Prashant Bhole [Mon, 16 Dec 2019 08:27:38 +0000 (17:27 +0900)]
libbpf: Fix build by renaming variables
In btf__align_of() variable name 't' is shadowed by inner block
declaration of another variable with same name. Patch renames
variables in order to fix it.
CC sharedobjs/btf.o
btf.c: In function ‘btf__align_of’:
btf.c:303:21: error: declaration of ‘t’ shadows a previous local [-Werror=shadow]
303 | int i, align = 1, t;
| ^
btf.c:283:25: note: shadowed declaration is here
283 | const struct btf_type *t = btf__type_by_id(btf, id);
|
====================
Add support for flexible array accesses in a relocatable manner in BPF CO-RE.
It's a typical pattern in C, and kernel in particular, to provide
a fixed-length struct with zero-sized or dimensionless array at the end. In
such cases variable-sized array contents follows immediately after the end of
a struct. This patch set adds support for such access pattern by allowing
accesses to such arrays.
Patch #1 adds libbpf support. Patch #2 adds few test cases for validation.
====================
Andrii Nakryiko [Sun, 15 Dec 2019 07:08:43 +0000 (23:08 -0800)]
libbpf: Support flexible arrays in CO-RE
Some data stuctures in kernel are defined with either zero-sized array or
flexible (dimensionless) array at the end of a struct. Actual data of such
array follows in memory immediately after the end of that struct, forming its
variable-sized "body" of elements. Support such access pattern in CO-RE
relocation handling.
====================
It's often important for BPF program to know kernel version or some specific
config values (e.g., CONFIG_HZ to convert jiffies to seconds) and change or
adjust program logic based on their values. As of today, any such need has to
be resolved by recompiling BPF program for specific kernel and kernel
configuration. In practice this is usually achieved by using BCC and its
embedded LLVM/Clang. With such set up #ifdef CONFIG_XXX and similar
compile-time constructs allow to deal with kernel varieties.
With CO-RE (Compile Once – Run Everywhere) approach, this is not an option,
unfortunately. All such logic variations have to be done as a normal
C language constructs (i.e., if/else, variables, etc), not a preprocessor
directives. This patch series add support for such advanced scenarios through
C extern variables. These extern variables will be recognized by libbpf and
supplied through extra .extern internal map, similarly to global data. This
.extern map is read-only, which allows BPF verifier to track its content
precisely as constants. That gives an opportunity to have pre-compiled BPF
program, which can potentially use BPF functionality (e.g., BPF helpers) or
kernel features (types, fields, etc), that are available only on a subset of
targeted kernels, while effectively eleminating (through verifier's dead code
detection) such unsupported functionality for other kernels (typically, older
versions). Patch #3 explicitly tests a scenario of using unsupported BPF
helper, to validate the approach.
This patch set heavily relies on BTF type information emitted by compiler for
each extern variable declaration. Based on specific types, libbpf does strict
checks of config data values correctness. See patch #1 for details.
Outline of the patch set:
- patch #1 does a small clean up of internal map names contants;
- patch #2 adds all of the libbpf internal machinery for externs support,
including setting up BTF information for .extern data section;
- patch #3 adds support for .extern into BPF skeleton;
- patch #4 adds externs selftests, as well as enhances test_skeleton.c test to
validate mmap()-ed .extern datasection functionality.
v3->v4:
- clean up copyrights and rebase onto latest skeleton patches (Alexei);
v2->v3:
- truncate too long strings (Alexei);
- clean ups, adding comments (Alexei);
v1->v2:
- use BTF type information for externs (Alexei);
- add strings support;
- add BPF skeleton support for .extern.
====================
Andrii Nakryiko [Sat, 14 Dec 2019 01:47:10 +0000 (17:47 -0800)]
selftests/bpf: Add tests for libbpf-provided externs
Add a set of tests validating libbpf-provided extern variables. One crucial
feature that's tested is dead code elimination together with using invalid BPF
helper. CONFIG_MISSING is not supposed to exist and should always be specified
by libbpf as zero, which allows BPF verifier to correctly do branch pruning
and not fail validation, when invalid BPF helper is called from dead if branch.
Andrii Nakryiko [Sat, 14 Dec 2019 01:47:09 +0000 (17:47 -0800)]
bpftool: Generate externs datasec in BPF skeleton
Add support for generation of mmap()-ed read-only view of libbpf-provided
extern variables. As externs are not supposed to be provided by user code
(that's what .data, .bss, and .rodata is for), don't mmap() it initially. Only
after skeleton load is performed, map .extern contents as read-only memory.
