sock_set_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation |= __GFP_MEMALLOC;
- static_key_slow_inc(&memalloc_socks);
+ static_branch_inc(&memalloc_socks_key);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);
{
sock_reset_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation &= ~__GFP_MEMALLOC;
- static_key_slow_dec(&memalloc_socks);
+ static_branch_dec(&memalloc_socks_key);
/*
* SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
if (likely(sk->sk_net_refcnt))
sock_inuse_add(sock_net(sk), -1);
- if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
+ if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk)))
sock_diag_broadcast_destroy(sk);
else
sk_destruct(sk);
}
EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
-void xdp_return_frame(struct xdp_frame *xdpf)
+static void xdp_return(void *data, struct xdp_mem_info *mem)
{
- struct xdp_mem_info *mem = &xdpf->mem;
struct xdp_mem_allocator *xa;
- void *data = xdpf->data;
struct page *page;
switch (mem->type) {
break;
}
}
+
+void xdp_return_frame(struct xdp_frame *xdpf)
+{
+ xdp_return(xdpf->data, &xdpf->mem);
+}
EXPORT_SYMBOL_GPL(xdp_return_frame);
+
+void xdp_return_buff(struct xdp_buff *xdp)
+{
+ xdp_return(xdp->data, &xdp->rxq->mem);
+}
+EXPORT_SYMBOL_GPL(xdp_return_buff);
DCCPF_SEQ_WMAX));
}
+static void dccp_tasklet_schedule(struct sock *sk)
+{
+ struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
+
+ if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
+ sock_hold(sk);
+ __tasklet_schedule(t);
+ }
+}
+
static void ccid2_hc_tx_rto_expire(struct timer_list *t)
{
struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
/* if we were blocked before, we may now send cwnd=1 packet */
if (sender_was_blocked)
- tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+ dccp_tasklet_schedule(sk);
/* restart backed-off timer */
sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
out:
done:
/* check if incoming Acks allow pending packets to be sent */
if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
- tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+ dccp_tasklet_schedule(sk);
dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
}
else
dccp_write_xmit(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void dccp_write_xmit_timer(struct timer_list *t)
struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
dccp_write_xmitlet((unsigned long)sk);
- sock_put(sk);
}
void dccp_init_xmit_timers(struct sock *sk)
depends on HAVE_NET_DSA && MAY_USE_DEVLINK
depends on BRIDGE || BRIDGE=n
select NET_SWITCHDEV
- select PHYLIB
+ select PHYLINK
---help---
Say Y if you want to enable support for the hardware switches supported
by the Distributed Switch Architecture.
static int dsa_port_setup(struct dsa_port *dp)
{
struct dsa_switch *ds = dp->ds;
- int err;
+ int err = 0;
memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
- err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index);
+ if (dp->type != DSA_PORT_TYPE_UNUSED)
+ err = devlink_port_register(ds->devlink, &dp->devlink_port,
+ dp->index);
if (err)
return err;
case DSA_PORT_TYPE_UNUSED:
break;
case DSA_PORT_TYPE_CPU:
+ /* dp->index is used now as port_number. However
+ * CPU ports should have separate numbering
+ * independent from front panel port numbers.
+ */
+ devlink_port_attrs_set(&dp->devlink_port,
+ DEVLINK_PORT_FLAVOUR_CPU,
+ dp->index, false, 0);
+ err = dsa_port_link_register_of(dp);
+ if (err) {
+ dev_err(ds->dev, "failed to setup link for port %d.%d\n",
+ ds->index, dp->index);
+ return err;
+ }
+ break;
case DSA_PORT_TYPE_DSA:
+ /* dp->index is used now as port_number. However
+ * DSA ports should have separate numbering
+ * independent from front panel port numbers.
+ */
+ devlink_port_attrs_set(&dp->devlink_port,
+ DEVLINK_PORT_FLAVOUR_DSA,
+ dp->index, false, 0);
err = dsa_port_link_register_of(dp);
if (err) {
dev_err(ds->dev, "failed to setup link for port %d.%d\n",
}
break;
case DSA_PORT_TYPE_USER:
+ devlink_port_attrs_set(&dp->devlink_port,
+ DEVLINK_PORT_FLAVOUR_PHYSICAL,
+ dp->index, false, 0);
err = dsa_slave_create(dp);
if (err)
dev_err(ds->dev, "failed to create slave for port %d.%d\n",
static void dsa_port_teardown(struct dsa_port *dp)
{
- devlink_port_unregister(&dp->devlink_port);
+ if (dp->type != DSA_PORT_TYPE_UNUSED)
+ devlink_port_unregister(&dp->devlink_port);
switch (dp->type) {
case DSA_PORT_TYPE_UNUSED:
/* DSA port data, such as switch, port index, etc. */
struct dsa_port *dp;
- /*
- * The phylib phy_device pointer for the PHY connected
- * to this port.
- */
- phy_interface_t phy_interface;
- int old_link;
- int old_pause;
- int old_duplex;
-
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *netpoll;
#endif
int port = cpu_dp->index;
int count = 0;
- if (ops && ops->get_sset_count && ops->get_ethtool_stats) {
+ if (ops->get_sset_count && ops->get_ethtool_stats) {
count = ops->get_sset_count(dev, ETH_SS_STATS);
ops->get_ethtool_stats(dev, stats, data);
}
ds->ops->get_ethtool_stats(ds, port, data + count);
}
+static void dsa_master_get_ethtool_phy_stats(struct net_device *dev,
+ struct ethtool_stats *stats,
+ uint64_t *data)
+{
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
+ struct dsa_switch *ds = cpu_dp->ds;
+ int port = cpu_dp->index;
+ int count = 0;
+
+ if (dev->phydev && !ops->get_ethtool_phy_stats) {
+ count = phy_ethtool_get_sset_count(dev->phydev);
+ if (count >= 0)
+ phy_ethtool_get_stats(dev->phydev, stats, data);
+ } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) {
+ count = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+ ops->get_ethtool_phy_stats(dev, stats, data);
+ }
+
+ if (count < 0)
+ count = 0;
+
+ if (ds->ops->get_ethtool_phy_stats)
+ ds->ops->get_ethtool_phy_stats(ds, port, data + count);
+}
+
static int dsa_master_get_sset_count(struct net_device *dev, int sset)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct dsa_switch *ds = cpu_dp->ds;
int count = 0;
- if (ops && ops->get_sset_count)
- count += ops->get_sset_count(dev, sset);
+ if (sset == ETH_SS_PHY_STATS && dev->phydev &&
+ !ops->get_ethtool_phy_stats)
+ count = phy_ethtool_get_sset_count(dev->phydev);
+ else if (ops->get_sset_count)
+ count = ops->get_sset_count(dev, sset);
+
+ if (count < 0)
+ count = 0;
- if (sset == ETH_SS_STATS && ds->ops->get_sset_count)
- count += ds->ops->get_sset_count(ds, cpu_dp->index);
+ if (ds->ops->get_sset_count)
+ count += ds->ops->get_sset_count(ds, cpu_dp->index, sset);
return count;
}
/* We do not want to be NULL-terminated, since this is a prefix */
pfx[sizeof(pfx) - 1] = '_';
- if (ops && ops->get_sset_count && ops->get_strings) {
- mcount = ops->get_sset_count(dev, ETH_SS_STATS);
+ if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
+ !ops->get_ethtool_phy_stats) {
+ mcount = phy_ethtool_get_sset_count(dev->phydev);
+ if (mcount < 0)
+ mcount = 0;
+ else
+ phy_ethtool_get_strings(dev->phydev, data);
+ } else if (ops->get_sset_count && ops->get_strings) {
+ mcount = ops->get_sset_count(dev, stringset);
+ if (mcount < 0)
+ mcount = 0;
ops->get_strings(dev, stringset, data);
}
- if (stringset == ETH_SS_STATS && ds->ops->get_strings) {
+ if (ds->ops->get_strings) {
ndata = data + mcount * len;
/* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
* the output after to prepend our CPU port prefix we
* constructed earlier
*/
- ds->ops->get_strings(ds, port, ndata);
- count = ds->ops->get_sset_count(ds, port);
+ ds->ops->get_strings(ds, port, stringset, ndata);
+ count = ds->ops->get_sset_count(ds, port, stringset);
for (i = 0; i < count; i++) {
memmove(ndata + (i * len + sizeof(pfx)),
ndata + i * len, len - sizeof(pfx));
ops->get_sset_count = dsa_master_get_sset_count;
ops->get_ethtool_stats = dsa_master_get_ethtool_stats;
ops->get_strings = dsa_master_get_strings;
+ ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats;
dev->ethtool_ops = ops;
return 0;
}
-static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable)
+static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp)
{
- struct device_node *port_dn = dp->dn;
struct device_node *phy_dn;
- struct dsa_switch *ds = dp->ds;
struct phy_device *phydev;
- int port = dp->index;
- int err = 0;
- phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
+ phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0);
if (!phy_dn)
- return 0;
+ return NULL;
phydev = of_phy_find_device(phy_dn);
if (!phydev) {
- err = -EPROBE_DEFER;
- goto err_put_of;
+ of_node_put(phy_dn);
+ return ERR_PTR(-EPROBE_DEFER);
}
+ return phydev;
+}
+
+static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable)
+{
+ struct dsa_switch *ds = dp->ds;
+ struct phy_device *phydev;
+ int port = dp->index;
+ int err = 0;
+
+ phydev = dsa_port_get_phy_device(dp);
+ if (!phydev)
+ return 0;
+
+ if (IS_ERR(phydev))
+ return PTR_ERR(phydev);
+
if (enable) {
err = genphy_config_init(phydev);
if (err < 0)
err_put_dev:
put_device(&phydev->mdio.dev);
-err_put_of:
- of_node_put(phy_dn);
return err;
}
else
dsa_port_setup_phy_of(dp, false);
}
+
+int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data)
+{
+ struct phy_device *phydev;
+ int ret = -EOPNOTSUPP;
+
+ if (of_phy_is_fixed_link(dp->dn))
+ return ret;
+
+ phydev = dsa_port_get_phy_device(dp);
+ if (IS_ERR_OR_NULL(phydev))
+ return ret;
+
+ ret = phy_ethtool_get_strings(phydev, data);
+ put_device(&phydev->mdio.dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dsa_port_get_phy_strings);
+
+int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data)
+{
+ struct phy_device *phydev;
+ int ret = -EOPNOTSUPP;
+
+ if (of_phy_is_fixed_link(dp->dn))
+ return ret;
+
+ phydev = dsa_port_get_phy_device(dp);
+ if (IS_ERR_OR_NULL(phydev))
+ return ret;
+
+ ret = phy_ethtool_get_stats(phydev, NULL, data);
+ put_device(&phydev->mdio.dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dsa_port_get_ethtool_phy_stats);
+
+int dsa_port_get_phy_sset_count(struct dsa_port *dp)
+{
+ struct phy_device *phydev;
+ int ret = -EOPNOTSUPP;
+
+ if (of_phy_is_fixed_link(dp->dn))
+ return ret;
+
+ phydev = dsa_port_get_phy_device(dp);
+ if (IS_ERR_OR_NULL(phydev))
+ return ret;
+
+ ret = phy_ethtool_get_sset_count(phydev);
+ put_device(&phydev->mdio.dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count);
#include <linux/netdevice.h>
#include <linux/phy.h>
#include <linux/phy_fixed.h>
+#include <linux/phylink.h>
#include <linux/of_net.h>
#include <linux/of_mdio.h>
#include <linux/mdio.h>
if (err)
goto clear_promisc;
- if (dev->phydev)
- phy_start(dev->phydev);
+ phylink_start(dp->pl);
return 0;
struct net_device *master = dsa_slave_to_master(dev);
struct dsa_port *dp = dsa_slave_to_port(dev);
- if (dev->phydev)
- phy_stop(dev->phydev);
+ phylink_stop(dp->pl);
dsa_port_disable(dp, dev->phydev);
break;
}
- if (!dev->phydev)
- return -ENODEV;
-
- return phy_mii_ioctl(dev->phydev, ifr, cmd);
+ return phylink_mii_ioctl(p->dp->pl, ifr, cmd);
}
static int dsa_slave_port_attr_set(struct net_device *dev,
ds->ops->get_regs(ds, dp->index, regs, _p);
}
-static u32 dsa_slave_get_link(struct net_device *dev)
+static int dsa_slave_nway_reset(struct net_device *dev)
{
- if (!dev->phydev)
- return -ENODEV;
-
- genphy_update_link(dev->phydev);
+ struct dsa_port *dp = dsa_slave_to_port(dev);
- return dev->phydev->link;
+ return phylink_ethtool_nway_reset(dp->pl);
}
static int dsa_slave_get_eeprom_len(struct net_device *dev)
strncpy(data + 2 * len, "rx_packets", len);
strncpy(data + 3 * len, "rx_bytes", len);
if (ds->ops->get_strings)
- ds->ops->get_strings(ds, dp->index, data + 4 * len);
+ ds->ops->get_strings(ds, dp->index, stringset,
+ data + 4 * len);
}
}
count = 4;
if (ds->ops->get_sset_count)
- count += ds->ops->get_sset_count(ds, dp->index);
+ count += ds->ops->get_sset_count(ds, dp->index, sset);
return count;
}
struct dsa_port *dp = dsa_slave_to_port(dev);
struct dsa_switch *ds = dp->ds;
+ phylink_ethtool_get_wol(dp->pl, w);
+
if (ds->ops->get_wol)
ds->ops->get_wol(ds, dp->index, w);
}
struct dsa_switch *ds = dp->ds;
int ret = -EOPNOTSUPP;
+ phylink_ethtool_set_wol(dp->pl, w);
+
if (ds->ops->set_wol)
ret = ds->ops->set_wol(ds, dp->index, w);
if (ret)
return ret;
- if (e->eee_enabled) {
- ret = phy_init_eee(dev->phydev, 0);
- if (ret)
- return ret;
- }
-
- return phy_ethtool_set_eee(dev->phydev, e);
+ return phylink_ethtool_set_eee(dp->pl, e);
}
static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
if (ret)
return ret;
- return phy_ethtool_get_eee(dev->phydev, e);
+ return phylink_ethtool_get_eee(dp->pl, e);
+}
+
+static int dsa_slave_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ return phylink_ethtool_ksettings_get(dp->pl, cmd);
+}
+
+static int dsa_slave_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+
+ return phylink_ethtool_ksettings_set(dp->pl, cmd);
}
#ifdef CONFIG_NET_POLL_CONTROLLER
.get_drvinfo = dsa_slave_get_drvinfo,
.get_regs_len = dsa_slave_get_regs_len,
.get_regs = dsa_slave_get_regs,
- .nway_reset = phy_ethtool_nway_reset,
- .get_link = dsa_slave_get_link,
+ .nway_reset = dsa_slave_nway_reset,
+ .get_link = ethtool_op_get_link,
.get_eeprom_len = dsa_slave_get_eeprom_len,
.get_eeprom = dsa_slave_get_eeprom,
.set_eeprom = dsa_slave_set_eeprom,
.get_wol = dsa_slave_get_wol,
.set_eee = dsa_slave_set_eee,
.get_eee = dsa_slave_get_eee,
- .get_link_ksettings = phy_ethtool_get_link_ksettings,
- .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_link_ksettings = dsa_slave_get_link_ksettings,
+ .set_link_ksettings = dsa_slave_set_link_ksettings,
.get_rxnfc = dsa_slave_get_rxnfc,
.set_rxnfc = dsa_slave_set_rxnfc,
.get_ts_info = dsa_slave_get_ts_info,
.name = "dsa",
};
-static void dsa_slave_adjust_link(struct net_device *dev)
+static void dsa_slave_phylink_validate(struct net_device *dev,
+ unsigned long *supported,
+ struct phylink_link_state *state)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_switch *ds = dp->ds;
- unsigned int status_changed = 0;
- if (p->old_link != dev->phydev->link) {
- status_changed = 1;
- p->old_link = dev->phydev->link;
- }
+ if (!ds->ops->phylink_validate)
+ return;
- if (p->old_duplex != dev->phydev->duplex) {
- status_changed = 1;
- p->old_duplex = dev->phydev->duplex;
- }
+ ds->ops->phylink_validate(ds, dp->index, supported, state);
+}
- if (p->old_pause != dev->phydev->pause) {
- status_changed = 1;
- p->old_pause = dev->phydev->pause;
- }
+static int dsa_slave_phylink_mac_link_state(struct net_device *dev,
+ struct phylink_link_state *state)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+
+ /* Only called for SGMII and 802.3z */
+ if (!ds->ops->phylink_mac_link_state)
+ return -EOPNOTSUPP;
+
+ return ds->ops->phylink_mac_link_state(ds, dp->index, state);
+}
+
+static void dsa_slave_phylink_mac_config(struct net_device *dev,
+ unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+
+ if (!ds->ops->phylink_mac_config)
+ return;
+
+ ds->ops->phylink_mac_config(ds, dp->index, mode, state);
+}
- if (ds->ops->adjust_link && status_changed)
- ds->ops->adjust_link(ds, dp->index, dev->phydev);
+static void dsa_slave_phylink_mac_an_restart(struct net_device *dev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
- if (status_changed)
- phy_print_status(dev->phydev);
+ if (!ds->ops->phylink_mac_an_restart)
+ return;
+
+ ds->ops->phylink_mac_an_restart(ds, dp->index);
}
-static int dsa_slave_fixed_link_update(struct net_device *dev,
- struct fixed_phy_status *status)
+static void dsa_slave_phylink_mac_link_down(struct net_device *dev,
+ unsigned int mode,
+ phy_interface_t interface)
{
- struct dsa_switch *ds;
- struct dsa_port *dp;
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
- if (dev) {
- dp = dsa_slave_to_port(dev);
- ds = dp->ds;
- if (ds->ops->fixed_link_update)
- ds->ops->fixed_link_update(ds, dp->index, status);
+ if (!ds->ops->phylink_mac_link_down) {
+ if (ds->ops->adjust_link && dev->phydev)
+ ds->ops->adjust_link(ds, dp->index, dev->phydev);
+ return;
}
- return 0;
+ ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface);
+}
+
+static void dsa_slave_phylink_mac_link_up(struct net_device *dev,
+ unsigned int mode,
+ phy_interface_t interface,
+ struct phy_device *phydev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+
+ if (!ds->ops->phylink_mac_link_up) {
+ if (ds->ops->adjust_link && dev->phydev)
+ ds->ops->adjust_link(ds, dp->index, dev->phydev);
+ return;
+ }
+
+ ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev);
+}
+
+static const struct phylink_mac_ops dsa_slave_phylink_mac_ops = {
+ .validate = dsa_slave_phylink_validate,
+ .mac_link_state = dsa_slave_phylink_mac_link_state,
+ .mac_config = dsa_slave_phylink_mac_config,
+ .mac_an_restart = dsa_slave_phylink_mac_an_restart,
+ .mac_link_down = dsa_slave_phylink_mac_link_down,
+ .mac_link_up = dsa_slave_phylink_mac_link_up,
+};
+
+void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up)
+{
+ const struct dsa_port *dp = dsa_to_port(ds, port);
+
+ phylink_mac_change(dp->pl, up);
+}
+EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change);
+
+static void dsa_slave_phylink_fixed_state(struct net_device *dev,
+ struct phylink_link_state *state)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+
+ /* No need to check that this operation is valid, the callback would
+ * not be called if it was not.
+ */
+ ds->ops->phylink_fixed_state(ds, dp->index, state);
}
/* slave device setup *******************************************************/
static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr)
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
- struct dsa_slave_priv *p = netdev_priv(slave_dev);
struct dsa_switch *ds = dp->ds;
slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr);
return -ENODEV;
}
- /* Use already configured phy mode */
- if (p->phy_interface == PHY_INTERFACE_MODE_NA)
- p->phy_interface = slave_dev->phydev->interface;
-
- return phy_connect_direct(slave_dev, slave_dev->phydev,
- dsa_slave_adjust_link, p->phy_interface);
+ return phylink_connect_phy(dp->pl, slave_dev->phydev);
}
static int dsa_slave_phy_setup(struct net_device *slave_dev)
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
- struct dsa_slave_priv *p = netdev_priv(slave_dev);
struct device_node *port_dn = dp->dn;
struct dsa_switch *ds = dp->ds;
- struct device_node *phy_dn;
- bool phy_is_fixed = false;
u32 phy_flags = 0;
int mode, ret;
mode = of_get_phy_mode(port_dn);
if (mode < 0)
mode = PHY_INTERFACE_MODE_NA;
- p->phy_interface = mode;
- phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
- if (!phy_dn && of_phy_is_fixed_link(port_dn)) {
- /* In the case of a fixed PHY, the DT node associated
- * to the fixed PHY is the Port DT node
- */
- ret = of_phy_register_fixed_link(port_dn);
- if (ret) {
- netdev_err(slave_dev, "failed to register fixed PHY: %d\n", ret);
- return ret;
- }
- phy_is_fixed = true;
- phy_dn = of_node_get(port_dn);
+ dp->pl = phylink_create(slave_dev, of_fwnode_handle(port_dn), mode,
+ &dsa_slave_phylink_mac_ops);
+ if (IS_ERR(dp->pl)) {
+ netdev_err(slave_dev,
+ "error creating PHYLINK: %ld\n", PTR_ERR(dp->pl));
+ return PTR_ERR(dp->pl);
}
+ /* Register only if the switch provides such a callback, since this
+ * callback takes precedence over polling the link GPIO in PHYLINK
+ * (see phylink_get_fixed_state).
+ */
+ if (ds->ops->phylink_fixed_state)
+ phylink_fixed_state_cb(dp->pl, dsa_slave_phylink_fixed_state);
+
if (ds->ops->get_phy_flags)
phy_flags = ds->ops->get_phy_flags(ds, dp->index);
- if (phy_dn) {
- slave_dev->phydev = of_phy_connect(slave_dev, phy_dn,
- dsa_slave_adjust_link,
- phy_flags,
- p->phy_interface);
- of_node_put(phy_dn);
- }
-
- if (slave_dev->phydev && phy_is_fixed)
- fixed_phy_set_link_update(slave_dev->phydev,
- dsa_slave_fixed_link_update);
-
- /* We could not connect to a designated PHY, so use the switch internal
- * MDIO bus instead
- */
- if (!slave_dev->phydev) {
+ ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags);
+ if (ret == -ENODEV) {
+ /* We could not connect to a designated PHY or SFP, so use the
+ * switch internal MDIO bus instead
+ */
ret = dsa_slave_phy_connect(slave_dev, dp->index);
if (ret) {
- netdev_err(slave_dev, "failed to connect to port %d: %d\n",
+ netdev_err(slave_dev,
+ "failed to connect to port %d: %d\n",
dp->index, ret);
- if (phy_is_fixed)
- of_phy_deregister_fixed_link(port_dn);
+ phylink_destroy(dp->pl);
return ret;
}
}
- phy_attached_info(slave_dev->phydev);
-
return 0;
}
int dsa_slave_suspend(struct net_device *slave_dev)
{
- struct dsa_slave_priv *p = netdev_priv(slave_dev);
+ struct dsa_port *dp = dsa_slave_to_port(slave_dev);
netif_device_detach(slave_dev);
- if (slave_dev->phydev) {
- phy_stop(slave_dev->phydev);
- p->old_pause = -1;
- p->old_link = -1;
- p->old_duplex = -1;
- phy_suspend(slave_dev->phydev);
- }
+ rtnl_lock();
+ phylink_stop(dp->pl);
+ rtnl_unlock();
return 0;
}
int dsa_slave_resume(struct net_device *slave_dev)
{
+ struct dsa_port *dp = dsa_slave_to_port(slave_dev);
+
netif_device_attach(slave_dev);
- if (slave_dev->phydev) {
- phy_resume(slave_dev->phydev);
- phy_start(slave_dev->phydev);
- }
+ rtnl_lock();
+ phylink_start(dp->pl);
+ rtnl_unlock();
return 0;
}
p->dp = port;
INIT_LIST_HEAD(&p->mall_tc_list);
p->xmit = cpu_dp->tag_ops->xmit;
-
- p->old_pause = -1;
- p->old_link = -1;
- p->old_duplex = -1;
-
port->slave = slave_dev;
netif_carrier_off(slave_dev);
return 0;
out_phy:
- phy_disconnect(slave_dev->phydev);
- if (of_phy_is_fixed_link(port->dn))
- of_phy_deregister_fixed_link(port->dn);
+ rtnl_lock();
+ phylink_disconnect_phy(p->dp->pl);
+ rtnl_unlock();
+ phylink_destroy(p->dp->pl);
out_free:
free_percpu(p->stats64);
free_netdev(slave_dev);
{
struct dsa_port *dp = dsa_slave_to_port(slave_dev);
struct dsa_slave_priv *p = netdev_priv(slave_dev);
- struct device_node *port_dn = dp->dn;
netif_carrier_off(slave_dev);
- if (slave_dev->phydev) {
- phy_disconnect(slave_dev->phydev);
+ rtnl_lock();
+ phylink_disconnect_phy(dp->pl);
+ rtnl_unlock();
- if (of_phy_is_fixed_link(port_dn))
- of_phy_deregister_fixed_link(port_dn);
- }
dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
unregister_netdev(slave_dev);
+ phylink_destroy(dp->pl);
free_percpu(p->stats64);
free_netdev(slave_dev);
}
switch (switchdev_work->event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
+
err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid);
if (err) {
netdev_dbg(dev, "fdb add failed err=%d\n", err);
case SWITCHDEV_FDB_DEL_TO_DEVICE:
fdb_info = &switchdev_work->fdb_info;
+ if (!fdb_info->added_by_user)
+ break;
+
err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid);
if (err) {
netdev_dbg(dev, "fdb del failed err=%d\n", err);
switch (event) {
case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */
case SWITCHDEV_FDB_DEL_TO_DEVICE:
- if (dsa_slave_switchdev_fdb_work_init(switchdev_work,
- ptr))
+ if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr))
goto err_fdb_work_init;
dev_hold(dev);
break;
{
const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
const struct ethhdr *eth = (const struct ethhdr *)data;
- struct flow_keys keys;
+ struct flow_keys_basic keys;
/* this should never happen, but better safe than sorry */
if (unlikely(len < sizeof(*eth)))
return len;
/* parse any remaining L2/L3 headers, check for L4 */
- if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto,
- sizeof(*eth), len, flags))
+ if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto,
+ sizeof(*eth), len, flags))
return max_t(u32, keys.control.thoff, sizeof(*eth));
/* parse for any L4 headers */
struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr src;
- const struct ieee802154_addr dst;
+ struct ieee802154_addr src;
+ struct ieee802154_addr dst;
};
/* Equivalent of ipv4 struct ipq
{
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
- struct frag_lowpan_compare_key key = {
- .tag = cb->d_tag,
- .d_size = cb->d_size,
- .src = *src,
- .dst = *dst,
- };
+ struct frag_lowpan_compare_key key = {};
struct inet_frag_queue *q;
+ key.tag = cb->d_tag;
+ key.d_size = cb->d_size;
+ key.src = *src;
+ key.dst = *dst;
+
q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (!q)
return NULL;
struct lowpan_frag_queue *fq;
struct net *net = dev_net(skb->dev);
struct lowpan_802154_cb *cb = lowpan_802154_cb(skb);
- struct ieee802154_hdr hdr;
+ struct ieee802154_hdr hdr = {};
int err;
if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
+#ifdef CONFIG_MMU
.mmap = tcp_mmap,
+#endif
.sendpage = inet_sendpage,
.splice_read = tcp_splice_read,
.read_sock = tcp_read_sock,
u8 tos, int oif, struct net_device *dev,
int rpf, struct in_device *idev, u32 *itag)
{
+ struct net *net = dev_net(dev);
+ struct flow_keys flkeys;
int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
- struct net *net = dev_net(dev);
bool dev_match;
fl4.flowi4_oif = 0;
no_addr = idev->ifa_list == NULL;
fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
+ if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) {
+ fl4.flowi4_proto = 0;
+ fl4.fl4_sport = 0;
+ fl4.fl4_dport = 0;
+ }
trace_fib_validate_source(dev, &fl4);
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
-#ifdef INET_CSK_DEBUG
-const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
-EXPORT_SYMBOL(inet_csk_timer_bug_msg);
-#endif
-
#if IS_ENABLED(CONFIG_IPV6)
/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
* only, and any IPv4 addresses if not IPv6 only
int tunnel_hlen;
int version;
__be16 df;
+ int nhoff;
+ int thoff;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
truncate = true;
}
+ nhoff = skb_network_header(skb) - skb_mac_header(skb);
+ if (skb->protocol == htons(ETH_P_IP) &&
+ (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
+ truncate = true;
+
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ if (skb->protocol == htons(ETH_P_IPV6) &&
+ (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
+ truncate = true;
+
if (version == 1) {
erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
ntohl(md->u.index), truncate, true);
erspan_build_header(skb, ntohl(tunnel->parms.o_key),
tunnel->index,
truncate, true);
- else
+ else if (tunnel->erspan_ver == 2)
erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
tunnel->dir, tunnel->hwid,
truncate, true);
+ else
+ goto free_skb;
tunnel->parms.o_flags &= ~TUNNEL_KEY;
__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
struct rtable *rt = (struct rtable *)cork->dst;
unsigned int wmem_alloc_delta = 0;
u32 tskey = 0;
+ bool paged;
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
- mtu = cork->fragsize;
+ mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
+ paged = !!cork->gso_size;
+
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
tskey = sk->sk_tskey++;
if (transhdrlen &&
length + fragheaderlen <= mtu &&
rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) &&
- !(flags & MSG_MORE) &&
- !exthdrlen)
+ (!(flags & MSG_MORE) || cork->gso_size) &&
+ (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
csummode = CHECKSUM_PARTIAL;
cork->length += length;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
+ else if (!paged)
alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += exthdrlen;
/*
* Find where to start putting bytes.
*/
- data = skb_put(skb, fraglen + exthdrlen);
+ data = skb_put(skb, fraglen + exthdrlen - pagedlen);
skb_set_network_header(skb, exthdrlen);
skb->transport_header = (skb->network_header +
fragheaderlen);
pskb_trim_unique(skb_prev, maxfraglen);
}
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
*rtp = NULL;
cork->fragsize = ip_sk_use_pmtu(sk) ?
dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+
+ cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0;
cork->dst = &rt->dst;
cork->length = 0;
cork->ttl = ipc->ttl;
return -EOPNOTSUPP;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
- mtu = cork->fragsize;
+ mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
- unsigned int flags)
+ struct inet_cork *cork, unsigned int flags)
{
- struct inet_cork cork;
struct sk_buff_head queue;
int err;
__skb_queue_head_init(&queue);
- cork.flags = 0;
- cork.addr = 0;
- cork.opt = NULL;
- err = ip_setup_cork(sk, &cork, ipc, rtp);
+ cork->flags = 0;
+ cork->addr = 0;
+ cork->opt = NULL;
+ err = ip_setup_cork(sk, cork, ipc, rtp);
if (err)
return ERR_PTR(err);
- err = __ip_append_data(sk, fl4, &queue, &cork,
+ err = __ip_append_data(sk, fl4, &queue, cork,
¤t->task_frag, getfrag,
from, length, transhdrlen, flags);
if (err) {
- __ip_flush_pending_frames(sk, &queue, &cork);
+ __ip_flush_pending_frames(sk, &queue, cork);
return ERR_PTR(err);
}
- return __ip_make_skb(sk, fl4, &queue, &cork);
+ return __ip_make_skb(sk, fl4, &queue, cork);
}
/*
oif = skb->skb_iif;
flowi4_init_output(&fl4, oif,
- IP4_REPLY_MARK(net, skb->mark),
+ IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark,
RT_TOS(arg->tos),
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}
-struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE;
+DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
- static_key_slow_inc(&ip_tunnel_metadata_cnt);
+ static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
- static_key_slow_dec(&ip_tunnel_metadata_cnt);
+ static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
*
* Multiple Nameservers in /proc/net/pnp
* -- Josef Siemes <jsiemes@web.de>, Aug 2002
+ *
+ * NTP servers in /proc/net/ipconfig/ntp_servers
+ * -- Chris Novakovic <chris@chrisn.me.uk>, April 2018
*/
#include <linux/types.h>
#define CONF_TIMEOUT_MAX (HZ*30) /* Maximum allowed timeout */
#define CONF_NAMESERVERS_MAX 3 /* Maximum number of nameservers
- '3' from resolv.h */
+#define CONF_NTP_SERVERS_MAX 3 /* Maximum number of NTP servers */
#define NONE cpu_to_be32(INADDR_NONE)
#define ANY cpu_to_be32(INADDR_ANY)
#define ic_proto_used 0
#endif
static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */
+static __be32 ic_ntp_servers[CONF_NTP_SERVERS_MAX]; /* NTP server IP addresses */
static u8 ic_domain[64]; /* DNS (not NIS) domain name */
/*
ic_nameservers[i] = NONE;
}
+/* Predefine NTP servers */
+static inline void __init ic_ntp_servers_predef(void)
+{
+ int i;
+
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++)
+ ic_ntp_servers[i] = NONE;
+}
+
/*
* DHCP/BOOTP support.
*/
17, /* Boot path */
26, /* MTU */
40, /* NIS domain name */
+ 42, /* NTP servers */
};
*e++ = 55; /* Parameter request list */
*e++ = 3; /* Default gateway request */
*e++ = 4;
e += 4;
- *e++ = 5; /* Name server request */
- *e++ = 8;
- e += 8;
+#if CONF_NAMESERVERS_MAX > 0
+ *e++ = 6; /* (DNS) name server request */
+ *e++ = 4 * CONF_NAMESERVERS_MAX;
+ e += 4 * CONF_NAMESERVERS_MAX;
+#endif
*e++ = 12; /* Host name request */
*e++ = 32;
e += 32;
*/
static inline void __init ic_bootp_init(void)
{
+ /* Re-initialise all name servers and NTP servers to NONE, in case any
+ * were set via the "ip=" or "nfsaddrs=" kernel command line parameters:
+ * any IP addresses specified there will already have been decoded but
+ * are no longer needed
+ */
ic_nameservers_predef();
+ ic_ntp_servers_predef();
dev_add_pack(&bootp_packet_type);
}
ic_bootp_string(utsname()->domainname, ext+1, *ext,
__NEW_UTS_LEN);
break;
+ case 42: /* NTP servers */
+ servers = *ext / 4;
+ if (servers > CONF_NTP_SERVERS_MAX)
+ servers = CONF_NTP_SERVERS_MAX;
+ for (i = 0; i < servers; i++) {
+ if (ic_ntp_servers[i] == NONE)
+ memcpy(&ic_ntp_servers[i], ext+1+4*i, 4);
+ }
+ break;
}
}
#endif /* IPCONFIG_DYNAMIC */
#ifdef CONFIG_PROC_FS
+/* proc_dir_entry for /proc/net/ipconfig */
+static struct proc_dir_entry *ipconfig_dir;
+/* Name servers: */
static int pnp_seq_show(struct seq_file *seq, void *v)
{
int i;
.llseek = seq_lseek,
.release = single_release,
};
+
+/* Create the /proc/net/ipconfig directory */
+static int __init ipconfig_proc_net_init(void)
+{
+ ipconfig_dir = proc_net_mkdir(&init_net, "ipconfig", init_net.proc_net);
+ if (!ipconfig_dir)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/* Create a new file under /proc/net/ipconfig */
+static int ipconfig_proc_net_create(const char *name,
+ const struct file_operations *fops)
+{
+ char *pname;
+ struct proc_dir_entry *p;
+
+ if (!ipconfig_dir)
+ return -ENOMEM;
+
+ pname = kasprintf(GFP_KERNEL, "%s%s", "ipconfig/", name);
+ if (!pname)
+ return -ENOMEM;
+
+ p = proc_create(pname, 0444, init_net.proc_net, fops);
+ kfree(pname);
+ if (!p)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */
+static int ntp_servers_seq_show(struct seq_file *seq, void *v)
+{
+ int i;
+
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ if (ic_ntp_servers[i] != NONE)
+ seq_printf(seq, "%pI4\n", &ic_ntp_servers[i]);
+ }
+ return 0;
+}
+
+static int ntp_servers_seq_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ntp_servers_seq_show, NULL);
+}
+
+static const struct file_operations ntp_servers_seq_fops = {
+ .open = ntp_servers_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
#endif /* CONFIG_PROC_FS */
/*
int err;
unsigned int i;
+ /* Initialise all name servers and NTP servers to NONE (but only if the
+ * "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded,
+ * otherwise we'll overwrite the IP addresses specified there)
+ */
+ if (ic_set_manually == 0) {
+ ic_nameservers_predef();
+ ic_ntp_servers_predef();
+ }
+
#ifdef CONFIG_PROC_FS
proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops);
+
+ if (ipconfig_proc_net_init() == 0)
+ ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops);
#endif /* CONFIG_PROC_FS */
if (!ic_enable)
&ic_servaddr, &root_server_addr, root_server_path);
if (ic_dev_mtu)
pr_cont(", mtu=%d", ic_dev_mtu);
- for (i = 0; i < CONF_NAMESERVERS_MAX; i++)
+ /* Name servers (if any): */
+ for (i = 0; i < CONF_NAMESERVERS_MAX; i++) {
if (ic_nameservers[i] != NONE) {
- pr_cont(" nameserver%u=%pI4",
- i, &ic_nameservers[i]);
- break;
+ if (i == 0)
+ pr_info(" nameserver%u=%pI4",
+ i, &ic_nameservers[i]);
+ else
+ pr_cont(", nameserver%u=%pI4",
+ i, &ic_nameservers[i]);
}
- for (i++; i < CONF_NAMESERVERS_MAX; i++)
- if (ic_nameservers[i] != NONE)
- pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]);
- pr_cont("\n");
+ if (i + 1 == CONF_NAMESERVERS_MAX)
+ pr_cont("\n");
+ }
+ /* NTP servers (if any): */
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ if (ic_ntp_servers[i] != NONE) {
+ if (i == 0)
+ pr_info(" ntpserver%u=%pI4",
+ i, &ic_ntp_servers[i]);
+ else
+ pr_cont(", ntpserver%u=%pI4",
+ i, &ic_ntp_servers[i]);
+ }
+ if (i + 1 == CONF_NTP_SERVERS_MAX)
+ pr_cont("\n");
+ }
#endif /* !SILENT */
/*
return 1;
}
+ /* Initialise all name servers and NTP servers to NONE */
ic_nameservers_predef();
+ ic_ntp_servers_predef();
/* Parse string for static IP assignment. */
ip = addrs;
ic_nameservers[1] = NONE;
}
break;
+ case 9:
+ if (CONF_NTP_SERVERS_MAX >= 1) {
+ ic_ntp_servers[0] = in_aton(ip);
+ if (ic_ntp_servers[0] == ANY)
+ ic_ntp_servers[0] = NONE;
+ }
+ break;
}
}
ip = cp;
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("IPv4 packet filter");
+MODULE_ALIAS("ipt_icmp");
void *ipt_alloc_initial_table(const struct xt_table *info)
{
counter = xt_get_this_cpu_counter(&e->counters);
ADD_COUNTER(*counter, skb->len, 1);
- t = ipt_get_target(e);
+ t = ipt_get_target_c(e);
WARN_ON(!t->u.kernel.target);
#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
static unsigned int
masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
const struct nf_nat_ipv4_multi_range_compat *mr;
mr = par->targinfo;
return true ^ invert;
}
+ memset(&flow, 0, sizeof(flow));
flow.flowi4_iif = LOOPBACK_IFINDEX;
flow.daddr = iph->saddr;
flow.saddr = rpfilter_get_saddr(iph->daddr);
- flow.flowi4_oif = 0;
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
flow.flowi4_tos = RT_TOS(iph->tos);
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
static unsigned int iptable_nat_do_chain(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct)
+ const struct nf_hook_state *state)
{
return ipt_do_table(skb, state, state->net->ipv4.nat_table);
}
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netfilter.h>
-#include <linux/rhashtable.h>
-#include <linux/ip.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
-#include <net/neighbour.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
- __be32 addr, __be32 new_addr)
-{
- struct tcphdr *tcph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*tcph)))
- return -1;
-
- tcph = (void *)(skb_network_header(skb) + thoff);
- inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
-
- return 0;
-}
-
-static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
- __be32 addr, __be32 new_addr)
-{
- struct udphdr *udph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*udph)))
- return -1;
-
- udph = (void *)(skb_network_header(skb) + thoff);
- if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
- inet_proto_csum_replace4(&udph->check, skb, addr,
- new_addr, true);
- if (!udph->check)
- udph->check = CSUM_MANGLED_0;
- }
-
- return 0;
-}
-
-static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
- unsigned int thoff, __be32 addr,
- __be32 new_addr)
-{
- switch (iph->protocol) {
- case IPPROTO_TCP:
- if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- case IPPROTO_UDP:
- if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- }
-
- return 0;
-}
-
-static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- struct iphdr *iph, unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- __be32 addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = iph->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
- iph->saddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = iph->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
- iph->daddr = new_addr;
- break;
- default:
- return -1;
- }
- csum_replace4(&iph->check, addr, new_addr);
-
- return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- struct iphdr *iph, unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- __be32 addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = iph->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
- iph->daddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = iph->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
- iph->saddr = new_addr;
- break;
- default:
- return -1;
- }
- csum_replace4(&iph->check, addr, new_addr);
-
- return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- enum flow_offload_tuple_dir dir)
-{
- struct iphdr *iph = ip_hdr(skb);
- unsigned int thoff = iph->ihl * 4;
-
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
- (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
- nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
- return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
- (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
- nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
- return -1;
-
- return 0;
-}
-
-static bool ip_has_options(unsigned int thoff)
-{
- return thoff != sizeof(struct iphdr);
-}
-
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple)
-{
- struct flow_ports *ports;
- unsigned int thoff;
- struct iphdr *iph;
-
- if (!pskb_may_pull(skb, sizeof(*iph)))
- return -1;
-
- iph = ip_hdr(skb);
- thoff = iph->ihl * 4;
-
- if (ip_is_fragment(iph) ||
- unlikely(ip_has_options(thoff)))
- return -1;
-
- if (iph->protocol != IPPROTO_TCP &&
- iph->protocol != IPPROTO_UDP)
- return -1;
-
- thoff = iph->ihl * 4;
- if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
- return -1;
-
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
- tuple->src_v4.s_addr = iph->saddr;
- tuple->dst_v4.s_addr = iph->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
- tuple->l3proto = AF_INET;
- tuple->l4proto = iph->protocol;
- tuple->iifidx = dev->ifindex;
-
- return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
- if (skb->len <= mtu)
- return false;
-
- if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
- return false;
-
- if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
- return false;
-
- return true;
-}
-
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
-{
- u32 mtu;
-
- mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (__nf_flow_exceeds_mtu(skb, mtu))
- return true;
-
- return false;
-}
-
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
- struct flow_offload_tuple tuple = {};
- enum flow_offload_tuple_dir dir;
- struct flow_offload *flow;
- struct net_device *outdev;
- const struct rtable *rt;
- struct iphdr *iph;
- __be32 nexthop;
-
- if (skb->protocol != htons(ETH_P_IP))
- return NF_ACCEPT;
-
- if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
- return NF_ACCEPT;
-
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
-
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
- dir = tuplehash->tuple.dir;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
- rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
- if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
- return NF_ACCEPT;
-
- if (skb_try_make_writable(skb, sizeof(*iph)))
- return NF_DROP;
-
- if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
- nf_flow_nat_ip(flow, skb, dir) < 0)
- return NF_DROP;
-
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
- iph = ip_hdr(skb);
- ip_decrease_ttl(iph);
-
- skb->dev = outdev;
- nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
- neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
-
- return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
static struct nf_flowtable_type flowtable_ipv4 = {
.family = NFPROTO_IPV4,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ip_hook,
.owner = THIS_MODULE,
static void ip_nat_q931_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */
nf_nat_follow_master(new, this);
static void ip_nat_callforwarding_expect(struct nf_conn *new,
struct nf_conntrack_expect *this)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
/* This must be a fresh one. */
BUG_ON(new->status & IPS_NAT_DONE_MASK);
#endif /* CONFIG_XFRM */
static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
- const struct nf_nat_range *range)
+ const struct nf_nat_range2 *range)
{
return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range)
+ struct nf_nat_range2 *range)
{
if (tb[CTA_NAT_V4_MINIP]) {
range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]);
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
- ret = do_chain(priv, skb, state, ct);
+ ret = do_chain(priv, skb, state);
if (ret != NF_ACCEPT)
return ret;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
unsigned int ret;
__be32 daddr = ip_hdr(skb)->daddr;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
const struct net_device *out)
{
struct nf_conn *ct;
struct nf_conn_nat *nat;
enum ip_conntrack_info ctinfo;
- struct nf_nat_range newrange;
+ struct nf_nat_range2 newrange;
const struct rtable *rt;
__be32 newsrc, nh;
struct nf_conntrack_tuple t = {};
const struct nf_ct_pptp_master *ct_pptp_info;
const struct nf_nat_pptp *nat_pptp_info;
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
struct nf_conn_nat *nat;
nat = nf_ct_nat_ext_add(ct);
static void
gre_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void
icmp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static unsigned int nft_nat_do_chain(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct)
+ const struct nf_hook_state *state)
{
struct nft_pktinfo pkt;
const struct nft_pktinfo *pkt)
{
struct nft_masq *priv = nft_expr_priv(expr);
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
ipc.addr = faddr = daddr;
if (ipc.opt && ipc.opt->opt.srr) {
- if (!daddr)
- return -EINVAL;
+ if (!daddr) {
+ err = -EINVAL;
+ goto out_free;
+ }
faddr = ipc.opt->opt.faddr;
}
tos = get_rttos(&ipc, inet);
out:
ip_rt_put(rt);
+out_free:
if (free)
kfree(ipc.opt);
if (!err) {
SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
+ SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
SNMP_MIB_SENTINEL
};
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_mtu_locked = lock;
- fnhe->fnhe_expires = expires;
+ fnhe->fnhe_expires = max(1UL, expires);
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+ struct fnhe_hash_bucket *hash;
+ struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+ u32 hval = fnhe_hashfun(daddr);
+
+ spin_lock_bh(&fnhe_lock);
+
+ hash = rcu_dereference_protected(nh->nh_exceptions,
+ lockdep_is_held(&fnhe_lock));
+ hash += hval;
+
+ fnhe_p = &hash->chain;
+ fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+ while (fnhe) {
+ if (fnhe->fnhe_daddr == daddr) {
+ rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+ fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+ fnhe_flush_routes(fnhe);
+ kfree_rcu(fnhe, rcu);
+ break;
+ }
+ fnhe_p = &fnhe->fnhe_next;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+ lockdep_is_held(&fnhe_lock));
+ }
+
+ spin_unlock_bh(&fnhe_lock);
+}
+
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
- if (fnhe->fnhe_daddr == daddr)
+ if (fnhe->fnhe_daddr == daddr) {
+ if (fnhe->fnhe_expires &&
+ time_after(jiffies, fnhe->fnhe_expires)) {
+ ip_del_fnhe(nh, daddr);
+ break;
+ }
return fnhe;
+ }
}
return NULL;
}
fnhe->fnhe_gw = 0;
fnhe->fnhe_pmtu = 0;
fnhe->fnhe_expires = 0;
+ fnhe->fnhe_mtu_locked = false;
fnhe_flush_routes(fnhe);
orig = NULL;
}
#endif
}
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
- struct fnhe_hash_bucket *hash;
- struct fib_nh_exception *fnhe, __rcu **fnhe_p;
- u32 hval = fnhe_hashfun(daddr);
-
- spin_lock_bh(&fnhe_lock);
-
- hash = rcu_dereference_protected(nh->nh_exceptions,
- lockdep_is_held(&fnhe_lock));
- hash += hval;
-
- fnhe_p = &hash->chain;
- fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
- while (fnhe) {
- if (fnhe->fnhe_daddr == daddr) {
- rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
- fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
- fnhe_flush_routes(fnhe);
- kfree_rcu(fnhe, rcu);
- break;
- }
- fnhe_p = &fnhe->fnhe_next;
- fnhe = rcu_dereference_protected(fnhe->fnhe_next,
- lockdep_is_held(&fnhe_lock));
- }
-
- spin_unlock_bh(&fnhe_lock);
-}
-
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
fnhe = find_exception(&FIB_RES_NH(*res), daddr);
if (do_cache) {
- if (fnhe) {
+ if (fnhe)
rth = rcu_dereference(fnhe->fnhe_rth_input);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(&FIB_RES_NH(*res), daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
- }
- }
-
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+ else
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
fl4.saddr = saddr;
fl4.flowi4_uid = sock_net_uid(net, NULL);
- if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+ if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
flkeys = &_flkeys;
+ } else {
+ fl4.flowi4_proto = 0;
+ fl4.fl4_sport = 0;
+ fl4.fl4_dport = 0;
+ }
err = fib_lookup(net, &fl4, res, 0);
if (err != 0) {
* the loopback interface and the IP_PKTINFO ipi_ifindex will
* be set to the loopback interface as well.
*/
- fi = NULL;
+ do_cache = false;
}
fnhe = NULL;
do_cache &= fi != NULL;
- if (do_cache) {
+ if (fi) {
struct rtable __rcu **prth;
struct fib_nh *nh = &FIB_RES_NH(*res);
fnhe = find_exception(nh, fl4->daddr);
+ if (!do_cache)
+ goto add;
if (fnhe) {
prth = &fnhe->fnhe_rth_output;
- rth = rcu_dereference(*prth);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(nh, fl4->daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
+ } else {
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
}
+ prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
}
-
- if (unlikely(fl4->flowi4_flags &
- FLOWI_FLAG_KNOWN_NH &&
- !(nh->nh_gw &&
- nh->nh_scope == RT_SCOPE_LINK))) {
- do_cache = false;
- goto add;
- }
- prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
rth = rcu_dereference(*prth);
-
-rt_cache:
if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
return rth;
}
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static int comp_sack_nr_max = 255;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
+ {
+ .procname = "tcp_comp_sack_delay_ns",
+ .data = &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {
+ .procname = "tcp_comp_sack_nr",
+ .data = &init_net.ipv4.sysctl_tcp_comp_sack_nr,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &comp_sack_nr_max,
+ },
{
.procname = "udp_rmem_min",
.data = &init_net.ipv4.sysctl_udp_rmem_min,
{
return skb->len < size_goal &&
sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
- skb != tcp_write_queue_head(sk) &&
+ !tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
uarg->zerocopy = 0;
}
- if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+ if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+ !tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
}
EXPORT_SYMBOL(tcp_set_rcvlowat);
-/* When user wants to mmap X pages, we first need to perform the mapping
- * before freeing any skbs in receive queue, otherwise user would be unable
- * to fallback to standard recvmsg(). This happens if some data in the
- * requested block is not exactly fitting in a page.
- *
- * We only support order-0 pages for the moment.
- * mmap() on TCP is very strict, there is no point
- * trying to accommodate with pathological layouts.
- */
+#ifdef CONFIG_MMU
+static const struct vm_operations_struct tcp_vm_ops = {
+};
+
int tcp_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma)
{
- unsigned long size = vma->vm_end - vma->vm_start;
- unsigned int nr_pages = size >> PAGE_SHIFT;
- struct page **pages_array = NULL;
- u32 seq, len, offset, nr = 0;
- struct sock *sk = sock->sk;
- const skb_frag_t *frags;
+ if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+ return -EPERM;
+ vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
+
+ /* Instruct vm_insert_page() to not down_read(mmap_sem) */
+ vma->vm_flags |= VM_MIXEDMAP;
+
+ vma->vm_ops = &tcp_vm_ops;
+ return 0;
+}
+EXPORT_SYMBOL(tcp_mmap);
+
+static int tcp_zerocopy_receive(struct sock *sk,
+ struct tcp_zerocopy_receive *zc)
+{
+ unsigned long address = (unsigned long)zc->address;
+ const skb_frag_t *frags = NULL;
+ u32 length = 0, seq, offset;
+ struct vm_area_struct *vma;
+ struct sk_buff *skb = NULL;
struct tcp_sock *tp;
- struct sk_buff *skb;
int ret;
- if (vma->vm_pgoff || !nr_pages)
+ if (address & (PAGE_SIZE - 1) || address != zc->address)
return -EINVAL;
- if (vma->vm_flags & VM_WRITE)
- return -EPERM;
- /* TODO: Maybe the following is not needed if pages are COW */
- vma->vm_flags &= ~VM_MAYWRITE;
-
- lock_sock(sk);
-
- ret = -ENOTCONN;
if (sk->sk_state == TCP_LISTEN)
- goto out;
+ return -ENOTCONN;
sock_rps_record_flow(sk);
- if (tcp_inq(sk) < size) {
- ret = sock_flag(sk, SOCK_DONE) ? -EIO : -EAGAIN;
+ down_read(¤t->mm->mmap_sem);
+
+ ret = -EINVAL;
+ vma = find_vma(current->mm, address);
+ if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
goto out;
- }
+ zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
+
tp = tcp_sk(sk);
seq = tp->copied_seq;
- /* Abort if urgent data is in the area */
- if (unlikely(tp->urg_data)) {
- u32 urg_offset = tp->urg_seq - seq;
+ zc->length = min_t(u32, zc->length, tcp_inq(sk));
+ zc->length &= ~(PAGE_SIZE - 1);
- ret = -EINVAL;
- if (urg_offset < size)
- goto out;
- }
- ret = -ENOMEM;
- pages_array = kvmalloc_array(nr_pages, sizeof(struct page *),
- GFP_KERNEL);
- if (!pages_array)
- goto out;
- skb = tcp_recv_skb(sk, seq, &offset);
- ret = -EINVAL;
-skb_start:
- /* We do not support anything not in page frags */
- offset -= skb_headlen(skb);
- if ((int)offset < 0)
- goto out;
- if (skb_has_frag_list(skb))
- goto out;
- len = skb->data_len - offset;
- frags = skb_shinfo(skb)->frags;
- while (offset) {
- if (frags->size > offset)
- goto out;
- offset -= frags->size;
- frags++;
- }
- while (nr < nr_pages) {
- if (len) {
- if (len < PAGE_SIZE)
- goto out;
- if (frags->size != PAGE_SIZE || frags->page_offset)
- goto out;
- pages_array[nr++] = skb_frag_page(frags);
- frags++;
- len -= PAGE_SIZE;
- seq += PAGE_SIZE;
- continue;
+ zap_page_range(vma, address, zc->length);
+
+ zc->recv_skip_hint = 0;
+ ret = 0;
+ while (length + PAGE_SIZE <= zc->length) {
+ if (zc->recv_skip_hint < PAGE_SIZE) {
+ if (skb) {
+ skb = skb->next;
+ offset = seq - TCP_SKB_CB(skb)->seq;
+ } else {
+ skb = tcp_recv_skb(sk, seq, &offset);
+ }
+
+ zc->recv_skip_hint = skb->len - offset;
+ offset -= skb_headlen(skb);
+ if ((int)offset < 0 || skb_has_frag_list(skb))
+ break;
+ frags = skb_shinfo(skb)->frags;
+ while (offset) {
+ if (frags->size > offset)
+ goto out;
+ offset -= frags->size;
+ frags++;
+ }
}
- skb = skb->next;
- offset = seq - TCP_SKB_CB(skb)->seq;
- goto skb_start;
- }
- /* OK, we have a full set of pages ready to be inserted into vma */
- for (nr = 0; nr < nr_pages; nr++) {
- ret = vm_insert_page(vma, vma->vm_start + (nr << PAGE_SHIFT),
- pages_array[nr]);
+ if (frags->size != PAGE_SIZE || frags->page_offset)
+ break;
+ ret = vm_insert_page(vma, address + length,
+ skb_frag_page(frags));
if (ret)
- goto out;
+ break;
+ length += PAGE_SIZE;
+ seq += PAGE_SIZE;
+ zc->recv_skip_hint -= PAGE_SIZE;
+ frags++;
}
- /* operation is complete, we can 'consume' all skbs */
- tp->copied_seq = seq;
- tcp_rcv_space_adjust(sk);
-
- /* Clean up data we have read: This will do ACK frames. */
- tcp_recv_skb(sk, seq, &offset);
- tcp_cleanup_rbuf(sk, size);
-
- ret = 0;
out:
- release_sock(sk);
- kvfree(pages_array);
+ up_read(¤t->mm->mmap_sem);
+ if (length) {
+ tp->copied_seq = seq;
+ tcp_rcv_space_adjust(sk);
+
+ /* Clean up data we have read: This will do ACK frames. */
+ tcp_recv_skb(sk, seq, &offset);
+ tcp_cleanup_rbuf(sk, length);
+ ret = 0;
+ if (length == zc->length)
+ zc->recv_skip_hint = 0;
+ } else {
+ if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE))
+ ret = -EIO;
+ }
+ zc->length = length;
return ret;
}
-EXPORT_SYMBOL(tcp_mmap);
+#endif
static void tcp_update_recv_tstamps(struct sk_buff *skb,
struct scm_timestamping *tss)
}
}
+static int tcp_inq_hint(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u32 copied_seq = READ_ONCE(tp->copied_seq);
+ u32 rcv_nxt = READ_ONCE(tp->rcv_nxt);
+ int inq;
+
+ inq = rcv_nxt - copied_seq;
+ if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) {
+ lock_sock(sk);
+ inq = tp->rcv_nxt - tp->copied_seq;
+ release_sock(sk);
+ }
+ return inq;
+}
+
/*
* This routine copies from a sock struct into the user buffer.
*
u32 peek_seq;
u32 *seq;
unsigned long used;
- int err;
+ int err, inq;
int target; /* Read at least this many bytes */
long timeo;
struct sk_buff *skb, *last;
u32 urg_hole = 0;
struct scm_timestamping tss;
bool has_tss = false;
+ bool has_cmsg;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
if (sk->sk_state == TCP_LISTEN)
goto out;
+ has_cmsg = tp->recvmsg_inq;
timeo = sock_rcvtimeo(sk, nonblock);
/* Urgent data needs to be handled specially. */
if (TCP_SKB_CB(skb)->has_rxtstamp) {
tcp_update_recv_tstamps(skb, &tss);
has_tss = true;
+ has_cmsg = true;
}
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
* on connected socket. I was just happy when found this 8) --ANK
*/
- if (has_tss)
- tcp_recv_timestamp(msg, sk, &tss);
-
/* Clean up data we have read: This will do ACK frames. */
tcp_cleanup_rbuf(sk, copied);
release_sock(sk);
+
+ if (has_cmsg) {
+ if (has_tss)
+ tcp_recv_timestamp(msg, sk, &tss);
+ if (tp->recvmsg_inq) {
+ inq = tcp_inq_hint(sk);
+ put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+ }
+ }
+
return copied;
out:
dst_release(sk->sk_rx_dst);
sk->sk_rx_dst = NULL;
tcp_saved_syn_free(tp);
+ tp->compressed_ack = 0;
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
case TCP_REPAIR_QUEUE:
if (!tp->repair)
err = -EPERM;
- else if (val < TCP_QUEUES_NR)
+ else if ((unsigned int)val < TCP_QUEUES_NR)
tp->repair_queue = val;
else
err = -EINVAL;
tp->notsent_lowat = val;
sk->sk_write_space(sk);
break;
+ case TCP_INQ:
+ if (val > 1 || val < 0)
+ err = -EINVAL;
+ else
+ tp->recvmsg_inq = val;
+ break;
default:
err = -ENOPROTOOPT;
break;
case TCP_NOTSENT_LOWAT:
val = tp->notsent_lowat;
break;
+ case TCP_INQ:
+ val = tp->recvmsg_inq;
+ break;
case TCP_SAVE_SYN:
val = tp->save_syn;
break;
}
return 0;
}
+#ifdef CONFIG_MMU
+ case TCP_ZEROCOPY_RECEIVE: {
+ struct tcp_zerocopy_receive zc;
+ int err;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+ if (len != sizeof(zc))
+ return -EINVAL;
+ if (copy_from_user(&zc, optval, len))
+ return -EFAULT;
+ lock_sock(sk);
+ err = tcp_zerocopy_receive(sk, &zc);
+ release_sock(sk);
+ if (!err && copy_to_user(optval, &zc, len))
+ err = -EFAULT;
+ return err;
+ }
+#endif
default:
return -ENOPROTOOPT;
}
}
}
}
- bbr->idle_restart = 0;
+ /* Restart after idle ends only once we process a new S/ACK for data */
+ if (rs->delivered > 0)
+ bbr->idle_restart = 0;
}
static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
#include <linux/static_key.h>
-#include <linux/sock_diag.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled);
+
+void clean_acked_data_enable(struct inet_connection_sock *icsk,
+ void (*cad)(struct sock *sk, u32 ack_seq))
+{
+ icsk->icsk_clean_acked = cad;
+ static_branch_inc(&clean_acked_data_enabled);
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_enable);
+
+void clean_acked_data_disable(struct inet_connection_sock *icsk)
+{
+ static_branch_dec(&clean_acked_data_enabled);
+ icsk->icsk_clean_acked = NULL;
+}
+EXPORT_SYMBOL_GPL(clean_acked_data_disable);
+#endif
+
static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
unsigned int len)
{
tp->undo_retrans = tp->retrans_out ? : -1;
}
-/* Enter Loss state. If we detect SACK reneging, forget all SACK information
+static bool tcp_is_rack(const struct sock *sk)
+{
+ return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+}
+
+/* If we detect SACK reneging, forget all SACK information
* and reset tags completely, otherwise preserve SACKs. If receiver
* dropped its ofo queue, we will know this due to reneging detection.
*/
+static void tcp_timeout_mark_lost(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb, *head;
+ bool is_reneg; /* is receiver reneging on SACKs? */
+
+ head = tcp_rtx_queue_head(sk);
+ is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED);
+ if (is_reneg) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
+ tp->sacked_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
+ } else if (tcp_is_reno(tp)) {
+ tcp_reset_reno_sack(tp);
+ }
+
+ skb = head;
+ skb_rbtree_walk_from(skb) {
+ if (is_reneg)
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
+ else if (tcp_is_rack(sk) && skb != head &&
+ tcp_rack_skb_timeout(tp, skb, 0) > 0)
+ continue; /* Don't mark recently sent ones lost yet */
+ tcp_mark_skb_lost(sk, skb);
+ }
+ tcp_verify_left_out(tp);
+ tcp_clear_all_retrans_hints(tp);
+}
+
+/* Enter Loss state. */
void tcp_enter_loss(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
- struct sk_buff *skb;
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
- bool is_reneg; /* is receiver reneging on SACKs? */
- bool mark_lost;
+
+ tcp_timeout_mark_lost(sk);
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
tcp_ca_event(sk, CA_EVENT_LOSS);
tcp_init_undo(tp);
}
- tp->snd_cwnd = 1;
+ tp->snd_cwnd = tcp_packets_in_flight(tp) + 1;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_jiffies32;
- tp->retrans_out = 0;
- tp->lost_out = 0;
-
- if (tcp_is_reno(tp))
- tcp_reset_reno_sack(tp);
-
- skb = tcp_rtx_queue_head(sk);
- is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
- if (is_reneg) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
- tp->sacked_out = 0;
- /* Mark SACK reneging until we recover from this loss event. */
- tp->is_sack_reneg = 1;
- }
- tcp_clear_all_retrans_hints(tp);
-
- skb_rbtree_walk_from(skb) {
- mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
- is_reneg);
- if (mark_lost)
- tcp_sum_lost(tp, skb);
- TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
- if (mark_lost) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- }
- }
- tcp_verify_left_out(tp);
-
/* Timeout in disordered state after receiving substantial DUPACKs
* suggests that the degree of reordering is over-estimated.
*/
return true;
/* Not-A-Trick#2 : Classic rule... */
- if (tcp_dupack_heuristics(tp) > tp->reordering)
+ if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
return true;
return false;
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_reno(tp)) {
- tcp_mark_head_lost(sk, 1, 1);
- } else {
+ if (tcp_is_sack(tp)) {
int sacked_upto = tp->sacked_out - tp->reordering;
if (sacked_upto >= 0)
tcp_mark_head_lost(sk, sacked_upto, 0);
return false;
}
-static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
+static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
{
struct tcp_sock *tp = tcp_sk(sk);
- /* Use RACK to detect loss */
- if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+ if (tcp_rtx_queue_empty(sk))
+ return;
+
+ if (unlikely(tcp_is_reno(tp))) {
+ tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED);
+ } else if (tcp_is_rack(sk)) {
u32 prior_retrans = tp->retrans_out;
tcp_rack_mark_lost(sk);
tcp_try_keep_open(sk);
return;
}
- tcp_rack_identify_loss(sk, ack_flag);
+ tcp_identify_packet_loss(sk, ack_flag);
break;
case TCP_CA_Loss:
tcp_process_loss(sk, flag, is_dupack, rexmit);
- tcp_rack_identify_loss(sk, ack_flag);
+ tcp_identify_packet_loss(sk, ack_flag);
if (!(icsk->icsk_ca_state == TCP_CA_Open ||
(*ack_flag & FLAG_LOST_RETRANS)))
return;
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
- tcp_rack_identify_loss(sk, ack_flag);
+ tcp_identify_packet_loss(sk, ack_flag);
if (!tcp_time_to_recover(sk, flag)) {
tcp_try_to_open(sk, flag);
return;
fast_rexmit = 1;
}
- if (do_lost)
+ if (!tcp_is_rack(sk) && do_lost)
tcp_update_scoreboard(sk, fast_rexmit);
*rexmit = REXMIT_LOST;
}
if (after(ack, prior_snd_una)) {
flag |= FLAG_SND_UNA_ADVANCED;
icsk->icsk_retransmits = 0;
+
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+ if (static_branch_unlikely(&clean_acked_data_enabled))
+ if (icsk->icsk_clean_acked)
+ icsk->icsk_clean_acked(sk, ack);
+#endif
}
prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
* If the sack array is full, forget about the last one.
*/
if (this_sack >= TCP_NUM_SACKS) {
+ if (tp->compressed_ack)
+ tcp_send_ack(sk);
this_sack--;
tp->rx_opt.num_sacks--;
sp--;
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
goto out_of_window;
- tcp_enter_quickack_mode(sk);
-
if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
/* Partial packet, seq < rcv_next < end_seq */
SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
{
struct tcp_sock *tp = tcp_sk(sk);
+ unsigned long rtt, delay;
/* More than one full frame received... */
if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
(tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
__tcp_select_window(sk) >= tp->rcv_wnd)) ||
/* We ACK each frame or... */
- tcp_in_quickack_mode(sk) ||
- /* We have out of order data. */
- (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) {
- /* Then ack it now */
+ tcp_in_quickack_mode(sk)) {
+send_now:
tcp_send_ack(sk);
- } else {
- /* Else, send delayed ack. */
+ return;
+ }
+
+ if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
tcp_send_delayed_ack(sk);
+ return;
}
+
+ if (!tcp_is_sack(tp) ||
+ tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ goto send_now;
+ tp->compressed_ack++;
+
+ if (hrtimer_is_queued(&tp->compressed_ack_timer))
+ return;
+
+ /* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */
+
+ rtt = tp->rcv_rtt_est.rtt_us;
+ if (tp->srtt_us && tp->srtt_us < rtt)
+ rtt = tp->srtt_us;
+
+ delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ rtt * (NSEC_PER_USEC >> 3)/20);
+ sock_hold(sk);
+ hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
+ HRTIMER_MODE_REL_PINNED_SOFT);
}
static inline void tcp_ack_snd_check(struct sock *sk)
#if IS_ENABLED(CONFIG_IPV6)
ireq->pktopts = NULL;
#endif
+ atomic64_set(&ireq->ir_cookie, 0);
ireq->ireq_state = TCP_NEW_SYN_RECV;
write_pnet(&ireq->ireq_net, sock_net(sk_listener));
ireq->ireq_family = sk_listener->sk_family;
-
- BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
- offsetof(struct sock, sk_cookie));
- BUILD_BUG_ON(offsetof(struct inet_request_sock, ireq_net) !=
- offsetof(struct sock, sk_net));
- sock_init_cookie((struct sock *)ireq);
}
return req;
struct sock *sk1 = NULL;
#endif
struct net *net;
+ struct sock *ctl_sk;
/* Never send a reset in response to a reset. */
if (th->rst)
arg.tos = ip_hdr(skb)->tos;
arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
+ if (sk)
+ ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_mark : sk->sk_mark;
+ ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len);
+ ctl_sk->sk_mark = 0;
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
local_bh_enable();
} rep;
struct net *net = sock_net(sk);
struct ip_reply_arg arg;
+ struct sock *ctl_sk;
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
arg.tos = tos;
arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk);
+ if (sk)
+ ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_mark : sk->sk_mark;
+ ip_send_unicast_reply(ctl_sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len);
+ ctl_sk->sk_mark = 0;
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
local_bh_enable();
}
init_net.ipv4.sysctl_tcp_wmem,
sizeof(init_net.ipv4.sysctl_tcp_wmem));
}
+ net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
+ net->ipv4.sysctl_tcp_comp_sack_nr = 44;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
struct inet_sock *inet = inet_sk(sk);
tw->tw_transparent = inet->transparent;
+ tw->tw_mark = sk->sk_mark;
tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale;
tcptw->tw_rcv_nxt = tp->rcv_nxt;
tcptw->tw_snd_nxt = tp->snd_nxt;
/* Account for an ACK we sent. */
static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (unlikely(tp->compressed_ack)) {
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
+ tp->compressed_ack);
+ tp->compressed_ack = 0;
+ if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
+ __sock_put(sk);
+ }
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
}
}
- if (mss > (1 << *rcv_wscale)) {
- if (!init_rcv_wnd) /* Use default unless specified otherwise */
- init_rcv_wnd = tcp_default_init_rwnd(mss);
- *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
- }
+ if (!init_rcv_wnd) /* Use default unless specified otherwise */
+ init_rcv_wnd = tcp_default_init_rwnd(mss);
+ *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
/* Set the clamp no higher than max representable value */
(*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
+ *md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- *md5 = tp->af_specific->md5_lookup(sk, sk);
- if (*md5) {
- opts->options |= OPTION_MD5;
- remaining -= TCPOLEN_MD5SIG_ALIGNED;
+ if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ remaining -= TCPOLEN_MD5SIG_ALIGNED;
+ }
}
-#else
- *md5 = NULL;
#endif
/* We always get an MSS option. The option bytes which will be seen in
opts->options = 0;
+ *md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- *md5 = tp->af_specific->md5_lookup(sk, sk);
- if (unlikely(*md5)) {
- opts->options |= OPTION_MD5;
- size += TCPOLEN_MD5SIG_ALIGNED;
+ if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ size += TCPOLEN_MD5SIG_ALIGNED;
+ }
}
-#else
- *md5 = NULL;
#endif
if (likely(tp->rx_opt.tstamp_ok)) {
};
static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet);
-static void tcp_tsq_handler(struct sock *sk)
+static void tcp_tsq_write(struct sock *sk)
{
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
0, GFP_ATOMIC);
}
}
+
+static void tcp_tsq_handler(struct sock *sk)
+{
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ tcp_tsq_write(sk);
+ else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
+ sock_hold(sk);
+ bh_unlock_sock(sk);
+}
/*
* One tasklet per cpu tries to send more skbs.
* We run in tasklet context but need to disable irqs when
smp_mb__before_atomic();
clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags);
- if (!sk->sk_lock.owned &&
- test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) {
- bh_lock_sock(sk);
- if (!sock_owned_by_user(sk)) {
- clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags);
- tcp_tsq_handler(sk);
- }
- bh_unlock_sock(sk);
- }
-
+ tcp_tsq_handler(sk);
sk_free(sk);
}
}
nflags = flags & ~TCP_DEFERRED_ALL;
} while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags);
- if (flags & TCPF_TSQ_DEFERRED)
- tcp_tsq_handler(sk);
-
+ if (flags & TCPF_TSQ_DEFERRED) {
+ tcp_tsq_write(sk);
+ __sock_put(sk);
+ }
/* Here begins the tricky part :
* We are called from release_sock() with :
* 1) BH disabled
if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED))
goto out;
- nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED;
+ nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED;
nval = cmpxchg(&sk->sk_tsq_flags, oval, nval);
if (nval != oval)
continue;
sk_free(sk);
}
-/* Note: Called under hard irq.
- * We can not call TCP stack right away.
+/* Note: Called under soft irq.
+ * We can call TCP stack right away, unless socket is owned by user.
*/
enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
{
struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer);
struct sock *sk = (struct sock *)tp;
- unsigned long nval, oval;
- for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) {
- struct tsq_tasklet *tsq;
- bool empty;
-
- if (oval & TSQF_QUEUED)
- break;
-
- nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED;
- nval = cmpxchg(&sk->sk_tsq_flags, oval, nval);
- if (nval != oval)
- continue;
+ tcp_tsq_handler(sk);
+ sock_put(sk);
- if (!refcount_inc_not_zero(&sk->sk_wmem_alloc))
- break;
- /* queue this socket to tasklet queue */
- tsq = this_cpu_ptr(&tsq_tasklet);
- empty = list_empty(&tsq->head);
- list_add(&tp->tsq_node, &tsq->head);
- if (empty)
- tasklet_schedule(&tsq->tasklet);
- break;
- }
return HRTIMER_NORESTART;
}
do_div(len_ns, rate);
hrtimer_start(&tcp_sk(sk)->pacing_timer,
ktime_add_ns(ktime_get(), len_ns),
- HRTIMER_MODE_ABS_PINNED);
+ HRTIMER_MODE_ABS_PINNED_SOFT);
+ sock_hold(sk);
}
static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
/* if no packet is in qdisc/device queue, then allow XPS to select
* another queue. We can be called from tcp_tsq_handler()
- * which holds one reference to sk_wmem_alloc.
+ * which holds one reference to sk.
*
* TODO: Ideally, in-flight pure ACK packets should not matter here.
* One way to get this would be to set skb->truesize = 2 on them.
static bool tcp_pacing_check(const struct sock *sk)
{
return tcp_needs_internal_pacing(sk) &&
- hrtimer_active(&tcp_sk(sk)->pacing_timer);
+ hrtimer_is_queued(&tcp_sk(sk)->pacing_timer);
}
/* TCP Small Queues :
skb, limit, mss_now, gfp)))
break;
- if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
- clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags);
if (tcp_small_queue_check(sk, skb, 0))
break;
return -EBUSY;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
- if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- BUG();
+ if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
tcp_init_wl(tp, 0);
+ tcp_write_queue_purge(sk);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
#include <linux/tcp.h>
#include <net/tcp.h>
-static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
+void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
return t1 > t2 || (t1 == t2 && after(seq1, seq2));
}
+static u32 tcp_rack_reo_wnd(const struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tp->rack.reord) {
+ /* If reordering has not been observed, be aggressive during
+ * the recovery or starting the recovery by DUPACK threshold.
+ */
+ if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery)
+ return 0;
+
+ if (tp->sacked_out >= tp->reordering &&
+ !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH))
+ return 0;
+ }
+
+ /* To be more reordering resilient, allow min_rtt/4 settling delay.
+ * Use min_rtt instead of the smoothed RTT because reordering is
+ * often a path property and less related to queuing or delayed ACKs.
+ * Upon receiving DSACKs, linearly increase the window up to the
+ * smoothed RTT.
+ */
+ return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps,
+ tp->srtt_us >> 3);
+}
+
+s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd)
+{
+ return tp->rack.rtt_us + reo_wnd -
+ tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+}
+
/* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01):
*
* Marks a packet lost, if some packet sent later has been (s)acked.
static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
{
struct tcp_sock *tp = tcp_sk(sk);
- u32 min_rtt = tcp_min_rtt(tp);
struct sk_buff *skb, *n;
u32 reo_wnd;
*reo_timeout = 0;
- /* To be more reordering resilient, allow min_rtt/4 settling delay
- * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed
- * RTT because reordering is often a path property and less related
- * to queuing or delayed ACKs.
- */
- reo_wnd = 1000;
- if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) &&
- min_rtt != ~0U) {
- reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
- reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
- }
-
+ reo_wnd = tcp_rack_reo_wnd(sk);
list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
tcp_tsorted_anchor) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
/* A packet is lost if it has not been s/acked beyond
* the recent RTT plus the reordering window.
*/
- remaining = tp->rack.rtt_us + reo_wnd -
- tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+ remaining = tcp_rack_skb_timeout(tp, skb, reo_wnd);
if (remaining <= 0) {
- tcp_rack_mark_skb_lost(sk, skb);
+ tcp_mark_skb_lost(sk, skb);
list_del_init(&skb->tcp_tsorted_anchor);
} else {
/* Record maximum wait time */
tp->rack.reo_wnd_steps = 1;
}
}
+
+/* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits
+ * the next unacked packet upon receiving
+ * a) three or more DUPACKs to start the fast recovery
+ * b) an ACK acknowledging new data during the fast recovery.
+ */
+void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced)
+{
+ const u8 state = inet_csk(sk)->icsk_ca_state;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if ((state < TCP_CA_Recovery && tp->sacked_out >= tp->reordering) ||
+ (state == TCP_CA_Recovery && snd_una_advanced)) {
+ struct sk_buff *skb = tcp_rtx_queue_head(sk);
+ u32 mss;
+
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
+ return;
+
+ mss = tcp_skb_mss(skb);
+ if (tcp_skb_pcount(skb) > 1 && skb->len > mss)
+ tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+ mss, mss, GFP_ATOMIC);
+
+ tcp_skb_mark_lost_uncond_verify(tp, skb);
+ }
+}
sock_put(sk);
}
+static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
+{
+ struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer);
+ struct sock *sk = (struct sock *)tp;
+
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk)) {
+ if (tp->compressed_ack)
+ tcp_send_ack(sk);
+ } else {
+ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
+ &sk->sk_tsq_flags))
+ sock_hold(sk);
+ }
+ bh_unlock_sock(sk);
+
+ sock_put(sk);
+
+ return HRTIMER_NORESTART;
+}
+
void tcp_init_xmit_timers(struct sock *sk)
{
inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
&tcp_keepalive_timer);
hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS_PINNED);
+ HRTIMER_MODE_ABS_PINNED_SOFT);
tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
+
+ hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL_PINNED_SOFT);
+ tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick;
}
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score += 4;
}
}
EXPORT_SYMBOL(udp_set_csum);
-static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
+static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
+ struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
uh->len = htons(len);
uh->check = 0;
+ if (cork->gso_size) {
+ const int hlen = skb_network_header_len(skb) +
+ sizeof(struct udphdr);
+
+ if (hlen + cork->gso_size > cork->fragsize)
+ return -EINVAL;
+ if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+ return -EINVAL;
+ if (sk->sk_no_check_tx)
+ return -EINVAL;
+ if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite)
+ return -EIO;
+
+ skb_shinfo(skb)->gso_size = cork->gso_size;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh),
+ cork->gso_size);
+ goto csum_partial;
+ }
+
if (is_udplite) /* UDP-Lite */
csum = udplite_csum(skb);
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+csum_partial:
udp4_hwcsum(skb, fl4->saddr, fl4->daddr);
goto send;
if (!skb)
goto out;
- err = udp_send_skb(skb, fl4);
+ err = udp_send_skb(skb, fl4, &inet->cork.base);
out:
up->len = 0;
}
EXPORT_SYMBOL(udp_push_pending_frames);
+static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size)
+{
+ switch (cmsg->cmsg_type) {
+ case UDP_SEGMENT:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16)))
+ return -EINVAL;
+ *gso_size = *(__u16 *)CMSG_DATA(cmsg);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
+int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size)
+{
+ struct cmsghdr *cmsg;
+ bool need_ip = false;
+ int err;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+
+ if (cmsg->cmsg_level != SOL_UDP) {
+ need_ip = true;
+ continue;
+ }
+
+ err = __udp_cmsg_send(cmsg, gso_size);
+ if (err)
+ return err;
+ }
+
+ return need_ip;
+}
+EXPORT_SYMBOL_GPL(udp_cmsg_send);
+
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
ipc.sockc.tsflags = sk->sk_tsflags;
ipc.addr = inet->inet_saddr;
ipc.oif = sk->sk_bound_dev_if;
+ ipc.gso_size = up->gso_size;
if (msg->msg_controllen) {
- err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
- if (unlikely(err)) {
+ err = udp_cmsg_send(sk, msg, &ipc.gso_size);
+ if (err > 0)
+ err = ip_cmsg_send(sk, msg, &ipc,
+ sk->sk_family == AF_INET6);
+ if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
if (ipc.opt && ipc.opt->opt.srr) {
- if (!daddr)
- return -EINVAL;
+ if (!daddr) {
+ err = -EINVAL;
+ goto out_free;
+ }
faddr = ipc.opt->opt.faddr;
connected = 0;
}
/* Lockless fast path for the non-corking case. */
if (!corkreq) {
+ struct inet_cork cork;
+
skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc, &rt,
- msg->msg_flags);
+ &cork, msg->msg_flags);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
- err = udp_send_skb(skb, fl4);
+ err = udp_send_skb(skb, fl4, &cork);
goto out;
}
out:
ip_rt_put(rt);
+out_free:
if (free)
kfree(ipc.opt);
if (!err)
return 0;
}
-static struct static_key udp_encap_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
void udp_encap_enable(void)
{
- static_key_enable(&udp_encap_needed);
+ static_branch_enable(&udp_encap_needed_key);
}
EXPORT_SYMBOL(udp_encap_enable);
goto drop;
nf_reset(skb);
- if (static_key_false(&udp_encap_needed) && up->encap_type) {
+ if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
bool slow = lock_sock_fast(sk);
udp_flush_pending_frames(sk);
unlock_sock_fast(sk, slow);
- if (static_key_false(&udp_encap_needed) && up->encap_type) {
+ if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
void (*encap_destroy)(struct sock *sk);
encap_destroy = READ_ONCE(up->encap_destroy);
if (encap_destroy)
up->no_check6_rx = valbool;
break;
+ case UDP_SEGMENT:
+ if (val < 0 || val > USHRT_MAX)
+ return -EINVAL;
+ up->gso_size = val;
+ break;
+
/*
* UDP-Lite's partial checksum coverage (RFC 3828).
*/
val = up->no_check6_rx;
break;
+ case UDP_SEGMENT:
+ val = up->gso_size;
+ break;
+
/* The following two cannot be changed on UDP sockets, the return is
* always 0 (which corresponds to the full checksum coverage of UDP). */
case UDPLITE_SEND_CSCOV:
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
+struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features)
+{
+ struct sock *sk = gso_skb->sk;
+ unsigned int sum_truesize = 0;
+ struct sk_buff *segs, *seg;
+ struct udphdr *uh;
+ unsigned int mss;
+ bool copy_dtor;
+ __sum16 check;
+ __be16 newlen;
+
+ mss = skb_shinfo(gso_skb)->gso_size;
+ if (gso_skb->len <= sizeof(*uh) + mss)
+ return ERR_PTR(-EINVAL);
+
+ skb_pull(gso_skb, sizeof(*uh));
+
+ /* clear destructor to avoid skb_segment assigning it to tail */
+ copy_dtor = gso_skb->destructor == sock_wfree;
+ if (copy_dtor)
+ gso_skb->destructor = NULL;
+
+ segs = skb_segment(gso_skb, features);
+ if (unlikely(IS_ERR_OR_NULL(segs))) {
+ if (copy_dtor)
+ gso_skb->destructor = sock_wfree;
+ return segs;
+ }
+
+ /* GSO partial and frag_list segmentation only requires splitting
+ * the frame into an MSS multiple and possibly a remainder, both
+ * cases return a GSO skb. So update the mss now.
+ */
+ if (skb_is_gso(segs))
+ mss *= skb_shinfo(segs)->gso_segs;
+
+ seg = segs;
+ uh = udp_hdr(seg);
+
+ /* compute checksum adjustment based on old length versus new */
+ newlen = htons(sizeof(*uh) + mss);
+ check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
+
+ for (;;) {
+ if (copy_dtor) {
+ seg->destructor = sock_wfree;
+ seg->sk = sk;
+ sum_truesize += seg->truesize;
+ }
+
+ if (!seg->next)
+ break;
+
+ uh->len = newlen;
+ uh->check = check;
+
+ if (seg->ip_summed == CHECKSUM_PARTIAL)
+ gso_reset_checksum(seg, ~check);
+ else
+ uh->check = gso_make_checksum(seg, ~check) ? :
+ CSUM_MANGLED_0;
+
+ seg = seg->next;
+ uh = udp_hdr(seg);
+ }
+
+ /* last packet can be partial gso_size, account for that in checksum */
+ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) +
+ seg->data_len);
+ check = csum16_add(csum16_sub(uh->check, uh->len), newlen);
+
+ uh->len = newlen;
+ uh->check = check;
+
+ if (seg->ip_summed == CHECKSUM_PARTIAL)
+ gso_reset_checksum(seg, ~check);
+ else
+ uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0;
+
+ /* update refcount for the packet */
+ if (copy_dtor) {
+ int delta = sum_truesize - gso_skb->truesize;
+
+ /* In some pathological cases, delta can be negative.
+ * We need to either use refcount_add() or refcount_sub_and_test()
+ */
+ if (likely(delta >= 0))
+ refcount_add(delta, &sk->sk_wmem_alloc);
+ else
+ WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+ }
+ return segs;
+}
+EXPORT_SYMBOL_GPL(__udp_gso_segment);
+
static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
goto out;
}
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+ if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ return __udp_gso_segment(skb, features);
+
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
bool "IPv6: Route Information (RFC 4191) support"
depends on IPV6_ROUTER_PREF
---help---
- This is experimental support of Route Information.
+ Support of Route Information.
If unsure, say N.
config IPV6_OPTIMISTIC_DAD
bool "IPv6: Enable RFC 4429 Optimistic DAD"
---help---
- This is experimental support for optimistic Duplicate
- Address Detection. It allows for autoconfigured addresses
- to be used more quickly.
+ Support for optimistic Duplicate Address Detection. It allows for
+ autoconfigured addresses to be used more quickly.
If unsure, say N.
depends on IPV6
select IP_MROUTE_COMMON
---help---
- Experimental support for IPv6 multicast forwarding.
+ Support for IPv6 multicast forwarding.
If unsure, say N.
config IPV6_MROUTE_MULTIPLE_TABLES
struct net *net = dev_net(dev);
struct inet6_dev *idev;
struct inet6_ifaddr *ifa, *tmp;
- int _keep_addr;
- bool keep_addr;
+ bool keep_addr = false;
int state, i;
ASSERT_RTNL();
}
- /* aggregate the system setting and interface setting */
- _keep_addr = net->ipv6.devconf_all->keep_addr_on_down;
- if (!_keep_addr)
- _keep_addr = idev->cnf.keep_addr_on_down;
-
/* combine the user config with event to determine if permanent
* addresses are to be removed from address hash table
*/
- keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6);
+ if (!how && !idev->cnf.disable_ipv6) {
+ /* aggregate the system setting and interface setting */
+ int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down;
+
+ if (!_keep_addr)
+ _keep_addr = idev->cnf.keep_addr_on_down;
+
+ keep_addr = (_keep_addr > 0);
+ }
/* Step 2: clear hash table */
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
write_lock_bh(&idev->lock);
}
- /* re-combine the user config with event to determine if permanent
- * addresses are to be removed from the interface list
- */
- keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
-
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
struct fib6_info *rt = NULL;
bool keep;
return -EAFNOSUPPORT;
}
+static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int flags)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ int flags)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb, int strict)
+{
+ return f6i;
+}
+
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
- .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+ .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+ .fib6_get_table = eafnosupport_fib6_get_table,
+ .fib6_table_lookup = eafnosupport_fib6_table_lookup,
+ .fib6_lookup = eafnosupport_fib6_lookup,
+ .fib6_multipath_select = eafnosupport_fib6_multipath_select,
};
EXPORT_SYMBOL_GPL(ipv6_stub);
.getsockopt = sock_common_getsockopt, /* ok */
.sendmsg = inet_sendmsg, /* ok */
.recvmsg = inet_recvmsg, /* ok */
+#ifdef CONFIG_MMU
.mmap = tcp_mmap,
+#endif
.sendpage = inet_sendpage,
.sendmsg_locked = tcp_sendmsg_locked,
.sendpage_locked = tcp_sendpage_locked,
static const struct ipv6_stub ipv6_stub_impl = {
.ipv6_sock_mc_join = ipv6_sock_mc_join,
.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
- .ipv6_dst_lookup = ip6_dst_lookup,
+ .ipv6_dst_lookup = ip6_dst_lookup,
+ .fib6_get_table = fib6_get_table,
+ .fib6_table_lookup = fib6_table_lookup,
+ .fib6_lookup = fib6_lookup,
+ .fib6_multipath_select = fib6_multipath_select,
.udpv6_encap_enable = udpv6_encap_enable,
.ndisc_send_na = ndisc_send_na,
.nd_tbl = &nd_tbl,
* if target < 0. "last header" is transport protocol header, ESP, or
* "No next header".
*
- * Note that *offset is used as input/output parameter. an if it is not zero,
+ * Note that *offset is used as input/output parameter, and if it is not zero,
* then it must be a valid offset to an inner IPv6 header. This can be used
* to explore inner IPv6 header, eg. ICMPv6 error messages.
*
return fib_rules_seq_read(net, AF_INET6);
}
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ int flags)
+{
+ struct fib6_info *f6i;
+ int err;
+
+ if (net->ipv6.fib6_has_custom_rules) {
+ struct fib_lookup_arg arg = {
+ .lookup_ptr = fib6_table_lookup,
+ .lookup_data = &oif,
+ .flags = FIB_LOOKUP_NOREF,
+ };
+
+ l3mdev_update_flow(net, flowi6_to_flowi(fl6));
+
+ err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
+ flowi6_to_flowi(fl6), flags, &arg);
+ if (err)
+ return ERR_PTR(err);
+
+ f6i = arg.result ? : net->ipv6.fib6_null_entry;
+ } else {
+ f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
+ oif, fl6, flags);
+ if (!f6i || f6i == net->ipv6.fib6_null_entry)
+ f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+ oif, fl6, flags);
+ }
+
+ return f6i;
+}
+
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
const struct sk_buff *skb,
int flags, pol_lookup_t lookup)
return &net->ipv6.ip6_null_entry->dst;
}
-static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
- int flags, struct fib_lookup_arg *arg)
+static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
+ struct flowi6 *flp6, const struct net_device *dev)
+{
+ struct fib6_rule *r = (struct fib6_rule *)rule;
+
+ /* If we need to find a source address for this traffic,
+ * we check the result if it meets requirement of the rule.
+ */
+ if ((rule->flags & FIB_RULE_FIND_SADDR) &&
+ r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
+ struct in6_addr saddr;
+
+ if (ipv6_dev_get_saddr(net, dev, &flp6->daddr,
+ rt6_flags2srcprefs(flags), &saddr))
+ return -EAGAIN;
+
+ if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen))
+ return -EAGAIN;
+
+ flp6->saddr = saddr;
+ }
+
+ return 0;
+}
+
+static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
+{
+ struct flowi6 *flp6 = &flp->u.ip6;
+ struct net *net = rule->fr_net;
+ struct fib6_table *table;
+ struct fib6_info *f6i;
+ int err = -EAGAIN, *oif;
+ u32 tb_id;
+
+ switch (rule->action) {
+ case FR_ACT_TO_TBL:
+ break;
+ case FR_ACT_UNREACHABLE:
+ return -ENETUNREACH;
+ case FR_ACT_PROHIBIT:
+ return -EACCES;
+ case FR_ACT_BLACKHOLE:
+ default:
+ return -EINVAL;
+ }
+
+ tb_id = fib_rule_get_table(rule, arg);
+ table = fib6_get_table(net, tb_id);
+ if (!table)
+ return -EAGAIN;
+
+ oif = (int *)arg->lookup_data;
+ f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
+ if (f6i != net->ipv6.fib6_null_entry) {
+ err = fib6_rule_saddr(net, rule, flags, flp6,
+ fib6_info_nh_dev(f6i));
+
+ if (likely(!err))
+ arg->result = f6i;
+ }
+
+ return err;
+}
+
+static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
{
struct flowi6 *flp6 = &flp->u.ip6;
struct rt6_info *rt = NULL;
rt = lookup(net, table, flp6, arg->lookup_data, flags);
if (rt != net->ipv6.ip6_null_entry) {
- struct fib6_rule *r = (struct fib6_rule *)rule;
-
- /*
- * If we need to find a source address for this traffic,
- * we check the result if it meets requirement of the rule.
- */
- if ((rule->flags & FIB_RULE_FIND_SADDR) &&
- r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
- struct in6_addr saddr;
-
- if (ipv6_dev_get_saddr(net,
- ip6_dst_idev(&rt->dst)->dev,
- &flp6->daddr,
- rt6_flags2srcprefs(flags),
- &saddr))
- goto again;
- if (!ipv6_prefix_equal(&saddr, &r->src.addr,
- r->src.plen))
- goto again;
- flp6->saddr = saddr;
- }
+ err = fib6_rule_saddr(net, rule, flags, flp6,
+ ip6_dst_idev(&rt->dst)->dev);
+
+ if (err == -EAGAIN)
+ goto again;
+
err = rt->dst.error;
if (err != -EAGAIN)
goto out;
return err;
}
+static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
+{
+ if (arg->lookup_ptr == fib6_table_lookup)
+ return fib6_rule_action_alt(rule, flp, flags, arg);
+
+ return __fib6_rule_action(rule, flp, flags, arg);
+}
+
static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
{
struct rt6_info *rt = (struct rt6_info *) arg->result;
return &rt->dst;
}
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ int flags)
+{
+ return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+}
+
static void __net_init fib6_tables_init(struct net *net)
{
fib6_link_table(net, net->ipv6.fib6_main_tbl);
ins = &fn->leaf;
for (iter = leaf; iter;
- iter = rcu_dereference_protected(iter->rt6_next,
+ iter = rcu_dereference_protected(iter->fib6_next,
lockdep_is_held(&rt->fib6_table->tb6_lock))) {
/*
* Search for duplicates
break;
next_iter:
- ins = &iter->rt6_next;
+ ins = &iter->fib6_next;
}
if (fallback_ins && !found) {
&sibling->fib6_siblings);
break;
}
- sibling = rcu_dereference_protected(sibling->rt6_next,
+ sibling = rcu_dereference_protected(sibling->fib6_next,
lockdep_is_held(&rt->fib6_table->tb6_lock));
}
/* For each sibling in the list, increment the counter of
if (err)
return err;
- rcu_assign_pointer(rt->rt6_next, iter);
+ rcu_assign_pointer(rt->fib6_next, iter);
atomic_inc(&rt->fib6_ref);
rcu_assign_pointer(rt->fib6_node, fn);
rcu_assign_pointer(*ins, rt);
atomic_inc(&rt->fib6_ref);
rcu_assign_pointer(rt->fib6_node, fn);
- rt->rt6_next = iter->rt6_next;
+ rt->fib6_next = iter->fib6_next;
rcu_assign_pointer(*ins, rt);
if (!info->skip_notify)
inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
- ins = &rt->rt6_next;
+ ins = &rt->fib6_next;
iter = rcu_dereference_protected(*ins,
lockdep_is_held(&rt->fib6_table->tb6_lock));
while (iter) {
if (iter->fib6_metric > rt->fib6_metric)
break;
if (rt6_qualify_for_ecmp(iter)) {
- *ins = iter->rt6_next;
+ *ins = iter->fib6_next;
iter->fib6_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
nsiblings--;
info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
} else {
- ins = &iter->rt6_next;
+ ins = &iter->fib6_next;
}
iter = rcu_dereference_protected(*ins,
lockdep_is_held(&rt->fib6_table->tb6_lock));
const struct in6_addr *addr; /* search key */
};
-static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
- struct lookup_args *args)
+static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root,
+ struct lookup_args *args)
{
struct fib6_node *fn;
__be32 dir;
#ifdef CONFIG_IPV6_SUBTREES
if (subtree) {
struct fib6_node *sfn;
- sfn = fib6_lookup_1(subtree, args + 1);
+ sfn = fib6_node_lookup_1(subtree,
+ args + 1);
if (!sfn)
goto backtrack;
fn = sfn;
/* called with rcu_read_lock() held
*/
-struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
- const struct in6_addr *saddr)
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct fib6_node *fn;
struct lookup_args args[] = {
}
};
- fn = fib6_lookup_1(root, daddr ? args : args + 1);
+ fn = fib6_node_lookup_1(root, daddr ? args : args + 1);
if (!fn || fn->fn_flags & RTN_TL_ROOT)
fn = root;
RT6_TRACE("fib6_del_route\n");
/* Unlink it */
- *rtp = rt->rt6_next;
+ *rtp = rt->fib6_next;
rt->fib6_node = NULL;
net->ipv6.rt6_stats->fib_rt_entries--;
net->ipv6.rt6_stats->fib_discarded_routes++;
FOR_WALKERS(net, w) {
if (w->state == FWS_C && w->leaf == rt) {
RT6_TRACE("walker %p adjusted by delroute\n", w);
- w->leaf = rcu_dereference_protected(rt->rt6_next,
+ w->leaf = rcu_dereference_protected(rt->fib6_next,
lockdep_is_held(&table->tb6_lock));
if (!w->leaf)
w->state = FWS_U;
fib6_del_route(table, fn, rtp, info);
return 0;
}
- rtp_next = &cur->rt6_next;
+ rtp_next = &cur->fib6_next;
}
return -ENOENT;
}
do {
iter->w.leaf = rcu_dereference_protected(
- iter->w.leaf->rt6_next,
+ iter->w.leaf->fib6_next,
lockdep_is_held(&iter->tbl->tb6_lock));
iter->skip--;
if (!iter->skip && iter->w.leaf)
if (!v)
goto iter_table;
- n = rcu_dereference_bh(((struct fib6_info *)v)->rt6_next);
+ n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next);
if (n) {
++*pos;
return n;
struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
struct ip6_tnl __rcu *collect_md_tun;
+ struct ip6_tnl __rcu *collect_md_tun_erspan;
struct net_device *fb_tunnel_dev;
};
static void ip6gre_tunnel_setup(struct net_device *dev);
static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu);
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu);
/* Tunnel hash table */
if (cand)
return cand;
- t = rcu_dereference(ign->collect_md_tun);
+ if (gre_proto == htons(ETH_P_ERSPAN) ||
+ gre_proto == htons(ETH_P_ERSPAN2))
+ t = rcu_dereference(ign->collect_md_tun_erspan);
+ else
+ t = rcu_dereference(ign->collect_md_tun);
+
if (t && t->dev->flags & IFF_UP)
return t;
return &ign->tunnels[prio][h];
}
+static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, t);
+}
+
+static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun_erspan, t);
+}
+
+static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, NULL);
+}
+
+static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign,
+ struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun_erspan, NULL);
+}
+
static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign,
const struct ip6_tnl *t)
{
{
struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
- if (t->parms.collect_md)
- rcu_assign_pointer(ign->collect_md_tun, t);
-
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
- if (t->parms.collect_md)
- rcu_assign_pointer(ign->collect_md_tun, NULL);
-
for (tp = ip6gre_bucket(ign, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
return NULL;
}
+static void ip6erspan_tunnel_uninit(struct net_device *dev)
+{
+ struct ip6_tnl *t = netdev_priv(dev);
+ struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+
+ ip6erspan_tunnel_unlink_md(ign, t);
+ ip6gre_tunnel_unlink(ign, t);
+ dst_cache_reset(&t->dst_cache);
+ dev_put(dev);
+}
+
static void ip6gre_tunnel_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+ ip6gre_tunnel_unlink_md(ign, t);
ip6gre_tunnel_unlink(ign, t);
dst_cache_reset(&t->dst_cache);
dev_put(dev);
else
fl6->daddr = tunnel->parms.raddr;
+ if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+ return -ENOMEM;
+
/* Push GRE header. */
protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
}
/**
- * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own
+ * ip6gre_tnl_addr_conflict - compare packet addresses to tunnel's own
* @t: the outgoing tunnel device
* @hdr: IPv6 header from the incoming packet
*
struct flowi6 fl6;
int err = -EINVAL;
__u32 mtu;
+ int nhoff;
+ int thoff;
if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
goto tx_err;
truncate = true;
}
- if (skb_cow_head(skb, dev->needed_headroom))
+ nhoff = skb_network_header(skb) - skb_mac_header(skb);
+ if (skb->protocol == htons(ETH_P_IP) &&
+ (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
+ truncate = true;
+
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ if (skb->protocol == htons(ETH_P_IPV6) &&
+ (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
+ truncate = true;
+
+ if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
t->parms.o_flags &= ~TUNNEL_KEY;
erspan_build_header(skb, ntohl(t->parms.o_key),
t->parms.index,
truncate, false);
- else
+ else if (t->parms.erspan_ver == 2)
erspan_build_header_v2(skb, ntohl(t->parms.o_key),
t->parms.dir,
t->parms.hwid,
truncate, false);
+ else
+ goto tx_err;
+
fl6.daddr = t->parms.raddr;
}
return NETDEV_TX_OK;
}
-static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+static void ip6gre_tnl_link_config_common(struct ip6_tnl *t)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
- int t_hlen;
if (dev->type != ARPHRD_ETHER) {
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
dev->flags |= IFF_POINTOPOINT;
else
dev->flags &= ~IFF_POINTOPOINT;
+}
- t->tun_hlen = gre_calc_hlen(t->parms.o_flags);
-
- t->hlen = t->encap_hlen + t->tun_hlen;
-
- t_hlen = t->hlen + sizeof(struct ipv6hdr);
+static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
+ int t_hlen)
+{
+ const struct __ip6_tnl_parm *p = &t->parms;
+ struct net_device *dev = t->dev;
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
}
}
-static int ip6gre_tnl_change(struct ip6_tnl *t,
- const struct __ip6_tnl_parm *p, int set_mtu)
+static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
+{
+ int t_hlen;
+
+ tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
+
+ t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ return t_hlen;
+}
+
+static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+ ip6gre_tnl_link_config_common(t);
+ ip6gre_tnl_link_config_route(t, set_mtu, ip6gre_calc_hlen(t));
+}
+
+static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t,
+ const struct __ip6_tnl_parm *p)
{
t->parms.laddr = p->laddr;
t->parms.raddr = p->raddr;
t->parms.o_flags = p->o_flags;
t->parms.fwmark = p->fwmark;
dst_cache_reset(&t->dst_cache);
+}
+
+static int ip6gre_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
+ int set_mtu)
+{
+ ip6gre_tnl_copy_tnl_parm(t, p);
ip6gre_tnl_link_config(t, set_mtu);
return 0;
}
{
struct ip6_tnl *t = netdev_priv(dev);
+ gro_cells_destroy(&t->gro_cells);
dst_cache_destroy(&t->dst_cache);
free_percpu(dev->tstats);
}
return -ENOMEM;
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
- if (ret) {
- free_percpu(dev->tstats);
- dev->tstats = NULL;
- return ret;
- }
+ if (ret)
+ goto cleanup_alloc_pcpu_stats;
- tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
- tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
- t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ ret = gro_cells_init(&tunnel->gro_cells, dev);
+ if (ret)
+ goto cleanup_dst_cache_init;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ t_hlen = ip6gre_calc_hlen(tunnel);
dev->mtu = ETH_DATA_LEN - t_hlen;
if (dev->type == ARPHRD_ETHER)
dev->mtu -= ETH_HLEN;
ip6gre_tnl_init_features(dev);
return 0;
+
+cleanup_dst_cache_init:
+ dst_cache_destroy(&tunnel->dst_cache);
+cleanup_alloc_pcpu_stats:
+ free_percpu(dev->tstats);
+ dev->tstats = NULL;
+ return ret;
}
static int ip6gre_tunnel_init(struct net_device *dev)
.ndo_get_iflink = ip6_tnl_get_iflink,
};
+static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel)
+{
+ int t_hlen;
+
+ tunnel->tun_hlen = 8;
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+ erspan_hdr_len(tunnel->parms.erspan_ver);
+
+ t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ return t_hlen;
+}
+
static int ip6erspan_tap_init(struct net_device *dev)
{
struct ip6_tnl *tunnel;
return -ENOMEM;
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
- if (ret) {
- free_percpu(dev->tstats);
- dev->tstats = NULL;
- return ret;
- }
+ if (ret)
+ goto cleanup_alloc_pcpu_stats;
- tunnel->tun_hlen = 8;
- tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
- erspan_hdr_len(tunnel->parms.erspan_ver);
- t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ ret = gro_cells_init(&tunnel->gro_cells, dev);
+ if (ret)
+ goto cleanup_dst_cache_init;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ t_hlen = ip6erspan_calc_hlen(tunnel);
dev->mtu = ETH_DATA_LEN - t_hlen;
if (dev->type == ARPHRD_ETHER)
dev->mtu -= ETH_HLEN;
dev->mtu -= 8;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
- ip6gre_tnl_link_config(tunnel, 1);
+ ip6erspan_tnl_link_config(tunnel, 1);
return 0;
+
+cleanup_dst_cache_init:
+ dst_cache_destroy(&tunnel->dst_cache);
+cleanup_alloc_pcpu_stats:
+ free_percpu(dev->tstats);
+ dev->tstats = NULL;
+ return ret;
}
static const struct net_device_ops ip6erspan_netdev_ops = {
.ndo_init = ip6erspan_tap_init,
- .ndo_uninit = ip6gre_tunnel_uninit,
+ .ndo_uninit = ip6erspan_tunnel_uninit,
.ndo_start_xmit = ip6erspan_tunnel_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
return ret;
}
-static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
- struct netlink_ext_ack *extack)
+static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
{
struct ip6_tnl *nt;
- struct net *net = dev_net(dev);
- struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
struct ip_tunnel_encap ipencap;
int err;
return err;
}
- ip6gre_netlink_parms(data, &nt->parms);
-
- if (nt->parms.collect_md) {
- if (rtnl_dereference(ign->collect_md_tun))
- return -EEXIST;
- } else {
- if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
- return -EEXIST;
- }
-
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
if (err)
goto out;
- ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
-
if (tb[IFLA_MTU])
ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
dev_hold(dev);
- ip6gre_tunnel_link(ign, nt);
out:
return err;
}
-static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[],
- struct netlink_ext_ack *extack)
+static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+ struct ip6gre_net *ign;
+ int err;
+
+ ip6gre_netlink_parms(data, &nt->parms);
+ ign = net_generic(net, ip6gre_net_id);
+
+ if (nt->parms.collect_md) {
+ if (rtnl_dereference(ign->collect_md_tun))
+ return -EEXIST;
+ } else {
+ if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+ }
+
+ err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ if (!err) {
+ ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link_md(ign, nt);
+ ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+ }
+ return err;
+}
+
+static struct ip6_tnl *
+ip6gre_changelink_common(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[], struct __ip6_tnl_parm *p_p,
+ struct netlink_ext_ack *extack)
{
struct ip6_tnl *t, *nt = netdev_priv(dev);
struct net *net = nt->net;
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
- struct __ip6_tnl_parm p;
struct ip_tunnel_encap ipencap;
if (dev == ign->fb_tunnel_dev)
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
if (ip6gre_netlink_encap_parms(data, &ipencap)) {
int err = ip6_tnl_encap_setup(nt, &ipencap);
if (err < 0)
- return err;
+ return ERR_PTR(err);
}
- ip6gre_netlink_parms(data, &p);
+ ip6gre_netlink_parms(data, p_p);
- t = ip6gre_tunnel_locate(net, &p, 0);
+ t = ip6gre_tunnel_locate(net, p_p, 0);
if (t) {
if (t->dev != dev)
- return -EEXIST;
+ return ERR_PTR(-EEXIST);
} else {
t = nt;
}
+ return t;
+}
+
+static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+ struct __ip6_tnl_parm p;
+ struct ip6_tnl *t;
+
+ t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ ip6gre_tunnel_unlink_md(ign, t);
ip6gre_tunnel_unlink(ign, t);
ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link_md(ign, t);
ip6gre_tunnel_link(ign, t);
return 0;
}
netif_keep_dst(dev);
}
+static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+ struct ip6gre_net *ign;
+ int err;
+
+ ip6gre_netlink_parms(data, &nt->parms);
+ ign = net_generic(net, ip6gre_net_id);
+
+ if (nt->parms.collect_md) {
+ if (rtnl_dereference(ign->collect_md_tun_erspan))
+ return -EEXIST;
+ } else {
+ if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+ }
+
+ err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ if (!err) {
+ ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
+ ip6erspan_tunnel_link_md(ign, nt);
+ ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+ }
+ return err;
+}
+
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+ ip6gre_tnl_link_config_common(t);
+ ip6gre_tnl_link_config_route(t, set_mtu, ip6erspan_calc_hlen(t));
+}
+
+static int ip6erspan_tnl_change(struct ip6_tnl *t,
+ const struct __ip6_tnl_parm *p, int set_mtu)
+{
+ ip6gre_tnl_copy_tnl_parm(t, p);
+ ip6erspan_tnl_link_config(t, set_mtu);
+ return 0;
+}
+
+static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+ struct __ip6_tnl_parm p;
+ struct ip6_tnl *t;
+
+ t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ ip6gre_tunnel_unlink_md(ign, t);
+ ip6gre_tunnel_unlink(ign, t);
+ ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6erspan_tunnel_link_md(ign, t);
+ ip6gre_tunnel_link(ign, t);
+ return 0;
+}
+
static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
.kind = "ip6gre",
.maxtype = IFLA_GRE_MAX,
.priv_size = sizeof(struct ip6_tnl),
.setup = ip6erspan_tap_setup,
.validate = ip6erspan_tap_validate,
- .newlink = ip6gre_newlink,
- .changelink = ip6gre_changelink,
+ .newlink = ip6erspan_newlink,
+ .changelink = ip6erspan_changelink,
.get_size = ip6gre_get_size,
.fill_info = ip6gre_fill_info,
.get_link_net = ip6_tnl_get_link_net,
if (skb->encapsulation &&
skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
- udpfrag = proto == IPPROTO_UDP && encap;
+ udpfrag = proto == IPPROTO_UDP && encap &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
else
- udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
return dst_output(net, sk, skb);
}
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
-{
- unsigned int mtu;
- struct inet6_dev *idev;
-
- if (dst_metric_locked(dst, RTAX_MTU)) {
- mtu = dst_metric_raw(dst, RTAX_MTU);
- if (mtu)
- return mtu;
- }
-
- mtu = IPV6_MIN_MTU;
- rcu_read_lock();
- idev = __in6_dev_get(dst->dev);
- if (idev)
- mtu = idev->cnf.mtu6;
- rcu_read_unlock();
-
- return mtu;
-}
-EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward);
-
static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
if (mtu < IPV6_MIN_MTU)
return -EINVAL;
cork->base.fragsize = mtu;
+ cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0;
+
if (dst_allfrag(xfrm_dst_path(&rt->dst)))
cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
+ bool paged;
skb = skb_peek_tail(queue);
if (!skb) {
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
}
- mtu = cork->fragsize;
+ paged = !!cork->gso_size;
+ mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
headersize == sizeof(struct ipv6hdr) &&
length <= mtu - headersize &&
- !(flags & MSG_MORE) &&
+ (!(flags & MSG_MORE) || cork->gso_size) &&
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
+ fraglen = datalen + fragheaderlen;
+
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
- alloclen = datalen + fragheaderlen;
+ else if (!paged)
+ alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += dst_exthdrlen;
*/
alloclen += sizeof(struct frag_hdr);
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy < 0) {
err = -EINVAL;
goto error;
/*
* Find where to start putting bytes
*/
- data = skb_put(skb, fraglen);
+ data = skb_put(skb, fraglen - pagedlen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
+ struct inet_cork_full *cork,
const struct sockcm_cookie *sockc)
{
- struct inet_cork_full cork;
struct inet6_cork v6_cork;
struct sk_buff_head queue;
int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
__skb_queue_head_init(&queue);
- cork.base.flags = 0;
- cork.base.addr = 0;
- cork.base.opt = NULL;
- cork.base.dst = NULL;
+ cork->base.flags = 0;
+ cork->base.addr = 0;
+ cork->base.opt = NULL;
+ cork->base.dst = NULL;
v6_cork.opt = NULL;
- err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
+ err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
if (err) {
- ip6_cork_release(&cork, &v6_cork);
+ ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
}
if (ipc6->dontfrag < 0)
ipc6->dontfrag = inet6_sk(sk)->dontfrag;
- err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
+ err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
¤t->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
flags, ipc6, sockc);
if (err) {
- __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
+ __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
return ERR_PTR(err);
}
- return __ip6_make_skb(sk, &queue, &cork, &v6_cork);
+ return __ip6_make_skb(sk, &queue, cork, &v6_cork);
}
else
mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
- dev->mtu = max_t(int, mtu, IPV6_MIN_MTU);
+ dev->mtu = max_t(int, mtu, IPV4_MIN_MTU);
}
/**
}
/**
- * vti6_tnl_ioctl - configure vti6 tunnels from userspace
+ * vti6_ioctl - configure vti6 tunnels from userspace
* @dev: virtual device associated with tunnel
* @ifr: parameters passed from userspace
* @cmd: command to be performed
dev->priv_destructor = vti6_dev_free;
dev->type = ARPHRD_TUNNEL6;
- dev->min_mtu = IPV6_MIN_MTU;
+ dev->min_mtu = IPV4_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
fields such as the source, destination, flowlabel, hop-limit and
the packet mark.
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+ tristate "IPv6 nf_tables nat chain support"
+ help
+ This option enables the "nat" chain for IPv6 in nf_tables. This
+ chain type is used to perform Network Address Translation (NAT)
+ packet transformations such as the source, destination address and
+ source and destination ports.
+
+config NFT_MASQ_IPV6
+ tristate "IPv6 masquerade support for nf_tables"
+ depends on NFT_MASQ
+ select NF_NAT_MASQUERADE_IPV6
+ help
+ This is the expression that provides IPv4 masquerading support for
+ nf_tables.
+
+config NFT_REDIR_IPV6
+ tristate "IPv6 redirect support for nf_tables"
+ depends on NFT_REDIR
+ select NF_NAT_REDIRECT
+ help
+ This is the expression that provides IPv4 redirect support for
+ nf_tables.
+
+endif # NF_NAT_IPV6
+
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
if NF_NAT_IPV6
-config NFT_CHAIN_NAT_IPV6
- depends on NF_TABLES_IPV6
- tristate "IPv6 nf_tables nat chain support"
- help
- This option enables the "nat" chain for IPv6 in nf_tables. This
- chain type is used to perform Network Address Translation (NAT)
- packet transformations such as the source, destination address and
- source and destination ports.
-
config NF_NAT_MASQUERADE_IPV6
tristate "IPv6 masquerade support"
help
This is the kernel functionality to provide NAT in the masquerade
flavour (automatic source address selection) for IPv6.
-config NFT_MASQ_IPV6
- tristate "IPv6 masquerade support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_MASQ
- select NF_NAT_MASQUERADE_IPV6
- help
- This is the expression that provides IPv4 masquerading support for
- nf_tables.
-
-config NFT_REDIR_IPV6
- tristate "IPv6 redirect support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_REDIR
- select NF_NAT_REDIRECT
- help
- This is the expression that provides IPv4 redirect support for
- nf_tables.
-
endif # NF_NAT_IPV6
config IP6_NF_IPTABLES
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("IPv6 packet filter");
+MODULE_ALIAS("ip6t_icmp6");
void *ip6t_alloc_initial_table(const struct xt_table *info)
{
.family = NFPROTO_IPV6,
};
- t = ip6t_get_target(e);
return xt_check_target(&par, t->u.target_size - sizeof(*t),
e->ipv6.proto,
e->ipv6.invflags & IP6T_INV_PROTO);
static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
+ const struct nf_nat_range2 *range = par->targinfo;
if (range->flags & NF_NAT_RANGE_MAP_IPS)
return -EINVAL;
return true;
}
+static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ int hdrlen, psidoff, nsidoff, lsidoff, srhoff = 0;
+ const struct ip6t_srh1 *srhinfo = par->matchinfo;
+ struct in6_addr *psid, *nsid, *lsid;
+ struct in6_addr _psid, _nsid, _lsid;
+ struct ipv6_sr_hdr *srh;
+ struct ipv6_sr_hdr _srh;
+
+ if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+ return false;
+ srh = skb_header_pointer(skb, srhoff, sizeof(_srh), &_srh);
+ if (!srh)
+ return false;
+
+ hdrlen = ipv6_optlen(srh);
+ if (skb->len - srhoff < hdrlen)
+ return false;
+
+ if (srh->type != IPV6_SRCRT_TYPE_4)
+ return false;
+
+ if (srh->segments_left > srh->first_segment)
+ return false;
+
+ /* Next Header matching */
+ if (srhinfo->mt_flags & IP6T_SRH_NEXTHDR)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NEXTHDR,
+ !(srh->nexthdr == srhinfo->next_hdr)))
+ return false;
+
+ /* Header Extension Length matching */
+ if (srhinfo->mt_flags & IP6T_SRH_LEN_EQ)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_EQ,
+ !(srh->hdrlen == srhinfo->hdr_len)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_LEN_GT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_GT,
+ !(srh->hdrlen > srhinfo->hdr_len)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_LEN_LT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_LT,
+ !(srh->hdrlen < srhinfo->hdr_len)))
+ return false;
+
+ /* Segments Left matching */
+ if (srhinfo->mt_flags & IP6T_SRH_SEGS_EQ)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_EQ,
+ !(srh->segments_left == srhinfo->segs_left)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_SEGS_GT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_GT,
+ !(srh->segments_left > srhinfo->segs_left)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_SEGS_LT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_LT,
+ !(srh->segments_left < srhinfo->segs_left)))
+ return false;
+
+ /**
+ * Last Entry matching
+ * Last_Entry field was introduced in revision 6 of the SRH draft.
+ * It was called First_Segment in the previous revision
+ */
+ if (srhinfo->mt_flags & IP6T_SRH_LAST_EQ)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_EQ,
+ !(srh->first_segment == srhinfo->last_entry)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_LAST_GT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_GT,
+ !(srh->first_segment > srhinfo->last_entry)))
+ return false;
+ if (srhinfo->mt_flags & IP6T_SRH_LAST_LT)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_LT,
+ !(srh->first_segment < srhinfo->last_entry)))
+ return false;
+
+ /**
+ * Tag matchig
+ * Tag field was introduced in revision 6 of the SRH draft
+ */
+ if (srhinfo->mt_flags & IP6T_SRH_TAG)
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_TAG,
+ !(srh->tag == srhinfo->tag)))
+ return false;
+
+ /* Previous SID matching */
+ if (srhinfo->mt_flags & IP6T_SRH_PSID) {
+ if (srh->segments_left == srh->first_segment)
+ return false;
+ psidoff = srhoff + sizeof(struct ipv6_sr_hdr) +
+ ((srh->segments_left + 1) * sizeof(struct in6_addr));
+ psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid);
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID,
+ ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk,
+ &srhinfo->psid_addr)))
+ return false;
+ }
+
+ /* Next SID matching */
+ if (srhinfo->mt_flags & IP6T_SRH_NSID) {
+ if (srh->segments_left == 0)
+ return false;
+ nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) +
+ ((srh->segments_left - 1) * sizeof(struct in6_addr));
+ nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid);
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID,
+ ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk,
+ &srhinfo->nsid_addr)))
+ return false;
+ }
+
+ /* Last SID matching */
+ if (srhinfo->mt_flags & IP6T_SRH_LSID) {
+ lsidoff = srhoff + sizeof(struct ipv6_sr_hdr);
+ lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid);
+ if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID,
+ ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk,
+ &srhinfo->lsid_addr)))
+ return false;
+ }
+ return true;
+}
+
static int srh_mt6_check(const struct xt_mtchk_param *par)
{
const struct ip6t_srh *srhinfo = par->matchinfo;
return 0;
}
-static struct xt_match srh_mt6_reg __read_mostly = {
- .name = "srh",
- .family = NFPROTO_IPV6,
- .match = srh_mt6,
- .matchsize = sizeof(struct ip6t_srh),
- .checkentry = srh_mt6_check,
- .me = THIS_MODULE,
+static int srh1_mt6_check(const struct xt_mtchk_param *par)
+{
+ const struct ip6t_srh1 *srhinfo = par->matchinfo;
+
+ if (srhinfo->mt_flags & ~IP6T_SRH_MASK) {
+ pr_info_ratelimited("unknown srh match flags %X\n",
+ srhinfo->mt_flags);
+ return -EINVAL;
+ }
+
+ if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) {
+ pr_info_ratelimited("unknown srh invflags %X\n",
+ srhinfo->mt_invflags);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match srh_mt6_reg[] __read_mostly = {
+ {
+ .name = "srh",
+ .revision = 0,
+ .family = NFPROTO_IPV6,
+ .match = srh_mt6,
+ .matchsize = sizeof(struct ip6t_srh),
+ .checkentry = srh_mt6_check,
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "srh",
+ .revision = 1,
+ .family = NFPROTO_IPV6,
+ .match = srh1_mt6,
+ .matchsize = sizeof(struct ip6t_srh1),
+ .checkentry = srh1_mt6_check,
+ .me = THIS_MODULE,
+ }
};
static int __init srh_mt6_init(void)
{
- return xt_register_match(&srh_mt6_reg);
+ return xt_register_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg));
}
static void __exit srh_mt6_exit(void)
{
- xt_unregister_match(&srh_mt6_reg);
+ xt_unregister_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg));
}
module_init(srh_mt6_init);
static unsigned int ip6table_nat_do_chain(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct)
+ const struct nf_hook_state *state)
{
return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat);
}
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
-#include <linux/ipv6.h>
-#include <linux/netdevice.h>
-#include <net/ipv6.h>
-#include <net/ip6_route.h>
-#include <net/neighbour.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
- struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- struct tcphdr *tcph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*tcph)))
- return -1;
-
- tcph = (void *)(skb_network_header(skb) + thoff);
- inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
- new_addr->s6_addr32, true);
-
- return 0;
-}
-
-static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
- struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- struct udphdr *udph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*udph)))
- return -1;
-
- udph = (void *)(skb_network_header(skb) + thoff);
- if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
- inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
- new_addr->s6_addr32, true);
- if (!udph->check)
- udph->check = CSUM_MANGLED_0;
- }
-
- return 0;
-}
-
-static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff, struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- switch (ip6h->nexthdr) {
- case IPPROTO_TCP:
- if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- case IPPROTO_UDP:
- if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- }
-
- return 0;
-}
-
-static int nf_flow_snat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- struct in6_addr addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = ip6h->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
- ip6h->saddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = ip6h->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
- ip6h->daddr = new_addr;
- break;
- default:
- return -1;
- }
-
- return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- struct in6_addr addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = ip6h->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
- ip6h->daddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = ip6h->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
- ip6h->saddr = new_addr;
- break;
- default:
- return -1;
- }
-
- return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_nat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb,
- enum flow_offload_tuple_dir dir)
-{
- struct ipv6hdr *ip6h = ipv6_hdr(skb);
- unsigned int thoff = sizeof(*ip6h);
-
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
- (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
- nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
- return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
- (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
- nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
- return -1;
-
- return 0;
-}
-
-static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple)
-{
- struct flow_ports *ports;
- struct ipv6hdr *ip6h;
- unsigned int thoff;
-
- if (!pskb_may_pull(skb, sizeof(*ip6h)))
- return -1;
-
- ip6h = ipv6_hdr(skb);
-
- if (ip6h->nexthdr != IPPROTO_TCP &&
- ip6h->nexthdr != IPPROTO_UDP)
- return -1;
-
- thoff = sizeof(*ip6h);
- if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
- return -1;
-
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
- tuple->src_v6 = ip6h->saddr;
- tuple->dst_v6 = ip6h->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
- tuple->l3proto = AF_INET6;
- tuple->l4proto = ip6h->nexthdr;
- tuple->iifidx = dev->ifindex;
-
- return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
- if (skb->len <= mtu)
- return false;
-
- if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
- return false;
-
- return true;
-}
-
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rt6_info *rt)
-{
- u32 mtu;
-
- mtu = ip6_dst_mtu_forward(&rt->dst);
- if (__nf_flow_exceeds_mtu(skb, mtu))
- return true;
-
- return false;
-}
-
-unsigned int
-nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
- struct flow_offload_tuple tuple = {};
- enum flow_offload_tuple_dir dir;
- struct flow_offload *flow;
- struct net_device *outdev;
- struct in6_addr *nexthop;
- struct ipv6hdr *ip6h;
- struct rt6_info *rt;
-
- if (skb->protocol != htons(ETH_P_IPV6))
- return NF_ACCEPT;
-
- if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
- return NF_ACCEPT;
-
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
-
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
- dir = tuplehash->tuple.dir;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
- rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
- if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
- return NF_ACCEPT;
-
- if (skb_try_make_writable(skb, sizeof(*ip6h)))
- return NF_DROP;
-
- if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
- nf_flow_nat_ipv6(flow, skb, dir) < 0)
- return NF_DROP;
-
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
- ip6h = ipv6_hdr(skb);
- ip6h->hop_limit--;
-
- skb->dev = outdev;
- nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
- neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
-
- return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
static struct nf_flowtable_type flowtable_ipv6 = {
.family = NFPROTO_IPV6,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ipv6_hook,
.owner = THIS_MODULE,
#endif
static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
- const struct nf_nat_range *range)
+ const struct nf_nat_range2 *range)
{
return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range)
+ struct nf_nat_range2 *range)
{
if (tb[CTA_NAT_V6_MINIP]) {
nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP],
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
- ret = do_chain(priv, skb, state, ct);
+ ret = do_chain(priv, skb, state);
if (ret != NF_ACCEPT)
return ret;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
unsigned int ret;
struct in6_addr daddr = ipv6_hdr(skb)->daddr;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct))
+ const struct nf_hook_state *state))
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
static atomic_t v6_worker_count;
unsigned int
-nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
const struct net_device *out)
{
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
struct in6_addr src;
struct nf_conn *ct;
- struct nf_nat_range newrange;
+ struct nf_nat_range2 newrange;
ct = nf_ct_get(skb, &ctinfo);
WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
static void
icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static unsigned int nft_nat_do_chain(void *priv,
struct sk_buff *skb,
- const struct nf_hook_state *state,
- struct nf_conn *ct)
+ const struct nf_hook_state *state)
{
struct nft_pktinfo pkt;
const struct nft_pktinfo *pkt)
{
struct nft_masq *priv = nft_expr_priv(expr);
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
const struct nft_pktinfo *pkt)
{
struct nft_redir *priv = nft_expr_priv(expr);
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
memset(&range, 0, sizeof(range));
if (priv->sreg_proto_min) {
return false;
}
-static struct fib6_info *rt6_multipath_select(const struct net *net,
- struct fib6_info *match,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb,
- int strict)
+struct fib6_info *fib6_multipath_select(const struct net *net,
+ struct fib6_info *match,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb,
+ int strict)
{
struct fib6_info *sibling, *next_sibling;
!(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
return rt;
- for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) {
+ for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
const struct net_device *dev = sprt->fib6_nh.nh_dev;
if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD)
match = NULL;
cont = NULL;
- for (rt = rr_head; rt; rt = rcu_dereference(rt->rt6_next)) {
+ for (rt = rr_head; rt; rt = rcu_dereference(rt->fib6_next)) {
if (rt->fib6_metric != metric) {
cont = rt;
break;
}
for (rt = leaf; rt && rt != rr_head;
- rt = rcu_dereference(rt->rt6_next)) {
+ rt = rcu_dereference(rt->fib6_next)) {
if (rt->fib6_metric != metric) {
cont = rt;
break;
if (match || !cont)
return match;
- for (rt = cont; rt; rt = rcu_dereference(rt->rt6_next))
+ for (rt = cont; rt; rt = rcu_dereference(rt->fib6_next))
match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
&do_rr);
if (do_rr) {
- struct fib6_info *next = rcu_dereference(rt0->rt6_next);
+ struct fib6_info *next = rcu_dereference(rt0->fib6_next);
/* no entries matched; do round-robin */
if (!next || next->fib6_metric != rt0->fib6_metric)
pn = rcu_dereference(fn->parent);
sn = FIB6_SUBTREE(pn);
if (sn && sn != fn)
- fn = fib6_lookup(sn, NULL, saddr);
+ fn = fib6_node_lookup(sn, NULL, saddr);
else
fn = pn;
if (fn->fn_flags & RTN_RTINFO)
flags &= ~RT6_LOOKUP_F_IFACE;
rcu_read_lock();
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
f6i = rcu_dereference(fn->leaf);
if (!f6i) {
f6i = rt6_device_match(net, f6i, &fl6->saddr,
fl6->flowi6_oif, flags);
if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
- f6i = rt6_multipath_select(net, f6i, fl6,
- fl6->flowi6_oif, skb, flags);
+ f6i = fib6_multipath_select(net, f6i, fl6,
+ fl6->flowi6_oif, skb,
+ flags);
}
if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
goto restart;
}
+ trace_fib6_table_lookup(net, f6i, table, fl6);
+
/* Search through exception table */
rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
if (rt) {
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
-
return rt;
}
struct fib6_info *from;
int err;
- from = rcu_dereference_protected(rt->from,
- lockdep_is_held(&rt6_exception_lock));
+ from = rcu_dereference(rt->from);
if (!from ||
!(rt->rt6i_flags & RTF_CACHE))
return -EINVAL;
rcu_read_unlock_bh();
}
-struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6,
- const struct sk_buff *skb, int flags)
+/* must be called with rcu lock held */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int strict)
{
struct fib6_node *fn, *saved_fn;
struct fib6_info *f6i;
- struct rt6_info *rt;
- int strict = 0;
-
- strict |= flags & RT6_LOOKUP_F_IFACE;
- strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
- if (net->ipv6.devconf_all->forwarding == 0)
- strict |= RT6_LOOKUP_F_REACHABLE;
-
- rcu_read_lock();
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
redo_rt6_select:
f6i = rt6_select(net, fn, oif, strict);
- if (f6i->fib6_nsiblings)
- f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict);
if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
}
}
+ trace_fib6_table_lookup(net, f6i, table, fl6);
+
+ return f6i;
+}
+
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6,
+ const struct sk_buff *skb, int flags)
+{
+ struct fib6_info *f6i;
+ struct rt6_info *rt;
+ int strict = 0;
+
+ strict |= flags & RT6_LOOKUP_F_IFACE;
+ strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
+ if (net->ipv6.devconf_all->forwarding == 0)
+ strict |= RT6_LOOKUP_F_REACHABLE;
+
+ rcu_read_lock();
+
+ f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+ if (f6i->fib6_nsiblings)
+ f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+
if (f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
}
dst_use_noref(&rt->dst, jiffies);
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
!(f6i->fib6_flags & RTF_GATEWAY))) {
dst_hold(&uncached_rt->dst);
}
- trace_fib6_table_lookup(net, uncached_rt, table, fl6);
return uncached_rt;
-
} else {
/* Get a percpu copy */
local_bh_enable();
rcu_read_unlock();
- trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
+
return pcpu_rt;
}
}
const struct ipv6hdr *inner_iph;
const struct icmp6hdr *icmph;
struct ipv6hdr _inner_iph;
+ struct icmp6hdr _icmph;
if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
goto out;
- icmph = icmp6_hdr(skb);
+ icmph = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_icmph), &_icmph);
+ if (!icmph)
+ goto out;
+
if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
*/
rcu_read_lock();
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
for_each_fib6_node_rt_rcu(fn) {
if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
rcu_read_unlock();
- trace_fib6_table_lookup(net, ret, table, fl6);
+ trace_fib6_table_lookup(net, rt, table, fl6);
return ret;
};
&cfg->fc_src);
if (rt_cache) {
rc = ip6_del_cached_rt(rt_cache, cfg);
- if (rc != -ESRCH)
+ if (rc != -ESRCH) {
+ rcu_read_unlock();
return rc;
+ }
}
continue;
}
if (iter->fib6_metric == rt->fib6_metric &&
rt6_qualify_for_ecmp(iter))
return iter;
- iter = rcu_dereference_protected(iter->rt6_next,
+ iter = rcu_dereference_protected(iter->fib6_next,
lockdep_is_held(&rt->fib6_table->tb6_lock));
}
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
rcu_read_unlock();
}
+/* Compute flowlabel for outer IPv6 header */
+static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
+ struct ipv6hdr *inner_hdr)
+{
+ int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel;
+ __be32 flowlabel = 0;
+ u32 hash;
+
+ if (do_flowlabel > 0) {
+ hash = skb_get_hash(skb);
+ rol32(hash, 16);
+ flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
+ } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) {
+ flowlabel = ip6_flowlabel(inner_hdr);
+ }
+ return flowlabel;
+}
+
/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
{
struct ipv6hdr *hdr, *inner_hdr;
struct ipv6_sr_hdr *isrh;
int hdrlen, tot_len, err;
+ __be32 flowlabel;
hdrlen = (osrh->hdrlen + 1) << 3;
tot_len = hdrlen + sizeof(*hdr);
return err;
inner_hdr = ipv6_hdr(skb);
+ flowlabel = seg6_make_flowlabel(net, skb, inner_hdr);
skb_push(skb, tot_len);
skb_reset_network_header(skb);
if (skb->protocol == htons(ETH_P_IPV6)) {
ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
- ip6_flowlabel(inner_hdr));
+ flowlabel);
hdr->hop_limit = inner_hdr->hop_limit;
} else {
- ip6_flow_hdr(hdr, 0, 0);
+ ip6_flow_hdr(hdr, 0, flowlabel);
hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
}
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
.extra1 = &zero,
.extra2 = &one,
},
+ {
+ .procname = "seg6_flowlabel",
+ .data = &init_net.ipv6.sysctl.seg6_flowlabel,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len;
ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len;
ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy,
+ ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
unsigned int tot_len = sizeof(struct tcphdr);
struct dst_entry *dst;
__be32 *topt;
+ __u32 mark = 0;
if (tsecr)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
fl6.flowi6_oif = oif;
}
- fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
+ if (sk)
+ mark = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_mark : sk->sk_mark;
+ fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark;
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score++;
}
__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}
-static struct static_key udpv6_encap_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
- static_key_enable(&udpv6_encap_needed);
+ static_branch_enable(&udpv6_encap_needed_key);
}
EXPORT_SYMBOL(udpv6_encap_enable);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto drop;
- if (static_key_false(&udpv6_encap_needed) && up->encap_type) {
+ if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
* Sending
*/
-static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6)
+static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
+ struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct udphdr *uh;
uh->len = htons(len);
uh->check = 0;
+ if (cork->gso_size) {
+ const int hlen = skb_network_header_len(skb) +
+ sizeof(struct udphdr);
+
+ if (hlen + cork->gso_size > cork->fragsize)
+ return -EINVAL;
+ if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+ return -EINVAL;
+ if (udp_sk(sk)->no_check6_tx)
+ return -EINVAL;
+ if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite)
+ return -EIO;
+
+ skb_shinfo(skb)->gso_size = cork->gso_size;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+ goto csum_partial;
+ }
+
if (is_udplite)
csum = udplite_csum(skb);
else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */
skb->ip_summed = CHECKSUM_NONE;
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+csum_partial:
udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len);
goto send;
} else
if (!skb)
goto out;
- err = udp_v6_send_skb(skb, &fl6);
+ err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base);
out:
up->len = 0;
ipc6.hlimit = -1;
ipc6.tclass = -1;
ipc6.dontfrag = -1;
+ ipc6.gso_size = up->gso_size;
sockc.tsflags = sk->sk_tsflags;
/* destination address check */
opt->tot_len = sizeof(*opt);
ipc6.opt = opt;
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc);
+ err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
+ if (err > 0)
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6,
+ &ipc6, &sockc);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
/* Lockless fast path for the non-corking case */
if (!corkreq) {
+ struct inet_cork_full cork;
struct sk_buff *skb;
skb = ip6_make_skb(sk, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc6,
&fl6, (struct rt6_info *)dst,
- msg->msg_flags, &sockc);
+ msg->msg_flags, &cork, &sockc);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
- err = udp_v6_send_skb(skb, &fl6);
+ err = udp_v6_send_skb(skb, &fl6, &cork.base);
goto out;
}
udp_v6_flush_pending_frames(sk);
release_sock(sk);
- if (static_key_false(&udpv6_encap_needed) && up->encap_type) {
+ if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
void (*encap_destroy)(struct sock *sk);
encap_destroy = READ_ONCE(up->encap_destroy);
if (encap_destroy)
const struct ipv6hdr *ipv6h;
struct udphdr *uh;
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+ if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ return __udp_gso_segment(skb, features);
+
/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
* do checksum of UDP packets sent as multiple IP fragments.