Andrii Nakryiko [Sat, 14 Dec 2019 01:47:08 +0000 (17:47 -0800)]
libbpf: Support libbpf-provided extern variables
Add support for extern variables, provided to BPF program by libbpf. Currently
the following extern variables are supported:
- LINUX_KERNEL_VERSION; version of a kernel in which BPF program is
executing, follows KERNEL_VERSION() macro convention, can be 4- and 8-byte
long;
- CONFIG_xxx values; a set of values of actual kernel config. Tristate,
boolean, strings, and integer values are supported.
Set of possible values is determined by declared type of extern variable.
Supported types of variables are:
- Tristate values. Are represented as `enum libbpf_tristate`. Accepted values
are **strictly** 'y', 'n', or 'm', which are represented as TRI_YES, TRI_NO,
or TRI_MODULE, respectively.
- Boolean values. Are represented as bool (_Bool) types. Accepted values are
'y' and 'n' only, turning into true/false values, respectively.
- Single-character values. Can be used both as a substritute for
bool/tristate, or as a small-range integer:
- 'y'/'n'/'m' are represented as is, as characters 'y', 'n', or 'm';
- integers in a range [-128, 127] or [0, 255] (depending on signedness of
char in target architecture) are recognized and represented with
respective values of char type.
- Strings. String values are declared as fixed-length char arrays. String of
up to that length will be accepted and put in first N bytes of char array,
with the rest of bytes zeroed out. If config string value is longer than
space alloted, it will be truncated and warning message emitted. Char array
is always zero terminated. String literals in config have to be enclosed in
double quotes, just like C-style string literals.
- Integers. 8-, 16-, 32-, and 64-bit integers are supported, both signed and
unsigned variants. Libbpf enforces parsed config value to be in the
supported range of corresponding integer type. Integers values in config can
be:
- decimal integers, with optional + and - signs;
- hexadecimal integers, prefixed with 0x or 0X;
- octal integers, starting with 0.
Config file itself is searched in /boot/config-$(uname -r) location with
fallback to /proc/config.gz, unless config path is specified explicitly
through bpf_object_open_opts' kernel_config_path option. Both gzipped and
plain text formats are supported. Libbpf adds explicit dependency on zlib
because of this, but this shouldn't be a problem, given libelf already depends
on zlib.
All detected extern variables, are put into a separate .extern internal map.
It, similarly to .rodata map, is marked as read-only from BPF program side, as
well as is frozen on load. This allows BPF verifier to track extern values as
constants and perform enhanced branch prediction and dead code elimination.
This can be relied upon for doing kernel version/feature detection and using
potentially unsupported field relocations or BPF helpers in a CO-RE-based BPF
program, while still having a single version of BPF program running on old and
new kernels. Selftests are validating this explicitly for unexisting BPF
helper.
====================
This patch set introduces an alternative and complimentary to existing libbpf
API interface for working with BPF objects, maps, programs, and global data
from userspace side. This approach is relying on code generation. bpftool
produces a struct (a.k.a. skeleton) tailored and specific to provided BPF
object file. It includes hard-coded fields and data structures for every map,
program, link, and global data present.
Altogether this approach significantly reduces amount of userspace boilerplate
code required to open, load, attach, and work with BPF objects. It improves
attach/detach story, by providing pre-allocated space for bpf_links, and
ensuring they are properly detached on shutdown. It allows to do away with by
name/title lookups of maps and programs, because libbpf's skeleton API, in
conjunction with generated code from bpftool, is filling in hard-coded fields
with actual pointers to corresponding struct bpf_map/bpf_program/bpf_link.
Also, thanks to BPF array mmap() support, working with global data (variables)
from userspace is now as natural as it is from BPF side: each variable is just
a struct field inside skeleton struct. Furthermore, this allows to have
a natural way for userspace to pre-initialize global data (including
previously impossible to initialize .rodata) by just assigning values to the
same per-variable fields. Libbpf will carefully take into account this
initialization image, will use it to pre-populate BPF maps at creation time,
and will re-mmap() BPF map's contents at exactly the same userspace memory
address such that it can continue working with all the same pointers without
any interruptions. If kernel doesn't support mmap(), global data will still be
successfully initialized, but after map creation global data structures inside
skeleton will be NULL-ed out. This allows userspace application to gracefully
handle lack of mmap() support, if necessary.
A bunch of selftests are also converted to using skeletons, demonstrating
significant simplification of userspace part of test and reduction in amount
of code necessary.
v2->v3:
- make skeleton part of public API;
- expose btf_dump__emit_type_decl and btf__align_of APIs;
- move LIBBPF_API and DECLARE_LIBBPF_OPTS into libbpf_common.h for reuse;
v1->v2:
- checkpatch.pl and reverse Christmas tree styling (Jakub);
- sanitize variable names to accomodate in-function static vars;
rfc->v1:
- runqslower moved out into separate patch set waiting for vmlinux.h
improvements;
- skeleton generation code deals with unknown internal maps more gracefully.
====================
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:40 +0000 (17:43 -0800)]
selftests/bpf: Add test validating data section to struct convertion layout
Add a simple selftests validating datasection-to-struct layour dumping. Global
variables are constructed in such a way as to cause both natural and
artificial padding (through custom alignment requirement).
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:37 +0000 (17:43 -0800)]
bpftool: Add skeleton codegen command
Add `bpftool gen skeleton` command, which takes in compiled BPF .o object file
and dumps a BPF skeleton struct and related code to work with that skeleton.
Skeleton itself is tailored to a specific structure of provided BPF object
file, containing accessors (just plain struct fields) for every map and
program, as well as dedicated space for bpf_links. If BPF program is using
global variables, corresponding structure definitions of compatible memory
layout are emitted as well, making it possible to initialize and subsequently
read/update global variables values using simple and clear C syntax for
accessing fields. This skeleton majorly improves usability of
opening/loading/attaching of BPF object, as well as interacting with it
throughout the lifetime of loaded BPF object.
Generated skeleton struct has the following structure:
struct <object-name> {
/* used by libbpf's skeleton API */
struct bpf_object_skeleton *skeleton;
/* bpf_object for libbpf APIs */
struct bpf_object *obj;
struct {
/* for every defined map in BPF object: */
struct bpf_map *<map-name>;
} maps;
struct {
/* for every program in BPF object: */
struct bpf_program *<program-name>;
} progs;
struct {
/* for every program in BPF object: */
struct bpf_link *<program-name>;
} links;
/* for every present global data section: */
struct <object-name>__<one of bss, data, or rodata> {
/* memory layout of corresponding data section,
* with every defined variable represented as a struct field
* with exactly the same type, but without const/volatile
* modifiers, e.g.:
*/
int *my_var_1;
...
} *<one of bss, data, or rodata>;
};
This provides great usability improvements:
- no need to look up maps and programs by name, instead just
my_obj->maps.my_map or my_obj->progs.my_prog would give necessary
bpf_map/bpf_program pointers, which user can pass to existing libbpf APIs;
- pre-defined places for bpf_links, which will be automatically populated for
program types that libbpf knows how to attach automatically (currently
tracepoints, kprobe/kretprobe, raw tracepoint and tracing programs). On
tearing down skeleton, all active bpf_links will be destroyed (meaning BPF
programs will be detached, if they are attached). For cases in which libbpf
doesn't know how to auto-attach BPF program, user can manually create link
after loading skeleton and they will be auto-detached on skeleton
destruction:
my_obj->links.my_fancy_prog = bpf_program__attach_cgroup_whatever(
my_obj->progs.my_fancy_prog, <whatever extra param);
- it's extremely easy and convenient to work with global data from userspace
now. Both for read-only and read/write variables, it's possible to
pre-initialize them before skeleton is loaded:
skel = my_obj__open(raw_embed_data);
my_obj->rodata->my_var = 123;
my_obj__load(skel); /* 123 will be initialization value for my_var */
After load, if kernel supports mmap() for BPF arrays, user can still read
(and write for .bss and .data) variables values, but at that point it will
be directly mmap()-ed to BPF array, backing global variables. This allows to
seamlessly exchange data with BPF side. From userspace program's POV, all
the pointers and memory contents stay the same, but mapped kernel memory
changes to point to created map.
If kernel doesn't yet support mmap() for BPF arrays, it's still possible to
use those data section structs to pre-initialize .bss, .data, and .rodata,
but after load their pointers will be reset to NULL, allowing user code to
gracefully handle this condition, if necessary.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:36 +0000 (17:43 -0800)]
libbpf: Add BPF object skeleton support
Add new set of APIs, allowing to open/load/attach BPF object through BPF
object skeleton, generated by bpftool for a specific BPF object file. All the
xxx_skeleton() APIs wrap up corresponding bpf_object_xxx() APIs, but
additionally also automate map/program lookups by name, global data
initialization and mmap()-ing, etc. All this greatly improves and simplifies
userspace usability of working with BPF programs. See follow up patches for
examples.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:35 +0000 (17:43 -0800)]
libbpf: Reduce log level of supported section names dump
It's quite spammy. And now that bpf_object__open() is trying to determine
program type from its section name, we are getting these verbose messages all
the time. Reduce their log level to DEBUG.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:34 +0000 (17:43 -0800)]
libbpf: Postpone BTF ID finding for TRACING programs to load phase
Move BTF ID determination for BPF_PROG_TYPE_TRACING programs to a load phase.