*/
static int
__xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass)
{
- int i;
+ int count[XFRM_MAX_DEPTH] = { };
int class[XFRM_MAX_DEPTH];
- int count[maxclass];
-
- memset(count, 0, sizeof(count));
+ int i;
for (i = 0; i < n; i++) {
int c;
struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
unsigned int i;
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
+ xfrm_flush_gc();
+
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
return 0;
}
+static inline int sadb_key_len(const struct sadb_key *key)
+{
+ int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8);
+
+ return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes,
+ sizeof(uint64_t));
+}
+
+static int verify_key_len(const void *p)
+{
+ const struct sadb_key *key = p;
+
+ if (sadb_key_len(key) > key->sadb_key_len)
+ return -EINVAL;
+
+ return 0;
+}
+
static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx)
{
return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) +
return -EINVAL;
if (ext_hdrs[ext_type-1] != NULL)
return -EINVAL;
- if (ext_type == SADB_EXT_ADDRESS_SRC ||
- ext_type == SADB_EXT_ADDRESS_DST ||
- ext_type == SADB_EXT_ADDRESS_PROXY ||
- ext_type == SADB_X_EXT_NAT_T_OA) {
+ switch (ext_type) {
+ case SADB_EXT_ADDRESS_SRC:
+ case SADB_EXT_ADDRESS_DST:
+ case SADB_EXT_ADDRESS_PROXY:
+ case SADB_X_EXT_NAT_T_OA:
if (verify_address_len(p))
return -EINVAL;
- }
- if (ext_type == SADB_X_EXT_SEC_CTX) {
+ break;
+ case SADB_X_EXT_SEC_CTX:
if (verify_sec_ctx_len(p))
return -EINVAL;
+ break;
+ case SADB_EXT_KEY_AUTH:
+ case SADB_EXT_KEY_ENCRYPT:
+ if (verify_key_len(p))
+ return -EINVAL;
+ break;
+ default:
+ break;
}
ext_hdrs[ext_type-1] = (void *) p;
}
key = ext_hdrs[SADB_EXT_KEY_AUTH - 1];
if (key != NULL &&
sa->sadb_sa_auth != SADB_X_AALG_NULL &&
- ((key->sadb_key_bits+7) / 8 == 0 ||
- (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+ key->sadb_key_bits == 0)
return ERR_PTR(-EINVAL);
key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1];
if (key != NULL &&
sa->sadb_sa_encrypt != SADB_EALG_NULL &&
- ((key->sadb_key_bits+7) / 8 == 0 ||
- (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+ key->sadb_key_bits == 0)
return ERR_PTR(-EINVAL);
x = xfrm_state_alloc(net);
static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
{
+ /* Drop reference taken during previous invocation */
+ if (pd->session)
+ l2tp_session_dec_refcount(pd->session);
+
pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
pd->session_idx++;
if (!pd || pd == SEQ_START_TOKEN)
return;
- /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
- if (pd->tunnel)
+ /* Drop reference taken by last invocation of l2tp_dfs_next_session()
+ * or l2tp_dfs_next_tunnel().
+ */
+ if (pd->session) {
+ l2tp_session_dec_refcount(pd->session);
+ pd->session = NULL;
+ }
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ }
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
goto out;
}
- /* Show the tunnel or session context */
- if (!pd->session) {
+ if (!pd->session)
l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
- } else {
+ else
l2tp_dfs_seq_session_show(m, pd->session);
- l2tp_session_dec_refcount(pd->session);
- }
out:
return 0;
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
{
+ /* Drop reference taken during previous invocation */
+ if (pd->session)
+ l2tp_session_dec_refcount(pd->session);
+
pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
pd->session_idx++;
if (!pd || pd == SEQ_START_TOKEN)
return;
- /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
- if (pd->tunnel)
+ /* Drop reference taken by last invocation of pppol2tp_next_session()
+ * or pppol2tp_next_tunnel().
+ */
+ if (pd->session) {
+ l2tp_session_dec_refcount(pd->session);
+ pd->session = NULL;
+ }
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ }
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
goto out;
}
- /* Show the tunnel or session context.
- */
- if (!pd->session) {
+ if (!pd->session)
pppol2tp_seq_tunnel_show(m, pd->tunnel);
- } else {
+ else
pppol2tp_seq_session_show(m, pd->session);
- l2tp_session_dec_refcount(pd->session);
- }
out:
return 0;
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
- struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- sap = llc->sap;
- /* Hold this for release_sock(), so that llc_backlog_rcv() could still
- * use it.
- */
- llc_sap_hold(sap);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
- llc_sap_put(sap);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
if (size > llc->dev->mtu)
size = llc->dev->mtu;
copied = size - hdrlen;
+ rc = -EINVAL;
+ if (copied < 0)
+ goto release;
release_sock(sk);
skb = sock_alloc_send_skb(sk, size, noblock, &rc);
lock_sock(sk);
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
sta->ampdu_mlme.addba_req_num[tid] = 0;
+ tid_tx->timeout =
+ le16_to_cpu(mgmt->u.action.u.addba_resp.timeout);
+
if (tid_tx->timeout) {
mod_timer(&tid_tx->session_timer,
TU_TO_EXP_TIME(tid_tx->timeout));
#define IEEE80211_AUTH_TIMEOUT (HZ / 5)
#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10)
+#define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2)
#define IEEE80211_AUTH_MAX_TRIES 3
#define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5)
#define IEEE80211_ASSOC_TIMEOUT (HZ / 5)
params[ac].acm = acm;
params[ac].uapsd = uapsd;
- if (params->cw_min == 0 ||
+ if (params[ac].cw_min == 0 ||
params[ac].cw_min > params[ac].cw_max) {
sdata_info(sdata,
"AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
tx_flags);
if (tx_flags == 0) {
- auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
- auth_data->timeout_started = true;
- run_again(sdata, auth_data->timeout);
+ if (auth_data->algorithm == WLAN_AUTH_SAE)
+ auth_data->timeout = jiffies +
+ IEEE80211_AUTH_TIMEOUT_SAE;
+ else
+ auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
} else {
auth_data->timeout =
round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG);
- auth_data->timeout_started = true;
- run_again(sdata, auth_data->timeout);
}
+ auth_data->timeout_started = true;
+ run_again(sdata, auth_data->timeout);
+
return 0;
}
ifmgd->status_received = false;
if (ifmgd->auth_data && ieee80211_is_auth(fc)) {
if (status_acked) {
- ifmgd->auth_data->timeout =
- jiffies + IEEE80211_AUTH_TIMEOUT_SHORT;
+ if (ifmgd->auth_data->algorithm ==
+ WLAN_AUTH_SAE)
+ ifmgd->auth_data->timeout =
+ jiffies +
+ IEEE80211_AUTH_TIMEOUT_SAE;
+ else
+ ifmgd->auth_data->timeout =
+ jiffies +
+ IEEE80211_AUTH_TIMEOUT_SHORT;
run_again(sdata, ifmgd->auth_data->timeout);
} else {
ifmgd->auth_data->timeout = jiffies - 1;
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
}
/* reset session timer */
- if (reset_agg_timer && tid_tx->timeout)
+ if (reset_agg_timer)
tid_tx->last_tx = jiffies;
return queued;
cmd = (struct ncsi_cmd_svf_pkt *)skb_network_header(nr->cmd);
ncf = &nc->vlan_filter;
- if (cmd->index > ncf->n_vids)
+ if (cmd->index == 0 || cmd->index > ncf->n_vids)
return -ERANGE;
/* Add or remove the VLAN filter. Remember HW indexes from 1 */
ncf = &nc->mac_filter;
bitmap = &ncf->bitmap;
- if (cmd->index > ncf->n_uc + ncf->n_mc + ncf->n_mixed)
+ if (cmd->index == 0 ||
+ cmd->index > ncf->n_uc + ncf->n_mc + ncf->n_mixed)
return -ERANGE;
index = (cmd->index - 1) * ETH_ALEN;
endif # NF_CONNTRACK
+config NF_OSF
+ tristate 'Passive OS fingerprint infrastructure'
+
config NF_TABLES
select NETFILTER_NETLINK
tristate "Netfilter nf_tables support"
help
This option enables support for the "netdev" table.
-config NFT_EXTHDR
- tristate "Netfilter nf_tables exthdr module"
- help
- This option adds the "exthdr" expression that you can use to match
- IPv6 extension headers and tcp options.
-
-config NFT_META
- tristate "Netfilter nf_tables meta module"
- help
- This option adds the "meta" expression that you can use to match and
- to set packet metainformation such as the packet mark.
-
-config NFT_RT
- tristate "Netfilter nf_tables routing module"
- help
- This option adds the "rt" expression that you can use to match
- packet routing information such as the packet nexthop.
-
config NFT_NUMGEN
tristate "Netfilter nf_tables number generator module"
help
config NFT_REJECT
default m if NETFILTER_ADVANCED=n
tristate "Netfilter nf_tables reject support"
+ depends on !NF_TABLES_INET || (IPV6!=m || m)
help
This option adds the "reject" expression that you can use to
explicitly deny and notify via TCP reset/ICMP informational errors
config NF_FLOW_TABLE_INET
tristate "Netfilter flow table mixed IPv4/IPv6 module"
- depends on NF_FLOW_TABLE_IPV4
- depends on NF_FLOW_TABLE_IPV6
+ depends on NF_FLOW_TABLE
help
This option adds the flow table mixed IPv4/IPv6 support.
config NETFILTER_XT_MATCH_OSF
tristate '"osf" Passive OS fingerprint match'
depends on NETFILTER_ADVANCED && NETFILTER_NETLINK
+ select NF_OSF
help
This option selects the Passive OS Fingerprinting match module
that allows to passively match the remote operating system by
nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
- nft_dynset.o
+ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
obj-$(CONFIG_NF_TABLES) += nf_tables.o
obj-$(CONFIG_NFT_COMPAT) += nft_compat.o
-obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o
-obj-$(CONFIG_NFT_META) += nft_meta.o
-obj-$(CONFIG_NFT_RT) += nft_rt.o
obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o
obj-$(CONFIG_NFT_CT) += nft_ct.o
obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o
obj-$(CONFIG_NFT_FIB) += nft_fib.o
obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o
obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o
+obj-$(CONFIG_NF_OSF) += nf_osf.o
# nf_tables netdev
obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o
# flow table infrastructure
obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
+nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
+
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
# generic X tables
EXPORT_SYMBOL(nf_nat_decode_session_hook);
#endif
-static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
+static void __net_init
+__netfilter_net_init(struct nf_hook_entries __rcu **e, int max)
{
int h;
If you want to compile it in kernel, say Y. To compile it as a
module, choose M here. If unsure, say N.
+config IP_VS_MH
+ tristate "maglev hashing scheduling"
+ ---help---
+ The maglev consistent hashing scheduling algorithm provides the
+ Google's Maglev hashing algorithm as a IPVS scheduler. It assigns
+ network connections to the servers through looking up a statically
+ assigned special hash table called the lookup table. Maglev hashing
+ is to assign a preference list of all the lookup table positions
+ to each destination.
+
+ Through this operation, The maglev hashing gives an almost equal
+ share of the lookup table to each of the destinations and provides
+ minimal disruption by using the lookup table. When the set of
+ destinations changes, a connection will likely be sent to the same
+ destination as it was before.
+
+ If you want to compile it in kernel, say Y. To compile it as a
+ module, choose M here. If unsure, say N.
+
config IP_VS_SED
tristate "shortest expected delay scheduling"
---help---
needs to be large enough to effectively fit all the destinations
multiplied by their respective weights.
+comment 'IPVS MH scheduler'
+
+config IP_VS_MH_TAB_INDEX
+ int "IPVS maglev hashing table index of size (the prime numbers)"
+ range 8 17
+ default 12
+ ---help---
+ The maglev hashing scheduler maps source IPs to destinations
+ stored in a hash table. This table is assigned by a preference
+ list of the positions to each destination until all slots in
+ the table are filled. The index determines the prime for size of
+ the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749,
+ 65521 or 131071. When using weights to allow destinations to
+ receive more connections, the table is assigned an amount
+ proportional to the weights specified. The table needs to be large
+ enough to effectively fit all the destinations multiplied by their
+ respective weights.
+
comment 'IPVS application helper'
config IP_VS_FTP
obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o
obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o
obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o
+obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o
obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o
obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o
static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
{
unsigned int hash;
- bool ret;
+ bool ret = false;
+
+ if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+ return refcount_dec_if_one(&cp->refcnt);
hash = ip_vs_conn_hashkey_conn(cp);
spin_lock(&cp->lock);
if (cp->flags & IP_VS_CONN_F_HASHED) {
- ret = false;
/* Decrease refcnt and unlink conn only if we are last user */
if (refcount_dec_if_one(&cp->refcnt)) {
hlist_del_rcu(&cp->c_list);
cp->flags &= ~IP_VS_CONN_F_HASHED;
ret = true;
}
- } else
- ret = refcount_read(&cp->refcnt) ? false : true;
+ }
spin_unlock(&cp->lock);
ct_write_unlock_bh(hash);
}
EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
-static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp)
-{
- __ip_vs_conn_put(cp);
- ip_vs_conn_expire(&cp->timer);
-}
-
/*
* Put back the conn and restart its timer with its timeout
*/
(refcount_read(&cp->refcnt) == 1) &&
!timer_pending(&cp->timer))
/* expire connection immediately */
- __ip_vs_conn_put_notimer(cp);
+ ip_vs_conn_expire(&cp->timer);
else
__ip_vs_conn_put_timer(cp);
}
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.inpkts++;
s->cnt.inpkts++;
s->cnt.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
struct netns_ipvs *ipvs = svc->ipvs;
struct ip_vs_cpu_stats *s;
+ local_bh_disable();
+
s = this_cpu_ptr(cp->dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
if (add && udest->af != svc->af)
ipvs->mixed_address_family_dests++;
+ /* keep the last_weight with latest non-0 weight */
+ if (add || udest->weight != 0)
+ atomic_set(&dest->last_weight, udest->weight);
+
/* set the weight and the flags */
atomic_set(&dest->weight, udest->weight);
conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn));
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
+#include <linux/hash.h>
#include <net/ip_vs.h>
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS);
}
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/jiffies.h>
+#include <linux/hash.h>
/* for sysctl */
#include <linux/fs.h>
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS);
}
tbl->counter = 1;
tbl->dead = false;
tbl->svc = svc;
+ atomic_set(&tbl->entries, 0);
/*
* Hook periodic timer for garbage collection
#include <linux/jiffies.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/hash.h>
/* for sysctl */
#include <linux/fs.h>
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS);
}
tbl->counter = 1;
tbl->dead = false;
tbl->svc = svc;
+ atomic_set(&tbl->entries, 0);
/*
* Hook periodic timer for garbage collection
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* IPVS: Maglev Hashing scheduling module
+ *
+ * Authors: Inju Song <inju.song@navercorp.com>
+ *
+ */
+
+/* The mh algorithm is to assign a preference list of all the lookup
+ * table positions to each destination and populate the table with
+ * the most-preferred position of destinations. Then it is to select
+ * destination with the hash key of source IP address through looking
+ * up a the lookup table.
+ *
+ * The algorithm is detailed in:
+ * [3.4 Consistent Hasing]
+https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf
+ *
+ */
+
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/ip.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+
+#include <net/ip_vs.h>
+
+#include <linux/siphash.h>
+#include <linux/bitops.h>
+#include <linux/gcd.h>
+
+#define IP_VS_SVC_F_SCHED_MH_FALLBACK IP_VS_SVC_F_SCHED1 /* MH fallback */
+#define IP_VS_SVC_F_SCHED_MH_PORT IP_VS_SVC_F_SCHED2 /* MH use port */
+
+struct ip_vs_mh_lookup {
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
+};
+
+struct ip_vs_mh_dest_setup {
+ unsigned int offset; /* starting offset */
+ unsigned int skip; /* skip */
+ unsigned int perm; /* next_offset */
+ int turns; /* weight / gcd() and rshift */
+};
+
+/* Available prime numbers for MH table */
+static int primes[] = {251, 509, 1021, 2039, 4093,
+ 8191, 16381, 32749, 65521, 131071};
+
+/* For IPVS MH entry hash table */
+#ifndef CONFIG_IP_VS_MH_TAB_INDEX
+#define CONFIG_IP_VS_MH_TAB_INDEX 12
+#endif
+#define IP_VS_MH_TAB_BITS (CONFIG_IP_VS_MH_TAB_INDEX / 2)
+#define IP_VS_MH_TAB_INDEX (CONFIG_IP_VS_MH_TAB_INDEX - 8)
+#define IP_VS_MH_TAB_SIZE primes[IP_VS_MH_TAB_INDEX]
+
+struct ip_vs_mh_state {
+ struct rcu_head rcu_head;
+ struct ip_vs_mh_lookup *lookup;
+ struct ip_vs_mh_dest_setup *dest_setup;
+ hsiphash_key_t hash1, hash2;
+ int gcd;
+ int rshift;
+};
+
+static inline void generate_hash_secret(hsiphash_key_t *hash1,
+ hsiphash_key_t *hash2)
+{
+ hash1->key[0] = 2654435761UL;
+ hash1->key[1] = 2654435761UL;
+
+ hash2->key[0] = 2654446892UL;
+ hash2->key[1] = 2654446892UL;
+}
+
+/* Helper function to determine if server is unavailable */
+static inline bool is_unavailable(struct ip_vs_dest *dest)
+{
+ return atomic_read(&dest->weight) <= 0 ||
+ dest->flags & IP_VS_DEST_F_OVERLOAD;
+}
+
+/* Returns hash value for IPVS MH entry */
+static inline unsigned int
+ip_vs_mh_hashkey(int af, const union nf_inet_addr *addr,
+ __be16 port, hsiphash_key_t *key, unsigned int offset)
+{
+ unsigned int v;
+ __be32 addr_fold = addr->ip;
+
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6)
+ addr_fold = addr->ip6[0] ^ addr->ip6[1] ^
+ addr->ip6[2] ^ addr->ip6[3];
+#endif
+ v = (offset + ntohs(port) + ntohl(addr_fold));
+ return hsiphash(&v, sizeof(v), key);
+}
+
+/* Reset all the hash buckets of the specified table. */
+static void ip_vs_mh_reset(struct ip_vs_mh_state *s)
+{
+ int i;
+ struct ip_vs_mh_lookup *l;
+ struct ip_vs_dest *dest;
+
+ l = &s->lookup[0];
+ for (i = 0; i < IP_VS_MH_TAB_SIZE; i++) {
+ dest = rcu_dereference_protected(l->dest, 1);
+ if (dest) {
+ ip_vs_dest_put(dest);
+ RCU_INIT_POINTER(l->dest, NULL);
+ }
+ l++;
+ }
+}
+
+static int ip_vs_mh_permutate(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ struct list_head *p;
+ struct ip_vs_mh_dest_setup *ds;
+ struct ip_vs_dest *dest;
+ int lw;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, skip
+ * permutation for the dests.
+ */
+ if (s->gcd < 1)
+ return 0;
+
+ /* Set dest_setup for the dests permutation */
+ p = &svc->destinations;
+ ds = &s->dest_setup[0];
+ while ((p = p->next) != &svc->destinations) {
+ dest = list_entry(p, struct ip_vs_dest, n_list);
+
+ ds->offset = ip_vs_mh_hashkey(svc->af, &dest->addr,
+ dest->port, &s->hash1, 0) %
+ IP_VS_MH_TAB_SIZE;
+ ds->skip = ip_vs_mh_hashkey(svc->af, &dest->addr,
+ dest->port, &s->hash2, 0) %
+ (IP_VS_MH_TAB_SIZE - 1) + 1;
+ ds->perm = ds->offset;
+
+ lw = atomic_read(&dest->last_weight);
+ ds->turns = ((lw / s->gcd) >> s->rshift) ? : (lw != 0);
+ ds++;
+ }
+
+ return 0;
+}
+
+static int ip_vs_mh_populate(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ int n, c, dt_count;
+ unsigned long *table;
+ struct list_head *p;
+ struct ip_vs_mh_dest_setup *ds;
+ struct ip_vs_dest *dest, *new_dest;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, skip
+ * the population for the dests and reset lookup table.
+ */
+ if (s->gcd < 1) {
+ ip_vs_mh_reset(s);
+ return 0;
+ }
+
+ table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE),
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ p = &svc->destinations;
+ n = 0;
+ dt_count = 0;
+ while (n < IP_VS_MH_TAB_SIZE) {
+ if (p == &svc->destinations)
+ p = p->next;
+
+ ds = &s->dest_setup[0];
+ while (p != &svc->destinations) {
+ /* Ignore added server with zero weight */
+ if (ds->turns < 1) {
+ p = p->next;
+ ds++;
+ continue;
+ }
+
+ c = ds->perm;
+ while (test_bit(c, table)) {
+ /* Add skip, mod IP_VS_MH_TAB_SIZE */
+ ds->perm += ds->skip;
+ if (ds->perm >= IP_VS_MH_TAB_SIZE)
+ ds->perm -= IP_VS_MH_TAB_SIZE;
+ c = ds->perm;
+ }
+
+ __set_bit(c, table);
+
+ dest = rcu_dereference_protected(s->lookup[c].dest, 1);
+ new_dest = list_entry(p, struct ip_vs_dest, n_list);
+ if (dest != new_dest) {
+ if (dest)
+ ip_vs_dest_put(dest);
+ ip_vs_dest_hold(new_dest);
+ RCU_INIT_POINTER(s->lookup[c].dest, new_dest);
+ }
+
+ if (++n == IP_VS_MH_TAB_SIZE)
+ goto out;
+
+ if (++dt_count >= ds->turns) {
+ dt_count = 0;
+ p = p->next;
+ ds++;
+ }
+ }
+ }
+
+out:
+ kfree(table);
+ return 0;
+}
+
+/* Get ip_vs_dest associated with supplied parameters. */
+static inline struct ip_vs_dest *
+ip_vs_mh_get(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
+{
+ unsigned int hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, 0)
+ % IP_VS_MH_TAB_SIZE;
+ struct ip_vs_dest *dest = rcu_dereference(s->lookup[hash].dest);
+
+ return (!dest || is_unavailable(dest)) ? NULL : dest;
+}
+
+/* As ip_vs_mh_get, but with fallback if selected server is unavailable */
+static inline struct ip_vs_dest *
+ip_vs_mh_get_fallback(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
+{
+ unsigned int offset, roffset;
+ unsigned int hash, ihash;
+ struct ip_vs_dest *dest;
+
+ /* First try the dest it's supposed to go to */
+ ihash = ip_vs_mh_hashkey(svc->af, addr, port,
+ &s->hash1, 0) % IP_VS_MH_TAB_SIZE;
+ dest = rcu_dereference(s->lookup[ihash].dest);
+ if (!dest)
+ return NULL;
+ if (!is_unavailable(dest))
+ return dest;
+
+ IP_VS_DBG_BUF(6, "MH: selected unavailable server %s:%u, reselecting",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
+
+ /* If the original dest is unavailable, loop around the table
+ * starting from ihash to find a new dest
+ */
+ for (offset = 0; offset < IP_VS_MH_TAB_SIZE; offset++) {
+ roffset = (offset + ihash) % IP_VS_MH_TAB_SIZE;
+ hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1,
+ roffset) % IP_VS_MH_TAB_SIZE;
+ dest = rcu_dereference(s->lookup[hash].dest);
+ if (!dest)
+ break;
+ if (!is_unavailable(dest))
+ return dest;
+ IP_VS_DBG_BUF(6,
+ "MH: selected unavailable server %s:%u (offset %u), reselecting",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr),
+ ntohs(dest->port), roffset);
+ }
+
+ return NULL;
+}
+
+/* Assign all the hash buckets of the specified table with the service. */
+static int ip_vs_mh_reassign(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ int ret;
+
+ if (svc->num_dests > IP_VS_MH_TAB_SIZE)
+ return -EINVAL;
+
+ if (svc->num_dests >= 1) {
+ s->dest_setup = kcalloc(svc->num_dests,
+ sizeof(struct ip_vs_mh_dest_setup),
+ GFP_KERNEL);
+ if (!s->dest_setup)
+ return -ENOMEM;
+ }
+
+ ip_vs_mh_permutate(s, svc);
+
+ ret = ip_vs_mh_populate(s, svc);
+ if (ret < 0)
+ goto out;
+
+ IP_VS_DBG_BUF(6, "MH: reassign lookup table of %s:%u\n",
+ IP_VS_DBG_ADDR(svc->af, &svc->addr),
+ ntohs(svc->port));
+
+out:
+ if (svc->num_dests >= 1) {
+ kfree(s->dest_setup);
+ s->dest_setup = NULL;
+ }
+ return ret;
+}
+
+static int ip_vs_mh_gcd_weight(struct ip_vs_service *svc)
+{
+ struct ip_vs_dest *dest;
+ int weight;
+ int g = 0;
+
+ list_for_each_entry(dest, &svc->destinations, n_list) {
+ weight = atomic_read(&dest->last_weight);
+ if (weight > 0) {
+ if (g > 0)
+ g = gcd(weight, g);
+ else
+ g = weight;
+ }
+ }
+ return g;
+}
+
+/* To avoid assigning huge weight for the MH table,
+ * calculate shift value with gcd.
+ */
+static int ip_vs_mh_shift_weight(struct ip_vs_service *svc, int gcd)
+{
+ struct ip_vs_dest *dest;
+ int new_weight, weight = 0;
+ int mw, shift;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, return
+ * shift value as zero.
+ */
+ if (gcd < 1)
+ return 0;
+
+ list_for_each_entry(dest, &svc->destinations, n_list) {
+ new_weight = atomic_read(&dest->last_weight);
+ if (new_weight > weight)
+ weight = new_weight;
+ }
+
+ /* Because gcd is greater than zero,
+ * the maximum weight and gcd are always greater than zero
+ */
+ mw = weight / gcd;
+
+ /* shift = occupied bits of weight/gcd - MH highest bits */
+ shift = fls(mw) - IP_VS_MH_TAB_BITS;
+ return (shift >= 0) ? shift : 0;
+}
+
+static void ip_vs_mh_state_free(struct rcu_head *head)
+{
+ struct ip_vs_mh_state *s;
+
+ s = container_of(head, struct ip_vs_mh_state, rcu_head);
+ kfree(s->lookup);
+ kfree(s);
+}
+
+static int ip_vs_mh_init_svc(struct ip_vs_service *svc)
+{
+ int ret;
+ struct ip_vs_mh_state *s;
+
+ /* Allocate the MH table for this service */
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ s->lookup = kcalloc(IP_VS_MH_TAB_SIZE, sizeof(struct ip_vs_mh_lookup),
+ GFP_KERNEL);
+ if (!s->lookup) {
+ kfree(s);
+ return -ENOMEM;
+ }
+
+ generate_hash_secret(&s->hash1, &s->hash2);
+ s->gcd = ip_vs_mh_gcd_weight(svc);
+ s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+ IP_VS_DBG(6,
+ "MH lookup table (memory=%zdbytes) allocated for current service\n",
+ sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+
+ /* Assign the lookup table with current dests */
+ ret = ip_vs_mh_reassign(s, svc);
+ if (ret < 0) {
+ ip_vs_mh_reset(s);
+ ip_vs_mh_state_free(&s->rcu_head);
+ return ret;
+ }
+
+ /* No more failures, attach state */
+ svc->sched_data = s;
+ return 0;
+}
+
+static void ip_vs_mh_done_svc(struct ip_vs_service *svc)
+{
+ struct ip_vs_mh_state *s = svc->sched_data;
+
+ /* Got to clean up lookup entry here */
+ ip_vs_mh_reset(s);
+
+ call_rcu(&s->rcu_head, ip_vs_mh_state_free);
+ IP_VS_DBG(6, "MH lookup table (memory=%zdbytes) released\n",
+ sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+}
+
+static int ip_vs_mh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
+{
+ struct ip_vs_mh_state *s = svc->sched_data;
+
+ s->gcd = ip_vs_mh_gcd_weight(svc);
+ s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+ /* Assign the lookup table with the updated service */
+ return ip_vs_mh_reassign(s, svc);
+}
+
+/* Helper function to get port number */
+static inline __be16
+ip_vs_mh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
+{
+ __be16 _ports[2], *ports;
+
+ /* At this point we know that we have a valid packet of some kind.
+ * Because ICMP packets are only guaranteed to have the first 8
+ * bytes, let's just grab the ports. Fortunately they're in the
+ * same position for all three of the protocols we care about.
+ */
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_SCTP:
+ ports = skb_header_pointer(skb, iph->len, sizeof(_ports),
+ &_ports);
+ if (unlikely(!ports))
+ return 0;
+
+ if (likely(!ip_vs_iph_inverse(iph)))
+ return ports[0];
+ else
+ return ports[1];
+ default:
+ return 0;
+ }
+}
+
+/* Maglev Hashing scheduling */
+static struct ip_vs_dest *
+ip_vs_mh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
+{
+ struct ip_vs_dest *dest;
+ struct ip_vs_mh_state *s;
+ __be16 port = 0;
+ const union nf_inet_addr *hash_addr;
+
+ hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr;
+
+ IP_VS_DBG(6, "%s : Scheduling...\n", __func__);
+
+ if (svc->flags & IP_VS_SVC_F_SCHED_MH_PORT)
+ port = ip_vs_mh_get_port(skb, iph);
+
+ s = (struct ip_vs_mh_state *)svc->sched_data;
+
+ if (svc->flags & IP_VS_SVC_F_SCHED_MH_FALLBACK)
+ dest = ip_vs_mh_get_fallback(svc, s, hash_addr, port);
+ else
+ dest = ip_vs_mh_get(svc, s, hash_addr, port);
+
+ if (!dest) {
+ ip_vs_scheduler_err(svc, "no destination available");
+ return NULL;
+ }
+
+ IP_VS_DBG_BUF(6, "MH: source IP address %s:%u --> server %s:%u\n",
+ IP_VS_DBG_ADDR(svc->af, hash_addr),
+ ntohs(port),
+ IP_VS_DBG_ADDR(dest->af, &dest->addr),
+ ntohs(dest->port));
+
+ return dest;
+}
+
+/* IPVS MH Scheduler structure */
+static struct ip_vs_scheduler ip_vs_mh_scheduler = {
+ .name = "mh",
+ .refcnt = ATOMIC_INIT(0),
+ .module = THIS_MODULE,
+ .n_list = LIST_HEAD_INIT(ip_vs_mh_scheduler.n_list),
+ .init_service = ip_vs_mh_init_svc,
+ .done_service = ip_vs_mh_done_svc,
+ .add_dest = ip_vs_mh_dest_changed,
+ .del_dest = ip_vs_mh_dest_changed,
+ .upd_dest = ip_vs_mh_dest_changed,
+ .schedule = ip_vs_mh_schedule,
+};
+
+static int __init ip_vs_mh_init(void)
+{
+ return register_ip_vs_scheduler(&ip_vs_mh_scheduler);
+}
+
+static void __exit ip_vs_mh_cleanup(void)
+{
+ unregister_ip_vs_scheduler(&ip_vs_mh_scheduler);
+ rcu_barrier();
+}
+
+module_init(ip_vs_mh_init);
+module_exit(ip_vs_mh_cleanup);
+MODULE_DESCRIPTION("Maglev hashing ipvs scheduler");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Inju Song <inju.song@navercorp.com>");
return tcp_state_active_table[state];
}
-static struct tcp_states_t tcp_states [] = {
+static struct tcp_states_t tcp_states[] = {
/* INPUT */
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};
-static struct tcp_states_t tcp_states_dos [] = {
+static struct tcp_states_t tcp_states_dos[] = {
/* INPUT */
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) &
+ return (offset + hash_32(ntohs(port) + ntohl(addr_fold),
+ IP_VS_SH_TAB_BITS)) &
IP_VS_SH_TAB_MASK;
}
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched/signal.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
} else {
array = kcalloc(count, sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
+EXPORT_SYMBOL_GPL(nf_conntrack_max);
seqcount_t nf_conntrack_generation __read_mostly;
static unsigned int nf_conntrack_hash_rnd __read_mostly;
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
- return a->master == b->master && a->class == b->class &&
+ return a->master == b->master &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
+ if (i->class != expect->class)
+ return -EALREADY;
+
if (nf_ct_remove_expect(i))
break;
} else if (expect_clash(i, expect)) {
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
+#include <linux/kmemleak.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
rcu_read_unlock();
alloc = max(newlen, NF_CT_EXT_PREALLOC);
+ kmemleak_not_leak(old);
new = __krealloc(old, alloc, gfp);
if (!new)
return NULL;
.timeout = 5 * 60,
};
-/* don't make this __exit, since it's called from __init ! */
-static void nf_conntrack_ftp_fini(void)
+static void __exit nf_conntrack_ftp_fini(void)
{
nf_conntrack_helpers_unregister(ftp, ports_c * 2);
kfree(ftp_buffer);
static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly;
static struct nf_conntrack_expect_policy irc_exp_policy;
-static void nf_conntrack_irc_fini(void);
-
static int __init nf_conntrack_irc_init(void)
{
int i, ret;
return 0;
}
-/* This function is intentionally _NOT_ defined as __exit, because
- * it is needed by the init function */
-static void nf_conntrack_irc_fini(void)
+static void __exit nf_conntrack_irc_fini(void)
{
nf_conntrack_helpers_unregister(irc, ports_c);
kfree(irc_buffer);
if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks)))
goto nla_put_failure;
+ if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max)))
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return skb->len;
return NF_ACCEPT; /* Don't change state */
}
break;
+ case TCP_CONNTRACK_SYN_SENT2:
+ /* tcp_conntracks table is not smart enough to handle
+ * simultaneous open.
+ */
+ ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
+ break;
+ case TCP_CONNTRACK_SYN_RECV:
+ if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
+ ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
+ new_state = TCP_CONNTRACK_ESTABLISHED;
+ break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
.timeout = 5 * 60,
};
-/* don't make this __exit, since it's called from __init ! */
-static void nf_conntrack_sane_fini(void)
+static void __exit nf_conntrack_sane_fini(void)
{
nf_conntrack_helpers_unregister(sane, ports_c * 2);
kfree(sane_buffer);
datalen, rtp_exp, rtcp_exp,
mediaoff, medialen, daddr);
else {
- if (nf_ct_expect_related(rtp_exp) == 0) {
- if (nf_ct_expect_related(rtcp_exp) != 0)
- nf_ct_unexpect_related(rtp_exp);
- else
+ /* -EALREADY handling works around end-points that send
+ * SDP messages with identical port but different media type,
+ * we pretend expectation was set up.
+ */
+ int errp = nf_ct_expect_related(rtp_exp);
+
+ if (errp == 0 || errp == -EALREADY) {
+ int errcp = nf_ct_expect_related(rtcp_exp);
+
+ if (errcp == 0 || errcp == -EALREADY)
ret = NF_ACCEPT;
+ else if (errp == 0)
+ nf_ct_unexpect_related(rtp_exp);
}
}
nf_ct_expect_put(rtcp_exp);
},
};
-static void nf_conntrack_sip_fini(void)
+static void __exit nf_conntrack_sip_fini(void)
{
nf_conntrack_helpers_unregister(sip, ports_c * 4);
}
.timeout = 5 * 60,
};
-static void nf_conntrack_tftp_fini(void)
+static void __exit nf_conntrack_tftp_fini(void)
{
nf_conntrack_helpers_unregister(tftp, ports_c * 2);
}
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
struct rcu_head rcu_head;
};
+static DEFINE_MUTEX(flowtable_lock);
+static LIST_HEAD(flowtables);
+
+static void
+flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
+ struct nf_flow_route *route,
+ enum flow_offload_tuple_dir dir)
+{
+ struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
+ struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+ struct dst_entry *dst = route->tuple[dir].dst;
+
+ ft->dir = dir;
+
+ switch (ctt->src.l3num) {
+ case NFPROTO_IPV4:
+ ft->src_v4 = ctt->src.u3.in;
+ ft->dst_v4 = ctt->dst.u3.in;
+ ft->mtu = ip_dst_mtu_maybe_forward(dst, true);
+ break;
+ case NFPROTO_IPV6:
+ ft->src_v6 = ctt->src.u3.in6;
+ ft->dst_v6 = ctt->dst.u3.in6;
+ ft->mtu = ip6_dst_mtu_forward(dst);
+ break;
+ }
+
+ ft->l3proto = ctt->src.l3num;
+ ft->l4proto = ctt->dst.protonum;
+ ft->src_port = ctt->src.u.tcp.port;
+ ft->dst_port = ctt->dst.u.tcp.port;
+
+ ft->iifidx = route->tuple[dir].ifindex;
+ ft->oifidx = route->tuple[!dir].ifindex;
+ ft->dst_cache = dst;
+}
+
struct flow_offload *
flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
{
entry->ct = ct;
- switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
- case NFPROTO_IPV4:
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
- break;
- case NFPROTO_IPV6:
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
- break;
- }
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
- FLOW_OFFLOAD_DIR_ORIGINAL;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
- FLOW_OFFLOAD_DIR_REPLY;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
+ flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+ flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY);
if (ct->status & IPS_SRC_NAT)
flow->flags |= FLOW_OFFLOAD_SNAT;
- else if (ct->status & IPS_DST_NAT)
+ if (ct->status & IPS_DST_NAT)
flow->flags |= FLOW_OFFLOAD_DNAT;
return flow;
}
EXPORT_SYMBOL_GPL(flow_offload_alloc);
+static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
+{
+ tcp->state = TCP_CONNTRACK_ESTABLISHED;
+ tcp->seen[0].td_maxwin = 0;
+ tcp->seen[1].td_maxwin = 0;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+ const struct nf_conntrack_l4proto *l4proto;
+ struct net *net = nf_ct_net(ct);
+ unsigned int *timeouts;
+ unsigned int timeout;
+ int l4num;
+
+ l4num = nf_ct_protonum(ct);
+ if (l4num == IPPROTO_TCP)
+ flow_offload_fixup_tcp(&ct->proto.tcp);
+
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), l4num);
+ if (!l4proto)
+ return;
+
+ timeouts = l4proto->get_timeouts(net);
+ if (!timeouts)
+ return;
+
+ if (l4num == IPPROTO_TCP)
+ timeout = timeouts[TCP_CONNTRACK_ESTABLISHED];
+ else if (l4num == IPPROTO_UDP)
+ timeout = timeouts[UDP_CT_REPLIED];
+ else
+ return;
+
+ ct->timeout = nfct_time_stamp + timeout;
+}
+
void flow_offload_free(struct flow_offload *flow)
{
struct flow_offload_entry *e;
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
e = container_of(flow, struct flow_offload_entry, flow);
- nf_ct_delete(e->ct, 0, 0);
+ if (flow->flags & FLOW_OFFLOAD_DYING)
+ nf_ct_delete(e->ct, 0, 0);
nf_ct_put(e->ct);
kfree_rcu(e, rcu_head);
}
EXPORT_SYMBOL_GPL(flow_offload_free);
-void flow_offload_dead(struct flow_offload *flow)
+static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple *tuple = data;
+
+ return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple_rhash *tuplehash = data;
+
+ return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
{
- flow->flags |= FLOW_OFFLOAD_DYING;
+ const struct flow_offload_tuple *tuple = arg->key;
+ const struct flow_offload_tuple_rhash *x = ptr;
+
+ if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
+ return 1;
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(flow_offload_dead);
+
+static const struct rhashtable_params nf_flow_offload_rhash_params = {
+ .head_offset = offsetof(struct flow_offload_tuple_rhash, node),
+ .hashfn = flow_offload_hash,
+ .obj_hashfn = flow_offload_hash_obj,
+ .obj_cmpfn = flow_offload_hash_cmp,
+ .automatic_shrinking = true,
+};
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
{
rhashtable_insert_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
rhashtable_insert_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
return 0;
}
EXPORT_SYMBOL_GPL(flow_offload_add);
static void flow_offload_del(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
+ struct flow_offload_entry *e;
+
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
+
+ e = container_of(flow, struct flow_offload_entry, flow);
+ clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
flow_offload_free(flow);
}
+void flow_offload_teardown(struct flow_offload *flow)
+{
+ struct flow_offload_entry *e;
+
+ flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+
+ e = container_of(flow, struct flow_offload_entry, flow);
+ flow_offload_fixup_ct_state(e->ct);
+}
+EXPORT_SYMBOL_GPL(flow_offload_teardown);
+
struct flow_offload_tuple_rhash *
flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple)
{
- return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
- *flow_table->type->params);
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct flow_offload *flow;
+ int dir;
+
+ tuplehash = rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
+ nf_flow_offload_rhash_params);
+ if (!tuplehash)
+ return NULL;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))
+ return NULL;
+
+ return tuplehash;
}
EXPORT_SYMBOL_GPL(flow_offload_lookup);
return (__s32)(flow->timeout - (u32)jiffies) <= 0;
}
-static inline bool nf_flow_is_dying(const struct flow_offload *flow)
-{
- return flow->flags & FLOW_OFFLOAD_DYING;
-}
-
static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
{
struct flow_offload_tuple_rhash *tuplehash;
flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
if (nf_flow_has_expired(flow) ||
- nf_flow_is_dying(flow))
+ (flow->flags & (FLOW_OFFLOAD_DYING |
+ FLOW_OFFLOAD_TEARDOWN)))
flow_offload_del(flow_table, flow);
}
out:
return 1;
}
-void nf_flow_offload_work_gc(struct work_struct *work)
+static void nf_flow_offload_work_gc(struct work_struct *work)
{
struct nf_flowtable *flow_table;
nf_flow_offload_gc_step(flow_table);
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
-EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
-
-static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
-{
- const struct flow_offload_tuple *tuple = data;
-
- return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
-}
-
-static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
-{
- const struct flow_offload_tuple_rhash *tuplehash = data;
-
- return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
-}
-
-static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
- const void *ptr)
-{
- const struct flow_offload_tuple *tuple = arg->key;
- const struct flow_offload_tuple_rhash *x = ptr;
-
- if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
- return 1;
-
- return 0;
-}
-
-const struct rhashtable_params nf_flow_offload_rhash_params = {
- .head_offset = offsetof(struct flow_offload_tuple_rhash, node),
- .hashfn = flow_offload_hash,
- .obj_hashfn = flow_offload_hash_obj,
- .obj_cmpfn = flow_offload_hash_cmp,
- .automatic_shrinking = true,
-};
-EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params);
static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
__be16 port, __be16 new_port)
}
EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
+int nf_flow_table_init(struct nf_flowtable *flowtable)
+{
+ int err;
+
+ INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+
+ err = rhashtable_init(&flowtable->rhashtable,
+ &nf_flow_offload_rhash_params);
+ if (err < 0)
+ return err;
+
+ queue_delayed_work(system_power_efficient_wq,
+ &flowtable->gc_work, HZ);
+
+ mutex_lock(&flowtable_lock);
+ list_add(&flowtable->list, &flowtables);
+ mutex_unlock(&flowtable_lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_init);
+
static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
{
struct net_device *dev = data;
- if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+ if (!dev) {
+ flow_offload_teardown(flow);
return;
+ }
- flow_offload_dead(flow);
+ if (flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
+ flow->tuplehash[1].tuple.iifidx == dev->ifindex)
+ flow_offload_dead(flow);
}
static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
- void *data)
+ struct net_device *dev)
{
- nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data);
+ nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
flush_delayed_work(&flowtable->gc_work);
}
void nf_flow_table_cleanup(struct net *net, struct net_device *dev)
{
- nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev);
+ struct nf_flowtable *flowtable;
+
+ mutex_lock(&flowtable_lock);
+ list_for_each_entry(flowtable, &flowtables, list)
+ nf_flow_table_iterate_cleanup(flowtable, dev);
+ mutex_unlock(&flowtable_lock);
}
EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
void nf_flow_table_free(struct nf_flowtable *flow_table)
{
+ mutex_lock(&flowtable_lock);
+ list_del(&flow_table->list);
+ mutex_unlock(&flowtable_lock);
+ cancel_delayed_work_sync(&flow_table->gc_work);
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
WARN_ON(!nf_flow_offload_gc_step(flow_table));
+ rhashtable_destroy(&flow_table->rhashtable);
}
EXPORT_SYMBOL_GPL(nf_flow_table_free);
static struct nf_flowtable_type flowtable_inet = {
.family = NFPROTO_INET,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_inet_hook,
.owner = THIS_MODULE,
--- /dev/null
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/neighbour.h>
+#include <net/netfilter/nf_flow_table.h>
+/* For layer 4 checksum field offset. */
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+static int nf_flow_state_check(struct flow_offload *flow, int proto,
+ struct sk_buff *skb, unsigned int thoff)
+{
+ struct tcphdr *tcph;
+
+ if (proto != IPPROTO_TCP)
+ return 0;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ if (unlikely(tcph->fin || tcph->rst)) {
+ flow_offload_teardown(flow);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
+ __be32 addr, __be32 new_addr)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
+
+ return 0;
+}
+
+static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
+ __be32 addr, __be32 new_addr)
+{
+ struct udphdr *udph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*udph)))
+ return -1;
+
+ udph = (void *)(skb_network_header(skb) + thoff);
+ if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace4(&udph->check, skb, addr,
+ new_addr, true);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
+ unsigned int thoff, __be32 addr,
+ __be32 new_addr)
+{
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ case IPPROTO_UDP:
+ if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ }
+
+ return 0;
+}
+
+static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ struct iphdr *iph, unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
+ iph->saddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
+ iph->daddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+ csum_replace4(&iph->check, addr, new_addr);
+
+ return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ struct iphdr *iph, unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
+ iph->daddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
+ iph->saddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+ csum_replace4(&iph->check, addr, new_addr);
+
+ return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ unsigned int thoff, enum flow_offload_tuple_dir dir)
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+ nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
+ return -1;
+ if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+ nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
+ return -1;
+
+ return 0;
+}
+
+static bool ip_has_options(unsigned int thoff)
+{
+ return thoff != sizeof(struct iphdr);
+}
+
+static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
+ struct flow_offload_tuple *tuple)
+{
+ struct flow_ports *ports;
+ unsigned int thoff;
+ struct iphdr *iph;
+
+ if (!pskb_may_pull(skb, sizeof(*iph)))
+ return -1;
+
+ iph = ip_hdr(skb);
+ thoff = iph->ihl * 4;
+
+ if (ip_is_fragment(iph) ||
+ unlikely(ip_has_options(thoff)))
+ return -1;
+
+ if (iph->protocol != IPPROTO_TCP &&
+ iph->protocol != IPPROTO_UDP)
+ return -1;
+
+ thoff = iph->ihl * 4;
+ if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+ return -1;
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+ tuple->src_v4.s_addr = iph->saddr;
+ tuple->dst_v4.s_addr = iph->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET;
+ tuple->l4proto = iph->protocol;
+ tuple->iifidx = dev->ifindex;
+
+ return 0;
+}
+
+/* Based on ip_exceeds_mtu(). */
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
+ return false;
+
+ return true;
+}
+
+unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ struct flow_offload_tuple tuple = {};
+ enum flow_offload_tuple_dir dir;
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ const struct rtable *rt;
+ unsigned int thoff;
+ struct iphdr *iph;
+ __be32 nexthop;
+
+ if (skb->protocol != htons(ETH_P_IP))
+ return NF_ACCEPT;
+
+ if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+ return NF_ACCEPT;
+
+ tuplehash = flow_offload_lookup(flow_table, &tuple);
+ if (tuplehash == NULL)
+ return NF_ACCEPT;
+
+ outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+ if (!outdev)
+ return NF_ACCEPT;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
+ (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
+ return NF_ACCEPT;
+
+ if (skb_try_make_writable(skb, sizeof(*iph)))
+ return NF_DROP;
+
+ thoff = ip_hdr(skb)->ihl * 4;
+ if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
+ return NF_ACCEPT;
+
+ if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+ nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
+ return NF_DROP;
+
+ flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ iph = ip_hdr(skb);
+ ip_decrease_ttl(iph);
+
+ skb->dev = outdev;
+ nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+ neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+
+ return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
+
+static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
+ struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
+ new_addr->s6_addr32, true);
+
+ return 0;
+}
+
+static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
+ struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ struct udphdr *udph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*udph)))
+ return -1;
+
+ udph = (void *)(skb_network_header(skb) + thoff);
+ if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
+ new_addr->s6_addr32, true);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff, struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ switch (ip6h->nexthdr) {
+ case IPPROTO_TCP:
+ if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ case IPPROTO_UDP:
+ if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ }
+
+ return 0;
+}
+
+static int nf_flow_snat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
+ ip6h->saddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
+ ip6h->daddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
+ ip6h->daddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
+ ip6h->saddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_nat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb,
+ enum flow_offload_tuple_dir dir)
+{
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ unsigned int thoff = sizeof(*ip6h);
+
+ if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+ nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+ return -1;
+ if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+ nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+ return -1;
+
+ return 0;
+}
+
+static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
+ struct flow_offload_tuple *tuple)
+{
+ struct flow_ports *ports;
+ struct ipv6hdr *ip6h;
+ unsigned int thoff;
+
+ if (!pskb_may_pull(skb, sizeof(*ip6h)))
+ return -1;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->nexthdr != IPPROTO_TCP &&
+ ip6h->nexthdr != IPPROTO_UDP)
+ return -1;
+
+ thoff = sizeof(*ip6h);
+ if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+ return -1;
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+ tuple->src_v6 = ip6h->saddr;
+ tuple->dst_v6 = ip6h->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET6;
+ tuple->l4proto = ip6h->nexthdr;
+ tuple->iifidx = dev->ifindex;
+
+ return 0;
+}
+
+unsigned int
+nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ struct flow_offload_tuple tuple = {};
+ enum flow_offload_tuple_dir dir;
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ struct in6_addr *nexthop;
+ struct ipv6hdr *ip6h;
+ struct rt6_info *rt;
+
+ if (skb->protocol != htons(ETH_P_IPV6))
+ return NF_ACCEPT;
+
+ if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
+ return NF_ACCEPT;
+
+ tuplehash = flow_offload_lookup(flow_table, &tuple);
+ if (tuplehash == NULL)
+ return NF_ACCEPT;
+
+ outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+ if (!outdev)
+ return NF_ACCEPT;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+ return NF_ACCEPT;
+
+ if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb,
+ sizeof(*ip6h)))
+ return NF_ACCEPT;
+
+ if (skb_try_make_writable(skb, sizeof(*ip6h)))
+ return NF_DROP;
+
+ if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+ nf_flow_nat_ipv6(flow, skb, dir) < 0)
+ return NF_DROP;
+
+ flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ ip6h = ipv6_hdr(skb);
+ ip6h->hop_limit--;
+
+ skb->dev = outdev;
+ nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
+ neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
+
+ return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
static int in_range(const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range)
+ const struct nf_nat_range2 *range)
{
/* If we are supposed to map IPs, then we must be in the
* range specified, otherwise let this drag us onto a new src IP.
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
- const struct nf_nat_range *range)
+ const struct nf_nat_range2 *range)
{
unsigned int h = hash_by_src(net, tuple);
const struct nf_conn *ct;
static void
find_best_ips_proto(const struct nf_conntrack_zone *zone,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
static void
get_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_tuple *orig_tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
/* Only bother mapping if it's not already in range and unique */
if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
- if (l4proto->in_range(tuple, maniptype,
- &range->min_proto,
- &range->max_proto) &&
+ if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) &&
+ l4proto->in_range(tuple, maniptype,
+ &range->min_proto,
+ &range->max_proto) &&
(range->min_proto.all == range->max_proto.all ||
!nf_nat_used_tuple(tuple, ct)))
goto out;
}
}
- /* Last change: get protocol to try to obtain unique tuple. */
+ /* Last chance: get protocol to try to obtain unique tuple. */
l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct);
out:
rcu_read_unlock();
unsigned int
nf_nat_setup_info(struct nf_conn *ct,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype)
{
struct net *net = nf_ct_net(ct);
(manip == NF_NAT_MANIP_SRC ?
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
- struct nf_nat_range range = {
+ struct nf_nat_range2 range = {
.flags = NF_NAT_RANGE_MAP_IPS,
.min_addr = ip,
.max_addr = ip,
static int nfnetlink_parse_nat_proto(struct nlattr *attr,
const struct nf_conn *ct,
- struct nf_nat_range *range)
+ struct nf_nat_range2 *range)
{
struct nlattr *tb[CTA_PROTONAT_MAX+1];
const struct nf_nat_l4proto *l4proto;
static int
nfnetlink_parse_nat(const struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range,
+ const struct nf_conn *ct, struct nf_nat_range2 *range,
const struct nf_nat_l3proto *l3proto)
{
struct nlattr *tb[CTA_NAT_MAX+1];
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
const struct nf_nat_l3proto *l3proto;
int err;
void nf_nat_follow_master(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
u16 *rover)
: tuple->src.u.all);
} else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) {
off = prandom_u32();
+ } else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) {
+ off = (ntohs(*portptr) - ntohs(range->base_proto.all));
} else {
off = *rover;
}
*portptr = htons(min + off % range_size);
if (++i != range_size && nf_nat_used_tuple(tuple, ct))
continue;
- if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL))
+ if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL|
+ NF_NAT_RANGE_PROTO_OFFSET)))
*rover = off;
return;
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
- struct nf_nat_range *range)
+ struct nf_nat_range2 *range)
{
if (tb[CTA_PROTONAT_PORT_MIN]) {
range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]);
static void
dccp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void
sctp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void
tcp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void
udp_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void
udplite_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto,
struct nf_conntrack_tuple *tuple,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
__be32 newdst;
- struct nf_nat_range newrange;
+ struct nf_nat_range2 newrange;
WARN_ON(hooknum != NF_INET_PRE_ROUTING &&
hooknum != NF_INET_LOCAL_OUT);
static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
unsigned int
-nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
unsigned int hooknum)
{
- struct nf_nat_range newrange;
+ struct nf_nat_range2 newrange;
struct in6_addr newdst;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
static void nf_nat_sip_expected(struct nf_conn *ct,
struct nf_conntrack_expect *exp)
{
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
/* This must be a fresh one. */
BUG_ON(ct->status & IPS_NAT_DONE_MASK);
--- /dev/null
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <linux/capability.h>
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+
+#include <net/ip.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/netfilter/nf_osf.h>
+
+static inline int nf_osf_ttl(const struct sk_buff *skb,
+ const struct nf_osf_info *info,
+ unsigned char f_ttl)
+{
+ const struct iphdr *ip = ip_hdr(skb);
+
+ if (info->flags & NF_OSF_TTL) {
+ if (info->ttl == NF_OSF_TTL_TRUE)
+ return ip->ttl == f_ttl;
+ if (info->ttl == NF_OSF_TTL_NOCHECK)
+ return 1;
+ else if (ip->ttl <= f_ttl)
+ return 1;
+ else {
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+ int ret = 0;
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(ip->saddr, ifa)) {
+ ret = (ip->ttl == f_ttl);
+ break;
+ }
+ }
+ endfor_ifa(in_dev);
+
+ return ret;
+ }
+ }
+
+ return ip->ttl == f_ttl;
+}
+
+bool
+nf_osf_match(const struct sk_buff *skb, u_int8_t family,
+ int hooknum, struct net_device *in, struct net_device *out,
+ const struct nf_osf_info *info, struct net *net,
+ const struct list_head *nf_osf_fingers)
+{
+ const unsigned char *optp = NULL, *_optp = NULL;
+ unsigned int optsize = 0, check_WSS = 0;
+ int fmatch = FMATCH_WRONG, fcount = 0;
+ const struct iphdr *ip = ip_hdr(skb);
+ const struct nf_osf_user_finger *f;
+ unsigned char opts[MAX_IPOPTLEN];
+ const struct nf_osf_finger *kf;
+ u16 window, totlen, mss = 0;
+ const struct tcphdr *tcp;
+ struct tcphdr _tcph;
+ bool df;
+
+ tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+ if (!tcp)
+ return false;
+
+ if (!tcp->syn)
+ return false;
+
+ totlen = ntohs(ip->tot_len);
+ df = ntohs(ip->frag_off) & IP_DF;
+ window = ntohs(tcp->window);
+
+ if (tcp->doff * 4 > sizeof(struct tcphdr)) {
+ optsize = tcp->doff * 4 - sizeof(struct tcphdr);
+
+ _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) +
+ sizeof(struct tcphdr), optsize, opts);
+ }
+
+ list_for_each_entry_rcu(kf, &nf_osf_fingers[df], finger_entry) {
+ int foptsize, optnum;
+
+ f = &kf->finger;
+
+ if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre))
+ continue;
+
+ optp = _optp;
+ fmatch = FMATCH_WRONG;
+
+ if (totlen != f->ss || !nf_osf_ttl(skb, info, f->ttl))
+ continue;
+
+ /*
+ * Should not happen if userspace parser was written correctly.
+ */
+ if (f->wss.wc >= OSF_WSS_MAX)
+ continue;
+
+ /* Check options */
+
+ foptsize = 0;
+ for (optnum = 0; optnum < f->opt_num; ++optnum)
+ foptsize += f->opt[optnum].length;
+
+ if (foptsize > MAX_IPOPTLEN ||
+ optsize > MAX_IPOPTLEN ||
+ optsize != foptsize)
+ continue;
+
+ check_WSS = f->wss.wc;
+
+ for (optnum = 0; optnum < f->opt_num; ++optnum) {
+ if (f->opt[optnum].kind == (*optp)) {
+ __u32 len = f->opt[optnum].length;
+ const __u8 *optend = optp + len;
+
+ fmatch = FMATCH_OK;
+
+ switch (*optp) {
+ case OSFOPT_MSS:
+ mss = optp[3];
+ mss <<= 8;
+ mss |= optp[2];
+
+ mss = ntohs((__force __be16)mss);
+ break;
+ case OSFOPT_TS:
+ break;
+ }
+
+ optp = optend;
+ } else
+ fmatch = FMATCH_OPT_WRONG;
+
+ if (fmatch != FMATCH_OK)
+ break;
+ }
+
+ if (fmatch != FMATCH_OPT_WRONG) {
+ fmatch = FMATCH_WRONG;
+
+ switch (check_WSS) {
+ case OSF_WSS_PLAIN:
+ if (f->wss.val == 0 || window == f->wss.val)
+ fmatch = FMATCH_OK;
+ break;
+ case OSF_WSS_MSS:
+ /*
+ * Some smart modems decrease mangle MSS to
+ * SMART_MSS_2, so we check standard, decreased
+ * and the one provided in the fingerprint MSS
+ * values.
+ */
+#define SMART_MSS_1 1460
+#define SMART_MSS_2 1448
+ if (window == f->wss.val * mss ||
+ window == f->wss.val * SMART_MSS_1 ||
+ window == f->wss.val * SMART_MSS_2)
+ fmatch = FMATCH_OK;
+ break;
+ case OSF_WSS_MTU:
+ if (window == f->wss.val * (mss + 40) ||
+ window == f->wss.val * (SMART_MSS_1 + 40) ||
+ window == f->wss.val * (SMART_MSS_2 + 40))
+ fmatch = FMATCH_OK;
+ break;
+ case OSF_WSS_MODULO:
+ if ((window % f->wss.val) == 0)
+ fmatch = FMATCH_OK;
+ break;
+ }
+ }
+
+ if (fmatch != FMATCH_OK)
+ continue;
+
+ fcount++;
+
+ if (info->flags & NF_OSF_LOG)
+ nf_log_packet(net, family, hooknum, skb,
+ in, out, NULL,
+ "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
+ f->genre, f->version, f->subtype,
+ &ip->saddr, ntohs(tcp->source),
+ &ip->daddr, ntohs(tcp->dest),
+ f->ttl - ip->ttl);
+
+ if ((info->flags & NF_OSF_LOG) &&
+ info->loglevel == NF_OSF_LOGLEVEL_FIRST)
+ break;
+ }
+
+ if (!fcount && (info->flags & NF_OSF_LOG))
+ nf_log_packet(net, family, hooknum, skb, in, out, NULL,
+ "Remote OS is not known: %pI4:%u -> %pI4:%u\n",
+ &ip->saddr, ntohs(tcp->source),
+ &ip->daddr, ntohs(tcp->dest));
+
+ if (fcount)
+ fmatch = FMATCH_OK;
+
+ return fmatch == FMATCH_OK;
+}
+EXPORT_SYMBOL_GPL(nf_osf_match);
+
+MODULE_LICENSE("GPL");
return err;
}
+static void nft_rule_expr_activate(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ struct nft_expr *expr;
+
+ expr = nft_expr_first(rule);
+ while (expr != nft_expr_last(rule) && expr->ops) {
+ if (expr->ops->activate)
+ expr->ops->activate(ctx, expr);
+
+ expr = nft_expr_next(expr);
+ }
+}
+
+static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ struct nft_expr *expr;
+
+ expr = nft_expr_first(rule);
+ while (expr != nft_expr_last(rule) && expr->ops) {
+ if (expr->ops->deactivate)
+ expr->ops->deactivate(ctx, expr);
+
+ expr = nft_expr_next(expr);
+ }
+}
+
static int
nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
{
nft_trans_destroy(trans);
return err;
}
+ nft_rule_expr_deactivate(ctx, rule);
return 0;
}
{
struct nft_table *table;
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
list_for_each_entry(table, &net->nft.tables, list) {
if (!nla_strcmp(nla, table->name) &&
table->family == family &&
nft_active_genmask(table, genmask))
return table;
}
- return NULL;
+
+ return ERR_PTR(-ENOENT);
}
static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
nft_active_genmask(table, genmask))
return table;
}
- return NULL;
-}
-
-static struct nft_table *nf_tables_table_lookup(const struct net *net,
- const struct nlattr *nla,
- u8 family, u8 genmask)
-{
- struct nft_table *table;
-
- if (nla == NULL)
- return ERR_PTR(-EINVAL);
-
- table = nft_table_lookup(net, nla, family, genmask);
- if (table != NULL)
- return table;
-
- return ERR_PTR(-ENOENT);
-}
-
-static struct nft_table *nf_tables_table_lookup_byhandle(const struct net *net,
- const struct nlattr *nla,
- u8 genmask)
-{
- struct nft_table *table;
-
- if (nla == NULL)
- return ERR_PTR(-EINVAL);
-
- table = nft_table_lookup_byhandle(net, nla, genmask);
- if (table != NULL)
- return table;
return ERR_PTR(-ENOENT);
}
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]);
return PTR_ERR(table);
+ }
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- const struct nlattr *name;
- struct nft_table *table;
int family = nfmsg->nfgen_family;
+ const struct nlattr *attr;
+ struct nft_table *table;
u32 flags = 0;
struct nft_ctx ctx;
int err;
- name = nla[NFTA_TABLE_NAME];
- table = nf_tables_table_lookup(net, name, family, genmask);
+ attr = nla[NFTA_TABLE_NAME];
+ table = nft_table_lookup(net, attr, family, genmask);
if (IS_ERR(table)) {
if (PTR_ERR(table) != -ENOENT)
return PTR_ERR(table);
} else {
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EEXIST;
+ }
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
if (table == NULL)
goto err_kzalloc;
- table->name = nla_strdup(name, GFP_KERNEL);
+ table->name = nla_strdup(attr, GFP_KERNEL);
if (table->name == NULL)
goto err_strdup;
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
- struct nft_table *table;
int family = nfmsg->nfgen_family;
+ const struct nlattr *attr;
+ struct nft_table *table;
struct nft_ctx ctx;
nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla);
(!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE]))
return nft_flush(&ctx, family);
- if (nla[NFTA_TABLE_HANDLE])
- table = nf_tables_table_lookup_byhandle(net,
- nla[NFTA_TABLE_HANDLE],
- genmask);
- else
- table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME],
- family, genmask);
+ if (nla[NFTA_TABLE_HANDLE]) {
+ attr = nla[NFTA_TABLE_HANDLE];
+ table = nft_table_lookup_byhandle(net, attr, genmask);
+ } else {
+ attr = nla[NFTA_TABLE_NAME];
+ table = nft_table_lookup(net, attr, family, genmask);
+ }
- if (IS_ERR(table))
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, attr);
return PTR_ERR(table);
+ }
if (nlh->nlmsg_flags & NLM_F_NONREC &&
table->use > 0)
*/
static struct nft_chain *
-nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle,
- u8 genmask)
+nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask)
{
struct nft_chain *chain;
return ERR_PTR(-ENOENT);
}
-static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
- const struct nlattr *nla,
- u8 genmask)
+static struct nft_chain *nft_chain_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_chain *chain;
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
return PTR_ERR(table);
+ }
- chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
- if (IS_ERR(chain))
+ chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]);
return PTR_ERR(chain);
+ }
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
nla[NFTA_CHAIN_NAME]) {
struct nft_chain *chain2;
- chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME],
- genmask);
+ chain2 = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
if (!IS_ERR(chain2))
return -EEXIST;
}
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
- const struct nlattr * uninitialized_var(name);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
+ const struct nlattr *attr;
struct nft_table *table;
struct nft_chain *chain;
u8 policy = NF_ACCEPT;
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
return PTR_ERR(table);
+ }
chain = NULL;
- name = nla[NFTA_CHAIN_NAME];
+ attr = nla[NFTA_CHAIN_NAME];
if (nla[NFTA_CHAIN_HANDLE]) {
handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
- chain = nf_tables_chain_lookup_byhandle(table, handle, genmask);
- if (IS_ERR(chain))
+ chain = nft_chain_lookup_byhandle(table, handle, genmask);
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]);
return PTR_ERR(chain);
+ }
+ attr = nla[NFTA_CHAIN_HANDLE];
} else {
- chain = nf_tables_chain_lookup(table, name, genmask);
+ chain = nft_chain_lookup(table, attr, genmask);
if (IS_ERR(chain)) {
- if (PTR_ERR(chain) != -ENOENT)
+ if (PTR_ERR(chain) != -ENOENT) {
+ NL_SET_BAD_ATTR(extack, attr);
return PTR_ERR(chain);
+ }
chain = NULL;
}
}
if (nla[NFTA_CHAIN_POLICY]) {
if (chain != NULL &&
- !nft_is_base_chain(chain))
+ !nft_is_base_chain(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]);
return -EOPNOTSUPP;
+ }
if (chain == NULL &&
- nla[NFTA_CHAIN_HOOK] == NULL)
+ nla[NFTA_CHAIN_HOOK] == NULL) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]);
return -EOPNOTSUPP;
+ }
policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY]));
switch (policy) {
nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
if (chain != NULL) {
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EEXIST;
+ }
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
+ int family = nfmsg->nfgen_family;
+ const struct nlattr *attr;
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule;
- int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
u64 handle;
u32 use;
int err;
- table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
return PTR_ERR(table);
+ }
if (nla[NFTA_CHAIN_HANDLE]) {
- handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
- chain = nf_tables_chain_lookup_byhandle(table, handle, genmask);
+ attr = nla[NFTA_CHAIN_HANDLE];
+ handle = be64_to_cpu(nla_get_be64(attr));
+ chain = nft_chain_lookup_byhandle(table, handle, genmask);
} else {
- chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+ attr = nla[NFTA_CHAIN_NAME];
+ chain = nft_chain_lookup(table, attr, genmask);
}
- if (IS_ERR(chain))
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, attr);
return PTR_ERR(chain);
+ }
if (nlh->nlmsg_flags & NLM_F_NONREC &&
chain->use > 0)
/* There are rules and elements that are still holding references to us,
* we cannot do a recursive removal in this case.
*/
- if (use > 0)
+ if (use > 0) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EBUSY;
+ }
return nft_delchain(&ctx);
}
* Rules
*/
-static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain,
- u64 handle)
+static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain,
+ u64 handle)
{
struct nft_rule *rule;
return ERR_PTR(-ENOENT);
}
-static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
- const struct nlattr *nla)
+static struct nft_rule *nft_rule_lookup(const struct nft_chain *chain,
+ const struct nlattr *nla)
{
if (nla == NULL)
return ERR_PTR(-EINVAL);
- return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla)));
+ return __nft_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla)));
}
static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
return netlink_dump_start(nlsk, skb, nlh, &c);
}
- table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
return PTR_ERR(table);
+ }
- chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
- if (IS_ERR(chain))
+ chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
return PTR_ERR(chain);
+ }
- rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
- if (IS_ERR(rule))
+ rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+ if (IS_ERR(rule)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
return PTR_ERR(rule);
+ }
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
kfree(rule);
}
+static void nf_tables_rule_release(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ nft_rule_expr_deactivate(ctx, rule);
+ nf_tables_rule_destroy(ctx, rule);
+}
+
#define NFT_RULE_MAXEXPRS 128
static struct nft_expr_info *info;
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
return PTR_ERR(table);
+ }
- chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
- if (IS_ERR(chain))
+ chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
return PTR_ERR(chain);
+ }
if (nla[NFTA_RULE_HANDLE]) {
handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE]));
- rule = __nf_tables_rule_lookup(chain, handle);
- if (IS_ERR(rule))
+ rule = __nft_rule_lookup(chain, handle);
+ if (IS_ERR(rule)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
return PTR_ERR(rule);
+ }
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
return -EEXIST;
+ }
if (nlh->nlmsg_flags & NLM_F_REPLACE)
old_rule = rule;
else
return -EOPNOTSUPP;
pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
- old_rule = __nf_tables_rule_lookup(chain, pos_handle);
- if (IS_ERR(old_rule))
+ old_rule = __nft_rule_lookup(chain, pos_handle);
+ if (IS_ERR(old_rule)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
return PTR_ERR(old_rule);
+ }
}
nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- if (nft_is_active_next(net, old_rule)) {
- trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
- old_rule);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err2;
- }
- nft_deactivate_next(net, old_rule);
- chain->use--;
- list_add_tail_rcu(&rule->list, &old_rule->list);
- } else {
+ if (!nft_is_active_next(net, old_rule)) {
err = -ENOENT;
goto err2;
}
- } else if (nlh->nlmsg_flags & NLM_F_APPEND)
- if (old_rule)
- list_add_rcu(&rule->list, &old_rule->list);
- else
- list_add_tail_rcu(&rule->list, &chain->rules);
- else {
- if (old_rule)
- list_add_tail_rcu(&rule->list, &old_rule->list);
- else
- list_add_rcu(&rule->list, &chain->rules);
- }
+ trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+ old_rule);
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+ nft_deactivate_next(net, old_rule);
+ chain->use--;
- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
- err = -ENOMEM;
- goto err3;
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ } else {
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_APPEND) {
+ if (old_rule)
+ list_add_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ } else {
+ if (old_rule)
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+ }
}
chain->use++;
return 0;
-err3:
- list_del_rcu(&rule->list);
err2:
- nf_tables_rule_destroy(&ctx, rule);
+ nf_tables_rule_release(&ctx, rule);
err1:
for (i = 0; i < n; i++) {
if (info[i].ops != NULL)
int family = nfmsg->nfgen_family, err = 0;
struct nft_ctx ctx;
- table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
return PTR_ERR(table);
+ }
if (nla[NFTA_RULE_CHAIN]) {
- chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN],
- genmask);
- if (IS_ERR(chain))
+ chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+ if (IS_ERR(chain)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
return PTR_ERR(chain);
+ }
}
nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
if (chain) {
if (nla[NFTA_RULE_HANDLE]) {
- rule = nf_tables_rule_lookup(chain,
- nla[NFTA_RULE_HANDLE]);
- if (IS_ERR(rule))
+ rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+ if (IS_ERR(rule)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
return PTR_ERR(rule);
+ }
err = nft_delrule(&ctx, rule);
} else if (nla[NFTA_RULE_ID]) {
rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
- if (IS_ERR(rule))
+ if (IS_ERR(rule)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]);
return PTR_ERR(rule);
+ }
err = nft_delrule(&ctx, rule);
} else {
EXPORT_SYMBOL_GPL(nft_unregister_set);
#define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \
- NFT_SET_TIMEOUT | NFT_SET_OBJECT)
+ NFT_SET_TIMEOUT | NFT_SET_OBJECT | \
+ NFT_SET_EVAL)
-static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags)
+static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags)
{
- if ((flags & NFT_SET_EVAL) && !ops->update)
- return false;
-
- return (flags & ops->features) == (flags & NFT_SET_FEATURES);
+ return (flags & type->features) == (flags & NFT_SET_FEATURES);
}
/*
best.space = ~0;
list_for_each_entry(type, &nf_tables_set_types, list) {
- if (!type->select_ops)
- ops = type->ops;
- else
- ops = type->select_ops(ctx, desc, flags);
- if (!ops)
- continue;
+ ops = &type->ops;
- if (!nft_set_ops_candidate(ops, flags))
+ if (!nft_set_ops_candidate(type, flags))
continue;
if (!ops->estimate(desc, flags, &est))
continue;
if (!try_module_get(type->owner))
continue;
if (bops != NULL)
- module_put(bops->type->owner);
+ module_put(to_set_type(bops)->owner);
bops = ops;
best = est;
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
+ struct netlink_ext_ack *extack,
u8 genmask)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_table *table = NULL;
if (nla[NFTA_SET_TABLE] != NULL) {
- table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE],
- family, genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family,
+ genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
return PTR_ERR(table);
+ }
}
nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
return 0;
}
-static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
- const struct nlattr *nla, u8 genmask)
+static struct nft_set *nft_set_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_set *set;
return ERR_PTR(-ENOENT);
}
-static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *table,
- const struct nlattr *nla, u8 genmask)
+static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla,
+ u8 genmask)
{
struct nft_set *set;
- if (nla == NULL)
- return ERR_PTR(-EINVAL);
-
list_for_each_entry(set, &table->sets, list) {
if (be64_to_cpu(nla_get_be64(nla)) == set->handle &&
nft_active_genmask(set, genmask))
return ERR_PTR(-ENOENT);
}
-static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
- const struct nlattr *nla,
- u8 genmask)
+static struct nft_set *nft_set_lookup_byid(const struct net *net,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_trans *trans;
u32 id = ntohl(nla_get_be32(nla));
{
struct nft_set *set;
- set = nf_tables_set_lookup(table, nla_set_name, genmask);
+ set = nft_set_lookup(table, nla_set_name, genmask);
if (IS_ERR(set)) {
if (!nla_set_id)
return set;
- set = nf_tables_set_lookup_byid(net, nla_set_id, genmask);
+ set = nft_set_lookup_byid(net, nla_set_id, genmask);
}
return set;
}
return 0;
}
+static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
+{
+ u64 ms = be64_to_cpu(nla_get_be64(nla));
+ u64 max = (u64)(~((u64)0));
+
+ max = div_u64(max, NSEC_PER_MSEC);
+ if (ms >= max)
+ return -ERANGE;
+
+ ms *= NSEC_PER_MSEC;
+ *result = nsecs_to_jiffies64(ms);
+ return 0;
+}
+
+static u64 nf_jiffies64_to_msecs(u64 input)
+{
+ u64 ms = jiffies64_to_nsecs(input);
+
+ return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC));
+}
+
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
if (set->timeout &&
nla_put_be64(skb, NFTA_SET_TIMEOUT,
- cpu_to_be64(jiffies_to_msecs(set->timeout)),
+ nf_jiffies64_to_msecs(set->timeout),
NFTA_SET_PAD))
goto nla_put_failure;
if (set->gc_int &&
int err;
/* Verify existence before starting dump */
- err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask);
+ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack,
+ genmask);
if (err < 0)
return err;
if (!nla[NFTA_SET_TABLE])
return -EINVAL;
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
+ set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
if (IS_ERR(set))
return PTR_ERR(set);
if (nla[NFTA_SET_TIMEOUT] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
- nla[NFTA_SET_TIMEOUT])));
+
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout);
+ if (err)
+ return err;
}
gc_int = 0;
if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
- table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
return PTR_ERR(table);
+ }
nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
- set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME], genmask);
+ set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask);
if (IS_ERR(set)) {
- if (PTR_ERR(set) != -ENOENT)
+ if (PTR_ERR(set) != -ENOENT) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
return PTR_ERR(set);
+ }
} else {
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
return -EEXIST;
+ }
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
+
return 0;
}
err = ops->init(set, &desc, nla);
if (err < 0)
- goto err2;
+ goto err3;
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err3;
+ goto err4;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err3:
+err4:
ops->destroy(set);
+err3:
+ kfree(set->name);
err2:
kvfree(set);
err1:
- module_put(ops->type->owner);
+ module_put(to_set_type(ops)->owner);
return err;
}
static void nft_set_destroy(struct nft_set *set)
{
set->ops->destroy(set);
- module_put(set->ops->type->owner);
+ module_put(to_set_type(set->ops)->owner);
kfree(set->name);
kvfree(set);
}
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
+ const struct nlattr *attr;
struct nft_set *set;
struct nft_ctx ctx;
int err;
if (nla[NFTA_SET_TABLE] == NULL)
return -EINVAL;
- err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask);
+ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack,
+ genmask);
if (err < 0)
return err;
- if (nla[NFTA_SET_HANDLE])
- set = nf_tables_set_lookup_byhandle(ctx.table, nla[NFTA_SET_HANDLE], genmask);
- else
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
- if (IS_ERR(set))
- return PTR_ERR(set);
+ if (nla[NFTA_SET_HANDLE]) {
+ attr = nla[NFTA_SET_HANDLE];
+ set = nft_set_lookup_byhandle(ctx.table, attr, genmask);
+ } else {
+ attr = nla[NFTA_SET_NAME];
+ set = nft_set_lookup(ctx.table, attr, genmask);
+ }
+ if (IS_ERR(set)) {
+ NL_SET_BAD_ATTR(extack, attr);
+ return PTR_ERR(set);
+ }
if (!list_empty(&set->bindings) ||
- (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0))
+ (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EBUSY;
+ }
return nft_delset(&ctx, set);
}
.align = __alignof__(u64),
},
[NFT_SET_EXT_EXPIRATION] = {
- .len = sizeof(unsigned long),
- .align = __alignof__(unsigned long),
+ .len = sizeof(u64),
+ .align = __alignof__(u64),
},
[NFT_SET_EXT_USERDATA] = {
.len = sizeof(struct nft_userdata),
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
+ struct netlink_ext_ack *extack,
u8 genmask)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
int family = nfmsg->nfgen_family;
struct nft_table *table;
- table = nf_tables_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE],
- family, genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
+ genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
return PTR_ERR(table);
+ }
nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
return 0;
if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
- cpu_to_be64(jiffies_to_msecs(
- *nft_set_ext_timeout(ext))),
+ nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
NFTA_SET_ELEM_PAD))
goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
- unsigned long expires, now = jiffies;
+ u64 expires, now = get_jiffies_64();
expires = *nft_set_ext_expiration(ext);
- if (time_before(now, expires))
+ if (time_before64(now, expires))
expires -= now;
else
expires = 0;
if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
- cpu_to_be64(jiffies_to_msecs(expires)),
+ nf_jiffies64_to_msecs(expires),
NFTA_SET_ELEM_PAD))
goto nla_put_failure;
}
struct nft_ctx ctx;
int rem, err = 0;
- err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+ genmask);
if (err < 0)
return err;
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
- genmask);
+ set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
if (IS_ERR(set))
return PTR_ERR(set);
memcpy(nft_set_ext_data(ext), data, set->dlen);
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION))
*nft_set_ext_expiration(ext) =
- jiffies + timeout;
+ get_jiffies_64() + timeout;
if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT))
*nft_set_ext_timeout(ext) = timeout;
if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) {
if (!(set->flags & NFT_SET_TIMEOUT))
return -EINVAL;
- timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
- nla[NFTA_SET_ELEM_TIMEOUT])));
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_TIMEOUT],
+ &timeout);
+ if (err)
+ return err;
} else if (set->flags & NFT_SET_TIMEOUT) {
timeout = set->timeout;
}
err = -EINVAL;
goto err2;
}
- obj = nf_tables_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF],
- set->objtype, genmask);
+ obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF],
+ set->objtype, genmask);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err2;
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^
nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) ||
nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^
- nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF))
- return -EBUSY;
+ nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) {
+ err = -EBUSY;
+ goto err5;
+ }
if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
memcmp(nft_set_ext_data(ext),
if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
return -EINVAL;
- err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+ genmask);
if (err < 0)
return err;
* NFT_GOTO verdicts. This function must be called on active data objects
* from the second phase of the commit protocol.
*/
-static void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
{
if (type == NFT_DATA_VERDICT) {
switch (data->verdict.code) {
struct nft_ctx ctx;
int rem, err = 0;
- err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+ genmask);
if (err < 0)
return err;
- set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
- genmask);
+ set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask);
if (IS_ERR(set))
return PTR_ERR(set);
if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
}
EXPORT_SYMBOL_GPL(nft_unregister_obj);
-struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
- const struct nlattr *nla,
- u32 objtype, u8 genmask)
+struct nft_object *nft_obj_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u32 objtype,
+ u8 genmask)
{
struct nft_object *obj;
}
return ERR_PTR(-ENOENT);
}
-EXPORT_SYMBOL_GPL(nf_tables_obj_lookup);
+EXPORT_SYMBOL_GPL(nft_obj_lookup);
-static struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table,
- const struct nlattr *nla,
- u32 objtype, u8 genmask)
+static struct nft_object *nft_obj_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla,
+ u32 objtype, u8 genmask)
{
struct nft_object *obj;
!nla[NFTA_OBJ_DATA])
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
return PTR_ERR(table);
+ }
objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
+ obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
- if (err != -ENOENT)
+ if (err != -ENOENT) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
return err;
-
+ }
} else {
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
return -EEXIST;
-
+ }
return 0;
}
!nla[NFTA_OBJ_TYPE])
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
return PTR_ERR(table);
+ }
objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
- if (IS_ERR(obj))
+ obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
+ if (IS_ERR(obj)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
return PTR_ERR(obj);
+ }
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
+ const struct nlattr *attr;
struct nft_table *table;
struct nft_object *obj;
struct nft_ctx ctx;
(!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE]))
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family,
- genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
return PTR_ERR(table);
+ }
objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
- if (nla[NFTA_OBJ_HANDLE])
- obj = nf_tables_obj_lookup_byhandle(table, nla[NFTA_OBJ_HANDLE],
- objtype, genmask);
- else
- obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME],
- objtype, genmask);
- if (IS_ERR(obj))
+ if (nla[NFTA_OBJ_HANDLE]) {
+ attr = nla[NFTA_OBJ_HANDLE];
+ obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask);
+ } else {
+ attr = nla[NFTA_OBJ_NAME];
+ obj = nft_obj_lookup(table, attr, objtype, genmask);
+ }
+
+ if (IS_ERR(obj)) {
+ NL_SET_BAD_ATTR(extack, attr);
return PTR_ERR(obj);
- if (obj->use > 0)
+ }
+ if (obj->use > 0) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EBUSY;
+ }
nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
[NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 },
};
-struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
- const struct nlattr *nla,
- u8 genmask)
+struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_flowtable *flowtable;
}
return ERR_PTR(-ENOENT);
}
-EXPORT_SYMBOL_GPL(nf_tables_flowtable_lookup);
+EXPORT_SYMBOL_GPL(nft_flowtable_lookup);
static struct nft_flowtable *
-nf_tables_flowtable_lookup_byhandle(const struct nft_table *table,
- const struct nlattr *nla, u8 genmask)
+nft_flowtable_lookup_byhandle(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_flowtable *flowtable;
flowtable->ops[i].pf = NFPROTO_NETDEV;
flowtable->ops[i].hooknum = hooknum;
flowtable->ops[i].priority = priority;
- flowtable->ops[i].priv = &flowtable->data.rhashtable;
+ flowtable->ops[i].priv = &flowtable->data;
flowtable->ops[i].hook = flowtable->data.type->hook;
flowtable->ops[i].dev = dev_array[i];
flowtable->dev_name[i] = kstrdup(dev_array[i]->name,
return ERR_PTR(-ENOENT);
}
-void nft_flow_table_iterate(struct net *net,
- void (*iter)(struct nf_flowtable *flowtable, void *data),
- void *data)
-{
- struct nft_flowtable *flowtable;
- const struct nft_table *table;
-
- nfnl_lock(NFNL_SUBSYS_NFTABLES);
- list_for_each_entry(table, &net->nft.tables, list) {
- list_for_each_entry(flowtable, &table->flowtables, list) {
- iter(&flowtable->data, data);
- }
- }
- nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-}
-EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
-
static void nft_unregister_flowtable_net_hooks(struct net *net,
struct nft_flowtable *flowtable)
{
!nla[NFTA_FLOWTABLE_HOOK])
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
- family, genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family,
+ genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]);
return PTR_ERR(table);
+ }
- flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
- genmask);
+ flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
+ genmask);
if (IS_ERR(flowtable)) {
err = PTR_ERR(flowtable);
- if (err != -ENOENT)
+ if (err != -ENOENT) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]);
return err;
+ }
} else {
- if (nlh->nlmsg_flags & NLM_F_EXCL)
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]);
return -EEXIST;
+ }
return 0;
}
}
flowtable->data.type = type;
- err = rhashtable_init(&flowtable->data.rhashtable, type->params);
+ err = type->init(&flowtable->data);
if (err < 0)
goto err3;
err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
flowtable);
if (err < 0)
- goto err3;
+ goto err4;
for (i = 0; i < flowtable->ops_len; i++) {
if (!flowtable->ops[i].dev)
if (flowtable->ops[i].dev == ft->ops[k].dev &&
flowtable->ops[i].pf == ft->ops[k].pf) {
err = -EBUSY;
- goto err4;
+ goto err5;
}
}
}
err = nf_register_net_hook(net, &flowtable->ops[i]);
if (err < 0)
- goto err4;
+ goto err5;
}
err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
if (err < 0)
- goto err5;
-
- INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc);
- queue_delayed_work(system_power_efficient_wq,
- &flowtable->data.gc_work, HZ);
+ goto err6;
list_add_tail_rcu(&flowtable->list, &table->flowtables);
table->use++;
return 0;
-err5:
+err6:
i = flowtable->ops_len;
-err4:
+err5:
for (k = i - 1; k >= 0; k--) {
kfree(flowtable->dev_name[k]);
nf_unregister_net_hook(net, &flowtable->ops[k]);
}
kfree(flowtable->ops);
+err4:
+ flowtable->data.type->free(&flowtable->data);
err3:
module_put(type->owner);
err2:
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
struct nft_flowtable *flowtable;
+ const struct nlattr *attr;
struct nft_table *table;
struct nft_ctx ctx;
!nla[NFTA_FLOWTABLE_HANDLE]))
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
- family, genmask);
- if (IS_ERR(table))
+ table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family,
+ genmask);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]);
return PTR_ERR(table);
+ }
- if (nla[NFTA_FLOWTABLE_HANDLE])
- flowtable = nf_tables_flowtable_lookup_byhandle(table,
- nla[NFTA_FLOWTABLE_HANDLE],
- genmask);
- else
- flowtable = nf_tables_flowtable_lookup(table,
- nla[NFTA_FLOWTABLE_NAME],
- genmask);
- if (IS_ERR(flowtable))
- return PTR_ERR(flowtable);
- if (flowtable->use > 0)
+ if (nla[NFTA_FLOWTABLE_HANDLE]) {
+ attr = nla[NFTA_FLOWTABLE_HANDLE];
+ flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask);
+ } else {
+ attr = nla[NFTA_FLOWTABLE_NAME];
+ flowtable = nft_flowtable_lookup(table, attr, genmask);
+ }
+
+ if (IS_ERR(flowtable)) {
+ NL_SET_BAD_ATTR(extack, attr);
+ return PTR_ERR(flowtable);
+ }
+ if (flowtable->use > 0) {
+ NL_SET_BAD_ATTR(extack, attr);
return -EBUSY;
+ }
nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
if (!nla[NFTA_FLOWTABLE_NAME])
return -EINVAL;
- table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE],
- family, genmask);
+ table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family,
+ genmask);
if (IS_ERR(table))
return PTR_ERR(table);
- flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
- genmask);
+ flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME],
+ genmask);
if (IS_ERR(flowtable))
return PTR_ERR(flowtable);
static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
{
- cancel_delayed_work_sync(&flowtable->data.gc_work);
kfree(flowtable->ops);
kfree(flowtable->name);
flowtable->data.type->free(&flowtable->data);
- rhashtable_destroy(&flowtable->data.rhashtable);
module_put(flowtable->data.type->owner);
}
struct nft_base_chain *basechain;
if (nft_trans_chain_name(trans))
- strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+ swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
if (!nft_is_base_chain(trans->ctx.chain))
return;
}
}
-static void nf_tables_commit_release(struct nft_trans *trans)
+static void nft_commit_release(struct nft_trans *trans)
{
switch (trans->msg_type) {
case NFT_MSG_DELTABLE:
kfree(trans);
}
+static void nf_tables_commit_release(struct net *net)
+{
+ struct nft_trans *trans, *next;
+
+ if (list_empty(&net->nft.commit_list))
+ return;
+
+ synchronize_rcu();
+
+ list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_del(&trans->list);
+ nft_commit_release(trans);
+ }
+}
+
static int nf_tables_commit(struct net *net, struct sk_buff *skb)
{
struct nft_trans *trans, *next;
}
}
- synchronize_rcu();
-
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
- list_del(&trans->list);
- nf_tables_commit_release(trans);
- }
-
+ nf_tables_commit_release(net);
nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
return 0;
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
+ nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
nft_clear(trans->ctx.net, nft_trans_rule(trans));
+ nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans));
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
case NFT_GOTO:
if (!tb[NFTA_VERDICT_CHAIN])
return -EINVAL;
- chain = nf_tables_chain_lookup(ctx->table,
- tb[NFTA_VERDICT_CHAIN], genmask);
+ chain = nft_chain_lookup(ctx->table, tb[NFTA_VERDICT_CHAIN],
+ genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
if (nft_is_base_chain(chain))
list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
list_del(&rule->list);
ctx->chain->use--;
- nf_tables_rule_destroy(ctx, rule);
+ nf_tables_rule_release(ctx, rule);
}
list_del(&ctx->chain->list);
ctx->table->use--;
list_for_each_entry_safe(rule, nr, &chain->rules, list) {
list_del(&rule->list);
chain->use--;
- nf_tables_rule_destroy(&ctx, rule);
+ nf_tables_rule_release(&ctx, rule);
}
}
list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
static noinline void nft_update_chain_stats(const struct nft_chain *chain,
const struct nft_pktinfo *pkt)
{
+ struct nft_base_chain *base_chain;
struct nft_stats *stats;
- local_bh_disable();
- stats = this_cpu_ptr(rcu_dereference(nft_base_chain(chain)->stats));
- u64_stats_update_begin(&stats->syncp);
- stats->pkts++;
- stats->bytes += pkt->skb->len;
- u64_stats_update_end(&stats->syncp);
- local_bh_enable();
+ base_chain = nft_base_chain(chain);
+ if (!base_chain->stats)
+ return;
+
+ stats = this_cpu_ptr(rcu_dereference(base_chain->stats));
+ if (stats) {
+ local_bh_disable();
+ u64_stats_update_begin(&stats->syncp);
+ stats->pkts++;
+ stats->bytes += pkt->skb->len;
+ u64_stats_update_end(&stats->syncp);
+ local_bh_enable();
+ }
}
struct nft_jumpstack {
&nft_payload_type,
&nft_dynset_type,
&nft_range_type,
+ &nft_meta_type,
+ &nft_rt_type,
+ &nft_exthdr_type,
};
int __init nf_tables_core_module_init(void)
nfacct->flags = flags;
}
- strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
+ nla_strlcpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
if (tb[NFACCT_BYTES]) {
atomic64_set(&nfacct->bytes,
!tb[NFCTH_POLICY_EXPECT_TIMEOUT])
return -EINVAL;
- strncpy(expect_policy->name,
- nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
+ nla_strlcpy(expect_policy->name,
+ nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
expect_policy->max_expected =
ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
if (ret < 0)
goto err1;
- strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
+ nla_strlcpy(helper->name,
+ nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
if (size > FIELD_SIZEOF(struct nf_conn_help, data)) {
ret = -ENOMEM;
#include <net/sock.h>
#include <net/netfilter/nf_log.h>
#include <net/netns/generic.h>
-#include <net/netfilter/nfnetlink_log.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
#include "../bridge/br_private.h"
#endif
+#define NFULNL_COPY_DISABLED 0xff
#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 100 /* every second */
#define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */
};
/* log handler for internal netfilter logging api */
-void
+static void
nfulnl_log_packet(struct net *net,
u_int8_t pf,
unsigned int hooknum,
struct nfulnl_instance *inst;
const struct nf_loginfo *li;
unsigned int qthreshold;
- unsigned int plen;
+ unsigned int plen = 0;
struct nfnl_log_net *log = nfnl_log_pernet(net);
const struct nfnl_ct_hook *nfnl_ct = NULL;
struct nf_conn *ct = NULL;
if (!inst)
return;
- plen = 0;
if (prefix)
plen = strlen(prefix) + 1;
/* FIXME: statistics */
goto unlock_and_release;
}
-EXPORT_SYMBOL_GPL(nfulnl_log_packet);
static int
nfulnl_rcv_nl_event(struct notifier_block *this,
struct list_head head;
struct nft_expr_ops ops;
unsigned int refcnt;
+
+ /* Unlike other expressions, ops doesn't have static storage duration.
+ * nft core assumes they do. We use kfree_rcu so that nft core can
+ * can check expr->ops->size even after nft_compat->destroy() frees
+ * the nft_xt struct that holds the ops structure.
+ */
+ struct rcu_head rcu_head;
+};
+
+/* Used for matches where *info is larger than X byte */
+#define NFT_MATCH_LARGE_THRESH 192
+
+struct nft_xt_match_priv {
+ void *info;
};
-static void nft_xt_put(struct nft_xt *xt)
+static bool nft_xt_put(struct nft_xt *xt)
{
if (--xt->refcnt == 0) {
list_del(&xt->head);
- kfree(xt);
+ kfree_rcu(xt, rcu_head);
+ return true;
}
+
+ return false;
}
static int nft_compat_chain_validate_dependency(const char *tablename,
struct xt_target *target = expr->ops->data;
struct xt_tgchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
+ struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
if (ctx->nla[NFTA_RULE_COMPAT]) {
ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
if (ret < 0)
- goto err;
+ return ret;
}
nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
ret = xt_check_target(&par, size, proto, inv);
if (ret < 0)
- goto err;
+ return ret;
/* The standard target cannot be used */
- if (target->target == NULL) {
- ret = -EINVAL;
- goto err;
- }
+ if (!target->target)
+ return -EINVAL;
+ nft_xt = container_of(expr->ops, struct nft_xt, ops);
+ nft_xt->refcnt++;
return 0;
-err:
- module_put(target->me);
- return ret;
}
static void
if (par.target->destroy != NULL)
par.target->destroy(&par);
- nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
- module_put(target->me);
+ if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+ module_put(target->me);
}
static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
return 0;
}
-static void nft_match_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+static void __nft_match_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt,
+ void *info)
{
- void *info = nft_expr_priv(expr);
struct xt_match *match = expr->ops->data;
struct sk_buff *skb = pkt->skb;
bool ret;
}
}
+static void nft_match_large_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+ __nft_match_eval(expr, regs, pkt, priv->info);
+}
+
+static void nft_match_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ __nft_match_eval(expr, regs, pkt, nft_expr_priv(expr));
+}
+
static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
[NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING },
[NFTA_MATCH_REV] = { .type = NLA_U32 },
}
static int
-nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
- const struct nlattr * const tb[])
+__nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[],
+ void *info)
{
- void *info = nft_expr_priv(expr);
struct xt_match *match = expr->ops->data;
struct xt_mtchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
+ struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
if (ctx->nla[NFTA_RULE_COMPAT]) {
ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
if (ret < 0)
- goto err;
+ return ret;
}
nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
ret = xt_check_match(&par, size, proto, inv);
if (ret < 0)
- goto err;
+ return ret;
+ nft_xt = container_of(expr->ops, struct nft_xt, ops);
+ nft_xt->refcnt++;
return 0;
-err:
- module_put(match->me);
+}
+
+static int
+nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ return __nft_match_init(ctx, expr, tb, nft_expr_priv(expr));
+}
+
+static int
+nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+ struct xt_match *m = expr->ops->data;
+ int ret;
+
+ priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
+ if (!priv->info)
+ return -ENOMEM;
+
+ ret = __nft_match_init(ctx, expr, tb, priv->info);
+ if (ret)
+ kfree(priv->info);
return ret;
}
static void
-nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+__nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ void *info)
{
struct xt_match *match = expr->ops->data;
- void *info = nft_expr_priv(expr);
struct xt_mtdtor_param par;
par.net = ctx->net;
if (par.match->destroy != NULL)
par.match->destroy(&par);
- nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
- module_put(match->me);
+ if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+ module_put(match->me);
}
-static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static void
+nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ __nft_match_destroy(ctx, expr, nft_expr_priv(expr));
+}
+
+static void
+nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+ __nft_match_destroy(ctx, expr, priv->info);
+ kfree(priv->info);
+}
+
+static int __nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr,
+ void *info)
{
- void *info = nft_expr_priv(expr);
struct xt_match *match = expr->ops->data;
if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) ||
return -1;
}
+static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ return __nft_match_dump(skb, expr, nft_expr_priv(expr));
+}
+
+static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(e);
+
+ return __nft_match_dump(skb, e, priv->info);
+}
+
static int nft_match_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
{
struct nft_xt *nft_match;
struct xt_match *match;
+ unsigned int matchsize;
char *mt_name;
u32 rev, family;
int err;
list_for_each_entry(nft_match, &nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
- if (nft_match_cmp(match, mt_name, rev, family)) {
- if (!try_module_get(match->me))
- return ERR_PTR(-ENOENT);
-
- nft_match->refcnt++;
+ if (nft_match_cmp(match, mt_name, rev, family))
return &nft_match->ops;
- }
}
match = xt_request_find_match(family, mt_name, rev);
goto err;
}
- nft_match->refcnt = 1;
+ nft_match->refcnt = 0;
nft_match->ops.type = &nft_match_type;
- nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
nft_match->ops.validate = nft_match_validate;
nft_match->ops.data = match;
+ matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
+ if (matchsize > NFT_MATCH_LARGE_THRESH) {
+ matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv));
+
+ nft_match->ops.eval = nft_match_large_eval;
+ nft_match->ops.init = nft_match_large_init;
+ nft_match->ops.destroy = nft_match_large_destroy;
+ nft_match->ops.dump = nft_match_large_dump;
+ }
+
+ nft_match->ops.size = matchsize;
+
list_add(&nft_match->head, &nft_match_list);
return &nft_match->ops;
list_for_each_entry(nft_target, &nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
- if (nft_target_cmp(target, tg_name, rev, family)) {
- if (!try_module_get(target->me))
- return ERR_PTR(-ENOENT);
-
- nft_target->refcnt++;
+ if (nft_target_cmp(target, tg_name, rev, family))
return &nft_target->ops;
- }
}
target = xt_request_find_target(family, tg_name, rev);
goto err;
}
- nft_target->refcnt = 1;
+ nft_target->refcnt = 0;
nft_target->ops.type = &nft_target_type;
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
static void __exit nft_compat_module_exit(void)
{
+ struct nft_xt *xt, *next;
+
+ /* list should be empty here, it can be non-empty only in case there
+ * was an error that caused nft_xt expr to not be initialized fully
+ * and noone else requested the same expression later.
+ *
+ * In this case, the lists contain 0-refcount entries that still
+ * hold module reference.
+ */
+ list_for_each_entry_safe(xt, next, &nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ if (WARN_ON_ONCE(xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ if (WARN_ON_ONCE(xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
u64 timeout;
void *elem;
- if (set->size && !atomic_add_unless(&set->nelems, 1, set->size))
+ if (!atomic_add_unless(&set->nelems, 1, set->size))
return NULL;
timeout = priv->timeout ? : set->timeout;
if (priv->op == NFT_DYNSET_OP_UPDATE &&
nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
timeout = priv->timeout ? : set->timeout;
- *nft_set_ext_expiration(ext) = jiffies + timeout;
+ *nft_set_ext_expiration(ext) = get_jiffies_64() + timeout;
}
if (sexpr != NULL)
if (err < 0)
goto err1;
+ if (set->size == 0)
+ set->size = 0xffff;
+
priv->set = set;
return 0;
#include <asm/unaligned.h>
#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/tcp.h>
return nft_exthdr_dump_common(skb, priv);
}
-static struct nft_expr_type nft_exthdr_type;
static const struct nft_expr_ops nft_exthdr_ipv6_ops = {
.type = &nft_exthdr_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
return ERR_PTR(-EOPNOTSUPP);
}
-static struct nft_expr_type nft_exthdr_type __read_mostly = {
+struct nft_expr_type nft_exthdr_type __read_mostly = {
.name = "exthdr",
.select_ops = nft_exthdr_select_ops,
.policy = nft_exthdr_policy,
.maxattr = NFTA_EXTHDR_MAX,
.owner = THIS_MODULE,
};
-
-static int __init nft_exthdr_module_init(void)
-{
- return nft_register_expr(&nft_exthdr_type);
-}
-
-static void __exit nft_exthdr_module_exit(void)
-{
- nft_unregister_expr(&nft_exthdr_type);
-}
-
-module_init(nft_exthdr_module_init);
-module_exit(nft_exthdr_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("exthdr");
if (!tb[NFTA_FLOW_TABLE_NAME])
return -EINVAL;
- flowtable = nf_tables_flowtable_lookup(ctx->table,
- tb[NFTA_FLOW_TABLE_NAME],
- genmask);
+ flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME],
+ genmask);
if (IS_ERR(flowtable))
return PTR_ERR(flowtable);
priv->len = len;
priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
- if (priv->modulus <= 1)
+ if (priv->modulus < 1)
return -ERANGE;
if (priv->offset + priv->modulus - 1 < priv->offset)
return err;
}
-static void nft_immediate_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+static void nft_immediate_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+ return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg));
+}
+
+static void nft_immediate_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
.size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
.eval = nft_immediate_eval,
.init = nft_immediate_init,
- .destroy = nft_immediate_destroy,
+ .activate = nft_immediate_activate,
+ .deactivate = nft_immediate_deactivate,
.dump = nft_immediate_dump,
.validate = nft_immediate_validate,
};
/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2014 Intel Corporation
+ * Author: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
*/
#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/tcp_states.h> /* for TCP_TIME_WAIT */
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
-#include <net/netfilter/nft_meta.h>
#include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */
+struct nft_meta {
+ enum nft_meta_keys key:8;
+ union {
+ enum nft_registers dreg:8;
+ enum nft_registers sreg:8;
+ };
+};
+
static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state);
-void nft_meta_get_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+#ifdef CONFIG_NF_TABLES_BRIDGE
+#include "../bridge/br_private.h"
+#endif
+
+static void nft_meta_get_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
{
const struct nft_meta *priv = nft_expr_priv(expr);
const struct sk_buff *skb = pkt->skb;
const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
struct sock *sk;
u32 *dest = ®s->data[priv->dreg];
+#ifdef CONFIG_NF_TABLES_BRIDGE
+ const struct net_bridge_port *p;
+#endif
switch (priv->key) {
case NFT_META_LEN:
case NFT_META_SECPATH:
nft_reg_store8(dest, !!skb->sp);
break;
+#endif
+#ifdef CONFIG_NF_TABLES_BRIDGE
+ case NFT_META_BRI_IIFNAME:
+ if (in == NULL || (p = br_port_get_rcu(in)) == NULL)
+ goto err;
+ strncpy((char *)dest, p->br->dev->name, IFNAMSIZ);
+ return;
+ case NFT_META_BRI_OIFNAME:
+ if (out == NULL || (p = br_port_get_rcu(out)) == NULL)
+ goto err;
+ strncpy((char *)dest, p->br->dev->name, IFNAMSIZ);
+ return;
#endif
default:
WARN_ON(1);
err:
regs->verdict.code = NFT_BREAK;
}
-EXPORT_SYMBOL_GPL(nft_meta_get_eval);
-void nft_meta_set_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+static void nft_meta_set_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
{
const struct nft_meta *meta = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
WARN_ON(1);
}
}
-EXPORT_SYMBOL_GPL(nft_meta_set_eval);
-const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
[NFTA_META_DREG] = { .type = NLA_U32 },
[NFTA_META_KEY] = { .type = NLA_U32 },
[NFTA_META_SREG] = { .type = NLA_U32 },
};
-EXPORT_SYMBOL_GPL(nft_meta_policy);
-int nft_meta_get_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_meta_get_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
{
struct nft_meta *priv = nft_expr_priv(expr);
unsigned int len;
case NFT_META_SECPATH:
len = sizeof(u8);
break;
+#endif
+#ifdef CONFIG_NF_TABLES_BRIDGE
+ case NFT_META_BRI_IIFNAME:
+ case NFT_META_BRI_OIFNAME:
+ if (ctx->family != NFPROTO_BRIDGE)
+ return -EOPNOTSUPP;
+ len = IFNAMSIZ;
+ break;
#endif
default:
return -EOPNOTSUPP;
return nft_validate_register_store(ctx, priv->dreg, NULL,
NFT_DATA_VALUE, len);
}
-EXPORT_SYMBOL_GPL(nft_meta_get_init);
static int nft_meta_get_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
#endif
}
-int nft_meta_set_validate(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nft_data **data)
+static int nft_meta_set_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
{
struct nft_meta *priv = nft_expr_priv(expr);
unsigned int hooks;
return nft_chain_validate_hooks(ctx->chain, hooks);
}
-EXPORT_SYMBOL_GPL(nft_meta_set_validate);
-int nft_meta_set_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_meta_set_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
{
struct nft_meta *priv = nft_expr_priv(expr);
unsigned int len;
return 0;
}
-EXPORT_SYMBOL_GPL(nft_meta_set_init);
-int nft_meta_get_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
+static int nft_meta_get_dump(struct sk_buff *skb,
+ const struct nft_expr *expr)
{
const struct nft_meta *priv = nft_expr_priv(expr);
nla_put_failure:
return -1;
}
-EXPORT_SYMBOL_GPL(nft_meta_get_dump);
-int nft_meta_set_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
+static int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
const struct nft_meta *priv = nft_expr_priv(expr);
nla_put_failure:
return -1;
}
-EXPORT_SYMBOL_GPL(nft_meta_set_dump);
-void nft_meta_set_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+static void nft_meta_set_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
const struct nft_meta *priv = nft_expr_priv(expr);
if (priv->key == NFT_META_NFTRACE)
static_branch_dec(&nft_trace_enabled);
}
-EXPORT_SYMBOL_GPL(nft_meta_set_destroy);
-static struct nft_expr_type nft_meta_type;
static const struct nft_expr_ops nft_meta_get_ops = {
.type = &nft_meta_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_meta)),
return ERR_PTR(-EINVAL);
}
-static struct nft_expr_type nft_meta_type __read_mostly = {
+struct nft_expr_type nft_meta_type __read_mostly = {
.name = "meta",
.select_ops = nft_meta_select_ops,
.policy = nft_meta_policy,
.maxattr = NFTA_META_MAX,
.owner = THIS_MODULE,
};
-
-static int __init nft_meta_module_init(void)
-{
- return nft_register_expr(&nft_meta_type);
-}
-
-static void __exit nft_meta_module_exit(void)
-{
- nft_unregister_expr(&nft_meta_type);
-}
-
-module_init(nft_meta_module_init);
-module_exit(nft_meta_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("meta");
const struct nft_nat *priv = nft_expr_priv(expr);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
memset(&range, 0, sizeof(range));
if (priv->sreg_addr_min) {
u32 modulus;
atomic_t counter;
u32 offset;
+ struct nft_set *map;
};
-static void nft_ng_inc_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+static u32 nft_ng_inc_gen(struct nft_ng_inc *priv)
{
- struct nft_ng_inc *priv = nft_expr_priv(expr);
u32 nval, oval;
do {
nval = (oval + 1 < priv->modulus) ? oval + 1 : 0;
} while (atomic_cmpxchg(&priv->counter, oval, nval) != oval);
- regs->data[priv->dreg] = nval + priv->offset;
+ return nval + priv->offset;
+}
+
+static void nft_ng_inc_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_ng_inc *priv = nft_expr_priv(expr);
+
+ regs->data[priv->dreg] = nft_ng_inc_gen(priv);
+}
+
+static void nft_ng_inc_map_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_ng_inc *priv = nft_expr_priv(expr);
+ const struct nft_set *map = priv->map;
+ const struct nft_set_ext *ext;
+ u32 result;
+ bool found;
+
+ result = nft_ng_inc_gen(priv);
+ found = map->ops->lookup(nft_net(pkt), map, &result, &ext);
+
+ if (!found)
+ return;
+
+ nft_data_copy(®s->data[priv->dreg],
+ nft_set_ext_data(ext), map->dlen);
}
static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = {
[NFTA_NG_MODULUS] = { .type = NLA_U32 },
[NFTA_NG_TYPE] = { .type = NLA_U32 },
[NFTA_NG_OFFSET] = { .type = NLA_U32 },
+ [NFTA_NG_SET_NAME] = { .type = NLA_STRING,
+ .len = NFT_SET_MAXNAMELEN - 1 },
+ [NFTA_NG_SET_ID] = { .type = NLA_U32 },
};
static int nft_ng_inc_init(const struct nft_ctx *ctx,
NFT_DATA_VALUE, sizeof(u32));
}
+static int nft_ng_inc_map_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_ng_inc *priv = nft_expr_priv(expr);
+ u8 genmask = nft_genmask_next(ctx->net);
+
+ nft_ng_inc_init(ctx, expr, tb);
+
+ priv->map = nft_set_lookup_global(ctx->net, ctx->table,
+ tb[NFTA_NG_SET_NAME],
+ tb[NFTA_NG_SET_ID], genmask);
+
+ if (IS_ERR(priv->map))
+ return PTR_ERR(priv->map);
+
+ return 0;
+}
+
static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg,
u32 modulus, enum nft_ng_types type, u32 offset)
{
priv->offset);
}
+static int nft_ng_inc_map_dump(struct sk_buff *skb,
+ const struct nft_expr *expr)
+{
+ const struct nft_ng_inc *priv = nft_expr_priv(expr);
+
+ if (nft_ng_dump(skb, priv->dreg, priv->modulus,
+ NFT_NG_INCREMENTAL, priv->offset) ||
+ nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
struct nft_ng_random {
enum nft_registers dreg:8;
u32 modulus;
.dump = nft_ng_inc_dump,
};
+static const struct nft_expr_ops nft_ng_inc_map_ops = {
+ .type = &nft_ng_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)),
+ .eval = nft_ng_inc_map_eval,
+ .init = nft_ng_inc_map_init,
+ .dump = nft_ng_inc_map_dump,
+};
+
static const struct nft_expr_ops nft_ng_random_ops = {
.type = &nft_ng_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)),
switch (type) {
case NFT_NG_INCREMENTAL:
+ if (tb[NFTA_NG_SET_NAME])
+ return &nft_ng_inc_map_ops;
return &nft_ng_inc_ops;
case NFT_NG_RANDOM:
return &nft_ng_random_ops;
return -EINVAL;
objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE]));
- obj = nf_tables_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype,
- genmask);
+ obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype,
+ genmask);
if (IS_ERR(obj))
return -ENOENT;
*/
#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
return nft_chain_validate_hooks(ctx->chain, hooks);
}
-static struct nft_expr_type nft_rt_type;
static const struct nft_expr_ops nft_rt_get_ops = {
.type = &nft_rt_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_rt)),
.validate = nft_rt_validate,
};
-static struct nft_expr_type nft_rt_type __read_mostly = {
+struct nft_expr_type nft_rt_type __read_mostly = {
.name = "rt",
.ops = &nft_rt_get_ops,
.policy = nft_rt_policy,
.maxattr = NFTA_RT_MAX,
.owner = THIS_MODULE,
};
-
-static int __init nft_rt_module_init(void)
-{
- return nft_register_expr(&nft_rt_type);
-}
-
-static void __exit nft_rt_module_exit(void)
-{
- nft_unregister_expr(&nft_rt_type);
-}
-
-module_init(nft_rt_module_init);
-module_exit(nft_rt_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Anders K. Pedersen <akp@cohaesio.com>");
-MODULE_ALIAS_NFT_EXPR("rt");
return true;
}
-static struct nft_set_type nft_bitmap_type;
-static struct nft_set_ops nft_bitmap_ops __read_mostly = {
- .type = &nft_bitmap_type,
- .privsize = nft_bitmap_privsize,
- .elemsize = offsetof(struct nft_bitmap_elem, ext),
- .estimate = nft_bitmap_estimate,
- .init = nft_bitmap_init,
- .destroy = nft_bitmap_destroy,
- .insert = nft_bitmap_insert,
- .remove = nft_bitmap_remove,
- .deactivate = nft_bitmap_deactivate,
- .flush = nft_bitmap_flush,
- .activate = nft_bitmap_activate,
- .lookup = nft_bitmap_lookup,
- .walk = nft_bitmap_walk,
- .get = nft_bitmap_get,
-};
-
static struct nft_set_type nft_bitmap_type __read_mostly = {
- .ops = &nft_bitmap_ops,
.owner = THIS_MODULE,
+ .ops = {
+ .privsize = nft_bitmap_privsize,
+ .elemsize = offsetof(struct nft_bitmap_elem, ext),
+ .estimate = nft_bitmap_estimate,
+ .init = nft_bitmap_init,
+ .destroy = nft_bitmap_destroy,
+ .insert = nft_bitmap_insert,
+ .remove = nft_bitmap_remove,
+ .deactivate = nft_bitmap_deactivate,
+ .flush = nft_bitmap_flush,
+ .activate = nft_bitmap_activate,
+ .lookup = nft_bitmap_lookup,
+ .walk = nft_bitmap_walk,
+ .get = nft_bitmap_get,
+ },
};
static int __init nft_bitmap_module_init(void)
static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
struct nft_set_estimate *est)
{
+ if (!desc->size)
+ return false;
+
+ if (desc->klen == 4)
+ return false;
+
est->size = sizeof(struct nft_hash) +
nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
desc->size * sizeof(struct nft_hash_elem);
return true;
}
-static struct nft_set_type nft_hash_type;
-static struct nft_set_ops nft_rhash_ops __read_mostly = {
- .type = &nft_hash_type,
- .privsize = nft_rhash_privsize,
- .elemsize = offsetof(struct nft_rhash_elem, ext),
- .estimate = nft_rhash_estimate,
- .init = nft_rhash_init,
- .destroy = nft_rhash_destroy,
- .insert = nft_rhash_insert,
- .activate = nft_rhash_activate,
- .deactivate = nft_rhash_deactivate,
- .flush = nft_rhash_flush,
- .remove = nft_rhash_remove,
- .lookup = nft_rhash_lookup,
- .update = nft_rhash_update,
- .walk = nft_rhash_walk,
- .get = nft_rhash_get,
- .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
-};
+static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features,
+ struct nft_set_estimate *est)
+{
+ if (!desc->size)
+ return false;
-static struct nft_set_ops nft_hash_ops __read_mostly = {
- .type = &nft_hash_type,
- .privsize = nft_hash_privsize,
- .elemsize = offsetof(struct nft_hash_elem, ext),
- .estimate = nft_hash_estimate,
- .init = nft_hash_init,
- .destroy = nft_hash_destroy,
- .insert = nft_hash_insert,
- .activate = nft_hash_activate,
- .deactivate = nft_hash_deactivate,
- .flush = nft_hash_flush,
- .remove = nft_hash_remove,
- .lookup = nft_hash_lookup,
- .walk = nft_hash_walk,
- .get = nft_hash_get,
- .features = NFT_SET_MAP | NFT_SET_OBJECT,
-};
+ if (desc->klen != 4)
+ return false;
-static struct nft_set_ops nft_hash_fast_ops __read_mostly = {
- .type = &nft_hash_type,
- .privsize = nft_hash_privsize,
- .elemsize = offsetof(struct nft_hash_elem, ext),
- .estimate = nft_hash_estimate,
- .init = nft_hash_init,
- .destroy = nft_hash_destroy,
- .insert = nft_hash_insert,
- .activate = nft_hash_activate,
- .deactivate = nft_hash_deactivate,
- .flush = nft_hash_flush,
- .remove = nft_hash_remove,
- .lookup = nft_hash_lookup_fast,
- .walk = nft_hash_walk,
- .get = nft_hash_get,
- .features = NFT_SET_MAP | NFT_SET_OBJECT,
-};
-
-static const struct nft_set_ops *
-nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc,
- u32 flags)
-{
- if (desc->size && !(flags & (NFT_SET_EVAL | NFT_SET_TIMEOUT))) {
- switch (desc->klen) {
- case 4:
- return &nft_hash_fast_ops;
- default:
- return &nft_hash_ops;
- }
- }
+ est->size = sizeof(struct nft_hash) +
+ nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
+ desc->size * sizeof(struct nft_hash_elem);
+ est->lookup = NFT_SET_CLASS_O_1;
+ est->space = NFT_SET_CLASS_O_N;
- return &nft_rhash_ops;
+ return true;
}
+static struct nft_set_type nft_rhash_type __read_mostly = {
+ .owner = THIS_MODULE,
+ .features = NFT_SET_MAP | NFT_SET_OBJECT |
+ NFT_SET_TIMEOUT | NFT_SET_EVAL,
+ .ops = {
+ .privsize = nft_rhash_privsize,
+ .elemsize = offsetof(struct nft_rhash_elem, ext),
+ .estimate = nft_rhash_estimate,
+ .init = nft_rhash_init,
+ .destroy = nft_rhash_destroy,
+ .insert = nft_rhash_insert,
+ .activate = nft_rhash_activate,
+ .deactivate = nft_rhash_deactivate,
+ .flush = nft_rhash_flush,
+ .remove = nft_rhash_remove,
+ .lookup = nft_rhash_lookup,
+ .update = nft_rhash_update,
+ .walk = nft_rhash_walk,
+ .get = nft_rhash_get,
+ },
+};
+
static struct nft_set_type nft_hash_type __read_mostly = {
- .select_ops = nft_hash_select_ops,
.owner = THIS_MODULE,
+ .features = NFT_SET_MAP | NFT_SET_OBJECT,
+ .ops = {
+ .privsize = nft_hash_privsize,
+ .elemsize = offsetof(struct nft_hash_elem, ext),
+ .estimate = nft_hash_estimate,
+ .init = nft_hash_init,
+ .destroy = nft_hash_destroy,
+ .insert = nft_hash_insert,
+ .activate = nft_hash_activate,
+ .deactivate = nft_hash_deactivate,
+ .flush = nft_hash_flush,
+ .remove = nft_hash_remove,
+ .lookup = nft_hash_lookup,
+ .walk = nft_hash_walk,
+ .get = nft_hash_get,
+ },
+};
+
+static struct nft_set_type nft_hash_fast_type __read_mostly = {
+ .owner = THIS_MODULE,
+ .features = NFT_SET_MAP | NFT_SET_OBJECT,
+ .ops = {
+ .privsize = nft_hash_privsize,
+ .elemsize = offsetof(struct nft_hash_elem, ext),
+ .estimate = nft_hash_fast_estimate,
+ .init = nft_hash_init,
+ .destroy = nft_hash_destroy,
+ .insert = nft_hash_insert,
+ .activate = nft_hash_activate,
+ .deactivate = nft_hash_deactivate,
+ .flush = nft_hash_flush,
+ .remove = nft_hash_remove,
+ .lookup = nft_hash_lookup_fast,
+ .walk = nft_hash_walk,
+ .get = nft_hash_get,
+ },
};
static int __init nft_hash_module_init(void)
{
- return nft_register_set(&nft_hash_type);
+ if (nft_register_set(&nft_hash_fast_type) ||
+ nft_register_set(&nft_hash_type) ||
+ nft_register_set(&nft_rhash_type))
+ return 1;
+ return 0;
}
static void __exit nft_hash_module_exit(void)
{
+ nft_unregister_set(&nft_rhash_type);
nft_unregister_set(&nft_hash_type);
+ nft_unregister_set(&nft_hash_fast_type);
}
module_init(nft_hash_module_init);
return true;
}
-static struct nft_set_type nft_rbtree_type;
-static struct nft_set_ops nft_rbtree_ops __read_mostly = {
- .type = &nft_rbtree_type,
- .privsize = nft_rbtree_privsize,
- .elemsize = offsetof(struct nft_rbtree_elem, ext),
- .estimate = nft_rbtree_estimate,
- .init = nft_rbtree_init,
- .destroy = nft_rbtree_destroy,
- .insert = nft_rbtree_insert,
- .remove = nft_rbtree_remove,
- .deactivate = nft_rbtree_deactivate,
- .flush = nft_rbtree_flush,
- .activate = nft_rbtree_activate,
- .lookup = nft_rbtree_lookup,
- .walk = nft_rbtree_walk,
- .get = nft_rbtree_get,
- .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT,
-};
-
static struct nft_set_type nft_rbtree_type __read_mostly = {
- .ops = &nft_rbtree_ops,
.owner = THIS_MODULE,
+ .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT,
+ .ops = {
+ .privsize = nft_rbtree_privsize,
+ .elemsize = offsetof(struct nft_rbtree_elem, ext),
+ .estimate = nft_rbtree_estimate,
+ .init = nft_rbtree_init,
+ .destroy = nft_rbtree_destroy,
+ .insert = nft_rbtree_insert,
+ .remove = nft_rbtree_remove,
+ .deactivate = nft_rbtree_deactivate,
+ .flush = nft_rbtree_flush,
+ .activate = nft_rbtree_activate,
+ .lookup = nft_rbtree_lookup,
+ .walk = nft_rbtree_walk,
+ .get = nft_rbtree_get,
+ },
};
static int __init nft_rbtree_module_init(void)
struct xt_match *m;
int err = -ENOENT;
+ if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+ return ERR_PTR(-EINVAL);
+
mutex_lock(&xt[af].mutex);
list_for_each_entry(m, &xt[af].match, list) {
if (strcmp(m->name, name) == 0) {
struct xt_target *t;
int err = -ENOENT;
+ if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+ return ERR_PTR(-EINVAL);
+
mutex_lock(&xt[af].mutex);
list_for_each_entry(t, &xt[af].target, list) {
if (strcmp(t->name, name) == 0) {
static unsigned int
netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
- struct nf_nat_range newrange;
+ const struct nf_nat_range2 *range = par->targinfo;
+ struct nf_nat_range2 newrange;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
union nf_inet_addr new_addr, netmask;
static int netmap_tg6_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
+ const struct nf_nat_range2 *range = par->targinfo;
if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
return -EINVAL;
enum ip_conntrack_info ctinfo;
__be32 new_ip, netmask;
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range newrange;
+ struct nf_nat_range2 newrange;
WARN_ON(xt_hooknum(par) != NF_INET_PRE_ROUTING &&
xt_hooknum(par) != NF_INET_POST_ROUTING &&
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_NFLOG.h>
#include <net/netfilter/nf_log.h>
-#include <net/netfilter/nfnetlink_log.h>
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("Xtables: packet logging to netlink using NFLOG");
if (info->flags & XT_NFLOG_F_COPY_LEN)
li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
- nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb,
- xt_in(par), xt_out(par), &li, info->prefix);
+ nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par),
+ xt_out(par), &li, "%s", info->prefix);
+
return XT_CONTINUE;
}
return -EINVAL;
if (info->prefix[sizeof(info->prefix) - 1] != '\0')
return -EINVAL;
- return 0;
+
+ return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+}
+
+static void nflog_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_logger_put(par->family, NF_LOG_TYPE_ULOG);
}
static struct xt_target nflog_tg_reg __read_mostly = {
.revision = 0,
.family = NFPROTO_UNSPEC,
.checkentry = nflog_tg_check,
+ .destroy = nflog_tg_destroy,
.target = nflog_tg,
.targetsize = sizeof(struct xt_nflog_info),
.me = THIS_MODULE,
static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
+ const struct nf_nat_range2 *range = par->targinfo;
if (range->flags & NF_NAT_RANGE_MAP_IPS)
return -EINVAL;
MODULE_ALIAS("ip6t_connmark");
static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
- const struct xt_connmark_tginfo1 *info,
- u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
{
enum ip_conntrack_info ctinfo;
+ u_int32_t new_targetmark;
struct nf_conn *ct;
u_int32_t newmark;
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ newmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ newmark <<= info->shift_bits;
+
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
- newmark = (ct->mark & ~info->ctmask) ^
- (skb->mark & info->nfmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (skb->mark & info->nfmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (ct->mark & ~info->ctmask) ^
+ new_targetmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_RESTORE:
- newmark = (skb->mark & ~info->nfmask) ^
- (ct->mark & info->ctmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (ct->mark & info->ctmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (skb->mark & ~info->nfmask) ^
+ new_targetmark;
skb->mark = newmark;
break;
}
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
-
- return connmark_tg_shift(skb, info, 0, 0);
+ const struct xt_connmark_tginfo2 info2 = {
+ .ctmark = info->ctmark,
+ .ctmask = info->ctmask,
+ .nfmask = info->nfmask,
+ .mode = info->mode,
+ };
+
+ return connmark_tg_shift(skb, &info2);
}
static unsigned int
{
const struct xt_connmark_tginfo2 *info = par->targinfo;
- return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
- info->shift_bits, info->shift_dir);
+ return connmark_tg_shift(skb, info);
}
static int connmark_tg_check(const struct xt_tgchk_param *par)
nf_ct_netns_put(par->net, par->family);
}
-static void xt_nat_convert_range(struct nf_nat_range *dst,
+static void xt_nat_convert_range(struct nf_nat_range2 *dst,
const struct nf_nat_ipv4_range *src)
{
memset(&dst->min_addr, 0, sizeof(dst->min_addr));
memset(&dst->max_addr, 0, sizeof(dst->max_addr));
+ memset(&dst->base_proto, 0, sizeof(dst->base_proto));
dst->flags = src->flags;
dst->min_addr.ip = src->min_ip;
xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
- struct nf_nat_range range;
+ struct nf_nat_range2 range;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
static unsigned int
xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
+ const struct nf_nat_range *range_v1 = par->targinfo;
+ struct nf_nat_range2 range;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
(ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED_REPLY)));
- return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC);
+ memcpy(&range, range_v1, sizeof(*range_v1));
+ memset(&range.base_proto, 0, sizeof(range.base_proto));
+
+ return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
}
static unsigned int
xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
- const struct nf_nat_range *range = par->targinfo;
+ const struct nf_nat_range *range_v1 = par->targinfo;
+ struct nf_nat_range2 range;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ WARN_ON(!(ct != NULL &&
+ (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)));
+
+ memcpy(&range, range_v1, sizeof(*range_v1));
+ memset(&range.base_proto, 0, sizeof(range.base_proto));
+
+ return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
+}
+
+static unsigned int
+xt_snat_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ const struct nf_nat_range2 *range = par->targinfo;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ WARN_ON(!(ct != NULL &&
+ (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+ ctinfo == IP_CT_RELATED_REPLY)));
+
+ return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC);
+}
+
+static unsigned int
+xt_dnat_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ const struct nf_nat_range2 *range = par->targinfo;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
(1 << NF_INET_LOCAL_OUT),
.me = THIS_MODULE,
},
+ {
+ .name = "SNAT",
+ .revision = 2,
+ .checkentry = xt_nat_checkentry,
+ .destroy = xt_nat_destroy,
+ .target = xt_snat_target_v2,
+ .targetsize = sizeof(struct nf_nat_range2),
+ .table = "nat",
+ .hooks = (1 << NF_INET_POST_ROUTING) |
+ (1 << NF_INET_LOCAL_IN),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "DNAT",
+ .revision = 2,
+ .target = xt_dnat_target_v2,
+ .targetsize = sizeof(struct nf_nat_range2),
+ .table = "nat",
+ .hooks = (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_OUT),
+ .me = THIS_MODULE,
+ },
};
static int __init xt_nat_init(void)
#include <net/netfilter/nf_log.h>
#include <linux/netfilter/xt_osf.h>
-struct xt_osf_finger {
- struct rcu_head rcu_head;
- struct list_head finger_entry;
- struct xt_osf_user_finger finger;
-};
-
-enum osf_fmatch_states {
- /* Packet does not match the fingerprint */
- FMATCH_WRONG = 0,
- /* Packet matches the fingerprint */
- FMATCH_OK,
- /* Options do not match the fingerprint, but header does */
- FMATCH_OPT_WRONG,
-};
-
/*
* Indexed by dont-fragment bit.