Performing it at open step is inconvenient, because it prevents BPF skeleton
generation on older host kernel, which doesn't contain BTF_KIND_FUNCs
information in vmlinux BTF. This is a common set up, though, when, e.g.,
selftests are compiled on older host kernel, but the test program itself is
executed in qemu VM with bleeding edge kernel. Having this BTF searching
performed at load time allows to successfully use bpf_object__open() for
codegen and inspection of BPF object file.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:33 +0000 (17:43 -0800)]
libbpf: Refactor global data map initialization
Refactor global data map initialization to use anonymous mmap()-ed memory
instead of malloc()-ed one. This allows to do a transparent re-mmap()-ing of
already existing memory address to point to BPF map's memory after
bpf_object__load() step (done in follow up patch). This choreographed setup
allows to have a nice and unsurprising way to pre-initialize read-only (and
r/w as well) maps by user and after BPF map creation keep working with
mmap()-ed contents of this map. All in a way that doesn't require user code to
update any pointers: the illusion of working with memory contents is preserved
before and after actual BPF map instantiation.
Selftests and runqslower example demonstrate this feature in follow up patches.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:32 +0000 (17:43 -0800)]
libbpf: Expose BPF program's function name
Add APIs to get BPF program function name, as opposed to bpf_program__title(),
which returns BPF program function's section name. Function name has a benefit
of being a valid C identifier and uniquely identifies a specific BPF program,
while section name can be duplicated across multiple independent BPF programs.
Add also bpf_object__find_program_by_name(), similar to
bpf_object__find_program_by_title(), to facilitate looking up BPF programs by
their C function names.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:31 +0000 (17:43 -0800)]
libbpf: Expose BTF-to-C type declaration emitting API
Expose API that allows to emit type declaration and field/variable definition
(if optional field name is specified) in valid C syntax for any provided BTF
type. This is going to be used by bpftool when emitting data section layout as
a struct. As part of making this API useful in a stand-alone fashion, move
initialization of some of the internal btf_dump state to earlier phase.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:29 +0000 (17:43 -0800)]
libbpf: Extract common user-facing helpers
LIBBPF_API and DECLARE_LIBBPF_OPTS are needed in many public libbpf API
headers. Extract them into libbpf_common.h to avoid unnecessary
interdependency between btf.h, libbpf.h, and bpf.h or code duplication.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:28 +0000 (17:43 -0800)]
libbpf: Add BPF_EMBED_OBJ macro for embedding BPF .o files
Add a convenience macro BPF_EMBED_OBJ, which allows to embed other files
(typically used to embed BPF .o files) into a hosting userspace programs. To
C program it is exposed as struct bpf_embed_data, containing a pointer to
raw data and its size in bytes.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:27 +0000 (17:43 -0800)]
libbpf: Move non-public APIs from libbpf.h to libbpf_internal.h
Few libbpf APIs are not public but currently exposed through libbpf.h to be
used by bpftool. Move them to libbpf_internal.h, where intent of being
non-stable and non-public is much more obvious.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:26 +0000 (17:43 -0800)]
libbpf: Add generic bpf_program__attach()
Generalize BPF program attaching and allow libbpf to auto-detect type (and
extra parameters, where applicable) and attach supported BPF program types
based on program sections. Currently this is supported for:
- kprobe/kretprobe;
- tracepoint;
- raw tracepoint;
- tracing programs (typed raw TP/fentry/fexit).
More types support can be trivially added within this framework.
Andrii Nakryiko [Sat, 14 Dec 2019 01:43:25 +0000 (17:43 -0800)]
libbpf: Don't require root for bpf_object__open()
Reorganize bpf_object__open and bpf_object__load steps such that
bpf_object__open doesn't need root access. This was previously done for
feature probing and BTF sanitization. This doesn't have to happen on open,
though, so move all those steps into the load phase.
This is important, because it makes it possible for tools like bpftool, to
just open BPF object file and inspect their contents: programs, maps, BTF,
etc. For such operations it is prohibitive to require root access. On the
other hand, there is a lot of custom libbpf logic in those steps, so its best
avoided for tools to reimplement all that on their own.
Fedora binutils has been patched to show "other info" for a symbol at the
end of the line. This was done in order to support unmaintained scripts
that would break with the extra info. [1]
As libbpf Makefile is not unmaintained, we can simply deal with either
output format, by just removing the "other info" field, as it always comes
inside brackets.
Fixes: 3464afdf11f9 (libbpf: Fix readelf output parsing on powerpc with recent binutils) Reported-by: Justin Forbes <jmforbes@linuxtx.org> Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Cc: Aurelien Jarno <aurelien@aurel32.net> Link: https://lore.kernel.org/bpf/20191213101114.GA3986@calabresa
====================
When working with frequently modified BPF programs, both the ID and the
tag may change. bpftool currently doesn't provide a "stable" way to match
such programs. This patchset allows bpftool to match programs and maps by
name.
When given a tag that matches several programs, bpftool currently only
considers the first match. The first patch changes that behavior to
either process all matching programs (for the show and dump commands) or
error out. The second patch implements program lookup by name, with the
same behavior as for tags in case of ambiguity. The last patch implements
map lookup by name.
Changelogs:
Changes in v2:
- Fix buffer overflow after realloc.
- Add example output to commit message.
- Properly close JSON arrays on errors.
- Fix style errors (line breaks, for loops, exit labels, type for
tagname).
- Move do_show code for argc == 2 to do_show_subset functions.
- Rebase.
====================
Paul Chaignon [Fri, 13 Dec 2019 19:10:37 +0000 (20:10 +0100)]
bpftool: Match maps by name
This patch implements lookup by name for maps and changes the behavior of
lookups by tag to be consistent with prog subcommands. Similarly to
program subcommands, the show and dump commands will return all maps with
the given name (or tag), whereas other commands will error out if several
maps have the same name (resp. tag).
When a map has BTF info, it is dumped in JSON with available BTF info.
This patch requires that all matched maps have BTF info before switching
the output format to JSON.
Paul Chaignon [Fri, 13 Dec 2019 19:10:17 +0000 (20:10 +0100)]
bpftool: Match programs by name
When working with frequently modified BPF programs, both the ID and the
tag may change. bpftool currently doesn't provide a "stable" way to match
such programs.
This patch implements lookup by name for programs. The show and dump
commands will return all programs with the given name, whereas other
commands will error out if several programs have the same name.
Paul Chaignon [Fri, 13 Dec 2019 19:10:04 +0000 (20:10 +0100)]
bpftool: Match several programs with same tag
When several BPF programs have the same tag, bpftool matches only the
first (in ID order). This patch changes that behavior such that dump and
show commands return all matched programs. Commands that require a single
program (e.g., pin and attach) will error out if given a tag that matches
several. bpftool prog dump will also error out if file or visual are
given and several programs have the given tag.
In the case of the dump command, a program header is added before each
dump only if the tag matches several programs; this patch doesn't change
the output if a single program matches. The output when several
programs match thus looks as follows.
This is the 6th iteration of the series that introduces the BPF
dispatcher, which is a mechanism to avoid indirect calls.
The BPF dispatcher is a multi-way branch code generator, targeted for
BPF programs. E.g. when an XDP program is executed via the
bpf_prog_run_xdp(), it is invoked via an indirect call. With
retpolines enabled, the indirect call has a substantial performance
impact. The dispatcher is a mechanism that transform indirect calls to
direct calls, and therefore avoids the retpoline. The dispatcher is
generated using the BPF JIT, and relies on text poking provided by
bpf_arch_text_poke().
The dispatcher hijacks a trampoline function it via the __fentry__ nop
of the trampoline. One dispatcher instance currently supports up to 48
dispatch points. This can be extended in the future.
In this series, only one dispatcher instance is supported, and the
only user is XDP. The dispatcher is updated when an XDP program is
attached/detached to/from a netdev. An alternative to this could have
been to update the dispatcher at program load point, but as there are
usually more XDP programs loaded than attached, so the latter was
picked.
The XDP dispatcher is always enabled, if available, because it helps
even when retpolines are disabled. Please refer to the "Performance"
section below.
The first patch refactors the image allocation from the BPF trampoline
code. Patch two introduces the dispatcher, and patch three adds a
dispatcher for XDP, and wires up the XDP control-/ fast-path. Patch
four adds the dispatcher to BPF_TEST_RUN. Patch five adds a simple
selftest, and the last adds alignment to jump targets.