* It is the only constant value in the fingerprint.
.cb = xt_osf_nfnetlink_callbacks,
};
-static inline int xt_osf_ttl(const struct sk_buff *skb, const struct xt_osf_info *info,
- unsigned char f_ttl)
-{
- const struct iphdr *ip = ip_hdr(skb);
-
- if (info->flags & XT_OSF_TTL) {
- if (info->ttl == XT_OSF_TTL_TRUE)
- return ip->ttl == f_ttl;
- if (info->ttl == XT_OSF_TTL_NOCHECK)
- return 1;
- else if (ip->ttl <= f_ttl)
- return 1;
- else {
- struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
- int ret = 0;
-
- for_ifa(in_dev) {
- if (inet_ifa_match(ip->saddr, ifa)) {
- ret = (ip->ttl == f_ttl);
- break;
- }
- }
- endfor_ifa(in_dev);
-
- return ret;
- }
- }
-
- return ip->ttl == f_ttl;
-}
-
static bool
xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
{
const struct xt_osf_info *info = p->matchinfo;
- const struct iphdr *ip = ip_hdr(skb);
- const struct tcphdr *tcp;
- struct tcphdr _tcph;
- int fmatch = FMATCH_WRONG, fcount = 0;
- unsigned int optsize = 0, check_WSS = 0;
- u16 window, totlen, mss = 0;
- bool df;
- const unsigned char *optp = NULL, *_optp = NULL;
- unsigned char opts[MAX_IPOPTLEN];
- const struct xt_osf_finger *kf;
- const struct xt_osf_user_finger *f;
struct net *net = xt_net(p);
if (!info)
return false;
- tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
- if (!tcp)
- return false;
-
- if (!tcp->syn)
- return false;
-
- totlen = ntohs(ip->tot_len);
- df = ntohs(ip->frag_off) & IP_DF;
- window = ntohs(tcp->window);
-
- if (tcp->doff * 4 > sizeof(struct tcphdr)) {
- optsize = tcp->doff * 4 - sizeof(struct tcphdr);
-
- _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) +
- sizeof(struct tcphdr), optsize, opts);
- }
-
- list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) {
- int foptsize, optnum;
-
- f = &kf->finger;
-
- if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre))
- continue;
-
- optp = _optp;
- fmatch = FMATCH_WRONG;
-
- if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl))
- continue;
-
- /*
- * Should not happen if userspace parser was written correctly.
- */
- if (f->wss.wc >= OSF_WSS_MAX)
- continue;
-
- /* Check options */
-
- foptsize = 0;
- for (optnum = 0; optnum < f->opt_num; ++optnum)
- foptsize += f->opt[optnum].length;
-
- if (foptsize > MAX_IPOPTLEN ||
- optsize > MAX_IPOPTLEN ||
- optsize != foptsize)
- continue;
-
- check_WSS = f->wss.wc;
-
- for (optnum = 0; optnum < f->opt_num; ++optnum) {
- if (f->opt[optnum].kind == (*optp)) {
- __u32 len = f->opt[optnum].length;
- const __u8 *optend = optp + len;
-
- fmatch = FMATCH_OK;
-
- switch (*optp) {
- case OSFOPT_MSS:
- mss = optp[3];
- mss <<= 8;
- mss |= optp[2];
-
- mss = ntohs((__force __be16)mss);
- break;
- case OSFOPT_TS:
- break;
- }
-
- optp = optend;
- } else
- fmatch = FMATCH_OPT_WRONG;
-
- if (fmatch != FMATCH_OK)
- break;
- }
-
- if (fmatch != FMATCH_OPT_WRONG) {
- fmatch = FMATCH_WRONG;
-
- switch (check_WSS) {
- case OSF_WSS_PLAIN:
- if (f->wss.val == 0 || window == f->wss.val)
- fmatch = FMATCH_OK;
- break;
- case OSF_WSS_MSS:
- /*
- * Some smart modems decrease mangle MSS to
- * SMART_MSS_2, so we check standard, decreased
- * and the one provided in the fingerprint MSS
- * values.
- */
-#define SMART_MSS_1 1460
-#define SMART_MSS_2 1448
- if (window == f->wss.val * mss ||
- window == f->wss.val * SMART_MSS_1 ||
- window == f->wss.val * SMART_MSS_2)
- fmatch = FMATCH_OK;
- break;
- case OSF_WSS_MTU:
- if (window == f->wss.val * (mss + 40) ||
- window == f->wss.val * (SMART_MSS_1 + 40) ||
- window == f->wss.val * (SMART_MSS_2 + 40))
- fmatch = FMATCH_OK;
- break;
- case OSF_WSS_MODULO:
- if ((window % f->wss.val) == 0)
- fmatch = FMATCH_OK;
- break;
- }
- }
-
- if (fmatch != FMATCH_OK)
- continue;
-
- fcount++;
-
- if (info->flags & XT_OSF_LOG)
- nf_log_packet(net, xt_family(p), xt_hooknum(p), skb,
- xt_in(p), xt_out(p), NULL,
- "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
- f->genre, f->version, f->subtype,
- &ip->saddr, ntohs(tcp->source),
- &ip->daddr, ntohs(tcp->dest),
- f->ttl - ip->ttl);
-
- if ((info->flags & XT_OSF_LOG) &&
- info->loglevel == XT_OSF_LOGLEVEL_FIRST)
- break;
- }
-
- if (!fcount && (info->flags & XT_OSF_LOG))
- nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, xt_in(p),
- xt_out(p), NULL,
- "Remote OS is not known: %pI4:%u -> %pI4:%u\n",
- &ip->saddr, ntohs(tcp->source),
- &ip->daddr, ntohs(tcp->dest));
-
- if (fcount)
- fmatch = FMATCH_OK;
-
- return fmatch == FMATCH_OK;
+ return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p),
+ xt_out(p), info, net, xt_osf_fingers);
}
static struct xt_match xt_osf_match = {
{
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
- "sk Eth Pid Groups "
- "Rmem Wmem Dump Locks Drops Inode\n");
+ "sk Eth Pid Groups "
+ "Rmem Wmem Dump Locks Drops Inode\n");
} else {
struct sock *s = v;
struct netlink_sock *nlk = nlk_sk(s);
- seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n",
+ seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n",
s,
s->sk_protocol,
nlk->portid,
return -ENOMEM;
nh = (struct nshhdr *)(skb->data);
length = nsh_hdr_len(nh);
+ if (length < NSH_BASE_HDR_LEN)
+ return -EINVAL;
inner_proto = tun_p_to_eth_p(nh->np);
if (!pskb_may_pull(skb, length))
return -ENOMEM;
if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
goto out;
nsh_len = nsh_hdr_len(nsh_hdr(skb));
+ if (nsh_len < NSH_BASE_HDR_LEN)
+ goto out;
if (unlikely(!pskb_may_pull(skb, nsh_len)))
goto out;
struct md_mark mark;
struct md_labels labels;
#ifdef CONFIG_NF_NAT_NEEDED
- struct nf_nat_range range; /* Only present for SRC NAT and DST NAT. */
+ struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */
#endif
};
*/
static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
- const struct nf_nat_range *range,
+ const struct nf_nat_range2 *range,
enum nf_nat_manip_type maniptype)
{
int hooknum, nh_off, err = NF_ACCEPT;
/* The nlattr stream should already have been validated */
nla_for_each_nested(nla, attr, rem) {
- if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
- if (tbl[nla_type(nla)].next)
- tbl = tbl[nla_type(nla)].next;
- nlattr_set(nla, val, tbl);
- } else {
+ if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+ nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+ else
memset(nla_data(nla), val, nla_len(nla));
- }
if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
struct tpacket3_hdr *);
static void packet_flush_mclist(struct sock *sk);
-static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb);
+static u16 packet_pick_tx_queue(struct sk_buff *skb);
struct packet_skb_cb {
union {
static int packet_direct_xmit(struct sk_buff *skb)
{
- struct net_device *dev = skb->dev;
- struct sk_buff *orig_skb = skb;
- struct netdev_queue *txq;
- int ret = NETDEV_TX_BUSY;
- bool again = false;
-
- if (unlikely(!netif_running(dev) ||
- !netif_carrier_ok(dev)))
- goto drop;
-
- skb = validate_xmit_skb_list(skb, dev, &again);
- if (skb != orig_skb)
- goto drop;
-
- packet_pick_tx_queue(dev, skb);
- txq = skb_get_tx_queue(dev, skb);
-
- local_bh_disable();
-
- HARD_TX_LOCK(dev, txq, smp_processor_id());
- if (!netif_xmit_frozen_or_drv_stopped(txq))
- ret = netdev_start_xmit(skb, dev, txq, false);
- HARD_TX_UNLOCK(dev, txq);
-
- local_bh_enable();
-
- if (!dev_xmit_complete(ret))
- kfree_skb(skb);
-
- return ret;
-drop:
- atomic_long_inc(&dev->tx_dropped);
- kfree_skb_list(skb);
- return NET_XMIT_DROP;
+ return dev_direct_xmit(skb, packet_pick_tx_queue(skb));
}
static struct net_device *packet_cached_dev_get(struct packet_sock *po)
return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
}
-static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 packet_pick_tx_queue(struct sk_buff *skb)
{
+ struct net_device *dev = skb->dev;
const struct net_device_ops *ops = dev->netdev_ops;
u16 queue_index;
queue_index = __packet_pick_tx_queue(dev, skb);
}
- skb_set_queue_mapping(skb, queue_index);
+ return queue_index;
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
if (skb == NULL)
goto out_unlock;
- skb_set_network_header(skb, reserve);
+ skb_reset_network_header(skb);
err = -EINVAL;
if (sock->type == SOCK_DGRAM) {
offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
if (unlikely(offset < 0))
goto out_free;
+ } else if (reserve) {
+ skb_push(skb, reserve);
}
/* Returns -EFAULT on error */
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
Say Y here to support SMD based ipcrouter channels. SMD is the
most common transport for IPC Router.
+config QRTR_TUN
+ tristate "TUN device for Qualcomm IPC Router"
+ ---help---
+ Say Y here to expose a character device that allows user space to
+ implement endpoints of QRTR, for purpose of tunneling data to other
+ hosts or testing purposes.
+
endif # QRTR
obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o
qrtr-smd-y := smd.o
+obj-$(CONFIG_QRTR_TUN) += qrtr-tun.o
+qrtr-tun-y := tun.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Linaro Ltd */
+
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/skbuff.h>
+#include <linux/uaccess.h>
+
+#include "qrtr.h"
+
+struct qrtr_tun {
+ struct qrtr_endpoint ep;
+
+ struct sk_buff_head queue;
+ wait_queue_head_t readq;
+};
+
+static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
+{
+ struct qrtr_tun *tun = container_of(ep, struct qrtr_tun, ep);
+
+ skb_queue_tail(&tun->queue, skb);
+
+ /* wake up any blocking processes, waiting for new data */
+ wake_up_interruptible(&tun->readq);
+
+ return 0;
+}
+
+static int qrtr_tun_open(struct inode *inode, struct file *filp)
+{
+ struct qrtr_tun *tun;
+
+ tun = kzalloc(sizeof(*tun), GFP_KERNEL);
+ if (!tun)
+ return -ENOMEM;
+
+ skb_queue_head_init(&tun->queue);
+ init_waitqueue_head(&tun->readq);
+
+ tun->ep.xmit = qrtr_tun_send;
+
+ filp->private_data = tun;
+
+ return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO);
+}
+
+static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct file *filp = iocb->ki_filp;
+ struct qrtr_tun *tun = filp->private_data;
+ struct sk_buff *skb;
+ int count;
+
+ while (!(skb = skb_dequeue(&tun->queue))) {
+ if (filp->f_flags & O_NONBLOCK)
+ return -EAGAIN;
+
+ /* Wait until we get data or the endpoint goes away */
+ if (wait_event_interruptible(tun->readq,
+ !skb_queue_empty(&tun->queue)))
+ return -ERESTARTSYS;
+ }
+
+ count = min_t(size_t, iov_iter_count(to), skb->len);
+ if (copy_to_iter(skb->data, count, to) != count)
+ count = -EFAULT;
+
+ kfree_skb(skb);
+
+ return count;
+}
+
+static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *filp = iocb->ki_filp;
+ struct qrtr_tun *tun = filp->private_data;
+ size_t len = iov_iter_count(from);
+ ssize_t ret;
+ void *kbuf;
+
+ kbuf = kzalloc(len, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ if (!copy_from_iter_full(kbuf, len, from))
+ return -EFAULT;
+
+ ret = qrtr_endpoint_post(&tun->ep, kbuf, len);
+
+ return ret < 0 ? ret : len;
+}
+
+static __poll_t qrtr_tun_poll(struct file *filp, poll_table *wait)
+{
+ struct qrtr_tun *tun = filp->private_data;
+ __poll_t mask = 0;
+
+ poll_wait(filp, &tun->readq, wait);
+
+ if (!skb_queue_empty(&tun->queue))
+ mask |= EPOLLIN | EPOLLRDNORM;
+
+ return mask;
+}
+
+static int qrtr_tun_release(struct inode *inode, struct file *filp)
+{
+ struct qrtr_tun *tun = filp->private_data;
+ struct sk_buff *skb;
+
+ qrtr_endpoint_unregister(&tun->ep);
+
+ /* Discard all SKBs */
+ while (!skb_queue_empty(&tun->queue)) {
+ skb = skb_dequeue(&tun->queue);
+ kfree_skb(skb);
+ }
+
+ kfree(tun);
+
+ return 0;
+}
+
+static const struct file_operations qrtr_tun_ops = {
+ .owner = THIS_MODULE,
+ .open = qrtr_tun_open,
+ .poll = qrtr_tun_poll,
+ .read_iter = qrtr_tun_read_iter,
+ .write_iter = qrtr_tun_write_iter,
+ .release = qrtr_tun_release,
+};
+
+static struct miscdevice qrtr_tun_miscdev = {
+ MISC_DYNAMIC_MINOR,
+ "qrtr-tun",
+ &qrtr_tun_ops,
+};
+
+static int __init qrtr_tun_init(void)
+{
+ int ret;
+
+ ret = misc_register(&qrtr_tun_miscdev);
+ if (ret)
+ pr_err("failed to register Qualcomm IPC Router tun device\n");
+
+ return ret;
+}
+
+static void __exit qrtr_tun_exit(void)
+{
+ misc_deregister(&qrtr_tun_miscdev);
+}
+
+module_init(qrtr_tun_init);
+module_exit(qrtr_tun_exit);
+
+MODULE_DESCRIPTION("Qualcomm IPC Router TUN device");
+MODULE_LICENSE("GPL v2");
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
- return ret;
+ goto out;
sends_out:
vfree(ic->i_sends);
ic->i_send_cq = NULL;
rds_ibdev_out:
rds_ib_remove_conn(rds_ibdev, conn);
+out:
rds_ib_dev_put(rds_ibdev);
return ret;
struct rds_cmsg_rx_trace t;
int i, j;
+ memset(&t, 0, sizeof(t));
inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
t.rx_traces = rs->rs_rx_traces;
for (i = 0; i < rs->rs_rx_traces; i++) {
ret = rfkill_register(rfkill->rfkill_dev);
if (ret < 0)
- return ret;
+ goto err_destroy;
platform_set_drvdata(pdev, rfkill);
dev_info(&pdev->dev, "%s device registered.\n", rfkill->name);
return 0;
+
+err_destroy:
+ rfkill_destroy(rfkill->rfkill_dev);
+
+ return ret;
}
static int rfkill_gpio_remove(struct platform_device *pdev)
memset(&cp, 0, sizeof(cp));
cp.local = rx->local;
cp.key = key;
- cp.security_level = 0;
+ cp.security_level = rx->min_sec_level;
cp.exclusive = false;
cp.upgrade = upgrade;
cp.service_id = srx->srx_service;
RXRPC_CALL_SEND_PING, /* A ping will need to be sent */
RXRPC_CALL_PINGING, /* Ping in process */
RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */
+ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */
};
/*
} __attribute__((packed)) pkt;
struct rxrpc_ackinfo ack_info;
size_t len;
- int ioc;
+ int ret, ioc;
u32 serial, mtu, call_id, padding;
_enter("%d", conn->debug_id);
break;
}
- kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
+ ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_call_final_resend);
+
_leave("");
- return;
}
/*
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_abort);
_debug("sendmsg failed: %d", ret);
return -EAGAIN;
}
if (timo) {
unsigned long now = jiffies, expect_rx_by;
- expect_rx_by = jiffies + timo;
+ expect_rx_by = now + timo;
WRITE_ONCE(call->expect_rx_by, expect_rx_by);
rxrpc_reduce_call_timer(call, expect_rx_by, now,
rxrpc_timer_set_for_normal);
ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
if (ret < 0)
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+ rxrpc_tx_fail_version_reply);
_leave("");
}
}
}
- /* we want to receive ICMP errors */
- opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
- }
+ switch (local->srx.transport.family) {
+ case AF_INET:
+ /* we want to receive ICMP errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
- /* we want to set the don't fragment bit */
- opt = IP_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
+ /* we want to set the don't fragment bit */
+ opt = IP_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+ break;
+
+ case AF_INET6:
+ /* we want to receive ICMP errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* we want to set the don't fragment bit */
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+ break;
+
+ default:
+ BUG();
}
/* set the socket up */
if (ping)
call->ping_time = now;
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_ack);
if (call->state < RXRPC_CALL_COMPLETE) {
if (ret < 0) {
ret = kernel_sendmsg(conn->params.local->socket,
&msg, iov, 1, sizeof(pkt));
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_abort);
+
rxrpc_put_connection(conn);
return ret;
conn->params.peer->last_tx_at = ktime_get_real();
up_read(&conn->params.local->defrag_sem);
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_data_nofrag);
if (ret == -EMSGSIZE)
goto send_fragmentable;
rxrpc_timer_set_for_lost_ack);
}
}
+
+ if (sp->hdr.seq == 1 &&
+ !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER,
+ &call->flags)) {
+ unsigned long nowj = jiffies, expect_rx_by;
+
+ expect_rx_by = nowj + call->next_rx_timo;
+ WRITE_ONCE(call->expect_rx_by, expect_rx_by);
+ rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
+ rxrpc_timer_set_for_normal);
+ }
}
rxrpc_set_keepalive(call);
#endif
}
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_data_frag);
+
up_write(&conn->params.local->defrag_sem);
goto done;
}
struct kvec iov[2];
size_t size;
__be32 code;
+ int ret;
_enter("%d", local->debug_id);
whdr.flags ^= RXRPC_CLIENT_INITIATED;
whdr.flags &= RXRPC_CLIENT_INITIATED;
- kernel_sendmsg(local->socket, &msg, iov, 2, size);
+ ret = kernel_sendmsg(local->socket, &msg, iov, 2, size);
+ if (ret < 0)
+ trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+ rxrpc_tx_fail_reject);
}
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
if (ret < 0)
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
+ rxrpc_tx_fail_version_keepalive);
peer->last_tx_at = ktime_get_real();
_leave("");
* Find the peer associated with an ICMP packet.
*/
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
- const struct sk_buff *skb)
+ const struct sk_buff *skb,
+ struct sockaddr_rxrpc *srx)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
- struct sockaddr_rxrpc srx;
_enter("");
- memset(&srx, 0, sizeof(srx));
- srx.transport_type = local->srx.transport_type;
- srx.transport_len = local->srx.transport_len;
- srx.transport.family = local->srx.transport.family;
+ memset(srx, 0, sizeof(*srx));
+ srx->transport_type = local->srx.transport_type;
+ srx->transport_len = local->srx.transport_len;
+ srx->transport.family = local->srx.transport.family;
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
* versa?
*/
- switch (srx.transport.family) {
+ switch (srx->transport.family) {
case AF_INET:
- srx.transport.sin.sin_port = serr->port;
+ srx->transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP");
- memcpy(&srx.transport.sin.sin_addr,
+ memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6 on v4 sock");
- memcpy(&srx.transport.sin.sin_addr,
+ memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset + 12,
sizeof(struct in_addr));
break;
default:
- memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+ memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
sizeof(struct in_addr));
break;
}
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
- srx.transport.sin6.sin6_port = serr->port;
+ srx->transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
- memcpy(&srx.transport.sin6.sin6_addr,
+ memcpy(&srx->transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
- srx.transport.sin6.sin6_addr.s6_addr32[0] = 0;
- srx.transport.sin6.sin6_addr.s6_addr32[1] = 0;
- srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
+ srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
+ srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
+ srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
+ memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
default:
- memcpy(&srx.transport.sin6.sin6_addr,
+ memcpy(&srx->transport.sin6.sin6_addr,
&ipv6_hdr(skb)->saddr,
sizeof(struct in6_addr));
break;
BUG();
}
- return rxrpc_lookup_peer_rcu(local, &srx);
+ return rxrpc_lookup_peer_rcu(local, srx);
}
/*
void rxrpc_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
+ struct sockaddr_rxrpc srx;
struct rxrpc_local *local = sk->sk_user_data;
struct rxrpc_peer *peer;
struct sk_buff *skb;
}
rcu_read_lock();
- peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
+ peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
return;
}
+ trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+
if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
serr->ee.ee_type == ICMP_DEST_UNREACH &&
serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
ee = &serr->ee;
- _net("Rx Error o=%d t=%d c=%d e=%d",
- ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
-
err = ee->ee_errno;
switch (ee->ee_origin) {
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_challenge);
return -EAGAIN;
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len);
if (ret < 0) {
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_response);
return -EAGAIN;
}
ret = rxrpc_send_data_packet(call, skb, false);
if (ret < 0) {
+ switch (ret) {
+ case -ENETUNREACH:
+ case -EHOSTUNREACH:
+ case -ECONNREFUSED:
+ rxrpc_set_call_completion(call,
+ RXRPC_CALL_LOCAL_ERROR,
+ 0, ret);
+ goto out;
+ }
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
rxrpc_timer_set_for_send);
}
+out:
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
_leave("");
}
return tcf_idr_search(tn, a, index);
}
+static size_t tcf_csum_get_fill_size(const struct tc_action *act)
+{
+ return nla_total_size(sizeof(struct tc_csum));
+}
+
static struct tc_action_ops act_csum_ops = {
.kind = "csum",
.type = TCA_ACT_CSUM,
.cleanup = tcf_csum_cleanup,
.walk = tcf_csum_walker,
.lookup = tcf_csum_search,
+ .get_fill_size = tcf_csum_get_fill_size,
.size = sizeof(struct tcf_csum),
};
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
return 0;
if (!flags) {
- tcf_idr_release(*a, bind);
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EINVAL;
}
if (exists && bind)
return 0;
- if (!lflags)
+ if (!lflags) {
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EINVAL;
+ }
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
case htons(ETH_P_8021AD):
break;
default:
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EPROTONOSUPPORT;
}
} else {
NL_SET_ERR_MSG(extack, "TC classifier not found");
err = -ENOENT;
}
- goto errout;
#endif
+ goto errout;
}
tp->classify = tp->ops->classify;
tp->protocol = protocol;
struct fl_flow_mask {
struct fl_flow_key key;
struct fl_flow_mask_range range;
- struct rcu_head rcu;
+ struct rhash_head ht_node;
+ struct rhashtable ht;
+ struct rhashtable_params filter_ht_params;
+ struct flow_dissector dissector;
+ struct list_head filters;
+ struct rcu_head rcu;
+ struct list_head list;
};
struct cls_fl_head {
struct rhashtable ht;
- struct fl_flow_mask mask;
- struct flow_dissector dissector;
- bool mask_assigned;
- struct list_head filters;
- struct rhashtable_params ht_params;
+ struct list_head masks;
union {
struct work_struct work;
struct rcu_head rcu;
};
struct cls_fl_filter {
+ struct fl_flow_mask *mask;
struct rhash_head ht_node;
struct fl_flow_key mkey;
struct tcf_exts exts;
struct net_device *hw_dev;
};
+static const struct rhashtable_params mask_ht_params = {
+ .key_offset = offsetof(struct fl_flow_mask, key),
+ .key_len = sizeof(struct fl_flow_key),
+ .head_offset = offsetof(struct fl_flow_mask, ht_node),
+ .automatic_shrinking = true,
+};
+
static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
{
return mask->range.end - mask->range.start;
{
const u8 *bytes = (const u8 *) &mask->key;
size_t size = sizeof(mask->key);
- size_t i, first = 0, last = size - 1;
+ size_t i, first = 0, last;
- for (i = 0; i < sizeof(mask->key); i++) {
+ for (i = 0; i < size; i++) {
+ if (bytes[i]) {
+ first = i;
+ break;
+ }
+ }
+ last = first;
+ for (i = size - 1; i != first; i--) {
if (bytes[i]) {
- if (!first && i)
- first = i;
last = i;
+ break;
}
}
mask->range.start = rounddown(first, sizeof(long));
memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
}
-static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head,
+static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
struct fl_flow_key *mkey)
{
- return rhashtable_lookup_fast(&head->ht,
- fl_key_get_start(mkey, &head->mask),
- head->ht_params);
+ return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask),
+ mask->filter_ht_params);
}
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
{
struct cls_fl_head *head = rcu_dereference_bh(tp->root);
struct cls_fl_filter *f;
+ struct fl_flow_mask *mask;
struct fl_flow_key skb_key;
struct fl_flow_key skb_mkey;
- if (!atomic_read(&head->ht.nelems))
- return -1;
-
- fl_clear_masked_range(&skb_key, &head->mask);
+ list_for_each_entry_rcu(mask, &head->masks, list) {
+ fl_clear_masked_range(&skb_key, mask);
- skb_key.indev_ifindex = skb->skb_iif;
- /* skb_flow_dissect() does not set n_proto in case an unknown protocol,
- * so do it rather here.
- */
- skb_key.basic.n_proto = skb->protocol;
- skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key);
- skb_flow_dissect(skb, &head->dissector, &skb_key, 0);
+ skb_key.indev_ifindex = skb->skb_iif;
+ /* skb_flow_dissect() does not set n_proto in case an unknown
+ * protocol, so do it rather here.
+ */
+ skb_key.basic.n_proto = skb->protocol;
+ skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
+ skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
- fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
+ fl_set_masked_key(&skb_mkey, &skb_key, mask);
- f = fl_lookup(head, &skb_mkey);
- if (f && !tc_skip_sw(f->flags)) {
- *res = f->res;
- return tcf_exts_exec(skb, &f->exts, res);
+ f = fl_lookup(mask, &skb_mkey);
+ if (f && !tc_skip_sw(f->flags)) {
+ *res = f->res;
+ return tcf_exts_exec(skb, &f->exts, res);
+ }
}
return -1;
}
if (!head)
return -ENOBUFS;
- INIT_LIST_HEAD_RCU(&head->filters);
+ INIT_LIST_HEAD_RCU(&head->masks);
rcu_assign_pointer(tp->root, head);
idr_init(&head->handle_idr);
- return 0;
+ return rhashtable_init(&head->ht, &mask_ht_params);
+}
+
+static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
+ bool async)
+{
+ if (!list_empty(&mask->filters))
+ return false;
+
+ rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
+ rhashtable_destroy(&mask->ht);
+ list_del_rcu(&mask->list);
+ if (async)
+ kfree_rcu(mask, rcu);
+ else
+ kfree(mask);
+
+ return true;
}
static void __fl_destroy_filter(struct cls_fl_filter *f)
}
static int fl_hw_replace_filter(struct tcf_proto *tp,
- struct flow_dissector *dissector,
- struct fl_flow_key *mask,
struct cls_fl_filter *f,
struct netlink_ext_ack *extack)
{
tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
cls_flower.command = TC_CLSFLOWER_REPLACE;
cls_flower.cookie = (unsigned long) f;
- cls_flower.dissector = dissector;
- cls_flower.mask = mask;
+ cls_flower.dissector = &f->mask->dissector;
+ cls_flower.mask = &f->mask->key;
cls_flower.key = &f->mkey;
cls_flower.exts = &f->exts;
cls_flower.classid = f->res.classid;
&cls_flower, false);
}
-static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
+static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
+ bool async = tcf_exts_get_net(&f->exts);
+ bool last;
idr_remove(&head->handle_idr, f->handle);
list_del_rcu(&f->list);
+ last = fl_mask_put(head, f->mask, async);
if (!tc_skip_hw(f->flags))
fl_hw_destroy_filter(tp, f, extack);
tcf_unbind_filter(tp, &f->res);
- if (tcf_exts_get_net(&f->exts))
+ if (async)
call_rcu(&f->rcu, fl_destroy_filter);
else
__fl_destroy_filter(f);
+
+ return last;
}
static void fl_destroy_sleepable(struct work_struct *work)
{
struct cls_fl_head *head = container_of(work, struct cls_fl_head,
work);
- if (head->mask_assigned)
- rhashtable_destroy(&head->ht);
kfree(head);
module_put(THIS_MODULE);
}
static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct fl_flow_mask *mask, *next_mask;
struct cls_fl_filter *f, *next;
- list_for_each_entry_safe(f, next, &head->filters, list)
- __fl_delete(tp, f, extack);
+ list_for_each_entry_safe(mask, next_mask, &head->masks, list) {
+ list_for_each_entry_safe(f, next, &mask->filters, list) {
+ if (__fl_delete(tp, f, extack))
+ break;
+ }
+ }
idr_destroy(&head->handle_idr);
__module_get(THIS_MODULE);
return ret;
}
-static bool fl_mask_eq(struct fl_flow_mask *mask1,
- struct fl_flow_mask *mask2)
+static void fl_mask_copy(struct fl_flow_mask *dst,
+ struct fl_flow_mask *src)
{
- const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
- const long *lmask2 = fl_key_get_start(&mask2->key, mask2);
+ const void *psrc = fl_key_get_start(&src->key, src);
+ void *pdst = fl_key_get_start(&dst->key, src);
- return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
- !memcmp(lmask1, lmask2, fl_mask_range(mask1));
+ memcpy(pdst, psrc, fl_mask_range(src));
+ dst->range = src->range;
}
static const struct rhashtable_params fl_ht_params = {
.automatic_shrinking = true,
};
-static int fl_init_hashtable(struct cls_fl_head *head,
- struct fl_flow_mask *mask)
+static int fl_init_mask_hashtable(struct fl_flow_mask *mask)
{
- head->ht_params = fl_ht_params;
- head->ht_params.key_len = fl_mask_range(mask);
- head->ht_params.key_offset += mask->range.start;
+ mask->filter_ht_params = fl_ht_params;
+ mask->filter_ht_params.key_len = fl_mask_range(mask);
+ mask->filter_ht_params.key_offset += mask->range.start;
- return rhashtable_init(&head->ht, &head->ht_params);
+ return rhashtable_init(&mask->ht, &mask->filter_ht_params);
}
#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
FL_KEY_SET(keys, cnt, id, member); \
} while(0);
-static void fl_init_dissector(struct cls_fl_head *head,
- struct fl_flow_mask *mask)
+static void fl_init_dissector(struct fl_flow_mask *mask)
{
struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
size_t cnt = 0;
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
- skb_flow_dissector_init(&head->dissector, keys, cnt);
+ skb_flow_dissector_init(&mask->dissector, keys, cnt);
+}
+
+static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
+ struct fl_flow_mask *mask)
+{
+ struct fl_flow_mask *newmask;
+ int err;
+
+ newmask = kzalloc(sizeof(*newmask), GFP_KERNEL);
+ if (!newmask)
+ return ERR_PTR(-ENOMEM);
+
+ fl_mask_copy(newmask, mask);
+
+ err = fl_init_mask_hashtable(newmask);
+ if (err)
+ goto errout_free;
+
+ fl_init_dissector(newmask);
+
+ INIT_LIST_HEAD_RCU(&newmask->filters);
+
+ err = rhashtable_insert_fast(&head->ht, &newmask->ht_node,
+ mask_ht_params);
+ if (err)
+ goto errout_destroy;
+
+ list_add_tail_rcu(&newmask->list, &head->masks);
+
+ return newmask;
+
+errout_destroy:
+ rhashtable_destroy(&newmask->ht);
+errout_free:
+ kfree(newmask);
+
+ return ERR_PTR(err);
}
static int fl_check_assign_mask(struct cls_fl_head *head,
+ struct cls_fl_filter *fnew,
+ struct cls_fl_filter *fold,
struct fl_flow_mask *mask)
{
- int err;
+ struct fl_flow_mask *newmask;
- if (head->mask_assigned) {
- if (!fl_mask_eq(&head->mask, mask))
+ fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params);
+ if (!fnew->mask) {
+ if (fold)
return -EINVAL;
- else
- return 0;
- }
- /* Mask is not assigned yet. So assign it and init hashtable
- * according to that.
- */
- err = fl_init_hashtable(head, mask);
- if (err)
- return err;
- memcpy(&head->mask, mask, sizeof(head->mask));
- head->mask_assigned = true;
+ newmask = fl_create_new_mask(head, mask);
+ if (IS_ERR(newmask))
+ return PTR_ERR(newmask);
- fl_init_dissector(head, mask);
+ fnew->mask = newmask;
+ } else if (fold && fold->mask == fnew->mask) {
+ return -EINVAL;
+ }
return 0;
}
if (err)
goto errout_idr;
- err = fl_check_assign_mask(head, &mask);
+ err = fl_check_assign_mask(head, fnew, fold, &mask);
if (err)
goto errout_idr;
if (!tc_skip_sw(fnew->flags)) {
- if (!fold && fl_lookup(head, &fnew->mkey)) {
+ if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
err = -EEXIST;
- goto errout_idr;
+ goto errout_mask;
}
- err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
- head->ht_params);
+ err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
+ fnew->mask->filter_ht_params);
if (err)
- goto errout_idr;
+ goto errout_mask;
}
if (!tc_skip_hw(fnew->flags)) {
- err = fl_hw_replace_filter(tp,
- &head->dissector,
- &mask.key,
- fnew,
- extack);
+ err = fl_hw_replace_filter(tp, fnew, extack);
if (err)
- goto errout_idr;
+ goto errout_mask;
}
if (!tc_in_hw(fnew->flags))
if (fold) {
if (!tc_skip_sw(fold->flags))
- rhashtable_remove_fast(&head->ht, &fold->ht_node,
- head->ht_params);
+ rhashtable_remove_fast(&fold->mask->ht,
+ &fold->ht_node,
+ fold->mask->filter_ht_params);
if (!tc_skip_hw(fold->flags))
fl_hw_destroy_filter(tp, fold, NULL);
}
tcf_exts_get_net(&fold->exts);
call_rcu(&fold->rcu, fl_destroy_filter);
} else {
- list_add_tail_rcu(&fnew->list, &head->filters);
+ list_add_tail_rcu(&fnew->list, &fnew->mask->filters);
}
kfree(tb);
return 0;
+errout_mask:
+ fl_mask_put(head, fnew->mask, false);
+
errout_idr:
if (fnew->handle)
idr_remove(&head->handle_idr, fnew->handle);
struct cls_fl_filter *f = arg;
if (!tc_skip_sw(f->flags))
- rhashtable_remove_fast(&head->ht, &f->ht_node,
- head->ht_params);
+ rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
+ f->mask->filter_ht_params);
__fl_delete(tp, f, extack);
- *last = list_empty(&head->filters);
+ *last = list_empty(&head->masks);
return 0;
}
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f;
-
- list_for_each_entry_rcu(f, &head->filters, list) {
- if (arg->count < arg->skip)
- goto skip;
- if (arg->fn(tp, f, arg) < 0) {
- arg->stop = 1;
- break;
- }
+ struct fl_flow_mask *mask;
+
+ list_for_each_entry_rcu(mask, &head->masks, list) {
+ list_for_each_entry_rcu(f, &mask->filters, list) {
+ if (arg->count < arg->skip)
+ goto skip;
+ if (arg->fn(tp, f, arg) < 0) {
+ arg->stop = 1;
+ break;
+ }
skip:
- arg->count++;
+ arg->count++;
+ }
}
}
static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
struct sk_buff *skb, struct tcmsg *t)
{
- struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *f = fh;
struct nlattr *nest;
struct fl_flow_key *key, *mask;
goto nla_put_failure;
key = &f->key;
- mask = &head->mask.key;
+ mask = &f->mask->key;
if (mask->indev_ifindex) {
struct net_device *dev;
return f->next == &detached;
}
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+ return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+ if (head->first)
+ head->last->next = flow;
+ else
+ head->first = flow;
+ head->last = flow;
+ flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+ rb_erase(&f->rate_node, &q->delayed);
+ q->throttled_flows--;
+ fq_flow_add_tail(&q->old_flows, f);
+}
+
static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
{
struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
static struct kmem_cache *fq_flow_cachep __read_mostly;
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
- if (head->first)
- head->last->next = flow;
- else
- head->first = flow;
- head->last = flow;
- flow->next = NULL;
-}
/* limit number of collected flows per round */
#define FQ_GC_MAX 8
f->socket_hash != sk->sk_hash)) {
f->credit = q->initial_quantum;
f->socket_hash = sk->sk_hash;
+ if (fq_flow_is_throttled(f))
+ fq_flow_unset_throttled(q, f);
f->time_next_packet = 0ULL;
}
return f;
q->time_next_delayed_flow = f->time_next_packet;
break;
}
- rb_erase(p, &q->delayed);
- q->throttled_flows--;
- fq_flow_add_tail(&q->old_flows, f);
+ fq_flow_unset_throttled(q, f);
}
}
*/
static inline bool qdisc_restart(struct Qdisc *q, int *packets)
{
- bool more, validate, nolock = q->flags & TCQ_F_NOLOCK;
spinlock_t *root_lock = NULL;
struct netdev_queue *txq;
struct net_device *dev;
struct sk_buff *skb;
+ bool validate;
/* Dequeue packet */
- if (nolock && test_and_set_bit(__QDISC_STATE_RUNNING, &q->state))
- return false;
-
skb = dequeue_skb(q, &validate, packets);
- if (unlikely(!skb)) {
- if (nolock)
- clear_bit(__QDISC_STATE_RUNNING, &q->state);
+ if (unlikely(!skb))
return false;
- }
- if (!nolock)
+ if (!(q->flags & TCQ_F_NOLOCK))
root_lock = qdisc_lock(q);
dev = qdisc_dev(q);
txq = skb_get_tx_queue(dev, skb);
- more = sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
- if (nolock)
- clear_bit(__QDISC_STATE_RUNNING, &q->state);
- return more;
+ return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
}
void __qdisc_run(struct Qdisc *q)
if (__skb_array_empty(q))
continue;
- skb = skb_array_consume_bh(q);
+ skb = __skb_array_consume(q);
}
if (likely(skb)) {
qdisc_qstats_cpu_backlog_dec(qdisc, skb);
if (!q->ring.queue)
continue;
- while ((skb = skb_array_consume_bh(q)) != NULL)
+ while ((skb = __skb_array_consume(q)) != NULL)
kfree_skb(skb);
}
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+ /* seqlock has the same scope of busylock, for NOLOCK qdisc */
+ spin_lock_init(&sch->seqlock);
+ lockdep_set_class(&sch->busylock,
+ dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
seqcount_init(&sch->running);
lockdep_set_class(&sch->running,
dev->qdisc_running_key ?: &qdisc_running_key);
qdisc = rtnl_dereference(dev_queue->qdisc);
if (qdisc) {
+ bool nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+ if (nolock)
+ spin_lock_bh(&qdisc->seqlock);
spin_lock_bh(qdisc_lock(qdisc));
if (!(qdisc->flags & TCQ_F_BUILTIN))
qdisc_reset(qdisc);
spin_unlock_bh(qdisc_lock(qdisc));
+ if (nolock)
+ spin_unlock_bh(&qdisc->seqlock);
}
}
dev_queue = netdev_get_tx_queue(dev, i);
q = dev_queue->qdisc_sleeping;
- if (q->flags & TCQ_F_NOLOCK) {
- val = test_bit(__QDISC_STATE_SCHED, &q->state);
- } else {
- root_lock = qdisc_lock(q);
- spin_lock_bh(root_lock);
+ root_lock = qdisc_lock(q);
+ spin_lock_bh(root_lock);
- val = (qdisc_is_running(q) ||
- test_bit(__QDISC_STATE_SCHED, &q->state));
+ val = (qdisc_is_running(q) ||
+ test_bit(__QDISC_STATE_SCHED, &q->state));
- spin_unlock_bh(root_lock);
- }
+ spin_unlock_bh(root_lock);
if (val)
return true;
extack);
if (IS_ERR(child))
return PTR_ERR(child);
- }
- if (child != &noop_qdisc)
+ /* child is fifo, no need to check for noop_qdisc */
qdisc_hash_add(child, true);
+ }
+
sch_tree_lock(sch);
q->flags = ctl->flags;
q->limit = ctl->limit;
err = PTR_ERR(child);
goto done;
}
+
+ /* child is fifo, no need to check for noop_qdisc */
+ qdisc_hash_add(child, true);
}
sch_tree_lock(sch);
q->qdisc->qstats.backlog);
qdisc_destroy(q->qdisc);
q->qdisc = child;
- if (child != &noop_qdisc)
- qdisc_hash_add(child, true);
}
q->limit = qopt->limit;
if (tb[TCA_TBF_PBURST])
*/
peer->param_flags = asoc->param_flags;
- sctp_transport_route(peer, NULL, sp);
-
/* Initialize the pmtu of the transport. */
- if (peer->param_flags & SPP_PMTUD_DISABLE) {
- if (asoc->pathmtu)
- peer->pathmtu = asoc->pathmtu;
- else
- peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
- }
+ sctp_transport_route(peer, NULL, sp);
/* If this is the first transport addr on this association,
* initialize the association PMTU to the peer's PMTU.
* If not and the current association PMTU is higher than the new
* peer's PMTU, reset the association PMTU to the new peer's PMTU.
*/
- if (asoc->pathmtu)
- asoc->pathmtu = min_t(int, peer->pathmtu, asoc->pathmtu);
- else
- asoc->pathmtu = peer->pathmtu;
-
- pr_debug("%s: association:%p PMTU set to %d\n", __func__, asoc,
- asoc->pathmtu);
+ sctp_assoc_set_pmtu(asoc, asoc->pathmtu ?
+ min_t(int, peer->pathmtu, asoc->pathmtu) :
+ peer->pathmtu);
peer->pmtu_pending = 0;
- asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu);
-
/* The asoc->peer.port might not be meaningful yet, but
* initialize the packet structure anyway.
*/
return match;
}
-/* Is this the association we are looking for? */
-struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
- struct net *net,
- const union sctp_addr *laddr,
- const union sctp_addr *paddr)
-{
- struct sctp_transport *transport;
-
- if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) &&
- (htons(asoc->peer.port) == paddr->v4.sin_port) &&
- net_eq(sock_net(asoc->base.sk), net)) {
- transport = sctp_assoc_lookup_paddr(asoc, paddr);
- if (!transport)
- goto out;
-
- if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr,
- sctp_sk(asoc->base.sk)))
- goto out;
- }
- transport = NULL;
-
-out:
- return transport;
-}
-
/* Do delayed input processing. This is scheduled by sctp_rcv(). */
static void sctp_assoc_bh_rcv(struct work_struct *work)
{
struct sctp_endpoint *ep;
struct sctp_chunk *chunk;
struct sctp_inq *inqueue;
- int state;
+ int first_time = 1; /* is this the first time through the loop */
int error = 0;
+ int state;
/* The association should be held so we should be safe. */
ep = asoc->ep;
state = asoc->state;
subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
+ /* If the first chunk in the packet is AUTH, do special
+ * processing specified in Section 6.3 of SCTP-AUTH spec
+ */
+ if (first_time && subtype.chunk == SCTP_CID_AUTH) {
+ struct sctp_chunkhdr *next_hdr;
+
+ next_hdr = sctp_inq_peek(inqueue);
+ if (!next_hdr)
+ goto normal;
+
+ /* If the next chunk is COOKIE-ECHO, skip the AUTH
+ * chunk while saving a pointer to it so we can do
+ * Authentication later (during cookie-echo
+ * processing).
+ */
+ if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+ chunk->auth_chunk = skb_clone(chunk->skb,
+ GFP_ATOMIC);
+ chunk->auth = 1;
+ continue;
+ }
+ }
+
+normal:
/* SCTP-AUTH, Section 6.3:
* The receiver has a list of chunk types which it expects
* to be received only after an AUTH-chunk. This list has
/* If there is an error on chunk, discard this packet. */
if (error && chunk)
chunk->pdiscard = 1;
+
+ if (first_time)
+ first_time = 0;
}
sctp_association_put(asoc);
}
}
}
+void sctp_assoc_update_frag_point(struct sctp_association *asoc)
+{
+ int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu,
+ sctp_datachk_len(&asoc->stream));
+
+ if (asoc->user_frag)
+ frag = min_t(int, frag, asoc->user_frag);
+
+ frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN -
+ sctp_datachk_len(&asoc->stream));
+
+ asoc->frag_point = SCTP_TRUNC4(frag);
+}
+
+void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu)
+{
+ if (asoc->pathmtu != pmtu) {
+ asoc->pathmtu = pmtu;
+ sctp_assoc_update_frag_point(asoc);
+ }
+
+ pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc,
+ asoc->pathmtu, asoc->frag_point);
+}
+
/* Update the association's pmtu and frag_point by going through all the
* transports. This routine is called when a transport's PMTU has changed.
*/
return;
/* Get the lowest pmtu of all the transports. */
- list_for_each_entry(t, &asoc->peer.transport_addr_list,
- transports) {
+ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) {
if (t->pmtu_pending && t->dst) {
- sctp_transport_update_pmtu(
- t, SCTP_TRUNC4(dst_mtu(t->dst)));
+ sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst));
t->pmtu_pending = 0;
}
if (!pmtu || (t->pathmtu < pmtu))
pmtu = t->pathmtu;
}
- if (pmtu) {
- asoc->pathmtu = pmtu;
- asoc->frag_point = sctp_frag_point(asoc, pmtu);
- }
-
- pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc,
- asoc->pathmtu, asoc->frag_point);
+ sctp_assoc_set_pmtu(asoc, pmtu);
}
/* Should we send a SACK to update our peer? */
struct list_head *pos, *temp;
struct sctp_chunk *chunk;
struct sctp_datamsg *msg;
- struct sctp_sock *sp;
- struct sctp_af *af;
int err;
msg = sctp_datamsg_new(GFP_KERNEL);
/* This is the biggest possible DATA chunk that can fit into
* the packet
*/
- sp = sctp_sk(asoc->base.sk);
- af = sp->pf->af;
- max_data = asoc->pathmtu - af->net_header_len -
- sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) -
- af->ip_options_len(asoc->base.sk);
- max_data = SCTP_TRUNC4(max_data);
+ max_data = asoc->frag_point;
/* If the the peer requested that we authenticate DATA chunks
* we need to account for bundling of the AUTH chunks along with
}
}
- /* Check what's our max considering the above */
- max_data = min_t(size_t, max_data, asoc->frag_point);
-
/* Set first_len and then account for possible bundles on first frag */
first_len = max_data;
skb_pull(chunk->skb, sizeof(*ch));
chunk->subh.v = NULL; /* Subheader is no longer valid. */
- if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) {
+ if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
return 1;
+ if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
+ return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
+
return __sctp_v6_cmp_addr(addr1, addr2);
}
{
struct sctp_transport *tp = packet->transport;
struct sctp_association *asoc = tp->asoc;
+ struct sctp_sock *sp = NULL;
struct sock *sk;
- size_t overhead = sizeof(struct ipv6hdr) + sizeof(struct sctphdr);
pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
packet->vtag = vtag;
/* set packet max_size with pathmtu, then calculate overhead */
packet->max_size = tp->pathmtu;
+
if (asoc) {
- struct sctp_sock *sp = sctp_sk(asoc->base.sk);
- struct sctp_af *af = sp->pf->af;
-
- overhead = af->net_header_len +
- af->ip_options_len(asoc->base.sk);
- overhead += sizeof(struct sctphdr);
- packet->overhead = overhead;
- packet->size = overhead;
- } else {
- packet->overhead = overhead;
- packet->size = overhead;
- return;
+ sk = asoc->base.sk;
+ sp = sctp_sk(sk);
}
+ packet->overhead = sctp_mtu_payload(sp, 0, 0);
+ packet->size = packet->overhead;
+
+ if (!asoc)
+ return;
/* update dst or transport pathmtu if in need */
- sk = asoc->base.sk;
if (!sctp_transport_dst_check(tp)) {
- sctp_transport_route(tp, NULL, sctp_sk(sk));
- if (asoc->param_flags & SPP_PMTUD_ENABLE)
- sctp_assoc_sync_pmtu(asoc);
- } else if (!sctp_transport_pmtu_check(tp)) {
+ sctp_transport_route(tp, NULL, sp);
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
}
/*
* Transmit DATA chunks on the retransmit queue. Upon return from
- * sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which
+ * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which
* need to be transmitted by the caller.
* We assume that pkt->transport has already been set.
*
* The return value is a normal kernel error return value.
*/
-static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
- int rtx_timeout, int *start_timer)
+static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
+ int rtx_timeout, int *start_timer, gfp_t gfp)
{
struct sctp_transport *transport = pkt->transport;
struct sctp_chunk *chunk, *chunk1;
* control chunks are already freed so there
* is nothing we can do.
*/
- sctp_packet_transmit(pkt, GFP_ATOMIC);
+ sctp_packet_transmit(pkt, gfp);
goto redo;
}
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* If we are retransmitting, we should only
* send a single packet.
case SCTP_XMIT_RWND_FULL:
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* Stop sending DATA as there is no more room
* at the receiver.
case SCTP_XMIT_DELAY:
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* Stop sending DATA because of nagle delay. */
done = 1;
sctp_outq_flush(q, 0, gfp);
}
-
-/*
- * Try to flush an outqueue.
- *
- * Description: Send everything in q which we legally can, subject to
- * congestion limitations.
- * * Note: This function can be called from multiple contexts so appropriate
- * locking concerns must be made. Today we use the sock lock to protect
- * this function.
- */
-static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
+static int sctp_packet_singleton(struct sctp_transport *transport,
+ struct sctp_chunk *chunk, gfp_t gfp)
{
- struct sctp_packet *packet;
+ const struct sctp_association *asoc = transport->asoc;
+ const __u16 sport = asoc->base.bind_addr.port;
+ const __u16 dport = asoc->peer.port;
+ const __u32 vtag = asoc->peer.i.init_tag;
struct sctp_packet singleton;
- struct sctp_association *asoc = q->asoc;
- __u16 sport = asoc->base.bind_addr.port;
- __u16 dport = asoc->peer.port;
- __u32 vtag = asoc->peer.i.init_tag;
- struct sctp_transport *transport = NULL;
- struct sctp_transport *new_transport;
- struct sctp_chunk *chunk, *tmp;
- enum sctp_xmit status;
- int error = 0;
- int start_timer = 0;
- int one_packet = 0;
+ sctp_packet_init(&singleton, transport, sport, dport);
+ sctp_packet_config(&singleton, vtag, 0);
+ sctp_packet_append_chunk(&singleton, chunk);
+ return sctp_packet_transmit(&singleton, gfp);
+}
+
+/* Struct to hold the context during sctp outq flush */
+struct sctp_flush_ctx {
+ struct sctp_outq *q;
+ /* Current transport being used. It's NOT the same as curr active one */
+ struct sctp_transport *transport;
/* These transports have chunks to send. */
struct list_head transport_list;
- struct list_head *ltransport;
-
- INIT_LIST_HEAD(&transport_list);
- packet = NULL;
-
- /*
- * 6.10 Bundling
- * ...
- * When bundling control chunks with DATA chunks, an
- * endpoint MUST place control chunks first in the outbound
- * SCTP packet. The transmitter MUST transmit DATA chunks
- * within a SCTP packet in increasing order of TSN.
- * ...
- */
-
- list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
- /* RFC 5061, 5.3
- * F1) This means that until such time as the ASCONF
- * containing the add is acknowledged, the sender MUST
- * NOT use the new IP address as a source for ANY SCTP
- * packet except on carrying an ASCONF Chunk.
- */
- if (asoc->src_out_of_asoc_ok &&
- chunk->chunk_hdr->type != SCTP_CID_ASCONF)
- continue;
-
- list_del_init(&chunk->list);
+ struct sctp_association *asoc;
+ /* Packet on the current transport above */
+ struct sctp_packet *packet;
+ gfp_t gfp;
+};
- /* Pick the right transport to use. */
- new_transport = chunk->transport;
+/* transport: current transport */
+static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
+ struct sctp_chunk *chunk)
+{
+ struct sctp_transport *new_transport = chunk->transport;
- if (!new_transport) {
- /*
- * If we have a prior transport pointer, see if
+ if (!new_transport) {
+ if (!sctp_chunk_is_data(chunk)) {
+ /* If we have a prior transport pointer, see if
* the destination address of the chunk
* matches the destination address of the
* current transport. If not a match, then
* after processing ASCONFs, we may have new
* transports created.
*/
- if (transport &&
- sctp_cmp_addr_exact(&chunk->dest,
- &transport->ipaddr))
- new_transport = transport;
+ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest,
+ &ctx->transport->ipaddr))
+ new_transport = ctx->transport;
else
- new_transport = sctp_assoc_lookup_paddr(asoc,
- &chunk->dest);
+ new_transport = sctp_assoc_lookup_paddr(ctx->asoc,
+ &chunk->dest);
+ }
- /* if we still don't have a new transport, then
- * use the current active path.
- */
- if (!new_transport)
- new_transport = asoc->peer.active_path;
- } else if ((new_transport->state == SCTP_INACTIVE) ||
- (new_transport->state == SCTP_UNCONFIRMED) ||
- (new_transport->state == SCTP_PF)) {
+ /* if we still don't have a new transport, then
+ * use the current active path.
+ */
+ if (!new_transport)
+ new_transport = ctx->asoc->peer.active_path;
+ } else {
+ __u8 type;
+
+ switch (new_transport->state) {
+ case SCTP_INACTIVE:
+ case SCTP_UNCONFIRMED:
+ case SCTP_PF:
/* If the chunk is Heartbeat or Heartbeat Ack,
* send it to chunk->transport, even if it's
* inactive.
*
* ASCONF_ACKs also must be sent to the source.
*/
- if (chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT &&
- chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT_ACK &&
- chunk->chunk_hdr->type != SCTP_CID_ASCONF_ACK)
- new_transport = asoc->peer.active_path;
+ type = chunk->chunk_hdr->type;
+ if (type != SCTP_CID_HEARTBEAT &&
+ type != SCTP_CID_HEARTBEAT_ACK &&
+ type != SCTP_CID_ASCONF_ACK)
+ new_transport = ctx->asoc->peer.active_path;
+ break;
+ default:
+ break;
}
+ }
+
+ /* Are we switching transports? Take care of transport locks. */
+ if (new_transport != ctx->transport) {
+ ctx->transport = new_transport;
+ ctx->packet = &ctx->transport->packet;
- /* Are we switching transports?
- * Take care of transport locks.
+ if (list_empty(&ctx->transport->send_ready))
+ list_add_tail(&ctx->transport->send_ready,
+ &ctx->transport_list);
+
+ sctp_packet_config(ctx->packet,
+ ctx->asoc->peer.i.init_tag,
+ ctx->asoc->peer.ecn_capable);
+ /* We've switched transports, so apply the
+ * Burst limit to the new transport.
*/
- if (new_transport != transport) {
- transport = new_transport;
- if (list_empty(&transport->send_ready)) {
- list_add_tail(&transport->send_ready,
- &transport_list);
- }
- packet = &transport->packet;
- sctp_packet_config(packet, vtag,
- asoc->peer.ecn_capable);
- }
+ sctp_transport_burst_limited(ctx->transport);
+ }
+}
+
+static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
+{
+ struct sctp_chunk *chunk, *tmp;
+ enum sctp_xmit status;
+ int one_packet, error;
+
+ list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) {
+ one_packet = 0;
+
+ /* RFC 5061, 5.3
+ * F1) This means that until such time as the ASCONF
+ * containing the add is acknowledged, the sender MUST
+ * NOT use the new IP address as a source for ANY SCTP
+ * packet except on carrying an ASCONF Chunk.
+ */
+ if (ctx->asoc->src_out_of_asoc_ok &&
+ chunk->chunk_hdr->type != SCTP_CID_ASCONF)
+ continue;
+
+ list_del_init(&chunk->list);
+
+ /* Pick the right transport to use. Should always be true for
+ * the first chunk as we don't have a transport by then.
+ */
+ sctp_outq_select_transport(ctx, chunk);
switch (chunk->chunk_hdr->type) {
- /*
- * 6.10 Bundling
+ /* 6.10 Bundling
* ...
* An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN
* COMPLETE with any other chunks. [Send them immediately.]
case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
case SCTP_CID_SHUTDOWN_COMPLETE:
- sctp_packet_init(&singleton, transport, sport, dport);
- sctp_packet_config(&singleton, vtag, 0);
- sctp_packet_append_chunk(&singleton, chunk);
- error = sctp_packet_transmit(&singleton, gfp);
+ error = sctp_packet_singleton(ctx->transport, chunk,
+ ctx->gfp);
if (error < 0) {
- asoc->base.sk->sk_err = -error;
+ ctx->asoc->base.sk->sk_err = -error;
return;
}
break;
case SCTP_CID_ABORT:
if (sctp_test_T_bit(chunk))
- packet->vtag = asoc->c.my_vtag;
+ ctx->packet->vtag = ctx->asoc->c.my_vtag;
/* fallthru */
+
/* The following chunks are "response" chunks, i.e.
* they are generated in response to something we
* received. If we are sending these, then we can
case SCTP_CID_FWD_TSN:
case SCTP_CID_I_FWD_TSN:
case SCTP_CID_RECONF:
- status = sctp_packet_transmit_chunk(packet, chunk,
- one_packet, gfp);
- if (status != SCTP_XMIT_OK) {
+ status = sctp_packet_transmit_chunk(ctx->packet, chunk,
+ one_packet, ctx->gfp);
+ if (status != SCTP_XMIT_OK) {
/* put the chunk back */
- list_add(&chunk->list, &q->control_chunk_list);
+ list_add(&chunk->list, &ctx->q->control_chunk_list);
break;
}
- asoc->stats.octrlchunks++;
+ ctx->asoc->stats.octrlchunks++;
/* PR-SCTP C5) If a FORWARD TSN is sent, the
* sender MUST assure that at least one T3-rtx
* timer is running.
*/
if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN ||
chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) {
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
}
- if (chunk == asoc->strreset_chunk)
- sctp_transport_reset_reconf_timer(transport);
+ if (chunk == ctx->asoc->strreset_chunk)
+ sctp_transport_reset_reconf_timer(ctx->transport);
break;
BUG();
}
}
+}
- if (q->asoc->src_out_of_asoc_ok)
- goto sctp_flush_out;
+/* Returns false if new data shouldn't be sent */
+static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx,
+ int rtx_timeout)
+{
+ int error, start_timer = 0;
+
+ if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
+ return false;
+
+ if (ctx->transport != ctx->asoc->peer.retran_path) {
+ /* Switch transports & prepare the packet. */
+ ctx->transport = ctx->asoc->peer.retran_path;
+ ctx->packet = &ctx->transport->packet;
+
+ if (list_empty(&ctx->transport->send_ready))
+ list_add_tail(&ctx->transport->send_ready,
+ &ctx->transport_list);
+
+ sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag,
+ ctx->asoc->peer.ecn_capable);
+ }
+
+ error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout,
+ &start_timer, ctx->gfp);
+ if (error < 0)
+ ctx->asoc->base.sk->sk_err = -error;
+
+ if (start_timer) {
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
+ }
+
+ /* This can happen on COOKIE-ECHO resend. Only
+ * one chunk can get bundled with a COOKIE-ECHO.
+ */
+ if (ctx->packet->has_cookie_echo)
+ return false;
+
+ /* Don't send new data if there is still data
+ * waiting to retransmit.
+ */
+ if (!list_empty(&ctx->q->retransmit))
+ return false;
+
+ return true;
+}
+
+static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
+ int rtx_timeout)
+{
+ struct sctp_chunk *chunk;
+ enum sctp_xmit status;
/* Is it OK to send data chunks? */
- switch (asoc->state) {
+ switch (ctx->asoc->state) {
case SCTP_STATE_COOKIE_ECHOED:
/* Only allow bundling when this packet has a COOKIE-ECHO
* chunk.
*/
- if (!packet || !packet->has_cookie_echo)
- break;
+ if (!ctx->packet || !ctx->packet->has_cookie_echo)
+ return;
/* fallthru */
case SCTP_STATE_ESTABLISHED:
case SCTP_STATE_SHUTDOWN_PENDING:
case SCTP_STATE_SHUTDOWN_RECEIVED:
- /*
- * RFC 2960 6.1 Transmission of DATA Chunks
- *
- * C) When the time comes for the sender to transmit,
- * before sending new DATA chunks, the sender MUST
- * first transmit any outstanding DATA chunks which
- * are marked for retransmission (limited by the
- * current cwnd).
- */
- if (!list_empty(&q->retransmit)) {
- if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
- goto sctp_flush_out;
- if (transport == asoc->peer.retran_path)
- goto retran;
-
- /* Switch transports & prepare the packet. */
-
- transport = asoc->peer.retran_path;
+ break;
- if (list_empty(&transport->send_ready)) {
- list_add_tail(&transport->send_ready,
- &transport_list);
- }
+ default:
+ /* Do nothing. */
+ return;
+ }
- packet = &transport->packet;
- sctp_packet_config(packet, vtag,
- asoc->peer.ecn_capable);
- retran:
- error = sctp_outq_flush_rtx(q, packet,
- rtx_timeout, &start_timer);
- if (error < 0)
- asoc->base.sk->sk_err = -error;
+ /* RFC 2960 6.1 Transmission of DATA Chunks
+ *
+ * C) When the time comes for the sender to transmit,
+ * before sending new DATA chunks, the sender MUST
+ * first transmit any outstanding DATA chunks which
+ * are marked for retransmission (limited by the
+ * current cwnd).
+ */
+ if (!list_empty(&ctx->q->retransmit) &&
+ !sctp_outq_flush_rtx(ctx, rtx_timeout))
+ return;
- if (start_timer) {
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
- }
+ /* Apply Max.Burst limitation to the current transport in
+ * case it will be used for new data. We are going to
+ * rest it before we return, but we want to apply the limit
+ * to the currently queued data.
+ */
+ if (ctx->transport)
+ sctp_transport_burst_limited(ctx->transport);
- /* This can happen on COOKIE-ECHO resend. Only
- * one chunk can get bundled with a COOKIE-ECHO.
- */
- if (packet->has_cookie_echo)
- goto sctp_flush_out;
+ /* Finally, transmit new packets. */
+ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) {
+ __u32 sid = ntohs(chunk->subh.data_hdr->stream);
- /* Don't send new data if there is still data
- * waiting to retransmit.
- */
- if (!list_empty(&q->retransmit))
- goto sctp_flush_out;
+ /* Has this chunk expired? */
+ if (sctp_chunk_abandoned(chunk)) {
+ sctp_sched_dequeue_done(ctx->q, chunk);
+ sctp_chunk_fail(chunk, 0);
+ sctp_chunk_free(chunk);
+ continue;
}
- /* Apply Max.Burst limitation to the current transport in
- * case it will be used for new data. We are going to
- * rest it before we return, but we want to apply the limit
- * to the currently queued data.
- */
- if (transport)
- sctp_transport_burst_limited(transport);
-
- /* Finally, transmit new packets. */
- while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
- __u32 sid = ntohs(chunk->subh.data_hdr->stream);
-
- /* Has this chunk expired? */
- if (sctp_chunk_abandoned(chunk)) {
- sctp_sched_dequeue_done(q, chunk);
- sctp_chunk_fail(chunk, 0);
- sctp_chunk_free(chunk);
- continue;
- }
+ if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
+ sctp_outq_head_data(ctx->q, chunk);
+ break;
+ }
- if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
- sctp_outq_head_data(q, chunk);
- goto sctp_flush_out;
- }
+ sctp_outq_select_transport(ctx, chunk);
- /* If there is a specified transport, use it.
- * Otherwise, we want to use the active path.
+ pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n",
+ __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ?
+ sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
+ "illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
+ chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
+ refcount_read(&chunk->skb->users) : -1);
+
+ /* Add the chunk to the packet. */
+ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0,
+ ctx->gfp);
+ if (status != SCTP_XMIT_OK) {
+ /* We could not append this chunk, so put
+ * the chunk back on the output queue.
*/
- new_transport = chunk->transport;
- if (!new_transport ||
- ((new_transport->state == SCTP_INACTIVE) ||
- (new_transport->state == SCTP_UNCONFIRMED) ||
- (new_transport->state == SCTP_PF)))
- new_transport = asoc->peer.active_path;
- if (new_transport->state == SCTP_UNCONFIRMED) {
- WARN_ONCE(1, "Attempt to send packet on unconfirmed path.");
- sctp_sched_dequeue_done(q, chunk);
- sctp_chunk_fail(chunk, 0);
- sctp_chunk_free(chunk);
- continue;
- }
-
- /* Change packets if necessary. */
- if (new_transport != transport) {
- transport = new_transport;
+ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n",
+ __func__, ntohl(chunk->subh.data_hdr->tsn),
+ status);
- /* Schedule to have this transport's
- * packet flushed.
- */
- if (list_empty(&transport->send_ready)) {
- list_add_tail(&transport->send_ready,
- &transport_list);
- }
-
- packet = &transport->packet;
- sctp_packet_config(packet, vtag,
- asoc->peer.ecn_capable);
- /* We've switched transports, so apply the
- * Burst limit to the new transport.
- */
- sctp_transport_burst_limited(transport);
- }
-
- pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
- "skb->users:%d\n",
- __func__, q, chunk, chunk && chunk->chunk_hdr ?
- sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
- "illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
- chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
- refcount_read(&chunk->skb->users) : -1);
-
- /* Add the chunk to the packet. */
- status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp);
-
- switch (status) {
- case SCTP_XMIT_PMTU_FULL:
- case SCTP_XMIT_RWND_FULL:
- case SCTP_XMIT_DELAY:
- /* We could not append this chunk, so put
- * the chunk back on the output queue.
- */
- pr_debug("%s: could not transmit tsn:0x%x, status:%d\n",
- __func__, ntohl(chunk->subh.data_hdr->tsn),
- status);
-
- sctp_outq_head_data(q, chunk);
- goto sctp_flush_out;
-
- case SCTP_XMIT_OK:
- /* The sender is in the SHUTDOWN-PENDING state,
- * The sender MAY set the I-bit in the DATA
- * chunk header.
- */
- if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
- chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
- if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
- asoc->stats.ouodchunks++;
- else
- asoc->stats.oodchunks++;
-
- /* Only now it's safe to consider this
- * chunk as sent, sched-wise.
- */
- sctp_sched_dequeue_done(q, chunk);
-
- break;
+ sctp_outq_head_data(ctx->q, chunk);
+ break;
+ }
- default:
- BUG();
- }
+ /* The sender is in the SHUTDOWN-PENDING state,
+ * The sender MAY set the I-bit in the DATA
+ * chunk header.
+ */
+ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
+ chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
+ if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
+ ctx->asoc->stats.ouodchunks++;
+ else
+ ctx->asoc->stats.oodchunks++;
- /* BUG: We assume that the sctp_packet_transmit()
- * call below will succeed all the time and add the
- * chunk to the transmitted list and restart the
- * timers.
- * It is possible that the call can fail under OOM
- * conditions.
- *
- * Is this really a problem? Won't this behave
- * like a lost TSN?
- */
- list_add_tail(&chunk->transmitted_list,
- &transport->transmitted);
+ /* Only now it's safe to consider this
+ * chunk as sent, sched-wise.
+ */
+ sctp_sched_dequeue_done(ctx->q, chunk);
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ list_add_tail(&chunk->transmitted_list,
+ &ctx->transport->transmitted);
- /* Only let one DATA chunk get bundled with a
- * COOKIE-ECHO chunk.
- */
- if (packet->has_cookie_echo)
- goto sctp_flush_out;
- }
- break;
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
- default:
- /* Do nothing. */
- break;
+ /* Only let one DATA chunk get bundled with a
+ * COOKIE-ECHO chunk.
+ */
+ if (ctx->packet->has_cookie_echo)
+ break;
}
+}
-sctp_flush_out:
+static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
+{
+ struct list_head *ltransport;
+ struct sctp_packet *packet;
+ struct sctp_transport *t;
+ int error = 0;
- /* Before returning, examine all the transports touched in
- * this call. Right now, we bluntly force clear all the
- * transports. Things might change after we implement Nagle.
- * But such an examination is still required.
- *
- * --xguo
- */
- while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) {
- struct sctp_transport *t = list_entry(ltransport,
- struct sctp_transport,
- send_ready);
+ while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) {
+ t = list_entry(ltransport, struct sctp_transport, send_ready);
packet = &t->packet;
if (!sctp_packet_empty(packet)) {
- error = sctp_packet_transmit(packet, gfp);
+ error = sctp_packet_transmit(packet, ctx->gfp);
if (error < 0)
- asoc->base.sk->sk_err = -error;
+ ctx->q->asoc->base.sk->sk_err = -error;
}
/* Clear the burst limited state, if any */
}
}
+/* Try to flush an outqueue.
+ *
+ * Description: Send everything in q which we legally can, subject to
+ * congestion limitations.
+ * * Note: This function can be called from multiple contexts so appropriate
+ * locking concerns must be made. Today we use the sock lock to protect
+ * this function.
+ */
+
+static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
+{
+ struct sctp_flush_ctx ctx = {
+ .q = q,
+ .transport = NULL,
+ .transport_list = LIST_HEAD_INIT(ctx.transport_list),
+ .asoc = q->asoc,
+ .packet = NULL,
+ .gfp = gfp,
+ };
+
+ /* 6.10 Bundling
+ * ...
+ * When bundling control chunks with DATA chunks, an
+ * endpoint MUST place control chunks first in the outbound
+ * SCTP packet. The transmitter MUST transmit DATA chunks
+ * within a SCTP packet in increasing order of TSN.
+ * ...
+ */
+
+ sctp_outq_flush_ctrl(&ctx);
+
+ if (q->asoc->src_out_of_asoc_ok)
+ goto sctp_flush_out;
+
+ sctp_outq_flush_data(&ctx, rtx_timeout);
+
+sctp_flush_out:
+
+ sctp_outq_flush_transports(&ctx);
+}
+
/* Update unack_data based on the incoming SACK chunk */
static void sctp_sack_update_unack_data(struct sctp_association *assoc,
struct sctp_sackhdr *sack)
* the outstanding bytes for this chunk, so only
* count bytes associated with a transport.
*/
- if (transport) {
+ if (transport && !tchunk->tsn_gap_acked) {
/* If this chunk is being used for RTT
* measurement, calculate the RTT and update
* the RTO using this value.
* first instance of the packet or a later
* instance).
*/
- if (!tchunk->tsn_gap_acked &&
- !sctp_chunk_retransmitted(tchunk) &&
+ if (!sctp_chunk_retransmitted(tchunk) &&
tchunk->rtt_in_progress) {
tchunk->rtt_in_progress = 0;
rtt = jiffies - tchunk->sent_at;
sctp_transport_update_rto(transport,
rtt);
}
+
+ if (TSN_lte(tsn, sack_ctsn)) {
+ /*
+ * SFR-CACC algorithm:
+ * 2) If the SACK contains gap acks
+ * and the flag CHANGEOVER_ACTIVE is
+ * set the receiver of the SACK MUST
+ * take the following action:
+ *
+ * B) For each TSN t being acked that
+ * has not been acked in any SACK so
+ * far, set cacc_saw_newack to 1 for
+ * the destination that the TSN was
+ * sent to.
+ */
+ if (sack->num_gap_ack_blocks &&
+ q->asoc->peer.primary_path->cacc.
+ changeover_active)
+ transport->cacc.cacc_saw_newack
+ = 1;
+ }
}
/* If the chunk hasn't been marked as ACKED,
restart_timer = 1;
forward_progress = true;
- if (!tchunk->tsn_gap_acked) {
- /*
- * SFR-CACC algorithm:
- * 2) If the SACK contains gap acks
- * and the flag CHANGEOVER_ACTIVE is
- * set the receiver of the SACK MUST
- * take the following action:
- *
- * B) For each TSN t being acked that
- * has not been acked in any SACK so
- * far, set cacc_saw_newack to 1 for
- * the destination that the TSN was
- * sent to.
- */
- if (transport &&
- sack->num_gap_ack_blocks &&
- q->asoc->peer.primary_path->cacc.
- changeover_active)
- transport->cacc.cacc_saw_newack
- = 1;
- }
-
list_add_tail(&tchunk->transmitted_list,
&q->sacked);
} else {
if (TSN_lte(tsn, ctsn))
goto pass;
- /* 3.3.4 Selective Acknowledgement (SACK) (3):
+ /* 3.3.4 Selective Acknowledgment (SACK) (3):
*
* Gap Ack Blocks:
* These fields contain the Gap Ack Blocks. They are repeated
gfp_t gfp);
static void *sctp_addto_param(struct sctp_chunk *chunk, int len,
const void *data);
-static void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len,
- const void *data);
/* Control chunk destructor */
static void sctp_control_release_owner(struct sk_buff *skb)
cpu_to_be16(sizeof(struct sctp_paramhdr)),
};
-/* A helper to initialize an op error inside a
- * provided chunk, as most cause codes will be embedded inside an
- * abort chunk.
+/* A helper to initialize an op error inside a provided chunk, as most
+ * cause codes will be embedded inside an abort chunk.
*/
-void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code,
- size_t paylen)
+int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code,
+ size_t paylen)
{
struct sctp_errhdr err;
__u16 len;
/* Cause code constants are now defined in network order. */
err.cause = cause_code;
len = sizeof(err) + paylen;
- err.length = htons(len);
- chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err);
-}
-
-/* A helper to initialize an op error inside a
- * provided chunk, as most cause codes will be embedded inside an
- * abort chunk. Differs from sctp_init_cause in that it won't oops
- * if there isn't enough space in the op error chunk
- */
-static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code,
- size_t paylen)
-{
- struct sctp_errhdr err;
- __u16 len;
-
- /* Cause code constants are now defined in network order. */
- err.cause = cause_code;
- len = sizeof(err) + paylen;
- err.length = htons(len);
+ err.length = htons(len);
if (skb_tailroom(chunk->skb) < len)
return -ENOSPC;
- chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, sizeof(err), &err);
+ chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err);
return 0;
}
+
/* 3.3.2 Initiation (INIT) (1)
*
* This chunk is used to initiate a SCTP association between two
* association. This reports on which TSN's we've seen to date,
* including duplicates and gaps.
*/
-struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
+struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc)
{
struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map;
- struct sctp_association *aptr = (struct sctp_association *)asoc;
struct sctp_gap_ack_block gabs[SCTP_MAX_GABS];
__u16 num_gabs, num_dup_tsns;
struct sctp_transport *trans;
/* Add the duplicate TSN information. */
if (num_dup_tsns) {
- aptr->stats.idupchunks += num_dup_tsns;
+ asoc->stats.idupchunks += num_dup_tsns;
sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns,
sctp_tsnmap_get_dups(map));
}
* association so no transport will match after a wrap event like this,
* Until the next sack
*/
- if (++aptr->peer.sack_generation == 0) {
+ if (++asoc->peer.sack_generation == 0) {
list_for_each_entry(trans, &asoc->peer.transport_addr_list,
transports)
trans->sack_generation = 0;
- aptr->peer.sack_generation = 1;
+ asoc->peer.sack_generation = 1;
}
nodata:
return retval;
const struct sctp_association *asoc,
const struct sctp_chunk *chunk)
{
- static const char error[] = "Association exceeded its max_retans count";
+ static const char error[] = "Association exceeded its max_retrans count";
size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr);
struct sctp_chunk *retval;
return retval;
}
-/* Create an Operation Error chunk of a fixed size,
- * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT)
- * This is a helper function to allocate an error chunk for
- * for those invalid parameter codes in which we may not want
- * to report all the errors, if the incoming chunk is large
+/* Create an Operation Error chunk of a fixed size, specifically,
+ * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads.
+ * This is a helper function to allocate an error chunk for for those
+ * invalid parameter codes in which we may not want to report all the
+ * errors, if the incoming chunk is large. If it can't fit in a single
+ * packet, we ignore it.
*/
-static inline struct sctp_chunk *sctp_make_op_error_fixed(
+static inline struct sctp_chunk *sctp_make_op_error_limited(
const struct sctp_association *asoc,
const struct sctp_chunk *chunk)
{
- size_t size = asoc ? asoc->pathmtu : 0;
+ size_t size = SCTP_DEFAULT_MAXSEGMENT;
+ struct sctp_sock *sp = NULL;
- if (!size)
- size = SCTP_DEFAULT_MAXSEGMENT;
+ if (asoc) {
+ size = min_t(size_t, size, asoc->pathmtu);
+ sp = sctp_sk(asoc->base.sk);
+ }
+
+ size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr));
return sctp_make_op_error_space(asoc, chunk, size);
}
return target;
}
-/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient
- * space in the chunk
- */
-static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
- int len, const void *data)
-{
- if (skb_tailroom(chunk->skb) >= len)
- return sctp_addto_chunk(chunk, len, data);
- else
- return NULL;
-}
-
/* Append bytes from user space to the end of a chunk. Will panic if
* chunk is not big enough.
* Returns a kernel err value.
kt = ktime_get_real();
if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
+ suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration));
+ __be32 n = htonl(usecs);
+
/*
* Section 3.3.10.3 Stale Cookie Error (3)
*
* Stale Cookie Error: Indicates the receipt of a valid State
* Cookie that has expired.
*/
- len = ntohs(chunk->chunk_hdr->length);
- *errp = sctp_make_op_error_space(asoc, chunk, len);
- if (*errp) {
- suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration));
- __be32 n = htonl(usecs);
-
- sctp_init_cause(*errp, SCTP_ERROR_STALE_COOKIE,
- sizeof(n));
- sctp_addto_chunk(*errp, sizeof(n), &n);
+ *errp = sctp_make_op_error(asoc, chunk,
+ SCTP_ERROR_STALE_COOKIE, &n,
+ sizeof(n), 0);
+ if (*errp)
*error = -SCTP_IERROR_STALE_COOKIE;
- } else
+ else
*error = -SCTP_IERROR_NOMEM;
goto fail;
if (*errp)
sctp_chunk_free(*errp);
- *errp = sctp_make_op_error_space(asoc, chunk, len);
-
- if (*errp) {
- sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len);
- sctp_addto_chunk(*errp, len, param.v);
- }
+ *errp = sctp_make_op_error(asoc, chunk, SCTP_ERROR_DNS_FAILED,
+ param.v, len, 0);
/* Stop processing this chunk. */
return 0;
/* Make an ERROR chunk, preparing enough room for
* returning multiple unknown parameters.
*/
- if (NULL == *errp)
- *errp = sctp_make_op_error_fixed(asoc, chunk);
-
- if (*errp) {
- if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM,
- SCTP_PAD4(ntohs(param.p->length))))
- sctp_addto_chunk_fixed(*errp,
- SCTP_PAD4(ntohs(param.p->length)),
- param.v);
- } else {
- /* If there is no memory for generating the ERROR
- * report as specified, an ABORT will be triggered
- * to the peer and the association won't be
- * established.
- */
- retval = SCTP_IERROR_NOMEM;
+ if (!*errp) {
+ *errp = sctp_make_op_error_limited(asoc, chunk);
+ if (!*errp) {
+ /* If there is no memory for generating the
+ * ERROR report as specified, an ABORT will be
+ * triggered to the peer and the association
+ * won't be established.
+ */
+ retval = SCTP_IERROR_NOMEM;
+ break;
+ }
}
+
+ if (!sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM,
+ ntohs(param.p->length)))
+ sctp_addto_chunk(*errp, ntohs(param.p->length),
+ param.v);
break;
default:
break;
* MUST be aborted. The ABORT chunk SHOULD contain the error
* cause 'Protocol Violation'.
*/
- if (SCTP_AUTH_RANDOM_LENGTH !=
- ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) {
+ if (SCTP_AUTH_RANDOM_LENGTH != ntohs(param.p->length) -
+ sizeof(struct sctp_paramhdr)) {
sctp_process_inv_paramlength(asoc, param.p,
- chunk, err_chunk);
+ chunk, err_chunk);
retval = SCTP_IERROR_ABORT;
}
break;
struct sctp_cmd_seq *commands);
static enum sctp_ierror sctp_sf_authenticate(
- struct net *net,
- const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
- const union sctp_subtype type,
struct sctp_chunk *chunk);
static enum sctp_disposition __sctp_sf_do_9_1_abort(
return SCTP_DISPOSITION_CONSUME;
}
+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
+ const struct sctp_association *asoc)
+{
+ struct sctp_chunk auth;
+
+ if (!chunk->auth_chunk)
+ return true;
+
+ /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
+ * is supposed to be authenticated and we have to do delayed
+ * authentication. We've just recreated the association using
+ * the information in the cookie and now it's much easier to
+ * do the authentication.
+ */
+
+ /* Make sure that we and the peer are AUTH capable */
+ if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+ return false;
+
+ /* set-up our fake chunk so that we can process it */
+ auth.skb = chunk->auth_chunk;
+ auth.asoc = chunk->asoc;
+ auth.sctp_hdr = chunk->sctp_hdr;
+ auth.chunk_hdr = (struct sctp_chunkhdr *)
+ skb_push(chunk->auth_chunk,
+ sizeof(struct sctp_chunkhdr));
+ skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
+ auth.transport = chunk->transport;
+
+ return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
+}
+
/*
* Respond to a normal COOKIE ECHO chunk.
* We are the side that is being asked for an association.
if (error)
goto nomem_init;
- /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
- * is supposed to be authenticated and we have to do delayed
- * authentication. We've just recreated the association using
- * the information in the cookie and now it's much easier to
- * do the authentication.
- */
- if (chunk->auth_chunk) {
- struct sctp_chunk auth;
- enum sctp_ierror ret;
-
- /* Make sure that we and the peer are AUTH capable */
- if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
- sctp_association_free(new_asoc);
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
- }
-
- /* set-up our fake chunk so that we can process it */
- auth.skb = chunk->auth_chunk;
- auth.asoc = chunk->asoc;
- auth.sctp_hdr = chunk->sctp_hdr;
- auth.chunk_hdr = (struct sctp_chunkhdr *)
- skb_push(chunk->auth_chunk,
- sizeof(struct sctp_chunkhdr));
- skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
- auth.transport = chunk->transport;
-
- ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
- if (ret != SCTP_IERROR_NO_ERROR) {
- sctp_association_free(new_asoc);
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
- }
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
repl = sctp_make_cookie_ack(new_asoc, chunk);
GFP_ATOMIC))
goto nomem;
+ if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+ goto nomem;
+
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Make sure no new addresses are being added during the
* restart. Though this is a pretty complicated attack
* since you'd have to get inside the cookie.
*/
- if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
+ if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
return SCTP_DISPOSITION_CONSUME;
- }
/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
* the peer has restarted (Action A), it MUST NOT setup a new
GFP_ATOMIC))
goto nomem;
+ if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+ goto nomem;
+
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Update the content of current association. */
sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
* a COOKIE ACK.
*/
+ if (!sctp_auth_chunk_verify(net, chunk, asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Don't accidentally move back into established state. */
if (asoc->state < SCTP_STATE_ESTABLISHED) {
sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
}
}
- repl = sctp_make_cookie_ack(new_asoc, chunk);
+ repl = sctp_make_cookie_ack(asoc, chunk);
if (!repl)
goto nomem;
* The return value is the disposition of the chunk.
*/
static enum sctp_ierror sctp_sf_authenticate(
- struct net *net,
- const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
- const union sctp_subtype type,
struct sctp_chunk *chunk)
{
struct sctp_shared_key *sh_key = NULL;
commands);
auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
- error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
+ error = sctp_sf_authenticate(asoc, chunk);
switch (error) {
case SCTP_IERROR_AUTH_BAD_HMAC:
/* Generate the ERROR chunk and discard the rest
list_for_each_entry(trans,
&asoc->peer.transport_addr_list, transports) {
- /* Clear the source and route cache */
- sctp_transport_dst_release(trans);
trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
2*asoc->pathmtu, 4380));
trans->ssthresh = asoc->peer.i.a_rwnd;
trans->rto = asoc->rto_initial;
sctp_max_rto(asoc, trans);
trans->rtt = trans->srtt = trans->rttvar = 0;
+ /* Clear the source and route cache */
sctp_transport_route(trans, NULL,
- sctp_sk(asoc->base.sk));
+ sctp_sk(asoc->base.sk));
}
}
retval = sctp_send_asconf(asoc, chunk);
*/
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
- sctp_transport_dst_release(transport);
sctp_transport_route(transport, NULL,
sctp_sk(asoc->base.sk));
}
struct sctp_sndrcvinfo *sinfo)
{
struct sock *sk = asoc->base.sk;
+ struct sctp_sock *sp = sctp_sk(sk);
struct net *net = sock_net(sk);
struct sctp_datamsg *datamsg;
bool wait_connect = false;
goto err;
}
- if (sctp_sk(sk)->disable_fragments && msg_len > asoc->frag_point) {
+ if (sp->disable_fragments && msg_len > asoc->frag_point) {
err = -EMSGSIZE;
goto err;
}
- if (asoc->pmtu_pending)
- sctp_assoc_pending_pmtu(asoc);
+ if (asoc->pmtu_pending) {
+ if (sp->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
+ asoc->pmtu_pending = 0;
+ }
if (sctp_wspace(asoc) < msg_len)
sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
if (err)
goto err;
- if (sctp_sk(sk)->strm_interleave) {
+ if (sp->strm_interleave) {
timeo = sock_sndtimeo(sk, 0);
err = sctp_wait_for_connect(asoc, &timeo);
if (err)
trans->pathmtu = params->spp_pathmtu;
sctp_assoc_sync_pmtu(asoc);
} else if (asoc) {
- asoc->pathmtu = params->spp_pathmtu;
+ sctp_assoc_set_pmtu(asoc, params->spp_pathmtu);
} else {
sp->pathmtu = params->spp_pathmtu;
}
static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen)
{
struct sctp_sock *sp = sctp_sk(sk);
- struct sctp_af *af = sp->pf->af;
struct sctp_assoc_value params;
struct sctp_association *asoc;
int val;
return -EINVAL;
}
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+
if (val) {
int min_len, max_len;
+ __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) :
+ sizeof(struct sctp_data_chunk);
- min_len = SCTP_DEFAULT_MINSEGMENT - af->net_header_len;
- min_len -= af->ip_options_len(sk);
- min_len -= sizeof(struct sctphdr) +
- sizeof(struct sctp_data_chunk);
-
- max_len = SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_data_chunk);
+ min_len = sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT,
+ datasize);
+ max_len = SCTP_MAX_CHUNK_LEN - datasize;
if (val < min_len || val > max_len)
return -EINVAL;
}
- asoc = sctp_id2assoc(sk, params.assoc_id);
if (asoc) {
- if (val == 0) {
- val = asoc->pathmtu - af->net_header_len;
- val -= af->ip_options_len(sk);
- val -= sizeof(struct sctphdr) +
- sctp_datachk_len(&asoc->stream);
- }
asoc->user_frag = val;
- asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu);
+ sctp_assoc_update_frag_point(asoc);
} else {
if (params.assoc_id && sctp_style(sk, UDP))
return -EINVAL;
new->out = NULL;
new->in = NULL;
+ new->outcnt = 0;
+ new->incnt = 0;
}
static int sctp_send_reconf(struct sctp_association *asoc,
&transport->fl, sk);
}
- if (transport->dst) {
- transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst));
- } else
+ if (transport->param_flags & SPP_PMTUD_DISABLE) {
+ struct sctp_association *asoc = transport->asoc;
+
+ if (!transport->pathmtu && asoc && asoc->pathmtu)
+ transport->pathmtu = asoc->pathmtu;
+ if (transport->pathmtu)
+ return;
+ }
+
+ if (transport->dst)
+ transport->pathmtu = sctp_dst_mtu(transport->dst);
+ else
transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
}
struct sctp_association *asoc = transport->asoc;
struct sctp_af *af = transport->af_specific;
+ sctp_transport_dst_release(transport);
af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt));
if (saddr)
else
af->get_saddr(opt, transport, &transport->fl);
- if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) {
- return;
- }
- if (transport->dst) {
- transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst));
+ sctp_transport_pmtu(transport, sctp_opt2sk(opt));
- /* Initialize sk->sk_rcv_saddr, if the transport is the
- * association's active path for getsockname().
- */
- if (asoc && (!asoc->peer.primary_path ||
- (transport == asoc->peer.active_path)))
- opt->pf->to_sk_saddr(&transport->saddr,
- asoc->base.sk);
- } else
- transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
+ /* Initialize sk->sk_rcv_saddr, if the transport is the
+ * association's active path for getsockname().
+ */
+ if (transport->dst && asoc &&
+ (!asoc->peer.primary_path || transport == asoc->peer.active_path))
+ opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk);
}
/* Hold a reference to a transport. */
return event;
fail_mark:
- sctp_chunk_put(chunk);
kfree_skb(skb);
fail:
return NULL;
#include <net/sock.h>
#include <net/tcp.h>
#include <net/smc.h>
+#include <asm/ioctls.h>
#include "smc.h"
#include "smc_clc.h"
* creation
*/
-struct smc_lgr_list smc_lgr_list = { /* established link groups */
- .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
- .list = LIST_HEAD_INIT(smc_lgr_list.list),
-};
-
static void smc_tcp_listen_work(struct work_struct *);
static void smc_set_keepalive(struct sock *sk, int val)
sk->sk_protocol = protocol;
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+ INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
spin_lock_init(&smc->accept_q_lock);
+ spin_lock_init(&smc->conn.send_lock);
sk->sk_prot->hash(sk);
sk_refcnt_debug_inc(sk);
smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
}
+/* register a new rmb, optionally send confirm_rkey msg to register with peer */
+static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc,
+ bool conf_rkey)
+{
+ /* register memory region for new rmb */
+ if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+ rmb_desc->regerr = 1;
+ return -EFAULT;
+ }
+ if (!conf_rkey)
+ return 0;
+ /* exchange confirm_rkey msg with peer */
+ if (smc_llc_do_confirm_rkey(link, rmb_desc)) {
+ rmb_desc->regerr = 1;
+ return -EFAULT;
+ }
+ return 0;
+}
+
static int smc_clnt_conf_first_link(struct smc_sock *smc)
{
+ struct net *net = sock_net(smc->clcsock->sk);
struct smc_link_group *lgr = smc->conn.lgr;
struct smc_link *link;
int rest;
smc_wr_remember_qp_attr(link);
- rc = smc_wr_reg_send(link,
- smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc)
+ if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
return SMC_CLC_DECL_INTERR;
/* send CONFIRM LINK response over RoCE fabric */
if (rc < 0)
return SMC_CLC_DECL_TCL;
- link->state = SMC_LNK_ACTIVE;
+ smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
return 0;
}
static void smc_conn_save_peer_info(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *clc)
{
- smc->conn.peer_conn_idx = clc->conn_idx;
+ int bufsize = smc_uncompress_bufsize(clc->rmbe_size);
+
+ smc->conn.peer_rmbe_idx = clc->rmbe_idx;
smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token);
- smc->conn.peer_rmbe_size = smc_uncompress_bufsize(clc->rmbe_size);
+ smc->conn.peer_rmbe_size = bufsize;
atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
+ smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
}
static void smc_link_save_peer_info(struct smc_link *link,
link->peer_mtu = clc->qp_mtu;
}
-/* setup for RDMA connection of client */
-static int smc_connect_rdma(struct smc_sock *smc)
+/* fall back during connect */
+static int smc_connect_fallback(struct smc_sock *smc)
{
- struct smc_clc_msg_accept_confirm aclc;
- int local_contact = SMC_FIRST_CONTACT;
- struct smc_ib_device *smcibdev;
- struct smc_link *link;
- u8 srv_first_contact;
- int reason_code = 0;
- int rc = 0;
- u8 ibport;
+ smc->use_fallback = true;
+ smc_copy_sock_settings_to_clc(smc);
+ if (smc->sk.sk_state == SMC_INIT)
+ smc->sk.sk_state = SMC_ACTIVE;
+ return 0;
+}
- sock_hold(&smc->sk); /* sock put in passive closing */
+/* decline and fall back during connect */
+static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
+{
+ int rc;
- if (!tcp_sk(smc->clcsock->sk)->syn_smc) {
- /* peer has not signalled SMC-capability */
- smc->use_fallback = true;
- goto out_connected;
+ if (reason_code < 0) /* error, fallback is not possible */
+ return reason_code;
+ if (reason_code != SMC_CLC_DECL_REPLY) {
+ rc = smc_clc_send_decline(smc, reason_code);
+ if (rc < 0)
+ return rc;
}
+ return smc_connect_fallback(smc);
+}
- /* IPSec connections opt out of SMC-R optimizations */
- if (using_ipsec(smc)) {
- reason_code = SMC_CLC_DECL_IPSEC;
- goto decline_rdma;
- }
+/* abort connecting */
+static int smc_connect_abort(struct smc_sock *smc, int reason_code,
+ int local_contact)
+{
+ if (local_contact == SMC_FIRST_CONTACT)
+ smc_lgr_forget(smc->conn.lgr);
+ mutex_unlock(&smc_create_lgr_pending);
+ smc_conn_free(&smc->conn);
+ if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
+ sock_put(&smc->sk); /* passive closing */
+ return reason_code;
+}
+
+/* check if there is a rdma device available for this connection. */
+/* called for connect and listen */
+static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
+ u8 *ibport)
+{
+ int reason_code = 0;
/* PNET table look up: search active ib_device and port
* within same PNETID that also contains the ethernet device
* used for the internal TCP socket
*/
- smc_pnet_find_roce_resource(smc->clcsock->sk, &smcibdev, &ibport);
- if (!smcibdev) {
+ smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport);
+ if (!(*ibdev))
reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
- goto decline_rdma;
- }
+
+ return reason_code;
+}
+
+/* CLC handshake during connect */
+static int smc_connect_clc(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *aclc,
+ struct smc_ib_device *ibdev, u8 ibport)
+{
+ int rc = 0;
/* do inband token exchange */
- reason_code = smc_clc_send_proposal(smc, smcibdev, ibport);
- if (reason_code < 0) {
- rc = reason_code;
- goto out_err;
- }
- if (reason_code > 0) /* configuration error */
- goto decline_rdma;
+ rc = smc_clc_send_proposal(smc, ibdev, ibport);
+ if (rc)
+ return rc;
/* receive SMC Accept CLC message */
- reason_code = smc_clc_wait_msg(smc, &aclc, sizeof(aclc),
- SMC_CLC_ACCEPT);
- if (reason_code < 0) {
- rc = reason_code;
- goto out_err;
- }
- if (reason_code > 0)
- goto decline_rdma;
+ return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT);
+}
+
+/* setup for RDMA connection of client */
+static int smc_connect_rdma(struct smc_sock *smc,
+ struct smc_clc_msg_accept_confirm *aclc,
+ struct smc_ib_device *ibdev, u8 ibport)
+{
+ int local_contact = SMC_FIRST_CONTACT;
+ struct smc_link *link;
+ int reason_code = 0;
- srv_first_contact = aclc.hdr.flag;
mutex_lock(&smc_create_lgr_pending);
- local_contact = smc_conn_create(smc, smcibdev, ibport, &aclc.lcl,
- srv_first_contact);
+ local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl,
+ aclc->hdr.flag);
if (local_contact < 0) {
- rc = local_contact;
- if (rc == -ENOMEM)
+ if (local_contact == -ENOMEM)
reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (rc == -ENOLINK)
+ else if (local_contact == -ENOLINK)
reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
- goto decline_rdma_unlock;
+ else
+ reason_code = SMC_CLC_DECL_INTERR; /* other error */
+ return smc_connect_abort(smc, reason_code, 0);
}
link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK];
- smc_conn_save_peer_info(smc, &aclc);
+ smc_conn_save_peer_info(smc, aclc);
/* create send buffer and rmb */
- rc = smc_buf_create(smc);
- if (rc) {
- reason_code = SMC_CLC_DECL_MEM;
- goto decline_rdma_unlock;
- }
+ if (smc_buf_create(smc))
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
if (local_contact == SMC_FIRST_CONTACT)
- smc_link_save_peer_info(link, &aclc);
+ smc_link_save_peer_info(link, aclc);
- rc = smc_rmb_rtoken_handling(&smc->conn, &aclc);
- if (rc) {
- reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
- }
+ if (smc_rmb_rtoken_handling(&smc->conn, aclc))
+ return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ local_contact);
smc_close_init(smc);
smc_rx_init(smc);
if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_ib_ready_link(link);
- if (rc) {
- reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
- }
+ if (smc_ib_ready_link(link))
+ return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ local_contact);
} else {
- struct smc_buf_desc *buf_desc = smc->conn.rmb_desc;
-
- if (!buf_desc->reused) {
- /* register memory region for new rmb */
- rc = smc_wr_reg_send(link,
- buf_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc) {
- reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
- }
- }
+ if (!smc->conn.rmb_desc->reused &&
+ smc_reg_rmb(link, smc->conn.rmb_desc, true))
+ return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ local_contact);
}
smc_rmb_sync_sg_for_device(&smc->conn);
- rc = smc_clc_send_confirm(smc);
- if (rc)
- goto out_err_unlock;
+ reason_code = smc_clc_send_confirm(smc);
+ if (reason_code)
+ return smc_connect_abort(smc, reason_code, local_contact);
+
+ smc_tx_init(smc);
if (local_contact == SMC_FIRST_CONTACT) {
/* QP confirmation over RoCE fabric */
reason_code = smc_clnt_conf_first_link(smc);
- if (reason_code < 0) {
- rc = reason_code;
- goto out_err_unlock;
- }
- if (reason_code > 0)
- goto decline_rdma_unlock;
+ if (reason_code)
+ return smc_connect_abort(smc, reason_code,
+ local_contact);
}
-
mutex_unlock(&smc_create_lgr_pending);
- smc_tx_init(smc);
-out_connected:
smc_copy_sock_settings_to_clc(smc);
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
- return rc ? rc : local_contact;
+ return 0;
+}
-decline_rdma_unlock:
- if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(smc->conn.lgr);
- mutex_unlock(&smc_create_lgr_pending);
- smc_conn_free(&smc->conn);
-decline_rdma:
- /* RDMA setup failed, switch back to TCP */
- smc->use_fallback = true;
- if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(smc, reason_code);
- if (rc < 0)
- goto out_err;
- }
- goto out_connected;
+/* perform steps before actually connecting */
+static int __smc_connect(struct smc_sock *smc)
+{
+ struct smc_clc_msg_accept_confirm aclc;
+ struct smc_ib_device *ibdev;
+ int rc = 0;
+ u8 ibport;
-out_err_unlock:
- if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(smc->conn.lgr);
- mutex_unlock(&smc_create_lgr_pending);
- smc_conn_free(&smc->conn);
-out_err:
- if (smc->sk.sk_state == SMC_INIT)
- sock_put(&smc->sk); /* passive closing */
- return rc;
+ sock_hold(&smc->sk); /* sock put in passive closing */
+
+ if (smc->use_fallback)
+ return smc_connect_fallback(smc);
+
+ /* if peer has not signalled SMC-capability, fall back */
+ if (!tcp_sk(smc->clcsock->sk)->syn_smc)
+ return smc_connect_fallback(smc);
+
+ /* IPSec connections opt out of SMC-R optimizations */
+ if (using_ipsec(smc))
+ return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
+
+ /* check if a RDMA device is available; if not, fall back */
+ if (smc_check_rdma(smc, &ibdev, &ibport))
+ return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+
+ /* perform CLC handshake */
+ rc = smc_connect_clc(smc, &aclc, ibdev, ibport);
+ if (rc)
+ return smc_connect_decline_fallback(smc, rc);
+
+ /* connect using rdma */
+ rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+ if (rc)
+ return smc_connect_decline_fallback(smc, rc);
+
+ return 0;
}
static int smc_connect(struct socket *sock, struct sockaddr *addr,
if (rc)
goto out;
- /* setup RDMA connection */
- rc = smc_connect_rdma(smc);
+ rc = __smc_connect(smc);
if (rc < 0)
goto out;
else
static int smc_serv_conf_first_link(struct smc_sock *smc)
{
+ struct net *net = sock_net(smc->clcsock->sk);
struct smc_link_group *lgr = smc->conn.lgr;
struct smc_link *link;
int rest;
link = &lgr->lnk[SMC_SINGLE_LINK];
- rc = smc_wr_reg_send(link,
- smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc)
+ if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
return SMC_CLC_DECL_INTERR;
/* send CONFIRM LINK request to client over the RoCE fabric */
return rc;
}
- link->state = SMC_LNK_ACTIVE;
+ smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
return 0;
}
-/* setup for RDMA connection of server */
-static void smc_listen_work(struct work_struct *work)
+/* listen worker: finish */
+static void smc_listen_out(struct smc_sock *new_smc)
{
- struct smc_sock *new_smc = container_of(work, struct smc_sock,
- smc_listen_work);
- struct smc_clc_msg_proposal_prefix *pclc_prfx;
- struct socket *newclcsock = new_smc->clcsock;
struct smc_sock *lsmc = new_smc->listen_smc;
- struct smc_clc_msg_accept_confirm cclc;
- int local_contact = SMC_REUSE_CONTACT;
struct sock *newsmcsk = &new_smc->sk;
- struct smc_clc_msg_proposal *pclc;
- struct smc_ib_device *smcibdev;
- u8 buf[SMC_CLC_MAX_LEN];
- struct smc_link *link;
- int reason_code = 0;
- int rc = 0;
- u8 ibport;
- /* check if peer is smc capable */
- if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
- goto out_connected;
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
+ if (lsmc->sk.sk_state == SMC_LISTEN) {
+ smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ } else { /* no longer listening */
+ smc_close_non_accepted(newsmcsk);
}
+ release_sock(&lsmc->sk);
- /* do inband token exchange -
- *wait for and receive SMC Proposal CLC message
- */
- reason_code = smc_clc_wait_msg(new_smc, &buf, sizeof(buf),
- SMC_CLC_PROPOSAL);
- if (reason_code < 0)
- goto out_err;
- if (reason_code > 0)
- goto decline_rdma;
+ /* Wake up accept */
+ lsmc->sk.sk_data_ready(&lsmc->sk);
+ sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
+}
- /* IPSec connections opt out of SMC-R optimizations */
- if (using_ipsec(new_smc)) {
- reason_code = SMC_CLC_DECL_IPSEC;
- goto decline_rdma;
- }
+/* listen worker: finish in state connected */
+static void smc_listen_out_connected(struct smc_sock *new_smc)
+{
+ struct sock *newsmcsk = &new_smc->sk;
- /* PNET table look up: search active ib_device and port
- * within same PNETID that also contains the ethernet device
- * used for the internal TCP socket
- */
- smc_pnet_find_roce_resource(newclcsock->sk, &smcibdev, &ibport);
- if (!smcibdev) {
- reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
- goto decline_rdma;
+ sk_refcnt_debug_inc(newsmcsk);
+ if (newsmcsk->sk_state == SMC_INIT)
+ newsmcsk->sk_state = SMC_ACTIVE;
+
+ smc_listen_out(new_smc);
+}
+
+/* listen worker: finish in error state */
+static void smc_listen_out_err(struct smc_sock *new_smc)
+{
+ struct sock *newsmcsk = &new_smc->sk;
+
+ if (newsmcsk->sk_state == SMC_INIT)
+ sock_put(&new_smc->sk); /* passive closing */
+ newsmcsk->sk_state = SMC_CLOSED;
+ smc_conn_free(&new_smc->conn);
+
+ smc_listen_out(new_smc);
+}
+
+/* listen worker: decline and fall back if possible */
+static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
+ int local_contact)
+{
+ /* RDMA setup failed, switch back to TCP */
+ if (local_contact == SMC_FIRST_CONTACT)
+ smc_lgr_forget(new_smc->conn.lgr);
+ if (reason_code < 0) { /* error, no fallback possible */
+ smc_listen_out_err(new_smc);
+ return;
+ }
+ smc_conn_free(&new_smc->conn);
+ new_smc->use_fallback = true;
+ if (reason_code && reason_code != SMC_CLC_DECL_REPLY) {
+ if (smc_clc_send_decline(new_smc, reason_code) < 0) {
+ smc_listen_out_err(new_smc);
+ return;
+ }
}
+ smc_listen_out_connected(new_smc);
+}
+
+/* listen worker: check prefixes */
+static int smc_listen_rdma_check(struct smc_sock *new_smc,
+ struct smc_clc_msg_proposal *pclc)
+{
+ struct smc_clc_msg_proposal_prefix *pclc_prfx;
+ struct socket *newclcsock = new_smc->clcsock;
- pclc = (struct smc_clc_msg_proposal *)&buf;
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+ if (smc_clc_prfx_match(newclcsock, pclc_prfx))
+ return SMC_CLC_DECL_CNFERR;
- rc = smc_clc_prfx_match(newclcsock, pclc_prfx);
- if (rc) {
- reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
- goto decline_rdma;
- }
+ return 0;
+}
+/* listen worker: initialize connection and buffers */
+static int smc_listen_rdma_init(struct smc_sock *new_smc,
+ struct smc_clc_msg_proposal *pclc,
+ struct smc_ib_device *ibdev, u8 ibport,
+ int *local_contact)
+{
/* allocate connection / link group */
- mutex_lock(&smc_create_lgr_pending);
- local_contact = smc_conn_create(new_smc, smcibdev, ibport, &pclc->lcl,
- 0);
- if (local_contact < 0) {
- rc = local_contact;
- if (rc == -ENOMEM)
- reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- goto decline_rdma_unlock;
+ *local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0);
+ if (*local_contact < 0) {
+ if (*local_contact == -ENOMEM)
+ return SMC_CLC_DECL_MEM;/* insufficient memory*/
+ return SMC_CLC_DECL_INTERR; /* other error */
}
- link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
/* create send buffer and rmb */
- rc = smc_buf_create(new_smc);
- if (rc) {
- reason_code = SMC_CLC_DECL_MEM;
- goto decline_rdma_unlock;
- }
+ if (smc_buf_create(new_smc))
+ return SMC_CLC_DECL_MEM;
- smc_close_init(new_smc);
- smc_rx_init(new_smc);
+ return 0;
+}
+
+/* listen worker: register buffers */
+static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
+{
+ struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
if (local_contact != SMC_FIRST_CONTACT) {
- struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc;
-
- if (!buf_desc->reused) {
- /* register memory region for new rmb */
- rc = smc_wr_reg_send(link,
- buf_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc) {
- reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
- }
+ if (!new_smc->conn.rmb_desc->reused) {
+ if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
+ return SMC_CLC_DECL_INTERR;
}
}
smc_rmb_sync_sg_for_device(&new_smc->conn);
- rc = smc_clc_send_accept(new_smc, local_contact);
- if (rc)
- goto out_err_unlock;
+ return 0;
+}
+
+/* listen worker: finish RDMA setup */
+static void smc_listen_rdma_finish(struct smc_sock *new_smc,
+ struct smc_clc_msg_accept_confirm *cclc,
+ int local_contact)
+{
+ struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
+ int reason_code = 0;
- /* receive SMC Confirm CLC message */
- reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
- SMC_CLC_CONFIRM);
- if (reason_code < 0)
- goto out_err_unlock;
- if (reason_code > 0)
- goto decline_rdma_unlock;
- smc_conn_save_peer_info(new_smc, &cclc);
if (local_contact == SMC_FIRST_CONTACT)
- smc_link_save_peer_info(link, &cclc);
+ smc_link_save_peer_info(link, cclc);
- rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc);
- if (rc) {
+ if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) {
reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
+ goto decline;
}
if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_ib_ready_link(link);
- if (rc) {
+ if (smc_ib_ready_link(link)) {
reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma_unlock;
+ goto decline;
}
/* QP confirmation over RoCE fabric */
reason_code = smc_serv_conf_first_link(new_smc);
- if (reason_code < 0)
- /* peer is not aware of a problem */
- goto out_err_unlock;
- if (reason_code > 0)
- goto decline_rdma_unlock;
+ if (reason_code)
+ goto decline;
}
+ return;
- smc_tx_init(new_smc);
+decline:
mutex_unlock(&smc_create_lgr_pending);
+ smc_listen_decline(new_smc, reason_code, local_contact);
+}
-out_connected:
- sk_refcnt_debug_inc(newsmcsk);
- if (newsmcsk->sk_state == SMC_INIT)
- newsmcsk->sk_state = SMC_ACTIVE;
-enqueue:
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
- if (lsmc->sk.sk_state == SMC_LISTEN) {
- smc_accept_enqueue(&lsmc->sk, newsmcsk);
- } else { /* no longer listening */
- smc_close_non_accepted(newsmcsk);
+/* setup for RDMA connection of server */
+static void smc_listen_work(struct work_struct *work)
+{
+ struct smc_sock *new_smc = container_of(work, struct smc_sock,
+ smc_listen_work);
+ struct socket *newclcsock = new_smc->clcsock;
+ struct smc_clc_msg_accept_confirm cclc;
+ struct smc_clc_msg_proposal *pclc;
+ struct smc_ib_device *ibdev;
+ u8 buf[SMC_CLC_MAX_LEN];
+ int local_contact = 0;
+ int reason_code = 0;
+ int rc = 0;
+ u8 ibport;
+
+ if (new_smc->use_fallback) {
+ smc_listen_out_connected(new_smc);
+ return;
}
- release_sock(&lsmc->sk);
- /* Wake up accept */
- lsmc->sk.sk_data_ready(&lsmc->sk);
- sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
- return;
+ /* check if peer is smc capable */
+ if (!tcp_sk(newclcsock->sk)->syn_smc) {
+ new_smc->use_fallback = true;
+ smc_listen_out_connected(new_smc);
+ return;
+ }
-decline_rdma_unlock:
- if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(new_smc->conn.lgr);
- mutex_unlock(&smc_create_lgr_pending);
-decline_rdma:
- /* RDMA setup failed, switch back to TCP */
- smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
- if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- if (smc_clc_send_decline(new_smc, reason_code) < 0)
- goto out_err;
+ /* do inband token exchange -
+ * wait for and receive SMC Proposal CLC message
+ */
+ pclc = (struct smc_clc_msg_proposal *)&buf;
+ reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+ SMC_CLC_PROPOSAL);
+ if (reason_code) {
+ smc_listen_decline(new_smc, reason_code, 0);
+ return;
}
- goto out_connected;
-out_err_unlock:
- if (local_contact == SMC_FIRST_CONTACT)
- smc_lgr_forget(new_smc->conn.lgr);
+ /* IPSec connections opt out of SMC-R optimizations */
+ if (using_ipsec(new_smc)) {
+ smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0);
+ return;
+ }
+
+ mutex_lock(&smc_create_lgr_pending);
+ smc_close_init(new_smc);
+ smc_rx_init(new_smc);
+ smc_tx_init(new_smc);
+
+ /* check if RDMA is available */
+ if (smc_check_rdma(new_smc, &ibdev, &ibport) ||
+ smc_listen_rdma_check(new_smc, pclc) ||
+ smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
+ &local_contact) ||
+ smc_listen_rdma_reg(new_smc, local_contact)) {
+ /* SMC not supported, decline */
+ mutex_unlock(&smc_create_lgr_pending);
+ smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact);
+ return;
+ }
+
+ /* send SMC Accept CLC message */
+ rc = smc_clc_send_accept(new_smc, local_contact);
+ if (rc) {
+ mutex_unlock(&smc_create_lgr_pending);
+ smc_listen_decline(new_smc, rc, local_contact);
+ return;
+ }
+
+ /* receive SMC Confirm CLC message */
+ reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+ SMC_CLC_CONFIRM);
+ if (reason_code) {
+ mutex_unlock(&smc_create_lgr_pending);
+ smc_listen_decline(new_smc, reason_code, local_contact);
+ return;
+ }
+
+ /* finish worker */
+ smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+ smc_conn_save_peer_info(new_smc, &cclc);
mutex_unlock(&smc_create_lgr_pending);
-out_err:
- if (newsmcsk->sk_state == SMC_INIT)
- sock_put(&new_smc->sk); /* passive closing */
- newsmcsk->sk_state = SMC_CLOSED;
- smc_conn_free(&new_smc->conn);
- goto enqueue; /* queue new sock with sk_err set */
+ smc_listen_out_connected(new_smc);
}
static void smc_tcp_listen_work(struct work_struct *work)
continue;
new_smc->listen_smc = lsmc;
- new_smc->use_fallback = false; /* assume rdma capability first*/
+ new_smc->use_fallback = lsmc->use_fallback;
sock_hold(lsk); /* sock_put in smc_listen_work */
INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
smc_copy_sock_settings_to_smc(new_smc);
}
out:
- if (lsmc->clcsock) {
- sock_release(lsmc->clcsock);
- lsmc->clcsock = NULL;
- }
release_sock(lsk);
sock_put(&lsmc->sk); /* sock_hold in smc_listen */
}
* them to the clc socket -- copy smc socket options to clc socket
*/
smc_copy_sock_settings_to_clc(smc);
- tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+ if (!smc->use_fallback)
+ tcp_sk(smc->clcsock->sk)->syn_smc = 1;
rc = kernel_listen(smc->clcsock, backlog);
if (rc)
if (lsmc->sk.sk_state != SMC_LISTEN) {
rc = -EINVAL;
+ release_sock(sk);
goto out;
}
if (!rc)
rc = sock_error(nsk);
+ release_sock(sk);
+ if (rc)
+ goto out;
+
+ if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) {
+ /* wait till data arrives on the socket */
+ timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept *
+ MSEC_PER_SEC);
+ if (smc_sk(nsk)->use_fallback) {
+ struct sock *clcsk = smc_sk(nsk)->clcsock->sk;
+
+ lock_sock(clcsk);
+ if (skb_queue_empty(&clcsk->sk_receive_queue))
+ sk_wait_data(clcsk, &timeo, NULL);
+ release_sock(clcsk);
+ } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) {
+ lock_sock(nsk);
+ smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available);
+ release_sock(nsk);
+ }
+ }
out:
- release_sock(sk);
sock_put(sk); /* sock_hold above */
return rc;
}
(sk->sk_state != SMC_APPCLOSEWAIT1) &&
(sk->sk_state != SMC_INIT))
goto out;
+
+ if (msg->msg_flags & MSG_FASTOPEN) {
+ if (sk->sk_state == SMC_INIT) {
+ smc->use_fallback = true;
+ } else {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
+
if (smc->use_fallback)
rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
else
goto out;
}
- if (smc->use_fallback)
+ if (smc->use_fallback) {
rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags);
- else
- rc = smc_rx_recvmsg(smc, msg, len, flags);
+ } else {
+ msg->msg_namelen = 0;
+ rc = smc_rx_recvmsg(smc, msg, NULL, len, flags);
+ }
out:
release_sock(sk);
/* delegate to CLC child sock */
release_sock(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
- /* if non-blocking connect finished ... */
lock_sock(sk);
- if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) {
- sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
- mask |= EPOLLERR;
- } else {
- rc = smc_connect_rdma(smc);
+ sk->sk_err = smc->clcsock->sk->sk_err;
+ if (sk->sk_err) {
+ mask |= EPOLLERR;
+ } else {
+ /* if non-blocking connect finished ... */
+ if (sk->sk_state == SMC_INIT &&
+ mask & EPOLLOUT &&
+ smc->clcsock->sk->sk_state != TCP_CLOSE) {
+ rc = __smc_connect(smc);
if (rc < 0)
mask |= EPOLLERR;
/* success cases including fallback */
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
+ int val, rc;
smc = smc_sk(sk);
/* generic setsockopts reaching us here always apply to the
* CLC socket
*/
- return smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
- optval, optlen);
+ rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
+ optval, optlen);
+ if (smc->clcsock->sk->sk_err) {
+ sk->sk_err = smc->clcsock->sk->sk_err;
+ sk->sk_error_report(sk);
+ }
+ if (rc)
+ return rc;
+
+ if (optlen < sizeof(int))
+ return rc;
+ get_user(val, (int __user *)optval);
+
+ lock_sock(sk);
+ switch (optname) {
+ case TCP_ULP:
+ case TCP_FASTOPEN:
+ case TCP_FASTOPEN_CONNECT:
+ case TCP_FASTOPEN_KEY:
+ case TCP_FASTOPEN_NO_COOKIE:
+ /* option not supported by SMC */
+ if (sk->sk_state == SMC_INIT) {
+ smc->use_fallback = true;
+ } else {
+ if (!smc->use_fallback)
+ rc = -EINVAL;
+ }
+ break;
+ case TCP_NODELAY:
+ if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (val && !smc->use_fallback)
+ mod_delayed_work(system_wq, &smc->conn.tx_work,
+ 0);
+ }
+ break;
+ case TCP_CORK:
+ if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (!val && !smc->use_fallback)
+ mod_delayed_work(system_wq, &smc->conn.tx_work,
+ 0);
+ }
+ break;
+ case TCP_DEFER_ACCEPT:
+ smc->sockopt_defer_accept = val;
+ break;
+ default:
+ break;
+ }
+ release_sock(sk);
+
+ return rc;
}
static int smc_getsockopt(struct socket *sock, int level, int optname,
unsigned long arg)
{
struct smc_sock *smc;
+ int answ;
smc = smc_sk(sock->sk);
- if (smc->use_fallback)
+ if (smc->use_fallback) {
+ if (!smc->clcsock)
+ return -EBADF;
return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
- else
- return sock_no_ioctl(sock, cmd, arg);
+ }
+ switch (cmd) {
+ case SIOCINQ: /* same as FIONREAD */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = atomic_read(&smc->conn.bytes_to_rcv);
+ break;
+ case SIOCOUTQ:
+ /* output queue size (not send + not acked) */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = smc->conn.sndbuf_desc->len -
+ atomic_read(&smc->conn.sndbuf_space);
+ break;
+ case SIOCOUTQNSD:
+ /* output queue size (not send only) */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = smc_tx_prepared_sends(&smc->conn);
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return put_user(answ, (int __user *)arg);
}
static ssize_t smc_sendpage(struct socket *sock, struct page *page,
smc = smc_sk(sk);
lock_sock(sk);
- if (sk->sk_state != SMC_ACTIVE)
+ if (sk->sk_state != SMC_ACTIVE) {
+ release_sock(sk);
goto out;
+ }
+ release_sock(sk);
if (smc->use_fallback)
rc = kernel_sendpage(smc->clcsock, page, offset,
size, flags);
rc = sock_no_sendpage(sock, page, offset, size, flags);
out:
- release_sock(sk);
return rc;
}
+/* Map the affected portions of the rmbe into an spd, note the number of bytes
+ * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor
+ * updates till whenever a respective page has been fully processed.
+ * Note that subsequent recv() calls have to wait till all splice() processing
+ * completed.
+ */
static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
+ unsigned int flags)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
smc = smc_sk(sk);
lock_sock(sk);
- if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED))
+
+ if (sk->sk_state == SMC_INIT ||
+ sk->sk_state == SMC_LISTEN ||
+ sk->sk_state == SMC_CLOSED)
+ goto out;
+
+ if (sk->sk_state == SMC_PEERFINCLOSEWAIT) {
+ rc = 0;
goto out;
+ }
+
if (smc->use_fallback) {
rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos,
pipe, len, flags);
} else {
- rc = -EOPNOTSUPP;
+ if (*ppos) {
+ rc = -ESPIPE;
+ goto out;
+ }
+ if (flags & SPLICE_F_NONBLOCK)
+ flags = MSG_DONTWAIT;
+ else
+ flags = 0;
+ rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags);
}
out:
release_sock(sk);
+
return rc;
}
static void __exit smc_exit(void)
{
- struct smc_link_group *lgr, *lg;
- LIST_HEAD(lgr_freeing_list);
-
- spin_lock_bh(&smc_lgr_list.lock);
- if (!list_empty(&smc_lgr_list.list))
- list_splice_init(&smc_lgr_list.list, &lgr_freeing_list);
- spin_unlock_bh(&smc_lgr_list.lock);
- list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
- list_del_init(&lgr->list);
- cancel_delayed_work_sync(&lgr->free_work);
- smc_lgr_free(lgr); /* free link group */
- }
+ smc_core_exit();
static_branch_disable(&tcp_have_smc);
smc_ib_unregister_client();
sock_unregister(PF_SMC);
struct rb_node alert_node;
struct smc_link_group *lgr; /* link group of connection */
u32 alert_token_local; /* unique conn. id */
- u8 peer_conn_idx; /* from tcp handshake */
+ u8 peer_rmbe_idx; /* from tcp handshake */
int peer_rmbe_size; /* size of peer rx buffer */
atomic_t peer_rmbe_space;/* remaining free bytes in peer
* rmbe
int rtoken_idx; /* idx to peer RMB rkey/addr */
struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */
- int sndbuf_size; /* sndbuf size <== sock wmem */
struct smc_buf_desc *rmb_desc; /* RMBE descriptor */
- int rmbe_size; /* RMBE size <== sock rmem */
int rmbe_size_short;/* compressed notation */
int rmbe_update_limit;
/* lower limit for consumer
u16 tx_cdc_seq; /* sequence # for CDC send */
spinlock_t send_lock; /* protect wr_sends */
struct delayed_work tx_work; /* retry of smc_cdc_msg_send */
+ u32 tx_off; /* base offset in peer rmb */
struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl.
* .prod cf. TCP rcv_nxt
atomic_t bytes_to_rcv; /* arrived data,
* not yet received
*/
+ atomic_t splice_pending; /* number of spliced bytes
+ * pending processing
+ */
#ifndef KERNEL_HAS_ATOMIC64
spinlock_t acurs_lock; /* protect cursors */
#endif
struct list_head accept_q; /* sockets to be accepted */
spinlock_t accept_q_lock; /* protects accept_q */
bool use_fallback; /* fallback to tcp */
+ int sockopt_defer_accept;
+ /* sockopt TCP_DEFER_ACCEPT
+ * value
+ */
u8 wait_close_tx_prepared : 1;
/* shutdown wr or close
* started, waiting for unsent
return be32_to_cpu(t);
}
-#define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */
-
-#define SMC_RMBE_SIZES 16 /* number of distinct sizes for an RMBE */
-/* theoretically, the RFC states that largest size would be 512K,
- * i.e. compressed 5 and thus 6 sizes (0..5), despite
- * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
- */
-
-/* convert the RMB size into the compressed notation - minimum 16K.
- * In contrast to plain ilog2, this rounds towards the next power of 2,
- * so the socket application gets at least its desired sndbuf / rcvbuf size.
- */
-static inline u8 smc_compress_bufsize(int size)
-{
- u8 compressed;
-
- if (size <= SMC_BUF_MIN_SIZE)
- return 0;
-
- size = (size - 1) >> 14;
- compressed = ilog2(size) + 1;
- if (compressed >= SMC_RMBE_SIZES)
- compressed = SMC_RMBE_SIZES - 1;
- return compressed;
-}
-
-/* convert the RMB size from compressed notation into integer */
-static inline int smc_uncompress_bufsize(u8 compressed)
-{
- u32 size;
-
- size = 0x00000001 << (((int)compressed) + 14);
- return (int)size;
-}
-
#ifdef CONFIG_XFRM
static inline bool using_ipsec(struct smc_sock *smc)
{
}
#endif
-struct smc_clc_msg_local;
-
-void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc,
- struct smc_ib_device *smcibdev, u8 ibport,
- struct smc_clc_msg_local *lcl, int srv_first_contact);
struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock);
void smc_close_non_accepted(struct sock *sk);
smc = container_of(cdcpend->conn, struct smc_sock, conn);
bh_lock_sock(&smc->sk);
if (!wc_status) {
- diff = smc_curs_diff(cdcpend->conn->sndbuf_size,
+ diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
&cdcpend->conn->tx_curs_fin,
&cdcpend->cursor);
/* sndbuf_space is decreased in smc_sendmsg */
smp_mb__before_atomic();
atomic_add(diff, &cdcpend->conn->sndbuf_space);
- /* guarantee 0 <= sndbuf_space <= sndbuf_size */
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
smp_mb__after_atomic();
smc_curs_write(&cdcpend->conn->tx_curs_fin,
smc_curs_read(&cdcpend->cursor, cdcpend->conn),
sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE,
"must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)");
BUILD_BUG_ON_MSG(
- offsetof(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE,
+ sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE,
"must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()");
BUILD_BUG_ON_MSG(
sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE,
}
static void smc_cdc_msg_recv_action(struct smc_sock *smc,
- struct smc_link *link,
struct smc_cdc_msg *cdc)
{
union smc_host_cursor cons_old, prod_old;
struct smc_connection *conn = &smc->conn;
int diff_cons, diff_prod;
- if (!cdc->prod_flags.failover_validation) {
- if (smc_cdc_before(ntohs(cdc->seqno),
- conn->local_rx_ctrl.seqno))
- /* received seqno is old */
- return;
- }
smc_curs_write(&prod_old,
smc_curs_read(&conn->local_rx_ctrl.prod, conn),
conn);
smp_mb__after_atomic();
}
- diff_prod = smc_curs_diff(conn->rmbe_size, &prod_old,
+ diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
&conn->local_rx_ctrl.prod);
if (diff_prod) {
/* bytes_to_rcv is decreased in smc_recvmsg */
smp_mb__before_atomic();
atomic_add(diff_prod, &conn->bytes_to_rcv);
- /* guarantee 0 <= bytes_to_rcv <= rmbe_size */
+ /* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
smp_mb__after_atomic();
smc->sk.sk_data_ready(&smc->sk);
} else if ((conn->local_rx_ctrl.prod_flags.write_blocked) ||
}
/* called under tasklet context */
-static inline void smc_cdc_msg_recv(struct smc_cdc_msg *cdc,
- struct smc_link *link, u64 wr_id)
+static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
{
- struct smc_link_group *lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
- struct smc_connection *connection;
- struct smc_sock *smc;
-
- /* lookup connection */
- read_lock_bh(&lgr->conns_lock);
- connection = smc_lgr_find_conn(ntohl(cdc->token), lgr);
- if (!connection) {
- read_unlock_bh(&lgr->conns_lock);
- return;
- }
- smc = container_of(connection, struct smc_sock, conn);
sock_hold(&smc->sk);
- read_unlock_bh(&lgr->conns_lock);
bh_lock_sock(&smc->sk);
- smc_cdc_msg_recv_action(smc, link, cdc);
+ smc_cdc_msg_recv_action(smc, cdc);
bh_unlock_sock(&smc->sk);
sock_put(&smc->sk); /* no free sk in softirq-context */
}
{
struct smc_link *link = (struct smc_link *)wc->qp->qp_context;
struct smc_cdc_msg *cdc = buf;
+ struct smc_connection *conn;
+ struct smc_link_group *lgr;
+ struct smc_sock *smc;
if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved))
return; /* short message */
if (cdc->len != SMC_WR_TX_SIZE)
return; /* invalid message */
- smc_cdc_msg_recv(cdc, link, wc->wr_id);
+
+ /* lookup connection */
+ lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+ read_lock_bh(&lgr->conns_lock);
+ conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
+ read_unlock_bh(&lgr->conns_lock);
+ if (!conn)
+ return;
+ smc = container_of(conn, struct smc_sock, conn);
+
+ if (!cdc->prod_flags.failover_validation) {
+ if (smc_cdc_before(ntohs(cdc->seqno),
+ conn->local_rx_ctrl.seqno))
+ /* received seqno is old */
+ return;
+ }
+ smc_cdc_msg_recv(smc, cdc);
}
static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = {
struct smc_cdc_producer_flags prod_flags;
struct smc_cdc_conn_state_flags conn_state_flags;
u8 reserved[18];
-} __aligned(8);
+} __packed; /* format defined in RFC7609 */
static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
{
if (clcm->type == SMC_CLC_DECLINE) {
reason_code = SMC_CLC_DECL_REPLY;
if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
- smc->conn.lgr->sync_err = true;
+ smc->conn.lgr->sync_err = 1;
smc_lgr_terminate(smc->conn.lgr);
}
}
hton24(cclc.qpn, link->roce_qp->qp_num);
cclc.rmb_rkey =
htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
- cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
+ cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
cclc.rmbe_alert_token = htonl(conn->alert_token_local);
cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
cclc.rmbe_size = conn->rmbe_size_short;
hton24(aclc.qpn, link->roce_qp->qp_num);
aclc.rmb_rkey =
htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
- aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */
+ aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */
aclc.rmbe_alert_token = htonl(conn->alert_token_local);
aclc.qp_mtu = link->path_mtu;
aclc.rmbe_size = conn->rmbe_size_short,
struct smc_clc_msg_local lcl;
u8 qpn[3]; /* QP number */
__be32 rmb_rkey; /* RMB rkey */
- u8 conn_idx; /* Connection index, which RMBE in RMB */
+ u8 rmbe_idx; /* Index of RMBE in RMB */
__be32 rmbe_alert_token;/* unique connection id */
#if defined(__BIG_ENDIAN_BITFIELD)
u8 rmbe_size : 4, /* RMBE buf size (compressed notation) */
#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10)
-static u32 smc_lgr_num; /* unique link group number */
+static struct smc_lgr_list smc_lgr_list = { /* established link groups */
+ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
+ .list = LIST_HEAD_INIT(smc_lgr_list.list),
+ .num = 0,
+};
+
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+ struct smc_buf_desc *buf_desc);
static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
{
list_del_init(&lgr->list); /* remove from smc_lgr_list */
free:
spin_unlock_bh(&smc_lgr_list.lock);
- if (!delayed_work_pending(&lgr->free_work))
+ if (!delayed_work_pending(&lgr->free_work)) {
+ if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
smc_lgr_free(lgr);
+ }
}
/* create a new SMC link group */
goto out;
}
lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- lgr->sync_err = false;
+ lgr->sync_err = 0;
memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
lgr->vlan_id = vlan_id;
rwlock_init(&lgr->sndbufs_lock);
INIT_LIST_HEAD(&lgr->sndbufs[i]);
INIT_LIST_HEAD(&lgr->rmbs[i]);
}
- smc_lgr_num += SMC_LGR_NUM_INCR;
- memcpy(&lgr->id, (u8 *)&smc_lgr_num, SMC_LGR_ID_SIZE);
+ smc_lgr_list.num += SMC_LGR_NUM_INCR;
+ memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
lgr->conns_all = RB_ROOT;
smc_ib_setup_per_ibdev(smcibdev);
get_random_bytes(rndvec, sizeof(rndvec));
lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16);
- rc = smc_wr_alloc_link_mem(lnk);
+ rc = smc_llc_link_init(lnk);
if (rc)
goto free_lgr;
+ rc = smc_wr_alloc_link_mem(lnk);
+ if (rc)
+ goto clear_llc_lnk;
rc = smc_ib_create_protection_domain(lnk);
if (rc)
goto free_link_mem;
rc = smc_wr_create_link(lnk);
if (rc)
goto destroy_qp;
- init_completion(&lnk->llc_confirm);
- init_completion(&lnk->llc_confirm_resp);
- init_completion(&lnk->llc_add);
- init_completion(&lnk->llc_add_resp);
smc->conn.lgr = lgr;
rwlock_init(&lgr->conns_lock);
smc_ib_dealloc_protection_domain(lnk);
free_link_mem:
smc_wr_free_link_mem(lnk);
+clear_llc_lnk:
+ smc_llc_link_clear(lnk);
free_lgr:
kfree(lgr);
out:
static void smc_buf_unuse(struct smc_connection *conn)
{
- if (conn->sndbuf_desc) {
+ if (conn->sndbuf_desc)
conn->sndbuf_desc->used = 0;
- conn->sndbuf_size = 0;
- }
if (conn->rmb_desc) {
- conn->rmb_desc->reused = true;
- conn->rmb_desc->used = 0;
- conn->rmbe_size = 0;
+ if (!conn->rmb_desc->regerr) {
+ conn->rmb_desc->reused = 1;
+ conn->rmb_desc->used = 0;
+ } else {
+ /* buf registration failed, reuse not possible */
+ struct smc_link_group *lgr = conn->lgr;
+
+ write_lock_bh(&lgr->rmbs_lock);
+ list_del(&conn->rmb_desc->list);
+ write_unlock_bh(&lgr->rmbs_lock);
+
+ smc_buf_free(lgr, true, conn->rmb_desc);
+ }
}
}
static void smc_link_clear(struct smc_link *lnk)
{
lnk->peer_qpn = 0;
+ smc_llc_link_clear(lnk);
smc_ib_modify_qp_reset(lnk);
smc_wr_free_link(lnk);
smc_ib_destroy_queue_pair(lnk);
smc_wr_free_link_mem(lnk);
}
-static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk,
- bool is_rmb)
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+ struct smc_buf_desc *buf_desc)
{
+ struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
if (is_rmb) {
if (buf_desc->mr_rx[SMC_SINGLE_LINK])
smc_ib_put_memory_region(
DMA_TO_DEVICE);
}
sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]);
- if (buf_desc->cpu_addr)
- free_pages((unsigned long)buf_desc->cpu_addr, buf_desc->order);
+ if (buf_desc->pages)
+ __free_pages(buf_desc->pages, buf_desc->order);
kfree(buf_desc);
}
static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
{
- struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
struct smc_buf_desc *buf_desc, *bf_desc;
struct list_head *buf_list;
int i;
list_for_each_entry_safe(buf_desc, bf_desc, buf_list,
list) {
list_del(&buf_desc->list);
- smc_buf_free(buf_desc, lnk, is_rmb);
+ smc_buf_free(lgr, is_rmb, buf_desc);
}
}
}
struct smc_sock *smc;
struct rb_node *node;
+ if (lgr->terminating)
+ return; /* lgr already terminating */
+ lgr->terminating = 1;
smc_lgr_forget(lgr);
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
write_lock_bh(&lgr->conns_lock);
node = rb_first(&lgr->conns_all);
smc_lgr_schedule_free_work(lgr);
}
+/* Called when IB port is terminated */
+void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ struct smc_link_group *lgr, *l;
+
+ list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
+ if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
+ lgr->lnk[SMC_SINGLE_LINK].ibport == ibport)
+ smc_lgr_terminate(lgr);
+ }
+}
+
/* Determine vlan of internal TCP socket.
* @vlan_id: address to store the determined vlan id into
*/
static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
- int rc = 0;
+ struct net_device *ndev;
+ int i, nest_lvl, rc = 0;
*vlan_id = 0;
if (!dst) {
goto out_rel;
}
- if (is_vlan_dev(dst->dev))
- *vlan_id = vlan_dev_vlan_id(dst->dev);
+ ndev = dst->dev;
+ if (is_vlan_dev(ndev)) {
+ *vlan_id = vlan_dev_vlan_id(ndev);
+ goto out_rel;
+ }
+
+ rtnl_lock();
+ nest_lvl = dev_get_nest_level(ndev);
+ for (i = 0; i < nest_lvl; i++) {
+ struct list_head *lower = &ndev->adj_list.lower;
+
+ if (list_empty(lower))
+ break;
+ lower = lower->next;
+ ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
+ if (is_vlan_dev(ndev)) {
+ *vlan_id = vlan_dev_vlan_id(ndev);
+ break;
+ }
+ }
+ rtnl_unlock();
out_rel:
dst_release(dst);
struct smc_clc_msg_local *lcl, int srv_first_contact)
{
struct smc_connection *conn = &smc->conn;
+ int local_contact = SMC_FIRST_CONTACT;
struct smc_link_group *lgr;
unsigned short vlan_id;
enum smc_lgr_role role;
- int local_contact = SMC_FIRST_CONTACT;
int rc = 0;
role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
return rc ? rc : local_contact;
}
+/* convert the RMB size into the compressed notation - minimum 16K.
+ * In contrast to plain ilog2, this rounds towards the next power of 2,
+ * so the socket application gets at least its desired sndbuf / rcvbuf size.
+ */
+static u8 smc_compress_bufsize(int size)
+{
+ u8 compressed;
+
+ if (size <= SMC_BUF_MIN_SIZE)
+ return 0;
+
+ size = (size - 1) >> 14;
+ compressed = ilog2(size) + 1;
+ if (compressed >= SMC_RMBE_SIZES)
+ compressed = SMC_RMBE_SIZES - 1;
+ return compressed;
+}
+
+/* convert the RMB size from compressed notation into integer */
+int smc_uncompress_bufsize(u8 compressed)
+{
+ u32 size;
+
+ size = 0x00000001 << (((int)compressed) + 14);
+ return (int)size;
+}
+
/* try to reuse a sndbuf or rmb description slot for a certain
* buffer size; if not available, return NULL
*/
-static inline
-struct smc_buf_desc *smc_buf_get_slot(struct smc_link_group *lgr,
- int compressed_bufsize,
- rwlock_t *lock,
- struct list_head *buf_list)
+static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize,
+ rwlock_t *lock,
+ struct list_head *buf_list)
{
struct smc_buf_desc *buf_slot;
if (!buf_desc)
return ERR_PTR(-ENOMEM);
- buf_desc->cpu_addr =
- (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN |
- __GFP_NOMEMALLOC |
- __GFP_NORETRY | __GFP_ZERO,
- get_order(bufsize));
- if (!buf_desc->cpu_addr) {
+ buf_desc->order = get_order(bufsize);
+ buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN |
+ __GFP_NOMEMALLOC | __GFP_COMP |
+ __GFP_NORETRY | __GFP_ZERO,
+ buf_desc->order);
+ if (!buf_desc->pages) {
kfree(buf_desc);
return ERR_PTR(-EAGAIN);
}
- buf_desc->order = get_order(bufsize);
+ buf_desc->cpu_addr = (void *)page_address(buf_desc->pages);
/* build the sg table from the pages */
lnk = &lgr->lnk[SMC_SINGLE_LINK];
rc = sg_alloc_table(&buf_desc->sgt[SMC_SINGLE_LINK], 1,
GFP_KERNEL);
if (rc) {
- smc_buf_free(buf_desc, lnk, is_rmb);
+ smc_buf_free(lgr, is_rmb, buf_desc);
return ERR_PTR(rc);
}
sg_set_buf(buf_desc->sgt[SMC_SINGLE_LINK].sgl,
is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
/* SMC protocol depends on mapping to one DMA address only */
if (rc != 1) {
- smc_buf_free(buf_desc, lnk, is_rmb);
+ smc_buf_free(lgr, is_rmb, buf_desc);
return ERR_PTR(-EAGAIN);
}
IB_ACCESS_LOCAL_WRITE,
buf_desc);
if (rc) {
- smc_buf_free(buf_desc, lnk, is_rmb);
+ smc_buf_free(lgr, is_rmb, buf_desc);
return ERR_PTR(rc);
}
}
+ buf_desc->len = bufsize;
return buf_desc;
}
static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
{
+ struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
struct smc_connection *conn = &smc->conn;
struct smc_link_group *lgr = conn->lgr;
- struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
struct list_head *buf_list;
int bufsize, bufsize_short;
int sk_buf_size;
continue;
/* check for reusable slot in the link group */
- buf_desc = smc_buf_get_slot(lgr, bufsize_short, lock, buf_list);
+ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
if (buf_desc) {
memset(buf_desc->cpu_addr, 0, bufsize);
break; /* found reusable slot */
if (is_rmb) {
conn->rmb_desc = buf_desc;
- conn->rmbe_size = bufsize;
conn->rmbe_size_short = bufsize_short;
smc->sk.sk_rcvbuf = bufsize * 2;
atomic_set(&conn->bytes_to_rcv, 0);
conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
} else {
conn->sndbuf_desc = buf_desc;
- conn->sndbuf_size = bufsize;
smc->sk.sk_sndbuf = bufsize * 2;
atomic_set(&conn->sndbuf_space, bufsize);
}
/* create rmb */
rc = __smc_buf_create(smc, true);
if (rc)
- smc_buf_free(smc->conn.sndbuf_desc,
- &smc->conn.lgr->lnk[SMC_SINGLE_LINK], false);
+ smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
return rc;
}
return conn->rtoken_idx;
return 0;
}
+
+/* Called (from smc_exit) when module is removed */
+void smc_core_exit(void)
+{
+ struct smc_link_group *lgr, *lg;
+ LIST_HEAD(lgr_freeing_list);
+
+ spin_lock_bh(&smc_lgr_list.lock);
+ if (!list_empty(&smc_lgr_list.list))
+ list_splice_init(&smc_lgr_list.list, &lgr_freeing_list);
+ spin_unlock_bh(&smc_lgr_list.lock);
+ list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
+ list_del_init(&lgr->list);
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+ cancel_delayed_work_sync(&lgr->free_work);
+ smc_lgr_free(lgr); /* free link group */
+ }
+}
struct smc_lgr_list { /* list of link group definition */
struct list_head list;
spinlock_t lock; /* protects list of link groups */
+ u32 num; /* unique link group number */
};
-extern struct smc_lgr_list smc_lgr_list; /* list of link groups */
-
enum smc_lgr_role { /* possible roles of a link group */
SMC_CLNT, /* client */
SMC_SERV /* server */
dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */
u64 wr_rx_id; /* seq # of last recv WR */
u32 wr_rx_cnt; /* number of WR recv buffers */
+ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */
struct ib_reg_wr wr_reg; /* WR register memory region */
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
u8 link_id; /* unique # within link group */
enum smc_link_state state; /* state of link */
+ struct workqueue_struct *llc_wq; /* single thread work queue */
struct completion llc_confirm; /* wait for rx of conf link */
struct completion llc_confirm_resp; /* wait 4 rx of cnf lnk rsp */
int llc_confirm_rc; /* rc from confirm link msg */
int llc_confirm_resp_rc; /* rc from conf_resp msg */
struct completion llc_add; /* wait for rx of add link */
struct completion llc_add_resp; /* wait for rx of add link rsp*/
+ struct delayed_work llc_testlink_wrk; /* testlink worker */
+ struct completion llc_testlink_resp; /* wait for rx of testlink */
+ int llc_testlink_time; /* testlink interval */
+ struct completion llc_confirm_rkey; /* wait 4 rx of cnf rkey */
+ int llc_confirm_rkey_rc; /* rc from cnf rkey msg */
};
/* For now we just allow one parallel link per link group. The SMC protocol
struct smc_buf_desc {
struct list_head list;
void *cpu_addr; /* virtual address of buffer */
+ struct page *pages;
+ int len; /* length of buffer */
struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
/* for rmb only: memory region
*/
u32 order; /* allocation order */
u32 used; /* currently used / unused */
- bool reused; /* new created / reused */
+ u8 reused : 1; /* new created / reused */
+ u8 regerr : 1; /* err during registration */
};
struct smc_rtoken { /* address/key of remote RMB */
};
#define SMC_LGR_ID_SIZE 4
+#define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */
+#define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */
+/* theoretically, the RFC states that largest size would be 512K,
+ * i.e. compressed 5 and thus 6 sizes (0..5), despite
+ * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
+ */
struct smc_link_group {
struct list_head list;
u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */
struct delayed_work free_work; /* delayed freeing of an lgr */
- bool sync_err; /* lgr no longer fits to peer */
+ u8 sync_err : 1; /* lgr no longer fits to peer */
+ u8 terminating : 1;/* lgr is terminating */
};
/* Find the connection associated with the given alert token in the link group.
struct smc_sock;
struct smc_clc_msg_accept_confirm;
+struct smc_clc_msg_local;
void smc_lgr_free(struct smc_link_group *lgr);
void smc_lgr_forget(struct smc_link_group *lgr);
void smc_lgr_terminate(struct smc_link_group *lgr);
+void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
int smc_buf_create(struct smc_sock *smc);
+int smc_uncompress_bufsize(u8 compressed);
int smc_rmb_rtoken_handling(struct smc_connection *conn,
struct smc_clc_msg_accept_confirm *clc);
int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey);
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
+void smc_conn_free(struct smc_connection *conn);
+int smc_conn_create(struct smc_sock *smc,
+ struct smc_ib_device *smcibdev, u8 ibport,
+ struct smc_clc_msg_local *lcl, int srv_first_contact);
+void smc_core_exit(void);
#endif
{
struct smc_sock *smc = smc_sk(sk);
- r->diag_family = sk->sk_family;
if (!smc->clcsock)
return;
r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
r->id.idiag_dport = smc->clcsock->sk->sk_dport;
r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
sock_diag_save_cookie(sk, r->id.idiag_cookie);
- memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
- memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
- r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
- r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
+ if (sk->sk_protocol == SMCPROTO_SMC) {
+ r->diag_family = PF_INET;
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+ r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
+ r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_protocol == SMCPROTO_SMC6) {
+ r->diag_family = PF_INET6;
+ memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr,
+ sizeof(smc->clcsock->sk->sk_v6_rcv_saddr));
+ memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr,
+ sizeof(smc->clcsock->sk->sk_v6_daddr));
+#endif
+ }
}
static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
struct smc_connection *conn = &smc->conn;
struct smc_diag_conninfo cinfo = {
.token = conn->alert_token_local,
- .sndbuf_size = conn->sndbuf_size,
- .rmbe_size = conn->rmbe_size,
+ .sndbuf_size = conn->sndbuf_desc ?
+ conn->sndbuf_desc->len : 0,
+ .rmbe_size = conn->rmb_desc ? conn->rmb_desc->len : 0,
.peer_rmbe_size = conn->peer_rmbe_size,
.rx_prod.wrap = conn->local_rx_ctrl.prod.wrap,
return -EMSGSIZE;
}
-static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb,
+ struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct nlattr *bc = NULL;
struct sock *sk;
int rc = 0;
- read_lock(&smc_proto.h.smc_hash->lock);
- head = &smc_proto.h.smc_hash->ht;
+ read_lock(&prot->h.smc_hash->lock);
+ head = &prot->h.smc_hash->ht;
if (hlist_empty(head))
goto out;
}
out:
- read_unlock(&smc_proto.h.smc_hash->lock);
+ read_unlock(&prot->h.smc_hash->lock);
+ return rc;
+}
+
+static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ int rc = 0;
+
+ rc = smc_diag_dump_proto(&smc_proto, skb, cb);
+ if (!rc)
+ rc = smc_diag_dump_proto(&smc_proto6, skb, cb);
return rc;
}
return rc;
}
-static void smc_ib_port_terminate(struct smc_ib_device *smcibdev, u8 ibport)
-{
- struct smc_link_group *lgr, *l;
-
- list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
- if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
- lgr->lnk[SMC_SINGLE_LINK].ibport == ibport)
- smc_lgr_terminate(lgr);
- }
-}
-
/* process context wrapper for might_sleep smc_ib_remember_port_attr */
static void smc_ib_port_event_work(struct work_struct *work)
{
smc_ib_remember_port_attr(smcibdev, port_idx + 1);
clear_bit(port_idx, &smcibdev->port_event_mask);
if (!smc_ib_port_active(smcibdev, port_idx + 1))
- smc_ib_port_terminate(smcibdev, port_idx + 1);
+ smc_port_terminate(smcibdev, port_idx + 1);
}
}
return rc;
}
-/* send ADD LINK request or response */
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
- union ib_gid *gid,
- enum smc_llc_reqresp reqresp)
+/* send LLC confirm rkey request */
+static int smc_llc_send_confirm_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc)
{
- struct smc_llc_msg_add_link *addllc;
+ struct smc_llc_msg_confirm_rkey *rkeyllc;
struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
int rc;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
return rc;
- addllc = (struct smc_llc_msg_add_link *)wr_buf;
+ rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf;
+ memset(rkeyllc, 0, sizeof(*rkeyllc));
+ rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY;
+ rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey);
+ rkeyllc->rtoken[0].rmb_key =
+ htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ rkeyllc->rtoken[0].rmb_vaddr = cpu_to_be64(
+ (u64)sg_dma_address(rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+ /* send llc message */
+ rc = smc_wr_tx_send(link, pend);
+ return rc;
+}
+
+/* prepare an add link message */
+static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
+ struct smc_link *link, u8 mac[],
+ union ib_gid *gid,
+ enum smc_llc_reqresp reqresp)
+{
memset(addllc, 0, sizeof(*addllc));
addllc->hd.common.type = SMC_LLC_ADD_LINK;
addllc->hd.length = sizeof(struct smc_llc_msg_add_link);
}
memcpy(addllc->sender_mac, mac, ETH_ALEN);
memcpy(addllc->sender_gid, gid, SMC_GID_SIZE);
- /* send llc message */
- rc = smc_wr_tx_send(link, pend);
- return rc;
}
-/* send DELETE LINK request or response */
-int smc_llc_send_delete_link(struct smc_link *link,
- enum smc_llc_reqresp reqresp)
+/* send ADD LINK request or response */
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
+ union ib_gid *gid,
+ enum smc_llc_reqresp reqresp)
{
- struct smc_llc_msg_del_link *delllc;
+ struct smc_llc_msg_add_link *addllc;
struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
int rc;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
return rc;
- delllc = (struct smc_llc_msg_del_link *)wr_buf;
+ addllc = (struct smc_llc_msg_add_link *)wr_buf;
+ smc_llc_prep_add_link(addllc, link, mac, gid, reqresp);
+ /* send llc message */
+ rc = smc_wr_tx_send(link, pend);
+ return rc;
+}
+
+/* prepare a delete link message */
+static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
+ struct smc_link *link,
+ enum smc_llc_reqresp reqresp)
+{
memset(delllc, 0, sizeof(*delllc));
delllc->hd.common.type = SMC_LLC_DELETE_LINK;
delllc->hd.length = sizeof(struct smc_llc_msg_add_link);
delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL;
delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
delllc->link_num = link->link_id;
+}
+
+/* send DELETE LINK request or response */
+int smc_llc_send_delete_link(struct smc_link *link,
+ enum smc_llc_reqresp reqresp)
+{
+ struct smc_llc_msg_del_link *delllc;
+ struct smc_wr_tx_pend_priv *pend;
+ struct smc_wr_buf *wr_buf;
+ int rc;
+
+ rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+ if (rc)
+ return rc;
+ delllc = (struct smc_llc_msg_del_link *)wr_buf;
+ smc_llc_prep_delete_link(delllc, link, reqresp);
/* send llc message */
rc = smc_wr_tx_send(link, pend);
return rc;
}
-/* send LLC test link request or response */
-int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16],
- enum smc_llc_reqresp reqresp)
+/* send LLC test link request */
+static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16])
{
struct smc_llc_msg_test_link *testllc;
struct smc_wr_tx_pend_priv *pend;
memset(testllc, 0, sizeof(*testllc));
testllc->hd.common.type = SMC_LLC_TEST_LINK;
testllc->hd.length = sizeof(struct smc_llc_msg_test_link);
- if (reqresp == SMC_LLC_RESP)
- testllc->hd.flags |= SMC_LLC_FLAG_RESP;
memcpy(testllc->user_data, user_data, sizeof(testllc->user_data));
/* send llc message */
rc = smc_wr_tx_send(link, pend);
return rc;
}
-/* send a prepared message */
-static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
+struct smc_llc_send_work {
+ struct work_struct work;
+ struct smc_link *link;
+ int llclen;
+ union smc_llc_msg llcbuf;
+};
+
+/* worker that sends a prepared message */
+static void smc_llc_send_message_work(struct work_struct *work)
{
+ struct smc_llc_send_work *llcwrk = container_of(work,
+ struct smc_llc_send_work, work);
struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
int rc;
- rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+ if (llcwrk->link->state == SMC_LNK_INACTIVE)
+ goto out;
+ rc = smc_llc_add_pending_send(llcwrk->link, &wr_buf, &pend);
if (rc)
- return rc;
- memcpy(wr_buf, llcbuf, llclen);
- /* send llc message */
- rc = smc_wr_tx_send(link, pend);
- return rc;
+ goto out;
+ memcpy(wr_buf, &llcwrk->llcbuf, llcwrk->llclen);
+ smc_wr_tx_send(llcwrk->link, pend);
+out:
+ kfree(llcwrk);
+}
+
+/* copy llcbuf and schedule an llc send on link */
+static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
+{
+ struct smc_llc_send_work *wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+
+ if (!wrk)
+ return -ENOMEM;
+ INIT_WORK(&wrk->work, smc_llc_send_message_work);
+ wrk->link = link;
+ wrk->llclen = llclen;
+ memcpy(&wrk->llcbuf, llcbuf, llclen);
+ queue_work(link->llc_wq, &wrk->work);
+ return 0;
}
/********************************* receive ***********************************/
}
if (lgr->role == SMC_SERV) {
- smc_llc_send_add_link(link,
+ smc_llc_prep_add_link(llc, link,
link->smcibdev->mac[link->ibport - 1],
&link->smcibdev->gid[link->ibport - 1],
SMC_LLC_REQ);
} else {
- smc_llc_send_add_link(link,
+ smc_llc_prep_add_link(llc, link,
link->smcibdev->mac[link->ibport - 1],
&link->smcibdev->gid[link->ibport - 1],
SMC_LLC_RESP);
}
+ smc_llc_send_message(link, llc, sizeof(*llc));
}
}
} else {
if (lgr->role == SMC_SERV) {
smc_lgr_forget(lgr);
- smc_llc_send_delete_link(link, SMC_LLC_REQ);
+ smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ);
+ smc_llc_send_message(link, llc, sizeof(*llc));
} else {
- smc_llc_send_delete_link(link, SMC_LLC_RESP);
+ smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP);
+ smc_llc_send_message(link, llc, sizeof(*llc));
smc_lgr_terminate(lgr);
}
}
struct smc_llc_msg_test_link *llc)
{
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
- /* unused as long as we don't send this type of msg */
+ if (link->state == SMC_LNK_ACTIVE)
+ complete(&link->llc_testlink_resp);
} else {
- smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP);
+ llc->hd.flags |= SMC_LLC_FLAG_RESP;
+ smc_llc_send_message(link, llc, sizeof(*llc));
}
}
lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
- /* unused as long as we don't send this type of msg */
+ link->llc_confirm_rkey_rc = llc->hd.flags &
+ SMC_LLC_FLAG_RKEY_NEG;
+ complete(&link->llc_confirm_rkey);
} else {
rc = smc_rtoken_add(lgr,
llc->rtoken[0].rmb_vaddr,
llc->hd.flags |= SMC_LLC_FLAG_RESP;
if (rc < 0)
llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG;
- smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+ smc_llc_send_message(link, llc, sizeof(*llc));
}
}
} else {
/* ignore rtokens for other links, we have only one link */
llc->hd.flags |= SMC_LLC_FLAG_RESP;
- smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+ smc_llc_send_message(link, llc, sizeof(*llc));
}
}
}
llc->hd.flags |= SMC_LLC_FLAG_RESP;
- smc_llc_send_message(link, (void *)llc, sizeof(*llc));
+ smc_llc_send_message(link, llc, sizeof(*llc));
}
}
return; /* short message */
if (llc->raw.hdr.length != sizeof(*llc))
return; /* invalid message */
+ if (link->state == SMC_LNK_INACTIVE)
+ return; /* link not active, drop msg */
switch (llc->raw.hdr.common.type) {
case SMC_LLC_TEST_LINK:
}
}
+/***************************** worker, utils *********************************/
+
+static void smc_llc_testlink_work(struct work_struct *work)
+{
+ struct smc_link *link = container_of(to_delayed_work(work),
+ struct smc_link, llc_testlink_wrk);
+ unsigned long next_interval;
+ struct smc_link_group *lgr;
+ unsigned long expire_time;
+ u8 user_data[16] = { 0 };
+ int rc;
+
+ lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+ if (link->state != SMC_LNK_ACTIVE)
+ return; /* don't reschedule worker */
+ expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
+ if (time_is_after_jiffies(expire_time)) {
+ next_interval = expire_time - jiffies;
+ goto out;
+ }
+ reinit_completion(&link->llc_testlink_resp);
+ smc_llc_send_test_link(link, user_data);
+ /* receive TEST LINK response over RoCE fabric */
+ rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
+ SMC_LLC_WAIT_TIME);
+ if (rc <= 0) {
+ smc_lgr_terminate(lgr);
+ return;
+ }
+ next_interval = link->llc_testlink_time;
+out:
+ queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+ next_interval);
+}
+
+int smc_llc_link_init(struct smc_link *link)
+{
+ struct smc_link_group *lgr = container_of(link, struct smc_link_group,
+ lnk[SMC_SINGLE_LINK]);
+ link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM,
+ *((u32 *)lgr->id),
+ link->link_id);
+ if (!link->llc_wq)
+ return -ENOMEM;
+ init_completion(&link->llc_confirm);
+ init_completion(&link->llc_confirm_resp);
+ init_completion(&link->llc_add);
+ init_completion(&link->llc_add_resp);
+ init_completion(&link->llc_confirm_rkey);
+ init_completion(&link->llc_testlink_resp);
+ INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
+ return 0;
+}
+
+void smc_llc_link_active(struct smc_link *link, int testlink_time)
+{
+ link->state = SMC_LNK_ACTIVE;
+ if (testlink_time) {
+ link->llc_testlink_time = testlink_time * HZ;
+ queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk,
+ link->llc_testlink_time);
+ }
+}
+
+/* called in tasklet context */
+void smc_llc_link_inactive(struct smc_link *link)
+{
+ link->state = SMC_LNK_INACTIVE;
+ cancel_delayed_work(&link->llc_testlink_wrk);
+}
+
+/* called in worker context */
+void smc_llc_link_clear(struct smc_link *link)
+{
+ flush_workqueue(link->llc_wq);
+ destroy_workqueue(link->llc_wq);
+}
+
+/* register a new rtoken at the remote peer */
+int smc_llc_do_confirm_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc)
+{
+ int rc;
+
+ reinit_completion(&link->llc_confirm_rkey);
+ smc_llc_send_confirm_rkey(link, rmb_desc);
+ /* receive CONFIRM RKEY response from server over RoCE fabric */
+ rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey,
+ SMC_LLC_WAIT_TIME);
+ if (rc <= 0 || link->llc_confirm_rkey_rc)
+ return -EFAULT;
+ return 0;
+}
+
/***************************** init, exit, misc ******************************/
static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {
enum smc_llc_reqresp reqresp);
int smc_llc_send_delete_link(struct smc_link *link,
enum smc_llc_reqresp reqresp);
-int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16],
- enum smc_llc_reqresp reqresp);
+int smc_llc_link_init(struct smc_link *link);
+void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_inactive(struct smc_link *link);
+void smc_llc_link_clear(struct smc_link *link);
+int smc_llc_do_confirm_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc);
int smc_llc_init(void) __init;
#endif /* SMC_LLC_H */
static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
struct nlattr *tb[])
{
- char *string, *ibname = NULL;
- int rc = 0;
+ char *string, *ibname;
+ int rc;
memset(pnetelem, 0, sizeof(*pnetelem));
INIT_LIST_HEAD(&pnetelem->list);
- if (tb[SMC_PNETID_NAME]) {
- string = (char *)nla_data(tb[SMC_PNETID_NAME]);
- if (!smc_pnetid_valid(string, pnetelem->pnet_name)) {
- rc = -EINVAL;
- goto error;
- }
- }
- if (tb[SMC_PNETID_ETHNAME]) {
- string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
- pnetelem->ndev = dev_get_by_name(net, string);
- if (!pnetelem->ndev)
- return -ENOENT;
- }
- if (tb[SMC_PNETID_IBNAME]) {
- ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
- ibname = strim(ibname);
- pnetelem->smcibdev = smc_pnet_find_ib(ibname);
- if (!pnetelem->smcibdev) {
- rc = -ENOENT;
- goto error;
- }
- }
- if (tb[SMC_PNETID_IBPORT]) {
- pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
- if (pnetelem->ib_port > SMC_MAX_PORTS) {
- rc = -EINVAL;
- goto error;
- }
- }
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_NAME])
+ goto error;
+ string = (char *)nla_data(tb[SMC_PNETID_NAME]);
+ if (!smc_pnetid_valid(string, pnetelem->pnet_name))
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_ETHNAME])
+ goto error;
+ rc = -ENOENT;
+ string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+ pnetelem->ndev = dev_get_by_name(net, string);
+ if (!pnetelem->ndev)
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_IBNAME])
+ goto error;
+ rc = -ENOENT;
+ ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+ ibname = strim(ibname);
+ pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+ if (!pnetelem->smcibdev)
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_IBPORT])
+ goto error;
+ pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+ if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
+ goto error;
+
return 0;
error:
void *hdr;
int rc;
+ if (!info->attrs[SMC_PNETID_NAME])
+ return -EINVAL;
pnetelem = smc_pnet_find_pnetid(
(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
if (!pnetelem)
static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
{
+ if (!info->attrs[SMC_PNETID_NAME])
+ return -EINVAL;
return smc_pnet_remove_by_pnetid(
(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
}
#include "smc_tx.h" /* smc_tx_consumer_update() */
#include "smc_rx.h"
-/* callback implementation for sk.sk_data_ready()
- * to wakeup rcvbuf consumers that blocked with smc_rx_wait_data().
+/* callback implementation to wakeup consumers blocked with smc_rx_wait().
* indirectly called by smc_cdc_msg_recv_action().
*/
-static void smc_rx_data_ready(struct sock *sk)
+static void smc_rx_wake_up(struct sock *sk)
{
struct socket_wq *wq;
rcu_read_unlock();
}
+/* Update consumer cursor
+ * @conn connection to update
+ * @cons consumer cursor
+ * @len number of Bytes consumed
+ */
+static void smc_rx_update_consumer(struct smc_connection *conn,
+ union smc_host_cursor cons, size_t len)
+{
+ smc_curs_add(conn->rmb_desc->len, &cons, len);
+ smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
+ conn);
+ /* send consumer cursor update if required */
+ /* similar to advertising new TCP rcv_wnd if required */
+ smc_tx_consumer_update(conn);
+}
+
+struct smc_spd_priv {
+ struct smc_sock *smc;
+ size_t len;
+};
+
+static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private;
+ struct smc_sock *smc = priv->smc;
+ struct smc_connection *conn;
+ union smc_host_cursor cons;
+ struct sock *sk = &smc->sk;
+
+ if (sk->sk_state == SMC_CLOSED ||
+ sk->sk_state == SMC_PEERFINCLOSEWAIT ||
+ sk->sk_state == SMC_APPFINCLOSEWAIT)
+ goto out;
+ conn = &smc->conn;
+ lock_sock(sk);
+ smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn),
+ conn);
+ smc_rx_update_consumer(conn, cons, priv->len);
+ release_sock(sk);
+ if (atomic_sub_and_test(priv->len, &conn->splice_pending))
+ smc_rx_wake_up(sk);
+out:
+ kfree(priv);
+ put_page(buf->page);
+ sock_put(sk);
+}
+
+static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+static const struct pipe_buf_operations smc_pipe_ops = {
+ .can_merge = 0,
+ .confirm = generic_pipe_buf_confirm,
+ .release = smc_rx_pipe_buf_release,
+ .steal = smc_rx_pipe_buf_nosteal,
+ .get = generic_pipe_buf_get
+};
+
+static void smc_rx_spd_release(struct splice_pipe_desc *spd,
+ unsigned int i)
+{
+ put_page(spd->pages[i]);
+}
+
+static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
+ struct smc_sock *smc)
+{
+ struct splice_pipe_desc spd;
+ struct partial_page partial;
+ struct smc_spd_priv *priv;
+ struct page *page;
+ int bytes;
+
+ page = virt_to_page(smc->conn.rmb_desc->cpu_addr);
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+ priv->len = len;
+ priv->smc = smc;
+ partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr;
+ partial.len = len;
+ partial.private = (unsigned long)priv;
+
+ spd.nr_pages_max = 1;
+ spd.nr_pages = 1;
+ spd.pages = &page;
+ spd.partial = &partial;
+ spd.ops = &smc_pipe_ops;
+ spd.spd_release = smc_rx_spd_release;
+
+ bytes = splice_to_pipe(pipe, &spd);
+ if (bytes > 0) {
+ sock_hold(&smc->sk);
+ get_page(smc->conn.rmb_desc->pages);
+ atomic_add(bytes, &smc->conn.splice_pending);
+ }
+
+ return bytes;
+}
+
+static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn)
+{
+ return atomic_read(&conn->bytes_to_rcv) &&
+ !atomic_read(&conn->splice_pending);
+}
+
/* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted
* @smc smc socket
* @timeo pointer to max seconds to wait, pointer to value 0 for no timeout
+ * @fcrit add'l criterion to evaluate as function pointer
* Returns:
* 1 if at least 1 byte available in rcvbuf or if socket error/shutdown.
* 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted).
*/
-static int smc_rx_wait_data(struct smc_sock *smc, long *timeo)
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+ int (*fcrit)(struct smc_connection *conn))
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
int rc;
- if (atomic_read(&conn->bytes_to_rcv))
+ if (fcrit(conn))
return 1;
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
add_wait_queue(sk_sleep(sk), &wait);
rc = sk_wait_event(sk, timeo,
sk->sk_err ||
sk->sk_shutdown & RCV_SHUTDOWN ||
- atomic_read(&conn->bytes_to_rcv) ||
+ fcrit(conn) ||
smc_cdc_rxed_any_close_or_senddone(conn),
&wait);
remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
-/* rcvbuf consumer: main API called by socket layer.
- * called under sk lock.
+/* smc_rx_recvmsg - receive data from RMBE
+ * @msg: copy data to receive buffer
+ * @pipe: copy data to pipe if set - indicates splice() call
+ *
+ * rcvbuf consumer: main API called by socket layer.
+ * Called under sk lock.
*/
-int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
- int flags)
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+ struct pipe_inode_info *pipe, size_t len, int flags)
{
size_t copylen, read_done = 0, read_remaining = len;
size_t chunk_len, chunk_off, chunk_len_sum;
struct smc_connection *conn = &smc->conn;
+ int (*func)(struct smc_connection *conn);
union smc_host_cursor cons;
int readable, chunk;
char *rcvbuf_base;
struct sock *sk;
+ int splbytes;
long timeo;
int target; /* Read at least these many bytes */
int rc;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
- msg->msg_namelen = 0;
/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
rcvbuf_base = conn->rmb_desc->cpu_addr;
do { /* while (read_remaining) */
- if (read_done >= target)
+ if (read_done >= target || (pipe && read_done))
break;
if (atomic_read(&conn->bytes_to_rcv))
goto copy;
+ if (sk->sk_shutdown & RCV_SHUTDOWN ||
+ smc_cdc_rxed_any_close_or_senddone(conn) ||
+ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+ break;
+
if (read_done) {
if (sk->sk_err ||
sk->sk_state == SMC_CLOSED ||
- sk->sk_shutdown & RCV_SHUTDOWN ||
!timeo ||
- signal_pending(current) ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.
- peer_conn_abort)
+ signal_pending(current))
break;
} else {
if (sk->sk_err) {
read_done = sock_error(sk);
break;
}
- if (sk->sk_shutdown & RCV_SHUTDOWN ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.
- peer_conn_abort)
- break;
if (sk->sk_state == SMC_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
return -EAGAIN;
}
- if (!atomic_read(&conn->bytes_to_rcv)) {
- smc_rx_wait_data(smc, &timeo);
+ if (!smc_rx_data_available(conn)) {
+ smc_rx_wait(smc, &timeo, smc_rx_data_available);
continue;
}
copy:
/* initialize variables for 1st iteration of subsequent loop */
- /* could be just 1 byte, even after smc_rx_wait_data above */
+ /* could be just 1 byte, even after waiting on data above */
readable = atomic_read(&conn->bytes_to_rcv);
+ splbytes = atomic_read(&conn->splice_pending);
+ if (!readable || (msg && splbytes)) {
+ if (splbytes)
+ func = smc_rx_data_available_and_no_splice_pend;
+ else
+ func = smc_rx_data_available;
+ smc_rx_wait(smc, &timeo, func);
+ continue;
+ }
+
/* not more than what user space asked for */
copylen = min_t(size_t, read_remaining, readable);
smc_curs_write(&cons,
smc_curs_read(&conn->local_tx_ctrl.cons, conn),
conn);
+ /* subsequent splice() calls pick up where previous left */
+ if (splbytes)
+ smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
/* determine chunks where to read from rcvbuf */
/* either unwrapped case, or 1st chunk of wrapped case */
- chunk_len = min_t(size_t,
- copylen, conn->rmbe_size - cons.count);
+ chunk_len = min_t(size_t, copylen, conn->rmb_desc->len -
+ cons.count);
chunk_len_sum = chunk_len;
chunk_off = cons.count;
smc_rmb_sync_sg_for_cpu(conn);
for (chunk = 0; chunk < 2; chunk++) {
if (!(flags & MSG_TRUNC)) {
- rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off,
- chunk_len);
- if (rc) {
+ if (msg) {
+ rc = memcpy_to_msg(msg, rcvbuf_base +
+ chunk_off,
+ chunk_len);
+ } else {
+ rc = smc_rx_splice(pipe, rcvbuf_base +
+ chunk_off, chunk_len,
+ smc);
+ }
+ if (rc < 0) {
if (!read_done)
read_done = -EFAULT;
smc_rmb_sync_sg_for_device(conn);
/* update cursors */
if (!(flags & MSG_PEEK)) {
- smc_curs_add(conn->rmbe_size, &cons, copylen);
/* increased in recv tasklet smc_cdc_msg_rcv() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->bytes_to_rcv);
- /* guarantee 0 <= bytes_to_rcv <= rmbe_size */
+ /* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
smp_mb__after_atomic();
- smc_curs_write(&conn->local_tx_ctrl.cons,
- smc_curs_read(&cons, conn),
- conn);
- /* send consumer cursor update if required */
- /* similar to advertising new TCP rcv_wnd if required */
- smc_tx_consumer_update(conn);
+ if (msg)
+ smc_rx_update_consumer(conn, cons, copylen);
}
} while (read_remaining);
out:
/* Initialize receive properties on connection establishment. NB: not __init! */
void smc_rx_init(struct smc_sock *smc)
{
- smc->sk.sk_data_ready = smc_rx_data_ready;
+ smc->sk.sk_data_ready = smc_rx_wake_up;
+ atomic_set(&smc->conn.splice_pending, 0);
}
#include "smc.h"
void smc_rx_init(struct smc_sock *smc);
-int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
- int flags);
+
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+ struct pipe_inode_info *pipe, size_t len, int flags);
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+ int (*fcrit)(struct smc_connection *conn));
+static inline int smc_rx_data_available(struct smc_connection *conn)
+{
+ return atomic_read(&conn->bytes_to_rcv);
+}
#endif /* SMC_RX_H */
#include <linux/sched/signal.h>
#include <net/sock.h>
+#include <net/tcp.h>
#include "smc.h"
#include "smc_wr.h"
#include "smc_tx.h"
#define SMC_TX_WORK_DELAY HZ
+#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */
/***************************** sndbuf producer *******************************/
return rc;
}
+static bool smc_tx_is_corked(struct smc_sock *smc)
+{
+ struct tcp_sock *tp = tcp_sk(smc->clcsock->sk);
+
+ return (tp->nonagle & TCP_NAGLE_CORK) ? true : false;
+}
+
/* sndbuf producer: main API called by socket layer.
* called under sock lock.
*/
tx_cnt_prep = prep.count;
/* determine chunks where to write into sndbuf */
/* either unwrapped case, or 1st chunk of wrapped case */
- chunk_len = min_t(size_t,
- copylen, conn->sndbuf_size - tx_cnt_prep);
+ chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len -
+ tx_cnt_prep);
chunk_len_sum = chunk_len;
chunk_off = tx_cnt_prep;
smc_sndbuf_sync_sg_for_cpu(conn);
}
smc_sndbuf_sync_sg_for_device(conn);
/* update cursors */
- smc_curs_add(conn->sndbuf_size, &prep, copylen);
+ smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
smc_curs_write(&conn->tx_curs_prep,
smc_curs_read(&prep, conn),
conn);
/* increased in send tasklet smc_cdc_tx_handler() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->sndbuf_space);
- /* guarantee 0 <= sndbuf_space <= sndbuf_size */
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
smp_mb__after_atomic();
/* since we just produced more new data into sndbuf,
* trigger sndbuf consumer: RDMA write into peer RMBE and CDC
*/
- smc_tx_sndbuf_nonempty(conn);
+ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
+ (atomic_read(&conn->sndbuf_space) >
+ (conn->sndbuf_desc->len >> 1)))
+ /* for a corked socket defer the RDMA writes if there
+ * is still sufficient sndbuf_space available
+ */
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_CORK_DELAY);
+ else
+ smc_tx_sndbuf_nonempty(conn);
} /* while (msg_data_left(msg)) */
return send_done;
rdma_wr.remote_addr =
lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr +
/* RMBE within RMB */
- ((conn->peer_conn_idx - 1) * conn->peer_rmbe_size) +
+ conn->tx_off +
/* offset within RMBE */
peer_rmbe_offset;
rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
atomic_sub(len, &conn->peer_rmbe_space);
/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
smp_mb__after_atomic();
- smc_curs_add(conn->sndbuf_size, sent, len);
+ smc_curs_add(conn->sndbuf_desc->len, sent, len);
}
/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
/* cf. wmem_alloc - (snd_max - snd_una) */
- to_send = smc_curs_diff(conn->sndbuf_size, &sent, &prep);
+ to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
if (to_send <= 0)
return 0;
dst_len_sum = dst_len;
src_off = sent.count;
/* dst_len determines the maximum src_len */
- if (sent.count + dst_len <= conn->sndbuf_size) {
+ if (sent.count + dst_len <= conn->sndbuf_desc->len) {
/* unwrapped src case: single chunk of entire dst_len */
src_len = dst_len;
} else {
/* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
- src_len = conn->sndbuf_size - sent.count;
+ src_len = conn->sndbuf_desc->len - sent.count;
}
src_len_sum = src_len;
dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
num_sges++;
src_off += src_len;
- if (src_off >= conn->sndbuf_size)
- src_off -= conn->sndbuf_size;
+ if (src_off >= conn->sndbuf_desc->len)
+ src_off -= conn->sndbuf_desc->len;
/* modulo in send ring */
if (src_len_sum == dst_len)
break; /* either on 1st or 2nd iteration */
dst_len = len - dst_len; /* remainder */
dst_len_sum += dst_len;
src_len = min_t(int,
- dst_len, conn->sndbuf_size - sent.count);
+ dst_len, conn->sndbuf_desc->len - sent.count);
src_len_sum = src_len;
}
}
rc = 0;
if (conn->alert_token_local) /* connection healthy */
- schedule_delayed_work(&conn->tx_work,
- SMC_TX_WORK_DELAY);
+ mod_delayed_work(system_wq, &conn->tx_work,
+ SMC_TX_WORK_DELAY);
}
goto out_unlock;
}
/* Wakeup sndbuf consumers from process context
* since there is more data to transmit
*/
-static void smc_tx_work(struct work_struct *work)
+void smc_tx_work(struct work_struct *work)
{
struct smc_connection *conn = container_of(to_delayed_work(work),
struct smc_connection,
smc_curs_write(&cfed,
smc_curs_read(&conn->rx_curs_confirmed, conn),
conn);
- to_confirm = smc_curs_diff(conn->rmbe_size, &cfed, &cons);
+ to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
((to_confirm > conn->rmbe_update_limit) &&
- ((to_confirm > (conn->rmbe_size / 2)) ||
+ ((to_confirm > (conn->rmb_desc->len / 2)) ||
conn->local_rx_ctrl.prod_flags.write_blocked))) {
if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
conn->alert_token_local) { /* connection healthy */
void smc_tx_init(struct smc_sock *smc)
{
smc->sk.sk_write_space = smc_tx_write_space;
- INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
- spin_lock_init(&smc->conn.send_lock);
}
smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
- return smc_curs_diff(conn->sndbuf_size, &sent, &prep);
+ return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
}
+void smc_tx_work(struct work_struct *work);
void smc_tx_init(struct smc_sock *smc);
int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
for (i = 0; i < num; i++) {
link = wc[i].qp->qp_context;
if (wc[i].status == IB_WC_SUCCESS) {
+ link->wr_rx_tstamp = jiffies;
smc_wr_rx_demultiplex(&wc[i]);
smc_wr_rx_post(link); /* refill WR RX */
} else {
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}
if (IS_ERR(mr->fmr.fm_mr))
goto out_fmr_err;
+ INIT_LIST_HEAD(&mr->mr_list);
return 0;
out_fmr_err:
LIST_HEAD(unmap_list);
int rc;
- /* Ensure MW is not on any rl_registered list */
- if (!list_empty(&mr->mr_list))
- list_del(&mr->mr_list);
-
kfree(mr->fmr.fm_physaddrs);
kfree(mr->mr_sg);
if (!mr->mr_sg)
goto out_list_err;
+ INIT_LIST_HEAD(&mr->mr_list);
sg_init_table(mr->mr_sg, depth);
init_completion(&frwr->fr_linv_done);
return 0;
{
int rc;
- /* Ensure MR is not on any rl_registered list */
- if (!list_empty(&mr->mr_list))
- list_del(&mr->mr_list);
-
rc = ib_dereg_mr(mr->frwr.fr_mr);
if (rc)
pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
return;
out_release:
- pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr);
+ pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr);
r_xprt->rx_stats.mrs_orphaned++;
spin_lock(&r_xprt->rx_buf.rb_mrlock);
list_for_each_entry(mr, mrs, mr_list)
if (mr->mr_handle == rep->rr_inv_rkey) {
- list_del(&mr->mr_list);
+ list_del_init(&mr->mr_list);
trace_xprtrdma_remoteinv(mr);
mr->frwr.fr_state = FRWR_IS_INVALID;
rpcrdma_mr_unmap_and_put(mr);
list_del(&mr->mr_all);
spin_unlock(&buf->rb_mrlock);
+
+ /* Ensure MW is not on any rl_registered list */
+ if (!list_empty(&mr->mr_list))
+ list_del(&mr->mr_list);
+
ia->ri_ops->ro_release_mr(mr);
count++;
spin_lock(&buf->rb_mrlock);
struct rpcrdma_mr *mr;
mr = list_first_entry(list, struct rpcrdma_mr, mr_list);
- list_del(&mr->mr_list);
+ list_del_init(&mr->mr_list);
return mr;
}
}
/**
- * tipc_service_find_range - find service range matching a service instance
+ * tipc_service_first_range - find first service range in tree matching instance
*
* Very time-critical, so binary search through range rb tree
*/
-static struct service_range *tipc_service_find_range(struct tipc_service *sc,
- u32 instance)
+static struct service_range *tipc_service_first_range(struct tipc_service *sc,
+ u32 instance)
{
struct rb_node *n = sc->ranges.rb_node;
struct service_range *sr;
return NULL;
}
+/* tipc_service_find_range - find service range matching publication parameters
+ */
+static struct service_range *tipc_service_find_range(struct tipc_service *sc,
+ u32 lower, u32 upper)
+{
+ struct rb_node *n = sc->ranges.rb_node;
+ struct service_range *sr;
+
+ sr = tipc_service_first_range(sc, lower);
+ if (!sr)
+ return NULL;
+
+ /* Look for exact match */
+ for (n = &sr->tree_node; n; n = rb_next(n)) {
+ sr = container_of(n, struct service_range, tree_node);
+ if (sr->upper == upper)
+ break;
+ }
+ if (!n || sr->lower != lower || sr->upper != upper)
+ return NULL;
+
+ return sr;
+}
+
static struct service_range *tipc_service_create_range(struct tipc_service *sc,
u32 lower, u32 upper)
{
/**
* tipc_service_remove_publ - remove a publication from a service
*/
-static struct publication *tipc_service_remove_publ(struct net *net,
- struct tipc_service *sc,
- u32 lower, u32 upper,
- u32 node, u32 key,
- struct service_range **rng)
+static struct publication *tipc_service_remove_publ(struct service_range *sr,
+ u32 node, u32 key)
{
- struct tipc_subscription *sub, *tmp;
- struct service_range *sr;
struct publication *p;
- bool found = false;
- bool last = false;
- struct rb_node *n;
-
- sr = tipc_service_find_range(sc, lower);
- if (!sr)
- return NULL;
- /* Find exact matching service range */
- for (n = &sr->tree_node; n; n = rb_next(n)) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->upper == upper)
- break;
- }
- if (!n || sr->lower != lower || sr->upper != upper)
- return NULL;
-
- /* Find publication, if it exists */
list_for_each_entry(p, &sr->all_publ, all_publ) {
if (p->key != key || (node && node != p->node))
continue;
- found = true;
- break;
+ list_del(&p->all_publ);
+ list_del(&p->local_publ);
+ return p;
}
- if (!found)
- return NULL;
-
- list_del(&p->all_publ);
- list_del(&p->local_publ);
- if (list_empty(&sr->all_publ))
- last = true;
-
- /* Notify any waiting subscriptions */
- list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
- tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN,
- p->port, p->node, p->scope, last);
- }
- *rng = sr;
- return p;
+ return NULL;
}
/**
u32 node, u32 key)
{
struct tipc_service *sc = tipc_service_find(net, type);
+ struct tipc_subscription *sub, *tmp;
struct service_range *sr = NULL;
struct publication *p = NULL;
+ bool last;
if (!sc)
return NULL;
spin_lock_bh(&sc->lock);
- p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr);
+ sr = tipc_service_find_range(sc, lower, upper);
+ if (!sr)
+ goto exit;
+ p = tipc_service_remove_publ(sr, node, key);
+ if (!p)
+ goto exit;
+
+ /* Notify any waiting subscriptions */
+ last = list_empty(&sr->all_publ);
+ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
+ tipc_sub_report_overlap(sub, lower, upper, TIPC_WITHDRAWN,
+ p->port, node, p->scope, last);
+ }
/* Remove service range item if this was its last publication */
- if (sr && list_empty(&sr->all_publ)) {
+ if (list_empty(&sr->all_publ)) {
rb_erase(&sr->tree_node, &sc->ranges);
kfree(sr);
}
hlist_del_init_rcu(&sc->service_list);
kfree_rcu(sc, rcu);
}
+exit:
spin_unlock_bh(&sc->lock);
return p;
}
goto not_found;
spin_lock_bh(&sc->lock);
- sr = tipc_service_find_range(sc, instance);
+ sr = tipc_service_first_range(sc, instance);
if (unlikely(!sr))
goto no_match;
spin_lock_bh(&sc->lock);
- sr = tipc_service_find_range(sc, instance);
+ sr = tipc_service_first_range(sc, instance);
if (!sr)
goto no_match;
spin_lock_bh(&sc->lock);
rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) {
list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) {
- tipc_service_remove_publ(net, sc, p->lower, p->upper,
- p->node, p->key, &sr);
+ tipc_service_remove_publ(sr, p->node, p->key);
kfree_rcu(p, rcu);
}
rb_erase(&sr->tree_node, &sc->ranges);
return mtu;
}
+bool tipc_node_get_id(struct net *net, u32 addr, u8 *id)
+{
+ u8 *own_id = tipc_own_id(net);
+ struct tipc_node *n;
+
+ if (!own_id)
+ return true;
+
+ if (addr == tipc_own_addr(net)) {
+ memcpy(id, own_id, TIPC_NODEID_LEN);
+ return true;
+ }
+ n = tipc_node_find(net, addr);
+ if (!n)
+ return false;
+
+ memcpy(id, &n->peer_id, TIPC_NODEID_LEN);
+ tipc_node_put(n);
+ return true;
+}
+
u16 tipc_node_get_capabilities(struct net *net, u32 addr)
{
struct tipc_node *n;
int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
+ struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
struct tipc_nl_msg msg;
char *name;
int err;
msg.portid = info->snd_portid;
msg.seq = info->snd_seq;
- if (!info->attrs[TIPC_NLA_LINK_NAME])
+ if (!info->attrs[TIPC_NLA_LINK])
+ return -EINVAL;
+
+ err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+ info->attrs[TIPC_NLA_LINK],
+ tipc_nl_link_policy, info->extack);
+ if (err)
+ return err;
+
+ if (!attrs[TIPC_NLA_LINK_NAME])
return -EINVAL;
- name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]);
+
+ name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!msg.skb)
rtnl_lock();
for (bearer_id = prev_bearer; bearer_id < MAX_BEARERS; bearer_id++) {
- err = __tipc_nl_add_monitor(net, &msg, prev_bearer);
+ err = __tipc_nl_add_monitor(net, &msg, bearer_id);
if (err)
break;
}
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
+bool tipc_node_get_id(struct net *net, u32 addr, u8 *id);
u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr);
void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128,
struct tipc_bearer *bearer,
srcaddr->sock.family = AF_TIPC;
srcaddr->sock.addrtype = TIPC_ADDR_ID;
+ srcaddr->sock.scope = 0;
srcaddr->sock.addr.id.ref = msg_origport(hdr);
srcaddr->sock.addr.id.node = msg_orignode(hdr);
srcaddr->sock.addr.name.domain = 0;
- srcaddr->sock.scope = 0;
m->msg_namelen = sizeof(struct sockaddr_tipc);
if (!msg_in_group(hdr))
/* Group message users may also want to know sending member's id */
srcaddr->member.family = AF_TIPC;
srcaddr->member.addrtype = TIPC_ADDR_NAME;
+ srcaddr->member.scope = 0;
srcaddr->member.addr.name.name.type = msg_nametype(hdr);
srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
srcaddr->member.addr.name.domain = 0;
static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
- struct sock *sk = sock->sk;
+ struct net *net = sock_net(sock->sk);
+ struct tipc_sioc_nodeid_req nr = {0};
struct tipc_sioc_ln_req lnr;
void __user *argp = (void __user *)arg;
case SIOCGETLINKNAME:
if (copy_from_user(&lnr, argp, sizeof(lnr)))
return -EFAULT;
- if (!tipc_node_get_linkname(sock_net(sk),
+ if (!tipc_node_get_linkname(net,
lnr.bearer_id & 0xffff, lnr.peer,
lnr.linkname, TIPC_MAX_LINK_NAME)) {
if (copy_to_user(argp, &lnr, sizeof(lnr)))
return 0;
}
return -EADDRNOTAVAIL;
+ case SIOCGETNODEID:
+ if (copy_from_user(&nr, argp, sizeof(nr)))
+ return -EFAULT;
+ if (!tipc_node_get_id(net, nr.peer, nr.node_id))
+ return -EADDRNOTAVAIL;
+ if (copy_to_user(argp, &nr, sizeof(nr)))
+ return -EFAULT;
+ return 0;
default:
return -ENOIOCTLCMD;
}
encryption handling of the TLS protocol to be done in-kernel.
If unsure, say N.
+
+config TLS_DEVICE
+ bool "Transport Layer Security HW offload"
+ depends on TLS
+ select SOCK_VALIDATE_XMIT
+ default n
+ help
+ Enable kernel support for HW offload of the TLS protocol.
+
+ If unsure, say N.
obj-$(CONFIG_TLS) += tls.o
tls-y := tls_main.o tls_sw.o
+
+tls-$(CONFIG_TLS_DEVICE) += tls_device.o tls_device_fallback.o
--- /dev/null
+/* Copyright (c) 2018, Mellanox Technologies All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <crypto/aead.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <net/dst.h>
+#include <net/inet_connection_sock.h>
+#include <net/tcp.h>
+#include <net/tls.h>
+
+/* device_offload_lock is used to synchronize tls_dev_add
+ * against NETDEV_DOWN notifications.
+ */
+static DECLARE_RWSEM(device_offload_lock);
+
+static void tls_device_gc_task(struct work_struct *work);
+
+static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task);
+static LIST_HEAD(tls_device_gc_list);
+static LIST_HEAD(tls_device_list);
+static DEFINE_SPINLOCK(tls_device_lock);
+
+static void tls_device_free_ctx(struct tls_context *ctx)
+{
+ struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx);
+
+ kfree(offload_ctx);
+ kfree(ctx);
+}
+
+static void tls_device_gc_task(struct work_struct *work)
+{
+ struct tls_context *ctx, *tmp;
+ unsigned long flags;
+ LIST_HEAD(gc_list);
+
+ spin_lock_irqsave(&tls_device_lock, flags);
+ list_splice_init(&tls_device_gc_list, &gc_list);
+ spin_unlock_irqrestore(&tls_device_lock, flags);
+
+ list_for_each_entry_safe(ctx, tmp, &gc_list, list) {
+ struct net_device *netdev = ctx->netdev;
+
+ if (netdev) {
+ netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+ TLS_OFFLOAD_CTX_DIR_TX);
+ dev_put(netdev);
+ }
+
+ list_del(&ctx->list);
+ tls_device_free_ctx(ctx);
+ }
+}
+
+static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&tls_device_lock, flags);
+ list_move_tail(&ctx->list, &tls_device_gc_list);
+
+ /* schedule_work inside the spinlock
+ * to make sure tls_device_down waits for that work.
+ */
+ schedule_work(&tls_device_gc_work);
+
+ spin_unlock_irqrestore(&tls_device_lock, flags);
+}
+
+/* We assume that the socket is already connected */
+static struct net_device *get_netdev_for_sock(struct sock *sk)
+{
+ struct dst_entry *dst = sk_dst_get(sk);
+ struct net_device *netdev = NULL;
+
+ if (likely(dst)) {
+ netdev = dst->dev;
+ dev_hold(netdev);
+ }
+
+ dst_release(dst);
+
+ return netdev;
+}
+
+static void destroy_record(struct tls_record_info *record)
+{
+ int nr_frags = record->num_frags;
+ skb_frag_t *frag;
+
+ while (nr_frags-- > 0) {
+ frag = &record->frags[nr_frags];
+ __skb_frag_unref(frag);
+ }
+ kfree(record);
+}
+
+static void delete_all_records(struct tls_offload_context *offload_ctx)
+{
+ struct tls_record_info *info, *temp;
+
+ list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) {
+ list_del(&info->list);
+ destroy_record(info);
+ }
+
+ offload_ctx->retransmit_hint = NULL;
+}
+
+static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_record_info *info, *temp;
+ struct tls_offload_context *ctx;
+ u64 deleted_records = 0;
+ unsigned long flags;
+
+ if (!tls_ctx)
+ return;
+
+ ctx = tls_offload_ctx(tls_ctx);
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ info = ctx->retransmit_hint;
+ if (info && !before(acked_seq, info->end_seq)) {
+ ctx->retransmit_hint = NULL;
+ list_del(&info->list);
+ destroy_record(info);
+ deleted_records++;
+ }
+
+ list_for_each_entry_safe(info, temp, &ctx->records_list, list) {
+ if (before(acked_seq, info->end_seq))
+ break;
+ list_del(&info->list);
+
+ destroy_record(info);
+ deleted_records++;
+ }
+
+ ctx->unacked_record_sn += deleted_records;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+}
+
+/* At this point, there should be no references on this
+ * socket and no in-flight SKBs associated with this
+ * socket, so it is safe to free all the resources.
+ */
+void tls_device_sk_destruct(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+
+ if (ctx->open_record)
+ destroy_record(ctx->open_record);
+
+ delete_all_records(ctx);
+ crypto_free_aead(ctx->aead_send);
+ ctx->sk_destruct(sk);
+ clean_acked_data_disable(inet_csk(sk));
+
+ if (refcount_dec_and_test(&tls_ctx->refcount))
+ tls_device_queue_ctx_destruction(tls_ctx);
+}
+EXPORT_SYMBOL(tls_device_sk_destruct);
+
+static void tls_append_frag(struct tls_record_info *record,
+ struct page_frag *pfrag,
+ int size)
+{
+ skb_frag_t *frag;
+
+ frag = &record->frags[record->num_frags - 1];
+ if (frag->page.p == pfrag->page &&
+ frag->page_offset + frag->size == pfrag->offset) {
+ frag->size += size;
+ } else {
+ ++frag;
+ frag->page.p = pfrag->page;
+ frag->page_offset = pfrag->offset;
+ frag->size = size;
+ ++record->num_frags;
+ get_page(pfrag->page);
+ }
+
+ pfrag->offset += size;
+ record->len += size;
+}
+
+static int tls_push_record(struct sock *sk,
+ struct tls_context *ctx,
+ struct tls_offload_context *offload_ctx,
+ struct tls_record_info *record,
+ struct page_frag *pfrag,
+ int flags,
+ unsigned char record_type)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct page_frag dummy_tag_frag;
+ skb_frag_t *frag;
+ int i;
+
+ /* fill prepend */
+ frag = &record->frags[0];
+ tls_fill_prepend(ctx,
+ skb_frag_address(frag),
+ record->len - ctx->tx.prepend_size,
+ record_type);
+
+ /* HW doesn't care about the data in the tag, because it fills it. */
+ dummy_tag_frag.page = skb_frag_page(frag);
+ dummy_tag_frag.offset = 0;
+
+ tls_append_frag(record, &dummy_tag_frag, ctx->tx.tag_size);
+ record->end_seq = tp->write_seq + record->len;
+ spin_lock_irq(&offload_ctx->lock);
+ list_add_tail(&record->list, &offload_ctx->records_list);
+ spin_unlock_irq(&offload_ctx->lock);
+ offload_ctx->open_record = NULL;
+ set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+ tls_advance_record_sn(sk, &ctx->tx);
+
+ for (i = 0; i < record->num_frags; i++) {
+ frag = &record->frags[i];
+ sg_unmark_end(&offload_ctx->sg_tx_data[i]);
+ sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag),
+ frag->size, frag->page_offset);
+ sk_mem_charge(sk, frag->size);
+ get_page(skb_frag_page(frag));
+ }
+ sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]);
+
+ /* all ready, send */
+ return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
+}
+
+static int tls_create_new_record(struct tls_offload_context *offload_ctx,
+ struct page_frag *pfrag,
+ size_t prepend_size)
+{
+ struct tls_record_info *record;
+ skb_frag_t *frag;
+
+ record = kmalloc(sizeof(*record), GFP_KERNEL);
+ if (!record)
+ return -ENOMEM;
+
+ frag = &record->frags[0];
+ __skb_frag_set_page(frag, pfrag->page);
+ frag->page_offset = pfrag->offset;
+ skb_frag_size_set(frag, prepend_size);
+
+ get_page(pfrag->page);
+ pfrag->offset += prepend_size;
+
+ record->num_frags = 1;
+ record->len = prepend_size;
+ offload_ctx->open_record = record;
+ return 0;
+}
+
+static int tls_do_allocation(struct sock *sk,
+ struct tls_offload_context *offload_ctx,
+ struct page_frag *pfrag,
+ size_t prepend_size)
+{
+ int ret;
+
+ if (!offload_ctx->open_record) {
+ if (unlikely(!skb_page_frag_refill(prepend_size, pfrag,
+ sk->sk_allocation))) {
+ sk->sk_prot->enter_memory_pressure(sk);
+ sk_stream_moderate_sndbuf(sk);
+ return -ENOMEM;
+ }
+
+ ret = tls_create_new_record(offload_ctx, pfrag, prepend_size);
+ if (ret)
+ return ret;
+
+ if (pfrag->size > pfrag->offset)
+ return 0;
+ }
+
+ if (!sk_page_frag_refill(sk, pfrag))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int tls_push_data(struct sock *sk,
+ struct iov_iter *msg_iter,
+ size_t size, int flags,
+ unsigned char record_type)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+ int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
+ struct tls_record_info *record = ctx->open_record;
+ struct page_frag *pfrag;
+ size_t orig_size = size;
+ u32 max_open_record_len;
+ int copy, rc = 0;
+ bool done = false;
+ long timeo;
+
+ if (flags &
+ ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
+ return -ENOTSUPP;
+
+ if (sk->sk_err)
+ return -sk->sk_err;
+
+ timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+ rc = tls_complete_pending_work(sk, tls_ctx, flags, &timeo);
+ if (rc < 0)
+ return rc;
+
+ pfrag = sk_page_frag(sk);
+
+ /* TLS_HEADER_SIZE is not counted as part of the TLS record, and
+ * we need to leave room for an authentication tag.
+ */
+ max_open_record_len = TLS_MAX_PAYLOAD_SIZE +
+ tls_ctx->tx.prepend_size;
+ do {
+ rc = tls_do_allocation(sk, ctx, pfrag,
+ tls_ctx->tx.prepend_size);
+ if (rc) {
+ rc = sk_stream_wait_memory(sk, &timeo);
+ if (!rc)
+ continue;
+
+ record = ctx->open_record;
+ if (!record)
+ break;
+handle_error:
+ if (record_type != TLS_RECORD_TYPE_DATA) {
+ /* avoid sending partial
+ * record with type !=
+ * application_data
+ */
+ size = orig_size;
+ destroy_record(record);
+ ctx->open_record = NULL;
+ } else if (record->len > tls_ctx->tx.prepend_size) {
+ goto last_record;
+ }
+
+ break;
+ }
+
+ record = ctx->open_record;
+ copy = min_t(size_t, size, (pfrag->size - pfrag->offset));
+ copy = min_t(size_t, copy, (max_open_record_len - record->len));
+
+ if (copy_from_iter_nocache(page_address(pfrag->page) +
+ pfrag->offset,
+ copy, msg_iter) != copy) {
+ rc = -EFAULT;
+ goto handle_error;
+ }
+ tls_append_frag(record, pfrag, copy);
+
+ size -= copy;
+ if (!size) {
+last_record:
+ tls_push_record_flags = flags;
+ if (more) {
+ tls_ctx->pending_open_record_frags =
+ record->num_frags;
+ break;
+ }
+
+ done = true;
+ }
+
+ if (done || record->len >= max_open_record_len ||
+ (record->num_frags >= MAX_SKB_FRAGS - 1)) {
+ rc = tls_push_record(sk,
+ tls_ctx,
+ ctx,
+ record,
+ pfrag,
+ tls_push_record_flags,
+ record_type);
+ if (rc < 0)
+ break;
+ }
+ } while (!done);
+
+ if (orig_size - size > 0)
+ rc = orig_size - size;
+
+ return rc;
+}
+
+int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+ unsigned char record_type = TLS_RECORD_TYPE_DATA;
+ int rc;
+
+ lock_sock(sk);
+
+ if (unlikely(msg->msg_controllen)) {
+ rc = tls_proccess_cmsg(sk, msg, &record_type);
+ if (rc)
+ goto out;
+ }
+
+ rc = tls_push_data(sk, &msg->msg_iter, size,
+ msg->msg_flags, record_type);
+
+out:
+ release_sock(sk);
+ return rc;
+}
+
+int tls_device_sendpage(struct sock *sk, struct page *page,
+ int offset, size_t size, int flags)
+{
+ struct iov_iter msg_iter;
+ char *kaddr = kmap(page);
+ struct kvec iov;
+ int rc;
+
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
+ lock_sock(sk);
+
+ if (flags & MSG_OOB) {
+ rc = -ENOTSUPP;
+ goto out;
+ }
+
+ iov.iov_base = kaddr + offset;
+ iov.iov_len = size;
+ iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+ rc = tls_push_data(sk, &msg_iter, size,
+ flags, TLS_RECORD_TYPE_DATA);
+ kunmap(page);
+
+out:
+ release_sock(sk);
+ return rc;
+}
+
+struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+ u32 seq, u64 *p_record_sn)
+{
+ u64 record_sn = context->hint_record_sn;
+ struct tls_record_info *info;
+
+ info = context->retransmit_hint;
+ if (!info ||
+ before(seq, info->end_seq - info->len)) {
+ /* if retransmit_hint is irrelevant start
+ * from the beggining of the list
+ */
+ info = list_first_entry(&context->records_list,
+ struct tls_record_info, list);
+ record_sn = context->unacked_record_sn;
+ }
+
+ list_for_each_entry_from(info, &context->records_list, list) {
+ if (before(seq, info->end_seq)) {
+ if (!context->retransmit_hint ||
+ after(info->end_seq,
+ context->retransmit_hint->end_seq)) {
+ context->hint_record_sn = record_sn;
+ context->retransmit_hint = info;
+ }
+ *p_record_sn = record_sn;
+ return info;
+ }
+ record_sn++;
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL(tls_get_record);
+
+static int tls_device_push_pending_record(struct sock *sk, int flags)
+{
+ struct iov_iter msg_iter;
+
+ iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
+ return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
+}
+
+int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
+{
+ u16 nonce_size, tag_size, iv_size, rec_seq_size;
+ struct tls_record_info *start_marker_record;
+ struct tls_offload_context *offload_ctx;
+ struct tls_crypto_info *crypto_info;
+ struct net_device *netdev;
+ char *iv, *rec_seq;
+ struct sk_buff *skb;
+ int rc = -EINVAL;
+ __be64 rcd_sn;
+
+ if (!ctx)
+ goto out;
+
+ if (ctx->priv_ctx_tx) {
+ rc = -EEXIST;
+ goto out;
+ }
+
+ start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL);
+ if (!start_marker_record) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL);
+ if (!offload_ctx) {
+ rc = -ENOMEM;
+ goto free_marker_record;
+ }
+
+ crypto_info = &ctx->crypto_send;
+ switch (crypto_info->cipher_type) {
+ case TLS_CIPHER_AES_GCM_128:
+ nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
+ tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+ iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
+ iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv;
+ rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
+ rec_seq =
+ ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq;
+ break;
+ default:
+ rc = -EINVAL;
+ goto free_offload_ctx;
+ }
+
+ ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size;
+ ctx->tx.tag_size = tag_size;
+ ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size;
+ ctx->tx.iv_size = iv_size;
+ ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+ GFP_KERNEL);
+ if (!ctx->tx.iv) {
+ rc = -ENOMEM;
+ goto free_offload_ctx;
+ }
+
+ memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
+
+ ctx->tx.rec_seq_size = rec_seq_size;
+ ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+ if (!ctx->tx.rec_seq) {
+ rc = -ENOMEM;
+ goto free_iv;
+ }
+ memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
+
+ rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info);
+ if (rc)
+ goto free_rec_seq;
+
+ /* start at rec_seq - 1 to account for the start marker record */
+ memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn));
+ offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1;
+
+ start_marker_record->end_seq = tcp_sk(sk)->write_seq;
+ start_marker_record->len = 0;
+ start_marker_record->num_frags = 0;
+
+ INIT_LIST_HEAD(&offload_ctx->records_list);
+ list_add_tail(&start_marker_record->list, &offload_ctx->records_list);
+ spin_lock_init(&offload_ctx->lock);
+ sg_init_table(offload_ctx->sg_tx_data,
+ ARRAY_SIZE(offload_ctx->sg_tx_data));
+
+ clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked);
+ ctx->push_pending_record = tls_device_push_pending_record;
+ offload_ctx->sk_destruct = sk->sk_destruct;
+
+ /* TLS offload is greatly simplified if we don't send
+ * SKBs where only part of the payload needs to be encrypted.
+ * So mark the last skb in the write queue as end of record.
+ */
+ skb = tcp_write_queue_tail(sk);
+ if (skb)
+ TCP_SKB_CB(skb)->eor = 1;
+
+ refcount_set(&ctx->refcount, 1);
+
+ /* We support starting offload on multiple sockets
+ * concurrently, so we only need a read lock here.
+ * This lock must precede get_netdev_for_sock to prevent races between
+ * NETDEV_DOWN and setsockopt.
+ */
+ down_read(&device_offload_lock);
+ netdev = get_netdev_for_sock(sk);
+ if (!netdev) {
+ pr_err_ratelimited("%s: netdev not found\n", __func__);
+ rc = -EINVAL;
+ goto release_lock;
+ }
+
+ if (!(netdev->features & NETIF_F_HW_TLS_TX)) {
+ rc = -ENOTSUPP;
+ goto release_netdev;
+ }
+
+ /* Avoid offloading if the device is down
+ * We don't want to offload new flows after
+ * the NETDEV_DOWN event
+ */
+ if (!(netdev->flags & IFF_UP)) {
+ rc = -EINVAL;
+ goto release_netdev;
+ }
+
+ ctx->priv_ctx_tx = offload_ctx;
+ rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX,
+ &ctx->crypto_send,
+ tcp_sk(sk)->write_seq);
+ if (rc)
+ goto release_netdev;
+
+ ctx->netdev = netdev;
+
+ spin_lock_irq(&tls_device_lock);
+ list_add_tail(&ctx->list, &tls_device_list);
+ spin_unlock_irq(&tls_device_lock);
+
+ sk->sk_validate_xmit_skb = tls_validate_xmit_skb;
+ /* following this assignment tls_is_sk_tx_device_offloaded
+ * will return true and the context might be accessed
+ * by the netdev's xmit function.
+ */
+ smp_store_release(&sk->sk_destruct,
+ &tls_device_sk_destruct);
+ up_read(&device_offload_lock);
+ goto out;
+
+release_netdev:
+ dev_put(netdev);
+release_lock:
+ up_read(&device_offload_lock);
+ clean_acked_data_disable(inet_csk(sk));
+ crypto_free_aead(offload_ctx->aead_send);
+free_rec_seq:
+ kfree(ctx->tx.rec_seq);
+free_iv:
+ kfree(ctx->tx.iv);
+free_offload_ctx:
+ kfree(offload_ctx);
+ ctx->priv_ctx_tx = NULL;
+free_marker_record:
+ kfree(start_marker_record);
+out:
+ return rc;
+}
+
+static int tls_device_down(struct net_device *netdev)
+{
+ struct tls_context *ctx, *tmp;
+ unsigned long flags;
+ LIST_HEAD(list);
+
+ /* Request a write lock to block new offload attempts */
+ down_write(&device_offload_lock);
+
+ spin_lock_irqsave(&tls_device_lock, flags);
+ list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) {
+ if (ctx->netdev != netdev ||
+ !refcount_inc_not_zero(&ctx->refcount))
+ continue;
+
+ list_move(&ctx->list, &list);
+ }
+ spin_unlock_irqrestore(&tls_device_lock, flags);
+
+ list_for_each_entry_safe(ctx, tmp, &list, list) {
+ netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+ TLS_OFFLOAD_CTX_DIR_TX);
+ ctx->netdev = NULL;
+ dev_put(netdev);
+ list_del_init(&ctx->list);
+
+ if (refcount_dec_and_test(&ctx->refcount))
+ tls_device_free_ctx(ctx);
+ }
+
+ up_write(&device_offload_lock);
+
+ flush_work(&tls_device_gc_work);
+
+ return NOTIFY_DONE;
+}
+
+static int tls_dev_event(struct notifier_block *this, unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+ if (!(dev->features & NETIF_F_HW_TLS_TX))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ case NETDEV_FEAT_CHANGE:
+ if (dev->tlsdev_ops &&
+ dev->tlsdev_ops->tls_dev_add &&
+ dev->tlsdev_ops->tls_dev_del)
+ return NOTIFY_DONE;
+ else
+ return NOTIFY_BAD;
+ case NETDEV_DOWN:
+ return tls_device_down(dev);
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block tls_dev_notifier = {
+ .notifier_call = tls_dev_event,
+};
+
+void __init tls_device_init(void)
+{
+ register_netdevice_notifier(&tls_dev_notifier);
+}
+
+void __exit tls_device_cleanup(void)
+{
+ unregister_netdevice_notifier(&tls_dev_notifier);
+ flush_work(&tls_device_gc_work);
+}
--- /dev/null
+/* Copyright (c) 2018, Mellanox Technologies All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <net/tls.h>
+#include <crypto/aead.h>
+#include <crypto/scatterwalk.h>
+#include <net/ip6_checksum.h>
+
+static void chain_to_walk(struct scatterlist *sg, struct scatter_walk *walk)
+{
+ struct scatterlist *src = walk->sg;
+ int diff = walk->offset - src->offset;
+
+ sg_set_page(sg, sg_page(src),
+ src->length - diff, walk->offset);
+
+ scatterwalk_crypto_chain(sg, sg_next(src), 0, 2);
+}
+
+static int tls_enc_record(struct aead_request *aead_req,
+ struct crypto_aead *aead, char *aad,
+ char *iv, __be64 rcd_sn,
+ struct scatter_walk *in,
+ struct scatter_walk *out, int *in_len)
+{
+ unsigned char buf[TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE];
+ struct scatterlist sg_in[3];
+ struct scatterlist sg_out[3];
+ u16 len;
+ int rc;
+
+ len = min_t(int, *in_len, ARRAY_SIZE(buf));
+
+ scatterwalk_copychunks(buf, in, len, 0);
+ scatterwalk_copychunks(buf, out, len, 1);
+
+ *in_len -= len;
+ if (!*in_len)
+ return 0;
+
+ scatterwalk_pagedone(in, 0, 1);
+ scatterwalk_pagedone(out, 1, 1);
+
+ len = buf[4] | (buf[3] << 8);
+ len -= TLS_CIPHER_AES_GCM_128_IV_SIZE;
+
+ tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE,
+ (char *)&rcd_sn, sizeof(rcd_sn), buf[0]);
+
+ memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE,
+ TLS_CIPHER_AES_GCM_128_IV_SIZE);
+
+ sg_init_table(sg_in, ARRAY_SIZE(sg_in));
+ sg_init_table(sg_out, ARRAY_SIZE(sg_out));
+ sg_set_buf(sg_in, aad, TLS_AAD_SPACE_SIZE);
+ sg_set_buf(sg_out, aad, TLS_AAD_SPACE_SIZE);
+ chain_to_walk(sg_in + 1, in);
+ chain_to_walk(sg_out + 1, out);
+
+ *in_len -= len;
+ if (*in_len < 0) {
+ *in_len += TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+ /* the input buffer doesn't contain the entire record.
+ * trim len accordingly. The resulting authentication tag
+ * will contain garbage, but we don't care, so we won't
+ * include any of it in the output skb
+ * Note that we assume the output buffer length
+ * is larger then input buffer length + tag size
+ */
+ if (*in_len < 0)
+ len += *in_len;
+
+ *in_len = 0;
+ }
+
+ if (*in_len) {
+ scatterwalk_copychunks(NULL, in, len, 2);
+ scatterwalk_pagedone(in, 0, 1);
+ scatterwalk_copychunks(NULL, out, len, 2);
+ scatterwalk_pagedone(out, 1, 1);
+ }
+
+ len -= TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+ aead_request_set_crypt(aead_req, sg_in, sg_out, len, iv);
+
+ rc = crypto_aead_encrypt(aead_req);
+
+ return rc;
+}
+
+static void tls_init_aead_request(struct aead_request *aead_req,
+ struct crypto_aead *aead)
+{
+ aead_request_set_tfm(aead_req, aead);
+ aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
+}
+
+static struct aead_request *tls_alloc_aead_request(struct crypto_aead *aead,
+ gfp_t flags)
+{
+ unsigned int req_size = sizeof(struct aead_request) +
+ crypto_aead_reqsize(aead);
+ struct aead_request *aead_req;
+
+ aead_req = kzalloc(req_size, flags);
+ if (aead_req)
+ tls_init_aead_request(aead_req, aead);
+ return aead_req;
+}
+
+static int tls_enc_records(struct aead_request *aead_req,
+ struct crypto_aead *aead, struct scatterlist *sg_in,
+ struct scatterlist *sg_out, char *aad, char *iv,
+ u64 rcd_sn, int len)
+{
+ struct scatter_walk out, in;
+ int rc;
+
+ scatterwalk_start(&in, sg_in);
+ scatterwalk_start(&out, sg_out);
+
+ do {
+ rc = tls_enc_record(aead_req, aead, aad, iv,
+ cpu_to_be64(rcd_sn), &in, &out, &len);
+ rcd_sn++;
+
+ } while (rc == 0 && len);
+
+ scatterwalk_done(&in, 0, 0);
+ scatterwalk_done(&out, 1, 0);
+
+ return rc;
+}
+
+/* Can't use icsk->icsk_af_ops->send_check here because the ip addresses
+ * might have been changed by NAT.
+ */
+static void update_chksum(struct sk_buff *skb, int headln)
+{
+ struct tcphdr *th = tcp_hdr(skb);
+ int datalen = skb->len - headln;
+ const struct ipv6hdr *ipv6h;
+ const struct iphdr *iph;
+
+ /* We only changed the payload so if we are using partial we don't
+ * need to update anything.
+ */
+ if (likely(skb->ip_summed == CHECKSUM_PARTIAL))
+ return;
+
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
+
+ if (skb->sk->sk_family == AF_INET6) {
+ ipv6h = ipv6_hdr(skb);
+ th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+ datalen, IPPROTO_TCP, 0);
+ } else {
+ iph = ip_hdr(skb);
+ th->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen,
+ IPPROTO_TCP, 0);
+ }
+}
+
+static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
+{
+ skb_copy_header(nskb, skb);
+
+ skb_put(nskb, skb->len);
+ memcpy(nskb->data, skb->data, headln);
+ update_chksum(nskb, headln);
+
+ nskb->destructor = skb->destructor;
+ nskb->sk = skb->sk;
+ skb->destructor = NULL;
+ skb->sk = NULL;
+ refcount_add(nskb->truesize - skb->truesize,
+ &nskb->sk->sk_wmem_alloc);
+}
+
+/* This function may be called after the user socket is already
+ * closed so make sure we don't use anything freed during
+ * tls_sk_proto_close here
+ */
+
+static int fill_sg_in(struct scatterlist *sg_in,
+ struct sk_buff *skb,
+ struct tls_offload_context *ctx,
+ u64 *rcd_sn,
+ s32 *sync_size,
+ int *resync_sgs)
+{
+ int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ int payload_len = skb->len - tcp_payload_offset;
+ u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
+ struct tls_record_info *record;
+ unsigned long flags;
+ int remaining;
+ int i;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ record = tls_get_record(ctx, tcp_seq, rcd_sn);
+ if (!record) {
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ WARN(1, "Record not found for seq %u\n", tcp_seq);
+ return -EINVAL;
+ }
+
+ *sync_size = tcp_seq - tls_record_start_seq(record);
+ if (*sync_size < 0) {
+ int is_start_marker = tls_record_is_start_marker(record);
+
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ /* This should only occur if the relevant record was
+ * already acked. In that case it should be ok
+ * to drop the packet and avoid retransmission.
+ *
+ * There is a corner case where the packet contains
+ * both an acked and a non-acked record.
+ * We currently don't handle that case and rely
+ * on TCP to retranmit a packet that doesn't contain
+ * already acked payload.
+ */
+ if (!is_start_marker)
+ *sync_size = 0;
+ return -EINVAL;
+ }
+
+ remaining = *sync_size;
+ for (i = 0; remaining > 0; i++) {
+ skb_frag_t *frag = &record->frags[i];
+
+ __skb_frag_ref(frag);
+ sg_set_page(sg_in + i, skb_frag_page(frag),
+ skb_frag_size(frag), frag->page_offset);
+
+ remaining -= skb_frag_size(frag);
+
+ if (remaining < 0)
+ sg_in[i].length += remaining;
+ }
+ *resync_sgs = i;
+
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ if (skb_to_sgvec(skb, &sg_in[i], tcp_payload_offset, payload_len) < 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static void fill_sg_out(struct scatterlist sg_out[3], void *buf,
+ struct tls_context *tls_ctx,
+ struct sk_buff *nskb,
+ int tcp_payload_offset,
+ int payload_len,
+ int sync_size,
+ void *dummy_buf)
+{
+ sg_set_buf(&sg_out[0], dummy_buf, sync_size);
+ sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len);
+ /* Add room for authentication tag produced by crypto */
+ dummy_buf += sync_size;
+ sg_set_buf(&sg_out[2], dummy_buf, TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+}
+
+static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
+ struct scatterlist sg_out[3],
+ struct scatterlist *sg_in,
+ struct sk_buff *skb,
+ s32 sync_size, u64 rcd_sn)
+{
+ int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ int payload_len = skb->len - tcp_payload_offset;
+ void *buf, *iv, *aad, *dummy_buf;
+ struct aead_request *aead_req;
+ struct sk_buff *nskb = NULL;
+ int buf_len;
+
+ aead_req = tls_alloc_aead_request(ctx->aead_send, GFP_ATOMIC);
+ if (!aead_req)
+ return NULL;
+
+ buf_len = TLS_CIPHER_AES_GCM_128_SALT_SIZE +
+ TLS_CIPHER_AES_GCM_128_IV_SIZE +
+ TLS_AAD_SPACE_SIZE +
+ sync_size +
+ TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+ buf = kmalloc(buf_len, GFP_ATOMIC);
+ if (!buf)
+ goto free_req;
+
+ iv = buf;
+ memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt,
+ TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+ aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE +
+ TLS_CIPHER_AES_GCM_128_IV_SIZE;
+ dummy_buf = aad + TLS_AAD_SPACE_SIZE;
+
+ nskb = alloc_skb(skb_headroom(skb) + skb->len, GFP_ATOMIC);
+ if (!nskb)
+ goto free_buf;
+
+ skb_reserve(nskb, skb_headroom(skb));
+
+ fill_sg_out(sg_out, buf, tls_ctx, nskb, tcp_payload_offset,
+ payload_len, sync_size, dummy_buf);
+
+ if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv,
+ rcd_sn, sync_size + payload_len) < 0)
+ goto free_nskb;
+
+ complete_skb(nskb, skb, tcp_payload_offset);
+
+ /* validate_xmit_skb_list assumes that if the skb wasn't segmented
+ * nskb->prev will point to the skb itself
+ */
+ nskb->prev = nskb;
+
+free_buf:
+ kfree(buf);
+free_req:
+ kfree(aead_req);
+ return nskb;
+free_nskb:
+ kfree_skb(nskb);
+ nskb = NULL;
+ goto free_buf;
+}
+
+static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb)
+{
+ int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+ int payload_len = skb->len - tcp_payload_offset;
+ struct scatterlist *sg_in, sg_out[3];
+ struct sk_buff *nskb = NULL;
+ int sg_in_max_elements;
+ int resync_sgs = 0;
+ s32 sync_size = 0;
+ u64 rcd_sn;
+
+ /* worst case is:
+ * MAX_SKB_FRAGS in tls_record_info
+ * MAX_SKB_FRAGS + 1 in SKB head and frags.
+ */
+ sg_in_max_elements = 2 * MAX_SKB_FRAGS + 1;
+
+ if (!payload_len)
+ return skb;
+
+ sg_in = kmalloc_array(sg_in_max_elements, sizeof(*sg_in), GFP_ATOMIC);
+ if (!sg_in)
+ goto free_orig;
+
+ sg_init_table(sg_in, sg_in_max_elements);
+ sg_init_table(sg_out, ARRAY_SIZE(sg_out));
+
+ if (fill_sg_in(sg_in, skb, ctx, &rcd_sn, &sync_size, &resync_sgs)) {
+ /* bypass packets before kernel TLS socket option was set */
+ if (sync_size < 0 && payload_len <= -sync_size)
+ nskb = skb_get(skb);
+ goto put_sg;
+ }
+
+ nskb = tls_enc_skb(tls_ctx, sg_out, sg_in, skb, sync_size, rcd_sn);
+
+put_sg:
+ while (resync_sgs)
+ put_page(sg_page(&sg_in[--resync_sgs]));
+ kfree(sg_in);
+free_orig:
+ kfree_skb(skb);
+ return nskb;
+}
+
+struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
+ struct net_device *dev,
+ struct sk_buff *skb)
+{
+ if (dev == tls_get_ctx(sk)->netdev)
+ return skb;
+
+ return tls_sw_fallback(sk, skb);
+}
+
+int tls_sw_fallback_init(struct sock *sk,
+ struct tls_offload_context *offload_ctx,
+ struct tls_crypto_info *crypto_info)
+{
+ const u8 *key;
+ int rc;
+
+ offload_ctx->aead_send =
+ crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(offload_ctx->aead_send)) {
+ rc = PTR_ERR(offload_ctx->aead_send);
+ pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc);
+ offload_ctx->aead_send = NULL;
+ goto err_out;
+ }
+
+ key = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->key;
+
+ rc = crypto_aead_setkey(offload_ctx->aead_send, key,
+ TLS_CIPHER_AES_GCM_128_KEY_SIZE);
+ if (rc)
+ goto free_aead;
+
+ rc = crypto_aead_setauthsize(offload_ctx->aead_send,
+ TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+ if (rc)
+ goto free_aead;
+
+ return 0;
+free_aead:
+ crypto_free_aead(offload_ctx->aead_send);
+err_out:
+ return rc;
+}
TLSV6,
TLS_NUM_PROTS,
};
-
enum {
TLS_BASE,
- TLS_SW_TX,
- TLS_SW_RX,
- TLS_SW_RXTX,
+ TLS_SW,
+#ifdef CONFIG_TLS_DEVICE
+ TLS_HW,
+#endif
TLS_HW_RECORD,
TLS_NUM_CONFIG,
};
static DEFINE_MUTEX(tcpv6_prot_mutex);
static LIST_HEAD(device_list);
static DEFINE_MUTEX(device_mutex);
-static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
+static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
static struct proto_ops tls_sw_proto_ops;
-static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
+static void update_sk_prot(struct sock *sk, struct tls_context *ctx)
{
int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
- sk->sk_prot = &tls_prots[ip_ver][ctx->conf];
+ sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf];
}
int wait_on_pending_writer(struct sock *sk, long *timeo)
size = sg->length - offset;
offset += sg->offset;
+ ctx->in_tcp_sendpages = true;
while (1) {
if (sg_is_last(sg))
sendpage_flags = flags;
offset -= sg->offset;
ctx->partially_sent_offset = offset;
ctx->partially_sent_record = (void *)sg;
+ ctx->in_tcp_sendpages = false;
return ret;
}
}
clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+ ctx->in_tcp_sendpages = false;
+ ctx->sk_write_space(sk);
return 0;
}
{
struct tls_context *ctx = tls_get_ctx(sk);
+ /* We are already sending pages, ignore notification */
+ if (ctx->in_tcp_sendpages)
+ return;
+
if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) {
gfp_t sk_allocation = sk->sk_allocation;
int rc;
struct tls_context *ctx = tls_get_ctx(sk);
long timeo = sock_sndtimeo(sk, 0);
void (*sk_proto_close)(struct sock *sk, long timeout);
+ bool free_ctx = false;
lock_sock(sk);
sk_proto_close = ctx->sk_proto_close;
- if (ctx->conf == TLS_HW_RECORD)
- goto skip_tx_cleanup;
-
- if (ctx->conf == TLS_BASE) {
- kfree(ctx);
- ctx = NULL;
+ if ((ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) ||
+ (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE)) {
+ free_ctx = true;
goto skip_tx_cleanup;
}
}
}
- kfree(ctx->tx.rec_seq);
- kfree(ctx->tx.iv);
- kfree(ctx->rx.rec_seq);
- kfree(ctx->rx.iv);
+ /* We need these for tls_sw_fallback handling of other packets */
+ if (ctx->tx_conf == TLS_SW) {
+ kfree(ctx->tx.rec_seq);
+ kfree(ctx->tx.iv);
+ tls_sw_free_resources_tx(sk);
+ }
+
+ if (ctx->rx_conf == TLS_SW) {
+ kfree(ctx->rx.rec_seq);
+ kfree(ctx->rx.iv);
+ tls_sw_free_resources_rx(sk);
+ }
- if (ctx->conf == TLS_SW_TX ||
- ctx->conf == TLS_SW_RX ||
- ctx->conf == TLS_SW_RXTX) {
- tls_sw_free_resources(sk);
+#ifdef CONFIG_TLS_DEVICE
+ if (ctx->tx_conf != TLS_HW) {
+#else
+ {
+#endif
+ kfree(ctx);
+ ctx = NULL;
}
skip_tx_cleanup:
/* free ctx for TLS_HW_RECORD, used by tcp_set_state
* for sk->sk_prot->unhash [tls_hw_unhash]
*/
- if (ctx && ctx->conf == TLS_HW_RECORD)
+ if (free_ctx)
kfree(ctx);
}
goto err_crypto_info;
}
- /* currently SW is default, we will have ethtool in future */
if (tx) {
- rc = tls_set_sw_offload(sk, ctx, 1);
- if (ctx->conf == TLS_SW_RX)
- conf = TLS_SW_RXTX;
- else
- conf = TLS_SW_TX;
+#ifdef CONFIG_TLS_DEVICE
+ rc = tls_set_device_offload(sk, ctx);
+ conf = TLS_HW;
+ if (rc) {
+#else
+ {
+#endif
+ rc = tls_set_sw_offload(sk, ctx, 1);
+ conf = TLS_SW;
+ }
} else {
rc = tls_set_sw_offload(sk, ctx, 0);
- if (ctx->conf == TLS_SW_TX)
- conf = TLS_SW_RXTX;
- else
- conf = TLS_SW_RX;
+ conf = TLS_SW;
}
if (rc)
goto err_crypto_info;
- ctx->conf = conf;
+ if (tx)
+ ctx->tx_conf = conf;
+ else
+ ctx->rx_conf = conf;
update_sk_prot(sk, ctx);
if (tx) {
ctx->sk_write_space = sk->sk_write_space;
ctx->hash = sk->sk_prot->hash;
ctx->unhash = sk->sk_prot->unhash;
ctx->sk_proto_close = sk->sk_prot->close;
- ctx->conf = TLS_HW_RECORD;
+ ctx->rx_conf = TLS_HW_RECORD;
+ ctx->tx_conf = TLS_HW_RECORD;
update_sk_prot(sk, ctx);
rc = 1;
break;
return err;
}
-static void build_protos(struct proto *prot, struct proto *base)
+static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
+ struct proto *base)
{
- prot[TLS_BASE] = *base;
- prot[TLS_BASE].setsockopt = tls_setsockopt;
- prot[TLS_BASE].getsockopt = tls_getsockopt;
- prot[TLS_BASE].close = tls_sk_proto_close;
-
- prot[TLS_SW_TX] = prot[TLS_BASE];
- prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg;
- prot[TLS_SW_TX].sendpage = tls_sw_sendpage;
-
- prot[TLS_SW_RX] = prot[TLS_BASE];
- prot[TLS_SW_RX].recvmsg = tls_sw_recvmsg;
- prot[TLS_SW_RX].close = tls_sk_proto_close;
-
- prot[TLS_SW_RXTX] = prot[TLS_SW_TX];
- prot[TLS_SW_RXTX].recvmsg = tls_sw_recvmsg;
- prot[TLS_SW_RXTX].close = tls_sk_proto_close;
-
- prot[TLS_HW_RECORD] = *base;
- prot[TLS_HW_RECORD].hash = tls_hw_hash;
- prot[TLS_HW_RECORD].unhash = tls_hw_unhash;
- prot[TLS_HW_RECORD].close = tls_sk_proto_close;
+ prot[TLS_BASE][TLS_BASE] = *base;
+ prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt;
+ prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt;
+ prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close;
+
+ prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
+ prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg;
+ prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage;
+
+ prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
+ prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg;
+ prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close;
+
+ prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
+ prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg;
+ prot[TLS_SW][TLS_SW].close = tls_sk_proto_close;
+
+#ifdef CONFIG_TLS_DEVICE
+ prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
+ prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg;
+ prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage;
+
+ prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW];
+ prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg;
+ prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage;
+#endif
+
+ prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
+ prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash;
+ prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash;
+ prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close;
}
static int tls_init(struct sock *sk)
ctx->getsockopt = sk->sk_prot->getsockopt;
ctx->sk_proto_close = sk->sk_prot->close;
- /* Build IPv6 TLS whenever the address of tcpv6_prot changes */
+ /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */
if (ip_ver == TLSV6 &&
unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
mutex_lock(&tcpv6_prot_mutex);
mutex_unlock(&tcpv6_prot_mutex);
}
- ctx->conf = TLS_BASE;
+ ctx->tx_conf = TLS_BASE;
+ ctx->rx_conf = TLS_BASE;
update_sk_prot(sk, ctx);
out:
return rc;
tls_sw_proto_ops.poll = tls_sw_poll;
tls_sw_proto_ops.splice_read = tls_sw_splice_read;
+#ifdef CONFIG_TLS_DEVICE
+ tls_device_init();
+#endif
tcp_register_ulp(&tcp_tls_ulp_ops);
return 0;
static void __exit tls_unregister(void)
{
tcp_unregister_ulp(&tcp_tls_ulp_ops);
+#ifdef CONFIG_TLS_DEVICE
+ tls_device_cleanup();
+#endif
}
module_init(tls_register);
gfp_t flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct strp_msg *rxm = strp_msg(skb);
struct aead_request *aead_req;
static void trim_both_sgl(struct sock *sk, int target_size)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
trim_sg(sk, ctx->sg_plaintext_data,
&ctx->sg_plaintext_num_elem,
static int alloc_encrypted_sg(struct sock *sk, int len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
int rc = 0;
rc = sk_alloc_sg(sk, len,
static int alloc_plaintext_sg(struct sock *sk, int len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
int rc = 0;
rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0,
static void tls_free_both_sg(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem,
&ctx->sg_encrypted_size);
}
static int tls_do_encryption(struct tls_context *tls_ctx,
- struct tls_sw_context *ctx, size_t data_len,
+ struct tls_sw_context_tx *ctx, size_t data_len,
gfp_t flags)
{
unsigned int req_size = sizeof(struct aead_request) +
unsigned char record_type)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
int rc;
sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1);
int bytes)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct scatterlist *sg = ctx->sg_plaintext_data;
int copy, i, rc = 0;
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
int ret = 0;
int required_size;
long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
int offset, size_t size, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
int ret = 0;
long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
bool eor;
long timeo, int *err)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct sk_buff *skb;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct scatterlist *sgout)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE];
struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
struct scatterlist *sgin = &sgin_arr[0];
struct strp_msg *rxm = strp_msg(skb);
int ret, nsg = ARRAY_SIZE(sgin_arr);
- char aad_recv[TLS_AAD_SPACE_SIZE];
struct sk_buff *unused;
ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
if (!sgout) {
nsg = skb_cow_data(skb, 0, &unused) + 1;
sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation);
- if (!sgout)
- sgout = sgin;
+ sgout = sgin;
}
sg_init_table(sgin, nsg);
- sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv));
+ sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE);
nsg = skb_to_sgvec(skb, &sgin[1],
rxm->offset + tls_ctx->rx.prepend_size,
rxm->full_len - tls_ctx->rx.prepend_size);
- tls_make_aad(aad_recv,
+ tls_make_aad(ctx->rx_aad_ciphertext,
rxm->full_len - tls_ctx->rx.overhead_size,
tls_ctx->rx.rec_seq,
tls_ctx->rx.rec_seq_size,
unsigned int len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct strp_msg *rxm = strp_msg(skb);
if (len < rxm->full_len) {
int *addr_len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
unsigned char control;
struct strp_msg *rxm;
struct sk_buff *skb;
if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
likely(!(flags & MSG_PEEK))) {
struct scatterlist sgin[MAX_SKB_FRAGS + 1];
- char unused[21];
int pages = 0;
zc = true;
sg_init_table(sgin, MAX_SKB_FRAGS + 1);
- sg_set_buf(&sgin[0], unused, 13);
+ sg_set_buf(&sgin[0], ctx->rx_aad_plaintext,
+ TLS_AAD_SPACE_SIZE);
err = zerocopy_from_iter(sk, &msg->msg_iter,
to_copy, &pages,
size_t len, unsigned int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sock->sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct strp_msg *rxm = NULL;
struct sock *sk = sock->sk;
struct sk_buff *skb;
unsigned int ret;
struct sock *sk = sock->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
/* Grab POLLOUT and POLLHUP from the underlying socket */
ret = ctx->sk_poll(file, sock, wait);
static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
char header[tls_ctx->rx.prepend_size];
struct strp_msg *rxm = strp_msg(skb);
size_t cipher_overhead;
static void tls_queue(struct strparser *strp, struct sk_buff *skb)
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct strp_msg *rxm;
rxm = strp_msg(skb);
static void tls_data_ready(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
strp_data_ready(&ctx->strp);
}
-void tls_sw_free_resources(struct sock *sk)
+void tls_sw_free_resources_tx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
if (ctx->aead_send)
crypto_free_aead(ctx->aead_send);
+ tls_free_both_sg(sk);
+
+ kfree(ctx);
+}
+
+void tls_sw_free_resources_rx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+
if (ctx->aead_recv) {
if (ctx->recv_pkt) {
kfree_skb(ctx->recv_pkt);
lock_sock(sk);
}
- tls_free_both_sg(sk);
-
kfree(ctx);
- kfree(tls_ctx);
}
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
struct tls_crypto_info *crypto_info;
struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
- struct tls_sw_context *sw_ctx;
+ struct tls_sw_context_tx *sw_ctx_tx = NULL;
+ struct tls_sw_context_rx *sw_ctx_rx = NULL;
struct cipher_context *cctx;
struct crypto_aead **aead;
struct strp_callbacks cb;
goto out;
}
- if (!ctx->priv_ctx) {
- sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL);
- if (!sw_ctx) {
+ if (tx) {
+ sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
+ if (!sw_ctx_tx) {
rc = -ENOMEM;
goto out;
}
- crypto_init_wait(&sw_ctx->async_wait);
+ crypto_init_wait(&sw_ctx_tx->async_wait);
+ ctx->priv_ctx_tx = sw_ctx_tx;
} else {
- sw_ctx = ctx->priv_ctx;
+ sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
+ if (!sw_ctx_rx) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ crypto_init_wait(&sw_ctx_rx->async_wait);
+ ctx->priv_ctx_rx = sw_ctx_rx;
}
- ctx->priv_ctx = (struct tls_offload_context *)sw_ctx;
-
if (tx) {
crypto_info = &ctx->crypto_send;
cctx = &ctx->tx;
- aead = &sw_ctx->aead_send;
+ aead = &sw_ctx_tx->aead_send;
} else {
crypto_info = &ctx->crypto_recv;
cctx = &ctx->rx;
- aead = &sw_ctx->aead_recv;
+ aead = &sw_ctx_rx->aead_recv;
}
switch (crypto_info->cipher_type) {
}
memcpy(cctx->rec_seq, rec_seq, rec_seq_size);
- if (tx) {
- sg_init_table(sw_ctx->sg_encrypted_data,
- ARRAY_SIZE(sw_ctx->sg_encrypted_data));
- sg_init_table(sw_ctx->sg_plaintext_data,
- ARRAY_SIZE(sw_ctx->sg_plaintext_data));
-
- sg_init_table(sw_ctx->sg_aead_in, 2);
- sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space,
- sizeof(sw_ctx->aad_space));
- sg_unmark_end(&sw_ctx->sg_aead_in[1]);
- sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data);
- sg_init_table(sw_ctx->sg_aead_out, 2);
- sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space,
- sizeof(sw_ctx->aad_space));
- sg_unmark_end(&sw_ctx->sg_aead_out[1]);
- sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data);
+ if (sw_ctx_tx) {
+ sg_init_table(sw_ctx_tx->sg_encrypted_data,
+ ARRAY_SIZE(sw_ctx_tx->sg_encrypted_data));
+ sg_init_table(sw_ctx_tx->sg_plaintext_data,
+ ARRAY_SIZE(sw_ctx_tx->sg_plaintext_data));
+
+ sg_init_table(sw_ctx_tx->sg_aead_in, 2);
+ sg_set_buf(&sw_ctx_tx->sg_aead_in[0], sw_ctx_tx->aad_space,
+ sizeof(sw_ctx_tx->aad_space));
+ sg_unmark_end(&sw_ctx_tx->sg_aead_in[1]);
+ sg_chain(sw_ctx_tx->sg_aead_in, 2,
+ sw_ctx_tx->sg_plaintext_data);
+ sg_init_table(sw_ctx_tx->sg_aead_out, 2);
+ sg_set_buf(&sw_ctx_tx->sg_aead_out[0], sw_ctx_tx->aad_space,
+ sizeof(sw_ctx_tx->aad_space));
+ sg_unmark_end(&sw_ctx_tx->sg_aead_out[1]);
+ sg_chain(sw_ctx_tx->sg_aead_out, 2,
+ sw_ctx_tx->sg_encrypted_data);
}
if (!*aead) {
if (rc)
goto free_aead;
- if (!tx) {
+ if (sw_ctx_rx) {
/* Set up strparser */
memset(&cb, 0, sizeof(cb));
cb.rcv_msg = tls_queue;
cb.parse_msg = tls_read_size;
- strp_init(&sw_ctx->strp, sk, &cb);
+ strp_init(&sw_ctx_rx->strp, sk, &cb);
write_lock_bh(&sk->sk_callback_lock);
- sw_ctx->saved_data_ready = sk->sk_data_ready;
+ sw_ctx_rx->saved_data_ready = sk->sk_data_ready;
sk->sk_data_ready = tls_data_ready;
write_unlock_bh(&sk->sk_callback_lock);
- sw_ctx->sk_poll = sk->sk_socket->ops->poll;
+ sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll;
- strp_check_rcv(&sw_ctx->strp);
+ strp_check_rcv(&sw_ctx_rx->strp);
}
goto out;
kfree(cctx->rec_seq);
cctx->rec_seq = NULL;
free_iv:
- kfree(ctx->tx.iv);
- ctx->tx.iv = NULL;
+ kfree(cctx->iv);
+ cctx->iv = NULL;
free_priv:
- kfree(ctx->priv_ctx);
- ctx->priv_ctx = NULL;
+ if (tx) {
+ kfree(ctx->priv_ctx_tx);
+ ctx->priv_ctx_tx = NULL;
+ } else {
+ kfree(ctx->priv_ctx_rx);
+ ctx->priv_ctx_rx = NULL;
+ }
out:
return rc;
}
ASSERT_RTNL();
+ if (strlen(newname) > NL80211_WIPHY_NAME_MAXLEN)
+ return -EINVAL;
+
/* prohibit calling the thing phy%d when %d is not its number */
sscanf(newname, PHY_NAME "%d%n", &wiphy_idx, &taken);
if (taken == strlen(newname) && wiphy_idx != rdev->wiphy_idx) {
if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) {
if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
+ kzfree(connkeys);
GENL_SET_ERR_MSG(info,
"external auth requires connection ownership");
return -EINVAL;
if (!tmp_rd) {
kfree(regdom);
+ kfree(wmm_ptrs);
return -ENOMEM;
}
regdom = tmp_rd;
--- /dev/null
+config XDP_SOCKETS
+ bool "XDP sockets"
+ depends on BPF_SYSCALL
+ default n
+ help
+ XDP sockets allows a channel between XDP programs and
+ userspace applications.
--- /dev/null
+obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o
+
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/mm.h>
+
+#include "xdp_umem.h"
+
+#define XDP_UMEM_MIN_FRAME_SIZE 2048
+
+int xdp_umem_create(struct xdp_umem **umem)
+{
+ *umem = kzalloc(sizeof(**umem), GFP_KERNEL);
+
+ if (!(*umem))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void xdp_umem_unpin_pages(struct xdp_umem *umem)
+{
+ unsigned int i;
+
+ if (umem->pgs) {
+ for (i = 0; i < umem->npgs; i++) {
+ struct page *page = umem->pgs[i];
+
+ set_page_dirty_lock(page);
+ put_page(page);
+ }
+
+ kfree(umem->pgs);
+ umem->pgs = NULL;
+ }
+}
+
+static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
+{
+ if (umem->user) {
+ atomic_long_sub(umem->npgs, &umem->user->locked_vm);
+ free_uid(umem->user);
+ }
+}
+
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ if (umem->fq) {
+ xskq_destroy(umem->fq);
+ umem->fq = NULL;
+ }
+
+ if (umem->cq) {
+ xskq_destroy(umem->cq);
+ umem->cq = NULL;
+ }
+
+ if (umem->pgs) {
+ xdp_umem_unpin_pages(umem);
+
+ task = get_pid_task(umem->pid, PIDTYPE_PID);
+ put_pid(umem->pid);
+ if (!task)
+ goto out;
+ mm = get_task_mm(task);
+ put_task_struct(task);
+ if (!mm)
+ goto out;
+
+ mmput(mm);
+ umem->pgs = NULL;
+ }
+
+ xdp_umem_unaccount_pages(umem);
+out:
+ kfree(umem);
+}
+
+static void xdp_umem_release_deferred(struct work_struct *work)
+{
+ struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
+
+ xdp_umem_release(umem);
+}
+
+void xdp_get_umem(struct xdp_umem *umem)
+{
+ atomic_inc(&umem->users);
+}
+
+void xdp_put_umem(struct xdp_umem *umem)
+{
+ if (!umem)
+ return;
+
+ if (atomic_dec_and_test(&umem->users)) {
+ INIT_WORK(&umem->work, xdp_umem_release_deferred);
+ schedule_work(&umem->work);
+ }
+}
+
+static int xdp_umem_pin_pages(struct xdp_umem *umem)
+{
+ unsigned int gup_flags = FOLL_WRITE;
+ long npgs;
+ int err;
+
+ umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL);
+ if (!umem->pgs)
+ return -ENOMEM;
+
+ down_write(¤t->mm->mmap_sem);
+ npgs = get_user_pages(umem->address, umem->npgs,
+ gup_flags, &umem->pgs[0], NULL);
+ up_write(¤t->mm->mmap_sem);
+
+ if (npgs != umem->npgs) {
+ if (npgs >= 0) {
+ umem->npgs = npgs;
+ err = -ENOMEM;
+ goto out_pin;
+ }
+ err = npgs;
+ goto out_pgs;
+ }
+ return 0;
+
+out_pin:
+ xdp_umem_unpin_pages(umem);
+out_pgs:
+ kfree(umem->pgs);
+ umem->pgs = NULL;
+ return err;
+}
+
+static int xdp_umem_account_pages(struct xdp_umem *umem)
+{
+ unsigned long lock_limit, new_npgs, old_npgs;
+
+ if (capable(CAP_IPC_LOCK))
+ return 0;
+
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ umem->user = get_uid(current_user());
+
+ do {
+ old_npgs = atomic_long_read(&umem->user->locked_vm);
+ new_npgs = old_npgs + umem->npgs;
+ if (new_npgs > lock_limit) {
+ free_uid(umem->user);
+ umem->user = NULL;
+ return -ENOBUFS;
+ }
+ } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
+ new_npgs) != old_npgs);
+ return 0;
+}
+
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+{
+ u32 frame_size = mr->frame_size, frame_headroom = mr->frame_headroom;
+ u64 addr = mr->addr, size = mr->len;
+ unsigned int nframes, nfpp;
+ int size_chk, err;
+
+ if (!umem)
+ return -EINVAL;
+
+ if (frame_size < XDP_UMEM_MIN_FRAME_SIZE || frame_size > PAGE_SIZE) {
+ /* Strictly speaking we could support this, if:
+ * - huge pages, or*
+ * - using an IOMMU, or
+ * - making sure the memory area is consecutive
+ * but for now, we simply say "computer says no".
+ */
+ return -EINVAL;
+ }
+
+ if (!is_power_of_2(frame_size))
+ return -EINVAL;
+
+ if (!PAGE_ALIGNED(addr)) {
+ /* Memory area has to be page size aligned. For
+ * simplicity, this might change.
+ */
+ return -EINVAL;
+ }
+
+ if ((addr + size) < addr)
+ return -EINVAL;
+
+ nframes = (unsigned int)div_u64(size, frame_size);
+ if (nframes == 0 || nframes > UINT_MAX)
+ return -EINVAL;
+
+ nfpp = PAGE_SIZE / frame_size;
+ if (nframes < nfpp || nframes % nfpp)
+ return -EINVAL;
+
+ frame_headroom = ALIGN(frame_headroom, 64);
+
+ size_chk = frame_size - frame_headroom - XDP_PACKET_HEADROOM;
+ if (size_chk < 0)
+ return -EINVAL;
+
+ umem->pid = get_task_pid(current, PIDTYPE_PID);
+ umem->size = (size_t)size;
+ umem->address = (unsigned long)addr;
+ umem->props.frame_size = frame_size;
+ umem->props.nframes = nframes;
+ umem->frame_headroom = frame_headroom;
+ umem->npgs = size / PAGE_SIZE;
+ umem->pgs = NULL;
+ umem->user = NULL;
+
+ umem->frame_size_log2 = ilog2(frame_size);
+ umem->nfpp_mask = nfpp - 1;
+ umem->nfpplog2 = ilog2(nfpp);
+ atomic_set(&umem->users, 1);
+
+ err = xdp_umem_account_pages(umem);
+ if (err)
+ goto out;
+
+ err = xdp_umem_pin_pages(umem);
+ if (err)
+ goto out_account;
+ return 0;
+
+out_account:
+ xdp_umem_unaccount_pages(umem);
+out:
+ put_pid(umem->pid);
+ return err;
+}
+
+bool xdp_umem_validate_queues(struct xdp_umem *umem)
+{
+ return (umem->fq && umem->cq);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_H_
+#define XDP_UMEM_H_
+
+#include <linux/mm.h>
+#include <linux/if_xdp.h>
+#include <linux/workqueue.h>
+
+#include "xsk_queue.h"
+#include "xdp_umem_props.h"
+
+struct xdp_umem {
+ struct xsk_queue *fq;
+ struct xsk_queue *cq;
+ struct page **pgs;
+ struct xdp_umem_props props;
+ u32 npgs;
+ u32 frame_headroom;
+ u32 nfpp_mask;
+ u32 nfpplog2;
+ u32 frame_size_log2;
+ struct user_struct *user;
+ struct pid *pid;
+ unsigned long address;
+ size_t size;
+ atomic_t users;
+ struct work_struct work;
+};
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u32 idx)
+{
+ u64 pg, off;
+ char *data;
+
+ pg = idx >> umem->nfpplog2;
+ off = (idx & umem->nfpp_mask) << umem->frame_size_log2;
+
+ data = page_address(umem->pgs[pg]);
+ return data + off;
+}
+
+static inline char *xdp_umem_get_data_with_headroom(struct xdp_umem *umem,
+ u32 idx)
+{
+ return xdp_umem_get_data(umem, idx) + umem->frame_headroom;
+}
+
+bool xdp_umem_validate_queues(struct xdp_umem *umem);
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr);
+void xdp_get_umem(struct xdp_umem *umem);
+void xdp_put_umem(struct xdp_umem *umem);
+int xdp_umem_create(struct xdp_umem **umem);
+
+#endif /* XDP_UMEM_H_ */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_PROPS_H_
+#define XDP_UMEM_PROPS_H_
+
+struct xdp_umem_props {
+ u32 frame_size;
+ u32 nframes;
+};
+
+#endif /* XDP_UMEM_PROPS_H_ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* XDP sockets
+ *
+ * AF_XDP sockets allows a channel between XDP programs and userspace
+ * applications.