I have rebased the series on commit 679152d3a32e ("libbpf: Fix printf
compilation warnings on ppc64le arch").
Generated code, x86-64
======================
The dispatcher currently has a maximum of 48 entries, where one entry
is a unique BPF program. Multiple users of a dispatcher instance using
the same BPF program will share that entry.
The program/slot lookup is performed by a binary search, O(log
n). Let's have a look at the generated code.
The trampoline function has the following signature:
unsigned int tramp(const void *ctx,
const struct bpf_insn *insnsi,
unsigned int (*bpf_func)(const void *,
const struct bpf_insn *))
On Intel x86-64 this means that rdx will contain the bpf_func. To,
make it easier to read, I've let the BPF programs have the following
range: 0xffffffffffffffff (-1) to 0xfffffffffffffff0
(-16). 0xffffffff81c00f10 is the retpoline thunk, in this case
__x86_indirect_thunk_rdx. If retpolines are disabled the thunk will be
a regular indirect call.
Dispatcher (full; walk all entries, and fallback):
1. 28.9 Mpps (28903269)
2. 4.1 Mpps (4080078)
3. 5 ns
xdp-perf runs, aliged vs non-aligned jump targets
-------------------------------------------------
In this test dispatchers of different sizes, with and without jump
target alignment, were exercised. As outlined above the function
lookup is performed via binary search. This means that depending on
the pointer value of the function, it can reside in the upper or lower
part of the search table. The performed tests were:
1. aligned, mititations=auto, function entry < other entries
2. aligned, mititations=auto, function entry > other entries
3. non-aligned, mititations=auto, function entry < other entries
4. non-aligned, mititations=auto, function entry > other entries
5. aligned, mititations=off, function entry < other entries
6. aligned, mititations=off, function entry > other entries
7. non-aligned, mititations=off, function entry < other entries
8. non-aligned, mititations=off, function entry > other entries
The micro benchmarks showed that alignment of jump target has some
positive impact.
A reply to this cover letter will contain complete data for all runs.
Multiple xdp-perf baseline with mitigations=auto
------------------------------------------------
Performance counter stats for './test_progs -v -t xdp_perf' (1024 runs):
v3->v4: [2]
* Moved away from doing dispatcher lookup based on the trampoline
function, to a model where the dispatcher instance is explicitly
passed to the bpf_dispatcher_change_prog() (Alexei)
v2->v3: [3]
* Removed xdp_call, and instead make the dispatcher available to all
XDP users via bpf_prog_run_xdp() and dev_xdp_install(). (Toke)
* Always enable the dispatcher, if available (Alexei)
* Reuse BPF trampoline image allocator (Alexei)
* Make sure the dispatcher is exercised in selftests (Alexei)
* Only allow one dispatcher, and wire it to XDP
v1->v2: [4]
* Fixed i386 build warning (kbuild robot)
* Made bpf_dispatcher_lookup() static (kbuild robot)
* Make sure xdp_call.h is only enabled for builtins
* Add xdp_call() to ixgbe, mlx4, and mlx5
RFC->v1: [5]
* Improved error handling (Edward and Andrii)
* Explicit cleanup (Andrii)
* Use 32B with sext cmp (Alexei)
* Align jump targets to 16B (Alexei)
* 4 to 16 entries (Toke)
* Added stats to xdp_call_run()
Björn Töpel [Fri, 13 Dec 2019 17:51:12 +0000 (18:51 +0100)]
bpf, x86: Align dispatcher branch targets to 16B
>From Intel 64 and IA-32 Architectures Optimization Reference Manual,
3.4.1.4 Code Alignment, Assembly/Compiler Coding Rule 11: All branch
targets should be 16-byte aligned.
This commits aligns branch targets according to the Intel manual.
The nops used to align branch targets make the dispatcher larger, and
therefore the number of supported dispatch points/programs are
descreased from 64 to 48.
Björn Töpel [Fri, 13 Dec 2019 17:51:09 +0000 (18:51 +0100)]
bpf, xdp: Start using the BPF dispatcher for XDP
This commit adds a BPF dispatcher for XDP. The dispatcher is updated
from the XDP control-path, dev_xdp_install(), and used when an XDP
program is run via bpf_prog_run_xdp().
Björn Töpel [Fri, 13 Dec 2019 17:51:08 +0000 (18:51 +0100)]
bpf: Introduce BPF dispatcher
The BPF dispatcher is a multi-way branch code generator, mainly
targeted for XDP programs. When an XDP program is executed via the
bpf_prog_run_xdp(), it is invoked via an indirect call. The indirect
call has a substantial performance impact, when retpolines are
enabled. The dispatcher transform indirect calls to direct calls, and
therefore avoids the retpoline. The dispatcher is generated using the
BPF JIT, and relies on text poking provided by bpf_arch_text_poke().