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ * Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__
+
+#include <linux/if_xdp.h>
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/socket.h>
+#include <linux/file.h>
+#include <linux/uaccess.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <net/xdp_sock.h>
+#include <net/xdp.h>
+
+#include "xsk_queue.h"
+#include "xdp_umem.h"
+
+#define TX_BATCH_SIZE 16
+
+static struct xdp_sock *xdp_sk(struct sock *sk)
+{
+ return (struct xdp_sock *)sk;
+}
+
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+ return !!xs->rx;
+}
+
+static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ u32 *id, len = xdp->data_end - xdp->data;
+ void *buffer;
+ int err = 0;
+
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+ return -EINVAL;
+
+ id = xskq_peek_id(xs->umem->fq);
+ if (!id)
+ return -ENOSPC;
+
+ buffer = xdp_umem_get_data_with_headroom(xs->umem, *id);
+ memcpy(buffer, xdp->data, len);
+ err = xskq_produce_batch_desc(xs->rx, *id, len,
+ xs->umem->frame_headroom);
+ if (!err)
+ xskq_discard_id(xs->umem->fq);
+
+ return err;
+}
+
+int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ int err;
+
+ err = __xsk_rcv(xs, xdp);
+ if (likely(!err))
+ xdp_return_buff(xdp);
+ else
+ xs->rx_dropped++;
+
+ return err;
+}
+
+void xsk_flush(struct xdp_sock *xs)
+{
+ xskq_produce_flush_desc(xs->rx);
+ xs->sk.sk_data_ready(&xs->sk);
+}
+
+int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+ int err;
+
+ err = __xsk_rcv(xs, xdp);
+ if (!err)
+ xsk_flush(xs);
+ else
+ xs->rx_dropped++;
+
+ return err;
+}
+
+static void xsk_destruct_skb(struct sk_buff *skb)
+{
+ u32 id = (u32)(long)skb_shinfo(skb)->destructor_arg;
+ struct xdp_sock *xs = xdp_sk(skb->sk);
+
+ WARN_ON_ONCE(xskq_produce_id(xs->umem->cq, id));
+
+ sock_wfree(skb);
+}
+
+static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
+ size_t total_len)
+{
+ bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
+ u32 max_batch = TX_BATCH_SIZE;
+ struct xdp_sock *xs = xdp_sk(sk);
+ bool sent_frame = false;
+ struct xdp_desc desc;
+ struct sk_buff *skb;
+ int err = 0;
+
+ if (unlikely(!xs->tx))
+ return -ENOBUFS;
+ if (need_wait)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&xs->mutex);
+
+ while (xskq_peek_desc(xs->tx, &desc)) {
+ char *buffer;
+ u32 id, len;
+
+ if (max_batch-- == 0) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ if (xskq_reserve_id(xs->umem->cq)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ len = desc.len;
+ if (unlikely(len > xs->dev->mtu)) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ skb = sock_alloc_send_skb(sk, len, !need_wait, &err);
+ if (unlikely(!skb)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ skb_put(skb, len);
+ id = desc.idx;
+ buffer = xdp_umem_get_data(xs->umem, id) + desc.offset;
+ err = skb_store_bits(skb, 0, buffer, len);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb->dev = xs->dev;
+ skb->priority = sk->sk_priority;
+ skb->mark = sk->sk_mark;
+ skb_shinfo(skb)->destructor_arg = (void *)(long)id;
+ skb->destructor = xsk_destruct_skb;
+
+ err = dev_direct_xmit(skb, xs->queue_id);
+ /* Ignore NET_XMIT_CN as packet might have been sent */
+ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
+ err = -EAGAIN;
+ /* SKB consumed by dev_direct_xmit() */
+ goto out;
+ }
+
+ sent_frame = true;
+ xskq_discard_desc(xs->tx);
+ }
+
+out:
+ if (sent_frame)
+ sk->sk_write_space(sk);
+
+ mutex_unlock(&xs->mutex);
+ return err;
+}
+
+static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (unlikely(!xs->dev))
+ return -ENXIO;
+ if (unlikely(!(xs->dev->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ return xsk_generic_xmit(sk, m, total_len);
+}
+
+static unsigned int xsk_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
+{
+ unsigned int mask = datagram_poll(file, sock, wait);
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (xs->rx && !xskq_empty_desc(xs->rx))
+ mask |= POLLIN | POLLRDNORM;
+ if (xs->tx && !xskq_full_desc(xs->tx))
+ mask |= POLLOUT | POLLWRNORM;
+
+ return mask;
+}
+
+static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
+ bool umem_queue)
+{
+ struct xsk_queue *q;
+
+ if (entries == 0 || *queue || !is_power_of_2(entries))
+ return -EINVAL;
+
+ q = xskq_create(entries, umem_queue);
+ if (!q)
+ return -ENOMEM;
+
+ *queue = q;
+ return 0;
+}
+
+static void __xsk_release(struct xdp_sock *xs)
+{
+ /* Wait for driver to stop using the xdp socket. */
+ synchronize_net();
+
+ dev_put(xs->dev);
+}
+
+static int xsk_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ struct net *net;
+
+ if (!sk)
+ return 0;
+
+ net = sock_net(sk);
+
+ local_bh_disable();
+ sock_prot_inuse_add(net, sk->sk_prot, -1);
+ local_bh_enable();
+
+ if (xs->dev) {
+ __xsk_release(xs);
+ xs->dev = NULL;
+ }
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ sk_refcnt_debug_release(sk);
+ sock_put(sk);
+
+ return 0;
+}
+
+static struct socket *xsk_lookup_xsk_from_fd(int fd)
+{
+ struct socket *sock;
+ int err;
+
+ sock = sockfd_lookup(fd, &err);
+ if (!sock)
+ return ERR_PTR(-ENOTSOCK);
+
+ if (sock->sk->sk_family != PF_XDP) {
+ sockfd_put(sock);
+ return ERR_PTR(-ENOPROTOOPT);
+ }
+
+ return sock;
+}
+
+static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+{
+ struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
+ struct sock *sk = sock->sk;
+ struct net_device *dev, *dev_curr;
+ struct xdp_sock *xs = xdp_sk(sk);
+ struct xdp_umem *old_umem = NULL;
+ int err = 0;
+
+ if (addr_len < sizeof(struct sockaddr_xdp))
+ return -EINVAL;
+ if (sxdp->sxdp_family != AF_XDP)
+ return -EINVAL;
+
+ mutex_lock(&xs->mutex);
+ dev_curr = xs->dev;
+ dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_release;
+ }
+
+ if (!xs->rx && !xs->tx) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (sxdp->sxdp_queue_id >= dev->num_rx_queues) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (sxdp->sxdp_flags & XDP_SHARED_UMEM) {
+ struct xdp_sock *umem_xs;
+ struct socket *sock;
+
+ if (xs->umem) {
+ /* We have already our own. */
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
+ if (IS_ERR(sock)) {
+ err = PTR_ERR(sock);
+ goto out_unlock;
+ }
+
+ umem_xs = xdp_sk(sock->sk);
+ if (!umem_xs->umem) {
+ /* No umem to inherit. */
+ err = -EBADF;
+ sockfd_put(sock);
+ goto out_unlock;
+ } else if (umem_xs->dev != dev ||
+ umem_xs->queue_id != sxdp->sxdp_queue_id) {
+ err = -EINVAL;
+ sockfd_put(sock);
+ goto out_unlock;
+ }
+
+ xdp_get_umem(umem_xs->umem);
+ old_umem = xs->umem;
+ xs->umem = umem_xs->umem;
+ sockfd_put(sock);
+ } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
+ err = -EINVAL;
+ goto out_unlock;
+ } else {
+ /* This xsk has its own umem. */
+ xskq_set_umem(xs->umem->fq, &xs->umem->props);
+ xskq_set_umem(xs->umem->cq, &xs->umem->props);
+ }
+
+ /* Rebind? */
+ if (dev_curr && (dev_curr != dev ||
+ xs->queue_id != sxdp->sxdp_queue_id)) {
+ __xsk_release(xs);
+ if (old_umem)
+ xdp_put_umem(old_umem);
+ }
+
+ xs->dev = dev;
+ xs->queue_id = sxdp->sxdp_queue_id;
+
+ xskq_set_umem(xs->rx, &xs->umem->props);
+ xskq_set_umem(xs->tx, &xs->umem->props);
+
+out_unlock:
+ if (err)
+ dev_put(dev);
+out_release:
+ mutex_unlock(&xs->mutex);
+ return err;
+}
+
+static int xsk_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ int err;
+
+ if (level != SOL_XDP)
+ return -ENOPROTOOPT;
+
+ switch (optname) {
+ case XDP_RX_RING:
+ case XDP_TX_RING:
+ {
+ struct xsk_queue **q;
+ int entries;
+
+ if (optlen < sizeof(entries))
+ return -EINVAL;
+ if (copy_from_user(&entries, optval, sizeof(entries)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx;
+ err = xsk_init_queue(entries, q, false);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+ case XDP_UMEM_REG:
+ {
+ struct xdp_umem_reg mr;
+ struct xdp_umem *umem;
+
+ if (xs->umem)
+ return -EBUSY;
+
+ if (copy_from_user(&mr, optval, sizeof(mr)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ err = xdp_umem_create(&umem);
+
+ err = xdp_umem_reg(umem, &mr);
+ if (err) {
+ kfree(umem);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+
+ /* Make sure umem is ready before it can be seen by others */
+ smp_wmb();
+
+ xs->umem = umem;
+ mutex_unlock(&xs->mutex);
+ return 0;
+ }
+ case XDP_UMEM_FILL_RING:
+ case XDP_UMEM_COMPLETION_RING:
+ {
+ struct xsk_queue **q;
+ int entries;
+
+ if (!xs->umem)
+ return -EINVAL;
+
+ if (copy_from_user(&entries, optval, sizeof(entries)))
+ return -EFAULT;
+
+ mutex_lock(&xs->mutex);
+ q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
+ &xs->umem->cq;
+ err = xsk_init_queue(entries, q, true);
+ mutex_unlock(&xs->mutex);
+ return err;
+ }
+ default:
+ break;
+ }
+
+ return -ENOPROTOOPT;
+}
+
+static int xsk_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct xdp_sock *xs = xdp_sk(sk);
+ int len;
+
+ if (level != SOL_XDP)
+ return -ENOPROTOOPT;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+ if (len < 0)
+ return -EINVAL;
+
+ switch (optname) {
+ case XDP_STATISTICS:
+ {
+ struct xdp_statistics stats;
+
+ if (len < sizeof(stats))
+ return -EINVAL;
+
+ mutex_lock(&xs->mutex);
+ stats.rx_dropped = xs->rx_dropped;
+ stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx);
+ stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx);
+ mutex_unlock(&xs->mutex);
+
+ if (copy_to_user(optval, &stats, sizeof(stats)))
+ return -EFAULT;
+ if (put_user(sizeof(stats), optlen))
+ return -EFAULT;
+
+ return 0;
+ }
+ default:
+ break;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static int xsk_mmap(struct file *file, struct socket *sock,
+ struct vm_area_struct *vma)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long size = vma->vm_end - vma->vm_start;
+ struct xdp_sock *xs = xdp_sk(sock->sk);
+ struct xsk_queue *q = NULL;
+ unsigned long pfn;
+ struct page *qpg;
+
+ if (offset == XDP_PGOFF_RX_RING) {
+ q = xs->rx;
+ } else if (offset == XDP_PGOFF_TX_RING) {
+ q = xs->tx;
+ } else {
+ if (!xs->umem)
+ return -EINVAL;
+
+ if (offset == XDP_UMEM_PGOFF_FILL_RING)
+ q = xs->umem->fq;
+ else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
+ q = xs->umem->cq;
+ }
+
+ if (!q)
+ return -EINVAL;
+
+ qpg = virt_to_head_page(q->ring);
+ if (size > (PAGE_SIZE << compound_order(qpg)))
+ return -EINVAL;
+
+ pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
+ return remap_pfn_range(vma, vma->vm_start, pfn,
+ size, vma->vm_page_prot);
+}
+
+static struct proto xsk_proto = {
+ .name = "XDP",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct xdp_sock),
+};
+
+static const struct proto_ops xsk_proto_ops = {
+ .family = PF_XDP,
+ .owner = THIS_MODULE,
+ .release = xsk_release,
+ .bind = xsk_bind,
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = xsk_poll,
+ .ioctl = sock_no_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = xsk_setsockopt,
+ .getsockopt = xsk_getsockopt,
+ .sendmsg = xsk_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .mmap = xsk_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+static void xsk_destruct(struct sock *sk)
+{
+ struct xdp_sock *xs = xdp_sk(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ return;
+
+ xskq_destroy(xs->rx);
+ xskq_destroy(xs->tx);
+ xdp_put_umem(xs->umem);
+
+ sk_refcnt_debug_dec(sk);
+}
+
+static int xsk_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
+{
+ struct sock *sk;
+ struct xdp_sock *xs;
+
+ if (!ns_capable(net->user_ns, CAP_NET_RAW))
+ return -EPERM;
+ if (sock->type != SOCK_RAW)
+ return -ESOCKTNOSUPPORT;
+
+ if (protocol)
+ return -EPROTONOSUPPORT;
+
+ sock->state = SS_UNCONNECTED;
+
+ sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern);
+ if (!sk)
+ return -ENOBUFS;
+
+ sock->ops = &xsk_proto_ops;
+
+ sock_init_data(sock, sk);
+
+ sk->sk_family = PF_XDP;
+
+ sk->sk_destruct = xsk_destruct;
+ sk_refcnt_debug_inc(sk);
+
+ xs = xdp_sk(sk);
+ mutex_init(&xs->mutex);
+
+ local_bh_disable();
+ sock_prot_inuse_add(net, &xsk_proto, 1);
+ local_bh_enable();
+
+ return 0;
+}
+
+static const struct net_proto_family xsk_family_ops = {
+ .family = PF_XDP,
+ .create = xsk_create,
+ .owner = THIS_MODULE,
+};
+
+static int __init xsk_init(void)
+{
+ int err;
+
+ err = proto_register(&xsk_proto, 0 /* no slab */);
+ if (err)
+ goto out;
+
+ err = sock_register(&xsk_family_ops);
+ if (err)
+ goto out_proto;
+
+ return 0;
+
+out_proto:
+ proto_unregister(&xsk_proto);
+out:
+ return err;
+}
+
+fs_initcall(xsk_init);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/slab.h>
+
+#include "xsk_queue.h"
+
+void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props)
+{
+ if (!q)
+ return;
+
+ q->umem_props = *umem_props;
+}
+
+static u32 xskq_umem_get_ring_size(struct xsk_queue *q)
+{
+ return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32);
+}
+
+static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q)
+{
+ return (sizeof(struct xdp_ring) +
+ q->nentries * sizeof(struct xdp_desc));
+}
+
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
+{
+ struct xsk_queue *q;
+ gfp_t gfp_flags;
+ size_t size;
+
+ q = kzalloc(sizeof(*q), GFP_KERNEL);
+ if (!q)
+ return NULL;
+
+ q->nentries = nentries;
+ q->ring_mask = nentries - 1;
+
+ gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
+ __GFP_COMP | __GFP_NORETRY;
+ size = umem_queue ? xskq_umem_get_ring_size(q) :
+ xskq_rxtx_get_ring_size(q);
+
+ q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
+ get_order(size));
+ if (!q->ring) {
+ kfree(q);
+ return NULL;
+ }
+
+ return q;
+}
+
+void xskq_destroy(struct xsk_queue *q)
+{
+ if (!q)
+ return;
+
+ page_frag_free(q->ring);
+ kfree(q);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _LINUX_XSK_QUEUE_H
+#define _LINUX_XSK_QUEUE_H
+
+#include <linux/types.h>
+#include <linux/if_xdp.h>
+
+#include "xdp_umem_props.h"
+
+#define RX_BATCH_SIZE 16
+
+struct xsk_queue {
+ struct xdp_umem_props umem_props;
+ u32 ring_mask;
+ u32 nentries;
+ u32 prod_head;
+ u32 prod_tail;
+ u32 cons_head;
+ u32 cons_tail;
+ struct xdp_ring *ring;
+ u64 invalid_descs;
+};
+
+/* Common functions operating for both RXTX and umem queues */
+
+static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
+{
+ return q ? q->invalid_descs : 0;
+}
+
+static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt)
+{
+ u32 entries = q->prod_tail - q->cons_tail;
+
+ if (entries == 0) {
+ /* Refresh the local pointer */
+ q->prod_tail = READ_ONCE(q->ring->producer);
+ entries = q->prod_tail - q->cons_tail;
+ }
+
+ return (entries > dcnt) ? dcnt : entries;
+}
+
+static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
+{
+ u32 free_entries = q->nentries - (producer - q->cons_tail);
+
+ if (free_entries >= dcnt)
+ return free_entries;
+
+ /* Refresh the local tail pointer */
+ q->cons_tail = READ_ONCE(q->ring->consumer);
+ return q->nentries - (producer - q->cons_tail);
+}
+
+/* UMEM queue */
+
+static inline bool xskq_is_valid_id(struct xsk_queue *q, u32 idx)
+{
+ if (unlikely(idx >= q->umem_props.nframes)) {
+ q->invalid_descs++;
+ return false;
+ }
+ return true;
+}
+
+static inline u32 *xskq_validate_id(struct xsk_queue *q)
+{
+ while (q->cons_tail != q->cons_head) {
+ struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+ unsigned int idx = q->cons_tail & q->ring_mask;
+
+ if (xskq_is_valid_id(q, ring->desc[idx]))
+ return &ring->desc[idx];
+
+ q->cons_tail++;
+ }
+
+ return NULL;
+}
+
+static inline u32 *xskq_peek_id(struct xsk_queue *q)
+{
+ struct xdp_umem_ring *ring;
+
+ if (q->cons_tail == q->cons_head) {
+ WRITE_ONCE(q->ring->consumer, q->cons_tail);
+ q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE);
+
+ /* Order consumer and data */
+ smp_rmb();
+
+ return xskq_validate_id(q);
+ }
+
+ ring = (struct xdp_umem_ring *)q->ring;
+ return &ring->desc[q->cons_tail & q->ring_mask];
+}
+
+static inline void xskq_discard_id(struct xsk_queue *q)
+{
+ q->cons_tail++;
+ (void)xskq_validate_id(q);
+}
+
+static inline int xskq_produce_id(struct xsk_queue *q, u32 id)
+{
+ struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+ ring->desc[q->prod_tail++ & q->ring_mask] = id;
+
+ /* Order producer and data */
+ smp_wmb();
+
+ WRITE_ONCE(q->ring->producer, q->prod_tail);
+ return 0;
+}
+
+static inline int xskq_reserve_id(struct xsk_queue *q)
+{
+ if (xskq_nb_free(q, q->prod_head, 1) == 0)
+ return -ENOSPC;
+
+ q->prod_head++;
+ return 0;
+}
+
+/* Rx/Tx queue */
+
+static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d)
+{
+ u32 buff_len;
+
+ if (unlikely(d->idx >= q->umem_props.nframes)) {
+ q->invalid_descs++;
+ return false;
+ }
+
+ buff_len = q->umem_props.frame_size;
+ if (unlikely(d->len > buff_len || d->len == 0 ||
+ d->offset > buff_len || d->offset + d->len > buff_len)) {
+ q->invalid_descs++;
+ return false;
+ }
+
+ return true;
+}
+
+static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q,
+ struct xdp_desc *desc)
+{
+ while (q->cons_tail != q->cons_head) {
+ struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+ unsigned int idx = q->cons_tail & q->ring_mask;
+
+ if (xskq_is_valid_desc(q, &ring->desc[idx])) {
+ if (desc)
+ *desc = ring->desc[idx];
+ return desc;
+ }
+
+ q->cons_tail++;
+ }
+
+ return NULL;
+}
+
+static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q,
+ struct xdp_desc *desc)
+{
+ struct xdp_rxtx_ring *ring;
+
+ if (q->cons_tail == q->cons_head) {
+ WRITE_ONCE(q->ring->consumer, q->cons_tail);
+ q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE);
+
+ /* Order consumer and data */
+ smp_rmb();
+
+ return xskq_validate_desc(q, desc);
+ }
+
+ ring = (struct xdp_rxtx_ring *)q->ring;
+ *desc = ring->desc[q->cons_tail & q->ring_mask];
+ return desc;
+}
+
+static inline void xskq_discard_desc(struct xsk_queue *q)
+{
+ q->cons_tail++;
+ (void)xskq_validate_desc(q, NULL);
+}
+
+static inline int xskq_produce_batch_desc(struct xsk_queue *q,
+ u32 id, u32 len, u16 offset)
+{
+ struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+ unsigned int idx;
+
+ if (xskq_nb_free(q, q->prod_head, 1) == 0)
+ return -ENOSPC;
+
+ idx = (q->prod_head++) & q->ring_mask;
+ ring->desc[idx].idx = id;
+ ring->desc[idx].len = len;
+ ring->desc[idx].offset = offset;
+
+ return 0;
+}
+
+static inline void xskq_produce_flush_desc(struct xsk_queue *q)
+{
+ /* Order producer and data */
+ smp_wmb();
+
+ q->prod_tail = q->prod_head,
+ WRITE_ONCE(q->ring->producer, q->prod_tail);
+}
+
+static inline bool xskq_full_desc(struct xsk_queue *q)
+{
+ return (xskq_nb_avail(q, q->nentries) == q->nentries);
+}
+
+static inline bool xskq_empty_desc(struct xsk_queue *q)
+{
+ return (xskq_nb_free(q, q->prod_tail, 1) == q->nentries);
+}
+
+void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props);
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
+void xskq_destroy(struct xsk_queue *q_ops);
+
+#endif /* _LINUX_XSK_QUEUE_H */
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
+static struct kmem_cache *xfrm_state_cache __ro_after_init;
static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
static HLIST_HEAD(xfrm_state_gc_list);
}
xfrm_dev_state_free(x);
security_xfrm_state_free(x);
- kfree(x);
+ kmem_cache_free(xfrm_state_cache, x);
}
static void xfrm_state_gc_task(struct work_struct *work)
{
struct xfrm_state *x;
- x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC);
+ x = kmem_cache_alloc(xfrm_state_cache, GFP_ATOMIC | __GFP_ZERO);
if (x) {
write_pnet(&x->xs_net, net);
return afinfo;
}
+void xfrm_flush_gc(void)
+{
+ flush_work(&xfrm_state_gc_work);
+}
+EXPORT_SYMBOL(xfrm_flush_gc);
+
/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
void xfrm_state_delete_tunnel(struct xfrm_state *x)
{
{
unsigned int sz;
+ if (net_eq(net, &init_net))
+ xfrm_state_cache = KMEM_CACHE(xfrm_state,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+
INIT_LIST_HEAD(&net->xfrm.state_all);
sz = sizeof(struct hlist_head) * 8;
# SPDX-License-Identifier: GPL-2.0
+
+BPF_SAMPLES_PATH ?= $(abspath $(srctree)/$(src))
+TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools
+
# List of programs to build
hostprogs-y := test_lru_dist
hostprogs-y += sock_example
hostprogs-y += syscall_tp
hostprogs-y += cpustat
hostprogs-y += xdp_adjust_tail
+hostprogs-y += xdpsock
+hostprogs-y += xdp_fwd
# Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
-CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
+LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
-test_lru_dist-objs := test_lru_dist.o $(LIBBPF)
-sock_example-objs := sock_example.o $(LIBBPF)
-fds_example-objs := bpf_load.o $(LIBBPF) fds_example.o
-sockex1-objs := bpf_load.o $(LIBBPF) sockex1_user.o
-sockex2-objs := bpf_load.o $(LIBBPF) sockex2_user.o
-sockex3-objs := bpf_load.o $(LIBBPF) sockex3_user.o
-tracex1-objs := bpf_load.o $(LIBBPF) tracex1_user.o
-tracex2-objs := bpf_load.o $(LIBBPF) tracex2_user.o
-tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
-tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
-tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
-tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
-tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o
-load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
-test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
-trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
-lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o
-offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o
-spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o
-map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o
-test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o
-test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o
-test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o
-test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o $(CGROUP_HELPERS)
-test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o
-test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o
-xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o
+CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
+TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o
+
+fds_example-objs := bpf_load.o fds_example.o
+sockex1-objs := bpf_load.o sockex1_user.o
+sockex2-objs := bpf_load.o sockex2_user.o
+sockex3-objs := bpf_load.o sockex3_user.o
+tracex1-objs := bpf_load.o tracex1_user.o
+tracex2-objs := bpf_load.o tracex2_user.o
+tracex3-objs := bpf_load.o tracex3_user.o
+tracex4-objs := bpf_load.o tracex4_user.o
+tracex5-objs := bpf_load.o tracex5_user.o
+tracex6-objs := bpf_load.o tracex6_user.o
+tracex7-objs := bpf_load.o tracex7_user.o
+load_sock_ops-objs := bpf_load.o load_sock_ops.o
+test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o
+trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS)
+lathist-objs := bpf_load.o lathist_user.o
+offwaketime-objs := bpf_load.o offwaketime_user.o $(TRACE_HELPERS)
+spintest-objs := bpf_load.o spintest_user.o $(TRACE_HELPERS)
+map_perf_test-objs := bpf_load.o map_perf_test_user.o
+test_overhead-objs := bpf_load.o test_overhead_user.o
+test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o
+test_cgrp2_attach-objs := test_cgrp2_attach.o
+test_cgrp2_attach2-objs := test_cgrp2_attach2.o $(CGROUP_HELPERS)
+test_cgrp2_sock-objs := test_cgrp2_sock.o
+test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o
+xdp1-objs := xdp1_user.o
# reuse xdp1 source intentionally
-xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o
-xdp_router_ipv4-objs := bpf_load.o $(LIBBPF) xdp_router_ipv4_user.o
-test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) $(CGROUP_HELPERS) \
+xdp2-objs := xdp1_user.o
+xdp_router_ipv4-objs := bpf_load.o xdp_router_ipv4_user.o
+test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \
test_current_task_under_cgroup_user.o
-trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o
-sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
-tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
-lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
-xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
-test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
-per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
-xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
-xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
-xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
-xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
-xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
-syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
-cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
-xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o
+trace_event-objs := bpf_load.o trace_event_user.o $(TRACE_HELPERS)
+sampleip-objs := bpf_load.o sampleip_user.o $(TRACE_HELPERS)
+tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o
+lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := bpf_load.o xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o test_map_in_map_user.o
+per_socket_stats_example-objs := cookie_uid_helper_example.o
+xdp_redirect-objs := bpf_load.o xdp_redirect_user.o
+xdp_redirect_map-objs := bpf_load.o xdp_redirect_map_user.o
+xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o
+xdp_monitor-objs := bpf_load.o xdp_monitor_user.o
+xdp_rxq_info-objs := xdp_rxq_info_user.o
+syscall_tp-objs := bpf_load.o syscall_tp_user.o
+cpustat-objs := bpf_load.o cpustat_user.o
+xdp_adjust_tail-objs := xdp_adjust_tail_user.o
+xdpsock-objs := bpf_load.o xdpsock_user.o
+xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
always += test_probe_write_user_kern.o
always += trace_output_kern.o
always += tcbpf1_kern.o
-always += tcbpf2_kern.o
always += tc_l2_redirect_kern.o
always += lathist_kern.o
always += offwaketime_kern.o
always += syscall_tp_kern.o
always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
+always += xdpsock_kern.o
+always += xdp_fwd_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
HOSTCFLAGS += -I$(srctree)/tools/perf
HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
-HOSTLOADLIBES_fds_example += -lelf
-HOSTLOADLIBES_sockex1 += -lelf
-HOSTLOADLIBES_sockex2 += -lelf
-HOSTLOADLIBES_sockex3 += -lelf
-HOSTLOADLIBES_tracex1 += -lelf
-HOSTLOADLIBES_tracex2 += -lelf
-HOSTLOADLIBES_tracex3 += -lelf
-HOSTLOADLIBES_tracex4 += -lelf -lrt
-HOSTLOADLIBES_tracex5 += -lelf
-HOSTLOADLIBES_tracex6 += -lelf
-HOSTLOADLIBES_tracex7 += -lelf
-HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
-HOSTLOADLIBES_load_sock_ops += -lelf
-HOSTLOADLIBES_test_probe_write_user += -lelf
-HOSTLOADLIBES_trace_output += -lelf -lrt
-HOSTLOADLIBES_lathist += -lelf
-HOSTLOADLIBES_offwaketime += -lelf
-HOSTLOADLIBES_spintest += -lelf
-HOSTLOADLIBES_map_perf_test += -lelf -lrt
-HOSTLOADLIBES_test_overhead += -lelf -lrt
-HOSTLOADLIBES_xdp1 += -lelf
-HOSTLOADLIBES_xdp2 += -lelf
-HOSTLOADLIBES_xdp_router_ipv4 += -lelf
-HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
-HOSTLOADLIBES_trace_event += -lelf
-HOSTLOADLIBES_sampleip += -lelf
-HOSTLOADLIBES_tc_l2_redirect += -l elf
-HOSTLOADLIBES_lwt_len_hist += -l elf
-HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
-HOSTLOADLIBES_test_map_in_map += -lelf
-HOSTLOADLIBES_xdp_redirect += -lelf
-HOSTLOADLIBES_xdp_redirect_map += -lelf
-HOSTLOADLIBES_xdp_redirect_cpu += -lelf
-HOSTLOADLIBES_xdp_monitor += -lelf
-HOSTLOADLIBES_xdp_rxq_info += -lelf
-HOSTLOADLIBES_syscall_tp += -lelf
-HOSTLOADLIBES_cpustat += -lelf
-HOSTLOADLIBES_xdp_adjust_tail += -lelf
+HOSTCFLAGS_trace_helpers.o += -I$(srctree)/tools/lib/bpf/
+
+HOSTCFLAGS_trace_output_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_offwaketime_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
+
+HOST_LOADLIBES += $(LIBBPF) -lelf
+HOSTLOADLIBES_tracex4 += -lrt
+HOSTLOADLIBES_trace_output += -lrt
+HOSTLOADLIBES_map_perf_test += -lrt
+HOSTLOADLIBES_test_overhead += -lrt
+HOSTLOADLIBES_xdpsock += -pthread
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
endif
# Trick to allow make to be run from this directory
-all: $(LIBBPF)
- $(MAKE) -C ../../ $(CURDIR)/
+all:
+ $(MAKE) -C ../../ $(CURDIR)/ BPF_SAMPLES_PATH=$(CURDIR)
clean:
$(MAKE) -C ../../ M=$(CURDIR) clean
@rm -f *~
$(LIBBPF): FORCE
- $(MAKE) -C $(dir $@) $(notdir $@)
+# Fix up variables inherited from Kbuild that tools/ build system won't like
+ $(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(BPF_SAMPLES_PATH)/../../ O=
$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c
$(call if_changed_dep,cc_s_c)
exit 2; \
else true; fi
-$(src)/*.c: verify_target_bpf
+$(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF)
+$(src)/*.c: verify_target_bpf $(LIBBPF)
$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
# But, there is no easy way to fix it, so just exclude it since it is
# useless for BPF samples.
$(obj)/%.o: $(src)/%.c
- $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
+ @echo " CLANG-bpf " $@
+ $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-I$(srctree)/tools/testing/selftests/bpf/ \
- -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
/* SPDX-License-Identifier: GPL-2.0 */
-/* eBPF mini library */
-#ifndef __LIBBPF_H
-#define __LIBBPF_H
-
-#include <bpf/bpf.h>
+/* eBPF instruction mini library */
+#ifndef __BPF_INSN_H
+#define __BPF_INSN_H
struct bpf_insn;
#include <poll.h>
#include <ctype.h>
#include <assert.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
}
if (is_kprobe || is_kretprobe) {
+ bool need_normal_check = true;
+ const char *event_prefix = "";
+
if (is_kprobe)
event += 7;
else
if (isdigit(*event))
return populate_prog_array(event, fd);
- snprintf(buf, sizeof(buf),
- "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
- is_kprobe ? 'p' : 'r', event, event);
- err = system(buf);
- if (err < 0) {
- printf("failed to create kprobe '%s' error '%s'\n",
- event, strerror(errno));
- return -1;
+#ifdef __x86_64__
+ if (strncmp(event, "sys_", 4) == 0) {
+ snprintf(buf, sizeof(buf),
+ "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events",
+ is_kprobe ? 'p' : 'r', event, event);
+ err = system(buf);
+ if (err >= 0) {
+ need_normal_check = false;
+ event_prefix = "__x64_";
+ }
+ }
+#endif
+ if (need_normal_check) {
+ snprintf(buf, sizeof(buf),
+ "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
+ is_kprobe ? 'p' : 'r', event, event);
+ err = system(buf);
+ if (err < 0) {
+ printf("failed to create kprobe '%s' error '%s'\n",
+ event, strerror(errno));
+ return -1;
+ }
}
strcpy(buf, DEBUGFS);
strcat(buf, "events/kprobes/");
+ strcat(buf, event_prefix);
strcat(buf, event);
strcat(buf, "/id");
} else if (is_tracepoint) {
/* Keeping compatible with ELF maps section changes
* ------------------------------------------------
- * The program size of struct bpf_map_def is known by loader
+ * The program size of struct bpf_load_map_def is known by loader
* code, but struct stored in ELF file can be different.
*
* Unfortunately sym[i].st_size is zero. To calculate the
* symbols.
*/
map_sz_elf = data_maps->d_size / nr_maps;
- map_sz_copy = sizeof(struct bpf_map_def);
+ map_sz_copy = sizeof(struct bpf_load_map_def);
if (map_sz_elf < map_sz_copy) {
/*
* Backward compat, loading older ELF file with
/* Memcpy relevant part of ELF maps data to loader maps */
for (i = 0; i < nr_maps; i++) {
+ struct bpf_load_map_def *def;
unsigned char *addr, *end;
- struct bpf_map_def *def;
const char *map_name;
size_t offset;
/* Symbol value is offset into ELF maps section data area */
offset = sym[i].st_value;
- def = (struct bpf_map_def *)(data_maps->d_buf + offset);
+ def = (struct bpf_load_map_def *)(data_maps->d_buf + offset);
maps[i].elf_offset = offset;
- memset(&maps[i].def, 0, sizeof(struct bpf_map_def));
+ memset(&maps[i].def, 0, sizeof(struct bpf_load_map_def));
memcpy(&maps[i].def, def, map_sz_copy);
/* Verify no newer features were requested */
if (nr_maps < 0) {
printf("Error: Failed loading ELF maps (errno:%d):%s\n",
nr_maps, strerror(-nr_maps));
- ret = 1;
goto done;
}
if (load_maps(map_data, nr_maps, fixup_map))
}
}
- ret = 0;
done:
close(fd);
return ret;
}
}
}
-
-#define MAX_SYMS 300000
-static struct ksym syms[MAX_SYMS];
-static int sym_cnt;
-
-static int ksym_cmp(const void *p1, const void *p2)
-{
- return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
-}
-
-int load_kallsyms(void)
-{
- FILE *f = fopen("/proc/kallsyms", "r");
- char func[256], buf[256];
- char symbol;
- void *addr;
- int i = 0;
-
- if (!f)
- return -ENOENT;
-
- while (!feof(f)) {
- if (!fgets(buf, sizeof(buf), f))
- break;
- if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
- break;
- if (!addr)
- continue;
- syms[i].addr = (long) addr;
- syms[i].name = strdup(func);
- i++;
- }
- sym_cnt = i;
- qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
- return 0;
-}
-
-struct ksym *ksym_search(long key)
-{
- int start = 0, end = sym_cnt;
- int result;
-
- while (start < end) {
- size_t mid = start + (end - start) / 2;
-
- result = key - syms[mid].addr;
- if (result < 0)
- end = mid;
- else if (result > 0)
- start = mid + 1;
- else
- return &syms[mid];
- }
-
- if (start >= 1 && syms[start - 1].addr < key &&
- key < syms[start].addr)
- /* valid ksym */
- return &syms[start - 1];
-
- /* out of range. return _stext */
- return &syms[0];
-}
-
#ifndef __BPF_LOAD_H
#define __BPF_LOAD_H
-#include "libbpf.h"
+#include <bpf/bpf.h>
#define MAX_MAPS 32
#define MAX_PROGS 32
-struct bpf_map_def {
+struct bpf_load_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
int fd;
char *name;
size_t elf_offset;
- struct bpf_map_def def;
+ struct bpf_load_map_def def;
};
typedef void (*fixup_map_cb)(struct bpf_map_data *map, int idx);
int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map);
void read_trace_pipe(void);
-struct ksym {
- long addr;
- char *name;
-};
-
-int load_kallsyms(void);
-struct ksym *ksym_search(long key);
int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
#endif
#include <sys/types.h>
#include <unistd.h>
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include "bpf_insn.h"
#define PORT 8888
#include <sys/resource.h>
#include <sys/wait.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#define MAX_CPU 8
#include <sys/types.h>
#include <sys/socket.h>
+#include <bpf/bpf.h>
+
+#include "bpf_insn.h"
#include "bpf_load.h"
-#include "libbpf.h"
#include "sock_example.h"
#define BPF_F_PIN (1 << 0)
#include <stdlib.h>
#include <signal.h>
#include <linux/bpf.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#define MAX_ENTRIES 20
#include <stdlib.h>
#include <string.h>
#include <linux/bpf.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include <unistd.h>
#include <errno.h>
#include <errno.h>
#include <arpa/inet.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_util.h"
#define MAX_INDEX 64
#include <arpa/inet.h>
#include <errno.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#define TEST_BIT(t) (1U << (t))
#include <sys/resource.h>
#include "libbpf.h"
#include "bpf_load.h"
+#include "trace_helpers.h"
#define PRINT_RAW_ADDR 0
#include "libbpf.h"
#include "bpf_load.h"
#include "perf-sys.h"
+#include "trace_helpers.h"
#define DEFAULT_FREQ 99
#define DEFAULT_SECS 5
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <stddef.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include "bpf_insn.h"
#include "sock_example.h"
char bpf_log_buf[BPF_LOG_BUF_SIZE];
#include <net/if.h>
#include <linux/if_packet.h>
#include <arpa/inet.h>
-#include "libbpf.h"
static inline int open_raw_sock(const char *name)
{
#include <stdio.h>
#include <assert.h>
#include <linux/bpf.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "sock_example.h"
#include <unistd.h>
#include <stdio.h>
#include <assert.h>
#include <linux/bpf.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "sock_example.h"
#include <unistd.h>
#include <stdio.h>
#include <assert.h>
#include <linux/bpf.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "sock_example.h"
#include <unistd.h>
#include <sys/resource.h>
#include "libbpf.h"
#include "bpf_load.h"
+#include "trace_helpers.h"
int main(int ac, char **argv)
{
#include <assert.h>
#include <stdbool.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
/* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*.
#include <string.h>
#include <errno.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
static void usage(void)
{
#include <errno.h>
#include <fcntl.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
static void usage(void)
{
#include <fcntl.h>
#include <linux/bpf.h>
+#include <bpf/bpf.h>
-#include "libbpf.h"
+#include "bpf_insn.h"
enum {
MAP_KEY_PACKETS,
#include <unistd.h>
#include <linux/bpf.h>
+#include <bpf/bpf.h>
-#include "libbpf.h"
+#include "bpf_insn.h"
#include "cgroup_helpers.h"
#define FOO "/foo"
#include <net/if.h>
#include <inttypes.h>
#include <linux/bpf.h>
+#include <bpf/bpf.h>
-#include "libbpf.h"
+#include "bpf_insn.h"
char bpf_log_buf[BPF_LOG_BUF_SIZE];
#include <fcntl.h>
#include <net/if.h>
#include <linux/bpf.h>
+#include <bpf/bpf.h>
-#include "libbpf.h"
+#include "bpf_insn.h"
#include "bpf_load.h"
static int usage(const char *argv0)
#include <stdio.h>
#include <linux/bpf.h>
#include <unistd.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include <linux/bpf.h>
#include "cgroup_helpers.h"
#include <stdlib.h>
#include <time.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_util.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#define PORT_A (map_fd[0])
#include <string.h>
#include <time.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#define MAX_CNT 1000000
#include <assert.h>
#include <linux/bpf.h>
#include <unistd.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include <sys/socket.h>
#include <string.h>
+++ /dev/null
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-# In Namespace 0 (at_ns0) using native tunnel
-# Overlay IP: 10.1.1.100
-# local 192.16.1.100 remote 192.16.1.200
-# veth0 IP: 172.16.1.100, tunnel dev <type>00
-
-# Out of Namespace using BPF set/get on lwtunnel
-# Overlay IP: 10.1.1.200
-# local 172.16.1.200 remote 172.16.1.100
-# veth1 IP: 172.16.1.200, tunnel dev <type>11
-
-function config_device {
- ip netns add at_ns0
- ip link add veth0 type veth peer name veth1
- ip link set veth0 netns at_ns0
- ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip link set dev veth1 up mtu 1500
- ip addr add dev veth1 172.16.1.200/24
-}
-
-function add_gre_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # out of namespace
- ip link add dev $DEV type $TYPE key 2 external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ip6gretap_tunnel {
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
- local ::11 remote ::22
-
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip addr add dev $DEV fc80::200/24
- ip link set dev $DEV up
-}
-
-function add_erspan_tunnel {
- # in namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 2 erspan_dir egress erspan_hwid 3
- fi
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ip6erspan_tunnel {
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # in namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 2 erspan_dir egress erspan_hwid 7
- fi
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip link set dev $DEV up
-}
-
-function add_vxlan_tunnel {
- # Set static ARP entry here because iptables set-mark works
- # on L3 packet, as a result not applying to ARP packets,
- # causing errors at get_tunnel_{key/opt}.
-
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE id 2 dstport 4789 gbp remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
- ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
-
- # out of namespace
- ip link add dev $DEV type $TYPE external gbp dstport 4789
- ip link set dev $DEV address 52:54:00:d9:02:00 up
- ip addr add dev $DEV 10.1.1.200/24
- arp -s 10.1.1.100 52:54:00:d9:01:00
-}
-
-function add_geneve_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE id 2 dstport 6081 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # out of namespace
- ip link add dev $DEV type $TYPE dstport 6081 external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function add_ipip_tunnel {
- # in namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE local 172.16.1.100 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # out of namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-function attach_bpf {
- DEV=$1
- SET_TUNNEL=$2
- GET_TUNNEL=$3
- tc qdisc add dev $DEV clsact
- tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL
- tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL
-}
-
-function test_gre {
- TYPE=gretap
- DEV_NS=gretap00
- DEV=gretap11
- config_device
- add_gre_tunnel
- attach_bpf $DEV gre_set_tunnel gre_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ip6gre {
- TYPE=ip6gre
- DEV_NS=ip6gre00
- DEV=ip6gre11
- config_device
- # reuse the ip6gretap function
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 -c 4 ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ping -c 1 10.1.1.100
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 -c 1 fc80::200
- cleanup
-}
-
-function test_ip6gretap {
- TYPE=ip6gretap
- DEV_NS=ip6gretap00
- DEV=ip6gretap11
- config_device
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 -c 4 ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping -i .2 -c 1 10.1.1.200
- ping -c 1 10.1.1.100
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 -c 1 fc80::200
- cleanup
-}
-
-function test_erspan {
- TYPE=erspan
- DEV_NS=erspan00
- DEV=erspan11
- config_device
- add_erspan_tunnel $1
- attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ip6erspan {
- TYPE=ip6erspan
- DEV_NS=ip6erspan00
- DEV=ip6erspan11
- config_device
- add_ip6erspan_tunnel $1
- attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
- ping6 -c 3 ::11
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_vxlan {
- TYPE=vxlan
- DEV_NS=vxlan00
- DEV=vxlan11
- config_device
- add_vxlan_tunnel
- attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_geneve {
- TYPE=geneve
- DEV_NS=geneve00
- DEV=geneve11
- config_device
- add_geneve_tunnel
- attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- cleanup
-}
-
-function test_ipip {
- TYPE=ipip
- DEV_NS=ipip00
- DEV=ipip11
- config_device
- tcpdump -nei veth1 &
- cat /sys/kernel/debug/tracing/trace_pipe &
- add_ipip_tunnel
- ethtool -K veth1 gso off gro off rx off tx off
- ip link set dev veth1 mtu 1500
- attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
- ping -c 1 10.1.1.100
- ip netns exec at_ns0 ping -c 1 10.1.1.200
- ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null
- sleep 0.2
- iperf -c 10.1.1.100 -n 5k -p 5200
- cleanup
-}
-
-function cleanup {
- set +ex
- pkill iperf
- ip netns delete at_ns0
- ip link del veth1
- ip link del ipip11
- ip link del gretap11
- ip link del ip6gre11
- ip link del ip6gretap11
- ip link del vxlan11
- ip link del geneve11
- ip link del erspan11
- ip link del ip6erspan11
- pkill tcpdump
- pkill cat
- set -ex
-}
-
-trap cleanup 0 2 3 6 9
-cleanup
-echo "Testing GRE tunnel..."
-test_gre
-echo "Testing IP6GRE tunnel..."
-test_ip6gre
-echo "Testing IP6GRETAP tunnel..."
-test_ip6gretap
-echo "Testing ERSPAN tunnel..."
-test_erspan v1
-test_erspan v2
-echo "Testing IP6ERSPAN tunnel..."
-test_ip6erspan v1
-test_ip6erspan v2
-echo "Testing VXLAN tunnel..."
-test_vxlan
-echo "Testing GENEVE tunnel..."
-test_geneve
-echo "Testing IPIP tunnel..."
-test_ipip
-echo "*** PASS ***"
#include "libbpf.h"
#include "bpf_load.h"
#include "perf-sys.h"
+#include "trace_helpers.h"
#define SAMPLE_FREQ 50
#include <sys/mman.h>
#include <time.h>
#include <signal.h>
-#include "libbpf.h"
+#include <libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
+#include "trace_helpers.h"
static int pmu_fd;
-int page_size;
-int page_cnt = 8;
-volatile struct perf_event_mmap_page *header;
-
-typedef void (*print_fn)(void *data, int size);
-
-static int perf_event_mmap(int fd)
-{
- void *base;
- int mmap_size;
-
- page_size = getpagesize();
- mmap_size = page_size * (page_cnt + 1);
-
- base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
- if (base == MAP_FAILED) {
- printf("mmap err\n");
- return -1;
- }
-
- header = base;
- return 0;
-}
-
-static int perf_event_poll(int fd)
-{
- struct pollfd pfd = { .fd = fd, .events = POLLIN };
-
- return poll(&pfd, 1, 1000);
-}
-
-struct perf_event_sample {
- struct perf_event_header header;
- __u32 size;
- char data[];
-};
-
-static void perf_event_read(print_fn fn)
-{
- __u64 data_tail = header->data_tail;
- __u64 data_head = header->data_head;
- __u64 buffer_size = page_cnt * page_size;
- void *base, *begin, *end;
- char buf[256];
-
- asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
- if (data_head == data_tail)
- return;
-
- base = ((char *)header) + page_size;
-
- begin = base + data_tail % buffer_size;
- end = base + data_head % buffer_size;
-
- while (begin != end) {
- struct perf_event_sample *e;
-
- e = begin;
- if (begin + e->header.size > base + buffer_size) {
- long len = base + buffer_size - begin;
-
- assert(len < e->header.size);
- memcpy(buf, begin, len);
- memcpy(buf + len, base, e->header.size - len);
- e = (void *) buf;
- begin = base + e->header.size - len;
- } else if (begin + e->header.size == base + buffer_size) {
- begin = base;
- } else {
- begin += e->header.size;
- }
-
- if (e->header.type == PERF_RECORD_SAMPLE) {
- fn(e->data, e->size);
- } else if (e->header.type == PERF_RECORD_LOST) {
- struct {
- struct perf_event_header header;
- __u64 id;
- __u64 lost;
- } *lost = (void *) e;
- printf("lost %lld events\n", lost->lost);
- } else {
- printf("unknown event type=%d size=%d\n",
- e->header.type, e->header.size);
- }
- }
-
- __sync_synchronize(); /* smp_mb() */
- header->data_tail = data_head;
-}
-
static __u64 time_get_ns(void)
{
struct timespec ts;
#define MAX_CNT 100000ll
-static void print_bpf_output(void *data, int size)
+static int print_bpf_output(void *data, int size)
{
static __u64 cnt;
struct {
if (e->cookie != 0x12345678) {
printf("BUG pid %llx cookie %llx sized %d\n",
e->pid, e->cookie, size);
- kill(0, SIGINT);
+ return LIBBPF_PERF_EVENT_ERROR;
}
cnt++;
if (cnt == MAX_CNT) {
printf("recv %lld events per sec\n",
MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
- kill(0, SIGINT);
+ return LIBBPF_PERF_EVENT_DONE;
}
+
+ return LIBBPF_PERF_EVENT_CONT;
}
static void test_bpf_perf_event(void)
{
char filename[256];
FILE *f;
+ int ret;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
(void) f;
start_time = time_get_ns();
- for (;;) {
- perf_event_poll(pmu_fd);
- perf_event_read(print_bpf_output);
- }
-
- return 0;
+ ret = perf_event_poller(pmu_fd, print_bpf_output);
+ kill(0, SIGINT);
+ return ret;
}
#include <stdio.h>
#include <linux/bpf.h>
#include <unistd.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
int main(int ac, char **argv)
#include <string.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include <linux/bpf.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include <linux/bpf.h>
#include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
struct pair {
#include <linux/filter.h>
#include <linux/seccomp.h>
#include <sys/prctl.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include <sys/resource.h>
#include <unistd.h>
#include "bpf_load.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "perf-sys.h"
#define SAMPLE_PERIOD 0x7fffffffffffffffULL
#include <stdio.h>
#include <linux/bpf.h>
#include <unistd.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
int main(int argc, char **argv)
#include <libgen.h>
#include <sys/resource.h>
-#include "bpf_load.h"
#include "bpf_util.h"
-#include "libbpf.h"
+#include "bpf/bpf.h"
+#include "bpf/libbpf.h"
static int ifindex;
static __u32 xdp_flags;
/* simple per-protocol drop counter
*/
-static void poll_stats(int interval)
+static void poll_stats(int map_fd, int interval)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
const unsigned int nr_keys = 256;
for (key = 0; key < nr_keys; key++) {
__u64 sum = 0;
- assert(bpf_map_lookup_elem(map_fd[0], &key, values) == 0);
+ assert(bpf_map_lookup_elem(map_fd, &key, values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[key][i]);
if (sum)
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
const char *optstr = "SN";
+ int prog_fd, map_fd, opt;
+ struct bpf_object *obj;
+ struct bpf_map *map;
char filename[256];
- int opt;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
ifindex = strtoul(argv[optind], NULL, 0);
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
+
+ map = bpf_map__next(NULL, obj);
+ if (!map) {
+ printf("finding a map in obj file failed\n");
return 1;
}
+ map_fd = bpf_map__fd(map);
- if (!prog_fd[0]) {
+ if (!prog_fd) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
- poll_stats(2);
+ poll_stats(map_fd, 2);
return 0;
}
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "bpf_load.h"
-#include "libbpf.h"
-#include "bpf_util.h"
+#include "bpf/bpf.h"
+#include "bpf/libbpf.h"
#define STATS_INTERVAL_S 2U
/* simple "icmp packet too big sent" counter
*/
-static void poll_stats(unsigned int kill_after_s)
+static void poll_stats(unsigned int map_fd, unsigned int kill_after_s)
{
time_t started_at = time(NULL);
__u64 value = 0;
while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
sleep(STATS_INTERVAL_S);
- assert(bpf_map_lookup_elem(map_fd[0], &key, &value) == 0);
+ assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
printf("icmp \"packet too big\" sent: %10llu pkts\n", value);
}
int main(int argc, char **argv)
{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
unsigned char opt_flags[256] = {};
unsigned int kill_after_s = 0;
const char *optstr = "i:T:SNh";
- struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int i, prog_fd, map_fd, opt;
+ struct bpf_object *obj;
+ struct bpf_map *map;
char filename[256];
- int opt;
- int i;
-
for (i = 0; i < strlen(optstr); i++)
if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
}
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return 1;
- if (load_bpf_file(filename)) {
- printf("%s", bpf_log_buf);
+ map = bpf_map__next(NULL, obj);
+ if (!map) {
+ printf("finding a map in obj file failed\n");
return 1;
}
+ map_fd = bpf_map__fd(map);
- if (!prog_fd[0]) {
+ if (!prog_fd) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
- poll_stats(kill_after_s);
+ poll_stats(map_fd, kill_after_s);
bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include "bpf_helpers.h"
+
+#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
+
+struct bpf_map_def SEC("maps") tx_port = {
+ .type = BPF_MAP_TYPE_DEVMAP,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 64,
+};
+
+/* from include/net/ip.h */
+static __always_inline int ip_decrease_ttl(struct iphdr *iph)
+{
+ u32 check = (__force u32)iph->check;
+
+ check += (__force u32)htons(0x0100);
+ iph->check = (__force __sum16)(check + (check >= 0xFFFF));
+ return --iph->ttl;
+}
+
+static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct bpf_fib_lookup fib_params;
+ struct ethhdr *eth = data;
+ struct ipv6hdr *ip6h;
+ struct iphdr *iph;
+ int out_index;
+ u16 h_proto;
+ u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ __builtin_memset(&fib_params, 0, sizeof(fib_params));
+
+ h_proto = eth->h_proto;
+ if (h_proto == htons(ETH_P_IP)) {
+ iph = data + nh_off;
+
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+
+ if (iph->ttl <= 1)
+ return XDP_PASS;
+
+ fib_params.family = AF_INET;
+ fib_params.tos = iph->tos;
+ fib_params.l4_protocol = iph->protocol;
+ fib_params.sport = 0;
+ fib_params.dport = 0;
+ fib_params.tot_len = ntohs(iph->tot_len);
+ fib_params.ipv4_src = iph->saddr;
+ fib_params.ipv4_dst = iph->daddr;
+ } else if (h_proto == htons(ETH_P_IPV6)) {
+ struct in6_addr *src = (struct in6_addr *) fib_params.ipv6_src;
+ struct in6_addr *dst = (struct in6_addr *) fib_params.ipv6_dst;
+
+ ip6h = data + nh_off;
+ if (ip6h + 1 > data_end)
+ return XDP_DROP;
+
+ if (ip6h->hop_limit <= 1)
+ return XDP_PASS;
+
+ fib_params.family = AF_INET6;
+ fib_params.flowlabel = *(__be32 *)ip6h & IPV6_FLOWINFO_MASK;
+ fib_params.l4_protocol = ip6h->nexthdr;
+ fib_params.sport = 0;
+ fib_params.dport = 0;
+ fib_params.tot_len = ntohs(ip6h->payload_len);
+ *src = ip6h->saddr;
+ *dst = ip6h->daddr;
+ } else {
+ return XDP_PASS;
+ }
+
+ fib_params.ifindex = ctx->ingress_ifindex;
+
+ out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+
+ /* verify egress index has xdp support
+ * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
+ * cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+ * NOTE: without verification that egress index supports XDP
+ * forwarding packets are dropped.
+ */
+ if (out_index > 0) {
+ if (h_proto == htons(ETH_P_IP))
+ ip_decrease_ttl(iph);
+ else if (h_proto == htons(ETH_P_IPV6))
+ ip6h->hop_limit--;
+
+ memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
+ memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
+ return bpf_redirect_map(&tx_port, out_index, 0);
+ }
+
+ return XDP_PASS;
+}
+
+SEC("xdp_fwd")
+int xdp_fwd_prog(struct xdp_md *ctx)
+{
+ return xdp_fwd_flags(ctx, 0);
+}
+
+SEC("xdp_fwd_direct")
+int xdp_fwd_direct_prog(struct xdp_md *ctx)
+{
+ return xdp_fwd_flags(ctx, BPF_FIB_LOOKUP_DIRECT);
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <linux/limits.h>
+#include <net/if.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <libgen.h>
+
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+
+
+static int do_attach(int idx, int fd, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, fd, 0);
+ if (err < 0)
+ printf("ERROR: failed to attach program to %s\n", name);
+
+ return err;
+}
+
+static int do_detach(int idx, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, -1, 0);
+ if (err < 0)
+ printf("ERROR: failed to detach program from %s\n", name);
+
+ return err;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] interface-list\n"
+ "\nOPTS:\n"
+ " -d detach program\n"
+ " -D direct table lookups (skip fib rules)\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ char filename[PATH_MAX];
+ int opt, i, idx, err;
+ int prog_id = 0;
+ int attach = 1;
+ int ret = 0;
+
+ while ((opt = getopt(argc, argv, ":dD")) != -1) {
+ switch (opt) {
+ case 'd':
+ attach = 0;
+ break;
+ case 'D':
+ prog_id = 1;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (optind == argc) {
+ usage(basename(argv[0]));
+ return 1;
+ }
+
+ if (attach) {
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (access(filename, O_RDONLY) < 0) {
+ printf("error accessing file %s: %s\n",
+ filename, strerror(errno));
+ return 1;
+ }
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ if (!prog_fd[prog_id]) {
+ printf("load_bpf_file: %s\n", strerror(errno));
+ return 1;
+ }
+ }
+ if (attach) {
+ for (i = 1; i < 64; ++i)
+ bpf_map_update_elem(map_fd[0], &i, &i, 0);
+ }
+
+ for (i = optind; i < argc; ++i) {
+ idx = if_nametoindex(argv[i]);
+ if (!idx)
+ idx = strtoul(argv[i], NULL, 0);
+
+ if (!idx) {
+ fprintf(stderr, "Invalid arg\n");
+ return 1;
+ }
+ if (!attach) {
+ err = do_detach(idx, argv[i]);
+ if (err)
+ ret = err;
+ } else {
+ err = do_attach(idx, prog_fd[prog_id], argv[i]);
+ if (err)
+ ret = err;
+ }
+ }
+
+ return ret;
+}
#include <net/if.h>
#include <time.h>
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
printf(" flag (internal value:%d)",
*long_options[i].flag);
else
- printf("(internal short-option: -%c)",
+ printf("short-option: -%c",
long_options[i].val);
printf("\n");
}
snprintf(bpf_obj_file, sizeof(bpf_obj_file), "%s_kern.o", argv[0]);
/* Parse commands line args */
- while ((opt = getopt_long(argc, argv, "h",
+ while ((opt = getopt_long(argc, argv, "hDSs:",
long_options, &longindex)) != -1) {
switch (opt) {
case 'D':
* use bpf/libbpf.h), but cannot as (currently) needed for XDP
* attaching to a device via bpf_set_link_xdp_fd()
*/
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include "bpf_load.h"
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
static int ifindex_in;
static int ifindex_out;
#include "bpf_load.h"
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
static int ifindex_in;
static int ifindex_out;
#include <sys/socket.h>
#include <unistd.h>
#include "bpf_load.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include <arpa/inet.h>
#include <fcntl.h>
#include <poll.h>
#include <arpa/inet.h>
#include <linux/if_link.h>
-#include "libbpf.h"
-#include "bpf_load.h"
+#include "bpf/bpf.h"
+#include "bpf/libbpf.h"
#include "bpf_util.h"
static int ifindex = -1;
static __u32 xdp_flags;
+static struct bpf_map *stats_global_map;
+static struct bpf_map *rx_queue_index_map;
+
/* Exit return codes */
#define EXIT_OK 0
#define EXIT_FAIL 1
static struct record *alloc_record_per_rxq(void)
{
- unsigned int nr_rxqs = map_data[2].def.max_entries;
+ unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
struct record *array;
size_t size;
static struct stats_record *alloc_stats_record(void)
{
- unsigned int nr_rxqs = map_data[2].def.max_entries;
+ unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
struct stats_record *rec;
int i;
static void free_stats_record(struct stats_record *r)
{
- unsigned int nr_rxqs = map_data[2].def.max_entries;
+ unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
int i;
for (i = 0; i < nr_rxqs; i++)
{
int fd, i, max_rxqs;
- fd = map_data[1].fd; /* map: stats_global_map */
+ fd = bpf_map__fd(stats_global_map);
map_collect_percpu(fd, 0, &rec->stats);
- fd = map_data[2].fd; /* map: rx_queue_index_map */
- max_rxqs = map_data[2].def.max_entries;
+ fd = bpf_map__fd(rx_queue_index_map);
+ max_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
for (i = 0; i < max_rxqs; i++)
map_collect_percpu(fd, i, &rec->rxq[i]);
}
struct stats_record *stats_prev,
int action)
{
+ unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
unsigned int nr_cpus = bpf_num_possible_cpus();
- unsigned int nr_rxqs = map_data[2].def.max_entries;
double pps = 0, err = 0;
struct record *rec, *prev;
double t;
int main(int argc, char **argv)
{
struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_XDP,
+ };
+ int prog_fd, map_fd, opt, err;
bool use_separators = true;
struct config cfg = { 0 };
+ struct bpf_object *obj;
+ struct bpf_map *map;
char filename[256];
int longindex = 0;
int interval = 2;
__u32 key = 0;
- int opt, err;
char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 };
int action = XDP_PASS; /* Default action */
char *action_str = NULL;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
- if (load_bpf_file(filename)) {
- fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ return EXIT_FAIL;
+
+ map = bpf_map__next(NULL, obj);
+ stats_global_map = bpf_map__next(map, obj);
+ rx_queue_index_map = bpf_map__next(stats_global_map, obj);
+ if (!map || !stats_global_map || !rx_queue_index_map) {
+ printf("finding a map in obj file failed\n");
return EXIT_FAIL;
}
+ map_fd = bpf_map__fd(map);
- if (!prog_fd[0]) {
+ if (!prog_fd) {
fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
return EXIT_FAIL;
}
setlocale(LC_NUMERIC, "en_US");
/* User-side setup ifindex in config_map */
- err = bpf_map_update_elem(map_fd[0], &key, &cfg, 0);
+ err = bpf_map_update_elem(map_fd, &key, &cfg, 0);
if (err) {
fprintf(stderr, "Store config failed (err:%d)\n", err);
exit(EXIT_FAIL_BPF);
/* Remove XDP program when program is interrupted */
signal(SIGINT, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+ if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
fprintf(stderr, "link set xdp fd failed\n");
return EXIT_FAIL_XDP;
}
#include <unistd.h>
#include <time.h>
#include "bpf_load.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
#include "bpf_util.h"
#include "xdp_tx_iptunnel_common.h"
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef XDPSOCK_H_
+#define XDPSOCK_H_
+
+/* Power-of-2 number of sockets */
+#define MAX_SOCKS 4
+
+/* Round-robin receive */
+#define RR_LB 0
+
+#endif /* XDPSOCK_H_ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#include "xdpsock.h"
+
+struct bpf_map_def SEC("maps") qidconf_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") xsks_map = {
+ .type = BPF_MAP_TYPE_XSKMAP,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") rr_map = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(unsigned int),
+ .max_entries = 1,
+};
+
+SEC("xdp_sock")
+int xdp_sock_prog(struct xdp_md *ctx)
+{
+ int *qidconf, key = 0, idx;
+ unsigned int *rr;
+
+ qidconf = bpf_map_lookup_elem(&qidconf_map, &key);
+ if (!qidconf)
+ return XDP_ABORTED;
+
+ if (*qidconf != ctx->rx_queue_index)
+ return XDP_PASS;
+
+#if RR_LB /* NB! RR_LB is configured in xdpsock.h */
+ rr = bpf_map_lookup_elem(&rr_map, &key);
+ if (!rr)
+ return XDP_ABORTED;
+
+ *rr = (*rr + 1) & (MAX_SOCKS - 1);
+ idx = *rr;
+#else
+ idx = 0;
+#endif
+
+ return bpf_redirect_map(&xsks_map, idx, 0);
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2017 - 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <getopt.h>
+#include <libgen.h>
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <linux/if_xdp.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/ethernet.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <time.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <locale.h>
+#include <sys/types.h>
+#include <poll.h>
+
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+
+#include "xdpsock.h"
+
+#ifndef SOL_XDP
+#define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+#define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+#define PF_XDP AF_XDP
+#endif
+
+#define NUM_FRAMES 131072
+#define FRAME_HEADROOM 0
+#define FRAME_SIZE 2048
+#define NUM_DESCS 1024
+#define BATCH_SIZE 16
+
+#define FQ_NUM_DESCS 1024
+#define CQ_NUM_DESCS 1024
+
+#define DEBUG_HEXDUMP 0
+
+typedef __u32 u32;
+
+static unsigned long prev_time;
+
+enum benchmark_type {
+ BENCH_RXDROP = 0,
+ BENCH_TXONLY = 1,
+ BENCH_L2FWD = 2,
+};
+
+static enum benchmark_type opt_bench = BENCH_RXDROP;
+static u32 opt_xdp_flags;
+static const char *opt_if = "";
+static int opt_ifindex;
+static int opt_queue;
+static int opt_poll;
+static int opt_shared_packet_buffer;
+static int opt_interval = 1;
+
+struct xdp_umem_uqueue {
+ u32 cached_prod;
+ u32 cached_cons;
+ u32 mask;
+ u32 size;
+ struct xdp_umem_ring *ring;
+};
+
+struct xdp_umem {
+ char (*frames)[FRAME_SIZE];
+ struct xdp_umem_uqueue fq;
+ struct xdp_umem_uqueue cq;
+ int fd;
+};
+
+struct xdp_uqueue {
+ u32 cached_prod;
+ u32 cached_cons;
+ u32 mask;
+ u32 size;
+ struct xdp_rxtx_ring *ring;
+};
+
+struct xdpsock {
+ struct xdp_uqueue rx;
+ struct xdp_uqueue tx;
+ int sfd;
+ struct xdp_umem *umem;
+ u32 outstanding_tx;
+ unsigned long rx_npkts;
+ unsigned long tx_npkts;
+ unsigned long prev_rx_npkts;
+ unsigned long prev_tx_npkts;
+};
+
+#define MAX_SOCKS 4
+static int num_socks;
+struct xdpsock *xsks[MAX_SOCKS];
+
+static unsigned long get_nsecs(void)
+{
+ struct timespec ts;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+ return ts.tv_sec * 1000000000UL + ts.tv_nsec;
+}
+
+static void dump_stats(void);
+
+#define lassert(expr) \
+ do { \
+ if (!(expr)) { \
+ fprintf(stderr, "%s:%s:%i: Assertion failed: " \
+ #expr ": errno: %d/\"%s\"\n", \
+ __FILE__, __func__, __LINE__, \
+ errno, strerror(errno)); \
+ dump_stats(); \
+ exit(EXIT_FAILURE); \
+ } \
+ } while (0)
+
+#define barrier() __asm__ __volatile__("": : :"memory")
+#define u_smp_rmb() barrier()
+#define u_smp_wmb() barrier()
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
+static const char pkt_data[] =
+ "\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00"
+ "\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14"
+ "\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b"
+ "\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa";
+
+static inline u32 umem_nb_free(struct xdp_umem_uqueue *q, u32 nb)
+{
+ u32 free_entries = q->size - (q->cached_prod - q->cached_cons);
+
+ if (free_entries >= nb)
+ return free_entries;
+
+ /* Refresh the local tail pointer */
+ q->cached_cons = q->ring->ptrs.consumer;
+
+ return q->size - (q->cached_prod - q->cached_cons);
+}
+
+static inline u32 xq_nb_free(struct xdp_uqueue *q, u32 ndescs)
+{
+ u32 free_entries = q->cached_cons - q->cached_prod;
+
+ if (free_entries >= ndescs)
+ return free_entries;
+
+ /* Refresh the local tail pointer */
+ q->cached_cons = q->ring->ptrs.consumer + q->size;
+ return q->cached_cons - q->cached_prod;
+}
+
+static inline u32 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb)
+{
+ u32 entries = q->cached_prod - q->cached_cons;
+
+ if (entries == 0) {
+ q->cached_prod = q->ring->ptrs.producer;
+ entries = q->cached_prod - q->cached_cons;
+ }
+
+ return (entries > nb) ? nb : entries;
+}
+
+static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs)
+{
+ u32 entries = q->cached_prod - q->cached_cons;
+
+ if (entries == 0) {
+ q->cached_prod = q->ring->ptrs.producer;
+ entries = q->cached_prod - q->cached_cons;
+ }
+
+ return (entries > ndescs) ? ndescs : entries;
+}
+
+static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq,
+ struct xdp_desc *d,
+ size_t nb)
+{
+ u32 i;
+
+ if (umem_nb_free(fq, nb) < nb)
+ return -ENOSPC;
+
+ for (i = 0; i < nb; i++) {
+ u32 idx = fq->cached_prod++ & fq->mask;
+
+ fq->ring->desc[idx] = d[i].idx;
+ }
+
+ u_smp_wmb();
+
+ fq->ring->ptrs.producer = fq->cached_prod;
+
+ return 0;
+}
+
+static inline int umem_fill_to_kernel(struct xdp_umem_uqueue *fq, u32 *d,
+ size_t nb)
+{
+ u32 i;
+
+ if (umem_nb_free(fq, nb) < nb)
+ return -ENOSPC;
+
+ for (i = 0; i < nb; i++) {
+ u32 idx = fq->cached_prod++ & fq->mask;
+
+ fq->ring->desc[idx] = d[i];
+ }
+
+ u_smp_wmb();
+
+ fq->ring->ptrs.producer = fq->cached_prod;
+
+ return 0;
+}
+
+static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq,
+ u32 *d, size_t nb)
+{
+ u32 idx, i, entries = umem_nb_avail(cq, nb);
+
+ u_smp_rmb();
+
+ for (i = 0; i < entries; i++) {
+ idx = cq->cached_cons++ & cq->mask;
+ d[i] = cq->ring->desc[idx];
+ }
+
+ if (entries > 0) {
+ u_smp_wmb();
+
+ cq->ring->ptrs.consumer = cq->cached_cons;
+ }
+
+ return entries;
+}
+
+static inline void *xq_get_data(struct xdpsock *xsk, __u32 idx, __u32 off)
+{
+ lassert(idx < NUM_FRAMES);
+ return &xsk->umem->frames[idx][off];
+}
+
+static inline int xq_enq(struct xdp_uqueue *uq,
+ const struct xdp_desc *descs,
+ unsigned int ndescs)
+{
+ struct xdp_rxtx_ring *r = uq->ring;
+ unsigned int i;
+
+ if (xq_nb_free(uq, ndescs) < ndescs)
+ return -ENOSPC;
+
+ for (i = 0; i < ndescs; i++) {
+ u32 idx = uq->cached_prod++ & uq->mask;
+
+ r->desc[idx].idx = descs[i].idx;
+ r->desc[idx].len = descs[i].len;
+ r->desc[idx].offset = descs[i].offset;
+ }
+
+ u_smp_wmb();
+
+ r->ptrs.producer = uq->cached_prod;
+ return 0;
+}
+
+static inline int xq_enq_tx_only(struct xdp_uqueue *uq,
+ __u32 idx, unsigned int ndescs)
+{
+ struct xdp_rxtx_ring *q = uq->ring;
+ unsigned int i;
+
+ if (xq_nb_free(uq, ndescs) < ndescs)
+ return -ENOSPC;
+
+ for (i = 0; i < ndescs; i++) {
+ u32 idx = uq->cached_prod++ & uq->mask;
+
+ q->desc[idx].idx = idx + i;
+ q->desc[idx].len = sizeof(pkt_data) - 1;
+ q->desc[idx].offset = 0;
+ }
+
+ u_smp_wmb();
+
+ q->ptrs.producer = uq->cached_prod;
+ return 0;
+}
+
+static inline int xq_deq(struct xdp_uqueue *uq,
+ struct xdp_desc *descs,
+ int ndescs)
+{
+ struct xdp_rxtx_ring *r = uq->ring;
+ unsigned int idx;
+ int i, entries;
+
+ entries = xq_nb_avail(uq, ndescs);
+
+ u_smp_rmb();
+
+ for (i = 0; i < entries; i++) {
+ idx = uq->cached_cons++ & uq->mask;
+ descs[i] = r->desc[idx];
+ }
+
+ if (entries > 0) {
+ u_smp_wmb();
+
+ r->ptrs.consumer = uq->cached_cons;
+ }
+
+ return entries;
+}
+
+static void swap_mac_addresses(void *data)
+{
+ struct ether_header *eth = (struct ether_header *)data;
+ struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost;
+ struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost;
+ struct ether_addr tmp;
+
+ tmp = *src_addr;
+ *src_addr = *dst_addr;
+ *dst_addr = tmp;
+}
+
+#if DEBUG_HEXDUMP
+static void hex_dump(void *pkt, size_t length, const char *prefix)
+{
+ int i = 0;
+ const unsigned char *address = (unsigned char *)pkt;
+ const unsigned char *line = address;
+ size_t line_size = 32;
+ unsigned char c;
+
+ printf("length = %zu\n", length);
+ printf("%s | ", prefix);
+ while (length-- > 0) {
+ printf("%02X ", *address++);
+ if (!(++i % line_size) || (length == 0 && i % line_size)) {
+ if (length == 0) {
+ while (i++ % line_size)
+ printf("__ ");
+ }
+ printf(" | "); /* right close */
+ while (line < address) {
+ c = *line++;
+ printf("%c", (c < 33 || c == 255) ? 0x2E : c);
+ }
+ printf("\n");
+ if (length > 0)
+ printf("%s | ", prefix);
+ }
+ }
+ printf("\n");
+}
+#endif
+
+static size_t gen_eth_frame(char *frame)
+{
+ memcpy(frame, pkt_data, sizeof(pkt_data) - 1);
+ return sizeof(pkt_data) - 1;
+}
+
+static struct xdp_umem *xdp_umem_configure(int sfd)
+{
+ int fq_size = FQ_NUM_DESCS, cq_size = CQ_NUM_DESCS;
+ struct xdp_umem_reg mr;
+ struct xdp_umem *umem;
+ void *bufs;
+
+ umem = calloc(1, sizeof(*umem));
+ lassert(umem);
+
+ lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
+ NUM_FRAMES * FRAME_SIZE) == 0);
+
+ mr.addr = (__u64)bufs;
+ mr.len = NUM_FRAMES * FRAME_SIZE;
+ mr.frame_size = FRAME_SIZE;
+ mr.frame_headroom = FRAME_HEADROOM;
+
+ lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)) == 0);
+ lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_FILL_RING, &fq_size,
+ sizeof(int)) == 0);
+ lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &cq_size,
+ sizeof(int)) == 0);
+
+ umem->fq.ring = mmap(0, sizeof(struct xdp_umem_ring) +
+ FQ_NUM_DESCS * sizeof(u32),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, sfd,
+ XDP_UMEM_PGOFF_FILL_RING);
+ lassert(umem->fq.ring != MAP_FAILED);
+
+ umem->fq.mask = FQ_NUM_DESCS - 1;
+ umem->fq.size = FQ_NUM_DESCS;
+
+ umem->cq.ring = mmap(0, sizeof(struct xdp_umem_ring) +
+ CQ_NUM_DESCS * sizeof(u32),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, sfd,
+ XDP_UMEM_PGOFF_COMPLETION_RING);
+ lassert(umem->cq.ring != MAP_FAILED);
+
+ umem->cq.mask = CQ_NUM_DESCS - 1;
+ umem->cq.size = CQ_NUM_DESCS;
+
+ umem->frames = (char (*)[FRAME_SIZE])bufs;
+ umem->fd = sfd;
+
+ if (opt_bench == BENCH_TXONLY) {
+ int i;
+
+ for (i = 0; i < NUM_FRAMES; i++)
+ (void)gen_eth_frame(&umem->frames[i][0]);
+ }
+
+ return umem;
+}
+
+static struct xdpsock *xsk_configure(struct xdp_umem *umem)
+{
+ struct sockaddr_xdp sxdp = {};
+ int sfd, ndescs = NUM_DESCS;
+ struct xdpsock *xsk;
+ bool shared = true;
+ u32 i;
+
+ sfd = socket(PF_XDP, SOCK_RAW, 0);
+ lassert(sfd >= 0);
+
+ xsk = calloc(1, sizeof(*xsk));
+ lassert(xsk);
+
+ xsk->sfd = sfd;
+ xsk->outstanding_tx = 0;
+
+ if (!umem) {
+ shared = false;
+ xsk->umem = xdp_umem_configure(sfd);
+ } else {
+ xsk->umem = umem;
+ }
+
+ lassert(setsockopt(sfd, SOL_XDP, XDP_RX_RING,
+ &ndescs, sizeof(int)) == 0);
+ lassert(setsockopt(sfd, SOL_XDP, XDP_TX_RING,
+ &ndescs, sizeof(int)) == 0);
+
+ /* Rx */
+ xsk->rx.ring = mmap(NULL,
+ sizeof(struct xdp_ring) +
+ NUM_DESCS * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, sfd,
+ XDP_PGOFF_RX_RING);
+ lassert(xsk->rx.ring != MAP_FAILED);
+
+ if (!shared) {
+ for (i = 0; i < NUM_DESCS / 2; i++)
+ lassert(umem_fill_to_kernel(&xsk->umem->fq, &i, 1)
+ == 0);
+ }
+
+ /* Tx */
+ xsk->tx.ring = mmap(NULL,
+ sizeof(struct xdp_ring) +
+ NUM_DESCS * sizeof(struct xdp_desc),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, sfd,
+ XDP_PGOFF_TX_RING);
+ lassert(xsk->tx.ring != MAP_FAILED);
+
+ xsk->rx.mask = NUM_DESCS - 1;
+ xsk->rx.size = NUM_DESCS;
+
+ xsk->tx.mask = NUM_DESCS - 1;
+ xsk->tx.size = NUM_DESCS;
+
+ sxdp.sxdp_family = PF_XDP;
+ sxdp.sxdp_ifindex = opt_ifindex;
+ sxdp.sxdp_queue_id = opt_queue;
+ if (shared) {
+ sxdp.sxdp_flags = XDP_SHARED_UMEM;
+ sxdp.sxdp_shared_umem_fd = umem->fd;
+ }
+
+ lassert(bind(sfd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0);
+
+ return xsk;
+}
+
+static void print_benchmark(bool running)
+{
+ const char *bench_str = "INVALID";
+
+ if (opt_bench == BENCH_RXDROP)
+ bench_str = "rxdrop";
+ else if (opt_bench == BENCH_TXONLY)
+ bench_str = "txonly";
+ else if (opt_bench == BENCH_L2FWD)
+ bench_str = "l2fwd";
+
+ printf("%s:%d %s ", opt_if, opt_queue, bench_str);
+ if (opt_xdp_flags & XDP_FLAGS_SKB_MODE)
+ printf("xdp-skb ");
+ else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE)
+ printf("xdp-drv ");
+ else
+ printf(" ");
+
+ if (opt_poll)
+ printf("poll() ");
+
+ if (running) {
+ printf("running...");
+ fflush(stdout);
+ }
+}
+
+static void dump_stats(void)
+{
+ unsigned long now = get_nsecs();
+ long dt = now - prev_time;
+ int i;
+
+ prev_time = now;
+
+ for (i = 0; i < num_socks; i++) {
+ char *fmt = "%-15s %'-11.0f %'-11lu\n";
+ double rx_pps, tx_pps;
+
+ rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
+ 1000000000. / dt;
+ tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) *
+ 1000000000. / dt;
+
+ printf("\n sock%d@", i);
+ print_benchmark(false);
+ printf("\n");
+
+ printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts",
+ dt / 1000000000.);
+ printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts);
+ printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts);
+
+ xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
+ xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;
+ }
+}
+
+static void *poller(void *arg)
+{
+ (void)arg;
+ for (;;) {
+ sleep(opt_interval);
+ dump_stats();
+ }
+
+ return NULL;
+}
+
+static void int_exit(int sig)
+{
+ (void)sig;
+ dump_stats();
+ bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+ exit(EXIT_SUCCESS);
+}
+
+static struct option long_options[] = {
+ {"rxdrop", no_argument, 0, 'r'},
+ {"txonly", no_argument, 0, 't'},
+ {"l2fwd", no_argument, 0, 'l'},
+ {"interface", required_argument, 0, 'i'},
+ {"queue", required_argument, 0, 'q'},
+ {"poll", no_argument, 0, 'p'},
+ {"shared-buffer", no_argument, 0, 's'},
+ {"xdp-skb", no_argument, 0, 'S'},
+ {"xdp-native", no_argument, 0, 'N'},
+ {"interval", required_argument, 0, 'n'},
+ {0, 0, 0, 0}
+};
+
+static void usage(const char *prog)
+{
+ const char *str =
+ " Usage: %s [OPTIONS]\n"
+ " Options:\n"
+ " -r, --rxdrop Discard all incoming packets (default)\n"
+ " -t, --txonly Only send packets\n"
+ " -l, --l2fwd MAC swap L2 forwarding\n"
+ " -i, --interface=n Run on interface n\n"
+ " -q, --queue=n Use queue n (default 0)\n"
+ " -p, --poll Use poll syscall\n"
+ " -s, --shared-buffer Use shared packet buffer\n"
+ " -S, --xdp-skb=n Use XDP skb-mod\n"
+ " -N, --xdp-native=n Enfore XDP native mode\n"
+ " -n, --interval=n Specify statistics update interval (default 1 sec).\n"
+ "\n";
+ fprintf(stderr, str, prog);
+ exit(EXIT_FAILURE);
+}
+
+static void parse_command_line(int argc, char **argv)
+{
+ int option_index, c;
+
+ opterr = 0;
+
+ for (;;) {
+ c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options,
+ &option_index);
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'r':
+ opt_bench = BENCH_RXDROP;
+ break;
+ case 't':
+ opt_bench = BENCH_TXONLY;
+ break;
+ case 'l':
+ opt_bench = BENCH_L2FWD;
+ break;
+ case 'i':
+ opt_if = optarg;
+ break;
+ case 'q':
+ opt_queue = atoi(optarg);
+ break;
+ case 's':
+ opt_shared_packet_buffer = 1;
+ break;
+ case 'p':
+ opt_poll = 1;
+ break;
+ case 'S':
+ opt_xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'N':
+ opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
+ break;
+ case 'n':
+ opt_interval = atoi(optarg);
+ break;
+ default:
+ usage(basename(argv[0]));
+ }
+ }
+
+ opt_ifindex = if_nametoindex(opt_if);
+ if (!opt_ifindex) {
+ fprintf(stderr, "ERROR: interface \"%s\" does not exist\n",
+ opt_if);
+ usage(basename(argv[0]));
+ }
+}
+
+static void kick_tx(int fd)
+{
+ int ret;
+
+ ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
+ if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN)
+ return;
+ lassert(0);
+}
+
+static inline void complete_tx_l2fwd(struct xdpsock *xsk)
+{
+ u32 descs[BATCH_SIZE];
+ unsigned int rcvd;
+ size_t ndescs;
+
+ if (!xsk->outstanding_tx)
+ return;
+
+ kick_tx(xsk->sfd);
+ ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE :
+ xsk->outstanding_tx;
+
+ /* re-add completed Tx buffers */
+ rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, ndescs);
+ if (rcvd > 0) {
+ umem_fill_to_kernel(&xsk->umem->fq, descs, rcvd);
+ xsk->outstanding_tx -= rcvd;
+ xsk->tx_npkts += rcvd;
+ }
+}
+
+static inline void complete_tx_only(struct xdpsock *xsk)
+{
+ u32 descs[BATCH_SIZE];
+ unsigned int rcvd;
+
+ if (!xsk->outstanding_tx)
+ return;
+
+ kick_tx(xsk->sfd);
+
+ rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, BATCH_SIZE);
+ if (rcvd > 0) {
+ xsk->outstanding_tx -= rcvd;
+ xsk->tx_npkts += rcvd;
+ }
+}
+
+static void rx_drop(struct xdpsock *xsk)
+{
+ struct xdp_desc descs[BATCH_SIZE];
+ unsigned int rcvd, i;
+
+ rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
+ if (!rcvd)
+ return;
+
+ for (i = 0; i < rcvd; i++) {
+ u32 idx = descs[i].idx;
+
+ lassert(idx < NUM_FRAMES);
+#if DEBUG_HEXDUMP
+ char *pkt;
+ char buf[32];
+
+ pkt = xq_get_data(xsk, idx, descs[i].offset);
+ sprintf(buf, "idx=%d", idx);
+ hex_dump(pkt, descs[i].len, buf);
+#endif
+ }
+
+ xsk->rx_npkts += rcvd;
+
+ umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd);
+}
+
+static void rx_drop_all(void)
+{
+ struct pollfd fds[MAX_SOCKS + 1];
+ int i, ret, timeout, nfds = 1;
+
+ memset(fds, 0, sizeof(fds));
+
+ for (i = 0; i < num_socks; i++) {
+ fds[i].fd = xsks[i]->sfd;
+ fds[i].events = POLLIN;
+ timeout = 1000; /* 1sn */
+ }
+
+ for (;;) {
+ if (opt_poll) {
+ ret = poll(fds, nfds, timeout);
+ if (ret <= 0)
+ continue;
+ }
+
+ for (i = 0; i < num_socks; i++)
+ rx_drop(xsks[i]);
+ }
+}
+
+static void tx_only(struct xdpsock *xsk)
+{
+ int timeout, ret, nfds = 1;
+ struct pollfd fds[nfds + 1];
+ unsigned int idx = 0;
+
+ memset(fds, 0, sizeof(fds));
+ fds[0].fd = xsk->sfd;
+ fds[0].events = POLLOUT;
+ timeout = 1000; /* 1sn */
+
+ for (;;) {
+ if (opt_poll) {
+ ret = poll(fds, nfds, timeout);
+ if (ret <= 0)
+ continue;
+
+ if (fds[0].fd != xsk->sfd ||
+ !(fds[0].revents & POLLOUT))
+ continue;
+ }
+
+ if (xq_nb_free(&xsk->tx, BATCH_SIZE) >= BATCH_SIZE) {
+ lassert(xq_enq_tx_only(&xsk->tx, idx, BATCH_SIZE) == 0);
+
+ xsk->outstanding_tx += BATCH_SIZE;
+ idx += BATCH_SIZE;
+ idx %= NUM_FRAMES;
+ }
+
+ complete_tx_only(xsk);
+ }
+}
+
+static void l2fwd(struct xdpsock *xsk)
+{
+ for (;;) {
+ struct xdp_desc descs[BATCH_SIZE];
+ unsigned int rcvd, i;
+ int ret;
+
+ for (;;) {
+ complete_tx_l2fwd(xsk);
+
+ rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
+ if (rcvd > 0)
+ break;
+ }
+
+ for (i = 0; i < rcvd; i++) {
+ char *pkt = xq_get_data(xsk, descs[i].idx,
+ descs[i].offset);
+
+ swap_mac_addresses(pkt);
+#if DEBUG_HEXDUMP
+ char buf[32];
+ u32 idx = descs[i].idx;
+
+ sprintf(buf, "idx=%d", idx);
+ hex_dump(pkt, descs[i].len, buf);
+#endif
+ }
+
+ xsk->rx_npkts += rcvd;
+
+ ret = xq_enq(&xsk->tx, descs, rcvd);
+ lassert(ret == 0);
+ xsk->outstanding_tx += rcvd;
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ char xdp_filename[256];
+ int i, ret, key = 0;
+ pthread_t pt;
+
+ parse_command_line(argc, argv);
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n",
+ strerror(errno));
+ exit(EXIT_FAILURE);
+ }
+
+ snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(xdp_filename)) {
+ fprintf(stderr, "ERROR: load_bpf_file %s\n", bpf_log_buf);
+ exit(EXIT_FAILURE);
+ }
+
+ if (!prog_fd[0]) {
+ fprintf(stderr, "ERROR: load_bpf_file: \"%s\"\n",
+ strerror(errno));
+ exit(EXIT_FAILURE);
+ }
+
+ if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd[0], opt_xdp_flags) < 0) {
+ fprintf(stderr, "ERROR: link set xdp fd failed\n");
+ exit(EXIT_FAILURE);
+ }
+
+ ret = bpf_map_update_elem(map_fd[0], &key, &opt_queue, 0);
+ if (ret) {
+ fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Create sockets... */
+ xsks[num_socks++] = xsk_configure(NULL);
+
+#if RR_LB
+ for (i = 0; i < MAX_SOCKS - 1; i++)
+ xsks[num_socks++] = xsk_configure(xsks[0]->umem);
+#endif
+
+ /* ...and insert them into the map. */
+ for (i = 0; i < num_socks; i++) {
+ key = i;
+ ret = bpf_map_update_elem(map_fd[1], &key, &xsks[i]->sfd, 0);
+ if (ret) {
+ fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+ signal(SIGABRT, int_exit);
+
+ setlocale(LC_ALL, "");
+
+ ret = pthread_create(&pt, NULL, poller, NULL);
+ lassert(ret == 0);
+
+ prev_time = get_nsecs();
+
+ if (opt_bench == BENCH_RXDROP)
+ rx_drop_all();
+ else if (opt_bench == BENCH_TXONLY)
+ tx_only(xsks[0]);
+ else
+ l2fwd(xsks[0]);
+
+ return 0;
+}
+++ /dev/null
-# List of programs to build
-hostprogs-y := sockmap
-
-# Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
-
-HOSTCFLAGS += -I$(objtree)/usr/include
-HOSTCFLAGS += -I$(srctree)/tools/lib/
-HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
-HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
-HOSTCFLAGS += -I$(srctree)/tools/perf
-
-sockmap-objs := ../bpf/bpf_load.o $(LIBBPF) sockmap_user.o
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-always += sockmap_kern.o
-
-HOSTLOADLIBES_sockmap += -lelf -lpthread
-
-# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
-# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
-LLC ?= llc
-CLANG ?= clang
-
-# Trick to allow make to be run from this directory
-all:
- $(MAKE) -C ../../ $(CURDIR)/
-
-clean:
- $(MAKE) -C ../../ M=$(CURDIR) clean
- @rm -f *~
-
-$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c
- $(call if_changed_dep,cc_s_c)
-
-$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE
- $(call filechk,offsets,__SYSCALL_NRS_H__)
-
-clean-files += syscall_nrs.h
-
-FORCE:
-
-
-# Verify LLVM compiler tools are available and bpf target is supported by llc
-.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
-
-verify_cmds: $(CLANG) $(LLC)
- @for TOOL in $^ ; do \
- if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
- echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
- exit 1; \
- else true; fi; \
- done
-
-verify_target_bpf: verify_cmds
- @if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
- echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
- echo " NOTICE: LLVM version >= 3.7.1 required" ;\
- exit 2; \
- else true; fi
-
-$(src)/*.c: verify_target_bpf
-
-# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
-# But, there is no easy way to fix it, so just exclude it since it is
-# useless for BPF samples.
-$(obj)/%.o: $(src)/%.c
- $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
- -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
- -Wno-compare-distinct-pointer-types \
- -Wno-gnu-variable-sized-type-not-at-end \
- -Wno-address-of-packed-member -Wno-tautological-compare \
- -Wno-unknown-warning-option \
- -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+++ /dev/null
-#Test a bunch of positive cases to verify basic functionality
-for prog in "--txmsg_redir --txmsg_skb" "--txmsg_redir --txmsg_ingress" "--txmsg" "--txmsg_redir" "--txmsg_redir --txmsg_ingress" "--txmsg_drop"; do
-for t in "sendmsg" "sendpage"; do
-for r in 1 10 100; do
- for i in 1 10 100; do
- for l in 1 10 100; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
- done
- done
-done
-done
-done
-
-#Test max iov
-t="sendmsg"
-r=1
-i=1024
-l=1
-prog="--txmsg"
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
-echo $TEST
-$TEST
-sleep 2
-prog="--txmsg_redir"
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
-echo $TEST
-$TEST
-
-# Test max iov with 1k send
-
-t="sendmsg"
-r=1
-i=1024
-l=1024
-prog="--txmsg"
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
-echo $TEST
-$TEST
-sleep 2
-prog="--txmsg_redir"
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
-echo $TEST
-$TEST
-sleep 2
-
-# Test apply with 1B
-r=1
-i=1024
-l=1024
-prog="--txmsg_apply 1"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply with larger value than send
-r=1
-i=8
-l=1024
-prog="--txmsg_apply 2048"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply with apply that never reaches limit
-r=1024
-i=1
-l=1
-prog="--txmsg_apply 2048"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply and redirect with 1B
-r=1
-i=1024
-l=1024
-prog="--txmsg_redir --txmsg_apply 1"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-prog="--txmsg_redir --txmsg_apply 1 --txmsg_ingress"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-prog="--txmsg_redir --txmsg_apply 1 --txmsg_skb"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-
-# Test apply and redirect with larger value than send
-r=1
-i=8
-l=1024
-prog="--txmsg_redir --txmsg_apply 2048"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-prog="--txmsg_redir --txmsg_apply 2048 --txmsg_ingress"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-prog="--txmsg_redir --txmsg_apply 2048 --txmsg_skb"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-
-# Test apply and redirect with apply that never reaches limit
-r=1024
-i=1
-l=1
-prog="--txmsg_apply 2048"
-
-for t in "sendmsg" "sendpage"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with 1B not really useful but test it anyways
-r=1
-i=1024
-l=1024
-prog="--txmsg_cork 1"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with a more reasonable 100B
-r=1
-i=1000
-l=1000
-prog="--txmsg_cork 100"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with larger value than send
-r=1
-i=8
-l=1024
-prog="--txmsg_cork 2048"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with cork that never reaches limit
-r=1024
-i=1
-l=1
-prog="--txmsg_cork 2048"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-r=1
-i=1024
-l=1024
-prog="--txmsg_redir --txmsg_cork 1"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with a more reasonable 100B
-r=1
-i=1000
-l=1000
-prog="--txmsg_redir --txmsg_cork 100"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with larger value than send
-r=1
-i=8
-l=1024
-prog="--txmsg_redir --txmsg_cork 2048"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test cork with cork that never reaches limit
-r=1024
-i=1
-l=1
-prog="--txmsg_cork 2048"
-
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-
-# mix and match cork and apply not really useful but valid programs
-
-# Test apply < cork
-r=100
-i=1
-l=5
-prog="--txmsg_apply 10 --txmsg_cork 100"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Try again with larger sizes so we hit overflow case
-r=100
-i=1000
-l=2048
-prog="--txmsg_apply 4096 --txmsg_cork 8096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply > cork
-r=100
-i=1
-l=5
-prog="--txmsg_apply 100 --txmsg_cork 10"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Again with larger sizes so we hit overflow cases
-r=100
-i=1000
-l=2048
-prog="--txmsg_apply 8096 --txmsg_cork 4096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-
-# Test apply = cork
-r=100
-i=1
-l=5
-prog="--txmsg_apply 10 --txmsg_cork 10"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-r=100
-i=1000
-l=2048
-prog="--txmsg_apply 4096 --txmsg_cork 4096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply < cork
-r=100
-i=1
-l=5
-prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 100"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Try again with larger sizes so we hit overflow case
-r=100
-i=1000
-l=2048
-prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 8096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Test apply > cork
-r=100
-i=1
-l=5
-prog="--txmsg_redir --txmsg_apply 100 --txmsg_cork 10"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Again with larger sizes so we hit overflow cases
-r=100
-i=1000
-l=2048
-prog="--txmsg_redir --txmsg_apply 8096 --txmsg_cork 4096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-
-# Test apply = cork
-r=100
-i=1
-l=5
-prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 10"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-r=100
-i=1000
-l=2048
-prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 4096"
-for t in "sendpage" "sendmsg"; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog"
- echo $TEST
- $TEST
- sleep 2
-done
-
-# Tests for bpf_msg_pull_data()
-for i in `seq 99 100 1600`; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 0 --txmsg_end $i --txmsg_cork 1600"
- echo $TEST
- $TEST
- sleep 2
-done
-
-for i in `seq 199 100 1600`; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 100 --txmsg_end $i --txmsg_cork 1600"
- echo $TEST
- $TEST
- sleep 2
-done
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 1500 --txmsg_end 1600 --txmsg_cork 1600"
-echo $TEST
-$TEST
-sleep 2
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 1111 --txmsg_end 1112 --txmsg_cork 1600"
-echo $TEST
-$TEST
-sleep 2
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 1111 --txmsg_end 0 --txmsg_cork 1600"
-echo $TEST
-$TEST
-sleep 2
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1600"
-echo $TEST
-$TEST
-sleep 2
-
-TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \
- --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1602"
-echo $TEST
-$TEST
-sleep 2
-
-# Run through gamut again with start and end
-for prog in "--txmsg" "--txmsg_redir" "--txmsg_drop"; do
-for t in "sendmsg" "sendpage"; do
-for r in 1 10 100; do
- for i in 1 10 100; do
- for l in 1 10 100; do
- TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog --txmsg_start 1 --txmsg_end 2"
- echo $TEST
- $TEST
- sleep 2
- done
- done
-done
-done
-done
-
-# Some specific tests to cover specific code paths
-./sockmap --cgroup /mnt/cgroup2/ -t sendpage \
- -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3
-./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \
- -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3
-./sockmap --cgroup /mnt/cgroup2/ -t sendpage \
- -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5
-./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \
- -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5
endif
ifdef CONFIG_GCC_PLUGIN_SANCOV
- ifeq ($(CFLAGS_KCOV),)
+ ifeq ($(strip $(CFLAGS_KCOV)),)
# It is needed because of the gcc-plugin.sh and gcc version checks.
gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV) += sancov_plugin.so
$(call if_changed,bison)
quiet_cmd_bison_h = YACC $@
- cmd_bison_h = bison -o/dev/null --defines=$@ -t -l $<
+ cmd_bison_h = $(YACC) -o/dev/null --defines=$@ -t -l $<
$(obj)/%.tab.h: $(src)/%.y FORCE
$(call if_changed,bison_h)
--- /dev/null
+#!/usr/bin/python3
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2018 Netronome Systems, Inc.
+
+# In case user attempts to run with Python 2.
+from __future__ import print_function
+
+import argparse
+import re
+import sys, os
+
+class NoHelperFound(BaseException):
+ pass
+
+class ParsingError(BaseException):
+ def __init__(self, line='<line not provided>', reader=None):
+ if reader:
+ BaseException.__init__(self,
+ 'Error at file offset %d, parsing line: %s' %
+ (reader.tell(), line))
+ else:
+ BaseException.__init__(self, 'Error parsing line: %s' % line)
+
+class Helper(object):
+ """
+ An object representing the description of an eBPF helper function.
+ @proto: function prototype of the helper function
+ @desc: textual description of the helper function
+ @ret: description of the return value of the helper function
+ """
+ def __init__(self, proto='', desc='', ret=''):
+ self.proto = proto
+ self.desc = desc
+ self.ret = ret
+
+ def proto_break_down(self):
+ """
+ Break down helper function protocol into smaller chunks: return type,
+ name, distincts arguments.
+ """
+ arg_re = re.compile('((const )?(struct )?(\w+|...))( (\**)(\w+))?$')
+ res = {}
+ proto_re = re.compile('(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$')
+
+ capture = proto_re.match(self.proto)
+ res['ret_type'] = capture.group(1)
+ res['ret_star'] = capture.group(2)
+ res['name'] = capture.group(3)
+ res['args'] = []
+
+ args = capture.group(4).split(', ')
+ for a in args:
+ capture = arg_re.match(a)
+ res['args'].append({
+ 'type' : capture.group(1),
+ 'star' : capture.group(6),
+ 'name' : capture.group(7)
+ })
+
+ return res
+
+class HeaderParser(object):
+ """
+ An object used to parse a file in order to extract the documentation of a
+ list of eBPF helper functions. All the helpers that can be retrieved are
+ stored as Helper object, in the self.helpers() array.
+ @filename: name of file to parse, usually include/uapi/linux/bpf.h in the
+ kernel tree
+ """
+ def __init__(self, filename):
+ self.reader = open(filename, 'r')
+ self.line = ''
+ self.helpers = []
+
+ def parse_helper(self):
+ proto = self.parse_proto()
+ desc = self.parse_desc()
+ ret = self.parse_ret()
+ return Helper(proto=proto, desc=desc, ret=ret)
+
+ def parse_proto(self):
+ # Argument can be of shape:
+ # - "void"
+ # - "type name"
+ # - "type *name"
+ # - Same as above, with "const" and/or "struct" in front of type
+ # - "..." (undefined number of arguments, for bpf_trace_printk())
+ # There is at least one term ("void"), and at most five arguments.
+ p = re.compile(' \* ?((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$')
+ capture = p.match(self.line)
+ if not capture:
+ raise NoHelperFound
+ self.line = self.reader.readline()
+ return capture.group(1)
+
+ def parse_desc(self):
+ p = re.compile(' \* ?(?:\t| {6,8})Description$')
+ capture = p.match(self.line)
+ if not capture:
+ # Helper can have empty description and we might be parsing another
+ # attribute: return but do not consume.
+ return ''
+ # Description can be several lines, some of them possibly empty, and it
+ # stops when another subsection title is met.
+ desc = ''
+ while True:
+ self.line = self.reader.readline()
+ if self.line == ' *\n':
+ desc += '\n'
+ else:
+ p = re.compile(' \* ?(?:\t| {6,8})(?:\t| {8})(.*)')
+ capture = p.match(self.line)
+ if capture:
+ desc += capture.group(1) + '\n'
+ else:
+ break
+ return desc
+
+ def parse_ret(self):
+ p = re.compile(' \* ?(?:\t| {6,8})Return$')
+ capture = p.match(self.line)
+ if not capture:
+ # Helper can have empty retval and we might be parsing another
+ # attribute: return but do not consume.
+ return ''
+ # Return value description can be several lines, some of them possibly
+ # empty, and it stops when another subsection title is met.
+ ret = ''
+ while True:
+ self.line = self.reader.readline()
+ if self.line == ' *\n':
+ ret += '\n'
+ else:
+ p = re.compile(' \* ?(?:\t| {6,8})(?:\t| {8})(.*)')
+ capture = p.match(self.line)
+ if capture:
+ ret += capture.group(1) + '\n'
+ else:
+ break
+ return ret
+
+ def run(self):
+ # Advance to start of helper function descriptions.
+ offset = self.reader.read().find('* Start of BPF helper function descriptions:')
+ if offset == -1:
+ raise Exception('Could not find start of eBPF helper descriptions list')
+ self.reader.seek(offset)
+ self.reader.readline()
+ self.reader.readline()
+ self.line = self.reader.readline()
+
+ while True:
+ try:
+ helper = self.parse_helper()
+ self.helpers.append(helper)
+ except NoHelperFound:
+ break
+
+ self.reader.close()
+ print('Parsed description of %d helper function(s)' % len(self.helpers),
+ file=sys.stderr)
+
+###############################################################################
+
+class Printer(object):
+ """
+ A generic class for printers. Printers should be created with an array of
+ Helper objects, and implement a way to print them in the desired fashion.
+ @helpers: array of Helper objects to print to standard output
+ """
+ def __init__(self, helpers):
+ self.helpers = helpers
+
+ def print_header(self):
+ pass
+
+ def print_footer(self):
+ pass
+
+ def print_one(self, helper):
+ pass
+
+ def print_all(self):
+ self.print_header()
+ for helper in self.helpers:
+ self.print_one(helper)
+ self.print_footer()
+
+class PrinterRST(Printer):
+ """
+ A printer for dumping collected information about helpers as a ReStructured
+ Text page compatible with the rst2man program, which can be used to
+ generate a manual page for the helpers.
+ @helpers: array of Helper objects to print to standard output
+ """
+ def print_header(self):
+ header = '''\
+.. Copyright (C) All BPF authors and contributors from 2014 to present.
+.. See git log include/uapi/linux/bpf.h in kernel tree for details.
+..
+.. %%%LICENSE_START(VERBATIM)
+.. Permission is granted to make and distribute verbatim copies of this
+.. manual provided the copyright notice and this permission notice are
+.. preserved on all copies.
+..
+.. Permission is granted to copy and distribute modified versions of this
+.. manual under the conditions for verbatim copying, provided that the
+.. entire resulting derived work is distributed under the terms of a
+.. permission notice identical to this one.
+..
+.. Since the Linux kernel and libraries are constantly changing, this
+.. manual page may be incorrect or out-of-date. The author(s) assume no
+.. responsibility for errors or omissions, or for damages resulting from
+.. the use of the information contained herein. The author(s) may not
+.. have taken the same level of care in the production of this manual,
+.. which is licensed free of charge, as they might when working
+.. professionally.
+..
+.. Formatted or processed versions of this manual, if unaccompanied by
+.. the source, must acknowledge the copyright and authors of this work.
+.. %%%LICENSE_END
+..
+.. Please do not edit this file. It was generated from the documentation
+.. located in file include/uapi/linux/bpf.h of the Linux kernel sources
+.. (helpers description), and from scripts/bpf_helpers_doc.py in the same
+.. repository (header and footer).
+
+===========
+BPF-HELPERS
+===========
+-------------------------------------------------------------------------------
+list of eBPF helper functions
+-------------------------------------------------------------------------------
+
+:Manual section: 7
+
+DESCRIPTION
+===========
+
+The extended Berkeley Packet Filter (eBPF) subsystem consists in programs
+written in a pseudo-assembly language, then attached to one of the several
+kernel hooks and run in reaction of specific events. This framework differs
+from the older, "classic" BPF (or "cBPF") in several aspects, one of them being
+the ability to call special functions (or "helpers") from within a program.
+These functions are restricted to a white-list of helpers defined in the
+kernel.
+
+These helpers are used by eBPF programs to interact with the system, or with
+the context in which they work. For instance, they can be used to print
+debugging messages, to get the time since the system was booted, to interact
+with eBPF maps, or to manipulate network packets. Since there are several eBPF
+program types, and that they do not run in the same context, each program type
+can only call a subset of those helpers.
+
+Due to eBPF conventions, a helper can not have more than five arguments.
+
+Internally, eBPF programs call directly into the compiled helper functions
+without requiring any foreign-function interface. As a result, calling helpers
+introduces no overhead, thus offering excellent performance.
+
+This document is an attempt to list and document the helpers available to eBPF
+developers. They are sorted by chronological order (the oldest helpers in the
+kernel at the top).
+
+HELPERS
+=======
+'''
+ print(header)
+
+ def print_footer(self):
+ footer = '''
+EXAMPLES
+========
+
+Example usage for most of the eBPF helpers listed in this manual page are
+available within the Linux kernel sources, at the following locations:
+
+* *samples/bpf/*
+* *tools/testing/selftests/bpf/*
+
+LICENSE
+=======
+
+eBPF programs can have an associated license, passed along with the bytecode
+instructions to the kernel when the programs are loaded. The format for that
+string is identical to the one in use for kernel modules (Dual licenses, such
+as "Dual BSD/GPL", may be used). Some helper functions are only accessible to
+programs that are compatible with the GNU Privacy License (GPL).
+
+In order to use such helpers, the eBPF program must be loaded with the correct
+license string passed (via **attr**) to the **bpf**\ () system call, and this
+generally translates into the C source code of the program containing a line
+similar to the following:
+
+::
+
+ char ____license[] __attribute__((section("license"), used)) = "GPL";
+
+IMPLEMENTATION
+==============
+
+This manual page is an effort to document the existing eBPF helper functions.
+But as of this writing, the BPF sub-system is under heavy development. New eBPF
+program or map types are added, along with new helper functions. Some helpers
+are occasionally made available for additional program types. So in spite of
+the efforts of the community, this page might not be up-to-date. If you want to
+check by yourself what helper functions exist in your kernel, or what types of
+programs they can support, here are some files among the kernel tree that you
+may be interested in:
+
+* *include/uapi/linux/bpf.h* is the main BPF header. It contains the full list
+ of all helper functions, as well as many other BPF definitions including most
+ of the flags, structs or constants used by the helpers.
+* *net/core/filter.c* contains the definition of most network-related helper
+ functions, and the list of program types from which they can be used.
+* *kernel/trace/bpf_trace.c* is the equivalent for most tracing program-related
+ helpers.
+* *kernel/bpf/verifier.c* contains the functions used to check that valid types
+ of eBPF maps are used with a given helper function.
+* *kernel/bpf/* directory contains other files in which additional helpers are
+ defined (for cgroups, sockmaps, etc.).
+
+Compatibility between helper functions and program types can generally be found
+in the files where helper functions are defined. Look for the **struct
+bpf_func_proto** objects and for functions returning them: these functions
+contain a list of helpers that a given program type can call. Note that the
+**default:** label of the **switch ... case** used to filter helpers can call
+other functions, themselves allowing access to additional helpers. The
+requirement for GPL license is also in those **struct bpf_func_proto**.
+
+Compatibility between helper functions and map types can be found in the
+**check_map_func_compatibility**\ () function in file *kernel/bpf/verifier.c*.
+
+Helper functions that invalidate the checks on **data** and **data_end**
+pointers for network processing are listed in function
+**bpf_helper_changes_pkt_data**\ () in file *net/core/filter.c*.
+
+SEE ALSO
+========
+
+**bpf**\ (2),
+**cgroups**\ (7),
+**ip**\ (8),
+**perf_event_open**\ (2),
+**sendmsg**\ (2),
+**socket**\ (7),
+**tc-bpf**\ (8)'''
+ print(footer)
+
+ def print_proto(self, helper):
+ """
+ Format function protocol with bold and italics markers. This makes RST
+ file less readable, but gives nice results in the manual page.
+ """
+ proto = helper.proto_break_down()
+
+ print('**%s %s%s(' % (proto['ret_type'],
+ proto['ret_star'].replace('*', '\\*'),
+ proto['name']),
+ end='')
+
+ comma = ''
+ for a in proto['args']:
+ one_arg = '{}{}'.format(comma, a['type'])
+ if a['name']:
+ if a['star']:
+ one_arg += ' {}**\ '.format(a['star'].replace('*', '\\*'))
+ else:
+ one_arg += '** '
+ one_arg += '*{}*\\ **'.format(a['name'])
+ comma = ', '
+ print(one_arg, end='')
+
+ print(')**')
+
+ def print_one(self, helper):
+ self.print_proto(helper)
+
+ if (helper.desc):
+ print('\tDescription')
+ # Do not strip all newline characters: formatted code at the end of
+ # a section must be followed by a blank line.
+ for line in re.sub('\n$', '', helper.desc, count=1).split('\n'):
+ print('{}{}'.format('\t\t' if line else '', line))
+
+ if (helper.ret):
+ print('\tReturn')
+ for line in helper.ret.rstrip().split('\n'):
+ print('{}{}'.format('\t\t' if line else '', line))
+
+ print('')
+
+###############################################################################
+
+# If script is launched from scripts/ from kernel tree and can access
+# ../include/uapi/linux/bpf.h, use it as a default name for the file to parse,
+# otherwise the --filename argument will be required from the command line.
+script = os.path.abspath(sys.argv[0])
+linuxRoot = os.path.dirname(os.path.dirname(script))
+bpfh = os.path.join(linuxRoot, 'include/uapi/linux/bpf.h')
+
+argParser = argparse.ArgumentParser(description="""
+Parse eBPF header file and generate documentation for eBPF helper functions.
+The RST-formatted output produced can be turned into a manual page with the
+rst2man utility.
+""")
+if (os.path.isfile(bpfh)):
+ argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h',
+ default=bpfh)
+else:
+ argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h')
+args = argParser.parse_args()
+
+# Parse file.
+headerParser = HeaderParser(args.filename)
+headerParser.run()
+
+# Print formatted output to standard output.
+printer = PrinterRST(headerParser.helpers)
+printer.print_all()
FAIL(c, dti, node, "incorrect #size-cells for PCI bridge");
prop = get_property(node, "bus-range");
- if (!prop) {
- FAIL(c, dti, node, "missing bus-range for PCI bridge");
+ if (!prop)
return;
- }
+
if (prop->val.len != (sizeof(cell_t) * 2)) {
FAIL_PROP(c, dti, node, prop, "value must be 2 cells");
return;
#!/usr/bin/env perl
-# Copyright (c) Mauro Carvalho Chehab <mchehab@infradead.org>
+# Copyright (c) Mauro Carvalho Chehab <mchehab@kernel.org>
# Released under GPLv2
#
# In order to use, you need to:
echo "$file_lines" | while read -r line
do
echo $line
- eval $(echo $line | awk -F "[ :]" '{printf("n1=%d;n2=%d;f=%s",$NF-5, $NF+5, $(NF-1))}')
+ n=$(echo $line | sed 's/.*:\([0-9]\+\).*/\1/g')
+ n1=$[$n-5]
+ n2=$[$n+5]
+ f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g')
awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") {printf("%d\t%s\n", NR, $0)}' $f
done
# so that 'bison: not found' will be displayed if it is missing.
ifeq ($(findstring 1,$(KBUILD_ENABLE_EXTRA_GCC_CHECKS)),)
-quiet_cmd_bison_no_warn = $(quet_cmd_bison)
+quiet_cmd_bison_no_warn = $(quiet_cmd_bison)
cmd_bison_no_warn = $(YACC) --version >/dev/null; \
$(cmd_bison) 2>/dev/null
$(obj)/parse.tab.c: $(src)/parse.y FORCE
$(call if_changed,bison_no_warn)
-quiet_cmd_bison_h_no_warn = $(quet_cmd_bison_h)
+quiet_cmd_bison_h_no_warn = $(quiet_cmd_bison_h)
cmd_bison_h_no_warn = $(YACC) --version >/dev/null; \
$(cmd_bison_h) 2>/dev/null
goto out;
}
- /* There will be a line like so:
- deps_drivers/net/dummy.o := \
- drivers/net/dummy.c \
- $(wildcard include/config/net/fastroute.h) \
- include/linux/module.h \
-
- Sum all files in the same dir or subdirs.
- */
+ /* Sum all files in the same dir or subdirs. */
while ((line = get_next_line(&pos, file, flen)) != NULL) {
char* p = line;
#!/usr/bin/perl
# SPDX-License-Identifier: GPL-2.0
#
-# Author: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+# Author: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
#
# Produce manpages from kernel-doc.
# See Documentation/doc-guide/kernel-doc.rst for instructions
magic |= VFS_CAP_FLAGS_EFFECTIVE;
memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
cap->magic_etc = cpu_to_le32(magic);
+ } else {
+ size = -ENOMEM;
}
}
kfree(tmpbuf);
return SECCLASS_QIPCRTR_SOCKET;
case PF_SMC:
return SECCLASS_SMC_SOCKET;
-#if PF_MAX > 44
+ case PF_XDP:
+ return SECCLASS_XDP_SOCKET;
+#if PF_MAX > 45
#error New address family defined, please update this function.
#endif
}
static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
{
struct sock *sk = sock->sk;
+ struct sk_security_struct *sksec = sk->sk_security;
u16 family;
int err;
family = sk->sk_family;
if (family == PF_INET || family == PF_INET6) {
char *addrp;
- struct sk_security_struct *sksec = sk->sk_security;
struct common_audit_data ad;
struct lsm_network_audit net = {0,};
struct sockaddr_in *addr4 = NULL;
struct sockaddr_in6 *addr6 = NULL;
+ u16 family_sa = address->sa_family;
unsigned short snum;
u32 sid, node_perm;
* need to check address->sa_family as it is possible to have
* sk->sk_family = PF_INET6 with addr->sa_family = AF_INET.
*/
- switch (address->sa_family) {
+ switch (family_sa) {
+ case AF_UNSPEC:
case AF_INET:
if (addrlen < sizeof(struct sockaddr_in))
return -EINVAL;
addr4 = (struct sockaddr_in *)address;
+ if (family_sa == AF_UNSPEC) {
+ /* see __inet_bind(), we only want to allow
+ * AF_UNSPEC if the address is INADDR_ANY
+ */
+ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY))
+ goto err_af;
+ family_sa = AF_INET;
+ }
snum = ntohs(addr4->sin_port);
addrp = (char *)&addr4->sin_addr.s_addr;
break;
addrp = (char *)&addr6->sin6_addr.s6_addr;
break;
default:
- /* Note that SCTP services expect -EINVAL, whereas
- * others expect -EAFNOSUPPORT.
- */
- if (sksec->sclass == SECCLASS_SCTP_SOCKET)
- return -EINVAL;
- else
- return -EAFNOSUPPORT;
+ goto err_af;
}
+ ad.type = LSM_AUDIT_DATA_NET;
+ ad.u.net = &net;
+ ad.u.net->sport = htons(snum);
+ ad.u.net->family = family_sa;
+
if (snum) {
int low, high;
snum, &sid);
if (err)
goto out;
- ad.type = LSM_AUDIT_DATA_NET;
- ad.u.net = &net;
- ad.u.net->sport = htons(snum);
- ad.u.net->family = family;
err = avc_has_perm(&selinux_state,
sksec->sid, sid,
sksec->sclass,
break;
}
- err = sel_netnode_sid(addrp, family, &sid);
+ err = sel_netnode_sid(addrp, family_sa, &sid);
if (err)
goto out;
- ad.type = LSM_AUDIT_DATA_NET;
- ad.u.net = &net;
- ad.u.net->sport = htons(snum);
- ad.u.net->family = family;
-
- if (address->sa_family == AF_INET)
+ if (family_sa == AF_INET)
ad.u.net->v4info.saddr = addr4->sin_addr.s_addr;
else
ad.u.net->v6info.saddr = addr6->sin6_addr;
}
out:
return err;
+err_af:
+ /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */
+ if (sksec->sclass == SECCLASS_SCTP_SOCKET)
+ return -EINVAL;
+ return -EAFNOSUPPORT;
}
/* This supports connect(2) and SCTP connect services such as sctp_connectx(3)
ad.type = LSM_AUDIT_DATA_NET;
ad.u.net = &net;
ad.u.net->dport = htons(snum);
- ad.u.net->family = sk->sk_family;
+ ad.u.net->family = address->sa_family;
err = avc_has_perm(&selinux_state,
sksec->sid, sid, sksec->sclass, perm, &ad);
if (err)
while (walk_size < addrlen) {
addr = addr_buf;
switch (addr->sa_family) {
+ case AF_UNSPEC:
case AF_INET:
len = sizeof(struct sockaddr_in);
break;
len = sizeof(struct sockaddr_in6);
break;
default:
- return -EAFNOSUPPORT;
+ return -EINVAL;
}
err = -EINVAL;
{ "manage_subnet", NULL } },
{ "bpf",
{"map_create", "map_read", "map_write", "prog_load", "prog_run"} },
+ { "xdp_socket",
+ { COMMON_SOCK_PERMS, NULL } },
{ NULL }
};
-#if PF_MAX > 44
+#if PF_MAX > 45
#error New address family defined, please update secclass_map.
#endif
int op_flag)
{
struct snd_ctl_tlv header;
- unsigned int *container;
+ unsigned int __user *container;
unsigned int container_size;
struct snd_kcontrol *kctl;
struct snd_ctl_elem_id id;
if (copy_from_user(&data->id, &data32->id, sizeof(data->id)) ||
copy_from_user(&data->type, &data32->type, 3 * sizeof(u32)))
goto error;
- if (get_user(data->owner, &data32->owner) ||
- get_user(data->type, &data32->type))
+ if (get_user(data->owner, &data32->owner))
goto error;
switch (data->type) {
case SNDRV_CTL_ELEM_TYPE_BOOLEAN:
s32 __user *src)
{
snd_pcm_sframes_t delay;
+ int err;
- delay = snd_pcm_delay(substream);
- if (delay < 0)
- return delay;
+ err = snd_pcm_delay(substream, &delay);
+ if (err)
+ return err;
if (put_user(delay, src))
return -EFAULT;
return 0;
return -ENOTTY;
if (substream->stream != dir)
return -EINVAL;
+ if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN)
+ return -EBADFD;
if ((ch = substream->runtime->channels) > 128)
return -EINVAL;
return err;
}
-static snd_pcm_sframes_t snd_pcm_delay(struct snd_pcm_substream *substream)
+static int snd_pcm_delay(struct snd_pcm_substream *substream,
+ snd_pcm_sframes_t *delay)
{
struct snd_pcm_runtime *runtime = substream->runtime;
int err;
n += runtime->delay;
}
snd_pcm_stream_unlock_irq(substream);
- return err < 0 ? err : n;
+ if (!err)
+ *delay = n;
+ return err;
}
static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream,
sync_ptr.s.status.hw_ptr = status->hw_ptr;
sync_ptr.s.status.tstamp = status->tstamp;
sync_ptr.s.status.suspended_state = status->suspended_state;
+ sync_ptr.s.status.audio_tstamp = status->audio_tstamp;
snd_pcm_stream_unlock_irq(substream);
if (copy_to_user(_sync_ptr, &sync_ptr, sizeof(sync_ptr)))
return -EFAULT;
return snd_pcm_hwsync(substream);
case SNDRV_PCM_IOCTL_DELAY:
{
- snd_pcm_sframes_t delay = snd_pcm_delay(substream);
+ snd_pcm_sframes_t delay;
snd_pcm_sframes_t __user *res = arg;
+ int err;
- if (delay < 0)
- return delay;
+ err = snd_pcm_delay(substream, &delay);
+ if (err)
+ return err;
if (put_user(delay, res))
return -EFAULT;
return 0;
case SNDRV_PCM_IOCTL_DROP:
return snd_pcm_drop(substream);
case SNDRV_PCM_IOCTL_DELAY:
- {
- result = snd_pcm_delay(substream);
- if (result < 0)
- return result;
- *frames = result;
- return 0;
- }
+ return snd_pcm_delay(substream, frames);
default:
return -EINVAL;
}
/*
* mmap status record
*/
-static int snd_pcm_mmap_status_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_status_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
/*
* mmap control record
*/
-static int snd_pcm_mmap_control_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_control_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
/*
* fault callback for mmapping a RAM page
*/
-static int snd_pcm_mmap_data_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
struct snd_rawmidi_params params;
unsigned int val;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(params.stream, &src->stream) ||
get_user(params.buffer_size, &src->buffer_size) ||
get_user(params.avail_min, &src->avail_min) ||
params.no_active_sensing = val;
switch (params.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
return snd_rawmidi_output_params(rfile->output, ¶ms);
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
return snd_rawmidi_input_params(rfile->input, ¶ms);
}
return -EINVAL;
int err;
struct snd_rawmidi_status status;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(status.stream, &src->stream))
return -EFAULT;
switch (status.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
err = snd_rawmidi_output_status(rfile->output, &status);
break;
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
err = snd_rawmidi_input_status(rfile->input, &status);
break;
default:
int err;
struct snd_rawmidi_status status;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(status.stream, &src->stream))
return -EFAULT;
switch (status.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
err = snd_rawmidi_output_status(rfile->output, &status);
break;
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
err = snd_rawmidi_input_status(rfile->input, &status);
break;
default:
#include <sound/seq_oss_legacy.h>
#include "seq_oss_readq.h"
#include "seq_oss_writeq.h"
+#include <linux/nospec.h>
/*
{
struct seq_oss_synthinfo *info;
- if (!snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- info = &dp->synths[dev];
switch (info->arg.event_passing) {
case SNDRV_SEQ_OSS_PROCESS_EVENTS:
if (! info->ch || ch < 0 || ch >= info->nr_voices) {
return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
}
+ ch = array_index_nospec(ch, info->nr_voices);
if (note == 255 && info->ch[ch].note >= 0) {
/* volume control */
int type;
{
struct seq_oss_synthinfo *info;
- if (!snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- info = &dp->synths[dev];
switch (info->arg.event_passing) {
case SNDRV_SEQ_OSS_PROCESS_EVENTS:
if (! info->ch || ch < 0 || ch >= info->nr_voices) {
return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
}
+ ch = array_index_nospec(ch, info->nr_voices);
if (info->ch[ch].note >= 0) {
note = info->ch[ch].note;
info->ch[ch].vel = 0;
static int
set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ if (!snd_seq_oss_synth_info(dp, dev))
return -ENXIO;
ev->type = type;
static int
set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ if (!snd_seq_oss_synth_info(dp, dev))
return -ENXIO;
ev->type = type;
#include "../seq_lock.h"
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
/*
{
if (dev < 0 || dev >= dp->max_mididev)
return NULL;
+ dev = array_index_nospec(dev, dp->max_mididev);
return get_mdev(dev);
}
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
/*
* constants
dp->max_synthdev = 0;
}
-/*
- * check if the specified device is MIDI mapped device
- */
-static int
-is_midi_dev(struct seq_oss_devinfo *dp, int dev)
+static struct seq_oss_synthinfo *
+get_synthinfo_nospec(struct seq_oss_devinfo *dp, int dev)
{
if (dev < 0 || dev >= dp->max_synthdev)
- return 0;
- if (dp->synths[dev].is_midi)
- return 1;
- return 0;
+ return NULL;
+ dev = array_index_nospec(dev, SNDRV_SEQ_OSS_MAX_SYNTH_DEVS);
+ return &dp->synths[dev];
}
/*
get_synthdev(struct seq_oss_devinfo *dp, int dev)
{
struct seq_oss_synth *rec;
- if (dev < 0 || dev >= dp->max_synthdev)
- return NULL;
- if (! dp->synths[dev].opened)
+ struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev);
+
+ if (!info)
return NULL;
- if (dp->synths[dev].is_midi)
- return &midi_synth_dev;
- if ((rec = get_sdev(dev)) == NULL)
+ if (!info->opened)
return NULL;
+ if (info->is_midi) {
+ rec = &midi_synth_dev;
+ snd_use_lock_use(&rec->use_lock);
+ } else {
+ rec = get_sdev(dev);
+ if (!rec)
+ return NULL;
+ }
if (! rec->opened) {
snd_use_lock_free(&rec->use_lock);
return NULL;
struct seq_oss_synth *rec;
struct seq_oss_synthinfo *info;
- if (snd_BUG_ON(dev < 0 || dev >= dp->max_synthdev))
- return;
- info = &dp->synths[dev];
- if (! info->opened)
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info || !info->opened)
return;
if (info->sysex)
info->sysex->len = 0; /* reset sysex */
const char __user *buf, int p, int c)
{
struct seq_oss_synth *rec;
+ struct seq_oss_synthinfo *info;
int rc;
- if (dev < 0 || dev >= dp->max_synthdev)
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info)
return -ENXIO;
- if (is_midi_dev(dp, dev))
+ if (info->is_midi)
return 0;
if ((rec = get_synthdev(dp, dev)) == NULL)
return -ENXIO;
if (rec->oper.load_patch == NULL)
rc = -ENXIO;
else
- rc = rec->oper.load_patch(&dp->synths[dev].arg, fmt, buf, p, c);
+ rc = rec->oper.load_patch(&info->arg, fmt, buf, p, c);
snd_use_lock_free(&rec->use_lock);
return rc;
}
/*
- * check if the device is valid synth device
+ * check if the device is valid synth device and return the synth info
*/
-int
-snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev)
+struct seq_oss_synthinfo *
+snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev)
{
struct seq_oss_synth *rec;
+
rec = get_synthdev(dp, dev);
if (rec) {
snd_use_lock_free(&rec->use_lock);
- return 1;
+ return get_synthinfo_nospec(dp, dev);
}
- return 0;
+ return NULL;
}
int i, send;
unsigned char *dest;
struct seq_oss_synth_sysex *sysex;
+ struct seq_oss_synthinfo *info;
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- sysex = dp->synths[dev].sysex;
+ sysex = info->sysex;
if (sysex == NULL) {
sysex = kzalloc(sizeof(*sysex), GFP_KERNEL);
if (sysex == NULL)
return -ENOMEM;
- dp->synths[dev].sysex = sysex;
+ info->sysex = sysex;
}
send = 0;
int
snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ struct seq_oss_synthinfo *info = snd_seq_oss_synth_info(dp, dev);
+
+ if (!info)
return -EINVAL;
- snd_seq_oss_fill_addr(dp, ev, dp->synths[dev].arg.addr.client,
- dp->synths[dev].arg.addr.port);
+ snd_seq_oss_fill_addr(dp, ev, info->arg.addr.client,
+ info->arg.addr.port);
return 0;
}
snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, unsigned long addr)
{
struct seq_oss_synth *rec;
+ struct seq_oss_synthinfo *info;
int rc;
- if (is_midi_dev(dp, dev))
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info || info->is_midi)
return -ENXIO;
if ((rec = get_synthdev(dp, dev)) == NULL)
return -ENXIO;
if (rec->oper.ioctl == NULL)
rc = -ENXIO;
else
- rc = rec->oper.ioctl(&dp->synths[dev].arg, cmd, addr);
+ rc = rec->oper.ioctl(&info->arg, cmd, addr);
snd_use_lock_free(&rec->use_lock);
return rc;
}
int
snd_seq_oss_synth_raw_event(struct seq_oss_devinfo *dp, int dev, unsigned char *data, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev) || is_midi_dev(dp, dev))
+ struct seq_oss_synthinfo *info;
+
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info || info->is_midi)
return -ENXIO;
ev->type = SNDRV_SEQ_EVENT_OSS;
memcpy(ev->data.raw8.d, data, 8);
void snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev);
int snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
const char __user *buf, int p, int c);
-int snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev);
+struct seq_oss_synthinfo *snd_seq_oss_synth_info(struct seq_oss_devinfo *dp,
+ int dev);
int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
struct snd_seq_event *ev);
int snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev);
}
return;
}
+ spin_lock_irqsave(&substream->runtime->lock, flags);
if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
- return;
+ goto out;
vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
}
- spin_lock_irqsave(&substream->runtime->lock, flags);
while (1) {
count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf));
if (count <= 0)
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].rate_shift;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
int change = 0;
val = ucontrol->value.integer.value[0] ? 1 : 0;
+ mutex_lock(&loopback->cable_lock);
if (val != loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify) {
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify = val;
change = 1;
}
+ mutex_unlock(&loopback->cable_lock);
return change;
}
struct snd_ctl_elem_value *ucontrol)
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
- struct loopback_cable *cable = loopback->cables
- [kcontrol->id.subdevice][kcontrol->id.device ^ 1];
+ struct loopback_cable *cable;
+
unsigned int val = 0;
+ mutex_lock(&loopback->cable_lock);
+ cable = loopback->cables[kcontrol->id.subdevice][kcontrol->id.device ^ 1];
if (cable != NULL) {
unsigned int running = cable->running ^ cable->pause;
val = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? 1 : 0;
}
+ mutex_unlock(&loopback->cable_lock);
ucontrol->value.integer.value[0] = val;
return 0;
}
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].rate;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].channels;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/nospec.h>
#include <sound/opl3.h>
#include <sound/asound_fm.h>
{
unsigned short reg_side;
unsigned char op_offset;
- unsigned char voice_offset;
+ unsigned char voice_offset, voice_op;
unsigned short opl3_reg;
unsigned char reg_val;
voice_offset = voice->voice - MAX_OPL2_VOICES;
}
/* Get register offset of operator */
- op_offset = snd_opl3_regmap[voice_offset][voice->op];
+ voice_offset = array_index_nospec(voice_offset, MAX_OPL2_VOICES);
+ voice_op = array_index_nospec(voice->op, 4);
+ op_offset = snd_opl3_regmap[voice_offset][voice_op];
reg_val = 0x00;
/* Set amplitude modulation (tremolo) effect */
u32 cycle;
unsigned int packets;
- s->max_payload_length = amdtp_stream_get_max_payload(s);
-
/*
* For in-stream, first packet has come.
* For out-stream, prepared to transmit first packet
amdtp_stream_update(s);
+ if (s->direction == AMDTP_IN_STREAM)
+ s->max_payload_length = amdtp_stream_get_max_payload(s);
+
if (s->flags & CIP_NO_HEADER)
s->tag = TAG_NO_CIP_HEADER;
else
err = init_stream(dice, AMDTP_IN_STREAM, i);
if (err < 0) {
for (; i >= 0; i--)
- destroy_stream(dice, AMDTP_OUT_STREAM, i);
+ destroy_stream(dice, AMDTP_IN_STREAM, i);
goto end;
}
}
#define OUI_WEISS 0x001c6a
#define OUI_LOUD 0x000ff2
#define OUI_FOCUSRITE 0x00130e
-#define OUI_TCELECTRONIC 0x001486
+#define OUI_TCELECTRONIC 0x000166
#define DICE_CATEGORY_ID 0x04
#define WEISS_CATEGORY_ID 0x00
#include "hpi_internal.h"
#include "hpimsginit.h"
+#include <linux/nospec.h>
/* The actual message size for each object type */
static u16 msg_size[HPI_OBJ_MAXINDEX + 1] = HPI_MESSAGE_SIZE_BY_OBJECT;
{
u16 size;
- if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+ if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+ object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
size = msg_size[object];
- else
+ } else {
size = sizeof(*phm);
+ }
memset(phm, 0, size);
phm->size = size;
{
u16 size;
- if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+ if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+ object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
size = res_size[object];
- else
+ } else {
size = sizeof(*phr);
+ }
memset(phr, 0, sizeof(*phr));
phr->size = size;
#include <linux/stringify.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
+#include <linux/nospec.h>
#ifdef MODULE_FIRMWARE
MODULE_FIRMWARE("asihpi/dsp5000.bin");
struct hpi_adapter *pa = NULL;
if (hm->h.adapter_index < ARRAY_SIZE(adapters))
- pa = &adapters[hm->h.adapter_index];
+ pa = &adapters[array_index_nospec(hm->h.adapter_index,
+ ARRAY_SIZE(adapters))];
if (!pa || !pa->adapter || !pa->adapter->type) {
hpi_init_response(&hr->r0, hm->h.object,
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/compat.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include "hda_codec.h"
#include "hda_local.h"
if (get_user(verb, &arg->verb))
return -EFAULT;
- res = get_wcaps(codec, verb >> 24);
+ /* open-code get_wcaps(verb>>24) with nospec */
+ verb >>= 24;
+ if (verb < codec->core.start_nid ||
+ verb >= codec->core.start_nid + codec->core.num_nodes) {
+ res = 0;
+ } else {
+ verb -= codec->core.start_nid;
+ verb = array_index_nospec(verb, codec->core.num_nodes);
+ res = codec->wcaps[verb];
+ }
if (put_user(res, &arg->res))
return -EFAULT;
return 0;
*/
u8 val;
pci_read_config_byte(chip->pci, 0x42, &val);
- if (!(val & 0x80) && chip->pci->revision == 0x30)
+ if (!(val & 0x80) && (chip->pci->revision == 0x30 ||
+ chip->pci->revision == 0x20))
snoop = false;
}
SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
+ SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
/* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0),
{}
pcm = get_pcm_rec(spec, per_pin->pcm_idx);
else
return;
+ if (!pcm->pcm)
+ return;
if (!test_bit(per_pin->pcm_idx, &spec->pcm_in_use))
return;
int dev, err;
int pin_idx, pcm_idx;
-
for (pcm_idx = 0; pcm_idx < spec->pcm_used; pcm_idx++) {
+ if (!get_pcm_rec(spec, pcm_idx)->pcm) {
+ /* no PCM: mark this for skipping permanently */
+ set_bit(pcm_idx, &spec->pcm_bitmap);
+ continue;
+ }
+
err = generic_hdmi_build_jack(codec, pcm_idx);
if (err < 0)
return err;
/* fallthrough */
case 0x10ec0215:
case 0x10ec0233:
+ case 0x10ec0235:
case 0x10ec0236:
case 0x10ec0255:
case 0x10ec0256:
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
}
}
-#if IS_REACHABLE(INPUT)
+#if IS_REACHABLE(CONFIG_INPUT)
static void gpio2_mic_hotkey_event(struct hda_codec *codec,
struct hda_jack_callback *event)
{
{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
{ }
},
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MIC
},
};
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
case 0x10ec0298:
spec->codec_variant = ALC269_TYPE_ALC298;
break;
+ case 0x10ec0235:
case 0x10ec0255:
spec->codec_variant = ALC269_TYPE_ALC255;
+ spec->shutup = alc256_shutup;
+ spec->init_hook = alc256_init;
break;
case 0x10ec0236:
case 0x10ec0256:
#include <linux/pci.h>
#include <linux/math64.h>
#include <linux/io.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include <sound/control.h>
struct snd_pcm_channel_info *info)
{
struct hdspm *hdspm = snd_pcm_substream_chip(substream);
+ unsigned int channel = info->channel;
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
- if (snd_BUG_ON(info->channel >= hdspm->max_channels_out)) {
+ if (snd_BUG_ON(channel >= hdspm->max_channels_out)) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: output channel out of range (%d)\n",
- info->channel);
+ channel);
return -EINVAL;
}
- if (hdspm->channel_map_out[info->channel] < 0) {
+ channel = array_index_nospec(channel, hdspm->max_channels_out);
+ if (hdspm->channel_map_out[channel] < 0) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: output channel %d mapped out\n",
- info->channel);
+ channel);
return -EINVAL;
}
- info->offset = hdspm->channel_map_out[info->channel] *
+ info->offset = hdspm->channel_map_out[channel] *
HDSPM_CHANNEL_BUFFER_BYTES;
} else {
- if (snd_BUG_ON(info->channel >= hdspm->max_channels_in)) {
+ if (snd_BUG_ON(channel >= hdspm->max_channels_in)) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: input channel out of range (%d)\n",
- info->channel);
+ channel);
return -EINVAL;
}
- if (hdspm->channel_map_in[info->channel] < 0) {
+ channel = array_index_nospec(channel, hdspm->max_channels_in);
+ if (hdspm->channel_map_in[channel] < 0) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: input channel %d mapped out\n",
- info->channel);
+ channel);
return -EINVAL;
}
- info->offset = hdspm->channel_map_in[info->channel] *
+ info->offset = hdspm->channel_map_in[channel] *
HDSPM_CHANNEL_BUFFER_BYTES;
}
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/io.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include <sound/control.h>
if (snd_BUG_ON(info->channel >= RME9652_NCHANNELS))
return -EINVAL;
- if ((chn = rme9652->channel_map[info->channel]) < 0) {
+ chn = rme9652->channel_map[array_index_nospec(info->channel,
+ RME9652_NCHANNELS)];
+ if (chn < 0)
return -EINVAL;
- }
info->offset = chn * RME9652_CHANNEL_BUFFER_BYTES;
info->first = 0;
#define DUAL_CHANNEL 2
static struct snd_soc_jack cz_jack;
-struct clk *da7219_dai_clk;
+static struct clk *da7219_dai_clk;
static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd)
{
}
if (adau->sigmadsp) {
- ret = adau17x1_setup_firmware(adau, params_rate(params));
+ ret = adau17x1_setup_firmware(component, params_rate(params));
if (ret < 0)
return ret;
}
}
EXPORT_SYMBOL_GPL(adau17x1_volatile_register);
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate)
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+ unsigned int rate)
{
int ret;
- int dspsr;
+ int dspsr, dsp_run;
+ struct adau *adau = snd_soc_component_get_drvdata(component);
+ struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+
+ snd_soc_dapm_mutex_lock(dapm);
ret = regmap_read(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, &dspsr);
if (ret)
- return ret;
+ goto err;
+
+ ret = regmap_read(adau->regmap, ADAU17X1_DSP_RUN, &dsp_run);
+ if (ret)
+ goto err;
regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 1);
regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, 0xf);
+ regmap_write(adau->regmap, ADAU17X1_DSP_RUN, 0);
ret = sigmadsp_setup(adau->sigmadsp, rate);
if (ret) {
regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 0);
- return ret;
+ goto err;
}
regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, dspsr);
+ regmap_write(adau->regmap, ADAU17X1_DSP_RUN, dsp_run);
- return 0;
+err:
+ snd_soc_dapm_mutex_unlock(dapm);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(adau17x1_setup_firmware);
extern const struct snd_soc_dai_ops adau17x1_dai_ops;
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate);
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+ unsigned int rate);
bool adau17x1_has_dsp(struct adau *adau);
#define ADAU17X1_CLOCK_CONTROL 0x4000
return irq;
}
- ret = devm_request_irq(dev, irq, pm8916_mbhc_switch_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ pm8916_mbhc_switch_irq_handler,
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING |
IRQF_ONESHOT,
"mbhc switch irq", priv);
return irq;
}
- ret = devm_request_irq(dev, irq, mbhc_btn_press_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ mbhc_btn_press_irq_handler,
IRQF_TRIGGER_RISING |
IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"mbhc btn press irq", priv);
return irq;
}
- ret = devm_request_irq(dev, irq, mbhc_btn_release_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ mbhc_btn_release_irq_handler,
IRQF_TRIGGER_RISING |
IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"mbhc btn release irq", priv);
{RT5514_PLL3_CALIB_CTRL5, 0x40220012},
{RT5514_DELAY_BUF_CTRL1, 0x7fff006a},
{RT5514_DELAY_BUF_CTRL3, 0x00000000},
+ {RT5514_ASRC_IN_CTRL1, 0x00000003},
{RT5514_DOWNFILTER0_CTRL1, 0x00020c2f},
{RT5514_DOWNFILTER0_CTRL2, 0x00020c2f},
{RT5514_DOWNFILTER0_CTRL3, 0x10000362},
case RT5514_PLL3_CALIB_CTRL5:
case RT5514_DELAY_BUF_CTRL1:
case RT5514_DELAY_BUF_CTRL3:
+ case RT5514_ASRC_IN_CTRL1:
case RT5514_DOWNFILTER0_CTRL1:
case RT5514_DOWNFILTER0_CTRL2:
case RT5514_DOWNFILTER0_CTRL3:
case RT5514_DSP_MAPPING | RT5514_PLL3_CALIB_CTRL5:
case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL3:
+ case RT5514_DSP_MAPPING | RT5514_ASRC_IN_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL2:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL3:
psr = ratio <= 256 * maxfp ? ESAI_xCCR_xPSR_BYPASS : ESAI_xCCR_xPSR_DIV8;
+ /* Do not loop-search if PM (1 ~ 256) alone can serve the ratio */
+ if (ratio <= 256) {
+ pm = ratio;
+ fp = 1;
+ goto out;
+ }
+
/* Set the max fluctuation -- 0.1% of the max devisor */
savesub = (psr ? 1 : 8) * 256 * maxfp / 1000;
* @dai_fmt: DAI configuration this device is currently used with
* @streams: Mask of current active streams: BIT(TX) and BIT(RX)
* @i2s_net: I2S and Network mode configurations of SCR register
+ * (this is the initial settings based on the DAI format)
* @synchronous: Use synchronous mode - both of TX and RX use STCK and SFCK
* @use_dma: DMA is used or FIQ with stream filter
* @use_dual_fifo: DMA with support for dual FIFO mode
}
if (!fsl_ssi_is_ac97(ssi)) {
+ /*
+ * Keep the ssi->i2s_net intact while having a local variable
+ * to override settings for special use cases. Otherwise, the
+ * ssi->i2s_net will lose the settings for regular use cases.
+ */
+ u8 i2s_net = ssi->i2s_net;
+
/* Normal + Network mode to send 16-bit data in 32-bit frames */
if (fsl_ssi_is_i2s_cbm_cfs(ssi) && sample_size == 16)
- ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
+ i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
/* Use Normal mode to send mono data at 1st slot of 2 slots */
if (channels == 1)
- ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL;
+ i2s_net = SSI_SCR_I2S_MODE_NORMAL;
regmap_update_bits(regs, REG_SSI_SCR,
- SSI_SCR_I2S_NET_MASK, ssi->i2s_net);
+ SSI_SCR_I2S_NET_MASK, i2s_net);
}
/* In synchronous mode, the SSI uses STCCR for capture */
for Baytrail Chromebooks but this option is now deprecated and is
not recommended, use SND_SST_ATOM_HIFI2_PLATFORM instead.
+config SND_SST_ATOM_HIFI2_PLATFORM
+ tristate
+ select SND_SOC_COMPRESS
+
config SND_SST_ATOM_HIFI2_PLATFORM_PCI
- tristate "PCI HiFi2 (Medfield, Merrifield) Platforms"
+ tristate "PCI HiFi2 (Merrifield) Platforms"
depends on X86 && PCI
select SND_SST_IPC_PCI
- select SND_SOC_COMPRESS
+ select SND_SST_ATOM_HIFI2_PLATFORM
help
- If you have a Intel Medfield or Merrifield/Edison platform, then
+ If you have a Intel Merrifield/Edison platform, then
enable this option by saying Y or m. Distros will typically not
- enable this option: Medfield devices are not available to
- developers and while Merrifield/Edison can run a mainline kernel with
- limited functionality it will require a firmware file which
- is not in the standard firmware tree
+ enable this option: while Merrifield/Edison can run a mainline
+ kernel with limited functionality it will require a firmware file
+ which is not in the standard firmware tree
-config SND_SST_ATOM_HIFI2_PLATFORM
+config SND_SST_ATOM_HIFI2_PLATFORM_ACPI
tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
+ default ACPI
depends on X86 && ACPI
select SND_SST_IPC_ACPI
- select SND_SOC_COMPRESS
+ select SND_SST_ATOM_HIFI2_PLATFORM
select SND_SOC_ACPI_INTEL_MATCH
select IOSF_MBI
help
static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
unsigned int freq)
{
- struct clk *parent_clk;
+ struct clk *parent_clk, *mux;
char *parent_clk_name;
int ret = 0;
return -ENODEV;
}
+ mux = clk_get_parent(dmic->fclk);
+ if (IS_ERR(mux)) {
+ dev_err(dmic->dev, "can't get fck mux parent\n");
+ clk_put(parent_clk);
+ return -ENODEV;
+ }
+
mutex_lock(&dmic->mutex);
if (dmic->active) {
/* disable clock while reparenting */
pm_runtime_put_sync(dmic->dev);
- ret = clk_set_parent(dmic->fclk, parent_clk);
+ ret = clk_set_parent(mux, parent_clk);
pm_runtime_get_sync(dmic->dev);
} else {
- ret = clk_set_parent(dmic->fclk, parent_clk);
+ ret = clk_set_parent(mux, parent_clk);
}
mutex_unlock(&dmic->mutex);
dmic->fclk_freq = freq;
err_busy:
+ clk_put(mux);
clk_put(parent_clk);
return ret;
return ret;
}
-static int rsnd_suspend(struct device *dev)
+static int __maybe_unused rsnd_suspend(struct device *dev)
{
struct rsnd_priv *priv = dev_get_drvdata(dev);
return 0;
}
-static int rsnd_resume(struct device *dev)
+static int __maybe_unused rsnd_resume(struct device *dev)
{
struct rsnd_priv *priv = dev_get_drvdata(dev);
*/
if (dobj->widget.kcontrol_type == SND_SOC_TPLG_TYPE_ENUM) {
/* enumerated widget mixer */
- for (i = 0; i < w->num_kcontrols; i++) {
+ for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
struct snd_kcontrol *kcontrol = w->kcontrols[i];
struct soc_enum *se =
(struct soc_enum *)kcontrol->private_value;
}
} else {
/* volume mixer or bytes controls */
- for (i = 0; i < w->num_kcontrols; i++) {
+ for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
struct snd_kcontrol *kcontrol = w->kcontrols[i];
if (dobj->widget.kcontrol_type
ec->hdr.name);
kc[i].name = kstrdup(ec->hdr.name, GFP_KERNEL);
- if (kc[i].name == NULL)
+ if (kc[i].name == NULL) {
+ kfree(se);
goto err_se;
+ }
kc[i].private_value = (long)se;
kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
kc[i].access = ec->hdr.access;
be->hdr.name, be->hdr.access);
kc[i].name = kstrdup(be->hdr.name, GFP_KERNEL);
- if (kc[i].name == NULL)
+ if (kc[i].name == NULL) {
+ kfree(sbe);
goto err;
+ }
kc[i].private_value = (long)sbe;
kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
kc[i].access = be->hdr.access;
/* match index */
if (dobj->index != index &&
- dobj->index != SND_SOC_TPLG_INDEX_ALL)
+ index != SND_SOC_TPLG_INDEX_ALL)
continue;
switch (dobj->type) {
}
usb_fill_int_urb(urb, line6->usbdev,
- usb_sndbulkpipe(line6->usbdev,
+ usb_sndintpipe(line6->usbdev,
line6->properties->ep_ctrl_w),
transfer_buffer, length, midi_sent, line6,
line6->interval);
}
break;
+ case USB_ID(0x0d8c, 0x0103):
+ if (!strcmp(kctl->id.name, "PCM Playback Volume")) {
+ usb_audio_info(chip,
+ "set volume quirk for CM102-A+/102S+\n");
+ cval->min = -256;
+ }
+ break;
+
case USB_ID(0x0471, 0x0101):
case USB_ID(0x0471, 0x0104):
case USB_ID(0x0471, 0x0105):
build_feature_ctl(state, _ftr, ch_bits, control,
&iterm, unitid, ch_read_only);
if (uac_v2v3_control_is_readable(master_bits, control))
- build_feature_ctl(state, _ftr, 0, i, &iterm, unitid,
+ build_feature_ctl(state, _ftr, 0, control,
+ &iterm, unitid,
!uac_v2v3_control_is_writeable(master_bits,
control));
}
check_input_term(state, d->bTerminalID, &iterm);
if (state->mixer->protocol == UAC_VERSION_2) {
/* Check for jack detection. */
- if (uac_v2v3_control_is_readable(d->bmControls,
+ if (uac_v2v3_control_is_readable(le16_to_cpu(d->bmControls),
UAC2_TE_CONNECTOR)) {
build_connector_control(state, &iterm, true);
}
if (err < 0 && err != -EINVAL)
return err;
- if (uac_v2v3_control_is_readable(desc->bmControls,
+ if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
UAC2_TE_CONNECTOR)) {
build_connector_control(&state, &state.oterm,
false);
/*
* Dell usb dock with ALC4020 codec had a firmware problem where it got
* screwed up when zero volume is passed; just skip it as a workaround
+ *
+ * Also the extension unit gives an access error, so skip it as well.
*/
static const struct usbmix_name_map dell_alc4020_map[] = {
+ { 4, NULL }, /* extension unit */
{ 16, NULL },
{ 19, NULL },
{ 0 }
* TODO: this conversion is not complete, update it
* after adding UAC3 values to asound.h
*/
- switch (is->bChPurpose) {
+ switch (is->bChRelationship) {
case UAC3_CH_MONO:
map = SNDRV_CHMAP_MONO;
break;
if (protocol == UAC_VERSION_1) {
attributes = csep->bmAttributes;
- } else {
+ } else if (protocol == UAC_VERSION_2) {
struct uac2_iso_endpoint_descriptor *csep2 =
(struct uac2_iso_endpoint_descriptor *) csep;
/* emulate the endpoint attributes of a v1 device */
if (csep2->bmControls & UAC2_CONTROL_PITCH)
attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
+ } else { /* UAC_VERSION_3 */
+ struct uac3_iso_endpoint_descriptor *csep3 =
+ (struct uac3_iso_endpoint_descriptor *) csep;
+
+ /* emulate the endpoint attributes of a v1 device */
+ if (le32_to_cpu(csep3->bmControls) & UAC2_CONTROL_PITCH)
+ attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
}
return attributes;
snd_printdd(KERN_DEBUG "%i\n", atomic_read(&us122l->mmap_count));
}
-static int usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
+static vm_fault_t usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
struct page *page;
#include "usbusx2y.h"
#include "usX2Yhwdep.h"
-static int snd_us428ctls_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_us428ctls_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
struct page * page;
}
-static int snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
void *vaddr;
#define KVM_REG_ARM_CRM_SHIFT 7
#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800
#define KVM_REG_ARM_32_CRN_SHIFT 11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK 0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT 28
#define ARM_CP15_REG_SHIFT_MASK(x,n) \
(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
#define KVM_REG_ARM_VFP_FPINST 0x1009
#define KVM_REG_ARM_VFP_FPINST2 0x100A
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
# define NEED_MOVBE 0
#endif
-#ifdef CONFIG_X86_5LEVEL
-# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31))
-#else
-# define NEED_LA57 0
-#endif
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
#define REQUIRED_MASK13 0
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
-#define REQUIRED_MASK16 (NEED_LA57)
+#define REQUIRED_MASK16 0
#define REQUIRED_MASK17 0
#define REQUIRED_MASK18 0
#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
__u64 padding[16];
};
-/* definition of registers in kvm_run */
+#define KVM_SYNC_X86_REGS (1UL << 0)
+#define KVM_SYNC_X86_SREGS (1UL << 1)
+#define KVM_SYNC_X86_EVENTS (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+ (KVM_SYNC_X86_REGS| \
+ KVM_SYNC_X86_SREGS| \
+ KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
struct kvm_sync_regs {
+ /* Members of this structure are potentially malicious.
+ * Care must be taken by code reading, esp. interpreting,
+ * data fields from them inside KVM to prevent TOCTOU and
+ * double-fetch types of vulnerabilities.
+ */
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_vcpu_events events;
};
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^
$(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
clean: bpftool_clean
$(call QUIET_CLEAN, bpf-progs)
static int cmd_load(char *arg)
{
- char *subcmd, *cont, *tmp = strdup(arg);
+ char *subcmd, *cont = NULL, *tmp = strdup(arg);
int ret = CMD_OK;
subcmd = strtok_r(tmp, " ", &cont);
bpf_reset();
bpf_reset_breakpoints();
- ret = cmd_load_bpf(cont);
+ if (!cont)
+ ret = CMD_ERR;
+ else
+ ret = cmd_load_bpf(cont);
} else if (matches(subcmd, "pcap") == 0) {
ret = cmd_load_pcap(cont);
} else {
--- /dev/null
+*.d
+bpftool
+FEATURE-DUMP.bpftool
=============
| **bpftool** **map { show | list }** [*MAP*]
-| **bpftool** **map dump** *MAP*
-| **bpftool** **map update** *MAP* **key** [**hex**] *BYTES* **value** [**hex**] *VALUE* [*UPDATE_FLAGS*]
-| **bpftool** **map lookup** *MAP* **key** [**hex**] *BYTES*
-| **bpftool** **map getnext** *MAP* [**key** [**hex**] *BYTES*]
-| **bpftool** **map delete** *MAP* **key** [**hex**] *BYTES*
-| **bpftool** **map pin** *MAP* *FILE*
+| **bpftool** **map dump** *MAP*
+| **bpftool** **map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*]
+| **bpftool** **map lookup** *MAP* **key** *DATA*
+| **bpftool** **map getnext** *MAP* [**key** *DATA*]
+| **bpftool** **map delete** *MAP* **key** *DATA*
+| **bpftool** **map pin** *MAP* *FILE*
+| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*]
| **bpftool** **map help**
|
| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
+| *DATA* := { [**hex**] *BYTES* }
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
-| *VALUE* := { *BYTES* | *MAP* | *PROG* }
+| *VALUE* := { *DATA* | *MAP* | *PROG* }
| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
DESCRIPTION
**bpftool map dump** *MAP*
Dump all entries in a given *MAP*.
- **bpftool map update** *MAP* **key** [**hex**] *BYTES* **value** [**hex**] *VALUE* [*UPDATE_FLAGS*]
+ **bpftool map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*]
Update map entry for a given *KEY*.
*UPDATE_FLAGS* can be one of: **any** update existing entry
the bytes are parsed as decimal values, unless a "0x" prefix
(for hexadecimal) or a "0" prefix (for octal) is provided.
- **bpftool map lookup** *MAP* **key** [**hex**] *BYTES*
+ **bpftool map lookup** *MAP* **key** *DATA*
Lookup **key** in the map.
- **bpftool map getnext** *MAP* [**key** [**hex**] *BYTES*]
+ **bpftool map getnext** *MAP* [**key** *DATA*]
Get next key. If *key* is not specified, get first key.
- **bpftool map delete** *MAP* **key** [**hex**] *BYTES*
+ **bpftool map delete** *MAP* **key** *DATA*
Remove entry from the map.
**bpftool map pin** *MAP* *FILE*
Note: *FILE* must be located in *bpffs* mount.
+ **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*]
+ Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map.
+
+ Install perf rings into a perf event array map and dump
+ output of any bpf_perf_event_output() call in the kernel.
+ By default read the number of CPUs on the system and
+ install perf ring for each CPU in the corresponding index
+ in the array.
+
+ If **cpu** and **index** are specified, install perf ring
+ for given **cpu** at **index** in the array (single ring).
+
+ Note that installing a perf ring into an array will silently
+ replace any existing ring. Any other application will stop
+ receiving events if it installed its rings earlier.
+
**bpftool map help**
Print short help message.
**# bpftool prog show**
::
- 10: xdp name some_prog tag 005a3d2123620c8b
+ 10: xdp name some_prog tag 005a3d2123620c8b gpl
loaded_at Sep 29/20:11 uid 0
xlated 528B jited 370B memlock 4096B map_ids 10
"id": 10,
"type": "xdp",
"tag": "005a3d2123620c8b",
+ "gpl_compatible": true,
"loaded_at": "Sep 29/20:11",
"uid": 0,
"bytes_xlated": 528,
*MAP-COMMANDS* :=
{ **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete**
- | **pin** | **help** }
+ | **pin** | **event_pipe** | **help** }
*PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin**
| **load** | **help** }
CFLAGS += -O2
CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers
-CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
+CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
+ -I$(srctree)/kernel/bpf/ \
+ -I$(srctree)/tools/include \
+ -I$(srctree)/tools/include/uapi \
+ -I$(srctree)/tools/lib/bpf \
+ -I$(srctree)/tools/perf
CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
# bpftool(8) bash completion -*- shell-script -*-
#
-# Copyright (C) 2017 Netronome Systems, Inc.
+# Copyright (C) 2017-2018 Netronome Systems, Inc.
#
# This software is dual licensed under the GNU General License
# Version 2, June 1991 as shown in the file COPYING in the top-level
command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
}
+_bpftool_get_perf_map_ids()
+{
+ COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \
+ command grep -C2 perf_event_array | \
+ command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) )
+}
+
+
_bpftool_get_prog_ids()
{
COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \
fi
return 0
;;
+ event_pipe)
+ case $prev in
+ $command)
+ COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+ return 0
+ ;;
+ id)
+ _bpftool_get_perf_map_ids
+ return 0
+ ;;
+ cpu)
+ return 0
+ ;;
+ index)
+ return 0
+ ;;
+ *)
+ _bpftool_once_attr 'cpu'
+ _bpftool_once_attr 'index'
+ return 0
+ ;;
+ esac
+ ;;
*)
[[ $prev == $object ]] && \
COMPREPLY=( $( compgen -W 'delete dump getnext help \
- lookup pin show list update' -- "$cur" ) )
+ lookup pin event_pipe show list update' -- \
+ "$cur" ) )
;;
esac
;;
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
/* Author: Jakub Kicinski <kubakici@wp.pl> */
+#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
#include <fts.h>
return NULL;
}
+void print_data_json(uint8_t *data, size_t len)
+{
+ unsigned int i;
+
+ jsonw_start_array(json_wtr);
+ for (i = 0; i < len; i++)
+ jsonw_printf(json_wtr, "%d", data[i]);
+ jsonw_end_array(json_wtr);
+}
+
void print_hex_data_json(uint8_t *data, size_t len)
{
unsigned int i;
}
}
+unsigned int get_page_size(void)
+{
+ static int result;
+
+ if (!result)
+ result = getpagesize();
+ return result;
+}
+
+unsigned int get_possible_cpus(void)
+{
+ static unsigned int result;
+ char buf[128];
+ long int n;
+ char *ptr;
+ int fd;
+
+ if (result)
+ return result;
+
+ fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
+ if (fd < 0) {
+ p_err("can't open sysfs possible cpus");
+ exit(-1);
+ }
+
+ n = read(fd, buf, sizeof(buf));
+ if (n < 2) {
+ p_err("can't read sysfs possible cpus");
+ exit(-1);
+ }
+ close(fd);
+
+ if (n == sizeof(buf)) {
+ p_err("read sysfs possible cpus overflow");
+ exit(-1);
+ }
+
+ ptr = buf;
+ n = 0;
+ while (*ptr && *ptr != '\n') {
+ unsigned int a, b;
+
+ if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
+ n += b - a + 1;
+
+ ptr = strchr(ptr, '-') + 1;
+ } else if (sscanf(ptr, "%u", &a) == 1) {
+ n++;
+ } else {
+ assert(0);
+ }
+
+ while (isdigit(*ptr))
+ ptr++;
+ if (*ptr == ',')
+ ptr++;
+ }
+
+ result = n;
+
+ return result;
+}
+
static char *
ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf)
{
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
int do_prog(int argc, char **arg);
int do_map(int argc, char **arg);
+int do_event_pipe(int argc, char **argv);
int do_cgroup(int argc, char **arg);
int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
const char *arch);
+void print_data_json(uint8_t *data, size_t len);
void print_hex_data_json(uint8_t *data, size_t len);
+unsigned int get_page_size(void);
+unsigned int get_possible_cpus(void);
const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
#endif
/*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
/* Author: Jakub Kicinski <kubakici@wp.pl> */
#include <assert.h>
-#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
#include <stdbool.h>
[BPF_MAP_TYPE_DEVMAP] = "devmap",
[BPF_MAP_TYPE_SOCKMAP] = "sockmap",
[BPF_MAP_TYPE_CPUMAP] = "cpumap",
+ [BPF_MAP_TYPE_SOCKHASH] = "sockhash",
};
-static unsigned int get_possible_cpus(void)
-{
- static unsigned int result;
- char buf[128];
- long int n;
- char *ptr;
- int fd;
-
- if (result)
- return result;
-
- fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
- if (fd < 0) {
- p_err("can't open sysfs possible cpus");
- exit(-1);
- }
-
- n = read(fd, buf, sizeof(buf));
- if (n < 2) {
- p_err("can't read sysfs possible cpus");
- exit(-1);
- }
- close(fd);
-
- if (n == sizeof(buf)) {
- p_err("read sysfs possible cpus overflow");
- exit(-1);
- }
-
- ptr = buf;
- n = 0;
- while (*ptr && *ptr != '\n') {
- unsigned int a, b;
-
- if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
- n += b - a + 1;
-
- ptr = strchr(ptr, '-') + 1;
- } else if (sscanf(ptr, "%u", &a) == 1) {
- n++;
- } else {
- assert(0);
- }
-
- while (isdigit(*ptr))
- ptr++;
- if (*ptr == ',')
- ptr++;
- }
-
- result = n;
-
- return result;
-}
-
static bool map_is_per_cpu(__u32 type)
{
return type == BPF_MAP_TYPE_PERCPU_HASH ||
return -1;
}
-static int
-map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
+int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
{
int err;
int fd;
fprintf(stderr,
"Usage: %s %s { show | list } [MAP]\n"
- " %s %s dump MAP\n"
- " %s %s update MAP key [hex] BYTES value [hex] VALUE [UPDATE_FLAGS]\n"
- " %s %s lookup MAP key [hex] BYTES\n"
- " %s %s getnext MAP [key [hex] BYTES]\n"
- " %s %s delete MAP key [hex] BYTES\n"
- " %s %s pin MAP FILE\n"
+ " %s %s dump MAP\n"
+ " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n"
+ " %s %s lookup MAP key DATA\n"
+ " %s %s getnext MAP [key DATA]\n"
+ " %s %s delete MAP key DATA\n"
+ " %s %s pin MAP FILE\n"
+ " %s %s event_pipe MAP [cpu N index M]\n"
" %s %s help\n"
"\n"
" MAP := { id MAP_ID | pinned FILE }\n"
+ " DATA := { [hex] BYTES }\n"
" " HELP_SPEC_PROGRAM "\n"
- " VALUE := { BYTES | MAP | PROG }\n"
+ " VALUE := { DATA | MAP | PROG }\n"
" UPDATE_FLAGS := { any | exist | noexist }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
- bin_name, argv[-2], bin_name, argv[-2]);
+ bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]);
return 0;
}
{ "getnext", do_getnext },
{ "delete", do_delete },
{ "pin", do_pin },
+ { "event_pipe", do_event_pipe },
{ 0 }
};
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+/* This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <libbpf.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+
+#include <bpf.h>
+#include <perf-sys.h>
+
+#include "main.h"
+
+#define MMAP_PAGE_CNT 16
+
+static bool stop;
+
+struct event_ring_info {
+ int fd;
+ int key;
+ unsigned int cpu;
+ void *mem;
+};
+
+struct perf_event_sample {
+ struct perf_event_header header;
+ u64 time;
+ __u32 size;
+ unsigned char data[];
+};
+
+static void int_exit(int signo)
+{
+ fprintf(stderr, "Stopping...\n");
+ stop = true;
+}
+
+static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
+{
+ struct event_ring_info *ring = priv;
+ struct perf_event_sample *e = event;
+ struct {
+ struct perf_event_header header;
+ __u64 id;
+ __u64 lost;
+ } *lost = event;
+
+ if (json_output) {
+ jsonw_start_object(json_wtr);
+ jsonw_name(json_wtr, "type");
+ jsonw_uint(json_wtr, e->header.type);
+ jsonw_name(json_wtr, "cpu");
+ jsonw_uint(json_wtr, ring->cpu);
+ jsonw_name(json_wtr, "index");
+ jsonw_uint(json_wtr, ring->key);
+ if (e->header.type == PERF_RECORD_SAMPLE) {
+ jsonw_name(json_wtr, "timestamp");
+ jsonw_uint(json_wtr, e->time);
+ jsonw_name(json_wtr, "data");
+ print_data_json(e->data, e->size);
+ } else if (e->header.type == PERF_RECORD_LOST) {
+ jsonw_name(json_wtr, "lost");
+ jsonw_start_object(json_wtr);
+ jsonw_name(json_wtr, "id");
+ jsonw_uint(json_wtr, lost->id);
+ jsonw_name(json_wtr, "count");
+ jsonw_uint(json_wtr, lost->lost);
+ jsonw_end_object(json_wtr);
+ }
+ jsonw_end_object(json_wtr);
+ } else {
+ if (e->header.type == PERF_RECORD_SAMPLE) {
+ printf("== @%lld.%09lld CPU: %d index: %d =====\n",
+ e->time / 1000000000ULL, e->time % 1000000000ULL,
+ ring->cpu, ring->key);
+ fprint_hex(stdout, e->data, e->size, " ");
+ printf("\n");
+ } else if (e->header.type == PERF_RECORD_LOST) {
+ printf("lost %lld events\n", lost->lost);
+ } else {
+ printf("unknown event type=%d size=%d\n",
+ e->header.type, e->header.size);
+ }
+ }
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void
+perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len)
+{
+ enum bpf_perf_event_ret ret;
+
+ ret = bpf_perf_event_read_simple(ring->mem,
+ MMAP_PAGE_CNT * get_page_size(),
+ get_page_size(), buf, buf_len,
+ print_bpf_output, ring);
+ if (ret != LIBBPF_PERF_EVENT_CONT) {
+ fprintf(stderr, "perf read loop failed with %d\n", ret);
+ stop = true;
+ }
+}
+
+static int perf_mmap_size(void)
+{
+ return get_page_size() * (MMAP_PAGE_CNT + 1);
+}
+
+static void *perf_event_mmap(int fd)
+{
+ int mmap_size = perf_mmap_size();
+ void *base;
+
+ base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (base == MAP_FAILED) {
+ p_err("event mmap failed: %s\n", strerror(errno));
+ return NULL;
+ }
+
+ return base;
+}
+
+static void perf_event_unmap(void *mem)
+{
+ if (munmap(mem, perf_mmap_size()))
+ fprintf(stderr, "Can't unmap ring memory!\n");
+}
+
+static int bpf_perf_event_open(int map_fd, int key, int cpu)
+{
+ struct perf_event_attr attr = {
+ .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ };
+ int pmu_fd;
+
+ pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+ if (pmu_fd < 0) {
+ p_err("failed to open perf event %d for CPU %d", key, cpu);
+ return -1;
+ }
+
+ if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
+ p_err("failed to update map for event %d for CPU %d", key, cpu);
+ goto err_close;
+ }
+ if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
+ p_err("failed to enable event %d for CPU %d", key, cpu);
+ goto err_close;
+ }
+
+ return pmu_fd;
+
+err_close:
+ close(pmu_fd);
+ return -1;
+}
+
+int do_event_pipe(int argc, char **argv)
+{
+ int i, nfds, map_fd, index = -1, cpu = -1;
+ struct bpf_map_info map_info = {};
+ struct event_ring_info *rings;
+ size_t tmp_buf_sz = 0;
+ void *tmp_buf = NULL;
+ struct pollfd *pfds;
+ __u32 map_info_len;
+ bool do_all = true;
+
+ map_info_len = sizeof(map_info);
+ map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
+ if (map_fd < 0)
+ return -1;
+
+ if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+ p_err("map is not a perf event array");
+ goto err_close_map;
+ }
+
+ while (argc) {
+ if (argc < 2)
+ BAD_ARG();
+
+ if (is_prefix(*argv, "cpu")) {
+ char *endptr;
+
+ NEXT_ARG();
+ cpu = strtoul(*argv, &endptr, 0);
+ if (*endptr) {
+ p_err("can't parse %s as CPU ID", **argv);
+ goto err_close_map;
+ }
+
+ NEXT_ARG();
+ } else if (is_prefix(*argv, "index")) {
+ char *endptr;
+
+ NEXT_ARG();
+ index = strtoul(*argv, &endptr, 0);
+ if (*endptr) {
+ p_err("can't parse %s as index", **argv);
+ goto err_close_map;
+ }
+
+ NEXT_ARG();
+ } else {
+ BAD_ARG();
+ }
+
+ do_all = false;
+ }
+
+ if (!do_all) {
+ if (index == -1 || cpu == -1) {
+ p_err("cpu and index must be specified together");
+ goto err_close_map;
+ }
+
+ nfds = 1;
+ } else {
+ nfds = min(get_possible_cpus(), map_info.max_entries);
+ cpu = 0;
+ index = 0;
+ }
+
+ rings = calloc(nfds, sizeof(rings[0]));
+ if (!rings)
+ goto err_close_map;
+
+ pfds = calloc(nfds, sizeof(pfds[0]));
+ if (!pfds)
+ goto err_free_rings;
+
+ for (i = 0; i < nfds; i++) {
+ rings[i].cpu = cpu + i;
+ rings[i].key = index + i;
+
+ rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
+ rings[i].cpu);
+ if (rings[i].fd < 0)
+ goto err_close_fds_prev;
+
+ rings[i].mem = perf_event_mmap(rings[i].fd);
+ if (!rings[i].mem)
+ goto err_close_fds_current;
+
+ pfds[i].fd = rings[i].fd;
+ pfds[i].events = POLLIN;
+ }
+
+ signal(SIGINT, int_exit);
+ signal(SIGHUP, int_exit);
+ signal(SIGTERM, int_exit);
+
+ if (json_output)
+ jsonw_start_array(json_wtr);
+
+ while (!stop) {
+ poll(pfds, nfds, 200);
+ for (i = 0; i < nfds; i++)
+ perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
+ }
+ free(tmp_buf);
+
+ if (json_output)
+ jsonw_end_array(json_wtr);
+
+ for (i = 0; i < nfds; i++) {
+ perf_event_unmap(rings[i].mem);
+ close(rings[i].fd);
+ }
+ free(pfds);
+ free(rings);
+ close(map_fd);
+
+ return 0;
+
+err_close_fds_prev:
+ while (i--) {
+ perf_event_unmap(rings[i].mem);
+err_close_fds_current:
+ close(rings[i].fd);
+ }
+ free(pfds);
+err_free_rings:
+ free(rings);
+err_close_map:
+ close(map_fd);
+ return -1;
+}
return;
}
- strftime(buf, size, "%b %d/%H:%M", &load_tm);
+ if (json_output)
+ strftime(buf, size, "%s", &load_tm);
+ else
+ strftime(buf, size, "%FT%T%z", &load_tm);
}
static int prog_fd_by_tag(unsigned char *tag)
info->tag[0], info->tag[1], info->tag[2], info->tag[3],
info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
+ jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible);
+
print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
if (info->load_time) {
print_boot_time(info->load_time, buf, sizeof(buf));
/* Piggy back on load_time, since 0 uid is a valid one */
- jsonw_string_field(json_wtr, "loaded_at", buf);
+ jsonw_name(json_wtr, "loaded_at");
+ jsonw_printf(json_wtr, "%s", buf);
jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
}
printf("tag ");
fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino);
+ printf("%s", info->gpl_compatible ? " gpl" : "");
printf("\n");
if (info->load_time) {
* required ordering.
*/
-#define READ_ONCE(x) \
- ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
-
-#define WRITE_ONCE(x, val) \
- ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__c = { 0 } }; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
+
+#define WRITE_ONCE(x, val) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__val = (val) }; \
+ __write_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
#ifndef __fallthrough
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef _LINUX_CORESIGHT_PMU_H
#include <stdbool.h>
#define spinlock_t pthread_mutex_t
-#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER;
+#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
#define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
+#define spin_lock_init(x) pthread_mutex_init(x, NULL)
#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x)
#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x)
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
#endif
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */
+
/*
* Flags for mlock
*/
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/uapi/asm/bitsperlong.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/uapi/asm/bitsperlong.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/uapi/asm/bitsperlong.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/uapi/asm/bitsperlong.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/uapi/asm/bitsperlong.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/uapi/asm/bitsperlong.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/uapi/asm/bitsperlong.h"
+#else
+#include <asm-generic/bitsperlong.h>
+#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/uapi/asm/errno.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/uapi/asm/errno.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/uapi/asm/errno.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/uapi/asm/errno.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/uapi/asm/errno.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/uapi/asm/errno.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/uapi/asm/errno.h"
+#else
+#include <asm-generic/errno.h>
+#endif
BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
+ BPF_BTF_GET_FD_BY_ID,
};
enum bpf_map_type {
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
BPF_MAP_TYPE_CPUMAP,
+ BPF_MAP_TYPE_XSKMAP,
+ BPF_MAP_TYPE_SOCKHASH,
};
enum bpf_prog_type {
__u32 start_id;
__u32 prog_id;
__u32 map_id;
+ __u32 btf_id;
};
__u32 next_id;
__u32 open_flags;
};
} __attribute__((aligned(8)));
-/* BPF helper function descriptions:
- *
- * void *bpf_map_lookup_elem(&map, &key)
- * Return: Map value or NULL
- *
- * int bpf_map_update_elem(&map, &key, &value, flags)
- * Return: 0 on success or negative error
- *
- * int bpf_map_delete_elem(&map, &key)
- * Return: 0 on success or negative error
- *
- * int bpf_probe_read(void *dst, int size, void *src)
- * Return: 0 on success or negative error
+/* The description below is an attempt at providing documentation to eBPF
+ * developers about the multiple available eBPF helper functions. It can be
+ * parsed and used to produce a manual page. The workflow is the following,
+ * and requires the rst2man utility:
+ *
+ * $ ./scripts/bpf_helpers_doc.py \
+ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
+ * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
+ * $ man /tmp/bpf-helpers.7
+ *
+ * Note that in order to produce this external documentation, some RST
+ * formatting is used in the descriptions to get "bold" and "italics" in
+ * manual pages. Also note that the few trailing white spaces are
+ * intentional, removing them would break paragraphs for rst2man.
+ *
+ * Start of BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Perform a lookup in *map* for an entry associated to *key*.
+ * Return
+ * Map value associated to *key*, or **NULL** if no entry was
+ * found.
+ *
+ * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+ * Description
+ * Add or update the value of the entry associated to *key* in
+ * *map* with *value*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * Flag value **BPF_NOEXIST** cannot be used for maps of types
+ * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all
+ * elements always exist), the helper would return an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_delete_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Delete entry with *key* from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * Description
+ * For tracing programs, safely attempt to read *size* bytes from
+ * address *src* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* u64 bpf_ktime_get_ns(void)
- * Return: current ktime
- *
- * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
- * Return: length of buffer written or negative error
- *
- * u32 bpf_prandom_u32(void)
- * Return: random value
- *
- * u32 bpf_raw_smp_processor_id(void)
- * Return: SMP processor ID
- *
- * int bpf_skb_store_bytes(skb, offset, from, len, flags)
- * store bytes into packet
- * @skb: pointer to skb
- * @offset: offset within packet from skb->mac_header
- * @from: pointer where to copy bytes from
- * @len: number of bytes to store into packet
- * @flags: bit 0 - if true, recompute skb->csum
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_l3_csum_replace(skb, offset, from, to, flags)
- * recompute IP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where IP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_l4_csum_replace(skb, offset, from, to, flags)
- * recompute TCP/UDP checksum
- * @skb: pointer to skb
- * @offset: offset within packet where TCP/UDP checksum is located
- * @from: old value of header field
- * @to: new value of header field
- * @flags: bits 0-3 - size of header field
- * bit 4 - is pseudo header
- * other bits - reserved
- * Return: 0 on success or negative error
- *
- * int bpf_tail_call(ctx, prog_array_map, index)
- * jump into another BPF program
- * @ctx: context pointer passed to next program
- * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- * @index: 32-bit index inside array that selects specific program to run
- * Return: 0 on success or negative error
- *
- * int bpf_clone_redirect(skb, ifindex, flags)
- * redirect to another netdev
- * @skb: pointer to skb
- * @ifindex: ifindex of the net device
- * @flags: bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * Return: 0 on success or negative error
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Return
+ * Current *ktime*.
+ *
+ * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
+ * Description
+ * This helper is a "printk()-like" facility for debugging. It
+ * prints a message defined by format *fmt* (of size *fmt_size*)
+ * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if
+ * available. It can take up to three additional **u64**
+ * arguments (as an eBPF helpers, the total number of arguments is
+ * limited to five).
+ *
+ * Each time the helper is called, it appends a line to the trace.
+ * The format of the trace is customizable, and the exact output
+ * one will get depends on the options set in
+ * *\/sys/kernel/debug/tracing/trace_options* (see also the
+ * *README* file under the same directory). However, it usually
+ * defaults to something like:
+ *
+ * ::
+ *
+ * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg>
+ *
+ * In the above:
+ *
+ * * ``telnet`` is the name of the current task.
+ * * ``470`` is the PID of the current task.
+ * * ``001`` is the CPU number on which the task is
+ * running.
+ * * In ``.N..``, each character refers to a set of
+ * options (whether irqs are enabled, scheduling
+ * options, whether hard/softirqs are running, level of
+ * preempt_disabled respectively). **N** means that
+ * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED**
+ * are set.
+ * * ``419421.045894`` is a timestamp.
+ * * ``0x00000001`` is a fake value used by BPF for the
+ * instruction pointer register.
+ * * ``<formatted msg>`` is the message formatted with
+ * *fmt*.
+ *
+ * The conversion specifiers supported by *fmt* are similar, but
+ * more limited than for printk(). They are **%d**, **%i**,
+ * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**,
+ * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size
+ * of field, padding with zeroes, etc.) is available, and the
+ * helper will return **-EINVAL** (but print nothing) if it
+ * encounters an unknown specifier.
+ *
+ * Also, note that **bpf_trace_printk**\ () is slow, and should
+ * only be used for debugging purposes. For this reason, a notice
+ * bloc (spanning several lines) is printed to kernel logs and
+ * states that the helper should not be used "for production use"
+ * the first time this helper is used (or more precisely, when
+ * **trace_printk**\ () buffers are allocated). For passing values
+ * to user space, perf events should be preferred.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * u32 bpf_get_prandom_u32(void)
+ * Description
+ * Get a pseudo-random number.
+ *
+ * From a security point of view, this helper uses its own
+ * pseudo-random internal state, and cannot be used to infer the
+ * seed of other random functions in the kernel. However, it is
+ * essential to note that the generator used by the helper is not
+ * cryptographically secure.
+ * Return
+ * A random 32-bit unsigned value.
+ *
+ * u32 bpf_get_smp_processor_id(void)
+ * Description
+ * Get the SMP (symmetric multiprocessing) processor id. Note that
+ * all programs run with preemption disabled, which means that the
+ * SMP processor id is stable during all the execution of the
+ * program.
+ * Return
+ * The SMP id of the processor running the program.
+ *
+ * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. *flags* are a combination of
+ * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * checksum for the packet after storing the bytes) and
+ * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
+ * **->swhash** and *skb*\ **->l4hash** to 0).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
+ * Description
+ * Recompute the layer 3 (e.g. IP) checksum for the packet
+ * associated to *skb*. Computation is incremental, so the helper
+ * must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored in *size*.
+ * Alternatively, it is possible to store the difference between
+ * the previous and the new values of the header field in *to*, by
+ * setting *from* and *size* to 0. For both methods, *offset*
+ * indicates the location of the IP checksum within the packet.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
+ * Description
+ * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
+ * packet associated to *skb*. Computation is incremental, so the
+ * helper must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored on the lowest
+ * four bits of *flags*. Alternatively, it is possible to store
+ * the difference between the previous and the new values of the
+ * header field in *to*, by setting *from* and the four lowest
+ * bits of *flags* to 0. For both methods, *offset* indicates the
+ * location of the IP checksum within the packet. In addition to
+ * the size of the field, *flags* can be added (bitwise OR) actual
+ * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
+ * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
+ * for updates resulting in a null checksum the value is set to
+ * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
+ * the checksum is to be computed against a pseudo-header.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
+ * Description
+ * This special helper is used to trigger a "tail call", or in
+ * other words, to jump into another eBPF program. The same stack
+ * frame is used (but values on stack and in registers for the
+ * caller are not accessible to the callee). This mechanism allows
+ * for program chaining, either for raising the maximum number of
+ * available eBPF instructions, or to execute given programs in
+ * conditional blocks. For security reasons, there is an upper
+ * limit to the number of successive tail calls that can be
+ * performed.
+ *
+ * Upon call of this helper, the program attempts to jump into a
+ * program referenced at index *index* in *prog_array_map*, a
+ * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
+ * *ctx*, a pointer to the context.
+ *
+ * If the call succeeds, the kernel immediately runs the first
+ * instruction of the new program. This is not a function call,
+ * and it never returns to the previous program. If the call
+ * fails, then the helper has no effect, and the caller continues
+ * to run its subsequent instructions. A call can fail if the
+ * destination program for the jump does not exist (i.e. *index*
+ * is superior to the number of entries in *prog_array_map*), or
+ * if the maximum number of tail calls has been reached for this
+ * chain of programs. This limit is defined in the kernel by the
+ * macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
+ * which is currently set to 32.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
+ * Description
+ * Clone and redirect the packet associated to *skb* to another
+ * net device of index *ifindex*. Both ingress and egress
+ * interfaces can be used for redirection. The **BPF_F_INGRESS**
+ * value in *flags* is used to make the distinction (ingress path
+ * is selected if the flag is present, egress path otherwise).
+ * This is the only flag supported for now.
+ *
+ * In comparison with **bpf_redirect**\ () helper,
+ * **bpf_clone_redirect**\ () has the associated cost of
+ * duplicating the packet buffer, but this can be executed out of
+ * the eBPF program. Conversely, **bpf_redirect**\ () is more
+ * efficient, but it is handled through an action code where the
+ * redirection happens only after the eBPF program has returned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* u64 bpf_get_current_pid_tgid(void)
- * Return: current->tgid << 32 | current->pid
+ * Return
+ * A 64-bit integer containing the current tgid and pid, and
+ * created as such:
+ * *current_task*\ **->tgid << 32 \|**
+ * *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
- * Return: current_gid << 32 | current_uid
- *
- * int bpf_get_current_comm(char *buf, int size_of_buf)
- * stores current->comm into buf
- * Return: 0 on success or negative error
- *
- * u32 bpf_get_cgroup_classid(skb)
- * retrieve a proc's classid
- * @skb: pointer to skb
- * Return: classid if != 0
- *
- * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
- * Return: 0 on success or negative error
- *
- * int bpf_skb_vlan_pop(skb)
- * Return: 0 on success or negative error
- *
- * int bpf_skb_get_tunnel_key(skb, key, size, flags)
- * int bpf_skb_set_tunnel_key(skb, key, size, flags)
- * retrieve or populate tunnel metadata
- * @skb: pointer to skb
- * @key: pointer to 'struct bpf_tunnel_key'
- * @size: size of 'struct bpf_tunnel_key'
- * @flags: room for future extensions
- * Return: 0 on success or negative error
- *
- * u64 bpf_perf_event_read(map, flags)
- * read perf event counter value
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * Return: value of perf event counter read or error code
- *
- * int bpf_redirect(ifindex, flags)
- * redirect to another netdev
- * @ifindex: ifindex of the net device
- * @flags:
- * cls_bpf:
- * bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * xdp_bpf:
- * all bits - reserved
- * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
- * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
- * int bpf_redirect_map(map, key, flags)
- * redirect to endpoint in map
- * @map: pointer to dev map
- * @key: index in map to lookup
- * @flags: --
- * Return: XDP_REDIRECT on success or XDP_ABORT on error
- *
- * u32 bpf_get_route_realm(skb)
- * retrieve a dst's tclassid
- * @skb: pointer to skb
- * Return: realm if != 0
- *
- * int bpf_perf_event_output(ctx, map, flags, data, size)
- * output perf raw sample
- * @ctx: struct pt_regs*
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * @data: data on stack to be output as raw data
- * @size: size of data
- * Return: 0 on success or negative error
- *
- * int bpf_get_stackid(ctx, map, flags)
- * walk user or kernel stack and return id
- * @ctx: struct pt_regs*
- * @map: pointer to stack_trace map
- * @flags: bits 0-7 - numer of stack frames to skip
- * bit 8 - collect user stack instead of kernel
- * bit 9 - compare stacks by hash only
- * bit 10 - if two different stacks hash into the same stackid
- * discard old
- * other bits - reserved
- * Return: >= 0 stackid on success or negative error
- *
- * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
- * calculate csum diff
- * @from: raw from buffer
- * @from_size: length of from buffer
- * @to: raw to buffer
- * @to_size: length of to buffer
- * @seed: optional seed
- * Return: csum result or negative error code
- *
- * int bpf_skb_get_tunnel_opt(skb, opt, size)
- * retrieve tunnel options metadata
- * @skb: pointer to skb
- * @opt: pointer to raw tunnel option data
- * @size: size of @opt
- * Return: option size
- *
- * int bpf_skb_set_tunnel_opt(skb, opt, size)
- * populate tunnel options metadata
- * @skb: pointer to skb
- * @opt: pointer to raw tunnel option data
- * @size: size of @opt
- * Return: 0 on success or negative error
- *
- * int bpf_skb_change_proto(skb, proto, flags)
- * Change protocol of the skb. Currently supported is v4 -> v6,
- * v6 -> v4 transitions. The helper will also resize the skb. eBPF
- * program is expected to fill the new headers via skb_store_bytes
- * and lX_csum_replace.
- * @skb: pointer to skb
- * @proto: new skb->protocol type
- * @flags: reserved
- * Return: 0 on success or negative error
- *
- * int bpf_skb_change_type(skb, type)
- * Change packet type of skb.
- * @skb: pointer to skb
- * @type: new skb->pkt_type type
- * Return: 0 on success or negative error
- *
- * int bpf_skb_under_cgroup(skb, map, index)
- * Check cgroup2 membership of skb
- * @skb: pointer to skb
- * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
- * @index: index of the cgroup in the bpf_map
- * Return:
- * == 0 skb failed the cgroup2 descendant test
- * == 1 skb succeeded the cgroup2 descendant test
- * < 0 error
- *
- * u32 bpf_get_hash_recalc(skb)
- * Retrieve and possibly recalculate skb->hash.
- * @skb: pointer to skb
- * Return: hash
+ * Return
+ * A 64-bit integer containing the current GID and UID, and
+ * created as such: *current_gid* **<< 32 \|** *current_uid*.
+ *
+ * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * Description
+ * Copy the **comm** attribute of the current task into *buf* of
+ * *size_of_buf*. The **comm** attribute contains the name of
+ * the executable (excluding the path) for the current task. The
+ * *size_of_buf* must be strictly positive. On success, the
+ * helper makes sure that the *buf* is NUL-terminated. On failure,
+ * it is filled with zeroes.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u32 bpf_get_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * Retrieve the classid for the current task, i.e. for the net_cls
+ * cgroup to which *skb* belongs.
+ *
+ * This helper can be used on TC egress path, but not on ingress.
+ *
+ * The net_cls cgroup provides an interface to tag network packets
+ * based on a user-provided identifier for all traffic coming from
+ * the tasks belonging to the related cgroup. See also the related
+ * kernel documentation, available from the Linux sources in file
+ * *Documentation/cgroup-v1/net_cls.txt*.
+ *
+ * The Linux kernel has two versions for cgroups: there are
+ * cgroups v1 and cgroups v2. Both are available to users, who can
+ * use a mixture of them, but note that the net_cls cgroup is for
+ * cgroup v1 only. This makes it incompatible with BPF programs
+ * run on cgroups, which is a cgroup-v2-only feature (a socket can
+ * only hold data for one version of cgroups at a time).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to
+ * "**y**" or to "**m**".
+ * Return
+ * The classid, or 0 for the default unconfigured classid.
+ *
+ * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+ * Description
+ * Push a *vlan_tci* (VLAN tag control information) of protocol
+ * *vlan_proto* to the packet associated to *skb*, then update
+ * the checksum. Note that if *vlan_proto* is different from
+ * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
+ * be **ETH_P_8021Q**.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_vlan_pop(struct sk_buff *skb)
+ * Description
+ * Pop a VLAN header from the packet associated to *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Get tunnel metadata. This helper takes a pointer *key* to an
+ * empty **struct bpf_tunnel_key** of **size**, that will be
+ * filled with tunnel metadata for the packet associated to *skb*.
+ * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
+ * indicates that the tunnel is based on IPv6 protocol instead of
+ * IPv4.
+ *
+ * The **struct bpf_tunnel_key** is an object that generalizes the
+ * principal parameters used by various tunneling protocols into a
+ * single struct. This way, it can be used to easily make a
+ * decision based on the contents of the encapsulation header,
+ * "summarized" in this struct. In particular, it holds the IP
+ * address of the remote end (IPv4 or IPv6, depending on the case)
+ * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
+ * this struct exposes the *key*\ **->tunnel_id**, which is
+ * generally mapped to a VNI (Virtual Network Identifier), making
+ * it programmable together with the **bpf_skb_set_tunnel_key**\
+ * () helper.
+ *
+ * Let's imagine that the following code is part of a program
+ * attached to the TC ingress interface, on one end of a GRE
+ * tunnel, and is supposed to filter out all messages coming from
+ * remote ends with IPv4 address other than 10.0.0.1:
+ *
+ * ::
+ *
+ * int ret;
+ * struct bpf_tunnel_key key = {};
+ *
+ * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ * if (ret < 0)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * if (key.remote_ipv4 != 0x0a000001)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * return TC_ACT_OK; // accept packet
+ *
+ * This interface can also be used with all encapsulation devices
+ * that can operate in "collect metadata" mode: instead of having
+ * one network device per specific configuration, the "collect
+ * metadata" mode only requires a single device where the
+ * configuration can be extracted from this helper.
+ *
+ * This can be used together with various tunnels such as VXLan,
+ * Geneve, GRE or IP in IP (IPIP).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Populate tunnel metadata for packet associated to *skb.* The
+ * tunnel metadata is set to the contents of *key*, of *size*. The
+ * *flags* can be set to a combination of the following values:
+ *
+ * **BPF_F_TUNINFO_IPV6**
+ * Indicate that the tunnel is based on IPv6 protocol
+ * instead of IPv4.
+ * **BPF_F_ZERO_CSUM_TX**
+ * For IPv4 packets, add a flag to tunnel metadata
+ * indicating that checksum computation should be skipped
+ * and checksum set to zeroes.
+ * **BPF_F_DONT_FRAGMENT**
+ * Add a flag to tunnel metadata indicating that the
+ * packet should not be fragmented.
+ * **BPF_F_SEQ_NUMBER**
+ * Add a flag to tunnel metadata indicating that a
+ * sequence number should be added to tunnel header before
+ * sending the packet. This flag was added for GRE
+ * encapsulation, but might be used with other protocols
+ * as well in the future.
+ *
+ * Here is a typical usage on the transmit path:
+ *
+ * ::
+ *
+ * struct bpf_tunnel_key key;
+ * populate key ...
+ * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
+ *
+ * See also the description of the **bpf_skb_get_tunnel_key**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags)
+ * Description
+ * Read the value of a perf event counter. This helper relies on a
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of
+ * the perf event counter is selected when *map* is updated with
+ * perf event file descriptors. The *map* is an array whose size
+ * is the number of available CPUs, and each cell contains a value
+ * relative to one CPU. The value to retrieve is indicated by
+ * *flags*, that contains the index of the CPU to look up, masked
+ * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * Note that before Linux 4.13, only hardware perf event can be
+ * retrieved.
+ *
+ * Also, be aware that the newer helper
+ * **bpf_perf_event_read_value**\ () is recommended over
+ * **bpf_perf_event_read**\ () in general. The latter has some ABI
+ * quirks where error and counter value are used as a return code
+ * (which is wrong to do since ranges may overlap). This issue is
+ * fixed with **bpf_perf_event_read_value**\ (), which at the same
+ * time provides more features over the **bpf_perf_event_read**\
+ * () interface. Please refer to the description of
+ * **bpf_perf_event_read_value**\ () for details.
+ * Return
+ * The value of the perf event counter read from the map, or a
+ * negative error code in case of failure.
+ *
+ * int bpf_redirect(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_clone_redirect**\
+ * (), except that the packet is not cloned, which provides
+ * increased performance.
+ *
+ * Except for XDP, both ingress and egress interfaces can be used
+ * for redirection. The **BPF_F_INGRESS** value in *flags* is used
+ * to make the distinction (ingress path is selected if the flag
+ * is present, egress path otherwise). Currently, XDP only
+ * supports redirection to the egress interface, and accepts no
+ * flag at all.
+ *
+ * The same effect can be attained with the more generic
+ * **bpf_redirect_map**\ (), which requires specific maps to be
+ * used but offers better performance.
+ * Return
+ * For XDP, the helper returns **XDP_REDIRECT** on success or
+ * **XDP_ABORTED** on error. For other program types, the values
+ * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on
+ * error.
+ *
+ * u32 bpf_get_route_realm(struct sk_buff *skb)
+ * Description
+ * Retrieve the realm or the route, that is to say the
+ * **tclassid** field of the destination for the *skb*. The
+ * indentifier retrieved is a user-provided tag, similar to the
+ * one used with the net_cls cgroup (see description for
+ * **bpf_get_cgroup_classid**\ () helper), but here this tag is
+ * held by a route (a destination entry), not by a task.
+ *
+ * Retrieving this identifier works with the clsact TC egress hook
+ * (see also **tc-bpf(8)**), or alternatively on conventional
+ * classful egress qdiscs, but not on TC ingress path. In case of
+ * clsact TC egress hook, this has the advantage that, internally,
+ * the destination entry has not been dropped yet in the transmit
+ * path. Therefore, the destination entry does not need to be
+ * artificially held via **netif_keep_dst**\ () for a classful
+ * qdisc until the *skb* is freed.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_IP_ROUTE_CLASSID** configuration option.
+ * Return
+ * The realm of the route for the packet associated to *skb*, or 0
+ * if none was found.
+ *
+ * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * The context of the program *ctx* needs also be passed to the
+ * helper.
+ *
+ * On user space, a program willing to read the values needs to
+ * call **perf_event_open**\ () on the perf event (either for
+ * one or for all CPUs) and to store the file descriptor into the
+ * *map*. This must be done before the eBPF program can send data
+ * into it. An example is available in file
+ * *samples/bpf/trace_output_user.c* in the Linux kernel source
+ * tree (the eBPF program counterpart is in
+ * *samples/bpf/trace_output_kern.c*).
+ *
+ * **bpf_perf_event_output**\ () achieves better performance
+ * than **bpf_trace_printk**\ () for sharing data with user
+ * space, and is much better suitable for streaming data from eBPF
+ * programs.
+ *
+ * Note that this helper is not restricted to tracing use cases
+ * and can be used with programs attached to TC or XDP as well,
+ * where it allows for passing data to user space listeners. Data
+ * can be:
+ *
+ * * Only custom structs,
+ * * Only the packet payload, or
+ * * A combination of both.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * Description
+ * This helper was provided as an easy way to load data from a
+ * packet. It can be used to load *len* bytes from *offset* from
+ * the packet associated to *skb*, into the buffer pointed by
+ * *to*.
+ *
+ * Since Linux 4.7, usage of this helper has mostly been replaced
+ * by "direct packet access", enabling packet data to be
+ * manipulated with *skb*\ **->data** and *skb*\ **->data_end**
+ * pointing respectively to the first byte of packet data and to
+ * the byte after the last byte of packet data. However, it
+ * remains useful if one wishes to read large quantities of data
+ * at once from a packet into the eBPF stack.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
+ * Description
+ * Walk a user or a kernel stack and return its id. To achieve
+ * this, the helper needs *ctx*, which is a pointer to the context
+ * on which the tracing program is executed, and a pointer to a
+ * *map* of type **BPF_MAP_TYPE_STACK_TRACE**.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * a combination of the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_FAST_STACK_CMP**
+ * Compare stacks by hash only.
+ * **BPF_F_REUSE_STACKID**
+ * If two different stacks hash into the same *stackid*,
+ * discard the old one.
+ *
+ * The stack id retrieved is a 32 bit long integer handle which
+ * can be further combined with other data (including other stack
+ * ids) and used as a key into maps. This can be useful for
+ * generating a variety of graphs (such as flame graphs or off-cpu
+ * graphs).
+ *
+ * For walking a stack, this helper is an improvement over
+ * **bpf_probe_read**\ (), which can be used with unrolled loops
+ * but is not efficient and consumes a lot of eBPF instructions.
+ * Instead, **bpf_get_stackid**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * Return
+ * The positive or null stack id on success, or a negative error
+ * in case of failure.
+ *
+ * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed)
+ * Description
+ * Compute a checksum difference, from the raw buffer pointed by
+ * *from*, of length *from_size* (that must be a multiple of 4),
+ * towards the raw buffer pointed by *to*, of size *to_size*
+ * (same remark). An optional *seed* can be added to the value
+ * (this can be cascaded, the seed may come from a previous call
+ * to the helper).
+ *
+ * This is flexible enough to be used in several ways:
+ *
+ * * With *from_size* == 0, *to_size* > 0 and *seed* set to
+ * checksum, it can be used when pushing new data.
+ * * With *from_size* > 0, *to_size* == 0 and *seed* set to
+ * checksum, it can be used when removing data from a packet.
+ * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it
+ * can be used to compute a diff. Note that *from_size* and
+ * *to_size* do not need to be equal.
+ *
+ * This helper can be used in combination with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to
+ * which one can feed in the difference computed with
+ * **bpf_csum_diff**\ ().
+ * Return
+ * The checksum result, or a negative error code in case of
+ * failure.
+ *
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Retrieve tunnel options metadata for the packet associated to
+ * *skb*, and store the raw tunnel option data to the buffer *opt*
+ * of *size*.
+ *
+ * This helper can be used with encapsulation devices that can
+ * operate in "collect metadata" mode (please refer to the related
+ * note in the description of **bpf_skb_get_tunnel_key**\ () for
+ * more details). A particular example where this can be used is
+ * in combination with the Geneve encapsulation protocol, where it
+ * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper)
+ * and retrieving arbitrary TLVs (Type-Length-Value headers) from
+ * the eBPF program. This allows for full customization of these
+ * headers.
+ * Return
+ * The size of the option data retrieved.
+ *
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * Description
+ * Set tunnel options metadata for the packet associated to *skb*
+ * to the option data contained in the raw buffer *opt* of *size*.
+ *
+ * See also the description of the **bpf_skb_get_tunnel_opt**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
+ * Description
+ * Change the protocol of the *skb* to *proto*. Currently
+ * supported are transition from IPv4 to IPv6, and from IPv6 to
+ * IPv4. The helper takes care of the groundwork for the
+ * transition, including resizing the socket buffer. The eBPF
+ * program is expected to fill the new headers, if any, via
+ * **skb_store_bytes**\ () and to recompute the checksums with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\
+ * (). The main case for this helper is to perform NAT64
+ * operations out of an eBPF program.
+ *
+ * Internally, the GSO type is marked as dodgy so that headers are
+ * checked and segments are recalculated by the GSO/GRO engine.
+ * The size for GSO target is adapted as well.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_change_type(struct sk_buff *skb, u32 type)
+ * Description
+ * Change the packet type for the packet associated to *skb*. This
+ * comes down to setting *skb*\ **->pkt_type** to *type*, except
+ * the eBPF program does not have a write access to *skb*\
+ * **->pkt_type** beside this helper. Using a helper here allows
+ * for graceful handling of errors.
+ *
+ * The major use case is to change incoming *skb*s to
+ * **PACKET_HOST** in a programmatic way instead of having to
+ * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for
+ * example.
+ *
+ * Note that *type* only allows certain values. At this time, they
+ * are:
+ *
+ * **PACKET_HOST**
+ * Packet is for us.
+ * **PACKET_BROADCAST**
+ * Send packet to all.
+ * **PACKET_MULTICAST**
+ * Send packet to group.
+ * **PACKET_OTHERHOST**
+ * Send packet to someone else.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
+ * Description
+ * Check whether *skb* is a descendant of the cgroup2 held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* failed the cgroup2 descendant test.
+ * * 1, if the *skb* succeeded the cgroup2 descendant test.
+ * * A negative error code, if an error occurred.
+ *
+ * u32 bpf_get_hash_recalc(struct sk_buff *skb)
+ * Description
+ * Retrieve the hash of the packet, *skb*\ **->hash**. If it is
+ * not set, in particular if the hash was cleared due to mangling,
+ * recompute this hash. Later accesses to the hash can be done
+ * directly with *skb*\ **->hash**.
+ *
+ * Calling **bpf_set_hash_invalid**\ (), changing a packet
+ * prototype with **bpf_skb_change_proto**\ (), or calling
+ * **bpf_skb_store_bytes**\ () with the
+ * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear
+ * the hash and to trigger a new computation for the next call to
+ * **bpf_get_hash_recalc**\ ().
+ * Return
+ * The 32-bit hash.
*
* u64 bpf_get_current_task(void)
- * Returns current task_struct
- * Return: current
- *
- * int bpf_probe_write_user(void *dst, void *src, int len)
- * safely attempt to write to a location
- * @dst: destination address in userspace
- * @src: source address on stack
- * @len: number of bytes to copy
- * Return: 0 on success or negative error
- *
- * int bpf_current_task_under_cgroup(map, index)
- * Check cgroup2 membership of current task
- * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
- * @index: index of the cgroup in the bpf_map
- * Return:
- * == 0 current failed the cgroup2 descendant test
- * == 1 current succeeded the cgroup2 descendant test
- * < 0 error
- *
- * int bpf_skb_change_tail(skb, len, flags)
- * The helper will resize the skb to the given new size, to be used f.e.
- * with control messages.
- * @skb: pointer to skb
- * @len: new skb length
- * @flags: reserved
- * Return: 0 on success or negative error
- *
- * int bpf_skb_pull_data(skb, len)
- * The helper will pull in non-linear data in case the skb is non-linear
- * and not all of len are part of the linear section. Only needed for
- * read/write with direct packet access.
- * @skb: pointer to skb
- * @len: len to make read/writeable
- * Return: 0 on success or negative error
- *
- * s64 bpf_csum_update(skb, csum)
- * Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
- * @skb: pointer to skb
- * @csum: csum to add
- * Return: csum on success or negative error
- *
- * void bpf_set_hash_invalid(skb)
- * Invalidate current skb->hash.
- * @skb: pointer to skb
- *
- * int bpf_get_numa_node_id()
- * Return: Id of current NUMA node.
- *
- * int bpf_skb_change_head()
- * Grows headroom of skb and adjusts MAC header offset accordingly.
- * Will extends/reallocae as required automatically.
- * May change skb data pointer and will thus invalidate any check
- * performed for direct packet access.
- * @skb: pointer to skb
- * @len: length of header to be pushed in front
- * @flags: Flags (unused for now)
- * Return: 0 on success or negative error
- *
- * int bpf_xdp_adjust_head(xdp_md, delta)
- * Adjust the xdp_md.data by delta
- * @xdp_md: pointer to xdp_md
- * @delta: An positive/negative integer to be added to xdp_md.data
- * Return: 0 on success or negative on error
+ * Return
+ * A pointer to the current task struct.
+ *
+ * int bpf_probe_write_user(void *dst, const void *src, u32 len)
+ * Description
+ * Attempt in a safe way to write *len* bytes from the buffer
+ * *src* to *dst* in memory. It only works for threads that are in
+ * user context, and *dst* must be a valid user space address.
+ *
+ * This helper should not be used to implement any kind of
+ * security mechanism because of TOC-TOU attacks, but rather to
+ * debug, divert, and manipulate execution of semi-cooperative
+ * processes.
+ *
+ * Keep in mind that this feature is meant for experiments, and it
+ * has a risk of crashing the system and running programs.
+ * Therefore, when an eBPF program using this helper is attached,
+ * a warning including PID and process name is printed to kernel
+ * logs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
+ * Description
+ * Check whether the probe is being run is the context of a given
+ * subset of the cgroup2 hierarchy. The cgroup2 to test is held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* task belongs to the cgroup2.
+ * * 1, if the *skb* task does not belong to the cgroup2.
+ * * A negative error code, if an error occurred.
+ *
+ * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Resize (trim or grow) the packet associated to *skb* to the
+ * new *len*. The *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * The basic idea is that the helper performs the needed work to
+ * change the size of the packet, then the eBPF program rewrites
+ * the rest via helpers like **bpf_skb_store_bytes**\ (),
+ * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ ()
+ * and others. This helper is a slow path utility intended for
+ * replies with control messages. And because it is targeted for
+ * slow path, the helper itself can afford to be slow: it
+ * implicitly linearizes, unclones and drops offloads from the
+ * *skb*.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_pull_data(struct sk_buff *skb, u32 len)
+ * Description
+ * Pull in non-linear data in case the *skb* is non-linear and not
+ * all of *len* are part of the linear section. Make *len* bytes
+ * from *skb* readable and writable. If a zero value is passed for
+ * *len*, then the whole length of the *skb* is pulled.
+ *
+ * This helper is only needed for reading and writing with direct
+ * packet access.
+ *
+ * For direct packet access, testing that offsets to access
+ * are within packet boundaries (test on *skb*\ **->data_end**) is
+ * susceptible to fail if offsets are invalid, or if the requested
+ * data is in non-linear parts of the *skb*. On failure the
+ * program can just bail out, or in the case of a non-linear
+ * buffer, use a helper to make the data available. The
+ * **bpf_skb_load_bytes**\ () helper is a first solution to access
+ * the data. Another one consists in using **bpf_skb_pull_data**
+ * to pull in once the non-linear parts, then retesting and
+ * eventually access the data.
+ *
+ * At the same time, this also makes sure the *skb* is uncloned,
+ * which is a necessary condition for direct write. As this needs
+ * to be an invariant for the write part only, the verifier
+ * detects writes and adds a prologue that is calling
+ * **bpf_skb_pull_data()** to effectively unclone the *skb* from
+ * the very beginning in case it is indeed cloned.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum)
+ * Description
+ * Add the checksum *csum* into *skb*\ **->csum** in case the
+ * driver has supplied a checksum for the entire packet into that
+ * field. Return an error otherwise. This helper is intended to be
+ * used in combination with **bpf_csum_diff**\ (), in particular
+ * when the checksum needs to be updated after data has been
+ * written into the packet through direct packet access.
+ * Return
+ * The checksum on success, or a negative error code in case of
+ * failure.
+ *
+ * void bpf_set_hash_invalid(struct sk_buff *skb)
+ * Description
+ * Invalidate the current *skb*\ **->hash**. It can be used after
+ * mangling on headers through direct packet access, in order to
+ * indicate that the hash is outdated and to trigger a
+ * recalculation the next time the kernel tries to access this
+ * hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ *
+ * int bpf_get_numa_node_id(void)
+ * Description
+ * Return the id of the current NUMA node. The primary use case
+ * for this helper is the selection of sockets for the local NUMA
+ * node, when the program is attached to sockets using the
+ * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**),
+ * but the helper is also available to other eBPF program types,
+ * similarly to **bpf_get_smp_processor_id**\ ().
+ * Return
+ * The id of current NUMA node.
+ *
+ * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Grows headroom of packet associated to *skb* and adjusts the
+ * offset of the MAC header accordingly, adding *len* bytes of
+ * space. It automatically extends and reallocates memory as
+ * required.
+ *
+ * This helper can be used on a layer 3 *skb* to push a MAC header
+ * for redirection into a layer 2 device.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that
+ * it is possible to use a negative value for *delta*. This helper
+ * can be used to prepare the packet for pushing or popping
+ * headers.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*
* int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
- * Copy a NUL terminated string from unsafe address. In case the string
- * length is smaller than size, the target is not padded with further NUL
- * bytes. In case the string length is larger than size, just count-1
- * bytes are copied and the last byte is set to NUL.
- * @dst: destination address
- * @size: maximum number of bytes to copy, including the trailing NUL
- * @unsafe_ptr: unsafe address
- * Return:
- * > 0 length of the string including the trailing NUL on success
- * < 0 error
- *
- * u64 bpf_get_socket_cookie(skb)
- * Get the cookie for the socket stored inside sk_buff.
- * @skb: pointer to skb
- * Return: 8 Bytes non-decreasing number on success or 0 if the socket
- * field is missing inside sk_buff
- *
- * u32 bpf_get_socket_uid(skb)
- * Get the owner uid of the socket stored inside sk_buff.
- * @skb: pointer to skb
- * Return: uid of the socket owner on success or overflowuid if failed.
- *
- * u32 bpf_set_hash(skb, hash)
- * Set full skb->hash.
- * @skb: pointer to skb
- * @hash: hash to set
- *
- * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
- * Calls setsockopt. Not all opts are available, only those with
- * integer optvals plus TCP_CONGESTION.
- * Supported levels: SOL_SOCKET and IPPROTO_TCP
- * @bpf_socket: pointer to bpf_socket
- * @level: SOL_SOCKET or IPPROTO_TCP
- * @optname: option name
- * @optval: pointer to option value
- * @optlen: length of optval in bytes
- * Return: 0 or negative error
- *
- * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
- * Calls getsockopt. Not all opts are available.
- * Supported levels: IPPROTO_TCP
- * @bpf_socket: pointer to bpf_socket
- * @level: IPPROTO_TCP
- * @optname: option name
- * @optval: pointer to option value
- * @optlen: length of optval in bytes
- * Return: 0 or negative error
- *
- * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
- * Set callback flags for sock_ops
- * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
- * @flags: flags value
- * Return: 0 for no error
- * -EINVAL if there is no full tcp socket
- * bits in flags that are not supported by current kernel
- *
- * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
- * Grow or shrink room in sk_buff.
- * @skb: pointer to skb
- * @len_diff: (signed) amount of room to grow/shrink
- * @mode: operation mode (enum bpf_adj_room_mode)
- * @flags: reserved for future use
- * Return: 0 on success or negative error code
- *
- * int bpf_sk_redirect_map(map, key, flags)
- * Redirect skb to a sock in map using key as a lookup key for the
- * sock in map.
- * @map: pointer to sockmap
- * @key: key to lookup sock in map
- * @flags: reserved for future use
- * Return: SK_PASS
- *
- * int bpf_sock_map_update(skops, map, key, flags)
- * @skops: pointer to bpf_sock_ops
- * @map: pointer to sockmap to update
- * @key: key to insert/update sock in map
- * @flags: same flags as map update elem
- *
- * int bpf_xdp_adjust_meta(xdp_md, delta)
- * Adjust the xdp_md.data_meta by delta
- * @xdp_md: pointer to xdp_md
- * @delta: An positive/negative integer to be added to xdp_md.data_meta
- * Return: 0 on success or negative on error
- *
- * int bpf_perf_event_read_value(map, flags, buf, buf_size)
- * read perf event counter value and perf event enabled/running time
- * @map: pointer to perf_event_array map
- * @flags: index of event in the map or bitmask flags
- * @buf: buf to fill
- * @buf_size: size of the buf
- * Return: 0 on success or negative error code
- *
- * int bpf_perf_prog_read_value(ctx, buf, buf_size)
- * read perf prog attached perf event counter and enabled/running time
- * @ctx: pointer to ctx
- * @buf: buf to fill
- * @buf_size: size of the buf
- * Return : 0 on success or negative error code
- *
- * int bpf_override_return(pt_regs, rc)
- * @pt_regs: pointer to struct pt_regs
- * @rc: the return value to set
- *
- * int bpf_msg_redirect_map(map, key, flags)
- * Redirect msg to a sock in map using key as a lookup key for the
- * sock in map.
- * @map: pointer to sockmap
- * @key: key to lookup sock in map
- * @flags: reserved for future use
- * Return: SK_PASS
- *
- * int bpf_bind(ctx, addr, addr_len)
- * Bind socket to address. Only binding to IP is supported, no port can be
- * set in addr.
- * @ctx: pointer to context of type bpf_sock_addr
- * @addr: pointer to struct sockaddr to bind socket to
- * @addr_len: length of sockaddr structure
- * Return: 0 on success or negative error code
- *
- * int bpf_xdp_adjust_tail(xdp_md, delta)
- * Adjust the xdp_md.data_end by delta. Only shrinking of packet's
- * size is supported.
- * @xdp_md: pointer to xdp_md
- * @delta: A negative integer to be added to xdp_md.data_end
- * Return: 0 on success or negative on error
+ * Description
+ * Copy a NUL terminated string from an unsafe address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read()** helper here instead
+ * to read the string would require to estimate the length at
+ * compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * u64 bpf_get_socket_cookie(struct sk_buff *skb)
+ * Description
+ * If the **struct sk_buff** pointed by *skb* has a known socket,
+ * retrieve the cookie (generated by the kernel) of this socket.
+ * If no cookie has been set yet, generate a new cookie. Once
+ * generated, the socket cookie remains stable for the life of the
+ * socket. This helper can be useful for monitoring per socket
+ * networking traffic statistics as it provides a unique socket
+ * identifier per namespace.
+ * Return
+ * A 8-byte long non-decreasing number on success, or 0 if the
+ * socket field is missing inside *skb*.
+ *
+ * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Return
+ * The owner UID of the socket associated to *skb*. If the socket
+ * is **NULL**, or if it is not a full socket (i.e. if it is a
+ * time-wait or a request socket instead), **overflowuid** value
+ * is returned (note that **overflowuid** might also be the actual
+ * UID value for the socket).
+ *
+ * u32 bpf_set_hash(struct sk_buff *skb, u32 hash)
+ * Description
+ * Set the full hash for *skb* (set the field *skb*\ **->hash**)
+ * to value *hash*.
+ * Return
+ * 0
+ *
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **setsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **setsockopt(2)** for more information.
+ * The option value of length *optlen* is pointed by *optval*.
+ *
+ * This helper actually implements a subset of **setsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **SOL_SOCKET**, which supports the following *optname*\ s:
+ * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
+ * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**.
+ * * **IPPROTO_TCP**, which supports the following *optname*\ s:
+ * **TCP_CONGESTION**, **TCP_BPF_IW**,
+ * **TCP_BPF_SNDCWND_CLAMP**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * Description
+ * Grow or shrink the room for data in the packet associated to
+ * *skb* by *len_diff*, and according to the selected *mode*.
+ *
+ * There is a single supported mode at this time:
+ *
+ * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
+ * (room space is added or removed below the layer 3 header).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the endpoint referenced by *map* at
+ * index *key*. Depending on its type, this *map* can contain
+ * references to net devices (for forwarding packets through other
+ * ports), or to CPUs (for redirecting XDP frames to another CPU;
+ * but this is only implemented for native XDP (with driver
+ * support) as of this writing).
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * When used to redirect packets to net devices, this helper
+ * provides a high performance increase over **bpf_redirect**\ ().
+ * This is due to various implementation details of the underlying
+ * mechanisms, one of which is the fact that **bpf_redirect_map**\
+ * () tries to send packet as a "bulk" to the device.
+ * Return
+ * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ *
+ * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a *map* referencing sockets. The
+ * *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust the address pointed by *xdp_md*\ **->data_meta** by
+ * *delta* (which can be positive or negative). Note that this
+ * operation modifies the address stored in *xdp_md*\ **->data**,
+ * so the latter must be loaded only after the helper has been
+ * called.
+ *
+ * The use of *xdp_md*\ **->data_meta** is optional and programs
+ * are not required to use it. The rationale is that when the
+ * packet is processed with XDP (e.g. as DoS filter), it is
+ * possible to push further meta data along with it before passing
+ * to the stack, and to give the guarantee that an ingress eBPF
+ * program attached as a TC classifier on the same device can pick
+ * this up for further post-processing. Since TC works with socket
+ * buffers, it remains possible to set from XDP the **mark** or
+ * **priority** pointers, or other pointers for the socket buffer.
+ * Having this scratch space generic and programmable allows for
+ * more flexibility as the user is free to store whatever meta
+ * data they need.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * Read the value of a perf event counter, and store it into *buf*
+ * of size *buf_size*. This helper relies on a *map* of type
+ * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event
+ * counter is selected when *map* is updated with perf event file
+ * descriptors. The *map* is an array whose size is the number of
+ * available CPUs, and each cell contains a value relative to one
+ * CPU. The value to retrieve is indicated by *flags*, that
+ * contains the index of the CPU to look up, masked with
+ * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * This helper behaves in a way close to
+ * **bpf_perf_event_read**\ () helper, save that instead of
+ * just returning the value observed, it fills the *buf*
+ * structure. This allows for additional data to be retrieved: in
+ * particular, the enabled and running times (in *buf*\
+ * **->enabled** and *buf*\ **->running**, respectively) are
+ * copied. In general, **bpf_perf_event_read_value**\ () is
+ * recommended over **bpf_perf_event_read**\ (), which has some
+ * ABI issues and provides fewer functionalities.
+ *
+ * These values are interesting, because hardware PMU (Performance
+ * Monitoring Unit) counters are limited resources. When there are
+ * more PMU based perf events opened than available counters,
+ * kernel will multiplex these events so each event gets certain
+ * percentage (but not all) of the PMU time. In case that
+ * multiplexing happens, the number of samples or counter value
+ * will not reflect the case compared to when no multiplexing
+ * occurs. This makes comparison between different runs difficult.
+ * Typically, the counter value should be normalized before
+ * comparing to other experiments. The usual normalization is done
+ * as follows.
+ *
+ * ::
+ *
+ * normalized_counter = counter * t_enabled / t_running
+ *
+ * Where t_enabled is the time enabled for event and t_running is
+ * the time running for event since last normalization. The
+ * enabled and running times are accumulated since the perf event
+ * open. To achieve scaling factor between two invocations of an
+ * eBPF program, users can can use CPU id as the key (which is
+ * typical for perf array usage model) to remember the previous
+ * value and do the calculation inside the eBPF program.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * For en eBPF program attached to a perf event, retrieve the
+ * value of the event counter associated to *ctx* and store it in
+ * the structure pointed by *buf* and of size *buf_size*. Enabled
+ * and running times are also stored in the structure (see
+ * description of helper **bpf_perf_event_read_value**\ () for
+ * more details).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * Description
+ * Emulate a call to **getsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **getsockopt(2)** for more information.
+ * The retrieved value is stored in the structure pointed by
+ * *opval* and of length *optlen*.
+ *
+ * This helper actually implements a subset of **getsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **IPPROTO_TCP**, which supports *optname*
+ * **TCP_CONGESTION**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_override_return(struct pt_reg *regs, u64 rc)
+ * Description
+ * Used for error injection, this helper uses kprobes to override
+ * the return value of the probed function, and to set it to *rc*.
+ * The first argument is the context *regs* on which the kprobe
+ * works.
+ *
+ * This helper works by setting setting the PC (program counter)
+ * to an override function which is run in place of the original
+ * probed function. This means the probed function is not run at
+ * all. The replacement function just returns with the required
+ * value.
+ *
+ * This helper has security implications, and thus is subject to
+ * restrictions. It is only available if the kernel was compiled
+ * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
+ * option, and in this case it only works on functions tagged with
+ * **ALLOW_ERROR_INJECTION** in the kernel code.
+ *
+ * Also, the helper is only available for the architectures having
+ * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
+ * x86 architecture is the only one to support this feature.
+ * Return
+ * 0
+ *
+ * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
+ * Description
+ * Attempt to set the value of the **bpf_sock_ops_cb_flags** field
+ * for the full TCP socket associated to *bpf_sock_ops* to
+ * *argval*.
+ *
+ * The primary use of this field is to determine if there should
+ * be calls to eBPF programs of type
+ * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP
+ * code. A program of the same type can change its value, per
+ * connection and as necessary, when the connection is
+ * established. This field is directly accessible for reading, but
+ * this helper must be used for updates in order to return an
+ * error if an eBPF program tries to set a callback that is not
+ * supported in the current kernel.
+ *
+ * The supported callback values that *argval* can combine are:
+ *
+ * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
+ * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
+ * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ *
+ * Here are some examples of where one could call such eBPF
+ * program:
+ *
+ * * When RTO fires.
+ * * When a packet is retransmitted.
+ * * When the connection terminates.
+ * * When a packet is sent.
+ * * When a packet is received.
+ * Return
+ * Code **-EINVAL** if the socket is not a full TCP socket;
+ * otherwise, a positive number containing the bits that could not
+ * be set is returned (which comes down to 0 if all bits were set
+ * as required).
+ *
+ * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, apply the verdict of the eBPF program to
+ * the next *bytes* (number of bytes) of message *msg*.
+ *
+ * For example, this helper can be used in the following cases:
+ *
+ * * A single **sendmsg**\ () or **sendfile**\ () system call
+ * contains multiple logical messages that the eBPF program is
+ * supposed to read and for which it should apply a verdict.
+ * * An eBPF program only cares to read the first *bytes* of a
+ * *msg*. If the message has a large payload, then setting up
+ * and calling the eBPF program repeatedly for all bytes, even
+ * though the verdict is already known, would create unnecessary
+ * overhead.
+ *
+ * When called from within an eBPF program, the helper sets a
+ * counter internal to the BPF infrastructure, that is used to
+ * apply the last verdict to the next *bytes*. If *bytes* is
+ * smaller than the current data being processed from a
+ * **sendmsg**\ () or **sendfile**\ () system call, the first
+ * *bytes* will be sent and the eBPF program will be re-run with
+ * the pointer for start of data pointing to byte number *bytes*
+ * **+ 1**. If *bytes* is larger than the current data being
+ * processed, then the eBPF verdict will be applied to multiple
+ * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are
+ * consumed.
+ *
+ * Note that if a socket closes with the internal counter holding
+ * a non-zero value, this is not a problem because data is not
+ * being buffered for *bytes* and is sent as it is received.
+ * Return
+ * 0
+ *
+ * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, prevent the execution of the verdict eBPF
+ * program for message *msg* until *bytes* (byte number) have been
+ * accumulated.
+ *
+ * This can be used when one needs a specific number of bytes
+ * before a verdict can be assigned, even if the data spans
+ * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme
+ * case would be a user calling **sendmsg**\ () repeatedly with
+ * 1-byte long message segments. Obviously, this is bad for
+ * performance, but it is still valid. If the eBPF program needs
+ * *bytes* bytes to validate a header, this helper can be used to
+ * prevent the eBPF program to be called again until *bytes* have
+ * been accumulated.
+ * Return
+ * 0
+ *
+ * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+ * Description
+ * For socket policies, pull in non-linear data from user space
+ * for *msg* and set pointers *msg*\ **->data** and *msg*\
+ * **->data_end** to *start* and *end* bytes offsets into *msg*,
+ * respectively.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it can only parse data that the (**data**, **data_end**)
+ * pointers have already consumed. For **sendmsg**\ () hooks this
+ * is likely the first scatterlist element. But for calls relying
+ * on the **sendpage** handler (e.g. **sendfile**\ ()) this will
+ * be the range (**0**, **0**) because the data is shared with
+ * user space and by default the objective is to avoid allowing
+ * user space to modify data while (or after) eBPF verdict is
+ * being decided. This helper can be used to pull in data and to
+ * set the start and end pointer to given values. Data will be
+ * copied if necessary (i.e. if data was not linear and if start
+ * and end pointers do not point to the same chunk).
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
+ * Description
+ * Bind the socket associated to *ctx* to the address pointed by
+ * *addr*, of length *addr_len*. This allows for making outgoing
+ * connection from the desired IP address, which can be useful for
+ * example when all processes inside a cgroup should use one
+ * single IP address on a host that has multiple IP configured.
+ *
+ * This helper works for IPv4 and IPv6, TCP and UDP sockets. The
+ * domain (*addr*\ **->sa_family**) must be **AF_INET** (or
+ * **AF_INET6**). Looking for a free port to bind to can be
+ * expensive, therefore binding to port is not permitted by the
+ * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
+ * must be set to zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
+ * only possible to shrink the packet as of this writing,
+ * therefore *delta* must be a negative integer.
+ *
+ * A call to this helper is susceptible to change the underlaying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
+ * Description
+ * Retrieve the XFRM state (IP transform framework, see also
+ * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*.
+ *
+ * The retrieved value is stored in the **struct bpf_xfrm_state**
+ * pointed by *xfrm_state* and of length *size*.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_XFRM** configuration option.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * To achieve this, the helper needs *ctx*, which is a pointer
+ * to the context on which the tracing program is executed.
+ * To store the stacktrace, the bpf program provides *buf* with
+ * a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect buildid+offset instead of ips for user stack,
+ * only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * **bpf_get_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * Return
+ * a non-negative value equal to or less than size on success, or
+ * a negative error in case of failure.
+ *
+ * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * Description
+ * This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * it provides an easy way to load *len* bytes from *offset*
+ * from the packet associated to *skb*, into the buffer pointed
+ * by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * a fifth argument *start_header* exists in order to select a
+ * base offset to start from. *start_header* can be one of:
+ *
+ * **BPF_HDR_START_MAC**
+ * Base offset to load data from is *skb*'s mac header.
+ * **BPF_HDR_START_NET**
+ * Base offset to load data from is *skb*'s network header.
+ *
+ * In general, "direct packet access" is the preferred method to
+ * access packet data, however, this helper is in particular useful
+ * in socket filters where *skb*\ **->data** does not always point
+ * to the start of the mac header and where "direct packet access"
+ * is not available.
+ *
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ * Description
+ * Do FIB lookup in kernel tables using parameters in *params*.
+ * If lookup is successful and result shows packet is to be
+ * forwarded, the neighbor tables are searched for the nexthop.
+ * If successful (ie., FIB lookup shows forwarding and nexthop
+ * is resolved), the nexthop address is returned in ipv4_dst,
+ * ipv6_dst or mpls_out based on family, smac is set to mac
+ * address of egress device, dmac is set to nexthop mac address,
+ * rt_metric is set to metric from route.
+ *
+ * *plen* argument is the size of the passed in struct.
+ * *flags* argument can be one or more BPF_FIB_LOOKUP_ flags:
+ *
+ * **BPF_FIB_LOOKUP_DIRECT** means do a direct table lookup vs
+ * full lookup using FIB rules
+ * **BPF_FIB_LOOKUP_OUTPUT** means do lookup from an egress
+ * perspective (default is ingress)
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ *
+ * Return
+ * Egress device index on success, 0 if packet needs to continue
+ * up the stack for further processing or a negative error in case
+ * of failure.
+ *
+ * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a sockhash *map* referencing sockets.
+ * The *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ * if the verdeict eBPF program returns **SK_PASS**), redirect it
+ * to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(msg_cork_bytes), \
FN(msg_pull_data), \
FN(bind), \
- FN(xdp_adjust_tail),
+ FN(xdp_adjust_tail), \
+ FN(skb_get_xfrm_state), \
+ FN(get_stack), \
+ FN(skb_load_bytes_relative), \
+ FN(fib_lookup), \
+ FN(sock_hash_update), \
+ FN(msg_redirect_hash), \
+ FN(sk_redirect_hash),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
#define BPF_F_TUNINFO_IPV6 (1ULL << 0)
-/* BPF_FUNC_get_stackid flags. */
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
#define BPF_F_SKIP_FIELD_MASK 0xffULL
#define BPF_F_USER_STACK (1ULL << 8)
+/* flags used by BPF_FUNC_get_stackid only. */
#define BPF_F_FAST_STACK_CMP (1ULL << 9)
#define BPF_F_REUSE_STACKID (1ULL << 10)
+/* flags used by BPF_FUNC_get_stack only. */
+#define BPF_F_USER_BUILD_ID (1ULL << 11)
/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
+#define BPF_F_SEQ_NUMBER (1ULL << 3)
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
BPF_ADJ_ROOM_NET,
};
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+ BPF_HDR_START_MAC,
+ BPF_HDR_START_NET,
+};
+
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
*/
__u32 tunnel_label;
};
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+ __u32 reqid;
+ __u32 spi; /* Stored in network byte order */
+ __u16 family;
+ union {
+ __u32 remote_ipv4; /* Stored in network byte order */
+ __u32 remote_ipv6[4]; /* Stored in network byte order */
+ };
+};
+
/* Generic BPF return codes which all BPF program types may support.
* The values are binary compatible with their TC_ACT_* counter-part to
* provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 gpl_compatible:1;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
__u32 ifindex;
__u64 netns_dev;
__u64 netns_ino;
+ __u32 btf_id;
+ __u32 btf_key_id;
+ __u32 btf_value_id;
+} __attribute__((aligned(8)));
+
+struct bpf_btf_info {
+ __aligned_u64 btf;
+ __u32 btf_size;
+ __u32 id;
} __attribute__((aligned(8)));
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
__u64 args[0];
};
+/* DIRECT: Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT: Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+
+struct bpf_fib_lookup {
+ /* input */
+ __u8 family; /* network family, AF_INET, AF_INET6, AF_MPLS */
+
+ /* set if lookup is to consider L4 data - e.g., FIB rules */
+ __u8 l4_protocol;
+ __be16 sport;
+ __be16 dport;
+
+ /* total length of packet from network header - used for MTU check */
+ __u16 tot_len;
+ __u32 ifindex; /* L3 device index for lookup */
+
+ union {
+ /* inputs to lookup */
+ __u8 tos; /* AF_INET */
+ __be32 flowlabel; /* AF_INET6 */
+
+ /* output: metric of fib result */
+ __u32 rt_metric;
+ };
+
+ union {
+ __be32 mpls_in;
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ };
+
+ /* input to bpf_fib_lookup, *dst is destination address.
+ * output: bpf_fib_lookup sets to gateway address
+ */
+ union {
+ /* return for MPLS lookups */
+ __be32 mpls_out[4]; /* support up to 4 labels */
+ __be32 ipv4_dst;
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
-#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
-#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
- __u32 name;
+ __u32 name_off;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* info in "struct btf_type").
*/
struct btf_enum {
- __u32 name;
+ __u32 name_off;
__s32 val;
};
* "struct btf_type").
*/
struct btf_member {
- __u32 name;
+ __u32 name_off;
__u32 type;
__u32 offset; /* offset in bits */
};
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ERSPAN Tunnel Metadata
+ *
+ * Copyright (c) 2018 VMware
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * Userspace API for metadata mode ERSPAN tunnel
+ */
+#ifndef _UAPI_ERSPAN_H
+#define _UAPI_ERSPAN_H
+
+#include <linux/types.h> /* For __beXX in userspace */
+#include <asm/byteorder.h>
+
+/* ERSPAN version 2 metadata header */
+struct erspan_md2 {
+ __be32 timestamp;
+ __be16 sgt; /* security group tag */
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 hwid_upper:2,
+ ft:5,
+ p:1;
+ __u8 o:1,
+ gra:2,
+ dir:1,
+ hwid:4;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u8 p:1,
+ ft:5,
+ hwid_upper:2;
+ __u8 hwid:4,
+ dir:1,
+ gra:2,
+ o:1;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+};
+
+struct erspan_metadata {
+ int version;
+ union {
+ __be32 index; /* Version 1 (type II)*/
+ struct erspan_md2 md2; /* Version 2 (type III) */
+ } u;
+};
+
+#endif /* _UAPI_ERSPAN_H */
IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */
};
+/* tun section */
+
+enum {
+ IFLA_TUN_UNSPEC,
+ IFLA_TUN_OWNER,
+ IFLA_TUN_GROUP,
+ IFLA_TUN_TYPE,
+ IFLA_TUN_PI,
+ IFLA_TUN_VNET_HDR,
+ IFLA_TUN_PERSIST,
+ IFLA_TUN_MULTI_QUEUE,
+ IFLA_TUN_NUM_QUEUES,
+ IFLA_TUN_NUM_DISABLED_QUEUES,
+ __IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
+
+enum {
+ IFLA_RMNET_UNSPEC,
+ IFLA_RMNET_MUX_ID,
+ IFLA_RMNET_FLAGS,
+ __IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
#endif /* _UAPI_LINUX_IF_LINK_H */
char padding[256];
};
+ /* 2048 is the size of the char array used to bound/pad the size
+ * of the union that holds sync regs.
+ */
+ #define SYNC_REGS_SIZE_BYTES 2048
/*
* shared registers between kvm and userspace.
* kvm_valid_regs specifies the register classes set by the host
__u64 kvm_dirty_regs;
union {
struct kvm_sync_regs regs;
- char padding[2048];
+ char padding[SYNC_REGS_SIZE_BYTES];
} s;
};
__u8 pad[36];
};
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HTL | \
+ KVM_X86_DISABLE_EXITS_PAUSE)
+
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
/* in */
#define KVM_CAP_PPC_GET_CPU_CHAR 151
#define KVM_CAP_S390_BPB 152
#define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
#ifdef KVM_CAP_IRQ_ROUTING
#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region)
#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd)
+
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
#define KVM_ARM_DEV_PMU (1 << 2)
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
#endif /* __LINUX_KVM_H */
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ * Indicates that thread was preempted in TASK_RUNNING state.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
#define SNDRV_PCM_FORMAT_DSD_U16_BE ((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
#define SNDRV_PCM_FORMAT_DSD_U32_BE ((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
#define SNDRV_PCM_FORMAT_LAST SNDRV_PCM_FORMAT_DSD_U32_BE
+#define SNDRV_PCM_FORMAT_FIRST SNDRV_PCM_FORMAT_S8
#ifdef SNDRV_LITTLE_ENDIAN
#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_LE
FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
FEATURE_DISPLAY = libelf bpf
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
check_feat := 1
attr.btf_fd = create_attr->btf_fd;
attr.btf_key_id = create_attr->btf_key_id;
attr.btf_value_id = create_attr->btf_value_id;
+ attr.map_ifindex = create_attr->map_ifindex;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
attr.log_size = 0;
attr.log_level = 0;
attr.kern_version = load_attr->kern_version;
+ attr.prog_ifindex = load_attr->prog_ifindex;
memcpy(attr.prog_name, load_attr->name,
min(name_len, BPF_OBJ_NAME_LEN - 1));
return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
}
+int bpf_btf_get_fd_by_id(__u32 id)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.btf_id = id;
+
+ return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
{
union bpf_attr attr;
__u32 btf_fd;
__u32 btf_key_id;
__u32 btf_value_id;
+ __u32 map_ifindex;
};
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
size_t insns_cnt;
const char *license;
__u32 kern_version;
+ __u32 prog_ifindex;
};
/* Recommend log buffer size */
int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
int bpf_prog_get_fd_by_id(__u32 id);
int bpf_map_get_fd_by_id(__u32 id);
+int bpf_btf_get_fd_by_id(__u32 id);
int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
for (i = 1; i <= btf->nr_types; i++) {
const struct btf_type *t = btf->types[i];
- const char *name = btf_name_by_offset(btf, t->name);
+ const char *name = btf_name_by_offset(btf, t->name_off);
if (name && !strcmp(type_name, name))
return i;
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
+#include <perf-sys.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
/* Index in elf obj file, for relocation use. */
int idx;
char *name;
+ int prog_ifindex;
char *section_name;
struct bpf_insn *insns;
size_t insns_cnt, main_prog_cnt;
int fd;
char *name;
size_t offset;
+ int map_ifindex;
struct bpf_map_def def;
uint32_t btf_key_id;
uint32_t btf_value_id;
int *pfd = &map->fd;
create_attr.name = map->name;
+ create_attr.map_ifindex = map->map_ifindex;
create_attr.map_type = def->type;
create_attr.map_flags = def->map_flags;
create_attr.key_size = def->key_size;
static int
load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
const char *name, struct bpf_insn *insns, int insns_cnt,
- char *license, u32 kern_version, int *pfd)
+ char *license, u32 kern_version, int *pfd, int prog_ifindex)
{
struct bpf_load_program_attr load_attr;
char *log_buf;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
load_attr.kern_version = kern_version;
+ load_attr.prog_ifindex = prog_ifindex;
if (!load_attr.insns || !load_attr.insns_cnt)
return -EINVAL;
}
err = load_program(prog->type, prog->expected_attach_type,
prog->name, prog->insns, prog->insns_cnt,
- license, kern_version, &fd);
+ license, kern_version, &fd,
+ prog->prog_ifindex);
if (!err)
prog->instances.fds[0] = fd;
goto out;
err = load_program(prog->type, prog->expected_attach_type,
prog->name, result.new_insn_ptr,
result.new_insn_cnt,
- license, kern_version, &fd);
+ license, kern_version, &fd,
+ prog->prog_ifindex);
if (err) {
pr_warning("Loading the %dth instance of program '%s' failed\n",
return 0;
}
-static int bpf_object__validate(struct bpf_object *obj)
+static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_SOCKET_FILTER:
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ case BPF_PROG_TYPE_XDP:
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_SK_MSG:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ return false;
+ case BPF_PROG_TYPE_UNSPEC:
+ case BPF_PROG_TYPE_KPROBE:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ default:
+ return true;
+ }
+}
+
+static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
{
- if (obj->kern_version == 0) {
+ if (needs_kver && obj->kern_version == 0) {
pr_warning("%s doesn't provide kernel version\n",
obj->path);
return -LIBBPF_ERRNO__KVERSION;
}
static struct bpf_object *
-__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
+__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
+ bool needs_kver)
{
struct bpf_object *obj;
int err;
CHECK_ERR(bpf_object__check_endianness(obj), err, out);
CHECK_ERR(bpf_object__elf_collect(obj), err, out);
CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
- CHECK_ERR(bpf_object__validate(obj), err, out);
+ CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
bpf_object__elf_finish(obj);
return obj;
pr_debug("loading %s\n", path);
- return __bpf_object__open(path, NULL, 0);
+ return __bpf_object__open(path, NULL, 0, true);
}
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
pr_debug("loading object '%s' from buffer\n",
name);
- return __bpf_object__open(name, obj_buf, obj_buf_sz);
+ return __bpf_object__open(name, obj_buf, obj_buf_sz, true);
}
int bpf_object__unload(struct bpf_object *obj)
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
-static void bpf_program__set_expected_attach_type(struct bpf_program *prog,
- enum bpf_attach_type type)
+void bpf_program__set_expected_attach_type(struct bpf_program *prog,
+ enum bpf_attach_type type)
{
prog->expected_attach_type = type;
}
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
struct bpf_object *obj;
+ struct bpf_map *map;
int section_idx;
int err;
if (!attr)
return -EINVAL;
+ if (!attr->file)
+ return -EINVAL;
- obj = bpf_object__open(attr->file);
- if (IS_ERR(obj))
+ obj = __bpf_object__open(attr->file, NULL, 0,
+ bpf_prog_type__needs_kver(attr->prog_type));
+ if (IS_ERR_OR_NULL(obj))
return -ENOENT;
bpf_object__for_each_program(prog, obj) {
* section name.
*/
prog_type = attr->prog_type;
+ prog->prog_ifindex = attr->ifindex;
expected_attach_type = attr->expected_attach_type;
if (prog_type == BPF_PROG_TYPE_UNSPEC) {
section_idx = bpf_program__identify_section(prog);
first_prog = prog;
}
+ bpf_map__for_each(map, obj) {
+ map->map_ifindex = attr->ifindex;
+ }
+
if (!first_prog) {
pr_warning("object file doesn't contain bpf program\n");
bpf_object__close(obj);
*prog_fd = bpf_program__fd(first_prog);
return 0;
}
+
+enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mem, unsigned long size,
+ unsigned long page_size, void **buf, size_t *buf_len,
+ bpf_perf_event_print_t fn, void *priv)
+{
+ volatile struct perf_event_mmap_page *header = mem;
+ __u64 data_tail = header->data_tail;
+ __u64 data_head = header->data_head;
+ void *base, *begin, *end;
+ int ret;
+
+ asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
+ if (data_head == data_tail)
+ return LIBBPF_PERF_EVENT_CONT;
+
+ base = ((char *)header) + page_size;
+
+ begin = base + data_tail % size;
+ end = base + data_head % size;
+
+ while (begin != end) {
+ struct perf_event_header *ehdr;
+
+ ehdr = begin;
+ if (begin + ehdr->size > base + size) {
+ long len = base + size - begin;
+
+ if (*buf_len < ehdr->size) {
+ free(*buf);
+ *buf = malloc(ehdr->size);
+ if (!*buf) {
+ ret = LIBBPF_PERF_EVENT_ERROR;
+ break;
+ }
+ *buf_len = ehdr->size;
+ }
+
+ memcpy(*buf, begin, len);
+ memcpy(*buf + len, base, ehdr->size - len);
+ ehdr = (void *)*buf;
+ begin = base + ehdr->size - len;
+ } else if (begin + ehdr->size == base + size) {
+ begin = base;
+ } else {
+ begin += ehdr->size;
+ }
+
+ ret = fn(ehdr, priv);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ break;
+
+ data_tail += ehdr->size;
+ }
+
+ __sync_synchronize(); /* smp_mb() */
+ header->data_tail = data_tail;
+
+ return ret;
+}
int libbpf_strerror(int err, char *buf, size_t size);
/*
- * In include/linux/compiler-gcc.h, __printf is defined. However
- * it should be better if libbpf.h doesn't depend on Linux header file.
+ * __printf is defined in include/linux/compiler-gcc.h. However,
+ * it would be better if libbpf.h didn't depend on Linux header files.
* So instead of __printf, here we use gcc attribute directly.
*/
typedef int (*libbpf_print_fn_t)(const char *, ...)
bpf_object_clear_priv_t clear_priv);
void *bpf_object__priv(struct bpf_object *prog);
-/* Accessors of bpf_program. */
+/* Accessors of bpf_program */
struct bpf_program;
struct bpf_program *bpf_program__next(struct bpf_program *prog,
struct bpf_object *obj);
/*
* Libbpf allows callers to adjust BPF programs before being loaded
- * into kernel. One program in an object file can be transform into
- * multiple variants to be attached to different code.
+ * into kernel. One program in an object file can be transformed into
+ * multiple variants to be attached to different hooks.
*
* bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd
- * are APIs for this propose.
+ * form an API for this purpose.
*
* - bpf_program_prep_t:
- * It defines 'preprocessor', which is a caller defined function
+ * Defines a 'preprocessor', which is a caller defined function
* passed to libbpf through bpf_program__set_prep(), and will be
* called before program is loaded. The processor should adjust
- * the program one time for each instances according to the number
+ * the program one time for each instance according to the instance id
* passed to it.
*
* - bpf_program__set_prep:
- * Attachs a preprocessor to a BPF program. The number of instances
- * whould be created is also passed through this function.
+ * Attaches a preprocessor to a BPF program. The number of instances
+ * that should be created is also passed through this function.
*
* - bpf_program__nth_fd:
- * After the program is loaded, get resuling fds from bpf program for
- * each instances.
+ * After the program is loaded, get resulting FD of a given instance
+ * of the BPF program.
*
- * If bpf_program__set_prep() is not used, the program whould be loaded
+ * If bpf_program__set_prep() is not used, the program would be loaded
* without adjustment during bpf_object__load(). The program has only
* one instance. In this case bpf_program__fd(prog) is equal to
* bpf_program__nth_fd(prog, 0).
struct bpf_insn *new_insn_ptr;
int new_insn_cnt;
- /* If not NULL, result fd is set to it */
+ /* If not NULL, result FD is written to it. */
int *pfd;
};
* - res: Output parameter, result of transformation.
*
* Return value:
- * - Zero: pre-processing success.
- * - Non-zero: pre-processing, stop loading.
+ * - Zero: pre-processing success.
+ * - Non-zero: pre-processing error, stop loading.
*/
typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
struct bpf_insn *insns, int insns_cnt,
int bpf_program__nth_fd(struct bpf_program *prog, int n);
/*
- * Adjust type of bpf program. Default is kprobe.
+ * Adjust type of BPF program. Default is kprobe.
*/
int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_xdp(struct bpf_program *prog);
int bpf_program__set_perf_event(struct bpf_program *prog);
void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
+void bpf_program__set_expected_attach_type(struct bpf_program *prog,
+ enum bpf_attach_type type);
bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_perf_event(struct bpf_program *prog);
/*
- * We don't need __attribute__((packed)) now since it is
- * unnecessary for 'bpf_map_def' because they are all aligned.
- * In addition, using it will trigger -Wpacked warning message,
- * and will be treated as an error due to -Werror.
+ * No need for __attribute__((packed)), all members of 'bpf_map_def'
+ * are all aligned. In addition, using __attribute__((packed))
+ * would trigger a -Wpacked warning message, and lead to an error
+ * if -Werror is set.
*/
struct bpf_map_def {
unsigned int type;
};
/*
- * There is another 'struct bpf_map' in include/linux/map.h. However,
- * it is not a uapi header so no need to consider name clash.
+ * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
+ * so no need to worry about a name clash.
*/
struct bpf_map;
struct bpf_map *
/*
* Get bpf_map through the offset of corresponding struct bpf_map_def
- * in the bpf object file.
+ * in the BPF object file.
*/
struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
const char *file;
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
+ int ifindex;
};
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd);
int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+
+enum bpf_perf_event_ret {
+ LIBBPF_PERF_EVENT_DONE = 0,
+ LIBBPF_PERF_EVENT_ERROR = -1,
+ LIBBPF_PERF_EVENT_CONT = -2,
+};
+
+typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
+ void *priv);
+int bpf_perf_event_read_simple(void *mem, unsigned long size,
+ unsigned long page_size,
+ void **buf, size_t *buf_len,
+ bpf_perf_event_print_t fn, void *priv);
#endif
if (ambiguous_option) {
fprintf(stderr,
- " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+ " Error: Ambiguous option: %s (could be --%s%s or --%s%s)\n",
arg,
(ambiguous_flags & OPT_UNSET) ? "no-" : "",
ambiguous_option->long_name,
return;
if (strstarts(arg, "no-")) {
- fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+ fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
exit(129);
}
if (!options->long_name)
continue;
if (strstarts(options->long_name, arg)) {
- fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+ fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
exit(129);
}
}
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/objtool/arch/$(ARCH)/include
WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
-LDFLAGS += -lelf $(LIBSUBCMD)
+CFLAGS += -Werror $(WARNINGS) $(HOSTCFLAGS) -g $(INCLUDES)
+LDFLAGS += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
# Allow old libelf to be used:
elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
return next;
}
+static struct instruction *next_insn_same_func(struct objtool_file *file,
+ struct instruction *insn)
+{
+ struct instruction *next = list_next_entry(insn, list);
+ struct symbol *func = insn->func;
+
+ if (!func)
+ return NULL;
+
+ if (&next->list != &file->insn_list && next->func == func)
+ return next;
+
+ /* Check if we're already in the subfunction: */
+ if (func == func->cfunc)
+ return NULL;
+
+ /* Move to the subfunction: */
+ return find_insn(file, func->cfunc->sec, func->cfunc->offset);
+}
+
+#define func_for_each_insn_all(file, func, insn) \
+ for (insn = find_insn(file, func->sec, func->offset); \
+ insn; \
+ insn = next_insn_same_func(file, insn))
+
#define func_for_each_insn(file, func, insn) \
for (insn = find_insn(file, func->sec, func->offset); \
insn && &insn->list != &file->insn_list && \
if (!strcmp(func->name, global_noreturns[i]))
return 1;
- if (!func->sec)
+ if (!func->len)
return 0;
- func_for_each_insn(file, func, insn) {
+ insn = find_insn(file, func->sec, func->offset);
+ if (!insn->func)
+ return 0;
+
+ func_for_each_insn_all(file, func, insn) {
empty = false;
if (insn->type == INSN_RETURN)
* case, the function's dead-end status depends on whether the target
* of the sibling call returns.
*/
- func_for_each_insn(file, func, insn) {
- if (insn->sec != func->sec ||
- insn->offset >= func->offset + func->len)
- break;
-
+ func_for_each_insn_all(file, func, insn) {
if (insn->type == INSN_JUMP_UNCONDITIONAL) {
struct instruction *dest = insn->jump_dest;
- struct symbol *dest_func;
if (!dest)
/* sibling call to another file */
return 0;
- if (dest->sec != func->sec ||
- dest->offset < func->offset ||
- dest->offset >= func->offset + func->len) {
- /* local sibling call */
- dest_func = find_symbol_by_offset(dest->sec,
- dest->offset);
- if (!dest_func)
- continue;
+ if (dest->func && dest->func->pfunc != insn->func->pfunc) {
+ /* local sibling call */
if (recursion == 5) {
- WARN_FUNC("infinite recursion (objtool bug!)",
- dest->sec, dest->offset);
- return -1;
+ /*
+ * Infinite recursion: two functions
+ * have sibling calls to each other.
+ * This is a very rare case. It means
+ * they aren't dead ends.
+ */
+ return 0;
}
- return __dead_end_function(file, dest_func,
+ return __dead_end_function(file, dest->func,
recursion + 1);
}
}
if (!ignore_func(file, func))
continue;
- func_for_each_insn(file, func, insn)
+ func_for_each_insn_all(file, func, insn)
insn->ignore = true;
}
}
return ret;
}
-static int add_switch_table(struct objtool_file *file, struct symbol *func,
- struct instruction *insn, struct rela *table,
- struct rela *next_table)
+static int add_switch_table(struct objtool_file *file, struct instruction *insn,
+ struct rela *table, struct rela *next_table)
{
struct rela *rela = table;
struct instruction *alt_insn;
struct alternative *alt;
+ struct symbol *pfunc = insn->func->pfunc;
+ unsigned int prev_offset = 0;
list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
if (rela == next_table)
break;
- if (rela->sym->sec != insn->sec ||
- rela->addend <= func->offset ||
- rela->addend >= func->offset + func->len)
+ /* Make sure the switch table entries are consecutive: */
+ if (prev_offset && rela->offset != prev_offset + 8)
break;
- alt_insn = find_insn(file, insn->sec, rela->addend);
- if (!alt_insn) {
- WARN("%s: can't find instruction at %s+0x%x",
- file->rodata->rela->name, insn->sec->name,
- rela->addend);
- return -1;
- }
+ /* Detect function pointers from contiguous objects: */
+ if (rela->sym->sec == pfunc->sec &&
+ rela->addend == pfunc->offset)
+ break;
+
+ alt_insn = find_insn(file, rela->sym->sec, rela->addend);
+ if (!alt_insn)
+ break;
+
+ /* Make sure the jmp dest is in the function or subfunction: */
+ if (alt_insn->func->pfunc != pfunc)
+ break;
alt = malloc(sizeof(*alt));
if (!alt) {
alt->insn = alt_insn;
list_add_tail(&alt->list, &insn->alts);
+ prev_offset = rela->offset;
+ }
+
+ if (!prev_offset) {
+ WARN_FUNC("can't find switch jump table",
+ insn->sec, insn->offset);
+ return -1;
}
return 0;
{
struct rela *text_rela, *rodata_rela;
struct instruction *orig_insn = insn;
+ unsigned long table_offset;
- text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
- if (text_rela && text_rela->sym == file->rodata->sym) {
- /* case 1 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend);
- if (rodata_rela)
- return rodata_rela;
-
- /* case 2 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend + 4);
- if (!rodata_rela)
- return NULL;
-
- file->ignore_unreachables = true;
- return rodata_rela;
- }
-
- /* case 3 */
/*
* Backward search using the @first_jump_src links, these help avoid
* much of the 'in between' code. Which avoids us getting confused by
* it.
*/
- for (insn = list_prev_entry(insn, list);
-
+ for (;
&insn->list != &file->insn_list &&
insn->sec == func->sec &&
insn->offset >= func->offset;
insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
- if (insn->type == INSN_JUMP_DYNAMIC)
+ if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
break;
/* allow small jumps within the range */
if (!text_rela || text_rela->sym != file->rodata->sym)
continue;
+ table_offset = text_rela->addend;
+ if (text_rela->type == R_X86_64_PC32)
+ table_offset += 4;
+
/*
* Make sure the .rodata address isn't associated with a
* symbol. gcc jump tables are anonymous data.
*/
- if (find_symbol_containing(file->rodata, text_rela->addend))
+ if (find_symbol_containing(file->rodata, table_offset))
continue;
- rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend);
- if (!rodata_rela)
- continue;
+ rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+ if (rodata_rela) {
+ /*
+ * Use of RIP-relative switch jumps is quite rare, and
+ * indicates a rare GCC quirk/bug which can leave dead
+ * code behind.
+ */
+ if (text_rela->type == R_X86_64_PC32)
+ file->ignore_unreachables = true;
- return rodata_rela;
+ return rodata_rela;
+ }
}
return NULL;
struct rela *rela, *prev_rela = NULL;
int ret;
- func_for_each_insn(file, func, insn) {
+ func_for_each_insn_all(file, func, insn) {
if (!last)
last = insn;
* the beginning of another switch table in the same function.
*/
if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela,
- rela);
+ ret = add_switch_table(file, prev_jump, prev_rela, rela);
if (ret)
return ret;
}
}
if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela, NULL);
+ ret = add_switch_table(file, prev_jump, prev_rela, NULL);
if (ret)
return ret;
}
while (1) {
next_insn = next_insn_same_sec(file, insn);
-
- if (file->c_file && func && insn->func && func != insn->func) {
+ if (file->c_file && func && insn->func && func != insn->func->pfunc) {
WARN("%s() falls through to next function %s()",
func->name, insn->func->name);
return 1;
}
- if (insn->func)
- func = insn->func;
+ func = insn->func ? insn->func->pfunc : NULL;
if (func && insn->ignore) {
WARN_FUNC("BUG: why am I validating an ignored function?",
i = insn;
save_insn = NULL;
- func_for_each_insn_continue_reverse(file, func, i) {
+ func_for_each_insn_continue_reverse(file, insn->func, i) {
if (i->save) {
save_insn = i;
break;
case INSN_JUMP_UNCONDITIONAL:
if (insn->jump_dest &&
(!func || !insn->jump_dest->func ||
- func == insn->jump_dest->func)) {
+ insn->jump_dest->func->pfunc == func)) {
ret = validate_branch(file, insn->jump_dest,
state);
if (ret)
for_each_sec(file, sec) {
list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
+ if (func->type != STT_FUNC || func->pfunc != func)
continue;
insn = find_insn(file, sec, func->offset);
return NULL;
}
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+{
+ struct section *sec;
+ struct symbol *sym;
+
+ list_for_each_entry(sec, &elf->sections, list)
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (!strcmp(sym->name, name))
+ return sym;
+
+ return NULL;
+}
+
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
{
struct symbol *sym;
static int read_symbols(struct elf *elf)
{
- struct section *symtab;
- struct symbol *sym;
+ struct section *symtab, *sec;
+ struct symbol *sym, *pfunc;
struct list_head *entry, *tmp;
int symbols_nr, i;
+ char *coldstr;
symtab = find_section_by_name(elf, ".symtab");
if (!symtab) {
hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
}
+ /* Create parent/child links for any cold subfunctions */
+ list_for_each_entry(sec, &elf->sections, list) {
+ list_for_each_entry(sym, &sec->symbol_list, list) {
+ if (sym->type != STT_FUNC)
+ continue;
+ sym->pfunc = sym->cfunc = sym;
+ coldstr = strstr(sym->name, ".cold.");
+ if (coldstr) {
+ coldstr[0] = '\0';
+ pfunc = find_symbol_by_name(elf, sym->name);
+ coldstr[0] = '.';
+
+ if (!pfunc) {
+ WARN("%s(): can't find parent function",
+ sym->name);
+ goto err;
+ }
+
+ sym->pfunc = pfunc;
+ pfunc->cfunc = sym;
+ }
+ }
+ }
+
return 0;
err:
unsigned char bind, type;
unsigned long offset;
unsigned int len;
+ struct symbol *pfunc, *cfunc;
};
struct rela {
struct elf *elf_open(const char *name, int flags);
struct section *find_section_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
99.93 │ mov %eax,%eax
+ annotate.offset_level::
+ Default is '1', meaning just jump targets will have offsets show right beside
+ the instruction. When set to '2' 'call' instructions will also have its offsets
+ shown, 3 or higher will show offsets for all instructions.
+
hist.*::
hist.percentage::
This option control the way to calculate overhead of filtered entries -
<command>...::
Any command you can specify in a shell.
+-i::
+--input=<file>::
+ Input file name.
+
-f::
--force::
Don't do ownership validation
-t::
---type=::
+--type=<type>::
Select the memory operation type: load or store (default: load,store)
-D::
---dump-raw-samples=::
+--dump-raw-samples::
Dump the raw decoded samples on the screen in a format that is easy to parse with
one sample per line.
-x::
---field-separator::
+--field-separator=<separator>::
Specify the field separator used when dump raw samples (-D option). By default,
The separator is the space character.
-C::
---cpu-list::
- Restrict dump of raw samples to those provided via this option. Note that the same
- option can be passed in record mode. It will be interpreted the same way as perf
- record.
+--cpu=<cpu>::
+ Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default
+ is to monitor all CPUS.
+-U::
+--hide-unresolved::
+ Only display entries resolved to a symbol.
+
+-p::
+--phys-data::
+ Record/Report sample physical addresses
+
+RECORD OPTIONS
+--------------
+-e::
+--event <event>::
+ Event selector. Use 'perf mem record -e list' to list available events.
-K::
--all-kernel::
--all-user::
Configure all used events to run in user space.
---ldload::
+-v::
+--verbose::
+ Be more verbose (show counter open errors, etc)
+
+--ldlat <n>::
Specify desired latency for loads event.
--p::
---phys-data::
- Record/Report sample physical addresses
+In addition, for report all perf report options are valid, and for record
+all perf record options.
SEE ALSO
--------
kallsyms pathname
-g::
---no-call-graph::
- Do not display call chains if present.
+--call-graph::
+ Display call chains if present (default on).
--max-stack::
Maximum number of functions to display in backtrace, default 5.