The dispatcher hijacks a trampoline function it via the __fentry__ nop
of the trampoline. One dispatcher instance currently supports up to 64
dispatch points. A user creates a dispatcher with its corresponding
trampoline with the DEFINE_BPF_DISPATCHER macro.
Andrii Nakryiko [Thu, 12 Dec 2019 01:36:09 +0000 (17:36 -0800)]
libbpf: Don't attach perf_buffer to offline/missing CPUs
It's quite common on some systems to have more CPUs enlisted as "possible",
than there are (and could ever be) present/online CPUs. In such cases,
perf_buffer creationg will fail due to inability to create perf event on
missing CPU with error like this:
libbpf: failed to open perf buffer event on cpu #16: No such device
This patch fixes the logic of perf_buffer__new() to ignore CPUs that are
missing or currently offline. In rare cases where user explicitly listed
specific CPUs to connect to, behavior is unchanged: libbpf will try to open
perf event buffer on specified CPU(s) anyways.
Andrii Nakryiko [Thu, 12 Dec 2019 01:35:48 +0000 (17:35 -0800)]
libbpf: Extract and generalize CPU mask parsing logic
This logic is re-used for parsing a set of online CPUs. Having it as an
isolated piece of code working with input string makes it conveninent to test
this logic as well. While refactoring, also improve the robustness of original
implementation.
====================
This change has been suggested by Martin Lau [0] during a review of a
related patch set that extends reuseport tests [1].
Patches 1 & 2 address a warning due to unrecognized section name from
libbpf when running reuseport tests. We don't want to carry this warning
into test_progs.
Patches 3-8 massage the reuseport tests to ease the switch to test_progs
framework. The intention here is to show the work. Happy to squash these,
if needed.
Patches 9-10 do the actual move and conversion to test_progs.
Output from a test_progs run after changes pasted below.
Jakub Sitnicki [Thu, 12 Dec 2019 10:22:59 +0000 (11:22 +0100)]
selftests/bpf: Switch reuseport tests for test_progs framework
The tests were originally written in abort-on-error style. With the switch
to test_progs we can no longer do that. So at the risk of not cleaning up
some resource on failure, we now return to the caller on error.
That said, failure inside one test should not affect others because we run
setup/cleanup before/after every test.
Jakub Sitnicki [Thu, 12 Dec 2019 10:22:55 +0000 (11:22 +0100)]
selftests/bpf: Run reuseport tests in a loop
Prepare for switching reuseport tests to test_progs framework. Loop over
the tests and perform setup/cleanup for each test separately, remembering
that with test_progs we can select tests to run.
Jakub Sitnicki [Thu, 12 Dec 2019 10:22:53 +0000 (11:22 +0100)]
selftests/bpf: Add helpers for getting socket family & type name
Having string arrays to map socket family & type to a name prevents us from
unrolling the test runner loop in the subsequent patch. Introduce helpers
that do the same thing.
Jakub Sitnicki [Thu, 12 Dec 2019 10:22:50 +0000 (11:22 +0100)]
libbpf: Recognize SK_REUSEPORT programs from section name
Allow loading BPF object files that contain SK_REUSEPORT programs without
having to manually set the program type before load if the the section name
is set to "sk_reuseport".
Makes user-space code needed to load SK_REUSEPORT BPF program more concise.
Andrii Nakryiko [Thu, 12 Dec 2019 17:19:18 +0000 (09:19 -0800)]
libbpf: Fix printf compilation warnings on ppc64le arch
On ppc64le __u64 and __s64 are defined as long int and unsigned long int,
respectively. This causes compiler to emit warning when %lld/%llu are used to
printf 64-bit numbers. Fix this by casting to size_t/ssize_t with %zu and %zd
format specifiers, respectively.
v1->v2:
- use size_t/ssize_t instead of custom typedefs (Martin).
Fixes: 1f8e2bcb2cd5 ("libbpf: Refactor relocation handling") Fixes: abd29c931459 ("libbpf: allow specifying map definitions using BTF") Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191212171918.638010-1-andriin@fb.com
Daniel Borkmann [Mon, 9 Dec 2019 15:08:03 +0000 (16:08 +0100)]
bpf, x86, arm64: Enable jit by default when not built as always-on
After Spectre 2 fix via 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON
config") most major distros use BPF_JIT_ALWAYS_ON configuration these days
which compiles out the BPF interpreter entirely and always enables the
JIT. Also given recent fix in e1608f3fa857 ("bpf: Avoid setting bpf insns
pages read-only when prog is jited"), we additionally avoid fragmenting
the direct map for the BPF insns pages sitting in the general data heap
since they are not used during execution. Latter is only needed when run
through the interpreter.