For sample events it's possible to display misc field with -F +misc option,
following letters are displayed for each bit:
- PERF_RECORD_MISC_KERNEL K
- PERF_RECORD_MISC_USER U
- PERF_RECORD_MISC_HYPERVISOR H
- PERF_RECORD_MISC_GUEST_KERNEL G
- PERF_RECORD_MISC_GUEST_USER g
- PERF_RECORD_MISC_MMAP_DATA* M
- PERF_RECORD_MISC_COMM_EXEC E
- PERF_RECORD_MISC_SWITCH_OUT S
+ PERF_RECORD_MISC_KERNEL K
+ PERF_RECORD_MISC_USER U
+ PERF_RECORD_MISC_HYPERVISOR H
+ PERF_RECORD_MISC_GUEST_KERNEL G
+ PERF_RECORD_MISC_GUEST_USER g
+ PERF_RECORD_MISC_MMAP_DATA* M
+ PERF_RECORD_MISC_COMM_EXEC E
+ PERF_RECORD_MISC_SWITCH_OUT S
+ PERF_RECORD_MISC_SWITCH_OUT_PREEMPT Sp
$ perf script -F +misc ...
sched-messaging 1414 K 28690.636582: 4590 cycles ...
-I msecs::
--interval-print msecs::
-Print count deltas every N milliseconds (minimum: 10ms)
+Print count deltas every N milliseconds (minimum: 1ms)
The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution.
example: 'perf stat -I 1000 -e cycles -a sleep 5'
endif
ifneq ($(NO_SYSCALL_TABLE),1)
- CFLAGS += -DHAVE_SYSCALL_TABLE
+ CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT
endif
# So far there's only x86 and arm libdw unwind support merged in perf.
ifeq ($(feature-jvmti), 1)
$(call detected_var,JDIR)
else
- $(warning No openjdk development package found, please install JDK package)
+ $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel)
NO_JVMTI := 1
endif
endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
libperf-y += regs_load.o
libperf-y += dwarf-unwind.o
+
+libperf-y += arch-tests.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ {
+ .desc = "DWARF unwind",
+ .func = test__dwarf_unwind,
+ },
+#endif
+ {
+ .func = NULL,
+ },
+};
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdbool.h>
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <api/fs/fs.h>
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef INCLUDE__PERF_CS_ETM_H__
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <string.h>
struct perf_evsel *pos;
int diagnose = 0;
+ *err = 0;
if (evlist->nr_entries == 0)
return NULL;
zfree(&buf);
return buf;
}
-
-/*
- * Compare the cpuid string returned by get_cpuid() function
- * with the name generated by the jevents file read from
- * pmu-events/arch/s390/mapfile.csv.
- *
- * Parameter mapcpuid is the cpuid as stored in the
- * pmu-events/arch/s390/mapfile.csv. This is just the type number.
- * Parameter cpuid is the cpuid returned by function get_cpuid().
- */
-int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
-{
- char *cp = strchr(cpuid, ',');
-
- if (cp == NULL)
- return -1;
- return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
-}
$(header): $(sys)/syscall_64.tbl $(systbl)
@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
(diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
- || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
+ || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
clean::
// SPDX-License-Identifier: GPL-2.0
static struct ins x86__instructions[] = {
+ { .name = "adc", .ops = &mov_ops, },
+ { .name = "adcb", .ops = &mov_ops, },
+ { .name = "adcl", .ops = &mov_ops, },
{ .name = "add", .ops = &mov_ops, },
{ .name = "addl", .ops = &mov_ops, },
{ .name = "addq", .ops = &mov_ops, },
+ { .name = "addsd", .ops = &mov_ops, },
{ .name = "addw", .ops = &mov_ops, },
{ .name = "and", .ops = &mov_ops, },
+ { .name = "andb", .ops = &mov_ops, },
+ { .name = "andl", .ops = &mov_ops, },
+ { .name = "andpd", .ops = &mov_ops, },
+ { .name = "andps", .ops = &mov_ops, },
+ { .name = "andq", .ops = &mov_ops, },
+ { .name = "andw", .ops = &mov_ops, },
+ { .name = "bsr", .ops = &mov_ops, },
+ { .name = "bt", .ops = &mov_ops, },
+ { .name = "btr", .ops = &mov_ops, },
{ .name = "bts", .ops = &mov_ops, },
+ { .name = "btsq", .ops = &mov_ops, },
{ .name = "call", .ops = &call_ops, },
{ .name = "callq", .ops = &call_ops, },
+ { .name = "cmovbe", .ops = &mov_ops, },
+ { .name = "cmove", .ops = &mov_ops, },
+ { .name = "cmovae", .ops = &mov_ops, },
{ .name = "cmp", .ops = &mov_ops, },
{ .name = "cmpb", .ops = &mov_ops, },
{ .name = "cmpl", .ops = &mov_ops, },
{ .name = "cmpq", .ops = &mov_ops, },
{ .name = "cmpw", .ops = &mov_ops, },
{ .name = "cmpxch", .ops = &mov_ops, },
+ { .name = "cmpxchg", .ops = &mov_ops, },
+ { .name = "cs", .ops = &mov_ops, },
{ .name = "dec", .ops = &dec_ops, },
{ .name = "decl", .ops = &dec_ops, },
+ { .name = "divsd", .ops = &mov_ops, },
+ { .name = "divss", .ops = &mov_ops, },
+ { .name = "gs", .ops = &mov_ops, },
{ .name = "imul", .ops = &mov_ops, },
{ .name = "inc", .ops = &dec_ops, },
{ .name = "incl", .ops = &dec_ops, },
{ .name = "lea", .ops = &mov_ops, },
{ .name = "lock", .ops = &lock_ops, },
{ .name = "mov", .ops = &mov_ops, },
+ { .name = "movapd", .ops = &mov_ops, },
+ { .name = "movaps", .ops = &mov_ops, },
{ .name = "movb", .ops = &mov_ops, },
{ .name = "movdqa", .ops = &mov_ops, },
+ { .name = "movdqu", .ops = &mov_ops, },
{ .name = "movl", .ops = &mov_ops, },
{ .name = "movq", .ops = &mov_ops, },
+ { .name = "movsd", .ops = &mov_ops, },
{ .name = "movslq", .ops = &mov_ops, },
+ { .name = "movss", .ops = &mov_ops, },
+ { .name = "movupd", .ops = &mov_ops, },
+ { .name = "movups", .ops = &mov_ops, },
+ { .name = "movw", .ops = &mov_ops, },
{ .name = "movzbl", .ops = &mov_ops, },
{ .name = "movzwl", .ops = &mov_ops, },
+ { .name = "mulsd", .ops = &mov_ops, },
+ { .name = "mulss", .ops = &mov_ops, },
{ .name = "nop", .ops = &nop_ops, },
{ .name = "nopl", .ops = &nop_ops, },
{ .name = "nopw", .ops = &nop_ops, },
{ .name = "or", .ops = &mov_ops, },
+ { .name = "orb", .ops = &mov_ops, },
{ .name = "orl", .ops = &mov_ops, },
+ { .name = "orps", .ops = &mov_ops, },
+ { .name = "orq", .ops = &mov_ops, },
+ { .name = "pand", .ops = &mov_ops, },
+ { .name = "paddq", .ops = &mov_ops, },
+ { .name = "pcmpeqb", .ops = &mov_ops, },
+ { .name = "por", .ops = &mov_ops, },
+ { .name = "rclb", .ops = &mov_ops, },
+ { .name = "rcll", .ops = &mov_ops, },
+ { .name = "retq", .ops = &ret_ops, },
+ { .name = "sbb", .ops = &mov_ops, },
+ { .name = "sbbl", .ops = &mov_ops, },
+ { .name = "sete", .ops = &mov_ops, },
+ { .name = "sub", .ops = &mov_ops, },
+ { .name = "subl", .ops = &mov_ops, },
+ { .name = "subq", .ops = &mov_ops, },
+ { .name = "subsd", .ops = &mov_ops, },
+ { .name = "subw", .ops = &mov_ops, },
{ .name = "test", .ops = &mov_ops, },
{ .name = "testb", .ops = &mov_ops, },
{ .name = "testl", .ops = &mov_ops, },
+ { .name = "ucomisd", .ops = &mov_ops, },
+ { .name = "ucomiss", .ops = &mov_ops, },
+ { .name = "vaddsd", .ops = &mov_ops, },
+ { .name = "vandpd", .ops = &mov_ops, },
+ { .name = "vmovdqa", .ops = &mov_ops, },
+ { .name = "vmovq", .ops = &mov_ops, },
+ { .name = "vmovsd", .ops = &mov_ops, },
+ { .name = "vmulsd", .ops = &mov_ops, },
+ { .name = "vorpd", .ops = &mov_ops, },
+ { .name = "vsubsd", .ops = &mov_ops, },
+ { .name = "vucomisd", .ops = &mov_ops, },
{ .name = "xadd", .ops = &mov_ops, },
{ .name = "xbeginl", .ops = &jump_ops, },
{ .name = "xbeginq", .ops = &jump_ops, },
- { .name = "retq", .ops = &ret_ops, },
+ { .name = "xchg", .ops = &mov_ops, },
+ { .name = "xor", .ops = &mov_ops, },
+ { .name = "xorb", .ops = &mov_ops, },
+ { .name = "xorpd", .ops = &mov_ops, },
+ { .name = "xorps", .ops = &mov_ops, },
};
static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
# The format is:
# <number> <abi> <name> <entry point>
#
+# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+#
# The abi is "common", "64" or "x32" for this file.
#
-0 common read sys_read
-1 common write sys_write
-2 common open sys_open
-3 common close sys_close
-4 common stat sys_newstat
-5 common fstat sys_newfstat
-6 common lstat sys_newlstat
-7 common poll sys_poll
-8 common lseek sys_lseek
-9 common mmap sys_mmap
-10 common mprotect sys_mprotect
-11 common munmap sys_munmap
-12 common brk sys_brk
-13 64 rt_sigaction sys_rt_sigaction
-14 common rt_sigprocmask sys_rt_sigprocmask
-15 64 rt_sigreturn sys_rt_sigreturn/ptregs
-16 64 ioctl sys_ioctl
-17 common pread64 sys_pread64
-18 common pwrite64 sys_pwrite64
-19 64 readv sys_readv
-20 64 writev sys_writev
-21 common access sys_access
-22 common pipe sys_pipe
-23 common select sys_select
-24 common sched_yield sys_sched_yield
-25 common mremap sys_mremap
-26 common msync sys_msync
-27 common mincore sys_mincore
-28 common madvise sys_madvise
-29 common shmget sys_shmget
-30 common shmat sys_shmat
-31 common shmctl sys_shmctl
-32 common dup sys_dup
-33 common dup2 sys_dup2
-34 common pause sys_pause
-35 common nanosleep sys_nanosleep
-36 common getitimer sys_getitimer
-37 common alarm sys_alarm
-38 common setitimer sys_setitimer
-39 common getpid sys_getpid
-40 common sendfile sys_sendfile64
-41 common socket sys_socket
-42 common connect sys_connect
-43 common accept sys_accept
-44 common sendto sys_sendto
-45 64 recvfrom sys_recvfrom
-46 64 sendmsg sys_sendmsg
-47 64 recvmsg sys_recvmsg
-48 common shutdown sys_shutdown
-49 common bind sys_bind
-50 common listen sys_listen
-51 common getsockname sys_getsockname
-52 common getpeername sys_getpeername
-53 common socketpair sys_socketpair
-54 64 setsockopt sys_setsockopt
-55 64 getsockopt sys_getsockopt
-56 common clone sys_clone/ptregs
-57 common fork sys_fork/ptregs
-58 common vfork sys_vfork/ptregs
-59 64 execve sys_execve/ptregs
-60 common exit sys_exit
-61 common wait4 sys_wait4
-62 common kill sys_kill
-63 common uname sys_newuname
-64 common semget sys_semget
-65 common semop sys_semop
-66 common semctl sys_semctl
-67 common shmdt sys_shmdt
-68 common msgget sys_msgget
-69 common msgsnd sys_msgsnd
-70 common msgrcv sys_msgrcv
-71 common msgctl sys_msgctl
-72 common fcntl sys_fcntl
-73 common flock sys_flock
-74 common fsync sys_fsync
-75 common fdatasync sys_fdatasync
-76 common truncate sys_truncate
-77 common ftruncate sys_ftruncate
-78 common getdents sys_getdents
-79 common getcwd sys_getcwd
-80 common chdir sys_chdir
-81 common fchdir sys_fchdir
-82 common rename sys_rename
-83 common mkdir sys_mkdir
-84 common rmdir sys_rmdir
-85 common creat sys_creat
-86 common link sys_link
-87 common unlink sys_unlink
-88 common symlink sys_symlink
-89 common readlink sys_readlink
-90 common chmod sys_chmod
-91 common fchmod sys_fchmod
-92 common chown sys_chown
-93 common fchown sys_fchown
-94 common lchown sys_lchown
-95 common umask sys_umask
-96 common gettimeofday sys_gettimeofday
-97 common getrlimit sys_getrlimit
-98 common getrusage sys_getrusage
-99 common sysinfo sys_sysinfo
-100 common times sys_times
-101 64 ptrace sys_ptrace
-102 common getuid sys_getuid
-103 common syslog sys_syslog
-104 common getgid sys_getgid
-105 common setuid sys_setuid
-106 common setgid sys_setgid
-107 common geteuid sys_geteuid
-108 common getegid sys_getegid
-109 common setpgid sys_setpgid
-110 common getppid sys_getppid
-111 common getpgrp sys_getpgrp
-112 common setsid sys_setsid
-113 common setreuid sys_setreuid
-114 common setregid sys_setregid
-115 common getgroups sys_getgroups
-116 common setgroups sys_setgroups
-117 common setresuid sys_setresuid
-118 common getresuid sys_getresuid
-119 common setresgid sys_setresgid
-120 common getresgid sys_getresgid
-121 common getpgid sys_getpgid
-122 common setfsuid sys_setfsuid
-123 common setfsgid sys_setfsgid
-124 common getsid sys_getsid
-125 common capget sys_capget
-126 common capset sys_capset
-127 64 rt_sigpending sys_rt_sigpending
-128 64 rt_sigtimedwait sys_rt_sigtimedwait
-129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
-130 common rt_sigsuspend sys_rt_sigsuspend
-131 64 sigaltstack sys_sigaltstack
-132 common utime sys_utime
-133 common mknod sys_mknod
+0 common read __x64_sys_read
+1 common write __x64_sys_write
+2 common open __x64_sys_open
+3 common close __x64_sys_close
+4 common stat __x64_sys_newstat
+5 common fstat __x64_sys_newfstat
+6 common lstat __x64_sys_newlstat
+7 common poll __x64_sys_poll
+8 common lseek __x64_sys_lseek
+9 common mmap __x64_sys_mmap
+10 common mprotect __x64_sys_mprotect
+11 common munmap __x64_sys_munmap
+12 common brk __x64_sys_brk
+13 64 rt_sigaction __x64_sys_rt_sigaction
+14 common rt_sigprocmask __x64_sys_rt_sigprocmask
+15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs
+16 64 ioctl __x64_sys_ioctl
+17 common pread64 __x64_sys_pread64
+18 common pwrite64 __x64_sys_pwrite64
+19 64 readv __x64_sys_readv
+20 64 writev __x64_sys_writev
+21 common access __x64_sys_access
+22 common pipe __x64_sys_pipe
+23 common select __x64_sys_select
+24 common sched_yield __x64_sys_sched_yield
+25 common mremap __x64_sys_mremap
+26 common msync __x64_sys_msync
+27 common mincore __x64_sys_mincore
+28 common madvise __x64_sys_madvise
+29 common shmget __x64_sys_shmget
+30 common shmat __x64_sys_shmat
+31 common shmctl __x64_sys_shmctl
+32 common dup __x64_sys_dup
+33 common dup2 __x64_sys_dup2
+34 common pause __x64_sys_pause
+35 common nanosleep __x64_sys_nanosleep
+36 common getitimer __x64_sys_getitimer
+37 common alarm __x64_sys_alarm
+38 common setitimer __x64_sys_setitimer
+39 common getpid __x64_sys_getpid
+40 common sendfile __x64_sys_sendfile64
+41 common socket __x64_sys_socket
+42 common connect __x64_sys_connect
+43 common accept __x64_sys_accept
+44 common sendto __x64_sys_sendto
+45 64 recvfrom __x64_sys_recvfrom
+46 64 sendmsg __x64_sys_sendmsg
+47 64 recvmsg __x64_sys_recvmsg
+48 common shutdown __x64_sys_shutdown
+49 common bind __x64_sys_bind
+50 common listen __x64_sys_listen
+51 common getsockname __x64_sys_getsockname
+52 common getpeername __x64_sys_getpeername
+53 common socketpair __x64_sys_socketpair
+54 64 setsockopt __x64_sys_setsockopt
+55 64 getsockopt __x64_sys_getsockopt
+56 common clone __x64_sys_clone/ptregs
+57 common fork __x64_sys_fork/ptregs
+58 common vfork __x64_sys_vfork/ptregs
+59 64 execve __x64_sys_execve/ptregs
+60 common exit __x64_sys_exit
+61 common wait4 __x64_sys_wait4
+62 common kill __x64_sys_kill
+63 common uname __x64_sys_newuname
+64 common semget __x64_sys_semget
+65 common semop __x64_sys_semop
+66 common semctl __x64_sys_semctl
+67 common shmdt __x64_sys_shmdt
+68 common msgget __x64_sys_msgget
+69 common msgsnd __x64_sys_msgsnd
+70 common msgrcv __x64_sys_msgrcv
+71 common msgctl __x64_sys_msgctl
+72 common fcntl __x64_sys_fcntl
+73 common flock __x64_sys_flock
+74 common fsync __x64_sys_fsync
+75 common fdatasync __x64_sys_fdatasync
+76 common truncate __x64_sys_truncate
+77 common ftruncate __x64_sys_ftruncate
+78 common getdents __x64_sys_getdents
+79 common getcwd __x64_sys_getcwd
+80 common chdir __x64_sys_chdir
+81 common fchdir __x64_sys_fchdir
+82 common rename __x64_sys_rename
+83 common mkdir __x64_sys_mkdir
+84 common rmdir __x64_sys_rmdir
+85 common creat __x64_sys_creat
+86 common link __x64_sys_link
+87 common unlink __x64_sys_unlink
+88 common symlink __x64_sys_symlink
+89 common readlink __x64_sys_readlink
+90 common chmod __x64_sys_chmod
+91 common fchmod __x64_sys_fchmod
+92 common chown __x64_sys_chown
+93 common fchown __x64_sys_fchown
+94 common lchown __x64_sys_lchown
+95 common umask __x64_sys_umask
+96 common gettimeofday __x64_sys_gettimeofday
+97 common getrlimit __x64_sys_getrlimit
+98 common getrusage __x64_sys_getrusage
+99 common sysinfo __x64_sys_sysinfo
+100 common times __x64_sys_times
+101 64 ptrace __x64_sys_ptrace
+102 common getuid __x64_sys_getuid
+103 common syslog __x64_sys_syslog
+104 common getgid __x64_sys_getgid
+105 common setuid __x64_sys_setuid
+106 common setgid __x64_sys_setgid
+107 common geteuid __x64_sys_geteuid
+108 common getegid __x64_sys_getegid
+109 common setpgid __x64_sys_setpgid
+110 common getppid __x64_sys_getppid
+111 common getpgrp __x64_sys_getpgrp
+112 common setsid __x64_sys_setsid
+113 common setreuid __x64_sys_setreuid
+114 common setregid __x64_sys_setregid
+115 common getgroups __x64_sys_getgroups
+116 common setgroups __x64_sys_setgroups
+117 common setresuid __x64_sys_setresuid
+118 common getresuid __x64_sys_getresuid
+119 common setresgid __x64_sys_setresgid
+120 common getresgid __x64_sys_getresgid
+121 common getpgid __x64_sys_getpgid
+122 common setfsuid __x64_sys_setfsuid
+123 common setfsgid __x64_sys_setfsgid
+124 common getsid __x64_sys_getsid
+125 common capget __x64_sys_capget
+126 common capset __x64_sys_capset
+127 64 rt_sigpending __x64_sys_rt_sigpending
+128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait
+129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo
+130 common rt_sigsuspend __x64_sys_rt_sigsuspend
+131 64 sigaltstack __x64_sys_sigaltstack
+132 common utime __x64_sys_utime
+133 common mknod __x64_sys_mknod
134 64 uselib
-135 common personality sys_personality
-136 common ustat sys_ustat
-137 common statfs sys_statfs
-138 common fstatfs sys_fstatfs
-139 common sysfs sys_sysfs
-140 common getpriority sys_getpriority
-141 common setpriority sys_setpriority
-142 common sched_setparam sys_sched_setparam
-143 common sched_getparam sys_sched_getparam
-144 common sched_setscheduler sys_sched_setscheduler
-145 common sched_getscheduler sys_sched_getscheduler
-146 common sched_get_priority_max sys_sched_get_priority_max
-147 common sched_get_priority_min sys_sched_get_priority_min
-148 common sched_rr_get_interval sys_sched_rr_get_interval
-149 common mlock sys_mlock
-150 common munlock sys_munlock
-151 common mlockall sys_mlockall
-152 common munlockall sys_munlockall
-153 common vhangup sys_vhangup
-154 common modify_ldt sys_modify_ldt
-155 common pivot_root sys_pivot_root
-156 64 _sysctl sys_sysctl
-157 common prctl sys_prctl
-158 common arch_prctl sys_arch_prctl
-159 common adjtimex sys_adjtimex
-160 common setrlimit sys_setrlimit
-161 common chroot sys_chroot
-162 common sync sys_sync
-163 common acct sys_acct
-164 common settimeofday sys_settimeofday
-165 common mount sys_mount
-166 common umount2 sys_umount
-167 common swapon sys_swapon
-168 common swapoff sys_swapoff
-169 common reboot sys_reboot
-170 common sethostname sys_sethostname
-171 common setdomainname sys_setdomainname
-172 common iopl sys_iopl/ptregs
-173 common ioperm sys_ioperm
+135 common personality __x64_sys_personality
+136 common ustat __x64_sys_ustat
+137 common statfs __x64_sys_statfs
+138 common fstatfs __x64_sys_fstatfs
+139 common sysfs __x64_sys_sysfs
+140 common getpriority __x64_sys_getpriority
+141 common setpriority __x64_sys_setpriority
+142 common sched_setparam __x64_sys_sched_setparam
+143 common sched_getparam __x64_sys_sched_getparam
+144 common sched_setscheduler __x64_sys_sched_setscheduler
+145 common sched_getscheduler __x64_sys_sched_getscheduler
+146 common sched_get_priority_max __x64_sys_sched_get_priority_max
+147 common sched_get_priority_min __x64_sys_sched_get_priority_min
+148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval
+149 common mlock __x64_sys_mlock
+150 common munlock __x64_sys_munlock
+151 common mlockall __x64_sys_mlockall
+152 common munlockall __x64_sys_munlockall
+153 common vhangup __x64_sys_vhangup
+154 common modify_ldt __x64_sys_modify_ldt
+155 common pivot_root __x64_sys_pivot_root
+156 64 _sysctl __x64_sys_sysctl
+157 common prctl __x64_sys_prctl
+158 common arch_prctl __x64_sys_arch_prctl
+159 common adjtimex __x64_sys_adjtimex
+160 common setrlimit __x64_sys_setrlimit
+161 common chroot __x64_sys_chroot
+162 common sync __x64_sys_sync
+163 common acct __x64_sys_acct
+164 common settimeofday __x64_sys_settimeofday
+165 common mount __x64_sys_mount
+166 common umount2 __x64_sys_umount
+167 common swapon __x64_sys_swapon
+168 common swapoff __x64_sys_swapoff
+169 common reboot __x64_sys_reboot
+170 common sethostname __x64_sys_sethostname
+171 common setdomainname __x64_sys_setdomainname
+172 common iopl __x64_sys_iopl/ptregs
+173 common ioperm __x64_sys_ioperm
174 64 create_module
-175 common init_module sys_init_module
-176 common delete_module sys_delete_module
+175 common init_module __x64_sys_init_module
+176 common delete_module __x64_sys_delete_module
177 64 get_kernel_syms
178 64 query_module
-179 common quotactl sys_quotactl
+179 common quotactl __x64_sys_quotactl
180 64 nfsservctl
181 common getpmsg
182 common putpmsg
183 common afs_syscall
184 common tuxcall
185 common security
-186 common gettid sys_gettid
-187 common readahead sys_readahead
-188 common setxattr sys_setxattr
-189 common lsetxattr sys_lsetxattr
-190 common fsetxattr sys_fsetxattr
-191 common getxattr sys_getxattr
-192 common lgetxattr sys_lgetxattr
-193 common fgetxattr sys_fgetxattr
-194 common listxattr sys_listxattr
-195 common llistxattr sys_llistxattr
-196 common flistxattr sys_flistxattr
-197 common removexattr sys_removexattr
-198 common lremovexattr sys_lremovexattr
-199 common fremovexattr sys_fremovexattr
-200 common tkill sys_tkill
-201 common time sys_time
-202 common futex sys_futex
-203 common sched_setaffinity sys_sched_setaffinity
-204 common sched_getaffinity sys_sched_getaffinity
+186 common gettid __x64_sys_gettid
+187 common readahead __x64_sys_readahead
+188 common setxattr __x64_sys_setxattr
+189 common lsetxattr __x64_sys_lsetxattr
+190 common fsetxattr __x64_sys_fsetxattr
+191 common getxattr __x64_sys_getxattr
+192 common lgetxattr __x64_sys_lgetxattr
+193 common fgetxattr __x64_sys_fgetxattr
+194 common listxattr __x64_sys_listxattr
+195 common llistxattr __x64_sys_llistxattr
+196 common flistxattr __x64_sys_flistxattr
+197 common removexattr __x64_sys_removexattr
+198 common lremovexattr __x64_sys_lremovexattr
+199 common fremovexattr __x64_sys_fremovexattr
+200 common tkill __x64_sys_tkill
+201 common time __x64_sys_time
+202 common futex __x64_sys_futex
+203 common sched_setaffinity __x64_sys_sched_setaffinity
+204 common sched_getaffinity __x64_sys_sched_getaffinity
205 64 set_thread_area
-206 64 io_setup sys_io_setup
-207 common io_destroy sys_io_destroy
-208 common io_getevents sys_io_getevents
-209 64 io_submit sys_io_submit
-210 common io_cancel sys_io_cancel
+206 64 io_setup __x64_sys_io_setup
+207 common io_destroy __x64_sys_io_destroy
+208 common io_getevents __x64_sys_io_getevents
+209 64 io_submit __x64_sys_io_submit
+210 common io_cancel __x64_sys_io_cancel
211 64 get_thread_area
-212 common lookup_dcookie sys_lookup_dcookie
-213 common epoll_create sys_epoll_create
+212 common lookup_dcookie __x64_sys_lookup_dcookie
+213 common epoll_create __x64_sys_epoll_create
214 64 epoll_ctl_old
215 64 epoll_wait_old
-216 common remap_file_pages sys_remap_file_pages
-217 common getdents64 sys_getdents64
-218 common set_tid_address sys_set_tid_address
-219 common restart_syscall sys_restart_syscall
-220 common semtimedop sys_semtimedop
-221 common fadvise64 sys_fadvise64
-222 64 timer_create sys_timer_create
-223 common timer_settime sys_timer_settime
-224 common timer_gettime sys_timer_gettime
-225 common timer_getoverrun sys_timer_getoverrun
-226 common timer_delete sys_timer_delete
-227 common clock_settime sys_clock_settime
-228 common clock_gettime sys_clock_gettime
-229 common clock_getres sys_clock_getres
-230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
-232 common epoll_wait sys_epoll_wait
-233 common epoll_ctl sys_epoll_ctl
-234 common tgkill sys_tgkill
-235 common utimes sys_utimes
+216 common remap_file_pages __x64_sys_remap_file_pages
+217 common getdents64 __x64_sys_getdents64
+218 common set_tid_address __x64_sys_set_tid_address
+219 common restart_syscall __x64_sys_restart_syscall
+220 common semtimedop __x64_sys_semtimedop
+221 common fadvise64 __x64_sys_fadvise64
+222 64 timer_create __x64_sys_timer_create
+223 common timer_settime __x64_sys_timer_settime
+224 common timer_gettime __x64_sys_timer_gettime
+225 common timer_getoverrun __x64_sys_timer_getoverrun
+226 common timer_delete __x64_sys_timer_delete
+227 common clock_settime __x64_sys_clock_settime
+228 common clock_gettime __x64_sys_clock_gettime
+229 common clock_getres __x64_sys_clock_getres
+230 common clock_nanosleep __x64_sys_clock_nanosleep
+231 common exit_group __x64_sys_exit_group
+232 common epoll_wait __x64_sys_epoll_wait
+233 common epoll_ctl __x64_sys_epoll_ctl
+234 common tgkill __x64_sys_tgkill
+235 common utimes __x64_sys_utimes
236 64 vserver
-237 common mbind sys_mbind
-238 common set_mempolicy sys_set_mempolicy
-239 common get_mempolicy sys_get_mempolicy
-240 common mq_open sys_mq_open
-241 common mq_unlink sys_mq_unlink
-242 common mq_timedsend sys_mq_timedsend
-243 common mq_timedreceive sys_mq_timedreceive
-244 64 mq_notify sys_mq_notify
-245 common mq_getsetattr sys_mq_getsetattr
-246 64 kexec_load sys_kexec_load
-247 64 waitid sys_waitid
-248 common add_key sys_add_key
-249 common request_key sys_request_key
-250 common keyctl sys_keyctl
-251 common ioprio_set sys_ioprio_set
-252 common ioprio_get sys_ioprio_get
-253 common inotify_init sys_inotify_init
-254 common inotify_add_watch sys_inotify_add_watch
-255 common inotify_rm_watch sys_inotify_rm_watch
-256 common migrate_pages sys_migrate_pages
-257 common openat sys_openat
-258 common mkdirat sys_mkdirat
-259 common mknodat sys_mknodat
-260 common fchownat sys_fchownat
-261 common futimesat sys_futimesat
-262 common newfstatat sys_newfstatat
-263 common unlinkat sys_unlinkat
-264 common renameat sys_renameat
-265 common linkat sys_linkat
-266 common symlinkat sys_symlinkat
-267 common readlinkat sys_readlinkat
-268 common fchmodat sys_fchmodat
-269 common faccessat sys_faccessat
-270 common pselect6 sys_pselect6
-271 common ppoll sys_ppoll
-272 common unshare sys_unshare
-273 64 set_robust_list sys_set_robust_list
-274 64 get_robust_list sys_get_robust_list
-275 common splice sys_splice
-276 common tee sys_tee
-277 common sync_file_range sys_sync_file_range
-278 64 vmsplice sys_vmsplice
-279 64 move_pages sys_move_pages
-280 common utimensat sys_utimensat
-281 common epoll_pwait sys_epoll_pwait
-282 common signalfd sys_signalfd
-283 common timerfd_create sys_timerfd_create
-284 common eventfd sys_eventfd
-285 common fallocate sys_fallocate
-286 common timerfd_settime sys_timerfd_settime
-287 common timerfd_gettime sys_timerfd_gettime
-288 common accept4 sys_accept4
-289 common signalfd4 sys_signalfd4
-290 common eventfd2 sys_eventfd2
-291 common epoll_create1 sys_epoll_create1
-292 common dup3 sys_dup3
-293 common pipe2 sys_pipe2
-294 common inotify_init1 sys_inotify_init1
-295 64 preadv sys_preadv
-296 64 pwritev sys_pwritev
-297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
-298 common perf_event_open sys_perf_event_open
-299 64 recvmmsg sys_recvmmsg
-300 common fanotify_init sys_fanotify_init
-301 common fanotify_mark sys_fanotify_mark
-302 common prlimit64 sys_prlimit64
-303 common name_to_handle_at sys_name_to_handle_at
-304 common open_by_handle_at sys_open_by_handle_at
-305 common clock_adjtime sys_clock_adjtime
-306 common syncfs sys_syncfs
-307 64 sendmmsg sys_sendmmsg
-308 common setns sys_setns
-309 common getcpu sys_getcpu
-310 64 process_vm_readv sys_process_vm_readv
-311 64 process_vm_writev sys_process_vm_writev
-312 common kcmp sys_kcmp
-313 common finit_module sys_finit_module
-314 common sched_setattr sys_sched_setattr
-315 common sched_getattr sys_sched_getattr
-316 common renameat2 sys_renameat2
-317 common seccomp sys_seccomp
-318 common getrandom sys_getrandom
-319 common memfd_create sys_memfd_create
-320 common kexec_file_load sys_kexec_file_load
-321 common bpf sys_bpf
-322 64 execveat sys_execveat/ptregs
-323 common userfaultfd sys_userfaultfd
-324 common membarrier sys_membarrier
-325 common mlock2 sys_mlock2
-326 common copy_file_range sys_copy_file_range
-327 64 preadv2 sys_preadv2
-328 64 pwritev2 sys_pwritev2
-329 common pkey_mprotect sys_pkey_mprotect
-330 common pkey_alloc sys_pkey_alloc
-331 common pkey_free sys_pkey_free
-332 common statx sys_statx
+237 common mbind __x64_sys_mbind
+238 common set_mempolicy __x64_sys_set_mempolicy
+239 common get_mempolicy __x64_sys_get_mempolicy
+240 common mq_open __x64_sys_mq_open
+241 common mq_unlink __x64_sys_mq_unlink
+242 common mq_timedsend __x64_sys_mq_timedsend
+243 common mq_timedreceive __x64_sys_mq_timedreceive
+244 64 mq_notify __x64_sys_mq_notify
+245 common mq_getsetattr __x64_sys_mq_getsetattr
+246 64 kexec_load __x64_sys_kexec_load
+247 64 waitid __x64_sys_waitid
+248 common add_key __x64_sys_add_key
+249 common request_key __x64_sys_request_key
+250 common keyctl __x64_sys_keyctl
+251 common ioprio_set __x64_sys_ioprio_set
+252 common ioprio_get __x64_sys_ioprio_get
+253 common inotify_init __x64_sys_inotify_init
+254 common inotify_add_watch __x64_sys_inotify_add_watch
+255 common inotify_rm_watch __x64_sys_inotify_rm_watch
+256 common migrate_pages __x64_sys_migrate_pages
+257 common openat __x64_sys_openat
+258 common mkdirat __x64_sys_mkdirat
+259 common mknodat __x64_sys_mknodat
+260 common fchownat __x64_sys_fchownat
+261 common futimesat __x64_sys_futimesat
+262 common newfstatat __x64_sys_newfstatat
+263 common unlinkat __x64_sys_unlinkat
+264 common renameat __x64_sys_renameat
+265 common linkat __x64_sys_linkat
+266 common symlinkat __x64_sys_symlinkat
+267 common readlinkat __x64_sys_readlinkat
+268 common fchmodat __x64_sys_fchmodat
+269 common faccessat __x64_sys_faccessat
+270 common pselect6 __x64_sys_pselect6
+271 common ppoll __x64_sys_ppoll
+272 common unshare __x64_sys_unshare
+273 64 set_robust_list __x64_sys_set_robust_list
+274 64 get_robust_list __x64_sys_get_robust_list
+275 common splice __x64_sys_splice
+276 common tee __x64_sys_tee
+277 common sync_file_range __x64_sys_sync_file_range
+278 64 vmsplice __x64_sys_vmsplice
+279 64 move_pages __x64_sys_move_pages
+280 common utimensat __x64_sys_utimensat
+281 common epoll_pwait __x64_sys_epoll_pwait
+282 common signalfd __x64_sys_signalfd
+283 common timerfd_create __x64_sys_timerfd_create
+284 common eventfd __x64_sys_eventfd
+285 common fallocate __x64_sys_fallocate
+286 common timerfd_settime __x64_sys_timerfd_settime
+287 common timerfd_gettime __x64_sys_timerfd_gettime
+288 common accept4 __x64_sys_accept4
+289 common signalfd4 __x64_sys_signalfd4
+290 common eventfd2 __x64_sys_eventfd2
+291 common epoll_create1 __x64_sys_epoll_create1
+292 common dup3 __x64_sys_dup3
+293 common pipe2 __x64_sys_pipe2
+294 common inotify_init1 __x64_sys_inotify_init1
+295 64 preadv __x64_sys_preadv
+296 64 pwritev __x64_sys_pwritev
+297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo
+298 common perf_event_open __x64_sys_perf_event_open
+299 64 recvmmsg __x64_sys_recvmmsg
+300 common fanotify_init __x64_sys_fanotify_init
+301 common fanotify_mark __x64_sys_fanotify_mark
+302 common prlimit64 __x64_sys_prlimit64
+303 common name_to_handle_at __x64_sys_name_to_handle_at
+304 common open_by_handle_at __x64_sys_open_by_handle_at
+305 common clock_adjtime __x64_sys_clock_adjtime
+306 common syncfs __x64_sys_syncfs
+307 64 sendmmsg __x64_sys_sendmmsg
+308 common setns __x64_sys_setns
+309 common getcpu __x64_sys_getcpu
+310 64 process_vm_readv __x64_sys_process_vm_readv
+311 64 process_vm_writev __x64_sys_process_vm_writev
+312 common kcmp __x64_sys_kcmp
+313 common finit_module __x64_sys_finit_module
+314 common sched_setattr __x64_sys_sched_setattr
+315 common sched_getattr __x64_sys_sched_getattr
+316 common renameat2 __x64_sys_renameat2
+317 common seccomp __x64_sys_seccomp
+318 common getrandom __x64_sys_getrandom
+319 common memfd_create __x64_sys_memfd_create
+320 common kexec_file_load __x64_sys_kexec_file_load
+321 common bpf __x64_sys_bpf
+322 64 execveat __x64_sys_execveat/ptregs
+323 common userfaultfd __x64_sys_userfaultfd
+324 common membarrier __x64_sys_membarrier
+325 common mlock2 __x64_sys_mlock2
+326 common copy_file_range __x64_sys_copy_file_range
+327 64 preadv2 __x64_sys_preadv2
+328 64 pwritev2 __x64_sys_pwritev2
+329 common pkey_mprotect __x64_sys_pkey_mprotect
+330 common pkey_alloc __x64_sys_pkey_alloc
+331 common pkey_free __x64_sys_pkey_free
+332 common statx __x64_sys_statx
#
# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation.
+# for native 64-bit operation. The __x32_compat_sys stubs are created
+# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
+# is defined.
#
-512 x32 rt_sigaction compat_sys_rt_sigaction
+512 x32 rt_sigaction __x32_compat_sys_rt_sigaction
513 x32 rt_sigreturn sys32_x32_rt_sigreturn
-514 x32 ioctl compat_sys_ioctl
-515 x32 readv compat_sys_readv
-516 x32 writev compat_sys_writev
-517 x32 recvfrom compat_sys_recvfrom
-518 x32 sendmsg compat_sys_sendmsg
-519 x32 recvmsg compat_sys_recvmsg
-520 x32 execve compat_sys_execve/ptregs
-521 x32 ptrace compat_sys_ptrace
-522 x32 rt_sigpending compat_sys_rt_sigpending
-523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait
-524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo
-525 x32 sigaltstack compat_sys_sigaltstack
-526 x32 timer_create compat_sys_timer_create
-527 x32 mq_notify compat_sys_mq_notify
-528 x32 kexec_load compat_sys_kexec_load
-529 x32 waitid compat_sys_waitid
-530 x32 set_robust_list compat_sys_set_robust_list
-531 x32 get_robust_list compat_sys_get_robust_list
-532 x32 vmsplice compat_sys_vmsplice
-533 x32 move_pages compat_sys_move_pages
-534 x32 preadv compat_sys_preadv64
-535 x32 pwritev compat_sys_pwritev64
-536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
-537 x32 recvmmsg compat_sys_recvmmsg
-538 x32 sendmmsg compat_sys_sendmmsg
-539 x32 process_vm_readv compat_sys_process_vm_readv
-540 x32 process_vm_writev compat_sys_process_vm_writev
-541 x32 setsockopt compat_sys_setsockopt
-542 x32 getsockopt compat_sys_getsockopt
-543 x32 io_setup compat_sys_io_setup
-544 x32 io_submit compat_sys_io_submit
-545 x32 execveat compat_sys_execveat/ptregs
-546 x32 preadv2 compat_sys_preadv64v2
-547 x32 pwritev2 compat_sys_pwritev64v2
+514 x32 ioctl __x32_compat_sys_ioctl
+515 x32 readv __x32_compat_sys_readv
+516 x32 writev __x32_compat_sys_writev
+517 x32 recvfrom __x32_compat_sys_recvfrom
+518 x32 sendmsg __x32_compat_sys_sendmsg
+519 x32 recvmsg __x32_compat_sys_recvmsg
+520 x32 execve __x32_compat_sys_execve/ptregs
+521 x32 ptrace __x32_compat_sys_ptrace
+522 x32 rt_sigpending __x32_compat_sys_rt_sigpending
+523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait
+524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo
+525 x32 sigaltstack __x32_compat_sys_sigaltstack
+526 x32 timer_create __x32_compat_sys_timer_create
+527 x32 mq_notify __x32_compat_sys_mq_notify
+528 x32 kexec_load __x32_compat_sys_kexec_load
+529 x32 waitid __x32_compat_sys_waitid
+530 x32 set_robust_list __x32_compat_sys_set_robust_list
+531 x32 get_robust_list __x32_compat_sys_get_robust_list
+532 x32 vmsplice __x32_compat_sys_vmsplice
+533 x32 move_pages __x32_compat_sys_move_pages
+534 x32 preadv __x32_compat_sys_preadv64
+535 x32 pwritev __x32_compat_sys_pwritev64
+536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo
+537 x32 recvmmsg __x32_compat_sys_recvmmsg
+538 x32 sendmmsg __x32_compat_sys_sendmmsg
+539 x32 process_vm_readv __x32_compat_sys_process_vm_readv
+540 x32 process_vm_writev __x32_compat_sys_process_vm_writev
+541 x32 setsockopt __x32_compat_sys_setsockopt
+542 x32 getsockopt __x32_compat_sys_getsockopt
+543 x32 io_setup __x32_compat_sys_io_setup
+544 x32 io_submit __x32_compat_sys_io_submit
+545 x32 execveat __x32_compat_sys_execveat/ptregs
+546 x32 preadv2 __x32_compat_sys_preadv64v2
+547 x32 pwritev2 __x32_compat_sys_pwritev64v2
OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"),
OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"),
- OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"),
+ OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"),
OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"),
OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"),
OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
"trace",
#endif
NULL };
};
argc = parse_options(argc, argv, options, record_mem_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ PARSE_OPT_KEEP_UNKNOWN);
rec_argc = argc + 9; /* max number of arguments */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
}
argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
- mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
+ mem_usage, PARSE_OPT_KEEP_UNKNOWN);
if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
usage_with_options(mem_usage, mem_options);
break;
case PERF_RECORD_SWITCH:
case PERF_RECORD_SWITCH_CPU_WIDE:
- if (has(SWITCH_OUT))
+ if (has(SWITCH_OUT)) {
ret += fprintf(fp, "S");
+ if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT)
+ ret += fprintf(fp, "p");
+ }
default:
break;
}
for_each_lang(scripts_path, scripts_dir, lang_dirent) {
scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
lang_dirent->d_name);
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
if (strstr(lang_path, "perl"))
continue;
#endif
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
if (strstr(lang_path, "python"))
continue;
#endif
static const char *output_name;
static int output_fd;
static int print_free_counters_hint;
+static int print_mixed_hw_group_error;
struct perf_stat {
bool record;
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
}
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+ struct perf_evlist *evlist = counter->evlist;
+ u32 pmu_type = counter->attr.type;
+ struct perf_evsel *pos;
+
+ if (counter->nr_members < 2)
+ return false;
+
+ evlist__for_each_entry(evlist, pos) {
+ /* software events can be part of any hardware group */
+ if (pos->attr.type == PERF_TYPE_SOFTWARE)
+ continue;
+ if (pmu_type == PERF_TYPE_SOFTWARE) {
+ pmu_type = pos->attr.type;
+ continue;
+ }
+ if (pmu_type != pos->attr.type)
+ return true;
+ }
+
+ return false;
+}
+
static void printout(int id, int nr, struct perf_evsel *counter, double uval,
char *prefix, u64 run, u64 ena, double noise,
struct runtime_stat *st)
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep);
- if (counter->supported)
+ if (counter->supported) {
print_free_counters_hint = 1;
+ if (is_mixed_hw_group(counter))
+ print_mixed_hw_group_error = 1;
+ }
fprintf(stat_config.output, "%-*s%s",
csv_output ? 0 : unit_width,
char *new_name;
char *config;
- if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+ if (counter->uniquified_name ||
+ !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
strlen(counter->pmu_name)))
return;
counter->name = new_name;
}
}
+
+ counter->uniquified_name = true;
}
static void collect_all_aliases(struct perf_evsel *counter,
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
" perf stat ...\n"
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+ if (print_mixed_hw_group_error)
+ fprintf(output,
+ "The events in group usually have to be from "
+ "the same PMU. Try reorganizing the group.\n");
}
static void print_counters(struct timespec *ts, int argc, const char **argv)
OPT_STRING(0, "post", &post_cmd, "command",
"command to run after to the measured command"),
OPT_UINTEGER('I', "interval-print", &stat_config.interval,
- "print counts at regular interval in ms (>= 10)"),
+ "print counts at regular interval in ms "
+ "(overhead is possible for values <= 100ms)"),
OPT_INTEGER(0, "interval-count", &stat_config.times,
"print counts for fixed number of times"),
OPT_UINTEGER(0, "timeout", &stat_config.timeout,
}
}
- if (interval && interval < 100) {
- if (interval < 10) {
- pr_err("print interval must be >= 10ms\n");
- parse_options_usage(stat_usage, stat_options, "I", 1);
- goto out;
- } else
- pr_warning("print interval < 100ms. "
- "The overhead percentage could be high in some cases. "
- "Please proceed with caution.\n");
- }
-
if (stat_config.times && interval)
interval_count = true;
else if (stat_config.times && !interval) {
STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
STATUS(HAVE_GLIBC_SUPPORT, glibc);
STATUS(HAVE_GTK2_SUPPORT, gtk2);
+#ifndef HAVE_SYSCALL_TABLE_SUPPORT
STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+#endif
+ STATUS(HAVE_SYSCALL_TABLE_SUPPORT, syscall_table);
STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
STATUS(HAVE_LIBELF_SUPPORT, libelf);
STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
{ "lock", cmd_lock, 0 },
{ "kvm", cmd_kvm, 0 },
{ "test", cmd_test, 0 },
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
{ "trace", cmd_trace, 0 },
#endif
{ "inject", cmd_inject, 0 },
argv[0] = cmd;
}
if (strstarts(cmd, "trace")) {
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
setup_path();
argv[0] = "trace";
return cmd_trace(argc, argv);
Family-model,Version,Filename,EventType
-209[78],1,cf_z10,core
-281[78],1,cf_z196,core
-282[78],1,cf_zec12,core
-296[45],1,cf_z13,core
-3906,3,cf_z14,core
+^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core
+^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core
+^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
+^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
+^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
GenuineIntel-6-4C,v13,silvermont,core
GenuineIntel-6-2A,v15,sandybridge,core
GenuineIntel-6-2C,v2,westmereep-dp,core
-GenuineIntel-6-2C,v2,westmereep-dp,core
GenuineIntel-6-25,v2,westmereep-sp,core
GenuineIntel-6-2F,v2,westmereex,core
GenuineIntel-6-55,v1,skylakex,core
# sampling disabled
sample_freq=0
sample_period=0
+freq=0
+write_backward=0
+sample_id_all=0
.max_entries = 1,
};
-SEC("func=SyS_epoll_pwait")
+SEC("func=do_epoll_wait")
int bpf_func__SyS_epoll_pwait(void *ctx)
{
int ind =0;
#define SEC(NAME) __attribute__((section(NAME), used))
#include <uapi/linux/fs.h>
-#include <uapi/asm/ptrace.h>
SEC("func=vfs_llseek")
int bpf_func__vfs_llseek(void *ctx)
{
.desc = "Breakpoint accounting",
.func = test__bp_accounting,
+ .is_supported = test__bp_signal_is_supported,
},
{
.desc = "Number of exit events of a simple workload",
snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
evsels[i] = perf_evsel__newtp("syscalls", name);
if (IS_ERR(evsels[i])) {
- pr_debug("perf_evsel__new\n");
+ pr_debug("perf_evsel__new(%s)\n", name);
goto out_delete_evlist;
}
trace_libc_inet_pton_backtrace() {
idx=0
expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
- expected[1]=".*inet_pton[[:space:]]\($libc\)$"
+ expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$"
case "$(uname -m)" in
s390x)
- eventattr='call-graph=dwarf'
+ eventattr='call-graph=dwarf,max-stack=4'
expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
- expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
+ expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$"
expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
- expected[5]="__libc_start_main[[:space:]]\($libc\)$"
- expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$"
;;
*)
eventattr='max-stack=3'
P_MMAP_FLAG(EXECUTABLE);
P_MMAP_FLAG(FILE);
P_MMAP_FLAG(FIXED);
+#ifdef MAP_FIXED_NOREPLACE
+ P_MMAP_FLAG(FIXED_NOREPLACE);
+#endif
P_MMAP_FLAG(GROWSDOWN);
P_MMAP_FLAG(HUGETLB);
P_MMAP_FLAG(LOCKED);
"J Toggle showing number of jump sources on targets\n"
"n Search next string\n"
"o Toggle disassembler output/simplified view\n"
+ "O Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
"s Toggle source code view\n"
"t Circulate percent, total period, samples view\n"
"/ Search string\n"
notes->options->use_offset = !notes->options->use_offset;
annotation__update_column_widths(notes);
continue;
+ case 'O':
+ if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+ notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+ continue;
case 'j':
notes->options->jump_arrows = !notes->options->jump_arrows;
continue;
"h/?/F1 Show this window\n" \
"UP/DOWN/PGUP\n" \
"PGDN/SPACE Navigate\n" \
- "q/ESC/CTRL+C Exit browser\n\n" \
+ "q/ESC/CTRL+C Exit browser or go back to previous screen\n\n" \
"For multiple event sessions:\n\n" \
"TAB/UNTAB Switch events\n\n" \
"For symbolic views (--sort has sym):\n\n" \
struct annotation_options annotation__default_options = {
.use_offset = true,
.jump_arrows = true,
+ .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS,
};
const char *disassembler_style;
max_percent = sample->percent;
}
+ if (al->samples_nr > nr_percent)
+ nr_percent = al->samples_nr;
+
if (max_percent < min_pcnt)
return -1;
if (!notes->options->use_offset) {
printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
} else {
- if (al->jump_sources) {
+ if (al->jump_sources &&
+ notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
if (notes->options->show_nr_jumps) {
int prev;
printed = scnprintf(bf, sizeof(bf), "%*d ",
obj__printf(obj, bf);
obj__set_color(obj, prev);
}
-
+print_addr:
printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
notes->widths.target, addr);
+ } else if (ins__is_call(&disasm_line(al)->ins) &&
+ notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+ goto print_addr;
+ } else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+ goto print_addr;
} else {
printed = scnprintf(bf, sizeof(bf), "%-*s ",
notes->widths.addr, " ");
*/
static struct annotation_config {
const char *name;
- bool *value;
+ void *value;
} annotation__configs[] = {
ANNOTATION__CFG(hide_src_code),
ANNOTATION__CFG(jump_arrows),
+ ANNOTATION__CFG(offset_level),
ANNOTATION__CFG(show_linenr),
ANNOTATION__CFG(show_nr_jumps),
ANNOTATION__CFG(show_nr_samples),
if (cfg == NULL)
pr_debug("%s variable unknown, ignoring...", var);
- else
- *cfg->value = perf_config_bool(name, value);
+ else if (strcmp(var, "annotate.offset_level") == 0) {
+ perf_config_int(cfg->value, name, value);
+
+ if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
+ *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
+ else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
+ *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+ } else {
+ *(bool *)cfg->value = perf_config_bool(name, value);
+ }
return 0;
}
show_nr_jumps,
show_nr_samples,
show_total_period;
+ u8 offset_level;
};
+enum {
+ ANNOTATION__OFFSET_JUMP_TARGETS = 1,
+ ANNOTATION__OFFSET_CALL,
+ ANNOTATION__MAX_OFFSET_LEVEL,
+};
+
+#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS
+
extern struct annotation_options annotation__default_options;
struct annotation;
+// SPDX-License-Identifier: GPL-2.0
/*
- * SPDX-License-Identifier: GPL-2.0
- *
* Copyright(C) 2015-2018 Linaro Limited.
*
* Author: Tor Jeremiassen <tor@ti.com>
+// SPDX-License-Identifier: GPL-2.0
/*
- * SPDX-License-Identifier: GPL-2.0
- *
* Copyright(C) 2015-2018 Linaro Limited.
*
* Author: Tor Jeremiassen <tor@ti.com>
for (i = 0; i < aux->num_cpu; i++)
zfree(&aux->metadata[i]);
+ thread__zput(aux->unknown_thread);
zfree(&aux->metadata);
zfree(&aux);
}
return buff->len;
}
-static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
- struct auxtrace_queue *queue)
+static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+ struct auxtrace_queue *queue)
{
struct cs_etm_queue *etmq = queue->priv;
etm->auxtrace.free = cs_etm__free;
session->auxtrace = &etm->auxtrace;
+ etm->unknown_thread = thread__new(999999999, 999999999);
+ if (!etm->unknown_thread)
+ goto err_free_queues;
+
+ /*
+ * Initialize list node so that at thread__zput() we can avoid
+ * segmentation fault at list_del_init().
+ */
+ INIT_LIST_HEAD(&etm->unknown_thread->node);
+
+ err = thread__set_comm(etm->unknown_thread, "unknown", 0);
+ if (err)
+ goto err_delete_thread;
+
+ if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+ goto err_delete_thread;
+
if (dump_trace) {
cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
return 0;
err = cs_etm__synth_events(etm, session);
if (err)
- goto err_free_queues;
+ goto err_delete_thread;
err = auxtrace_queues__process_index(&etm->queues, session);
if (err)
- goto err_free_queues;
+ goto err_delete_thread;
etm->data_queued = etm->queues.populated;
return 0;
+err_delete_thread:
+ thread__zput(etm->unknown_thread);
err_free_queues:
auxtrace_queues__free(&etm->queues);
session->auxtrace = NULL;
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
{
bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
- const char *in_out = out ? "OUT" : "IN ";
+ const char *in_out = !out ? "IN " :
+ !(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+ "OUT " : "OUT preempt";
if (event->header.type == PERF_RECORD_SWITCH)
return fprintf(fp, " %s\n", in_out);
* than leader in case leader 'leads' the sampling.
*/
if ((leader != evsel) && leader->sample_read) {
- attr->sample_freq = 0;
- attr->sample_period = 0;
+ attr->freq = 0;
+ attr->sample_freq = 0;
+ attr->sample_period = 0;
+ attr->write_backward = 0;
+ attr->sample_id_all = 0;
}
if (opts->no_samples)
goto fallback_missing_features;
} else if (!perf_missing_features.group_read &&
evsel->attr.inherit &&
- (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+ (evsel->attr.read_format & PERF_FORMAT_GROUP) &&
+ perf_evsel__is_group_leader(evsel)) {
perf_missing_features.group_read = true;
pr_debug2("switching off group read\n");
goto fallback_missing_features;
(paranoid = perf_event_paranoid()) > 1) {
const char *name = perf_evsel__name(evsel);
char *new_name;
+ const char *sep = ":";
- if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+ /* Is there already the separator in the name. */
+ if (strchr(name, '/') ||
+ strchr(name, ':'))
+ sep = "";
+
+ if (asprintf(&new_name, "%s%su", name, sep) < 0)
return false;
if (evsel->name)
#if defined(__i386__) || defined(__x86_64__)
if (evsel->attr.type == PERF_TYPE_HARDWARE)
return scnprintf(msg, size, "%s",
- "No hardware sampling interrupt available.\n"
- "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+ "No hardware sampling interrupt available.\n");
#endif
break;
case EBUSY:
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
- "/bin/dmesg may provide additional information.\n"
- "No CONFIG_PERF_EVENTS=y kernel support configured?",
+ "/bin/dmesg | grep -i perf may provide additional information.\n",
err, str_error_r(err, sbuf, sizeof(sbuf)),
perf_evsel__name(evsel));
}
unsigned int sample_size;
int id_pos;
int is_pos;
+ bool uniquified_name;
bool snapshot;
bool supported;
bool needs_swap;
done
echo "#endif /* HAVE_LIBELF_SUPPORT */"
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt |
sort |
while read cmd
dir = opendir(path);
if (!dir) {
- pr_warning("failed: can't open node sysfs data\n");
+ pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+ __func__, path);
return -1;
}
return ret;
}
-static void map_groups__fixup_end(struct map_groups *mg)
-{
- int i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- __map_groups__fixup_end(mg, i);
-}
-
static char *get_kernel_version(const char *root_dir)
{
char version[PATH_MAX];
{
struct dso *kernel = machine__get_kernel(machine);
const char *name = NULL;
+ struct map *map;
u64 addr = 0;
int ret;
machine__destroy_kernel_maps(machine);
return -1;
}
- machine__set_kernel_mmap(machine, addr, 0);
+
+ /* we have a real start address now, so re-order the kmaps */
+ map = machine__kernel_map(machine);
+
+ map__get(map);
+ map_groups__remove(&machine->kmaps, map);
+
+ /* assume it's the last in the kmaps */
+ machine__set_kernel_mmap(machine, addr, ~0ULL);
+
+ map_groups__insert(&machine->kmaps, map);
+ map__put(map);
}
- /*
- * Now that we have all the maps created, just set the ->end of them:
- */
- map_groups__fixup_end(&machine->kmaps);
+ /* update end address of the kernel map using adjacent module address */
+ map = map__next(machine__kernel_map(machine));
+ if (map)
+ machine__set_kernel_mmap(machine, addr, map->start);
+
return 0;
}
struct perf_evsel *last;
if (list_empty(&parse_state.list)) {
- WARN_ONCE(true, "WARNING: event parser found nothing");
+ WARN_ONCE(true, "WARNING: event parser found nothing\n");
return -1;
}
/*
* PMU CORE devices have different name other than cpu in sysfs on some
- * platforms. looking for possible sysfs files to identify as core device.
+ * platforms.
+ * Looking for possible sysfs files to identify the arm core device.
*/
-static int is_pmu_core(const char *name)
+static int is_arm_pmu_core(const char *name)
{
struct stat st;
char path[PATH_MAX];
if (!sysfs)
return 0;
- /* Look for cpu sysfs (x86 and others) */
- scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
- if ((stat(path, &st) == 0) &&
- (strncmp(name, "cpu", strlen("cpu")) == 0))
- return 1;
-
/* Look for cpu sysfs (specific to arm) */
scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
sysfs, name);
if (stat(path, &st) == 0)
return 1;
+ /* Look for cpu sysfs (specific to s390) */
+ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
+ sysfs, name);
+ if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
+ return 1;
+
return 0;
}
* cpuid string generated on this platform.
* Otherwise return non-zero.
*/
-int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
{
regex_t re;
regmatch_t pmatch[1];
struct pmu_events_map *map;
struct pmu_event *pe;
const char *name = pmu->name;
+ const char *pname;
map = perf_pmu__find_map(pmu);
if (!map)
break;
}
- if (!is_pmu_core(name)) {
- /* check for uncore devices */
- if (pe->pmu == NULL)
- continue;
- if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+ if (!is_arm_pmu_core(name)) {
+ pname = pe->pmu ? pe->pmu : "cpu";
+ if (strncmp(pname, name, strlen(pname)))
continue;
}
int symbol__annotation_init(void)
{
+ if (symbol_conf.init_annotation)
+ return 0;
+
if (symbol_conf.initialized) {
pr_err("Annotation needs to be init before symbol__init()\n");
return -1;
}
- if (symbol_conf.init_annotation) {
- pr_warning("Annotation being initialized multiple times\n");
- return 0;
- }
-
symbol_conf.priv_size += sizeof(struct annotation);
symbol_conf.init_annotation = true;
return 0;
#include <stdlib.h>
#include <linux/compiler.h>
-#ifdef HAVE_SYSCALL_TABLE
+#ifdef HAVE_SYSCALL_TABLE_SUPPORT
#include <string.h>
#include "string2.h"
#include "util.h"
return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
}
-#else /* HAVE_SYSCALL_TABLE */
+#else /* HAVE_SYSCALL_TABLE_SUPPORT */
#include <libaudit.h>
{
return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
}
-#endif /* HAVE_SYSCALL_TABLE */
+#endif /* HAVE_SYSCALL_TABLE_SUPPORT */
}
}
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
void setup_python_scripting(void)
{
register_python_scripting(&python_scripting_unsupported_ops);
}
}
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
void setup_perl_scripting(void)
{
register_perl_scripting(&perl_scripting_unsupported_ops);
# to compile vs uClibc, that can be done here as well.
CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
CROSS_COMPILE ?= $(CROSS)
+LD = $(CC)
HOSTCC = gcc
# check if compiler option is supported
};
static unsigned long dimm_fail_cmd_flags[NUM_DCR];
+static int dimm_fail_cmd_code[NUM_DCR];
struct nfit_test_fw {
enum intel_fw_update_state state;
if (i >= ARRAY_SIZE(handle))
return -ENXIO;
- if ((1 << func) & dimm_fail_cmd_flags[i])
+ if ((1 << func) & dimm_fail_cmd_flags[i]) {
+ if (dimm_fail_cmd_code[i])
+ return dimm_fail_cmd_code[i];
return -EIO;
+ }
return i;
}
static void put_dimms(void *data)
{
- struct device **dimm_dev = data;
+ struct nfit_test *t = data;
int i;
- for (i = 0; i < NUM_DCR; i++)
- if (dimm_dev[i])
- device_unregister(dimm_dev[i]);
+ for (i = 0; i < t->num_dcr; i++)
+ if (t->dimm_dev[i])
+ device_unregister(t->dimm_dev[i]);
}
static struct class *nfit_test_dimm;
{
int dimm;
- if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1
- || dimm >= NUM_DCR || dimm < 0)
+ if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1)
return -ENXIO;
return dimm;
}
-
static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
if (dimm < 0)
return dimm;
- return sprintf(buf, "%#x", handle[dimm]);
+ return sprintf(buf, "%#x\n", handle[dimm]);
}
DEVICE_ATTR_RO(handle);
}
static DEVICE_ATTR_RW(fail_cmd);
+static ssize_t fail_cmd_code_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int dimm = dimm_name_to_id(dev);
+
+ if (dimm < 0)
+ return dimm;
+
+ return sprintf(buf, "%d\n", dimm_fail_cmd_code[dimm]);
+}
+
+static ssize_t fail_cmd_code_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int dimm = dimm_name_to_id(dev);
+ unsigned long val;
+ ssize_t rc;
+
+ if (dimm < 0)
+ return dimm;
+
+ rc = kstrtol(buf, 0, &val);
+ if (rc)
+ return rc;
+
+ dimm_fail_cmd_code[dimm] = val;
+ return size;
+}
+static DEVICE_ATTR_RW(fail_cmd_code);
+
static struct attribute *nfit_test_dimm_attributes[] = {
&dev_attr_fail_cmd.attr,
+ &dev_attr_fail_cmd_code.attr,
&dev_attr_handle.attr,
NULL,
};
NULL,
};
+static int nfit_test_dimm_init(struct nfit_test *t)
+{
+ int i;
+
+ if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t))
+ return -ENOMEM;
+ for (i = 0; i < t->num_dcr; i++) {
+ t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
+ &t->pdev.dev, 0, NULL,
+ nfit_test_dimm_attribute_groups,
+ "test_dimm%d", i + t->dcr_idx);
+ if (!t->dimm_dev[i])
+ return -ENOMEM;
+ }
+ return 0;
+}
+
static void smart_init(struct nfit_test *t)
{
int i;
if (!t->_fit)
return -ENOMEM;
- if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev))
+ if (nfit_test_dimm_init(t))
return -ENOMEM;
- for (i = 0; i < NUM_DCR; i++) {
- t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
- &t->pdev.dev, 0, NULL,
- nfit_test_dimm_attribute_groups,
- "test_dimm%d", i);
- if (!t->dimm_dev[i])
- return -ENOMEM;
- }
-
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
if (!t->spa_set[1])
return -ENOMEM;
+ if (nfit_test_dimm_init(t))
+ return -ENOMEM;
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
set_bit(ND_INTEL_ENABLE_LSS_STATUS, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
}
static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
LDFLAGS += -m32
endif
-targets: mapshift $(TARGETS)
+targets: generated/map-shift.h $(TARGETS)
main: $(OFILES)
idr.c: ../../../lib/idr.c
sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
-.PHONY: mapshift
-
-mapshift:
+generated/map-shift.h:
@if ! grep -qws $(SHIFT) generated/map-shift.h; then \
echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \
generated/map-shift.h; \
#include <linux/radix-tree.h>
#include <linux/slab.h>
#include <linux/errno.h>
+#include <pthread.h>
#include "test.h"
item_kill_tree(&tree);
}
+bool stop_iteration = false;
+
+static void *creator_func(void *ptr)
+{
+ /* 'order' is set up to ensure we have sibling entries */
+ unsigned int order = RADIX_TREE_MAP_SHIFT - 1;
+ struct radix_tree_root *tree = ptr;
+ int i;
+
+ for (i = 0; i < 10000; i++) {
+ item_insert_order(tree, 0, order);
+ item_delete_rcu(tree, 0);
+ }
+
+ stop_iteration = true;
+ return NULL;
+}
+
+static void *iterator_func(void *ptr)
+{
+ struct radix_tree_root *tree = ptr;
+ struct radix_tree_iter iter;
+ struct item *item;
+ void **slot;
+
+ while (!stop_iteration) {
+ rcu_read_lock();
+ radix_tree_for_each_slot(slot, tree, &iter, 0) {
+ item = radix_tree_deref_slot(slot);
+
+ if (!item)
+ continue;
+ if (radix_tree_deref_retry(item)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+
+ item_sanity(item, iter.index);
+ }
+ rcu_read_unlock();
+ }
+ return NULL;
+}
+
+static void multiorder_iteration_race(void)
+{
+ const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
+ pthread_t worker_thread[num_threads];
+ RADIX_TREE(tree, GFP_KERNEL);
+ int i;
+
+ pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+ for (i = 1; i < num_threads; i++)
+ pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+
+ for (i = 0; i < num_threads; i++)
+ pthread_join(worker_thread[i], NULL);
+
+ item_kill_tree(&tree);
+}
+
void multiorder_checks(void)
{
int i;
multiorder_join();
multiorder_split();
multiorder_account();
+ multiorder_iteration_race();
radix_tree_cpu_dead(0);
}
return 0;
}
+static void item_free_rcu(struct rcu_head *head)
+{
+ struct item *item = container_of(head, struct item, rcu_head);
+
+ free(item);
+}
+
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+{
+ struct item *item = radix_tree_delete(root, index);
+
+ if (item) {
+ item_sanity(item, index);
+ call_rcu(&item->rcu_head, item_free_rcu);
+ return 1;
+ }
+ return 0;
+}
+
void item_check_present(struct radix_tree_root *root, unsigned long index)
{
struct item *item;
#include <linux/rcupdate.h>
struct item {
+ struct rcu_head rcu_head;
unsigned long index;
unsigned int order;
};
struct item *item_create(unsigned long index, unsigned int order);
int __item_insert(struct radix_tree_root *root, struct item *item);
int item_insert(struct radix_tree_root *root, unsigned long index);
+void item_sanity(struct item *item, unsigned long index);
int item_insert_order(struct radix_tree_root *root, unsigned long index,
unsigned order);
int item_delete(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
void item_check_present(struct radix_tree_root *root, unsigned long index);
test_verifier_log
feature
test_libbpf_open
+test_sock
+test_sock_addr
+urandom_read
+test_btf
+test_sockmap
GENFLAGS := -DHAVE_GENHDR
endif
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf -lrt -lpthread
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
$(TEST_CUSTOM_PROGS): urandom_read
urandom_read: urandom_read.c
- $(CC) -o $(TEST_CUSTOM_PROGS) -static $<
+ $(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
- test_sock test_sock_addr test_btf
+ test_sock test_btf test_sockmap
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
- test_btf_haskv.o test_btf_nokv.o
+ test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
+ test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
test_xdp_meta.sh \
test_offload.py \
- test_sock_addr.sh
+ test_sock_addr.sh \
+ test_tunnel.sh
# Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
include ../lib.mk
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
+$(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_progs: trace_helpers.c
.PHONY: force
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
-BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help |& grep dwarfris)
-BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help |& grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version |& grep LLVM)
+BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
+BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
ifneq ($(BTF_LLC_PROBE),)
ifneq ($(BTF_PAHOLE_PROBE),)
(void *) BPF_FUNC_sock_ops_cb_flags_set;
static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_sk_redirect_map;
+static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) =
+ (void *) BPF_FUNC_sk_redirect_hash;
static int (*bpf_sock_map_update)(void *map, void *key, void *value,
unsigned long long flags) =
(void *) BPF_FUNC_sock_map_update;
+static int (*bpf_sock_hash_update)(void *map, void *key, void *value,
+ unsigned long long flags) =
+ (void *) BPF_FUNC_sock_hash_update;
static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
void *buf, unsigned int buf_size) =
(void *) BPF_FUNC_perf_event_read_value;
(void *) BPF_FUNC_override_return;
static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_msg_redirect_map;
+static int (*bpf_msg_redirect_hash)(void *ctx,
+ void *map, void *key, int flags) =
+ (void *) BPF_FUNC_msg_redirect_hash;
static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
(void *) BPF_FUNC_msg_apply_bytes;
static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
(void *) BPF_FUNC_bind;
static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_tail;
-
+static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
+ int size, int flags) =
+ (void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
+ (void *) BPF_FUNC_get_stack;
+static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
+ int plen, __u32 flags) =
+ (void *) BPF_FUNC_fib_lookup;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_RAND__
+#define __BPF_RAND__
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <time.h>
+
+static inline uint64_t bpf_rand_mask(uint64_t mask)
+{
+ return (((uint64_t)(uint32_t)rand()) |
+ ((uint64_t)(uint32_t)rand() << 32)) & mask;
+}
+
+#define bpf_rand_ux(x, m) \
+static inline uint64_t bpf_rand_u##x(int shift) \
+{ \
+ return bpf_rand_mask((m)) << shift; \
+}
+
+bpf_rand_ux( 8, 0xffULL)
+bpf_rand_ux(16, 0xffffULL)
+bpf_rand_ux(24, 0xffffffULL)
+bpf_rand_ux(32, 0xffffffffULL)
+bpf_rand_ux(40, 0xffffffffffULL)
+bpf_rand_ux(48, 0xffffffffffffULL)
+bpf_rand_ux(56, 0xffffffffffffffULL)
+bpf_rand_ux(64, 0xffffffffffffffffULL)
+
+static inline void bpf_semi_rand_init(void)
+{
+ srand(time(NULL));
+}
+
+static inline uint64_t bpf_semi_rand_get(void)
+{
+ switch (rand() % 39) {
+ case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0);
+ case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0);
+ case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0);
+ case 3: return 0x8000000000000000ULL | bpf_rand_u32(0);
+ case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0);
+ case 5: return 0x0000000100000000ULL | bpf_rand_u24(0);
+ case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0);
+ case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0);
+ case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24);
+ case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0);
+ case 10: return 0x0000000010000000ULL | bpf_rand_u32(0);
+ case 11: return 0xf000000000000000ULL | bpf_rand_u8(0);
+ case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8);
+ case 13: return 0x000000000f000000ULL | bpf_rand_u8(16);
+ case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32);
+ case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48);
+ case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1);
+ case 17: return 0xffff800000000000ULL | bpf_rand_u8(4);
+ case 18: return 0xffff800000000000ULL | bpf_rand_u8(20);
+ case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0);
+ case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0);
+ case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20);
+ case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40);
+ case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 27: return 0x0000800000000000ULL;
+ case 28: return 0x8000000000000000ULL;
+ case 29: return 0x0000000000000000ULL;
+ case 30: return 0xffffffffffffffffULL;
+ case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64);
+ case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64);
+ case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64);
+ case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64);
+ case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64);
+ default: return bpf_rand_u64(0);
+ }
+}
+
+#endif /* __BPF_RAND__ */
#include "bpf_rlimit.h"
+static uint32_t pass_cnt;
+static uint32_t error_cnt;
+static uint32_t skip_cnt;
+
+#define CHECK(condition, format...) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \
+ fprintf(stderr, format); \
+ } \
+ __ret; \
+})
+
+static int count_result(int err)
+{
+ if (err)
+ error_cnt++;
+ else
+ pass_cnt++;
+
+ fprintf(stderr, "\n");
+ return err;
+}
+
#define min(a, b) ((a) < (b) ? (a) : (b))
#define __printf(a, b) __attribute__((format(printf, a, b)))
void *raw_btf;
type_sec_size = get_type_sec_size(raw_types);
- if (type_sec_size < 0) {
- fprintf(stderr, "Cannot get nr_raw_types\n");
+ if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types"))
return NULL;
- }
size_needed = sizeof(*hdr) + type_sec_size + str_sec_size;
raw_btf = malloc(size_needed);
- if (!raw_btf) {
- fprintf(stderr, "Cannot allocate memory for raw_btf\n");
+ if (CHECK(!raw_btf, "Cannot allocate memory for raw_btf"))
return NULL;
- }
/* Copy header */
memcpy(raw_btf, hdr, sizeof(*hdr));
for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) {
if (raw_types[i] == NAME_TBD) {
next_str = get_next_str(next_str, end_str);
- if (!next_str) {
- fprintf(stderr, "Error in getting next_str\n");
+ if (CHECK(!next_str, "Error in getting next_str")) {
free(raw_btf);
return NULL;
}
free(raw_btf);
err = ((btf_fd == -1) != test->btf_load_err);
- if (err)
- fprintf(stderr, "btf_load_err:%d btf_fd:%d\n",
- test->btf_load_err, btf_fd);
+ CHECK(err, "btf_fd:%d test->btf_load_err:%u",
+ btf_fd, test->btf_load_err);
if (err || btf_fd == -1)
goto done;
map_fd = bpf_create_map_xattr(&create_attr);
err = ((map_fd == -1) != test->map_create_err);
- if (err)
- fprintf(stderr, "map_create_err:%d map_fd:%d\n",
- test->map_create_err, map_fd);
+ CHECK(err, "map_fd:%d test->map_create_err:%u",
+ map_fd, test->map_create_err);
done:
if (!err)
- fprintf(stderr, "OK\n");
+ fprintf(stderr, "OK");
if (*btf_log_buf && (err || args.always_log))
- fprintf(stderr, "%s\n", btf_log_buf);
+ fprintf(stderr, "\n%s", btf_log_buf);
if (btf_fd != -1)
close(btf_fd);
int err = 0;
if (args.raw_test_num)
- return do_test_raw(args.raw_test_num);
+ return count_result(do_test_raw(args.raw_test_num));
for (i = 1; i <= ARRAY_SIZE(raw_tests); i++)
- err |= do_test_raw(i);
+ err |= count_result(do_test_raw(i));
return err;
}
const char *str_sec;
__u32 raw_types[MAX_NR_RAW_TYPES];
__u32 str_sec_size;
- int info_size_delta;
+ int btf_size_delta;
+ int (*special_test)(unsigned int test_num);
};
+static int test_big_btf_info(unsigned int test_num);
+static int test_btf_id(unsigned int test_num);
+
const struct btf_get_info_test get_info_tests[] = {
{
.descr = "== raw_btf_size+1",
},
.str_sec = "",
.str_sec_size = sizeof(""),
- .info_size_delta = 1,
+ .btf_size_delta = 1,
},
{
.descr = "== raw_btf_size-3",
},
.str_sec = "",
.str_sec_size = sizeof(""),
- .info_size_delta = -3,
+ .btf_size_delta = -3,
+},
+{
+ .descr = "Large bpf_btf_info",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .special_test = test_big_btf_info,
+},
+{
+ .descr = "BTF ID",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* unsigned int */ /* [2] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .special_test = test_btf_id,
},
};
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64)(unsigned long)ptr;
+}
+
+static int test_big_btf_info(unsigned int test_num)
+{
+ const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
+ uint8_t *raw_btf = NULL, *user_btf = NULL;
+ unsigned int raw_btf_size;
+ struct {
+ struct bpf_btf_info info;
+ uint64_t garbage;
+ } info_garbage;
+ struct bpf_btf_info *info;
+ int btf_fd = -1, err;
+ uint32_t info_len;
+
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+
+ user_btf = malloc(raw_btf_size);
+ if (CHECK(!user_btf, "!user_btf")) {
+ err = -1;
+ goto done;
+ }
+
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ /*
+ * GET_INFO should error out if the userspace info
+ * has non zero tailing bytes.
+ */
+ info = &info_garbage.info;
+ memset(info, 0, sizeof(*info));
+ info_garbage.garbage = 0xdeadbeef;
+ info_len = sizeof(info_garbage);
+ info->btf = ptr_to_u64(user_btf);
+ info->btf_size = raw_btf_size;
+
+ err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+ if (CHECK(!err, "!err")) {
+ err = -1;
+ goto done;
+ }
+
+ /*
+ * GET_INFO should succeed even info_len is larger than
+ * the kernel supported as long as tailing bytes are zero.
+ * The kernel supported info len should also be returned
+ * to userspace.
+ */
+ info_garbage.garbage = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+ if (CHECK(err || info_len != sizeof(*info),
+ "err:%d errno:%d info_len:%u sizeof(*info):%lu",
+ err, errno, info_len, sizeof(*info))) {
+ err = -1;
+ goto done;
+ }
+
+ fprintf(stderr, "OK");
+
+done:
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ free(raw_btf);
+ free(user_btf);
+
+ if (btf_fd != -1)
+ close(btf_fd);
+
+ return err;
+}
+
+static int test_btf_id(unsigned int test_num)
+{
+ const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
+ struct bpf_create_map_attr create_attr = {};
+ uint8_t *raw_btf = NULL, *user_btf[2] = {};
+ int btf_fd[2] = {-1, -1}, map_fd = -1;
+ struct bpf_map_info map_info = {};
+ struct bpf_btf_info info[2] = {};
+ unsigned int raw_btf_size;
+ uint32_t info_len;
+ int err, i, ret;
+
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+
+ for (i = 0; i < 2; i++) {
+ user_btf[i] = malloc(raw_btf_size);
+ if (CHECK(!user_btf[i], "!user_btf[%d]", i)) {
+ err = -1;
+ goto done;
+ }
+ info[i].btf = ptr_to_u64(user_btf[i]);
+ info[i].btf_size = raw_btf_size;
+ }
+
+ btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ /* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */
+ info_len = sizeof(info[0]);
+ err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len);
+ if (CHECK(err, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id);
+ if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ ret = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len);
+ if (CHECK(err || info[0].id != info[1].id ||
+ info[0].btf_size != info[1].btf_size ||
+ (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)),
+ "err:%d errno:%d id0:%u id1:%u btf_size0:%u btf_size1:%u memcmp:%d",
+ err, errno, info[0].id, info[1].id,
+ info[0].btf_size, info[1].btf_size, ret)) {
+ err = -1;
+ goto done;
+ }
+
+ /* Test btf members in struct bpf_map_info */
+ create_attr.name = "test_btf_id";
+ create_attr.map_type = BPF_MAP_TYPE_ARRAY;
+ create_attr.key_size = sizeof(int);
+ create_attr.value_size = sizeof(unsigned int);
+ create_attr.max_entries = 4;
+ create_attr.btf_fd = btf_fd[0];
+ create_attr.btf_key_id = 1;
+ create_attr.btf_value_id = 2;
+
+ map_fd = bpf_create_map_xattr(&create_attr);
+ if (CHECK(map_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ info_len = sizeof(map_info);
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ if (CHECK(err || map_info.btf_id != info[0].id ||
+ map_info.btf_key_id != 1 || map_info.btf_value_id != 2,
+ "err:%d errno:%d info.id:%u btf_id:%u btf_key_id:%u btf_value_id:%u",
+ err, errno, info[0].id, map_info.btf_id, map_info.btf_key_id,
+ map_info.btf_value_id)) {
+ err = -1;
+ goto done;
+ }
+
+ for (i = 0; i < 2; i++) {
+ close(btf_fd[i]);
+ btf_fd[i] = -1;
+ }
+
+ /* Test BTF ID is removed from the kernel */
+ btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
+ if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+ close(btf_fd[0]);
+ btf_fd[0] = -1;
+
+ /* The map holds the last ref to BTF and its btf_id */
+ close(map_fd);
+ map_fd = -1;
+ btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
+ if (CHECK(btf_fd[0] != -1, "BTF lingers")) {
+ err = -1;
+ goto done;
+ }
+
+ fprintf(stderr, "OK");
+
+done:
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ free(raw_btf);
+ if (map_fd != -1)
+ close(map_fd);
+ for (i = 0; i < 2; i++) {
+ free(user_btf[i]);
+ if (btf_fd[i] != -1)
+ close(btf_fd[i]);
+ }
+
+ return err;
+}
+
static int do_test_get_info(unsigned int test_num)
{
const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
unsigned int raw_btf_size, user_btf_size, expected_nbytes;
uint8_t *raw_btf = NULL, *user_btf = NULL;
- int btf_fd = -1, err;
+ struct bpf_btf_info info = {};
+ int btf_fd = -1, err, ret;
+ uint32_t info_len;
- fprintf(stderr, "BTF GET_INFO_BY_ID test[%u] (%s): ",
+ fprintf(stderr, "BTF GET_INFO test[%u] (%s): ",
test_num, test->descr);
+ if (test->special_test)
+ return test->special_test(test_num);
+
raw_btf = btf_raw_create(&hdr_tmpl,
test->raw_types,
test->str_sec,
*btf_log_buf = '\0';
user_btf = malloc(raw_btf_size);
- if (!user_btf) {
- fprintf(stderr, "Cannot allocate memory for user_btf\n");
+ if (CHECK(!user_btf, "!user_btf")) {
err = -1;
goto done;
}
btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
btf_log_buf, BTF_LOG_BUF_SIZE,
args.always_log);
- if (btf_fd == -1) {
- fprintf(stderr, "bpf_load_btf:%s(%d)\n",
- strerror(errno), errno);
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
err = -1;
goto done;
}
- user_btf_size = (int)raw_btf_size + test->info_size_delta;
+ user_btf_size = (int)raw_btf_size + test->btf_size_delta;
expected_nbytes = min(raw_btf_size, user_btf_size);
if (raw_btf_size > expected_nbytes)
memset(user_btf + expected_nbytes, 0xff,
raw_btf_size - expected_nbytes);
- err = bpf_obj_get_info_by_fd(btf_fd, user_btf, &user_btf_size);
- if (err || user_btf_size != raw_btf_size ||
- memcmp(raw_btf, user_btf, expected_nbytes)) {
- fprintf(stderr,
- "err:%d(errno:%d) raw_btf_size:%u user_btf_size:%u expected_nbytes:%u memcmp:%d\n",
- err, errno,
- raw_btf_size, user_btf_size, expected_nbytes,
- memcmp(raw_btf, user_btf, expected_nbytes));
+ info_len = sizeof(info);
+ info.btf = ptr_to_u64(user_btf);
+ info.btf_size = user_btf_size;
+
+ ret = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len);
+ if (CHECK(err || !info.id || info_len != sizeof(info) ||
+ info.btf_size != raw_btf_size ||
+ (ret = memcmp(raw_btf, user_btf, expected_nbytes)),
+ "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
+ err, errno, info.id, info_len, sizeof(info),
+ raw_btf_size, info.btf_size, expected_nbytes, ret)) {
err = -1;
goto done;
}
while (expected_nbytes < raw_btf_size) {
fprintf(stderr, "%u...", expected_nbytes);
- if (user_btf[expected_nbytes++] != 0xff) {
- fprintf(stderr, "!= 0xff\n");
+ if (CHECK(user_btf[expected_nbytes++] != 0xff,
+ "user_btf[%u]:%x != 0xff", expected_nbytes - 1,
+ user_btf[expected_nbytes - 1])) {
err = -1;
goto done;
}
}
- fprintf(stderr, "OK\n");
+ fprintf(stderr, "OK");
done:
if (*btf_log_buf && (err || args.always_log))
- fprintf(stderr, "%s\n", btf_log_buf);
+ fprintf(stderr, "\n%s", btf_log_buf);
free(raw_btf);
free(user_btf);
int err = 0;
if (args.get_info_test_num)
- return do_test_get_info(args.get_info_test_num);
+ return count_result(do_test_get_info(args.get_info_test_num));
for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++)
- err |= do_test_get_info(i);
+ err |= count_result(do_test_get_info(i));
return err;
}
Elf *elf;
int ret;
- if (elf_version(EV_CURRENT) == EV_NONE) {
- fprintf(stderr, "Failed to init libelf\n");
+ if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
+ "elf_version(EV_CURRENT) == EV_NONE"))
return -1;
- }
elf_fd = open(fn, O_RDONLY);
- if (elf_fd == -1) {
- fprintf(stderr, "Cannot open file %s: %s(%d)\n",
- fn, strerror(errno), errno);
+ if (CHECK(elf_fd == -1, "open(%s): errno:%d", fn, errno))
return -1;
- }
elf = elf_begin(elf_fd, ELF_C_READ, NULL);
- if (!elf) {
- fprintf(stderr, "Failed to read ELF from %s. %s\n", fn,
- elf_errmsg(elf_errno()));
+ if (CHECK(!elf, "elf_begin(%s): %s", fn, elf_errmsg(elf_errno()))) {
ret = -1;
goto done;
}
- if (!gelf_getehdr(elf, &ehdr)) {
- fprintf(stderr, "Failed to get EHDR from %s\n", fn);
+ if (CHECK(!gelf_getehdr(elf, &ehdr), "!gelf_getehdr(%s)", fn)) {
ret = -1;
goto done;
}
const char *sh_name;
GElf_Shdr sh;
- if (gelf_getshdr(scn, &sh) != &sh) {
- fprintf(stderr,
- "Failed to get section header from %s\n", fn);
+ if (CHECK(gelf_getshdr(scn, &sh) != &sh,
+ "file:%s gelf_getshdr != &sh", fn)) {
ret = -1;
goto done;
}
return err;
if (err == 0) {
- fprintf(stderr, "SKIP. No ELF %s found\n", BTF_ELF_SEC);
+ fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC);
+ skip_cnt++;
return 0;
}
obj = bpf_object__open(test->file);
- if (IS_ERR(obj))
+ if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
return PTR_ERR(obj);
err = bpf_object__btf_fd(obj);
- if (err == -1) {
- fprintf(stderr, "bpf_object__btf_fd: -1\n");
+ if (CHECK(err == -1, "bpf_object__btf_fd: -1"))
goto done;
- }
prog = bpf_program__next(NULL, obj);
- if (!prog) {
- fprintf(stderr, "Cannot find bpf_prog\n");
+ if (CHECK(!prog, "Cannot find bpf_prog")) {
err = -1;
goto done;
}
bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
err = bpf_object__load(obj);
- if (err < 0) {
- fprintf(stderr, "bpf_object__load: %d\n", err);
+ if (CHECK(err < 0, "bpf_object__load: %d", err))
goto done;
- }
map = bpf_object__find_map_by_name(obj, "btf_map");
- if (!map) {
- fprintf(stderr, "btf_map not found\n");
+ if (CHECK(!map, "btf_map not found")) {
err = -1;
goto done;
}
err = (bpf_map__btf_key_id(map) == 0 || bpf_map__btf_value_id(map) == 0)
!= test->btf_kv_notfound;
- if (err) {
- fprintf(stderr,
- "btf_kv_notfound:%u btf_key_id:%u btf_value_id:%u\n",
- test->btf_kv_notfound,
- bpf_map__btf_key_id(map),
- bpf_map__btf_value_id(map));
+ if (CHECK(err, "btf_key_id:%u btf_value_id:%u test->btf_kv_notfound:%u",
+ bpf_map__btf_key_id(map), bpf_map__btf_value_id(map),
+ test->btf_kv_notfound))
goto done;
- }
- fprintf(stderr, "OK\n");
+ fprintf(stderr, "OK");
done:
bpf_object__close(obj);
int err = 0;
if (args.file_test_num)
- return do_test_file(args.file_test_num);
+ return count_result(do_test_file(args.file_test_num));
for (i = 1; i <= ARRAY_SIZE(file_tests); i++)
- err |= do_test_file(i);
+ err |= count_result(do_test_file(i));
return err;
}
unsigned int key;
uint8_t *raw_btf;
ssize_t nread;
- int err;
+ int err, ret;
fprintf(stderr, "%s......", test->descr);
raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
args.always_log);
free(raw_btf);
- if (btf_fd == -1) {
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
err = -1;
- fprintf(stderr, "bpf_load_btf: %s(%d)\n",
- strerror(errno), errno);
goto done;
}
create_attr.btf_value_id = test->value_id;
map_fd = bpf_create_map_xattr(&create_attr);
- if (map_fd == -1) {
+ if (CHECK(map_fd == -1, "errno:%d", errno)) {
err = -1;
- fprintf(stderr, "bpf_creat_map_btf: %s(%d)\n",
- strerror(errno), errno);
goto done;
}
- if (snprintf(pin_path, sizeof(pin_path), "%s/%s",
- "/sys/fs/bpf", test->map_name) == sizeof(pin_path)) {
+ ret = snprintf(pin_path, sizeof(pin_path), "%s/%s",
+ "/sys/fs/bpf", test->map_name);
+
+ if (CHECK(ret == sizeof(pin_path), "pin_path %s/%s is too long",
+ "/sys/fs/bpf", test->map_name)) {
err = -1;
- fprintf(stderr, "pin_path is too long\n");
goto done;
}
err = bpf_obj_pin(map_fd, pin_path);
- if (err) {
- fprintf(stderr, "Cannot pin to %s. %s(%d).\n", pin_path,
- strerror(errno), errno);
+ if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno))
goto done;
- }
for (key = 0; key < test->max_entries; key++) {
set_pprint_mapv(&mapv, key);
}
pin_file = fopen(pin_path, "r");
- if (!pin_file) {
+ if (CHECK(!pin_file, "fopen(%s): errno:%d", pin_path, errno)) {
err = -1;
- fprintf(stderr, "fopen(%s): %s(%d)\n", pin_path,
- strerror(errno), errno);
goto done;
}
*line == '#')
;
- if (nread <= 0) {
+ if (CHECK(nread <= 0, "Unexpected EOF")) {
err = -1;
- fprintf(stderr, "Unexpected EOF\n");
goto done;
}
mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
pprint_enum_str[mapv.aenum]);
- if (nexpected_line == sizeof(expected_line)) {
+ if (CHECK(nexpected_line == sizeof(expected_line),
+ "expected_line is too long")) {
err = -1;
- fprintf(stderr, "expected_line is too long\n");
goto done;
}
nread = getline(&line, &line_len, pin_file);
} while (++key < test->max_entries && nread > 0);
- if (key < test->max_entries) {
+ if (CHECK(key < test->max_entries,
+ "Unexpected EOF. key:%u test->max_entries:%u",
+ key, test->max_entries)) {
err = -1;
- fprintf(stderr, "Unexpected EOF\n");
goto done;
}
- if (nread > 0) {
+ if (CHECK(nread > 0, "Unexpected extra pprint output: %s", line)) {
err = -1;
- fprintf(stderr, "Unexpected extra pprint output: %s\n", line);
goto done;
}
done:
if (!err)
- fprintf(stderr, "OK\n");
+ fprintf(stderr, "OK");
if (*btf_log_buf && (err || args.always_log))
- fprintf(stderr, "%s\n", btf_log_buf);
+ fprintf(stderr, "\n%s", btf_log_buf);
if (btf_fd != -1)
close(btf_fd);
if (map_fd != -1)
return 0;
}
+static void print_summary(void)
+{
+ fprintf(stderr, "PASS:%u SKIP:%u FAIL:%u\n",
+ pass_cnt - skip_cnt, skip_cnt, error_cnt);
+}
+
int main(int argc, char **argv)
{
int err = 0;
err |= test_file();
if (args.pprint_test)
- err |= test_pprint();
+ err |= count_result(test_pprint());
if (args.raw_test || args.get_info_test || args.file_test ||
args.pprint_test)
- return err;
+ goto done;
err |= test_raw();
err |= test_get_info();
err |= test_file();
+done:
+ print_summary();
return err;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* Permit pretty deep stack traces */
+#define MAX_STACK_RAWTP 100
+struct stack_trace_t {
+ int pid;
+ int kern_stack_size;
+ int user_stack_size;
+ int user_stack_buildid_size;
+ __u64 kern_stack[MAX_STACK_RAWTP];
+ __u64 user_stack[MAX_STACK_RAWTP];
+ struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+struct bpf_map_def SEC("maps") perfmap = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(__u32),
+ .max_entries = 2,
+};
+
+struct bpf_map_def SEC("maps") stackdata_map = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct stack_trace_t),
+ .max_entries = 1,
+};
+
+/* Allocate per-cpu space twice the needed. For the code below
+ * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+ * if (usize < 0)
+ * return 0;
+ * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+ *
+ * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64),
+ * verifier will complain that access "raw_data + usize"
+ * with size "max_len - usize" may be out of bound.
+ * The maximum "raw_data + usize" is "raw_data + max_len"
+ * and the maximum "max_len - usize" is "max_len", verifier
+ * concludes that the maximum buffer access range is
+ * "raw_data[0...max_len * 2 - 1]" and hence reject the program.
+ *
+ * Doubling the to-be-used max buffer size can fix this verifier
+ * issue and avoid complicated C programming massaging.
+ * This is an acceptable workaround since there is one entry here.
+ */
+struct bpf_map_def SEC("maps") rawdata_map = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2,
+ .max_entries = 1,
+};
+
+SEC("tracepoint/raw_syscalls/sys_enter")
+int bpf_prog1(void *ctx)
+{
+ int max_len, max_buildid_len, usize, ksize, total_size;
+ struct stack_trace_t *data;
+ void *raw_data;
+ __u32 key = 0;
+
+ data = bpf_map_lookup_elem(&stackdata_map, &key);
+ if (!data)
+ return 0;
+
+ max_len = MAX_STACK_RAWTP * sizeof(__u64);
+ max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id);
+ data->pid = bpf_get_current_pid_tgid();
+ data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack,
+ max_len, 0);
+ data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len,
+ BPF_F_USER_STACK);
+ data->user_stack_buildid_size = bpf_get_stack(
+ ctx, data->user_stack_buildid, max_buildid_len,
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+ bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data));
+
+ /* write both kernel and user stacks to the same buffer */
+ raw_data = bpf_map_lookup_elem(&rawdata_map, &key);
+ if (!raw_data)
+ return 0;
+
+ usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+ if (usize < 0)
+ return 0;
+
+ ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+ if (ksize < 0)
+ return 0;
+
+ total_size = usize + ksize;
+ if (total_size > 0 && total_size <= max_len)
+ bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
#include "bpf_util.h"
#include "bpf_endian.h"
#include "bpf_rlimit.h"
+#include "trace_helpers.h"
static int error_cnt, pass_cnt;
+static bool jit_enabled;
#define MAGIC_BYTES 123
return (__u64) (unsigned long) ptr;
}
+static bool is_jit_enabled(void)
+{
+ const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+ bool enabled = false;
+ int sysctl_fd;
+
+ sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
+ if (sysctl_fd != -1) {
+ char tmpc;
+
+ if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+ enabled = (tmpc != '0');
+ close(sysctl_fd);
+ }
+
+ return enabled;
+}
+
static void test_bpf_obj_id(void)
{
const __u64 array_magic_value = 0xfaceb00c;
const __u32 array_key = 0;
const int nr_iters = 2;
const char *file = "./test_obj_id.o";
- const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
const char *expected_prog_name = "test_obj_id";
const char *expected_map_name = "test_map_id";
const __u64 nsec_per_sec = 1000000000;
char jited_insns[128], xlated_insns[128], zeros[128];
__u32 i, next_id, info_len, nr_id_found, duration = 0;
struct timespec real_time_ts, boot_time_ts;
- int sysctl_fd, jit_enabled = 0, err = 0;
+ int err = 0;
__u64 array_value;
uid_t my_uid = getuid();
time_t now, load_time;
- sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
- if (sysctl_fd != -1) {
- char tmpc;
-
- if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
- jit_enabled = (tmpc != '0');
- close(sysctl_fd);
- }
-
err = bpf_prog_get_fd_by_id(0);
CHECK(err >= 0 || errno != ENOENT,
"get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
return 0;
}
+static int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len)
+{
+ __u32 key, next_key, *cur_key_p, *next_key_p;
+ char *val_buf1, *val_buf2;
+ int i, err = 0;
+
+ val_buf1 = malloc(stack_trace_len);
+ val_buf2 = malloc(stack_trace_len);
+ cur_key_p = NULL;
+ next_key_p = &key;
+ while (bpf_map_get_next_key(smap_fd, cur_key_p, next_key_p) == 0) {
+ err = bpf_map_lookup_elem(smap_fd, next_key_p, val_buf1);
+ if (err)
+ goto out;
+ err = bpf_map_lookup_elem(amap_fd, next_key_p, val_buf2);
+ if (err)
+ goto out;
+ for (i = 0; i < stack_trace_len; i++) {
+ if (val_buf1[i] != val_buf2[i]) {
+ err = -1;
+ goto out;
+ }
+ }
+ key = *next_key_p;
+ cur_key_p = &key;
+ next_key_p = &next_key;
+ }
+ if (errno != ENOENT)
+ err = -1;
+
+out:
+ free(val_buf1);
+ free(val_buf2);
+ return err;
+}
+
static void test_stacktrace_map()
{
- int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
const char *file = "./test_stacktrace_map.o";
- int bytes, efd, err, pmu_fd, prog_fd;
+ int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
struct perf_event_attr attr = {};
__u32 key, val, duration = 0;
struct bpf_object *obj;
if (stackmap_fd < 0)
goto disable_pmu;
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (stack_amap_fd < 0)
+ goto disable_pmu;
+
/* give some time for bpf program run */
sleep(1);
"err %d errno %d\n", err, errno))
goto disable_pmu_noerr;
+ stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
+ err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
+ if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu_noerr;
+
goto disable_pmu_noerr;
disable_pmu:
error_cnt++;
static void test_stacktrace_build_id(void)
{
- int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
const char *file = "./test_stacktrace_build_id.o";
- int bytes, efd, err, pmu_fd, prog_fd;
+ int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
struct perf_event_attr attr = {};
__u32 key, previous_key, val, duration = 0;
struct bpf_object *obj;
err, errno))
goto disable_pmu;
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
== 0);
- assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+ assert(system("./urandom_read") == 0);
/* disable stack trace collection */
key = 0;
val = 1;
previous_key = key;
} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
- CHECK(build_id_matches < 1, "build id match",
- "Didn't find expected build ID from the map");
+ if (CHECK(build_id_matches < 1, "build id match",
+ "Didn't find expected build ID from the map\n"))
+ goto disable_pmu;
+
+ stack_trace_len = PERF_MAX_STACK_DEPTH
+ * sizeof(struct bpf_stack_build_id);
+ err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
+ CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
+ "err %d errno %d\n", err, errno);
disable_pmu:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
return;
}
+static void test_stacktrace_build_id_nmi(void)
+{
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+ const char *file = "./test_stacktrace_build_id.o";
+ int err, pmu_fd, prog_fd;
+ struct perf_event_attr attr = {
+ .sample_freq = 5000,
+ .freq = 1,
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ };
+ __u32 key, previous_key, val, duration = 0;
+ struct bpf_object *obj;
+ char buf[256];
+ int i, j;
+ struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
+ int build_id_matches = 0;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+ return;
+
+ pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+ 0 /* cpu 0 */, -1 /* group id */,
+ 0 /* flags */);
+ if (CHECK(pmu_fd < 0, "perf_event_open",
+ "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+ pmu_fd, errno))
+ goto close_prog;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
+ err, errno))
+ goto close_pmu;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+ if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
+ err, errno))
+ goto disable_pmu;
+
+ /* find map fds */
+ control_map_fd = bpf_find_map(__func__, obj, "control_map");
+ if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+ if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+ if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
+ err, errno))
+ goto disable_pmu;
+
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
+ == 0);
+ assert(system("taskset 0x1 ./urandom_read 100000") == 0);
+ /* disable stack trace collection */
+ key = 0;
+ val = 1;
+ bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+ /* for every element in stackid_hmap, we can find a corresponding one
+ * in stackmap, and vise versa.
+ */
+ err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+ if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+ if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = extract_build_id(buf, 256);
+
+ if (CHECK(err, "get build_id with readelf",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = bpf_map_get_next_key(stackmap_fd, NULL, &key);
+ if (CHECK(err, "get_next_key from stackmap",
+ "err %d, errno %d\n", err, errno))
+ goto disable_pmu;
+
+ do {
+ char build_id[64];
+
+ err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
+ if (CHECK(err, "lookup_elem from stackmap",
+ "err %d, errno %d\n", err, errno))
+ goto disable_pmu;
+ for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
+ if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
+ id_offs[i].offset != 0) {
+ for (j = 0; j < 20; ++j)
+ sprintf(build_id + 2 * j, "%02x",
+ id_offs[i].build_id[j] & 0xff);
+ if (strstr(buf, build_id) != NULL)
+ build_id_matches = 1;
+ }
+ previous_key = key;
+ } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
+
+ if (CHECK(build_id_matches < 1, "build id match",
+ "Didn't find expected build ID from the map\n"))
+ goto disable_pmu;
+
+ /*
+ * We intentionally skip compare_stack_ips(). This is because we
+ * only support one in_nmi() ips-to-build_id translation per cpu
+ * at any time, thus stack_amap here will always fallback to
+ * BPF_STACK_BUILD_ID_IP;
+ */
+
+disable_pmu:
+ ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+
+close_pmu:
+ close(pmu_fd);
+
+close_prog:
+ bpf_object__close(obj);
+}
+
+#define MAX_CNT_RAWTP 10ull
+#define MAX_STACK_RAWTP 100
+struct get_stack_trace_t {
+ int pid;
+ int kern_stack_size;
+ int user_stack_size;
+ int user_stack_buildid_size;
+ __u64 kern_stack[MAX_STACK_RAWTP];
+ __u64 user_stack[MAX_STACK_RAWTP];
+ struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+static int get_stack_print_output(void *data, int size)
+{
+ bool good_kern_stack = false, good_user_stack = false;
+ const char *nonjit_func = "___bpf_prog_run";
+ struct get_stack_trace_t *e = data;
+ int i, num_stack;
+ static __u64 cnt;
+ struct ksym *ks;
+
+ cnt++;
+
+ if (size < sizeof(struct get_stack_trace_t)) {
+ __u64 *raw_data = data;
+ bool found = false;
+
+ num_stack = size / sizeof(__u64);
+ /* If jit is enabled, we do not have a good way to
+ * verify the sanity of the kernel stack. So we
+ * just assume it is good if the stack is not empty.
+ * This could be improved in the future.
+ */
+ if (jit_enabled) {
+ found = num_stack > 0;
+ } else {
+ for (i = 0; i < num_stack; i++) {
+ ks = ksym_search(raw_data[i]);
+ if (strcmp(ks->name, nonjit_func) == 0) {
+ found = true;
+ break;
+ }
+ }
+ }
+ if (found) {
+ good_kern_stack = true;
+ good_user_stack = true;
+ }
+ } else {
+ num_stack = e->kern_stack_size / sizeof(__u64);
+ if (jit_enabled) {
+ good_kern_stack = num_stack > 0;
+ } else {
+ for (i = 0; i < num_stack; i++) {
+ ks = ksym_search(e->kern_stack[i]);
+ if (strcmp(ks->name, nonjit_func) == 0) {
+ good_kern_stack = true;
+ break;
+ }
+ }
+ }
+ if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
+ good_user_stack = true;
+ }
+ if (!good_kern_stack || !good_user_stack)
+ return LIBBPF_PERF_EVENT_ERROR;
+
+ if (cnt == MAX_CNT_RAWTP)
+ return LIBBPF_PERF_EVENT_DONE;
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void test_get_stack_raw_tp(void)
+{
+ const char *file = "./test_get_stack_rawtp.o";
+ int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
+ struct perf_event_attr attr = {};
+ struct timespec tv = {0, 10};
+ __u32 key = 0, duration = 0;
+ struct bpf_object *obj;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
+ efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+ if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+
+ perfmap_fd = bpf_find_map(__func__, obj, "perfmap");
+ if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+ perfmap_fd, errno))
+ goto close_prog;
+
+ err = load_kallsyms();
+ if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT;
+ pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/,
+ -1/*group_fd*/, 0);
+ if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
+ errno))
+ goto close_prog;
+
+ err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY);
+ if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err,
+ errno))
+ goto close_prog;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n",
+ err, errno))
+ goto close_prog;
+
+ err = perf_event_mmap(pmu_fd);
+ if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ /* trigger some syscall action */
+ for (i = 0; i < MAX_CNT_RAWTP; i++)
+ nanosleep(&tv, NULL);
+
+ err = perf_event_poller(pmu_fd, get_stack_print_output);
+ if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
+}
+
int main(void)
{
+ jit_enabled = is_jit_enabled();
+
test_pkt_access();
test_xdp();
test_xdp_adjust_tail();
test_tp_attach_query();
test_stacktrace_map();
test_stacktrace_build_id();
+ test_stacktrace_build_id_nmi();
test_stacktrace_map_raw_tp();
+ test_get_stack_raw_tp();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#define CG_PATH "/foo"
#define CONNECT4_PROG_PATH "./connect4_prog.o"
ping_once()
{
- ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1
+ ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
echo -n "Wait for testing IPv4/IPv6 to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
- if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then
+ if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
echo " OK"
return
fi
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#undef SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH
+#include "./test_sockmap_kern.h"
-/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io
#include <stdio.h>
#include <stdlib.h>
#include <sys/socket.h>
#include <fcntl.h>
#include <sys/wait.h>
#include <time.h>
+#include <sched.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <getopt.h>
-#include "../bpf/bpf_load.h"
-#include "../bpf/bpf_util.h"
-#include "../bpf/libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
int running;
-void running_handler(int a);
+static void running_handler(int a);
/* randomly selected ports for testing on lo */
#define S1_PORT 10000
#define S2_PORT 10001
+#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o"
+#define CG_PATH "/sockmap"
+
/* global sockets */
int s1, s2, c1, c2, p1, p2;
+int test_cnt;
+int passed;
+int failed;
+int map_fd[8];
+struct bpf_map *maps[8];
+int prog_fd[11];
int txmsg_pass;
int txmsg_noisy;
printf("\n");
}
-static int sockmap_init_sockets(void)
+static int sockmap_init_sockets(int verbose)
{
int i, err, one = 1;
struct sockaddr_in addr;
return errno;
}
- printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
- printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
- c1, s1, c2, s2);
+ if (verbose) {
+ printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
+ printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
+ c1, s1, c2, s2);
+ }
return 0;
}
bool sendpage;
bool data_test;
bool drop_expected;
+ int iov_count;
+ int iov_length;
+ int rate;
};
static int msg_loop_sendpage(int fd, int iov_length, int cnt,
clock_gettime(CLOCK_MONOTONIC, &s->end);
} else {
int slct, recv, max_fd = fd;
+ int fd_flags = O_NONBLOCK;
struct timeval timeout;
float total_bytes;
fd_set w;
+ fcntl(fd, fd_flags);
total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
err = clock_gettime(CLOCK_MONOTONIC, &s->start);
if (err < 0)
perror("recv start time: ");
while (s->bytes_recvd < total_bytes) {
- timeout.tv_sec = 1;
- timeout.tv_usec = 0;
+ timeout.tv_sec = 0;
+ timeout.tv_usec = 10;
/* FD sets */
FD_ZERO(&w);
clock_gettime(CLOCK_MONOTONIC, &s->end);
goto out_errno;
} else if (!slct) {
- fprintf(stderr, "unexpected timeout\n");
+ if (opt->verbose)
+ fprintf(stderr, "unexpected timeout\n");
errno = -EIO;
clock_gettime(CLOCK_MONOTONIC, &s->end);
goto out_errno;
return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec);
}
-static int sendmsg_test(int iov_count, int iov_buf, int cnt,
- struct sockmap_options *opt)
+static int sendmsg_test(struct sockmap_options *opt)
{
float sent_Bps = 0, recvd_Bps = 0;
int rx_fd, txpid, rxpid, err = 0;
struct msg_stats s = {0};
+ int iov_count = opt->iov_count;
+ int iov_buf = opt->iov_length;
+ int cnt = opt->rate;
int status;
errno = 0;
iov_count = 1;
err = msg_loop(rx_fd, iov_count, iov_buf,
cnt, &s, false, opt);
- if (err)
+ if (err && opt->verbose)
fprintf(stderr,
"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
iov_count, iov_buf, cnt, err);
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
}
- fprintf(stdout,
- "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
- s.bytes_sent, sent_Bps, sent_Bps/giga,
- s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+ if (opt->verbose)
+ fprintf(stdout,
+ "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+ s.bytes_sent, sent_Bps, sent_Bps/giga,
+ s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
exit(1);
} else if (rxpid == -1) {
perror("msg_loop_rx: ");
sent_Bps = sentBps(s);
recvd_Bps = recvdBps(s);
}
- fprintf(stdout,
- "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
- s.bytes_sent, sent_Bps, sent_Bps/giga,
- s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+ if (opt->verbose)
+ fprintf(stdout,
+ "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
+ s.bytes_sent, sent_Bps, sent_Bps/giga,
+ s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
exit(1);
} else if (txpid == -1) {
perror("msg_loop_tx: ");
SENDPAGE,
};
-int main(int argc, char **argv)
+static int run_options(struct sockmap_options *options, int cg_fd, int test)
{
- int iov_count = 1, length = 1024, rate = 1, tx_prog_fd;
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
- int opt, longindex, err, cg_fd = 0;
- struct sockmap_options options = {0};
- int test = PING_PONG;
- char filename[256];
-
- while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
- long_options, &longindex)) != -1) {
- switch (opt) {
- case 's':
- txmsg_start = atoi(optarg);
- break;
- case 'e':
- txmsg_end = atoi(optarg);
- break;
- case 'a':
- txmsg_apply = atoi(optarg);
- break;
- case 'k':
- txmsg_cork = atoi(optarg);
- break;
- case 'c':
- cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
- if (cg_fd < 0) {
- fprintf(stderr,
- "ERROR: (%i) open cg path failed: %s\n",
- cg_fd, optarg);
- return cg_fd;
- }
- break;
- case 'r':
- rate = atoi(optarg);
- break;
- case 'v':
- options.verbose = 1;
- break;
- case 'i':
- iov_count = atoi(optarg);
- break;
- case 'l':
- length = atoi(optarg);
- break;
- case 'd':
- options.data_test = true;
- break;
- case 't':
- if (strcmp(optarg, "ping") == 0) {
- test = PING_PONG;
- } else if (strcmp(optarg, "sendmsg") == 0) {
- test = SENDMSG;
- } else if (strcmp(optarg, "base") == 0) {
- test = BASE;
- } else if (strcmp(optarg, "base_sendpage") == 0) {
- test = BASE_SENDPAGE;
- } else if (strcmp(optarg, "sendpage") == 0) {
- test = SENDPAGE;
- } else {
- usage(argv);
- return -1;
- }
- break;
- case 0:
- break;
- case 'h':
- default:
- usage(argv);
- return -1;
- }
- }
-
- if (!cg_fd) {
- fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
- argv[0]);
- return -1;
- }
-
- if (setrlimit(RLIMIT_MEMLOCK, &r)) {
- perror("setrlimit(RLIMIT_MEMLOCK)");
- return 1;
- }
-
- snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
- running = 1;
-
- /* catch SIGINT */
- signal(SIGINT, running_handler);
-
- if (load_bpf_file(filename)) {
- fprintf(stderr, "load_bpf_file: (%s) %s\n",
- filename, strerror(errno));
- return 1;
- }
+ int i, key, next_key, err, tx_prog_fd = -1, zero = 0;
/* If base test skip BPF setup */
if (test == BASE || test == BASE_SENDPAGE)
err = bpf_prog_attach(prog_fd[0], map_fd[0],
BPF_SK_SKB_STREAM_PARSER, 0);
if (err) {
- fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n",
- err, strerror(errno));
+ fprintf(stderr,
+ "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n",
+ prog_fd[0], map_fd[0], err, strerror(errno));
return err;
}
}
run:
- err = sockmap_init_sockets();
+ err = sockmap_init_sockets(options->verbose);
if (err) {
fprintf(stderr, "ERROR: test socket failed: %d\n", err);
goto out;
fprintf(stderr,
"ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
err, strerror(errno));
- return err;
+ goto out;
}
err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
fprintf(stderr,
"ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
err, strerror(errno));
- return err;
+ goto out;
}
if (txmsg_redir || txmsg_redir_noisy)
fprintf(stderr,
"ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
err, strerror(errno));
- return err;
+ goto out;
}
if (txmsg_apply) {
fprintf(stderr,
"ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n",
err, strerror(errno));
- return err;
+ goto out;
}
}
fprintf(stderr,
"ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n",
err, strerror(errno));
- return err;
+ goto out;
}
}
fprintf(stderr,
"ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n",
err, strerror(errno));
- return err;
+ goto out;
}
}
fprintf(stderr,
"ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n",
err, strerror(errno));
- return err;
+ goto out;
}
}
}
if (txmsg_skb) {
- int skb_fd = (test == SENDMSG || test == SENDPAGE) ? p2 : p1;
+ int skb_fd = (test == SENDMSG || test == SENDPAGE) ?
+ p2 : p1;
int ingress = BPF_F_INGRESS;
i = 0;
- err = bpf_map_update_elem(map_fd[7], &i, &ingress, BPF_ANY);
+ err = bpf_map_update_elem(map_fd[7],
+ &i, &ingress, BPF_ANY);
if (err) {
fprintf(stderr,
"ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
}
i = 3;
- err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY);
+ err = bpf_map_update_elem(map_fd[0],
+ &i, &skb_fd, BPF_ANY);
if (err) {
fprintf(stderr,
"ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
}
if (txmsg_drop)
- options.drop_expected = true;
+ options->drop_expected = true;
if (test == PING_PONG)
- err = forever_ping_pong(rate, &options);
+ err = forever_ping_pong(options->rate, options);
else if (test == SENDMSG) {
- options.base = false;
- options.sendpage = false;
- err = sendmsg_test(iov_count, length, rate, &options);
+ options->base = false;
+ options->sendpage = false;
+ err = sendmsg_test(options);
} else if (test == SENDPAGE) {
- options.base = false;
- options.sendpage = true;
- err = sendmsg_test(iov_count, length, rate, &options);
+ options->base = false;
+ options->sendpage = true;
+ err = sendmsg_test(options);
} else if (test == BASE) {
- options.base = true;
- options.sendpage = false;
- err = sendmsg_test(iov_count, length, rate, &options);
+ options->base = true;
+ options->sendpage = false;
+ err = sendmsg_test(options);
} else if (test == BASE_SENDPAGE) {
- options.base = true;
- options.sendpage = true;
- err = sendmsg_test(iov_count, length, rate, &options);
+ options->base = true;
+ options->sendpage = true;
+ err = sendmsg_test(options);
} else
fprintf(stderr, "unknown test\n");
out:
+ /* Detatch and zero all the maps */
bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
+ bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
+ bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
+ if (tx_prog_fd >= 0)
+ bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
+
+ for (i = 0; i < 8; i++) {
+ key = next_key = 0;
+ bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
+ while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) {
+ bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
+ key = next_key;
+ }
+ }
+
close(s1);
close(s2);
close(p1);
close(p2);
close(c1);
close(c2);
+ return err;
+}
+
+static char *test_to_str(int test)
+{
+ switch (test) {
+ case SENDMSG:
+ return "sendmsg";
+ case SENDPAGE:
+ return "sendpage";
+ }
+ return "unknown";
+}
+
+#define OPTSTRING 60
+static void test_options(char *options)
+{
+ memset(options, 0, OPTSTRING);
+
+ if (txmsg_pass)
+ strncat(options, "pass,", OPTSTRING);
+ if (txmsg_noisy)
+ strncat(options, "pass_noisy,", OPTSTRING);
+ if (txmsg_redir)
+ strncat(options, "redir,", OPTSTRING);
+ if (txmsg_redir_noisy)
+ strncat(options, "redir_noisy,", OPTSTRING);
+ if (txmsg_drop)
+ strncat(options, "drop,", OPTSTRING);
+ if (txmsg_apply)
+ strncat(options, "apply,", OPTSTRING);
+ if (txmsg_cork)
+ strncat(options, "cork,", OPTSTRING);
+ if (txmsg_start)
+ strncat(options, "start,", OPTSTRING);
+ if (txmsg_end)
+ strncat(options, "end,", OPTSTRING);
+ if (txmsg_ingress)
+ strncat(options, "ingress,", OPTSTRING);
+ if (txmsg_skb)
+ strncat(options, "skb,", OPTSTRING);
+}
+
+static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
+{
+ char *options = calloc(60, sizeof(char));
+ int err;
+
+ if (test == SENDPAGE)
+ opt->sendpage = true;
+ else
+ opt->sendpage = false;
+
+ if (txmsg_drop)
+ opt->drop_expected = true;
+ else
+ opt->drop_expected = false;
+
+ test_options(options);
+
+ fprintf(stdout,
+ "[TEST %i]: (%i, %i, %i, %s, %s): ",
+ test_cnt, opt->rate, opt->iov_count, opt->iov_length,
+ test_to_str(test), options);
+ fflush(stdout);
+ err = run_options(opt, cgrp, test);
+ fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED");
+ test_cnt++;
+ !err ? passed++ : failed++;
+ free(options);
+ return err;
+}
+
+static int test_exec(int cgrp, struct sockmap_options *opt)
+{
+ int err = __test_exec(cgrp, SENDMSG, opt);
+
+ if (err)
+ goto out;
+
+ err = __test_exec(cgrp, SENDPAGE, opt);
+out:
+ return err;
+}
+
+static int test_loop(int cgrp)
+{
+ struct sockmap_options opt;
+
+ int err, i, l, r;
+
+ opt.verbose = 0;
+ opt.base = false;
+ opt.sendpage = false;
+ opt.data_test = false;
+ opt.drop_expected = false;
+ opt.iov_count = 0;
+ opt.iov_length = 0;
+ opt.rate = 0;
+
+ r = 1;
+ for (i = 1; i < 100; i += 33) {
+ for (l = 1; l < 100; l += 33) {
+ opt.rate = r;
+ opt.iov_count = i;
+ opt.iov_length = l;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+ }
+ sched_yield();
+out:
+ return err;
+}
+
+static int test_txmsg(int cgrp)
+{
+ int err;
+
+ txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
+ txmsg_apply = txmsg_cork = 0;
+ txmsg_ingress = txmsg_skb = 0;
+
+ txmsg_pass = 1;
+ err = test_loop(cgrp);
+ txmsg_pass = 0;
+ if (err)
+ goto out;
+
+ txmsg_redir = 1;
+ err = test_loop(cgrp);
+ txmsg_redir = 0;
+ if (err)
+ goto out;
+
+ txmsg_drop = 1;
+ err = test_loop(cgrp);
+ txmsg_drop = 0;
+ if (err)
+ goto out;
+
+ txmsg_redir = 1;
+ txmsg_ingress = 1;
+ err = test_loop(cgrp);
+ txmsg_redir = 0;
+ txmsg_ingress = 0;
+ if (err)
+ goto out;
+out:
+ txmsg_pass = 0;
+ txmsg_redir = 0;
+ txmsg_drop = 0;
+ return err;
+}
+
+static int test_send(struct sockmap_options *opt, int cgrp)
+{
+ int err;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1024;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1024;
+ opt->iov_count = 1;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1;
+ opt->rate = 1024;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 256;
+ opt->iov_count = 1024;
+ opt->rate = 10;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->rate = 100;
+ opt->iov_count = 1;
+ opt->iov_length = 5;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+out:
+ sched_yield();
+ return err;
+}
+
+static int test_mixed(int cgrp)
+{
+ struct sockmap_options opt = {0};
+ int err;
+
+ txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
+ txmsg_apply = txmsg_cork = 0;
+ txmsg_start = txmsg_end = 0;
+ /* Test small and large iov_count values with pass/redir/apply/cork */
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 0;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 0;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1024;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_cork = 4096;
+ txmsg_apply = 4096;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 0;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 0;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1024;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_cork = 4096;
+ txmsg_apply = 4096;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+out:
+ return err;
+}
+
+static int test_start_end(int cgrp)
+{
+ struct sockmap_options opt = {0};
+ int err, i;
+
+ /* Test basic start/end with lots of iov_count and iov_lengths */
+ txmsg_start = 1;
+ txmsg_end = 2;
+ err = test_txmsg(cgrp);
+ if (err)
+ goto out;
+
+ /* Test start/end with cork */
+ opt.rate = 16;
+ opt.iov_count = 1;
+ opt.iov_length = 100;
+ txmsg_cork = 1600;
+
+ for (i = 99; i <= 1600; i += 500) {
+ txmsg_start = 0;
+ txmsg_end = i;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+
+ /* Test start/end with cork but pull data in middle */
+ for (i = 199; i <= 1600; i += 500) {
+ txmsg_start = 100;
+ txmsg_end = i;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+
+ /* Test start/end with cork pulling last sg entry */
+ txmsg_start = 1500;
+ txmsg_end = 1600;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end pull of single byte in last page */
+ txmsg_start = 1111;
+ txmsg_end = 1112;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with end < start */
+ txmsg_start = 1111;
+ txmsg_end = 0;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with end > data */
+ txmsg_start = 0;
+ txmsg_end = 1601;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with start > data */
+ txmsg_start = 1601;
+ txmsg_end = 1600;
+ err = test_exec(cgrp, &opt);
+
+out:
+ txmsg_start = 0;
+ txmsg_end = 0;
+ sched_yield();
+ return err;
+}
+
+char *map_names[] = {
+ "sock_map",
+ "sock_map_txmsg",
+ "sock_map_redir",
+ "sock_apply_bytes",
+ "sock_cork_bytes",
+ "sock_pull_bytes",
+ "sock_redir_flags",
+ "sock_skb_opts",
+};
+
+int prog_attach_type[] = {
+ BPF_SK_SKB_STREAM_PARSER,
+ BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_SOCK_OPS,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+};
+
+int prog_type[] = {
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_SOCK_OPS,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+};
+
+static int populate_progs(char *bpf_file)
+{
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int i = 0;
+ long err;
+
+ obj = bpf_object__open(bpf_file);
+ err = libbpf_get_error(obj);
+ if (err) {
+ char err_buf[256];
+
+ libbpf_strerror(err, err_buf, sizeof(err_buf));
+ printf("Unable to load eBPF objects in file '%s' : %s\n",
+ bpf_file, err_buf);
+ return -1;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ bpf_program__set_type(prog, prog_type[i]);
+ bpf_program__set_expected_attach_type(prog,
+ prog_attach_type[i]);
+ i++;
+ }
+
+ i = bpf_object__load(obj);
+ i = 0;
+ bpf_object__for_each_program(prog, obj) {
+ prog_fd[i] = bpf_program__fd(prog);
+ i++;
+ }
+
+ for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) {
+ maps[i] = bpf_object__find_map_by_name(obj, map_names[i]);
+ map_fd[i] = bpf_map__fd(maps[i]);
+ if (map_fd[i] < 0) {
+ fprintf(stderr, "load_bpf_file: (%i) %s\n",
+ map_fd[i], strerror(errno));
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int __test_suite(char *bpf_file)
+{
+ int cg_fd, err;
+
+ err = populate_progs(bpf_file);
+ if (err < 0) {
+ fprintf(stderr, "ERROR: (%i) load bpf failed\n", err);
+ return err;
+ }
+
+ if (setup_cgroup_environment()) {
+ fprintf(stderr, "ERROR: cgroup env failed\n");
+ return -EINVAL;
+ }
+
+ cg_fd = create_and_get_cgroup(CG_PATH);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, optarg);
+ return cg_fd;
+ }
+
+ /* Tests basic commands and APIs with range of iov values */
+ txmsg_start = txmsg_end = 0;
+ err = test_txmsg(cg_fd);
+ if (err)
+ goto out;
+
+ /* Tests interesting combinations of APIs used together */
+ err = test_mixed(cg_fd);
+ if (err)
+ goto out;
+
+ /* Tests pull_data API using start/end API */
+ err = test_start_end(cg_fd);
+ if (err)
+ goto out;
+
+out:
+ printf("Summary: %i PASSED %i FAILED\n", passed, failed);
+ cleanup_cgroup_environment();
+ close(cg_fd);
+ return err;
+}
+
+static int test_suite(void)
+{
+ int err;
+
+ err = __test_suite(BPF_SOCKMAP_FILENAME);
+ if (err)
+ goto out;
+ err = __test_suite(BPF_SOCKHASH_FILENAME);
+out:
+ return err;
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ int iov_count = 1, length = 1024, rate = 1;
+ struct sockmap_options options = {0};
+ int opt, longindex, err, cg_fd = 0;
+ char *bpf_file = BPF_SOCKMAP_FILENAME;
+ int test = PING_PONG;
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
+ if (argc < 2)
+ return test_suite();
+
+ while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 's':
+ txmsg_start = atoi(optarg);
+ break;
+ case 'e':
+ txmsg_end = atoi(optarg);
+ break;
+ case 'a':
+ txmsg_apply = atoi(optarg);
+ break;
+ case 'k':
+ txmsg_cork = atoi(optarg);
+ break;
+ case 'c':
+ cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, optarg);
+ return cg_fd;
+ }
+ break;
+ case 'r':
+ rate = atoi(optarg);
+ break;
+ case 'v':
+ options.verbose = 1;
+ break;
+ case 'i':
+ iov_count = atoi(optarg);
+ break;
+ case 'l':
+ length = atoi(optarg);
+ break;
+ case 'd':
+ options.data_test = true;
+ break;
+ case 't':
+ if (strcmp(optarg, "ping") == 0) {
+ test = PING_PONG;
+ } else if (strcmp(optarg, "sendmsg") == 0) {
+ test = SENDMSG;
+ } else if (strcmp(optarg, "base") == 0) {
+ test = BASE;
+ } else if (strcmp(optarg, "base_sendpage") == 0) {
+ test = BASE_SENDPAGE;
+ } else if (strcmp(optarg, "sendpage") == 0) {
+ test = SENDPAGE;
+ } else {
+ usage(argv);
+ return -1;
+ }
+ break;
+ case 0:
+ break;
+ case 'h':
+ default:
+ usage(argv);
+ return -1;
+ }
+ }
+
+ if (!cg_fd) {
+ fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
+ argv[0]);
+ return -1;
+ }
+
+ err = populate_progs(bpf_file);
+ if (err) {
+ fprintf(stderr, "populate program: (%s) %s\n",
+ bpf_file, strerror(errno));
+ return 1;
+ }
+ running = 1;
+
+ /* catch SIGINT */
+ signal(SIGINT, running_handler);
+
+ options.iov_count = iov_count;
+ options.iov_length = length;
+ options.rate = rate;
+
+ err = run_options(&options, cg_fd, test);
close(cg_fd);
return err;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#define SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP
+#include "./test_sockmap_kern.h"
-/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/if_ether.h>
-#include <uapi/linux/if_packet.h>
-#include <uapi/linux/ip.h>
-#include "../../tools/testing/selftests/bpf/bpf_helpers.h"
-#include "../../tools/testing/selftests/bpf/bpf_endian.h"
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
/* Sockmap sample program connects a client and a backend together
* using cgroups.
})
struct bpf_map_def SEC("maps") sock_map = {
- .type = BPF_MAP_TYPE_SOCKMAP,
+ .type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_txmsg = {
- .type = BPF_MAP_TYPE_SOCKMAP,
+ .type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_redir = {
- .type = BPF_MAP_TYPE_SOCKMAP,
+ .type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
len, flags);
+#ifdef SOCKMAP
return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
+#else
+ return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags);
+#endif
+
}
SEC("sockops")
if (lport == 10000) {
ret = 1;
+#ifdef SOCKMAP
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
+#else
+ err = bpf_sock_hash_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#endif
bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
if (bpf_ntohl(rport) == 10001) {
ret = 10;
+#ifdef SOCKMAP
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
+#else
+ err = bpf_sock_hash_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#endif
bpf_printk("active(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
key = 2;
flags = *f;
}
+#ifdef SOCKMAP
return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+ return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
}
SEC("sk_msg4")
}
bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
len1, flags, err1 ? err1 : err2);
+#ifdef SOCKMAP
err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+ err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
bpf_printk("sk_msg3: err %i\n", err);
return err;
}
return SK_DROP;
}
-
+int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
- .max_entries = 10000,
+ .max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
.map_flags = BPF_F_STACK_BUILD_ID,
};
+struct bpf_map_def SEC("maps") stack_amap = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct bpf_stack_build_id)
+ * PERF_MAX_STACK_DEPTH,
+ .max_entries = 128,
+};
+
/* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
struct random_urandom_args {
unsigned long long pad;
SEC("tracepoint/random/urandom_read")
int oncpu(struct random_urandom_args *args)
{
+ __u32 max_len = sizeof(struct bpf_stack_build_id)
+ * PERF_MAX_STACK_DEPTH;
__u32 key = 0, val = 0, *value_p;
+ void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK);
- if ((int)key >= 0)
+ if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
+ stack_p = bpf_map_lookup_elem(&stack_amap, &key);
+ if (stack_p)
+ bpf_get_stack(args, stack_p, max_len,
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+ }
return 0;
}
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
- .max_entries = 10000,
+ .max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
- .max_entries = 10000,
+ .max_entries = 16384,
+};
+
+struct bpf_map_def SEC("maps") stack_amap = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
+ .max_entries = 16384,
};
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
+ __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
__u32 key = 0, val = 0, *value_p;
+ void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(ctx, &stackmap, 0);
- if ((int)key >= 0)
+ if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
+ stack_p = bpf_map_lookup_elem(&stack_amap, &key);
+ if (stack_p)
+ bpf_get_stack(ctx, stack_p, max_len, 0);
+ }
return 0;
}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# End-to-end eBPF tunnel test suite
+# The script tests BPF network tunnel implementation.
+#
+# Topology:
+# ---------
+# root namespace | at_ns0 namespace
+# |
+# ----------- | -----------
+# | tnl dev | | | tnl dev | (overlay network)
+# ----------- | -----------
+# metadata-mode | native-mode
+# with bpf |
+# |
+# ---------- | ----------
+# | veth1 | --------- | veth0 | (underlay network)
+# ---------- peer ----------
+#
+#
+# Device Configuration
+# --------------------
+# Root namespace with metadata-mode tunnel + BPF
+# Device names and addresses:
+# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
+# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
+#
+# Namespace at_ns0 with native tunnel
+# Device names and addresses:
+# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
+# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
+#
+#
+# End-to-end ping packet flow
+# ---------------------------
+# Most of the tests start by namespace creation, device configuration,
+# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
+# from root namespace, the following operations happen:
+# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
+# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
+# with remote_ip=172.16.1.200 and others.
+# 3) Outer tunnel header is prepended and route the packet to veth1's egress
+# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
+# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
+# 6) Forward the packet to the overlay tnl dev
+
+PING_ARG="-c 3 -w 10 -q"
+ret=0
+GREEN='\033[0;92m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+config_device()
+{
+ ip netns add at_ns0
+ ip link add veth0 type veth peer name veth1
+ ip link set veth0 netns at_ns0
+ ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip link set dev veth1 up mtu 1500
+ ip addr add dev veth1 172.16.1.200/24
+}
+
+add_gre_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE key 2 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6gretap_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
+ local ::11 remote ::22
+
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip addr add dev $DEV fc80::200/24
+ ip link set dev $DEV up
+}
+
+add_erspan_tunnel()
+{
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 3
+ fi
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6erspan_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 7
+ fi
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_vxlan_tunnel()
+{
+ # Set static ARP entry here because iptables set-mark works
+ # on L3 packet, as a result not applying to ARP packets,
+ # causing errors at get_tunnel_{key/opt}.
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ id 2 dstport 4789 gbp remote 172.16.1.200
+ ip netns exec at_ns0 \
+ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
+ ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external gbp dstport 4789
+ ip link set dev $DEV address 52:54:00:d9:02:00 up
+ ip addr add dev $DEV 10.1.1.200/24
+ arp -s 10.1.1.100 52:54:00:d9:01:00
+}
+
+add_ip6vxlan_tunnel()
+{
+ #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0
+ ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ #ip -4 addr del 172.16.1.200 dev veth1
+ ip -6 addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \
+ local ::11 remote ::22
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external dstport 4789
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_geneve_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ id 2 dstport 6081 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE dstport 6081 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6geneve_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 \
+ remote ::22 # geneve has no local option
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_ipip_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local 172.16.1.100 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ipip6tnl_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local ::11 remote ::22
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+test_gre()
+{
+ TYPE=gretap
+ DEV_NS=gretap00
+ DEV=gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_gre_tunnel
+ attach_bpf $DEV gre_set_tunnel gre_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gre()
+{
+ TYPE=ip6gre
+ DEV_NS=ip6gre00
+ DEV=ip6gre11
+ ret=0
+
+ check $TYPE
+ config_device
+ # reuse the ip6gretap function
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gretap()
+{
+ TYPE=ip6gretap
+ DEV_NS=ip6gretap00
+ DEV=ip6gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_erspan()
+{
+ TYPE=erspan
+ DEV_NS=erspan00
+ DEV=erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_erspan_tunnel $1
+ attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6erspan()
+{
+ TYPE=ip6erspan
+ DEV_NS=ip6erspan00
+ DEV=ip6erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6erspan_tunnel $1
+ attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
+ ping6 $PING_ARG ::11
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=vxlan00
+ DEV=vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_vxlan_tunnel
+ attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=ip6vxlan00
+ DEV=ip6vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6vxlan_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip4 over ip6
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
+test_geneve()
+{
+ TYPE=geneve
+ DEV_NS=geneve00
+ DEV=geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_geneve_tunnel
+ attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6geneve()
+{
+ TYPE=geneve
+ DEV_NS=ip6geneve00
+ DEV=ip6geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6geneve_tunnel
+ attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
+test_ipip()
+{
+ TYPE=ipip
+ DEV_NS=ipip00
+ DEV=ipip11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ipip6()
+{
+ TYPE=ip6tnl
+ DEV_NS=ipip6tnl00
+ DEV=ipip6tnl11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip6tnl_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip4 over ip6
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+setup_xfrm_tunnel()
+{
+ auth=0x$(printf '1%.0s' {1..40})
+ enc=0x$(printf '2%.0s' {1..32})
+ spi_in_to_out=0x1
+ spi_out_to_in=0x2
+ # at_ns0 namespace
+ # at_ns0 -> root
+ ip netns exec at_ns0 \
+ ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+ spi $spi_in_to_out reqid 1 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip netns exec at_ns0 \
+ ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
+ tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+ mode tunnel
+ # root -> at_ns0
+ ip netns exec at_ns0 \
+ ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+ spi $spi_out_to_in reqid 2 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip netns exec at_ns0 \
+ ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
+ tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+ mode tunnel
+ # address & route
+ ip netns exec at_ns0 \
+ ip addr add dev veth0 10.1.1.100/32
+ ip netns exec at_ns0 \
+ ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
+ src 10.1.1.100
+
+ # root namespace
+ # at_ns0 -> root
+ ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+ spi $spi_in_to_out reqid 1 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
+ tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+ mode tunnel
+ # root -> at_ns0
+ ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+ spi $spi_out_to_in reqid 2 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
+ tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+ mode tunnel
+ # address & route
+ ip addr add dev veth1 10.1.1.200/32
+ ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
+}
+
+test_xfrm_tunnel()
+{
+ config_device
+ #tcpdump -nei veth1 ip &
+ output=$(mktemp)
+ cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
+ setup_xfrm_tunnel
+ tc qdisc add dev veth1 clsact
+ tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
+ sec xfrm_get_state
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ sleep 1
+ grep "reqid 1" $output
+ check_err $?
+ grep "spi 0x1" $output
+ check_err $?
+ grep "remote ip 0xac100164" $output
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+}
+
+attach_bpf()
+{
+ DEV=$1
+ SET=$2
+ GET=$3
+ tc qdisc add dev $DEV clsact
+ tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET
+ tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET
+}
+
+cleanup()
+{
+ ip netns delete at_ns0 2> /dev/null
+ ip link del veth1 2> /dev/null
+ ip link del ipip11 2> /dev/null
+ ip link del ipip6tnl11 2> /dev/null
+ ip link del gretap11 2> /dev/null
+ ip link del ip6gre11 2> /dev/null
+ ip link del ip6gretap11 2> /dev/null
+ ip link del vxlan11 2> /dev/null
+ ip link del ip6vxlan11 2> /dev/null
+ ip link del geneve11 2> /dev/null
+ ip link del ip6geneve11 2> /dev/null
+ ip link del erspan11 2> /dev/null
+ ip link del ip6erspan11 2> /dev/null
+}
+
+cleanup_exit()
+{
+ echo "CATCH SIGKILL or SIGINT, cleanup and exit"
+ cleanup
+ exit 0
+}
+
+check()
+{
+ ip link help $1 2>&1 | grep -q "^Usage:"
+ if [ $? -ne 0 ];then
+ echo "SKIP $1: iproute2 not support"
+ cleanup
+ return 1
+ fi
+}
+
+enable_debug()
+{
+ echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
+}
+
+check_err()
+{
+ if [ $ret -eq 0 ]; then
+ ret=$1
+ fi
+}
+
+bpf_tunnel_test()
+{
+ echo "Testing GRE tunnel..."
+ test_gre
+ echo "Testing IP6GRE tunnel..."
+ test_ip6gre
+ echo "Testing IP6GRETAP tunnel..."
+ test_ip6gretap
+ echo "Testing ERSPAN tunnel..."
+ test_erspan v2
+ echo "Testing IP6ERSPAN tunnel..."
+ test_ip6erspan v2
+ echo "Testing VXLAN tunnel..."
+ test_vxlan
+ echo "Testing IP6VXLAN tunnel..."
+ test_ip6vxlan
+ echo "Testing GENEVE tunnel..."
+ test_geneve
+ echo "Testing IP6GENEVE tunnel..."
+ test_ip6geneve
+ echo "Testing IPIP tunnel..."
+ test_ipip
+ echo "Testing IPIP6 tunnel..."
+ test_ipip6
+ echo "Testing IPSec tunnel..."
+ test_xfrm_tunnel
+}
+
+trap cleanup 0 3 6
+trap cleanup_exit 2 9
+
+cleanup
+bpf_tunnel_test
+
+exit 0
+// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2016 VMware
* Copyright (c) 2016 Facebook
*
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <uapi/linux/if_ether.h>
-#include <uapi/linux/if_packet.h>
-#include <uapi/linux/ip.h>
-#include <uapi/linux/ipv6.h>
-#include <uapi/linux/in.h>
-#include <uapi/linux/tcp.h>
-#include <uapi/linux/filter.h>
-#include <uapi/linux/pkt_cls.h>
-#include <uapi/linux/erspan.h>
-#include <net/ipv6.h>
+#include <stddef.h>
+#include <string.h>
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+#include <linux/pkt_cls.h>
+#include <linux/erspan.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
-#define _htonl __builtin_bswap32
#define ERROR(ret) do {\
char fmt[] = "ERROR line:%d ret:%d\n";\
bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
- } while(0)
+ } while (0)
+
+int _version SEC("version") = 1;
struct geneve_opt {
__be16 opt_class;
- u8 type;
- u8 length:5;
- u8 r3:1;
- u8 r2:1;
- u8 r1:1;
- u8 opt_data[8]; /* hard-coded to 8 byte */
+ __u8 type;
+ __u8 length:5;
+ __u8 r3:1;
+ __u8 r2:1;
+ __u8 r1:1;
+ __u8 opt_data[8]; /* hard-coded to 8 byte */
};
struct vxlan_metadata {
- u32 gbp;
+ __u32 gbp;
};
SEC("gre_set_tunnel")
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = _htonl(0x11); /* ::11 */
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
md.version = 1;
md.u.index = bpf_htonl(123);
#else
- u8 direction = 1;
- u8 hwid = 7;
+ __u8 direction = 1;
+ __u8 hwid = 7;
md.version = 2;
md.u.md2.dir = direction;
char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
- u32 index;
+ __u32 index;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = _htonl(0x11);
+ key.remote_ipv6[3] = bpf_htonl(0x11);
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
__builtin_memset(&md, 0, sizeof(md));
#ifdef ERSPAN_V1
- md.u.index = htonl(123);
+ md.u.index = bpf_htonl(123);
md.version = 1;
#else
- u8 direction = 0;
- u8 hwid = 17;
+ __u8 direction = 0;
+ __u8 hwid = 17;
md.version = 2;
md.u.md2.dir = direction;
char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
- u32 index;
+ __u32 index;
int ret;
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
return TC_ACT_OK;
}
+SEC("ip6vxlan_set_tunnel")
+int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6vxlan_get_tunnel")
+int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ struct bpf_tunnel_key key;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+
+ return TC_ACT_OK;
+}
+
SEC("geneve_set_tunnel")
int _geneve_set_tunnel(struct __sk_buff *skb)
{
key.tunnel_ttl = 64;
__builtin_memset(&gopt, 0x0, sizeof(gopt));
- gopt.opt_class = 0x102; /* Open Virtual Networking (OVN) */
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
gopt.type = 0x08;
gopt.r1 = 0;
gopt.r2 = 0;
gopt.r3 = 0;
gopt.length = 2; /* 4-byte multiple */
- *(int *) &gopt.opt_data = 0xdeadbeef;
+ *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX);
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
return TC_ACT_OK;
}
+SEC("ip6geneve_set_tunnel")
+int _ip6geneve_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&gopt, 0x0, sizeof(gopt));
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+ gopt.type = 0x08;
+ gopt.r1 = 0;
+ gopt.r2 = 0;
+ gopt.r3 = 0;
+ gopt.length = 2; /* 4-byte multiple */
+ *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
+
+ ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6geneve_get_tunnel")
+int _ip6geneve_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, gopt.opt_class);
+
+ return TC_ACT_OK;
+}
+
SEC("ipip_set_tunnel")
int _ipip_set_tunnel(struct __sk_buff *skb)
{
if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
return TC_ACT_SHOT;
- if (tcp->dest == htons(5200))
+ if (tcp->dest == bpf_htons(5200))
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- else if (tcp->dest == htons(5201))
+ else if (tcp->dest == bpf_htons(5201))
key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
else
return TC_ACT_SHOT;
return TC_ACT_SHOT;
}
- key.remote_ipv6[0] = _htonl(0x2401db00);
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_ttl = 64;
- if (iph->protocol == IPPROTO_ICMP) {
- key.remote_ipv6[3] = _htonl(1);
- } else {
- if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) {
- ERROR(iph->protocol);
- return TC_ACT_SHOT;
- }
-
- if (tcp->dest == htons(5200)) {
- key.remote_ipv6[3] = _htonl(1);
- } else if (tcp->dest == htons(5201)) {
- key.remote_ipv6[3] = _htonl(2);
- } else {
- ERROR(tcp->dest);
- return TC_ACT_SHOT;
- }
- }
-
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
- bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
- _htonl(key.remote_ipv6[3]));
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
return TC_ACT_SHOT;
}
- key.remote_ipv6[0] = _htonl(0x2401db00);
+ key.remote_ipv6[0] = bpf_htonl(0x2401db00);
key.tunnel_ttl = 64;
- if (iph->nexthdr == NEXTHDR_ICMP) {
- key.remote_ipv6[3] = _htonl(1);
+ if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
+ key.remote_ipv6[3] = bpf_htonl(1);
} else {
- if (iph->nexthdr != NEXTHDR_TCP) {
+ if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
ERROR(iph->nexthdr);
return TC_ACT_SHOT;
}
- if (tcp->dest == htons(5200)) {
- key.remote_ipv6[3] = _htonl(1);
- } else if (tcp->dest == htons(5201)) {
- key.remote_ipv6[3] = _htonl(2);
+ if (tcp->dest == bpf_htons(5200)) {
+ key.remote_ipv6[3] = bpf_htonl(1);
+ } else if (tcp->dest == bpf_htons(5201)) {
+ key.remote_ipv6[3] = bpf_htonl(2);
} else {
ERROR(tcp->dest);
return TC_ACT_SHOT;
}
}
- ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
- ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6);
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
- bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]),
- _htonl(key.remote_ipv6[3]));
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
+ return TC_ACT_OK;
+}
+
+SEC("xfrm_get_state")
+int _xfrm_get_state(struct __sk_buff *skb)
+{
+ struct bpf_xfrm_state x;
+ char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
+ int ret;
+
+ ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
+ if (ret < 0)
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
+ bpf_ntohl(x.remote_ipv4));
return TC_ACT_OK;
}
# endif
#endif
#include "bpf_rlimit.h"
+#include "bpf_rand.h"
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
-#define MAX_INSNS 512
+#define MAX_INSNS BPF_MAXINSNS
#define MAX_FIXUPS 8
#define MAX_NR_MAPS 4
#define POINTER_VALUE 0xcafe4all
struct bpf_insn insns[MAX_INSNS];
int fixup_map1[MAX_FIXUPS];
int fixup_map2[MAX_FIXUPS];
+ int fixup_map3[MAX_FIXUPS];
int fixup_prog[MAX_FIXUPS];
int fixup_map_in_map[MAX_FIXUPS];
const char *errstr;
} result, result_unpriv;
enum bpf_prog_type prog_type;
uint8_t flags;
+ __u8 data[TEST_DATA_LEN];
+ void (*fill_helper)(struct bpf_test *self);
};
/* Note we want this to be 64 bit aligned so that the end of our array is
int foo[MAX_ENTRIES];
};
+struct other_val {
+ long long foo;
+ long long bar;
+};
+
+static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
+{
+ /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+#define PUSH_CNT 51
+ unsigned int len = BPF_MAXINSNS;
+ struct bpf_insn *insn = self->insns;
+ int i = 0, j, k = 0;
+
+ insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+loop:
+ for (j = 0; j < PUSH_CNT; j++) {
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+ i++;
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+ insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
+ insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
+ insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_push),
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+ i++;
+ }
+
+ for (j = 0; j < PUSH_CNT; j++) {
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+ i++;
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+ insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_pop),
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+ i++;
+ }
+ if (++k < 5)
+ goto loop;
+
+ for (; i < len - 1; i++)
+ insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+ insn[len - 1] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
+{
+ struct bpf_insn *insn = self->insns;
+ unsigned int len = BPF_MAXINSNS;
+ int i = 0;
+
+ insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2);
+ i++;
+ while (i < len - 1)
+ insn[i++] = BPF_LD_ABS(BPF_B, 1);
+ insn[i] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_rand_ld_dw(struct bpf_test *self)
+{
+ struct bpf_insn *insn = self->insns;
+ uint64_t res = 0;
+ int i = 0;
+
+ insn[i++] = BPF_MOV32_IMM(BPF_REG_0, 0);
+ while (i < self->retval) {
+ uint64_t val = bpf_semi_rand_get();
+ struct bpf_insn tmp[2] = { BPF_LD_IMM64(BPF_REG_1, val) };
+
+ res ^= val;
+ insn[i++] = tmp[0];
+ insn[i++] = tmp[1];
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ }
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+ insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ insn[i] = BPF_EXIT_INSN();
+ res ^= (res >> 32);
+ self->retval = (uint32_t)res;
+}
+
static struct bpf_test tests[] = {
{
"add+sub+mul",
.errstr = "R1 min value is negative",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
+ {
+ "map lookup helper access to map",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 8 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map update helper access to map",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map update helper access to map: wrong size",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 3 },
+ .fixup_map3 = { 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=8 off=0 size=16",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
+ offsetof(struct other_val, bar)),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm): out-of-bound 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
+ sizeof(struct other_val) - 4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=12 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm): out-of-bound 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=-4 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3,
+ offsetof(struct other_val, bar)),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg): out-of-bound 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3,
+ sizeof(struct other_val) - 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=12 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg): out-of-bound 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, -4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=-4 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+ offsetof(struct other_val, bar), 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 11 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable): no max check",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable): wrong max check",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+ offsetof(struct other_val, bar) + 1, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 11 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=9 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
{
"map element value is preserved across register spilling",
.insns = {
.errstr = "BPF_XADD stores into R2 packet",
.prog_type = BPF_PROG_TYPE_XDP,
},
+ {
+ "bpf_get_stack return R0 within range",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)),
+ BPF_MOV64_IMM(BPF_REG_4, 256),
+ BPF_EMIT_CALL(BPF_FUNC_get_stack),
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32),
+ BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_9),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_EMIT_CALL(BPF_FUNC_get_stack),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 4 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "ld_abs: invalid op 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_DW, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "unknown opcode",
+ },
+ {
+ "ld_abs: invalid op 2",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 256),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_IND(BPF_DW, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "unknown opcode",
+ },
+ {
+ "ld_abs: nmap reduced",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26),
+ BPF_MOV32_IMM(BPF_REG_0, 18),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64),
+ BPF_LD_IND(BPF_W, BPF_REG_7, 14),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60),
+ BPF_MOV32_IMM(BPF_REG_0, 280971478),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60),
+ BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13),
+ BPF_MOV32_IMM(BPF_REG_0, 22),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+ BPF_LD_IND(BPF_H, BPF_REG_7, 14),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52),
+ BPF_MOV32_IMM(BPF_REG_0, 17366),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52),
+ BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ BPF_MOV32_IMM(BPF_REG_0, 256),
+ BPF_EXIT_INSN(),
+ BPF_MOV32_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 256,
+ },
+ {
+ "ld_abs: div + abs, test 1",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+ BPF_LD_ABS(BPF_B, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+ BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 10,
+ },
+ {
+ "ld_abs: div + abs, test 2",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+ BPF_LD_ABS(BPF_B, 128),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+ BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: div + abs, test 3",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: div + abs, test 4",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_B, 256),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: vlan + abs, test 1",
+ .insns = { },
+ .data = {
+ 0x34,
+ },
+ .fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0xbef,
+ },
+ {
+ "ld_abs: vlan + abs, test 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 0),
+ BPF_LD_ABS(BPF_H, 0),
+ BPF_LD_ABS(BPF_W, 0),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+ BPF_MOV64_IMM(BPF_REG_6, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 2),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_push),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+ BPF_LD_ABS(BPF_B, 0),
+ BPF_LD_ABS(BPF_H, 0),
+ BPF_LD_ABS(BPF_W, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 0x34,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 42,
+ },
+ {
+ "ld_abs: jump around ld_abs",
+ .insns = { },
+ .data = {
+ 10, 11,
+ },
+ .fill_helper = bpf_fill_jump_around_ld_abs,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 10,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 1",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 4090,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 2",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 2047,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 3",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 511,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 4",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 5,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
return outer_map_fd;
}
-static char bpf_vlog[32768];
+static char bpf_vlog[UINT_MAX >> 8];
static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
int *map_fds)
{
int *fixup_map1 = test->fixup_map1;
int *fixup_map2 = test->fixup_map2;
+ int *fixup_map3 = test->fixup_map3;
int *fixup_prog = test->fixup_prog;
int *fixup_map_in_map = test->fixup_map_in_map;
+ if (test->fill_helper)
+ test->fill_helper(test);
+
/* Allocating HTs with 1 elem is fine here, since we only test
* for verifier and not do a runtime lookup, so the only thing
* that really matters is value size in this case.
} while (*fixup_map2);
}
+ if (*fixup_map3) {
+ map_fds[1] = create_map(sizeof(struct other_val), 1);
+ do {
+ prog[*fixup_map3].imm = map_fds[1];
+ fixup_map3++;
+ } while (*fixup_map3);
+ }
+
if (*fixup_prog) {
map_fds[2] = create_prog_array();
do {
int *passes, int *errors)
{
int fd_prog, expected_ret, reject_from_alignment;
+ int prog_len, prog_type = test->prog_type;
struct bpf_insn *prog = test->insns;
- int prog_len = probe_filter_length(prog);
- char data_in[TEST_DATA_LEN] = {};
- int prog_type = test->prog_type;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
uint32_t retval;
map_fds[i] = -1;
do_test_fixup(test, prog, map_fds);
+ prog_len = probe_filter_length(prog);
fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
}
if (fd_prog >= 0) {
- err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
- NULL, NULL, &retval, NULL);
+ err = bpf_prog_test_run(fd_prog, 1, test->data,
+ sizeof(test->data), NULL, NULL,
+ &retval, NULL);
if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
printf("Unexpected bpf_prog_test_run error\n");
goto fail_log;
FILE *fd;
fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+ if (!fd) {
+ perror("fopen /proc/sys/"UNPRIV_SYSCTL);
+ unpriv_disabled = true;
+ return;
+ }
if (fgets(buf, 2, fd) == buf && atoi(buf))
unpriv_disabled = true;
fclose(fd);
return EXIT_FAILURE;
}
+ bpf_semi_rand_init();
return do_test(unpriv, from, to);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <assert.h>
+#include <errno.h>
+#include <poll.h>
+#include <unistd.h>
+#include <linux/perf_event.h>
+#include <sys/mman.h>
+#include "trace_helpers.h"
+
+#define MAX_SYMS 300000
+static struct ksym syms[MAX_SYMS];
+static int sym_cnt;
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+ return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+int load_kallsyms(void)
+{
+ FILE *f = fopen("/proc/kallsyms", "r");
+ char func[256], buf[256];
+ char symbol;
+ void *addr;
+ int i = 0;
+
+ if (!f)
+ return -ENOENT;
+
+ while (!feof(f)) {
+ if (!fgets(buf, sizeof(buf), f))
+ break;
+ if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
+ break;
+ if (!addr)
+ continue;
+ syms[i].addr = (long) addr;
+ syms[i].name = strdup(func);
+ i++;
+ }
+ sym_cnt = i;
+ qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
+ return 0;
+}
+
+struct ksym *ksym_search(long key)
+{
+ int start = 0, end = sym_cnt;
+ int result;
+
+ while (start < end) {
+ size_t mid = start + (end - start) / 2;
+
+ result = key - syms[mid].addr;
+ if (result < 0)
+ end = mid;
+ else if (result > 0)
+ start = mid + 1;
+ else
+ return &syms[mid];
+ }
+
+ if (start >= 1 && syms[start - 1].addr < key &&
+ key < syms[start].addr)
+ /* valid ksym */
+ return &syms[start - 1];
+
+ /* out of range. return _stext */
+ return &syms[0];
+}
+
+static int page_size;
+static int page_cnt = 8;
+static struct perf_event_mmap_page *header;
+
+int perf_event_mmap(int fd)
+{
+ void *base;
+ int mmap_size;
+
+ page_size = getpagesize();
+ mmap_size = page_size * (page_cnt + 1);
+
+ base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (base == MAP_FAILED) {
+ printf("mmap err\n");
+ return -1;
+ }
+
+ header = base;
+ return 0;
+}
+
+static int perf_event_poll(int fd)
+{
+ struct pollfd pfd = { .fd = fd, .events = POLLIN };
+
+ return poll(&pfd, 1, 1000);
+}
+
+struct perf_event_sample {
+ struct perf_event_header header;
+ __u32 size;
+ char data[];
+};
+
+static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv)
+{
+ struct perf_event_sample *e = event;
+ perf_event_print_fn fn = priv;
+ int ret;
+
+ if (e->header.type == PERF_RECORD_SAMPLE) {
+ ret = fn(e->data, e->size);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ return ret;
+ } else if (e->header.type == PERF_RECORD_LOST) {
+ struct {
+ struct perf_event_header header;
+ __u64 id;
+ __u64 lost;
+ } *lost = (void *) e;
+ printf("lost %lld events\n", lost->lost);
+ } else {
+ printf("unknown event type=%d size=%d\n",
+ e->header.type, e->header.size);
+ }
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+int perf_event_poller(int fd, perf_event_print_fn output_fn)
+{
+ enum bpf_perf_event_ret ret;
+ void *buf = NULL;
+ size_t len = 0;
+
+ for (;;) {
+ perf_event_poll(fd);
+ ret = bpf_perf_event_read_simple(header, page_cnt * page_size,
+ page_size, &buf, &len,
+ bpf_perf_event_print,
+ output_fn);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ break;
+ }
+ free(buf);
+
+ return ret;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TRACE_HELPER_H
+#define __TRACE_HELPER_H
+
+#include <libbpf.h>
+
+struct ksym {
+ long addr;
+ char *name;
+};
+
+int load_kallsyms(void);
+struct ksym *ksym_search(long key);
+
+typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
+
+int perf_event_mmap(int fd);
+/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */
+int perf_event_poller(int fd, perf_event_print_fn output_fn);
+#endif
#include <stdlib.h>
#define BUF_SIZE 256
-int main(void)
+
+int main(int argc, char *argv[])
{
int fd = open("/dev/urandom", O_RDONLY);
int i;
char buf[BUF_SIZE];
+ int count = 4;
if (fd < 0)
return 1;
- for (i = 0; i < 4; ++i)
+
+ if (argc == 2)
+ count = atoi(argv[1]);
+
+ for (i = 0; i < count; ++i)
read(fd, buf, BUF_SIZE);
close(fd);
# SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := dnotify_test devpts_pts
-all: $(TEST_PROGS)
-include ../lib.mk
+TEST_GEN_PROGS := devpts_pts
+TEST_GEN_PROGS_EXTENDED := dnotify_test
-clean:
- rm -fr $(TEST_PROGS)
+include ../lib.mk
all:
TEST_PROGS := fw_run_tests.sh
+TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
include ../lib.mk
if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
fi
- if [ "$OLD_FWPATH" = "" ]; then
- OLD_FWPATH=" "
- fi
if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then
- echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ if [ "$OLD_FWPATH" = "" ]; then
+ # A zero-length write won't work; write a null byte
+ printf '\000' >/sys/module/firmware_class/parameters/path
+ else
+ echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ fi
fi
if [ -f $FW ]; then
rm -f "$FW"
run_test_config_0003
else
echo "Running basic kernel configuration, working with your config"
- run_test
+ run_tests
fi
echo "Test extended error support"
echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
-echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger &>/dev/null
+! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
fail "Failed to generate extended error in histogram"
fi
--- /dev/null
+#!/bin/sh
+# description: event trigger - test multiple actions on hist trigger
+
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test multiple actions on hist trigger"
+echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+TRIGGER1=events/sched/sched_wakeup/trigger
+TRIGGER2=events/sched/sched_switch/trigger
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' > $TRIGGER1
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
+
+do_reset
+
+exit 0
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
# After inclusion, $(OUTPUT) is defined and
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
#include <errno.h>
#include <unistd.h>
#include <fcntl.h>
+#include "kselftest.h"
ssize_t test_write(int fd, const void *buf, size_t count);
ssize_t test_read(int fd, void *buf, size_t count);
int kvm_fd;
kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
vm->mode = mode;
kvm_fd = open(KVM_DEV_PATH, perm);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
/* Create VM. */
vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL);
cpuid = allocate_kvm_cpuid2();
kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
int dev_fd, ret;
dev_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i",
- __func__, KVM_DEV_PATH, dev_fd, errno);
+ if (dev_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
TEST_ASSERT(ret >= sizeof(struct kvm_run),
{
}
+#define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
int main(int argc, char *argv[])
{
struct kvm_vm *vm;
setbuf(stdout, NULL);
cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
- TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS,
- "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n",
- cap, KVM_SYNC_X86_VALID_FIELDS);
+ if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+ fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+ if ((cap & INVALID_SYNC_FIELD) != 0) {
+ fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+ exit(KSFT_SKIP);
+ }
/* Create VM */
vm = vm_create_default(VCPU_ID, guest_code);
run = vcpu_state(vm, VCPU_ID);
/* Request reading invalid register set from VCPU. */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+ run->kvm_valid_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+ run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(rv < 0 && errno == EINVAL,
"Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
/* Request setting invalid register set into VCPU. */
- run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(rv < 0 && errno == EINVAL,
"Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
/* Request and verify all valid register sets. */
/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
"Unexpected exit reason: %u (%s),\n",
run->s.regs.sregs.apic_base = 1 << 11;
/* TODO run->s.regs.events.XYZ = ABC; */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
/* Clear kvm_dirty_regs bits, verify new s.regs values are
* overwritten with existing guest values.
*/
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
run->kvm_dirty_regs = 0;
run->s.regs.regs.r11 = 0xDEADBEEF;
rv = _vcpu_run(vm, VCPU_ID);
* with kvm_sync_regs values.
*/
run->kvm_valid_regs = 0;
- run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_dirty_regs = TEST_SYNC_FIELDS;
run->s.regs.regs.r11 = 0xBBBB;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
if (!(entry->ecx & CPUID_VMX)) {
- printf("nested VMX not enabled, skipping test");
- return 0;
+ fprintf(stderr, "nested VMX not enabled, skipping test\n");
+ exit(KSFT_SKIP);
}
vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);
.ONESHELL:
define RUN_TESTS
- @export KSFT_TAP_LEVEL=`echo 1`;
- @test_num=`echo 0`;
- @echo "TAP version 13";
- @for TEST in $(1); do \
+ @export KSFT_TAP_LEVEL=`echo 1`; \
+ test_num=`echo 0`; \
+ echo "TAP version 13"; \
+ for TEST in $(1); do \
BASENAME_TEST=`basename $$TEST`; \
test_num=`echo $$test_num+1 | bc`; \
echo "selftests: $$BASENAME_TEST"; \
reuseport_dualstack
reuseaddr_conflict
tcp_mmap
+udpgso
+udpgso_bench_rx
+udpgso_bench_tx
CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += udpgso_bench.sh
+TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
-TEST_GEN_FILES += tcp_mmap
+TEST_GEN_FILES += tcp_mmap tcp_inq
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+ learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+ flood_test $swp2 $h1 $h2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
NUM_NETIFS=4
source lib.sh
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+ learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+ flood_test $swp2 $h1 $h2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
exit $EXIT_STATUS
vrf_destroy $vrf_name
}
+tunnel_create()
+{
+ local name=$1; shift
+ local type=$1; shift
+ local local=$1; shift
+ local remote=$1; shift
+
+ ip link add name $name type $type \
+ local $local remote $remote "$@"
+ ip link set dev $name up
+}
+
+tunnel_destroy()
+{
+ local name=$1; shift
+
+ ip link del dev $name
+}
+
master_name_get()
{
local if_name=$1
ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
}
+tc_rule_stats_get()
+{
+ local dev=$1; shift
+ local pref=$1; shift
+
+ tc -j -s filter show dev $dev ingress pref $pref |
+ jq '.[1].options.actions[].stats.packets'
+}
+
mac_get()
{
local if_name=$1
echo $((ageing_time / 100))
}
-forwarding_enable()
+declare -A SYSCTL_ORIG
+sysctl_set()
+{
+ local key=$1; shift
+ local value=$1; shift
+
+ SYSCTL_ORIG[$key]=$(sysctl -n $key)
+ sysctl -qw $key=$value
+}
+
+sysctl_restore()
{
- ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding)
- ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding)
+ local key=$1; shift
- sysctl -q -w net.ipv4.conf.all.forwarding=1
- sysctl -q -w net.ipv6.conf.all.forwarding=1
+ sysctl -qw $key=${SYSCTL_ORIG["$key"]}
+}
+
+forwarding_enable()
+{
+ sysctl_set net.ipv4.conf.all.forwarding 1
+ sysctl_set net.ipv6.conf.all.forwarding 1
}
forwarding_restore()
{
- sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd
- sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd
+ sysctl_restore net.ipv6.conf.all.forwarding
+ sysctl_restore net.ipv4.conf.all.forwarding
}
tc_offload_check()
return 0
}
+slow_path_trap_install()
+{
+ local dev=$1; shift
+ local direction=$1; shift
+
+ if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+ # For slow-path testing, we need to install a trap to get to
+ # slow path the packets that would otherwise be switched in HW.
+ tc filter add dev $dev $direction pref 1 \
+ flower skip_sw action trap
+ fi
+}
+
+slow_path_trap_uninstall()
+{
+ local dev=$1; shift
+ local direction=$1; shift
+
+ if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+ tc filter del dev $dev $direction pref 1 flower skip_sw
+ fi
+}
+
+__icmp_capture_add_del()
+{
+ local add_del=$1; shift
+ local pref=$1; shift
+ local vsuf=$1; shift
+ local tundev=$1; shift
+ local filter=$1; shift
+
+ tc filter $add_del dev "$tundev" ingress \
+ proto ip$vsuf pref $pref \
+ flower ip_proto icmp$vsuf $filter \
+ action pass
+}
+
+icmp_capture_install()
+{
+ __icmp_capture_add_del add 100 "" "$@"
+}
+
+icmp_capture_uninstall()
+{
+ __icmp_capture_add_del del 100 "" "$@"
+}
+
+icmp6_capture_install()
+{
+ __icmp_capture_add_del add 100 v6 "$@"
+}
+
+icmp6_capture_uninstall()
+{
+ __icmp_capture_add_del del 100 v6 "$@"
+}
+
+matchall_sink_create()
+{
+ local dev=$1; shift
+
+ tc qdisc add dev $dev clsact
+ tc filter add dev $dev ingress \
+ pref 10000 \
+ matchall \
+ action drop
+}
+
+tests_run()
+{
+ local current_test
+
+ for current_test in ${TESTS:-$ALL_TESTS}; do
+ $current_test
+ done
+}
+
##############################################################################
# Tests
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the device to mirror to is a
+# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated,
+# and another gretap / ip6gretap netdevice is then capable of decapsulating the
+# traffic. Test that the payload is what is expected (ICMP ping request or
+# reply, depending on test).
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+ test_gretap_mac
+ test_ip6gretap_mac
+ test_two_spans
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_mac()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local prot=$1; shift
+ local what=$1; shift
+
+ local swp3mac=$(mac_get $swp3)
+ local h3mac=$(mac_get $h3)
+
+ RET=0
+
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ tc qdisc add dev $h3 clsact
+ tc filter add dev $h3 ingress pref 77 prot $prot \
+ flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
+ action pass
+
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+ tc filter del dev $h3 ingress pref 77
+ tc qdisc del dev $h3 clsact
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what: envelope MAC ($tcflags)"
+}
+
+test_two_spans()
+{
+ RET=0
+
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+ mirror_install $swp1 egress gt6 "matchall $tcflags"
+ quick_test_span_gre_dir gt4 ingress
+ quick_test_span_gre_dir gt6 egress
+
+ mirror_uninstall $swp1 ingress
+ fail_test_span_gre_dir gt4 ingress
+ quick_test_span_gre_dir gt6 egress
+
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+ mirror_uninstall $swp1 egress
+ quick_test_span_gre_dir gt4 ingress
+ fail_test_span_gre_dir gt6 egress
+
+ mirror_uninstall $swp1 ingress
+ log_test "two simultaneously configured mirrors ($tcflags)"
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_gretap_mac()
+{
+ test_span_gre_mac gt4 ingress ip "mirror to gretap"
+ test_span_gre_mac gt4 egress ip "mirror to gretap"
+}
+
+test_ip6gretap_mac()
+{
+ test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
+ test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | +---------------------------------------------------------------------+ |
+# | | OL + gt6 (ip6gretap) + gt4 (gretap) | |
+# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | |
+# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | |
+# | | : ttl=100 : ttl=100 | |
+# | | : tos=inherit : tos=inherit | |
+# | +-------------------------:--|-------------------:--|-----------------+ |
+# | : | : | |
+# | +-------------------------:--|-------------------:--|-----------------+ |
+# | | UL : |,---------------------' | |
+# | | + $swp3 : || : | |
+# | | | 192.0.2.129/28 : vv : | |
+# | | | 2001:db8:2::1/64 : + ul (dummy) : | |
+# | +---|---------------------:----------------------:--------------------+ |
+# +-----|---------------------:----------------------:----------------------+
+# | : :
+# +-----|---------------------:----------------------:----------------------+
+# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) |
+# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 |
+# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 |
+# | ttl=100 ttl=100 |
+# | tos=inherit tos=inherit |
+# | |
+# +-------------------------------------------------------------------------+
+#
+# This tests mirroring to gretap and ip6gretap configured in an overlay /
+# underlay manner, i.e. with a bound dummy device that marks underlay VRF where
+# the encapsulated packed should be routed.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+h3_create()
+{
+ simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64
+
+ tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+ ip link set h3-gt4 vrf v$h3
+ matchall_sink_create h3-gt4
+
+ tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+ ip link set h3-gt6 vrf v$h3
+ matchall_sink_create h3-gt6
+}
+
+h3_destroy()
+{
+ tunnel_destroy h3-gt6
+ tunnel_destroy h3-gt4
+
+ simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64
+}
+
+switch_create()
+{
+ # Bridge between H1 and H2.
+
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+
+ # Underlay.
+
+ simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+ ip link add name ul type dummy
+ ip link set dev ul master v$swp3
+ ip link set dev ul up
+
+ # Overlay.
+
+ vrf_create vrf-ol
+ ip link set dev vrf-ol up
+
+ tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+ ttl 100 tos inherit dev ul
+ ip link set dev gt4 master vrf-ol
+ ip link set dev gt4 up
+
+ tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+ ttl 100 tos inherit dev ul allow-localremote
+ ip link set dev gt6 master vrf-ol
+ ip link set dev gt6 up
+}
+
+switch_destroy()
+{
+ vrf_destroy vrf-ol
+
+ tunnel_destroy gt6
+ tunnel_destroy gt4
+
+ simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+ ip link del dev ul
+
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap w/ UL"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap w/ UL"
+}
+
+test_all()
+{
+ RET=0
+
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test how mirrors to gretap and ip6gretap react to changes to relevant
+# configuration.
+
+ALL_TESTS="
+ test_ttl
+ test_tun_up
+ test_egress_up
+ test_remote_ip
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ # This test downs $swp3, which deletes the configured IPv6 address
+ # unless this sysctl is set.
+ sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_ttl()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local prot=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ tc qdisc add dev $h3 clsact
+ tc filter add dev $h3 ingress pref 77 prot $prot \
+ flower ip_ttl 50 action pass
+
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0
+
+ ip link set dev $tundev type $type ttl 50
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+ ip link set dev $tundev type $type ttl 100
+ tc filter del dev $h3 ingress pref 77
+ tc qdisc del dev $h3 clsact
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: TTL change ($tcflags)"
+}
+
+test_span_gre_tun_up()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev down
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev up
+
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: tunnel down/up ($tcflags)"
+}
+
+test_span_gre_egress_up()
+{
+ local tundev=$1; shift
+ local remote_ip=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $swp3 down
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ # After setting the device up, wait for neighbor to get resolved so that
+ # we can expect mirroring to work.
+ ip link set dev $swp3 up
+ while true; do
+ ip neigh sh dev $swp3 $remote_ip nud reachable |
+ grep -q ^
+ if [[ $? -ne 0 ]]; then
+ sleep 1
+ else
+ break
+ fi
+ done
+
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: egress down/up ($tcflags)"
+}
+
+test_span_gre_remote_ip()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local correct_ip=$1; shift
+ local wrong_ip=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev type $type remote $wrong_ip
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev type $type remote $correct_ip
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: remote address change ($tcflags)"
+}
+
+test_ttl()
+{
+ test_span_gre_ttl gt4 gretap ip "mirror to gretap"
+ test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap"
+}
+
+test_tun_up()
+{
+ test_span_gre_tun_up gt4 "mirror to gretap"
+ test_span_gre_tun_up gt6 "mirror to ip6gretap"
+}
+
+test_egress_up()
+{
+ test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap"
+ test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap"
+}
+
+test_remote_ip()
+{
+ test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap"
+ test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The
+# interfaces on H1 and H2 have two addresses each. Flower match on one of the
+# addresses is configured with mirror action. It is expected that when pinging
+# this address, mirroring takes place, whereas when pinging the other one,
+# there's no mirroring.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+
+ ip address add dev $h1 192.0.2.3/28
+ ip address add dev $h2 192.0.2.4/28
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h2 192.0.2.4/28
+ ip address del dev $h1 192.0.2.3/28
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_dir_acl()
+{
+ test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4
+}
+
+full_test_span_gre_dir_acl()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local match_dip=$1; shift
+ local what=$1; shift
+
+ mirror_install $swp1 $direction $tundev \
+ "protocol ip flower $tcflags dst_ip $match_dip"
+ fail_test_span_gre_dir $tundev $direction
+ test_span_gre_dir_acl "$tundev" "$direction" \
+ "$forward_type" "$backward_type"
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what ($tcflags)"
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap"
+ full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap"
+ full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap"
+}
+
+test_all()
+{
+ RET=0
+
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+do_test_span_gre_dir_ips()
+{
+ local expect=$1; shift
+ local tundev=$1; shift
+ local direction=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ icmp_capture_install h3-$tundev
+ mirror_test v$h1 $ip1 $ip2 h3-$tundev 100 $expect
+ mirror_test v$h2 $ip2 $ip1 h3-$tundev 100 $expect
+ icmp_capture_uninstall h3-$tundev
+}
+
+quick_test_span_gre_dir_ips()
+{
+ do_test_span_gre_dir_ips 10 "$@"
+}
+
+fail_test_span_gre_dir_ips()
+{
+ do_test_span_gre_dir_ips 0 "$@"
+}
+
+test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ quick_test_span_gre_dir_ips "$tundev" "$direction" "$ip1" "$ip2"
+
+ icmp_capture_install h3-$tundev "type $forward_type"
+ mirror_test v$h1 $ip1 $ip2 h3-$tundev 100 10
+ icmp_capture_uninstall h3-$tundev
+
+ icmp_capture_install h3-$tundev "type $backward_type"
+ mirror_test v$h2 $ip2 $ip1 h3-$tundev 100 10
+ icmp_capture_uninstall h3-$tundev
+}
+
+full_test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local what=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ test_span_gre_dir_ips "$tundev" "$direction" "$forward_type" \
+ "$backward_type" "$ip1" "$ip2"
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what ($tcflags)"
+}
+
+quick_test_span_gre_dir()
+{
+ quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+fail_test_span_gre_dir()
+{
+ fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+test_span_gre_dir()
+{
+ test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_dir()
+{
+ full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for
+# the tunnel remote address has invalid address at the time that the mirroring
+# is set up. Later on, the neighbor is deleted and it is expected to be
+# reinitialized using the usual ARP process, and the mirroring offload updated.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_neigh()
+{
+ local addr=$1; shift
+ local tundev=$1; shift
+ local direction=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+ ip neigh del dev $swp3 $addr
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what: neighbor change ($tcflags)"
+}
+
+test_gretap()
+{
+ test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap"
+ test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap"
+ test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint
+# is reachable through a next-hop route (as opposed to directly-attached route).
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ sysctl_set net.ipv4.conf.all.rp_filter 0
+ sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.161/28
+ ip address add dev $h3 192.0.2.162/28
+ ip address add dev gt4 192.0.2.129/32
+ ip address add dev h3-gt4 192.0.2.130/32
+
+ # IPv6 route can't be added after address. Such routes are rejected due
+ # to the gateway address having been configured on the local system. It
+ # works the other way around though.
+ ip address add dev $swp3 2001:db8:4::1/64
+ ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2
+ ip address add dev $h3 2001:db8:4::2/64
+ ip address add dev gt6 2001:db8:2::1
+ ip address add dev h3-gt6 2001:db8:2::2
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2
+ ip address del dev $h3 2001:db8:4::2/64
+ ip address del dev $swp3 2001:db8:4::1/64
+
+ ip address del dev $h3 192.0.2.162/28
+ ip address del dev $swp3 192.0.2.161/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+
+ sysctl_restore net.ipv4.conf.$h3.rp_filter
+ sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+test_gretap()
+{
+ RET=0
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+
+ # For IPv4, test that there's no mirroring without the route directing
+ # the traffic to tunnel remote address. Then add it and test that
+ # mirroring starts. For IPv6 we can't test this due to the limitation
+ # that routes for locally-specified IPv6 addresses can't be added.
+ fail_test_span_gre_dir gt4 ingress
+
+ ip route add 192.0.2.130/32 via 192.0.2.162
+ quick_test_span_gre_dir gt4 ingress
+ ip route del 192.0.2.130/32 via 192.0.2.162
+
+ mirror_uninstall $swp1 ingress
+ log_test "mirror to gre with next-hop remote ($tcflags)"
+}
+
+test_ip6gretap()
+{
+ RET=0
+
+ mirror_install $swp1 ingress gt6 "matchall $tcflags"
+ quick_test_span_gre_dir gt6 ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "mirror to ip6gre with next-hop remote ($tcflags)"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+# This is the standard topology for testing mirroring to gretap and ip6gretap
+# netdevices. The tests that use it tweak it in one way or another--importantly,
+# $swp3 and $h3 need to have addresses set up.
+#
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | + $swp3 + gt6 (ip6gretap) + gt4 (gretap) |
+# | | : loc=2001:db8:2::1 : loc=192.0.2.129 |
+# | | : rem=2001:db8:2::2 : rem=192.0.2.130 |
+# | | : ttl=100 : ttl=100 |
+# | | : tos=inherit : tos=inherit |
+# | | : : |
+# +-----|---------------------:----------------------:----------------------+
+# | : :
+# +-----|---------------------:----------------------:----------------------+
+# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) |
+# | loc=2001:db8:2::2 loc=192.0.2.130 |
+# | rem=2001:db8:2::1 rem=192.0.2.129 |
+# | ttl=100 ttl=100 |
+# | tos=inherit tos=inherit |
+# | |
+# +-------------------------------------------------------------------------+
+
+mirror_gre_topo_h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+mirror_gre_topo_h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+mirror_gre_topo_h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+}
+
+mirror_gre_topo_h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+mirror_gre_topo_h3_create()
+{
+ simple_if_init $h3
+
+ tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+ ip link set h3-gt4 vrf v$h3
+ matchall_sink_create h3-gt4
+
+ tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+ ip link set h3-gt6 vrf v$h3
+ matchall_sink_create h3-gt6
+}
+
+mirror_gre_topo_h3_destroy()
+{
+ tunnel_destroy h3-gt6
+ tunnel_destroy h3-gt4
+
+ simple_if_fini $h3
+}
+
+mirror_gre_topo_switch_create()
+{
+ ip link set dev $swp3 up
+
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+ ttl 100 tos inherit
+
+ tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+ ttl 100 tos inherit allow-localremote
+
+ tc qdisc add dev $swp1 clsact
+}
+
+mirror_gre_topo_switch_destroy()
+{
+ tc qdisc del dev $swp1 clsact
+
+ tunnel_destroy gt6
+ tunnel_destroy gt4
+
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link del dev br1
+
+ ip link set dev $swp3 down
+}
+
+mirror_gre_topo_create()
+{
+ mirror_gre_topo_h1_create
+ mirror_gre_topo_h2_create
+ mirror_gre_topo_h3_create
+
+ mirror_gre_topo_switch_create
+}
+
+mirror_gre_topo_destroy()
+{
+ mirror_gre_topo_switch_destroy
+
+ mirror_gre_topo_h3_destroy
+ mirror_gre_topo_h2_destroy
+ mirror_gre_topo_h1_destroy
+}
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+mirror_install()
+{
+ local from_dev=$1; shift
+ local direction=$1; shift
+ local to_dev=$1; shift
+ local filter=$1; shift
+
+ tc filter add dev $from_dev $direction \
+ pref 1000 $filter \
+ action mirred egress mirror dev $to_dev
+}
+
+mirror_uninstall()
+{
+ local from_dev=$1; shift
+ local direction=$1; shift
+
+ tc filter del dev $swp1 $direction pref 1000
+}
+
+mirror_test()
+{
+ local vrf_name=$1; shift
+ local sip=$1; shift
+ local dip=$1; shift
+ local dev=$1; shift
+ local pref=$1; shift
+ local expect=$1; shift
+
+ local t0=$(tc_rule_stats_get $dev $pref)
+ ip vrf exec $vrf_name \
+ ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null
+ local t1=$(tc_rule_stats_get $dev $pref)
+ local delta=$((t1 - t0))
+ # Tolerate a couple stray extra packets.
+ ((expect <= delta && delta <= expect + 2))
+ check_err $? "Expected to capture $expect packets, got $delta."
+}
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6"
NUM_NETIFS=4
source lib.sh
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
+tests_run
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
NUM_NETIFS=8
source lib.sh
diff=$(echo $weights_ratio - $packets_ratio | bc -l)
diff=${diff#-}
- test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0
+ test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
check_err $? "Too large discrepancy between expected and measured ratios"
log_test "$desc"
log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
local weight_rp13=$3
local t0_rp12 t0_rp13 t1_rp12 t1_rp13
local packets_rp12 packets_rp13
- local hash_policy
# Transmit multiple flows from h1 to h2 and make sure they are
# distributed between both multipath links (rp12 and rp13)
# according to the configured weights.
- hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
- sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+ sysctl_set net.ipv4.fib_multipath_hash_policy 1
ip route replace 198.51.100.0/24 vrf vrf-r1 \
nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \
nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13
ip route replace 198.51.100.0/24 vrf vrf-r1 \
nexthop via 169.254.2.22 dev $rp12 \
nexthop via 169.254.3.23 dev $rp13
- sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy
+ sysctl_restore net.ipv4.fib_multipath_hash_policy
}
multipath6_l4_test()
local weight_rp13=$3
local t0_rp12 t0_rp13 t1_rp12 t1_rp13
local packets_rp12 packets_rp13
- local hash_policy
# Transmit multiple flows from h1 to h2 and make sure they are
# distributed between both multipath links (rp12 and rp13)
# according to the configured weights.
- hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy)
- sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+ sysctl_set net.ipv6.fib_multipath_hash_policy 1
ip route replace 2001:db8:2::/64 vrf vrf-r1 \
nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \
nexthop via fe80:2::22 dev $rp12 \
nexthop via fe80:3::23 dev $rp13
- sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
}
multipath6_test()
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
-multipath_test
+tests_run
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
+ mirred_egress_mirror_test gact_trap_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
{
RET=0
+ if [[ "$tcflags" != "skip_sw" ]]; then
+ return 0;
+ fi
+
tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
skip_hw dst_ip 192.0.2.2 action drop
tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \
ip link set $swp1 address $swp1origmac
}
+mirred_egress_redirect_test()
+{
+ mirred_egress_test "redirect"
+}
+
+mirred_egress_mirror_test()
+{
+ mirred_egress_test "mirror"
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-gact_drop_and_ok_test
-mirred_egress_test "redirect"
-mirred_egress_test "mirror"
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- gact_drop_and_ok_test
- mirred_egress_test "redirect"
- mirred_egress_test "mirror"
- gact_trap_test
+ tests_run
fi
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test"
NUM_NETIFS=2
source tc_common.sh
source lib.sh
setup_prepare
setup_wait
-unreachable_chain_test
-gact_goto_chain_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- unreachable_chain_test
- gact_goto_chain_test
+ tests_run
fi
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \
+ match_src_ip_test match_ip_flags_test"
NUM_NETIFS=2
source tc_common.sh
source lib.sh
setup_prepare
setup_wait
-match_dst_mac_test
-match_src_mac_test
-match_dst_ip_test
-match_src_ip_test
-match_ip_flags_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- match_dst_mac_test
- match_src_mac_test
- match_dst_ip_test
- match_src_ip_test
- match_ip_flags_test
+ tests_run
fi
exit $EXIT_STATUS
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="shared_block_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
setup_prepare
setup_wait
-shared_block_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- shared_block_test
+ tests_run
fi
exit $EXIT_STATUS
fail=0
- min=1280
+ min=68 # vti6 can carry IPv4 packets too
max=$((65535 - 40))
# Check invalid values first
for v in $((min - 1)) $((max + 1)); do
done
# Now check valid values
- for v in 1280 1300 $((65535 - 40)); do
+ for v in 68 1280 1300 $((65535 - 40)); do
${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
${ns_a} ip link del vti6_a
echo "PASS: macsec"
}
+#-------------------------------------------------------------------
+# Example commands
+# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07 replay-window 32 \
+# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+# sel src 14.0.0.52/24 dst 14.0.0.70/24
+# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07
+#
+# Subcommands not tested
+# ip x s update
+# ip x s allocspi
+# ip x s deleteall
+# ip x p update
+# ip x p deleteall
+# ip x p set
+#-------------------------------------------------------------------
+kci_test_ipsec()
+{
+ srcip="14.0.0.52"
+ dstip="14.0.0.70"
+ algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+
+ # flush to be sure there's nothing configured
+ ip x s flush ; ip x p flush
+ check_err $?
+
+ # start the monitor in the background
+ tmpfile=`mktemp ipsectestXXX`
+ ip x m > $tmpfile &
+ mpid=$!
+ sleep 0.2
+
+ ipsecid="proto esp src $srcip dst $dstip spi 0x07"
+ ip x s add $ipsecid \
+ mode transport reqid 0x07 replay-window 32 \
+ $algo sel src $srcip/24 dst $dstip/24
+ check_err $?
+
+ lines=`ip x s list | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x s count | grep -q "SAD count 1"
+ check_err $?
+
+ lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x s delete $ipsecid
+ check_err $?
+
+ lines=`ip x s list | wc -l`
+ test $lines -eq 0
+ check_err $?
+
+ ipsecsel="dir out src $srcip/24 dst $dstip/24"
+ ip x p add $ipsecsel \
+ tmpl proto esp src $srcip dst $dstip \
+ spi 0x07 mode transport reqid 0x07
+ check_err $?
+
+ lines=`ip x p list | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x p count | grep -q "SPD IN 0 OUT 1 FWD 0"
+ check_err $?
+
+ lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x p delete $ipsecsel
+ check_err $?
+
+ lines=`ip x p list | wc -l`
+ test $lines -eq 0
+ check_err $?
+
+ # check the monitor results
+ kill $mpid
+ lines=`wc -l $tmpfile | cut "-d " -f1`
+ test $lines -eq 20
+ check_err $?
+ rm -rf $tmpfile
+
+ # clean up any leftovers
+ ip x s flush
+ check_err $?
+ ip x p flush
+ check_err $?
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: ipsec"
+ return 1
+ fi
+ echo "PASS: ipsec"
+}
+
kci_test_gretap()
{
testns="testns"
kci_test_vrf
kci_test_encap
kci_test_macsec
+ kci_test_ipsec
kci_del_dummy
}
--- /dev/null
+/*
+ * Copyright 2018 Google Inc.
+ * Author: Soheil Hassas Yeganeh (soheil@google.com)
+ *
+ * Simple example on how to use TCP_INQ and TCP_CM_INQ.
+ *
+ * License (GPLv2):
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ */
+#define _GNU_SOURCE
+
+#include <error.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#ifndef TCP_INQ
+#define TCP_INQ 36
+#endif
+
+#ifndef TCP_CM_INQ
+#define TCP_CM_INQ TCP_INQ
+#endif
+
+#define BUF_SIZE 8192
+#define CMSG_SIZE 32
+
+static int family = AF_INET6;
+static socklen_t addr_len = sizeof(struct sockaddr_in6);
+static int port = 4974;
+
+static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (family) {
+ case PF_INET:
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = AF_INET;
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ addr4->sin_port = htons(port);
+ break;
+ case PF_INET6:
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_addr = in6addr_loopback;
+ addr6->sin6_port = htons(port);
+ break;
+ default:
+ error(1, 0, "illegal family");
+ }
+}
+
+void *start_server(void *arg)
+{
+ int server_fd = (int)(unsigned long)arg;
+ struct sockaddr_in addr;
+ socklen_t addrlen = sizeof(addr);
+ char *buf;
+ int fd;
+ int r;
+
+ buf = malloc(BUF_SIZE);
+
+ for (;;) {
+ fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+ if (fd == -1) {
+ perror("accept");
+ break;
+ }
+ do {
+ r = send(fd, buf, BUF_SIZE, 0);
+ } while (r < 0 && errno == EINTR);
+ if (r < 0)
+ perror("send");
+ if (r != BUF_SIZE)
+ fprintf(stderr, "can only send %d bytes\n", r);
+ /* TCP_INQ can overestimate in-queue by one byte if we send
+ * the FIN packet. Sleep for 1 second, so that the client
+ * likely invoked recvmsg().
+ */
+ sleep(1);
+ close(fd);
+ }
+
+ free(buf);
+ close(server_fd);
+ pthread_exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct sockaddr_storage listen_addr, addr;
+ int c, one = 1, inq = -1;
+ pthread_t server_thread;
+ char cmsgbuf[CMSG_SIZE];
+ struct iovec iov[1];
+ struct cmsghdr *cm;
+ struct msghdr msg;
+ int server_fd, fd;
+ char *buf;
+
+ while ((c = getopt(argc, argv, "46p:")) != -1) {
+ switch (c) {
+ case '4':
+ family = PF_INET;
+ addr_len = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ family = PF_INET6;
+ addr_len = sizeof(struct sockaddr_in6);
+ break;
+ case 'p':
+ port = atoi(optarg);
+ break;
+ }
+ }
+
+ server_fd = socket(family, SOCK_STREAM, 0);
+ if (server_fd < 0)
+ error(1, errno, "server socket");
+ setup_loopback_addr(family, &listen_addr);
+ if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR,
+ &one, sizeof(one)) != 0)
+ error(1, errno, "setsockopt(SO_REUSEADDR)");
+ if (bind(server_fd, (const struct sockaddr *)&listen_addr,
+ addr_len) == -1)
+ error(1, errno, "bind");
+ if (listen(server_fd, 128) == -1)
+ error(1, errno, "listen");
+ if (pthread_create(&server_thread, NULL, start_server,
+ (void *)(unsigned long)server_fd) != 0)
+ error(1, errno, "pthread_create");
+
+ fd = socket(family, SOCK_STREAM, 0);
+ if (fd < 0)
+ error(1, errno, "client socket");
+ setup_loopback_addr(family, &addr);
+ if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1)
+ error(1, errno, "connect");
+ if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0)
+ error(1, errno, "setsockopt(TCP_INQ)");
+
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_iov = iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsgbuf;
+ msg.msg_controllen = sizeof(cmsgbuf);
+ msg.msg_flags = 0;
+
+ buf = malloc(BUF_SIZE);
+ iov[0].iov_base = buf;
+ iov[0].iov_len = BUF_SIZE / 2;
+
+ if (recvmsg(fd, &msg, 0) != iov[0].iov_len)
+ error(1, errno, "recvmsg");
+ if (msg.msg_flags & MSG_CTRUNC)
+ error(1, 0, "control message is truncated");
+
+ for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm))
+ if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ)
+ inq = *((int *) CMSG_DATA(cm));
+
+ if (inq != BUF_SIZE - iov[0].iov_len) {
+ fprintf(stderr, "unexpected inq: %d\n", inq);
+ exit(1);
+ }
+
+ printf("PASSED\n");
+ free(buf);
+ close(fd);
+ return 0;
+}
#include <time.h>
#include <sys/time.h>
#include <netinet/in.h>
-#include <netinet/tcp.h>
#include <arpa/inet.h>
#include <poll.h>
+#include <linux/tcp.h>
+#include <assert.h>
#ifndef MSG_ZEROCOPY
#define MSG_ZEROCOPY 0x4000000
void *child_thread(void *arg)
{
unsigned long total_mmap = 0, total = 0;
+ struct tcp_zerocopy_receive zc;
unsigned long delta_usec;
int flags = MAP_SHARED;
struct timeval t0, t1;
char *buffer = NULL;
- void *oaddr = NULL;
+ void *addr = NULL;
double throughput;
struct rusage ru;
int lu, fd;
perror("malloc");
goto error;
}
+ if (zflg) {
+ addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0);
+ if (addr == (void *)-1)
+ zflg = 0;
+ }
while (1) {
struct pollfd pfd = { .fd = fd, .events = POLLIN, };
int sub;
poll(&pfd, 1, 10000);
if (zflg) {
- void *naddr;
-
- naddr = mmap(oaddr, chunk_size, PROT_READ, flags, fd, 0);
- if (naddr == (void *)-1) {
- if (errno == EAGAIN) {
- /* That is if SO_RCVLOWAT is buggy */
- usleep(1000);
- continue;
- }
- if (errno == EINVAL) {
- flags = MAP_SHARED;
- oaddr = NULL;
- goto fallback;
- }
- if (errno != EIO)
- perror("mmap()");
+ socklen_t zc_len = sizeof(zc);
+ int res;
+
+ zc.address = (__u64)addr;
+ zc.length = chunk_size;
+ zc.recv_skip_hint = 0;
+ res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
+ &zc, &zc_len);
+ if (res == -1)
break;
+
+ if (zc.length) {
+ assert(zc.length <= chunk_size);
+ total_mmap += zc.length;
+ if (xflg)
+ hash_zone(addr, zc.length);
+ total += zc.length;
}
- total_mmap += chunk_size;
- if (xflg)
- hash_zone(naddr, chunk_size);
- total += chunk_size;
- if (!keepflag) {
- flags |= MAP_FIXED;
- oaddr = naddr;
+ if (zc.recv_skip_hint) {
+ assert(zc.recv_skip_hint <= chunk_size);
+ lu = read(fd, buffer, zc.recv_skip_hint);
+ if (lu > 0) {
+ if (xflg)
+ hash_zone(buffer, lu);
+ total += lu;
+ }
}
continue;
}
-fallback:
sub = 0;
while (sub < chunk_size) {
lu = read(fd, buffer + sub, chunk_size - sub);
error:
free(buffer);
close(fd);
+ if (zflg)
+ munmap(addr, chunk_size);
pthread_exit(0);
}
setup_sockaddr(cfg_family, host, &listenaddr);
if (mss &&
- setsockopt(fdlisten, SOL_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+ setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG,
+ &mss, sizeof(mss)) == -1) {
perror("setsockopt TCP_MAXSEG");
exit(1);
}
setup_sockaddr(cfg_family, host, &addr);
if (mss &&
- setsockopt(fd, SOL_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+ setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
perror("setsockopt TCP_MAXSEG");
exit(1);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/in.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <netinet/if_ether.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#define CONST_MTU_TEST 1500
+
+#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr))
+#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr))
+
+#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4)
+#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6)
+
+#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4)
+#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6)
+
+static bool cfg_do_ipv4;
+static bool cfg_do_ipv6;
+static bool cfg_do_connected;
+static bool cfg_do_connectionless;
+static bool cfg_do_msgmore;
+static bool cfg_do_setsockopt;
+static int cfg_specific_test_id = -1;
+
+static const char cfg_ifname[] = "lo";
+static unsigned short cfg_port = 9000;
+
+static char buf[ETH_MAX_MTU];
+
+struct testcase {
+ int tlen; /* send() buffer size, may exceed mss */
+ bool tfail; /* send() call is expected to fail */
+ int gso_len; /* mss after applying gso */
+ int r_num_mss; /* recv(): number of calls of full mss */
+ int r_len_last; /* recv(): size of last non-mss dgram, if any */
+};
+
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+struct testcase testcases_v4[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V4,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V4 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V4 * 2,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V4 * 2) + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = CONST_MAX_SEGS_V4,
+ .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 -
+ (CONST_MAX_SEGS_V4 * CONST_MSS_V4),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+#ifndef IP6_MAX_MTU
+#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr))
+#endif
+
+struct testcase testcases_v6[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V6,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V6 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V6 * 2,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V6 * 2) + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = CONST_MAX_SEGS_V6,
+ .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 -
+ (CONST_MAX_SEGS_V6 * CONST_MSS_V6),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+static unsigned int get_device_mtu(int fd, const char *ifname)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFMTU, &ifr))
+ error(1, errno, "ioctl get mtu");
+
+ return ifr.ifr_mtu;
+}
+
+static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ ifr.ifr_mtu = mtu;
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCSIFMTU, &ifr))
+ error(1, errno, "ioctl set mtu");
+}
+
+static void set_device_mtu(int fd, int mtu)
+{
+ int val;
+
+ val = get_device_mtu(fd, cfg_ifname);
+ fprintf(stderr, "device mtu (orig): %u\n", val);
+
+ __set_device_mtu(fd, cfg_ifname, mtu);
+ val = get_device_mtu(fd, cfg_ifname);
+ if (val != mtu)
+ error(1, 0, "unable to set device mtu to %u\n", val);
+
+ fprintf(stderr, "device mtu (test): %u\n", val);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+static unsigned int get_path_mtu(int fd, bool is_ipv4)
+{
+ socklen_t vallen;
+ unsigned int mtu;
+ int ret;
+
+ vallen = sizeof(mtu);
+ if (is_ipv4)
+ ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen);
+ else
+ ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen);
+
+ if (ret)
+ error(1, errno, "getsockopt mtu");
+
+
+ fprintf(stderr, "path mtu (read): %u\n", mtu);
+ return mtu;
+}
+
+/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */
+static void set_route_mtu(int mtu, bool is_ipv4)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct nlmsghdr *nh;
+ struct rtattr *rta;
+ struct rtmsg *rt;
+ char data[NLMSG_ALIGN(sizeof(*nh)) +
+ NLMSG_ALIGN(sizeof(*rt)) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) +
+ NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))];
+ int fd, ret, alen, off = 0;
+
+ alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6);
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (fd == -1)
+ error(1, errno, "socket netlink");
+
+ memset(data, 0, sizeof(data));
+
+ nh = (void *)data;
+ nh->nlmsg_type = RTM_NEWROUTE;
+ nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE;
+ off += NLMSG_ALIGN(sizeof(*nh));
+
+ rt = (void *)(data + off);
+ rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6;
+ rt->rtm_table = RT_TABLE_MAIN;
+ rt->rtm_dst_len = alen << 3;
+ rt->rtm_protocol = RTPROT_BOOT;
+ rt->rtm_scope = RT_SCOPE_UNIVERSE;
+ rt->rtm_type = RTN_UNICAST;
+ off += NLMSG_ALIGN(sizeof(*rt));
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_DST;
+ rta->rta_len = RTA_LENGTH(alen);
+ if (is_ipv4)
+ memcpy(RTA_DATA(rta), &addr4, alen);
+ else
+ memcpy(RTA_DATA(rta), &addr6, alen);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_OIF;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo");
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* MTU is a subtype in a metrics type */
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_METRICS;
+ rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int));
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* now fill MTU subtype. Note that it fits within above rta_len */
+ rta = (void *)(((char *) rta) + RTA_LENGTH(0));
+ rta->rta_type = RTAX_MTU;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = mtu;
+
+ nh->nlmsg_len = off;
+
+ ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr));
+ if (ret != off)
+ error(1, errno, "send netlink: %uB != %uB\n", ret, off);
+
+ if (close(fd))
+ error(1, errno, "close netlink");
+
+ fprintf(stderr, "route mtu (test): %u\n", mtu);
+}
+
+static bool __send_one(int fd, struct msghdr *msg, int flags)
+{
+ int ret;
+
+ ret = sendmsg(fd, msg, flags);
+ if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM))
+ return false;
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != msg->msg_iov->iov_len)
+ error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len);
+ if (msg->msg_flags)
+ error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags);
+
+ return true;
+}
+
+static bool send_one(int fd, int len, int gso_len,
+ struct sockaddr *addr, socklen_t alen)
+{
+ char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ struct cmsghdr *cm;
+
+ iov.iov_base = buf;
+ iov.iov_len = len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_name = addr;
+ msg.msg_namelen = alen;
+
+ if (gso_len && !cfg_do_setsockopt) {
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ cm = CMSG_FIRSTHDR(&msg);
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(uint16_t));
+ *((uint16_t *) CMSG_DATA(cm)) = gso_len;
+ }
+
+ /* If MSG_MORE, send 1 byte followed by remainder */
+ if (cfg_do_msgmore && len > 1) {
+ iov.iov_len = 1;
+ if (!__send_one(fd, &msg, MSG_MORE))
+ error(1, 0, "send 1B failed");
+
+ iov.iov_base++;
+ iov.iov_len = len - 1;
+ }
+
+ return __send_one(fd, &msg, 0);
+}
+
+static int recv_one(int fd, int flags)
+{
+ int ret;
+
+ ret = recv(fd, buf, sizeof(buf), flags);
+ if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT))
+ return 0;
+ if (ret == -1)
+ error(1, errno, "recv");
+
+ return ret;
+}
+
+static void run_one(struct testcase *test, int fdt, int fdr,
+ struct sockaddr *addr, socklen_t alen)
+{
+ int i, ret, val, mss;
+ bool sent;
+
+ fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+ addr->sa_family == AF_INET ? 4 : 6,
+ test->tlen, test->gso_len,
+ test->tfail ? "(fail)" : "");
+
+ val = test->gso_len;
+ if (cfg_do_setsockopt) {
+ if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
+ error(1, errno, "setsockopt udp segment");
+ }
+
+ sent = send_one(fdt, test->tlen, test->gso_len, addr, alen);
+ if (sent && test->tfail)
+ error(1, 0, "send succeeded while expecting failure");
+ if (!sent && !test->tfail)
+ error(1, 0, "send failed while expecting success");
+ if (!sent)
+ return;
+
+ mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6;
+
+ /* Recv all full MSS datagrams */
+ for (i = 0; i < test->r_num_mss; i++) {
+ ret = recv_one(fdr, 0);
+ if (ret != mss)
+ error(1, 0, "recv.%d: %d != %d", i, ret, mss);
+ }
+
+ /* Recv the non-full last datagram, if tlen was not a multiple of mss */
+ if (test->r_len_last) {
+ ret = recv_one(fdr, 0);
+ if (ret != test->r_len_last)
+ error(1, 0, "recv.%d: %d != %d (last)",
+ i, ret, test->r_len_last);
+ }
+
+ /* Verify received all data */
+ ret = recv_one(fdr, MSG_DONTWAIT);
+ if (ret)
+ error(1, 0, "recv: unexpected datagram");
+}
+
+static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
+{
+ struct testcase *tests, *test;
+
+ tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6;
+
+ for (test = tests; test->tlen; test++) {
+ /* if a specific test is given, then skip all others */
+ if (cfg_specific_test_id == -1 ||
+ cfg_specific_test_id == test - tests)
+ run_one(test, fdt, fdr, addr, alen);
+ }
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ int fdr, fdt, val;
+
+ fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdr == -1)
+ error(1, errno, "socket r");
+
+ if (bind(fdr, addr, alen))
+ error(1, errno, "bind");
+
+ /* Have tests fail quickly instead of hang */
+ if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ fdt = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdt == -1)
+ error(1, errno, "socket t");
+
+ /* Do not fragment these datagrams: only succeed if GSO works */
+ set_pmtu_discover(fdt, addr->sa_family == AF_INET);
+
+ if (cfg_do_connectionless) {
+ set_device_mtu(fdt, CONST_MTU_TEST);
+ run_all(fdt, fdr, addr, alen);
+ }
+
+ if (cfg_do_connected) {
+ set_device_mtu(fdt, CONST_MTU_TEST + 100);
+ set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET);
+
+ if (connect(fdt, addr, alen))
+ error(1, errno, "connect");
+
+ val = get_path_mtu(fdt, addr->sa_family == AF_INET);
+ if (val != CONST_MTU_TEST)
+ error(1, 0, "bad path mtu %u\n", val);
+
+ run_all(fdt, fdr, addr, 0 /* use connected addr */);
+ }
+
+ if (close(fdt))
+ error(1, errno, "close t");
+ if (close(fdr))
+ error(1, errno, "close r");
+}
+
+static void run_test_v4(void)
+{
+ struct sockaddr_in addr = {0};
+
+ addr.sin_family = AF_INET;
+ addr.sin_port = htons(cfg_port);
+ addr.sin_addr = addr4;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+ struct sockaddr_in6 addr = {0};
+
+ addr.sin6_family = AF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = addr6;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "46cCmst:")) != -1) {
+ switch (c) {
+ case '4':
+ cfg_do_ipv4 = true;
+ break;
+ case '6':
+ cfg_do_ipv6 = true;
+ break;
+ case 'c':
+ cfg_do_connected = true;
+ break;
+ case 'C':
+ cfg_do_connectionless = true;
+ break;
+ case 'm':
+ cfg_do_msgmore = true;
+ break;
+ case 's':
+ cfg_do_setsockopt = true;
+ break;
+ case 't':
+ cfg_specific_test_id = strtoul(optarg, NULL, 0);
+ break;
+ default:
+ error(1, 0, "%s: parse error", argv[0]);
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (cfg_do_ipv4)
+ run_test_v4();
+ if (cfg_do_ipv6)
+ run_test_v6();
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso regression tests
+
+echo "ipv4 cmsg"
+./in_netns.sh ./udpgso -4 -C
+
+echo "ipv4 setsockopt"
+./in_netns.sh ./udpgso -4 -C -s
+
+echo "ipv6 cmsg"
+./in_netns.sh ./udpgso -6 -C
+
+echo "ipv6 setsockopt"
+./in_netns.sh ./udpgso -6 -C -s
+
+echo "ipv4 connected"
+./in_netns.sh ./udpgso -4 -c
+
+# blocked on 2nd loopback address
+# echo "ipv6 connected"
+# ./in_netns.sh ./udpgso -6 -c
+
+echo "ipv4 msg_more"
+./in_netns.sh ./udpgso -4 -C -m
+
+echo "ipv6 msg_more"
+./in_netns.sh ./udpgso -6 -C -m
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso benchmarks
+
+wake_children() {
+ local -r jobs="$(jobs -p)"
+
+ if [[ "${jobs}" != "" ]]; then
+ kill -1 ${jobs} 2>/dev/null
+ fi
+}
+trap wake_children EXIT
+
+run_one() {
+ local -r args=$@
+
+ ./udpgso_bench_rx &
+ ./udpgso_bench_rx -t &
+
+ ./udpgso_bench_tx ${args}
+}
+
+run_in_netns() {
+ local -r args=$@
+
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp"
+ run_in_netns ${args}
+
+ echo "udp gso"
+ run_in_netns ${args} -S
+
+ echo "udp gso zerocopy"
+ run_in_netns ${args} -S -z
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp"
+ run_in_netns ${args} -t
+
+ echo "tcp zerocopy"
+ run_in_netns ${args} -t -z
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 127.0.0.1"
+ local -r ipv6_args="${core_args} -6 -D ::1"
+
+ echo "ipv4"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv4_args}"
+
+ echo "ipv6"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static int cfg_port = 8000;
+static bool cfg_tcp;
+static bool cfg_verify;
+
+static bool interrupted;
+static unsigned long packets, bytes;
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void do_poll(int fd)
+{
+ struct pollfd pfd;
+ int ret;
+
+ pfd.events = POLLIN;
+ pfd.revents = 0;
+ pfd.fd = fd;
+
+ do {
+ ret = poll(&pfd, 1, 10);
+ if (ret == -1)
+ error(1, errno, "poll");
+ if (ret == 0)
+ continue;
+ if (pfd.revents != POLLIN)
+ error(1, errno, "poll: 0x%x expected 0x%x\n",
+ pfd.revents, POLLIN);
+ } while (!ret && !interrupted);
+}
+
+static int do_socket(bool do_tcp)
+{
+ struct sockaddr_in6 addr = {0};
+ int fd, val;
+
+ fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ val = 1 << 21;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)))
+ error(1, errno, "setsockopt rcvbuf");
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
+ error(1, errno, "setsockopt reuseport");
+
+ addr.sin6_family = PF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = in6addr_any;
+ if (bind(fd, (void *) &addr, sizeof(addr)))
+ error(1, errno, "bind");
+
+ if (do_tcp) {
+ int accept_fd = fd;
+
+ if (listen(accept_fd, 1))
+ error(1, errno, "listen");
+
+ do_poll(accept_fd);
+
+ fd = accept(accept_fd, NULL, NULL);
+ if (fd == -1)
+ error(1, errno, "accept");
+ if (close(accept_fd))
+ error(1, errno, "close accept fd");
+ }
+
+ return fd;
+}
+
+/* Flush all outstanding bytes for the tcp receive queue */
+static void do_flush_tcp(int fd)
+{
+ int ret;
+
+ while (true) {
+ /* MSG_TRUNC flushes up to len bytes */
+ ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "flush");
+ if (ret == 0) {
+ /* client detached */
+ exit(0);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+
+}
+
+static char sanitized_char(char val)
+{
+ return (val >= 'a' && val <= 'z') ? val : '.';
+}
+
+static void do_verify_udp(const char *data, int len)
+{
+ char cur = data[0];
+ int i;
+
+ /* verify contents */
+ if (cur < 'a' || cur > 'z')
+ error(1, 0, "data initial byte out of range");
+
+ for (i = 1; i < len; i++) {
+ if (cur == 'z')
+ cur = 'a';
+ else
+ cur++;
+
+ if (data[i] != cur)
+ error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n",
+ i, len,
+ sanitized_char(data[i]), data[i],
+ sanitized_char(cur), cur);
+ }
+}
+
+/* Flush all outstanding datagrams. Verify first few bytes of each. */
+static void do_flush_udp(int fd)
+{
+ static char rbuf[ETH_DATA_LEN];
+ int ret, len, budget = 256;
+
+ len = cfg_verify ? sizeof(rbuf) : 0;
+ while (budget--) {
+ /* MSG_TRUNC will make return value full datagram length */
+ ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "recv");
+ if (len) {
+ if (ret == 0)
+ error(1, errno, "recv: 0 byte datagram\n");
+
+ do_verify_udp(rbuf, ret);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "ptv")) != -1) {
+ switch (c) {
+ case 'p':
+ cfg_port = htons(strtoul(optarg, NULL, 0));
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'v':
+ cfg_verify = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_tcp && cfg_verify)
+ error(1, 0, "TODO: implement verify mode for tcp");
+}
+
+static void do_recv(void)
+{
+ unsigned long tnow, treport;
+ int fd;
+
+ fd = do_socket(cfg_tcp);
+
+ treport = gettimeofday_ms() + 1000;
+ do {
+ do_poll(fd);
+
+ if (cfg_tcp)
+ do_flush_tcp(fd);
+ else
+ do_flush_udp(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ if (packets)
+ fprintf(stderr,
+ "%s rx: %6lu MB/s %8lu calls/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ bytes >> 20, packets);
+ bytes = packets = 0;
+ treport = tnow + 1000;
+ }
+
+ } while (!interrupted);
+
+ if (close(fd))
+ error(1, errno, "close");
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ signal(SIGINT, sigint_handler);
+
+ do_recv();
+
+ return 0;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#ifndef SO_ZEROCOPY
+#define SO_ZEROCOPY 60
+#endif
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY 0x4000000
+#endif
+
+#define NUM_PKT 100
+
+static bool cfg_cache_trash;
+static int cfg_cpu = -1;
+static int cfg_connected = true;
+static int cfg_family = PF_UNSPEC;
+static uint16_t cfg_mss;
+static int cfg_payload_len = (1472 * 42);
+static int cfg_port = 8000;
+static int cfg_runtime_ms = -1;
+static bool cfg_segment;
+static bool cfg_sendmmsg;
+static bool cfg_tcp;
+static bool cfg_zerocopy;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+
+static bool interrupted;
+static char buf[NUM_PKT][ETH_MAX_MTU];
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int set_cpu(int cpu)
+{
+ cpu_set_t mask;
+
+ CPU_ZERO(&mask);
+ CPU_SET(cpu, &mask);
+ if (sched_setaffinity(0, sizeof(mask), &mask))
+ error(1, 0, "setaffinity %d", cpu);
+
+ return 0;
+}
+
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+}
+
+static void flush_zerocopy(int fd)
+{
+ struct msghdr msg = {0}; /* flush */
+ int ret;
+
+ while (1) {
+ ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+ if (ret == -1 && errno == EAGAIN)
+ break;
+ if (ret == -1)
+ error(1, errno, "errqueue");
+ if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC))
+ error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags);
+ msg.msg_flags = 0;
+ }
+}
+
+static int send_tcp(int fd, char *data)
+{
+ int ret, done = 0, count = 0;
+
+ while (done < cfg_payload_len) {
+ ret = send(fd, data + done, cfg_payload_len - done,
+ cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "write");
+
+ done += ret;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp(int fd, char *data)
+{
+ int ret, total_len, len, count = 0;
+
+ total_len = cfg_payload_len;
+
+ while (total_len) {
+ len = total_len < cfg_mss ? total_len : cfg_mss;
+
+ ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0,
+ cfg_connected ? NULL : (void *)&cfg_dst_addr,
+ cfg_connected ? 0 : cfg_alen);
+ if (ret == -1)
+ error(1, errno, "write");
+ if (ret != len)
+ error(1, errno, "write: %uB != %uB\n", ret, len);
+
+ total_len -= len;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp_sendmmsg(int fd, char *data)
+{
+ const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN;
+ struct mmsghdr mmsgs[max_nr_msg];
+ struct iovec iov[max_nr_msg];
+ unsigned int off = 0, left;
+ int i = 0, ret;
+
+ memset(mmsgs, 0, sizeof(mmsgs));
+
+ left = cfg_payload_len;
+ while (left) {
+ if (i == max_nr_msg)
+ error(1, 0, "sendmmsg: exceeds max_nr_msg");
+
+ iov[i].iov_base = data + off;
+ iov[i].iov_len = cfg_mss < left ? cfg_mss : left;
+
+ mmsgs[i].msg_hdr.msg_iov = iov + i;
+ mmsgs[i].msg_hdr.msg_iovlen = 1;
+
+ off += iov[i].iov_len;
+ left -= iov[i].iov_len;
+ i++;
+ }
+
+ ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmmsg");
+
+ return ret;
+}
+
+static void send_udp_segment_cmsg(struct cmsghdr *cm)
+{
+ uint16_t *valp;
+
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+ valp = (void *)CMSG_DATA(cm);
+ *valp = cfg_mss;
+}
+
+static int send_udp_segment(int fd, char *data)
+{
+ char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ int ret;
+
+ iov.iov_base = data;
+ iov.iov_len = cfg_payload_len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+ send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg));
+
+ msg.msg_name = (void *)&cfg_dst_addr;
+ msg.msg_namelen = cfg_alen;
+
+ ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != iov.iov_len)
+ error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len);
+
+ return 1;
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+ filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int max_len, hdrlen;
+ int c;
+
+ while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+ switch (c) {
+ case '4':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ break;
+ case 'c':
+ cfg_cache_trash = true;
+ break;
+ case 'C':
+ cfg_cpu = strtol(optarg, NULL, 0);
+ break;
+ case 'D':
+ setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+ break;
+ case 'l':
+ cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
+ break;
+ case 'm':
+ cfg_sendmmsg = true;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 's':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'S':
+ cfg_segment = true;
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'u':
+ cfg_connected = false;
+ break;
+ case 'z':
+ cfg_zerocopy = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_family == PF_UNSPEC)
+ error(1, 0, "must pass one of -4 or -6");
+ if (cfg_tcp && !cfg_connected)
+ error(1, 0, "connectionless tcp makes no sense");
+ if (cfg_segment && cfg_sendmmsg)
+ error(1, 0, "cannot combine segment offload and sendmmsg");
+
+ if (cfg_family == PF_INET)
+ hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr);
+ else
+ hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr);
+
+ cfg_mss = ETH_DATA_LEN - hdrlen;
+ max_len = ETH_MAX_MTU - hdrlen;
+
+ if (cfg_payload_len > max_len)
+ error(1, 0, "payload length %u exceeds max %u",
+ cfg_payload_len, max_len);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+int main(int argc, char **argv)
+{
+ unsigned long num_msgs, num_sends;
+ unsigned long tnow, treport, tstop;
+ int fd, i, val;
+
+ parse_opts(argc, argv);
+
+ if (cfg_cpu > 0)
+ set_cpu(cfg_cpu);
+
+ for (i = 0; i < sizeof(buf[0]); i++)
+ buf[0][i] = 'a' + (i % 26);
+ for (i = 1; i < NUM_PKT; i++)
+ memcpy(buf[i], buf[0], sizeof(buf[0]));
+
+ signal(SIGINT, sigint_handler);
+
+ fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ if (cfg_zerocopy) {
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val)))
+ error(1, errno, "setsockopt zerocopy");
+ }
+
+ if (cfg_connected &&
+ connect(fd, (void *)&cfg_dst_addr, cfg_alen))
+ error(1, errno, "connect");
+
+ if (cfg_segment)
+ set_pmtu_discover(fd, cfg_family == PF_INET);
+
+ num_msgs = num_sends = 0;
+ tnow = gettimeofday_ms();
+ tstop = tnow + cfg_runtime_ms;
+ treport = tnow + 1000;
+
+ i = 0;
+ do {
+ if (cfg_tcp)
+ num_sends += send_tcp(fd, buf[i]);
+ else if (cfg_segment)
+ num_sends += send_udp_segment(fd, buf[i]);
+ else if (cfg_sendmmsg)
+ num_sends += send_udp_sendmmsg(fd, buf[i]);
+ else
+ num_sends += send_udp(fd, buf[i]);
+ num_msgs++;
+
+ if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
+ flush_zerocopy(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ fprintf(stderr,
+ "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ (num_msgs * cfg_payload_len) >> 20,
+ num_sends, num_msgs);
+ num_msgs = num_sends = 0;
+ treport = tnow + 1000;
+ }
+
+ /* cold cache when writing buffer */
+ if (cfg_cache_trash)
+ i = ++i < NUM_PKT ? i : 0;
+
+ } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
+
+ if (close(fd))
+ error(1, errno, "close");
+
+ return 0;
+}
"cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
"expExitCode": "0",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
"matchCount": "1",
"teardown": [
"$TC action flush action bpf",
"cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
"expExitCode": "255",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
"matchCount": "0",
"teardown": [
- "$TC action flush action bpf",
+ [
+ "$TC action flush action bpf",
+ 0,
+ 1,
+ 255
+ ],
"rm -f _c.o"
]
},
255
]
],
- "cmdUnderTest": "for i in `seq 1 32`; do cmd=\"action csum tcp continue index $i \"; args=\"$args$cmd\"; done && $TC actions add $args",
- "expExitCode": "255",
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
"verifyCmd": "$TC actions ls action csum",
"matchPattern": "^[ \t]+index [0-9]* ref",
"matchCount": "32",
"teardown": [
"$TC actions flush action csum"
]
+ },
+ {
+ "id": "b4e9",
+ "name": "Delete batch of 32 csum actions",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action csum",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "0015",
+ "name": "Add batch of 32 csum tcp actions with large cookies",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions ls action csum",
+ "matchPattern": "^[ \t]+index [0-9]* ref",
+ "matchCount": "32",
+ "teardown": [
+ "$TC actions flush action csum"
+ ]
+ },
+ {
+ "id": "989e",
+ "name": "Delete batch of 32 csum actions with large cookies",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action csum",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
}
]
"matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*allow mark.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*use mark 789.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 656768.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action jump 1.*type 0xED3E.*use mark 65.*index 2",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 4294967295.*index 90",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow prio.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 7.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use prio 3.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow prio.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 998877.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action jump 10.*type 0xED3E.*use prio 998877.*index 9",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
"matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 4294967295.*index 99",
"matchCount": "1",
"teardown": [
- "$TC actions flush action skbedit"
+ "$TC actions flush action ife"
]
},
{
},
{
"id": "8b69",
- "name": "Add mirred mirror action with maximum index",
+ "name": "Add mirred mirror action with index at 32-bit maximum",
"category": [
"actions",
"mirred"
"$TC actions flush action mirred"
]
},
+ {
+ "id": "3f66",
+ "name": "Add mirred mirror action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "mirred"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action mirred",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action mirred ingress mirror dev lo pipe index 429496729555",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action mirred index 429496729555",
+ "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) pipe.*index 429496729555",
+ "matchCount": "0",
+ "teardown": []
+ },
{
"id": "a70e",
"name": "Delete mirred mirror action",
],
"cmdUnderTest": "$TC actions add action police rate 10mbit burst 10k index 4294967295",
"expExitCode": "0",
- "verifyCmd": "$TC actions get action mirred index 4294967295",
+ "verifyCmd": "$TC actions get action police index 4294967295",
"matchPattern": "action order [0-9]*: police 0xffffffff rate 10Mbit burst 10Kb mtu 2Kb",
"matchCount": "1",
"teardown": [
- "$TC actions flush action mirred"
+ "$TC actions flush action police"
]
},
{
[
{
"id": "6f5a",
- "name": "Add vlan pop action",
+ "name": "Add vlan pop action with pipe opcode",
"category": [
"actions",
"vlan"
255
]
],
- "cmdUnderTest": "$TC actions add action vlan pop index 8",
+ "cmdUnderTest": "$TC actions add action vlan pop pipe index 8",
"expExitCode": "0",
"verifyCmd": "$TC actions list action vlan",
- "matchPattern": "action order [0-9]+: vlan.*pop.*index 8 ref",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*pipe.*index 8 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action vlan"
]
},
{
- "id": "ee6f",
- "name": "Add vlan pop action with large index",
+ "id": "df35",
+ "name": "Add vlan pop action with pass opcode",
"category": [
"actions",
"vlan"
255
]
],
- "cmdUnderTest": "$TC actions add action vlan pop index 4294967295",
+ "cmdUnderTest": "$TC actions add action vlan pop pass index 8",
"expExitCode": "0",
- "verifyCmd": "$TC actions list action vlan",
- "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*pass.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "b0d4",
+ "name": "Add vlan pop action with drop opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop drop index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*drop.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "95ee",
+ "name": "Add vlan pop action with reclassify opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop reclassify index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*reclassify.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "0283",
+ "name": "Add vlan pop action with continue opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop continue index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*continue.*index 8 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action vlan"
"$TC actions flush action vlan"
]
},
+ {
+ "id": "a178",
+ "name": "Add vlan pop action with invalid opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop foo index 8",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*foo.*index 8 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "ee6f",
+ "name": "Add vlan pop action with index at 32-bit maximum",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop index 4294967295",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "0dfa",
+ "name": "Add vlan pop action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop reclassify index 429496729599",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action vlan index 429496729599",
+ "matchPattern": "action order [0-9]+: vlan.*pop.reclassify.*index 429496729599",
+ "matchCount": "0",
+ "teardown": []
+ },
{
"id": "2b91",
"name": "Add vlan invalid action",
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*bad_mode",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "57fc",
- "name": "Add vlan action with invalid protocol type",
+ "name": "Add vlan push action with invalid protocol type",
"category": [
"actions",
"vlan"
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*push",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "3989",
"$TC actions flush action vlan"
]
},
+ {
+ "id": "1f4b",
+ "name": "Add vlan push action with maximum 12-bit vlan ID",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan push id 4094 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 4094.*protocol 802.1Q.*priority 0.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
{
"id": "1f7b",
"name": "Add vlan push action with invalid vlan ID",
"$TC actions flush action vlan"
]
},
+ {
+ "id": "fe40",
+ "name": "Add vlan push action with maximum 3-bit IEEE 802.1p priority",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan push id 4 priority 7 reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 4.*protocol 802.1Q.*priority 7.*reclassify.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
{
"id": "5d02",
"name": "Add vlan push action with invalid IEEE 802.1p priority",
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*push id 5.*index 1 ref",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "6812",
"$TC actions flush action vlan"
]
},
+ {
+ "id": "3deb",
+ "name": "Replace existing vlan push action with new ID",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 500 pipe index 12"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 700 pipe index 12",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 12",
+ "matchPattern": "action order [0-9]+: vlan.*push id 700 protocol 802.1Q priority 0 pipe.*index 12 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "9e76",
+ "name": "Replace existing vlan push action with new protocol",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 1 protocol 802.1Q pipe index 1"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 1 protocol 802.1ad pipe index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1ad priority 0 pipe.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "ede4",
+ "name": "Replace existing vlan push action with new priority",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 1 protocol 802.1Q priority 3 reclassify index 1"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 1 priority 4 reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1Q priority 4 reclassify.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "d413",
+ "name": "Replace existing vlan pop action with new cookie",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan pop continue index 1 cookie 22334455"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan pop continue index 1 cookie a1b1c2d1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*pop continue.*index 1 ref.*cookie a1b1c2d1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
{
"id": "83a4",
"name": "Delete vlan pop action",
},
{
"id": "1d78",
- "name": "Add vlan action with cookie",
+ "name": "Add vlan push action with cookie",
"category": [
"actions",
"vlan"
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
- protection_keys test_vdso test_vsyscall
+ protection_keys test_vdso test_vsyscall mov_ss_trap
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mov_ss_trap.c: Exercise the bizarre side effects of a watchpoint on MOV SS
+ *
+ * This does MOV SS from a watchpointed address followed by various
+ * types of kernel entries. A MOV SS that hits a watchpoint will queue
+ * up a #DB trap but will not actually deliver that trap. The trap
+ * will be delivered after the next instruction instead. The CPU's logic
+ * seems to be:
+ *
+ * - Any fault: drop the pending #DB trap.
+ * - INT $N, INT3, INTO, SYSCALL, SYSENTER: enter the kernel and then
+ * deliver #DB.
+ * - ICEBP: enter the kernel but do not deliver the watchpoint trap
+ * - breakpoint: only one #DB is delivered (phew!)
+ *
+ * There are plenty of ways for a kernel to handle this incorrectly. This
+ * test tries to exercise all the cases.
+ *
+ * This should mostly cover CVE-2018-1087 and CVE-2018-8897.
+ */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <setjmp.h>
+#include <sys/prctl.h>
+
+#define X86_EFLAGS_RF (1UL << 16)
+
+#if __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+unsigned short ss;
+extern unsigned char breakpoint_insn[];
+sigjmp_buf jmpbuf;
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void enable_watchpoint(void)
+{
+ pid_t parent = getpid();
+ int status;
+
+ pid_t child = fork();
+ if (child < 0)
+ err(1, "fork");
+
+ if (child) {
+ if (waitpid(child, &status, 0) != child)
+ err(1, "waitpid for child");
+ } else {
+ unsigned long dr0, dr1, dr7;
+
+ dr0 = (unsigned long)&ss;
+ dr1 = (unsigned long)breakpoint_insn;
+ dr7 = ((1UL << 1) | /* G0 */
+ (3UL << 16) | /* RW0 = read or write */
+ (1UL << 18) | /* LEN0 = 2 bytes */
+ (1UL << 3)); /* G1, RW1 = insn */
+
+ if (ptrace(PTRACE_ATTACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_ATTACH");
+
+ if (waitpid(parent, &status, 0) != parent)
+ err(1, "waitpid for child");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[0]), dr0) != 0)
+ err(1, "PTRACE_POKEUSER DR0");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[1]), dr1) != 0)
+ err(1, "PTRACE_POKEUSER DR1");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[7]), dr7) != 0)
+ err(1, "PTRACE_POKEUSER DR7");
+
+ printf("\tDR0 = %lx, DR1 = %lx, DR7 = %lx\n", dr0, dr1, dr7);
+
+ if (ptrace(PTRACE_DETACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_DETACH");
+
+ exit(0);
+ }
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static char const * const signames[] = {
+ [SIGSEGV] = "SIGSEGV",
+ [SIGBUS] = "SIBGUS",
+ [SIGTRAP] = "SIGTRAP",
+ [SIGILL] = "SIGILL",
+};
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot SIGTRAP with RIP=%lx, EFLAGS.RF=%d\n",
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP],
+ !!(ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_RF));
+}
+
+static void handle_and_return(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+}
+
+static void handle_and_longjmp(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+
+ siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+ unsigned long nr;
+
+ asm volatile ("mov %%ss, %[ss]" : [ss] "=m" (ss));
+ printf("\tSS = 0x%hx, &SS = 0x%p\n", ss, &ss);
+
+ if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, 0, 0, 0) == 0)
+ printf("\tPR_SET_PTRACER_ANY succeeded\n");
+
+ printf("\tSet up a watchpoint\n");
+ sethandler(SIGTRAP, sigtrap, 0);
+ enable_watchpoint();
+
+ printf("[RUN]\tRead from watched memory (should get SIGTRAP)\n");
+ asm volatile ("mov %[ss], %[tmp]" : [tmp] "=r" (nr) : [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT3\n");
+ asm volatile ("mov %[ss], %%ss; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0xcd, 0x3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CS CS INT3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0x2e, 0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CSx14 INT3\n");
+ asm volatile ("mov %[ss], %%ss; .fill 14,1,0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 4\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $4" :: [ss] "m" (ss));
+
+#ifdef __i386__
+ printf("[RUN]\tMOV SS; INTO\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ nr = -1;
+ asm volatile ("add $1, %[tmp]; mov %[ss], %%ss; into"
+ : [tmp] "+r" (nr) : [ss] "m" (ss));
+#endif
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; ICEBP\n");
+
+ /* Some emulators (e.g. QEMU TCG) don't emulate ICEBP. */
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+
+ asm volatile ("mov %[ss], %%ss; .byte 0xf1" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; CLI\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; cli" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; #PF\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; mov (-1), %[tmp]"
+ : [tmp] "=r" (nr) : [ss] "m" (ss));
+ }
+
+ /*
+ * INT $1: if #DB has DPL=3 and there isn't special handling,
+ * then the kernel will die.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT 1\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $1" :: [ss] "m" (ss));
+ }
+
+#ifdef __x86_64__
+ /*
+ * In principle, we should test 32-bit SYSCALL as well, but
+ * the calling convention is so unpredictable that it's
+ * not obviously worth the effort.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSCALL\n");
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+ nr = SYS_getpid;
+ /*
+ * Toggle the high bit of RSP to make it noncanonical to
+ * strengthen this test on non-SMAP systems.
+ */
+ asm volatile ("btc $63, %%rsp\n\t"
+ "mov %[ss], %%ss; syscall\n\t"
+ "btc $63, %%rsp"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+ }
+#endif
+
+ printf("[RUN]\tMOV SS; breakpointed NOP\n");
+ asm volatile ("mov %[ss], %%ss; breakpoint_insn: nop" :: [ss] "m" (ss));
+
+ /*
+ * Invoking SYSENTER directly breaks all the rules. Just handle
+ * the SIGSEGV.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSENTER\n");
+ stack_t stack = {
+ .ss_sp = altstack_data,
+ .ss_size = SIGSTKSZ,
+ };
+ if (sigaltstack(&stack, NULL) != 0)
+ err(1, "sigaltstack");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
+ nr = SYS_getpid;
+ asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr)
+ : [ss] "m" (ss) : "flags", "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+
+ /* We're unreachable here. SYSENTER forgets RIP. */
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT $0x80\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ nr = 20; /* compat getpid */
+ asm volatile ("mov %[ss], %%ss; int $0x80"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "flags"
+#ifdef __x86_64__
+ , "r8", "r9", "r10", "r11"
+#endif
+ );
+ }
+
+ printf("[OK]\tI aten't dead\n");
+ return 0;
+}
uint64_t shadow_plb[NR_MPX_BOUNDS_REGISTERS][2]; /* shadow MPX bound registers */
unsigned long shadow_map[NR_MPX_BOUNDS_REGISTERS];
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
/*
* The kernel is supposed to provide some information about the bounds
* exception in the siginfo. It should match what we have in the bounds
br_count++;
dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count);
-#define SEGV_BNDERR 3 /* failed address bound checks */
-
dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n",
status, ip, br_reason);
dprintf2("si_signo: %d\n", si->si_signo);
{
va_list ap;
- va_start(ap, format);
if (!dprint_in_signal) {
+ va_start(ap, format);
vprintf(format, ap);
+ va_end(ap);
} else {
int ret;
- int len = vsnprintf(dprint_in_signal_buffer,
- DPRINT_IN_SIGNAL_BUF_SIZE,
- format, ap);
/*
- * len is amount that would have been printed,
- * but actual write is truncated at BUF_SIZE.
+ * No printf() functions are signal-safe.
+ * They deadlock easily. Write the format
+ * string to get some output, even if
+ * incomplete.
*/
- if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
- len = DPRINT_IN_SIGNAL_BUF_SIZE;
- ret = write(1, dprint_in_signal_buffer, len);
+ ret = write(1, format, strlen(format));
if (ret < 0)
- abort();
+ exit(1);
}
- va_end(ap);
}
#define dprintf_level(level, args...) do { \
if (level <= DEBUG_LEVEL) \
sigsafe_printf(args); \
- fflush(NULL); \
} while (0)
#define dprintf0(args...) dprintf_level(0, args)
#define dprintf1(args...) dprintf_level(1, args)
test_nr, iteration_nr); \
dprintf0("errno at assert: %d", errno); \
abort_hooks(); \
- assert(condition); \
+ exit(__LINE__); \
} \
} while (0)
-#define raw_assert(cond) assert(cond)
void cat_into_file(char *str, char *file)
{
* these need to be raw because they are called under
* pkey_assert()
*/
- raw_assert(fd >= 0);
+ if (fd < 0) {
+ fprintf(stderr, "error opening '%s'\n", str);
+ perror("error: ");
+ exit(__LINE__);
+ }
+
ret = write(fd, str, strlen(str));
if (ret != strlen(str)) {
perror("write to file failed");
fprintf(stderr, "filename: '%s' str: '%s'\n", file, str);
- raw_assert(0);
+ exit(__LINE__);
}
close(fd);
}
#ifdef __i386__
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 380
+# define SYS_mprotect_key 380
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 381
-# define SYS_pkey_free 382
+# define SYS_pkey_alloc 381
+# define SYS_pkey_free 382
#endif
-#define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x14
+
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x14
#else
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 329
+# define SYS_mprotect_key 329
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 330
-# define SYS_pkey_free 331
+# define SYS_pkey_alloc 330
+# define SYS_pkey_free 331
#endif
-#define REG_IP_IDX REG_RIP
-#define si_pkey_offset 0x20
+
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
#endif
}
}
-#define SEGV_BNDERR 3 /* failed address bound checks */
-#define SEGV_PKUERR 4
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
+#ifndef SEGV_PKUERR
+# define SEGV_PKUERR 4
+#endif
static char *si_code_str(int si_code)
{
dump_mem(pkru_ptr - 128, 256);
pkey_assert(*pkru_ptr);
- si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
- dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
- dump_mem(si_pkey_ptr - 8, 24);
- siginfo_pkey = *si_pkey_ptr;
- pkey_assert(siginfo_pkey < NR_PKEYS);
- last_si_pkey = siginfo_pkey;
-
if ((si->si_code == SEGV_MAPERR) ||
(si->si_code == SEGV_ACCERR) ||
(si->si_code == SEGV_BNDERR)) {
exit(4);
}
+ si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+ dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
+ dump_mem((u8 *)si_pkey_ptr - 8, 24);
+ siginfo_pkey = *si_pkey_ptr;
+ pkey_assert(siginfo_pkey < NR_PKEYS);
+ last_si_pkey = siginfo_pkey;
+
dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
/* need __rdpkru() version so we do not do shadow_pkru checking */
dprintf1("signal pkru from pkru: %08x\n", __rdpkru());
dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
pkru_faults++;
dprintf1("<<<<==================================================\n");
- return;
- if (trapno == 14) {
- fprintf(stderr,
- "ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
- trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(1);
- } else {
- fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(2);
- }
dprint_in_signal = 0;
}
return forkret;
}
-#define PKEY_DISABLE_ACCESS 0x1
-#define PKEY_DISABLE_WRITE 0x2
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS 0x1
+#endif
+
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE 0x2
+#endif
-u32 pkey_get(int pkey, unsigned long flags)
+static u32 hw_pkey_get(int pkey, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 pkru = __rdpkru();
return masked_pkru;
}
-int pkey_set(int pkey, unsigned long rights, unsigned long flags)
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 old_pkru = __rdpkru();
pkey, flags);
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- pkey_rights = pkey_get(pkey, syscall_flags);
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, syscall_flags);
+ ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
assert(!ret);
/*pkru and flags have the same format */
shadow_pkru |= flags << (pkey * 2);
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
{
unsigned long syscall_flags = 0;
int ret;
- int pkey_rights = pkey_get(pkey, syscall_flags);
+ int pkey_rights = hw_pkey_get(pkey, syscall_flags);
u32 orig_pkru = rdpkru();
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, 0);
+ ret = hw_pkey_set(pkey, pkey_rights, 0);
/* pkru and flags have the same format */
shadow_pkru &= ~(flags << (pkey * 2));
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
struct pkey_malloc_record {
void *ptr;
long size;
+ int prot;
};
struct pkey_malloc_record *pkey_malloc_records;
+struct pkey_malloc_record *pkey_last_malloc_record;
long nr_pkey_malloc_records;
-void record_pkey_malloc(void *ptr, long size)
+void record_pkey_malloc(void *ptr, long size, int prot)
{
long i;
struct pkey_malloc_record *rec = NULL;
(int)(rec - pkey_malloc_records), rec, ptr, size);
rec->ptr = ptr;
rec->size = size;
+ rec->prot = prot;
+ pkey_last_malloc_record = rec;
nr_pkey_malloc_records++;
}
pkey_assert(ptr != (void *)-1);
ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
pkey_assert(!ret);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
rdpkru();
dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
size = ALIGN_UP(size, HPAGE_SIZE * 2);
ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
pkey_assert(ptr != (void *)-1);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
mprotect_pkey(ptr, size, prot, pkey);
dprintf1("unaligned ptr: %p\n", ptr);
pkey_assert(ptr != (void *)-1);
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr);
return ptr;
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
close(fd);
}
int last_pkru_faults;
+#define UNKNOWN_PKEY -2
void expected_pk_fault(int pkey)
{
dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
__func__, last_pkru_faults, pkru_faults);
dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
pkey_assert(last_pkru_faults + 1 == pkru_faults);
- pkey_assert(last_si_pkey == pkey);
+
+ /*
+ * For exec-only memory, we do not know the pkey in
+ * advance, so skip this check.
+ */
+ if (pkey != UNKNOWN_PKEY)
+ pkey_assert(last_si_pkey == pkey);
+
/*
* The signal handler shold have cleared out PKRU to let the
* test program continue. We now have to restore it.
last_si_pkey = -1;
}
-void do_not_expect_pk_fault(void)
-{
- pkey_assert(last_pkru_faults == pkru_faults);
-}
+#define do_not_expect_pk_fault(msg) do { \
+ if (last_pkru_faults != pkru_faults) \
+ dprintf0("unexpected PK fault: %s\n", msg); \
+ pkey_assert(last_pkru_faults == pkru_faults); \
+} while (0)
int test_fds[10] = { -1 };
int nr_test_fds;
pkey_assert(i < NR_PKEYS*2);
/*
- * There are 16 pkeys supported in hardware. One is taken
- * up for the default (0) and another can be taken up by
- * an execute-only mapping. Ensure that we can allocate
- * at least 14 (16-2).
+ * There are 16 pkeys supported in hardware. Three are
+ * allocated by the time we get here:
+ * 1. The default key (0)
+ * 2. One possibly consumed by an execute-only mapping.
+ * 3. One allocated by the test code and passed in via
+ * 'pkey' to this function.
+ * Ensure that we can allocate at least another 13 (16-3).
*/
- pkey_assert(i >= NR_PKEYS-2);
+ pkey_assert(i >= NR_PKEYS-3);
for (i = 0; i < nr_allocated_pkeys; i++) {
err = sys_pkey_free(allocated_pkeys[i]);
}
}
+/*
+ * pkey 0 is special. It is allocated by default, so you do not
+ * have to call pkey_alloc() to use it first. Make sure that it
+ * is usable.
+ */
+void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
+{
+ long size;
+ int prot;
+
+ assert(pkey_last_malloc_record);
+ size = pkey_last_malloc_record->size;
+ /*
+ * This is a bit of a hack. But mprotect() requires
+ * huge-page-aligned sizes when operating on hugetlbfs.
+ * So, make sure that we use something that's a multiple
+ * of a huge page when we can.
+ */
+ if (size >= HPAGE_SIZE)
+ size = HPAGE_SIZE;
+ prot = pkey_last_malloc_record->prot;
+
+ /* Use pkey 0 */
+ mprotect_pkey(ptr, size, prot, 0);
+
+ /* Make sure that we can set it back to the original pkey. */
+ mprotect_pkey(ptr, size, prot, pkey);
+}
+
void test_ptrace_of_child(int *ptr, u16 pkey)
{
__attribute__((__unused__)) int peek_result;
pkey_assert(ret != -1);
/* Now access from the current task, and expect NO exception: */
peek_result = read_ptr(plain_ptr);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("read plain pointer after ptrace");
ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
pkey_assert(ret != -1);
free(plain_ptr_unaligned);
}
-void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+void *get_pointer_to_instructions(void)
{
void *p1;
- int scratch;
- int ptr_contents;
- int ret;
p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE);
dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write);
/* Point 'p1' at the *second* page of the function: */
p1 += PAGE_SIZE;
+ /*
+ * Try to ensure we fault this in on next touch to ensure
+ * we get an instruction fault as opposed to a data one
+ */
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+
+ return p1;
+}
+
+void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ p1 = get_pointer_to_instructions();
lots_o_noops_around_write(&scratch);
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
*/
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
lots_o_noops_around_write(&scratch);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
expected_pk_fault(pkey);
}
+void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ dprintf1("%s() start\n", __func__);
+
+ p1 = get_pointer_to_instructions();
+ lots_o_noops_around_write(&scratch);
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+
+ /* Use a *normal* mprotect(), not mprotect_pkey(): */
+ ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
+ pkey_assert(!ret);
+
+ dprintf2("pkru: %x\n", rdpkru());
+
+ /* Make sure this is an *instruction* fault */
+ madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+ lots_o_noops_around_write(&scratch);
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+ expected_pk_fault(UNKNOWN_PKEY);
+
+ /*
+ * Put the memory back to non-PROT_EXEC. Should clear the
+ * exec-only pkey off the VMA and allow it to be readable
+ * again. Go to PROT_NONE first to check for a kernel bug
+ * that did not clear the pkey when doing PROT_NONE.
+ */
+ ret = mprotect(p1, PAGE_SIZE, PROT_NONE);
+ pkey_assert(!ret);
+
+ ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC);
+ pkey_assert(!ret);
+ ptr_contents = read_ptr(p1);
+ do_not_expect_pk_fault("plain read on recently PROT_EXEC area");
+}
+
void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
{
int size = PAGE_SIZE;
test_kernel_gup_of_access_disabled_region,
test_kernel_gup_write_to_write_disabled_region,
test_executing_on_unreadable_memory,
+ test_implicit_mprotect_exec_only_memory,
+ test_mprotect_with_pkey_0,
test_ptrace_of_child,
test_pkey_syscalls_on_non_allocated_pkey,
test_pkey_syscalls_bad_args,
" shl $32, %r8\n"
" orq $0x7f7f7f7f, %r8\n"
" movq %r8, %r9\n"
- " movq %r8, %r10\n"
- " movq %r8, %r11\n"
- " movq %r8, %r12\n"
- " movq %r8, %r13\n"
- " movq %r8, %r14\n"
- " movq %r8, %r15\n"
+ " incq %r9\n"
+ " movq %r9, %r10\n"
+ " incq %r10\n"
+ " movq %r10, %r11\n"
+ " incq %r11\n"
+ " movq %r11, %r12\n"
+ " incq %r12\n"
+ " movq %r12, %r13\n"
+ " incq %r13\n"
+ " movq %r13, %r14\n"
+ " incq %r14\n"
+ " movq %r14, %r15\n"
+ " incq %r15\n"
" ret\n"
" .code32\n"
" .popsection\n"
int err = 0;
int num = 8;
uint64_t *r64 = ®s64.r8;
+ uint64_t expected = 0x7f7f7f7f7f7f7f7fULL;
if (!kernel_is_64bit)
return 0;
do {
- if (*r64 == 0x7f7f7f7f7f7f7f7fULL)
+ if (*r64 == expected++)
continue; /* register did not change */
if (syscall_addr != (long)&int80) {
/*
continue;
}
} else {
- /* INT80 syscall entrypoint can be used by
+ /*
+ * INT80 syscall entrypoint can be used by
* 64-bit programs too, unlike SYSCALL/SYSENTER.
* Therefore it must preserve R12+
* (they are callee-saved registers in 64-bit C ABI).
*
- * This was probably historically not intended,
- * but R8..11 are clobbered (cleared to 0).
- * IOW: they are the only registers which aren't
- * preserved across INT80 syscall.
+ * Starting in Linux 4.17 (and any kernel that
+ * backports the change), R8..11 are preserved.
+ * Historically (and probably unintentionally), they
+ * were clobbered or zeroed.
*/
- if (*r64 == 0 && num <= 11)
- continue;
}
printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64);
err++;
static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
static u32 kvm_next_vmid;
static unsigned int kvm_vmid_bits __read_mostly;
-static DEFINE_SPINLOCK(kvm_vmid_lock);
+static DEFINE_RWLOCK(kvm_vmid_lock);
static bool vgic_present;
{
phys_addr_t pgd_phys;
u64 vmid;
+ bool new_gen;
- if (!need_new_vmid_gen(kvm))
+ read_lock(&kvm_vmid_lock);
+ new_gen = need_new_vmid_gen(kvm);
+ read_unlock(&kvm_vmid_lock);
+
+ if (!new_gen)
return;
- spin_lock(&kvm_vmid_lock);
+ write_lock(&kvm_vmid_lock);
/*
* We need to re-check the vmid_gen here to ensure that if another vcpu
* use the same vmid.
*/
if (!need_new_vmid_gen(kvm)) {
- spin_unlock(&kvm_vmid_lock);
+ write_unlock(&kvm_vmid_lock);
return;
}
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
- spin_unlock(&kvm_vmid_lock);
+ write_unlock(&kvm_vmid_lock);
}
static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
#include <linux/arm-smccc.h>
#include <linux/preempt.h>
#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
#include <linux/wait.h>
#include <asm/cputype.h>
smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
+{
+ return 1; /* PSCI version */
+}
+
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices))
+ return -EFAULT;
+
+ return 0;
+}
+
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+
+ val = kvm_psci_version(vcpu, vcpu->kvm);
+ if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ bool wants_02;
+ u64 val;
+
+ if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
+ return -EFAULT;
+
+ wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
+
+ switch (val) {
+ case KVM_ARM_PSCI_0_1:
+ if (wants_02)
+ return -EINVAL;
+ vcpu->kvm->arch.psci_version = val;
+ return 0;
+ case KVM_ARM_PSCI_0_2:
+ case KVM_ARM_PSCI_1_0:
+ if (!wants_02)
+ return -EINVAL;
+ vcpu->kvm->arch.psci_version = val;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
struct vgic_irq *irq;
struct kvm_vcpu *vcpu = NULL;
+ unsigned long flags;
if (iter->dist_id == 0) {
print_dist_state(s, &kvm->arch.vgic);
irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS];
}
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
print_irq_state(s, irq, vcpu);
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
return 0;
}
* We cannot rely on the vgic maintenance interrupt to be
* delivered synchronously. This means we can only use it to
* exit the VM, and we perform the handling of EOIed
- * interrupts on the exit path (see vgic_process_maintenance).
+ * interrupts on the exit path (see vgic_fold_lr_state).
*/
return IRQ_HANDLED;
}
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+ unsigned long flags;
int ret;
/* In this case there is no put, since we keep the reference. */
irq->intid = intid;
irq->target_vcpu = vcpu;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
/*
* There could be a race with another vgic_add_lpi(), so we need to
dist->lpi_list_count++;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
/*
* We "cache" the configuration table entries in our struct vgic_irq's.
int ret;
unsigned long flags;
- ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
- &prop, 1);
+ ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+ &prop, 1);
if (ret)
return ret;
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
+ unsigned long flags;
u32 *intids;
int irq_count, i = 0;
if (!intids)
return -ENOMEM;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (i == irq_count)
break;
continue;
intids[i++] = irq->intid;
}
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
*intid_ptr = intids;
return i;
static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
{
int ret = 0;
+ unsigned long flags;
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
irq->target_vcpu = vcpu;
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
if (irq->hw) {
struct its_vlpi_map map;
* this very same byte in the last iteration. Reuse that.
*/
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
- &pendmask, 1);
+ ret = kvm_read_guest_lock(vcpu->kvm,
+ pendbase + byte_offset,
+ &pendmask, 1);
if (ret) {
kfree(intids);
return ret;
return false;
/* Each 1st level entry is represented by a 64-bit value. */
- if (kvm_read_guest(its->dev->kvm,
+ if (kvm_read_guest_lock(its->dev->kvm,
BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
&indirect_ptr, sizeof(indirect_ptr)))
return false;
cbaser = CBASER_ADDRESS(its->cbaser);
while (its->cwriter != its->creadr) {
- int ret = kvm_read_guest(kvm, cbaser + its->creadr,
- cmd_buf, ITS_CMD_SIZE);
+ int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
+ cmd_buf, ITS_CMD_SIZE);
/*
* If kvm_read_guest() fails, this could be due to the guest
* programming a bogus value in CBASER or something else going
int next_offset;
size_t byte_offset;
- ret = kvm_read_guest(kvm, gpa, entry, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, entry, esz);
if (ret)
return ret;
int ret;
BUG_ON(esz > sizeof(val));
- ret = kvm_read_guest(kvm, gpa, &val, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, &val, esz);
if (ret)
return ret;
val = le64_to_cpu(val);
#include <linux/irqchip/arm-gic.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <linux/nospec.h>
+
#include <kvm/iodev.h>
#include <kvm/arm_vgic.h>
if (n > vgic_v3_max_apr_idx(vcpu))
return 0;
+
+ n = array_index_nospec(n, 4);
+
/* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */
return vgicv3->vgic_ap1r[n];
}
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
- if (irq->hw)
+ if (irq->hw) {
vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
- else
+ } else {
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+
irq->active = active;
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+ active && vgic_irq_is_sgi(irq->intid))
+ irq->active_source = requester_vcpu->vcpu_id;
+ }
if (irq->active)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_v2_write_lr(i, 0);
}
-void vgic_v2_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
- cpuif->vgic_hcr |= GICH_HCR_NPIE;
-}
-
void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~GICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u32 val = cpuif->vgic_lr[lr];
- u32 intid = val & GICH_LR_VIRTUALID;
+ u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
+ /* Extract the source vCPU id from the LR */
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ cpuid &= 7;
+
/* Notify fds when the guest EOI'ed a level-triggered SPI */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
kvm_notify_acked_irq(vcpu->kvm, 0,
/* Always preserve the active bit */
irq->active = !!(val & GICH_LR_ACTIVE_BIT);
+ if (irq->active && vgic_irq_is_sgi(intid))
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & GICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid)) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_sgi(intid))
irq->source |= (1 << cpuid);
- }
}
/*
u32 val = irq->intid;
bool allow_pending = true;
- if (irq->active)
+ if (irq->active) {
val |= GICH_LR_ACTIVE_BIT;
+ if (vgic_irq_is_sgi(irq->intid))
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= GICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= GICH_LR_HW;
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= GICH_LR_EOI;
+ }
}
}
static bool common_trap;
static bool gicv4_enable;
-void vgic_v3_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
- cpuif->vgic_hcr |= ICH_HCR_NPIE;
-}
-
void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~ICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u64 val = cpuif->vgic_lr[lr];
- u32 intid;
+ u32 intid, cpuid;
struct vgic_irq *irq;
+ bool is_v2_sgi = false;
- if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3) {
intid = val & ICH_LR_VIRTUAL_ID_MASK;
- else
+ } else {
intid = val & GICH_LR_VIRTUALID;
+ is_v2_sgi = vgic_irq_is_sgi(intid);
+ }
/* Notify fds when the guest EOI'ed a level-triggered IRQ */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
/* Always preserve the active bit */
irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+ if (irq->active && is_v2_sgi)
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & ICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid) &&
- model == KVM_DEV_TYPE_ARM_VGIC_V2) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (is_v2_sgi)
irq->source |= (1 << cpuid);
- }
}
/*
{
u32 model = vcpu->kvm->arch.vgic.vgic_model;
u64 val = irq->intid;
- bool allow_pending = true;
+ bool allow_pending = true, is_v2_sgi;
- if (irq->active)
+ is_v2_sgi = (vgic_irq_is_sgi(irq->intid) &&
+ model == KVM_DEV_TYPE_ARM_VGIC_V2);
+
+ if (irq->active) {
val |= ICH_LR_ACTIVE_BIT;
+ if (is_v2_sgi)
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= ICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= ICH_LR_HW;
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= ICH_LR_EOI;
+ }
}
}
bit_nr = irq->intid % BITS_PER_BYTE;
ptr = pendbase + byte_offset;
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
ptr = pendbase + byte_offset;
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
last_byte_offset = byte_offset;
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/list_sort.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
+#include <linux/nospec.h>
+
#include <asm/kvm_hyp.h>
#include "vgic.h"
* kvm->lock (mutex)
* its->cmd_lock (mutex)
* its->its_lock (mutex)
- * vgic_cpu->ap_list_lock
- * kvm->lpi_list_lock
- * vgic_irq->irq_lock
+ * vgic_cpu->ap_list_lock must be taken with IRQs disabled
+ * kvm->lpi_list_lock must be taken with IRQs disabled
+ * vgic_irq->irq_lock must be taken with IRQs disabled
+ *
+ * As the ap_list_lock might be taken from the timer interrupt handler,
+ * we have to disable IRQs before taking this lock and everything lower
+ * than it.
*
* If you need to take multiple locks, always take the upper lock first,
* then the lower ones, e.g. first take the its_lock, then the irq_lock.
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = NULL;
+ unsigned long flags;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (irq->intid != intid)
irq = NULL;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return irq;
}
u32 intid)
{
/* SGIs and PPIs */
- if (intid <= VGIC_MAX_PRIVATE)
+ if (intid <= VGIC_MAX_PRIVATE) {
+ intid = array_index_nospec(intid, VGIC_MAX_PRIVATE);
return &vcpu->arch.vgic_cpu.private_irqs[intid];
+ }
/* SPIs */
- if (intid <= VGIC_MAX_SPI)
+ if (intid <= VGIC_MAX_SPI) {
+ intid = array_index_nospec(intid, VGIC_MAX_SPI);
return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
+ }
/* LPIs */
if (intid >= VGIC_MIN_LPI)
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
+ unsigned long flags;
if (irq->intid < VGIC_MIN_LPI)
return;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
if (!kref_put(&irq->refcount, vgic_irq_release)) {
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return;
};
list_del(&irq->lpi_list);
dist->lpi_list_count--;
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
kfree(irq);
}
list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;
+ bool target_vcpu_needs_kick = false;
spin_lock(&irq->irq_lock);
list_del(&irq->ap_list);
irq->vcpu = target_vcpu;
list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
+ target_vcpu_needs_kick = true;
}
spin_unlock(&irq->irq_lock);
spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
spin_unlock_irqrestore(&vcpuA->arch.vgic_cpu.ap_list_lock, flags);
+
+ if (target_vcpu_needs_kick) {
+ kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu);
+ kvm_vcpu_kick(target_vcpu);
+ }
+
goto retry;
}
vgic_v3_set_underflow(vcpu);
}
-static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
-{
- if (kvm_vgic_global_state.type == VGIC_V2)
- vgic_v2_set_npie(vcpu);
- else
- vgic_v3_set_npie(vcpu);
-}
-
/* Requires the ap_list_lock to be held. */
static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
bool *multi_sgi)
DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ int w;
+
spin_lock(&irq->irq_lock);
/* GICv2 SGIs can count for more than one... */
- if (vgic_irq_is_sgi(irq->intid) && irq->source) {
- int w = hweight8(irq->source);
-
- count += w;
- *multi_sgi |= (w > 1);
- } else {
- count++;
- }
+ w = vgic_irq_get_lr_count(irq);
spin_unlock(&irq->irq_lock);
+
+ count += w;
+ *multi_sgi |= (w > 1);
}
return count;
}
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
int count;
- bool npie = false;
bool multi_sgi;
u8 prio = 0xff;
if (likely(vgic_target_oracle(irq) == vcpu)) {
vgic_populate_lr(vcpu, irq, count++);
- if (irq->source) {
- npie = true;
+ if (irq->source)
prio = irq->priority;
- }
}
spin_unlock(&irq->irq_lock);
}
}
- if (npie)
- vgic_set_npie(vcpu);
-
vcpu->arch.vgic_cpu.used_lrs = count;
/* Nuke remaining LRs */
return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
}
+static inline int vgic_irq_get_lr_count(struct vgic_irq *irq)
+{
+ /* Account for the active state as an interrupt */
+ if (vgic_irq_is_sgi(irq->intid) && irq->source)
+ return hweight8(irq->source) + irq->active;
+
+ return irq_is_pending(irq) || irq->active;
+}
+
+static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq)
+{
+ return vgic_irq_get_lr_count(irq) > 1;
+}
+
/*
* This struct provides an intermediate representation of the fields contained
* in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
projects / linux.git / commitdiff