Since both x86 and arm64 JITs have seen a lot of exposure over the years,
are generally most up to date and maintained, there is more downside in
!BPF_JIT_ALWAYS_ON configurations to have the interpreter enabled by default
rather than the JIT. Add a ARCH_WANT_DEFAULT_BPF_JIT config which archs can
use to set the bpf_jit_{enable,kallsyms} to 1. Back in the days the
bpf_jit_kallsyms knob was set to 0 by default since major distros still
had /proc/kallsyms addresses exposed to unprivileged user space which is
not the case anymore. Hence both knobs are set via BPF_JIT_DEFAULT_ON which
is set to 'y' in case of BPF_JIT_ALWAYS_ON or ARCH_WANT_DEFAULT_BPF_JIT.
Daniel Borkmann [Fri, 6 Dec 2019 21:49:34 +0000 (22:49 +0100)]
bpf: Emit audit messages upon successful prog load and unload
Allow for audit messages to be emitted upon BPF program load and
unload for having a timeline of events. The load itself is in
syscall context, so additional info about the process initiating
the BPF prog creation can be logged and later directly correlated
to the unload event.
The only info really needed from BPF side is the globally unique
prog ID where then audit user space tooling can query / dump all
info needed about the specific BPF program right upon load event
and enrich the record, thus these changes needed here can be kept
small and non-intrusive to the core.
Switch existing pattern of "offsetof(..., member) + FIELD_SIZEOF(...,
member)' to "offsetofend(..., member)" which does exactly what
we need without all the copy-paste.
Suggested-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20191210191933.105321-1-sdf@google.com
T6 has a separate region known as high priority filter region
that allows classifying packets going through ULD path. So,
query firmware for HPFILTER resources and enable the high
priority offload filter support when it is available.
Signed-off-by: Shahjada Abul Husain <shahjada@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Chen Wandun [Tue, 10 Dec 2019 10:24:50 +0000 (18:24 +0800)]
enetc: remove variable 'tc_max_sized_frame' set but not used
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/freescale/enetc/enetc_qos.c: In function enetc_setup_tc_cbs:
drivers/net/ethernet/freescale/enetc/enetc_qos.c:195:6: warning: variable tc_max_sized_frame set but not used [-Wunused-but-set-variable]
Fixes: c431047c4efe ("enetc: add support Credit Based Shaper(CBS) for hardware offload") Signed-off-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Tue, 10 Dec 2019 05:04:01 +0000 (21:04 -0800)]
nfp: add support for TLV device stats
Device stats are currently hard coded in the PCI BAR0 layout.
Add a ability to read them from the TLV area instead.
Names for the stats are maintained by the driver, and their
meaning documented. This allows us to more easily add and
remove device stats.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: Cleanup duplicate initialization of sk->sk_state.
When a TCP socket is created, sk->sk_state is initialized twice as
TCP_CLOSE in sock_init_data() and tcp_init_sock(). The tcp_init_sock() is
always called after the sock_init_data(), so it is not necessary to update
sk->sk_state in the tcp_init_sock().
Before v2.1.8, the code of the two functions was in the inet_create(). In
the patch of v2.1.8, the tcp_v4/v6_init_sock() were added and the code of
initialization of sk->state was duplicated.
Signed-off-by: Kuniyuki Iwashima <kuni1840@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Maloy [Mon, 9 Dec 2019 23:52:46 +0000 (00:52 +0100)]
tipc: introduce variable window congestion control
We introduce a simple variable window congestion control for links.
The algorithm is inspired by the Reno algorithm, covering both 'slow
start', 'congestion avoidance', and 'fast recovery' modes.
- We introduce hard lower and upper window limits per link, still
different and configurable per bearer type.
- We introduce a 'slow start theshold' variable, initially set to
the maximum window size.
- We let a link start at the minimum congestion window, i.e. in slow
start mode, and then let is grow rapidly (+1 per rceived ACK) until
it reaches the slow start threshold and enters congestion avoidance
mode.
- In congestion avoidance mode we increment the congestion window for
each window-size number of acked packets, up to a possible maximum
equal to the configured maximum window.
- For each non-duplicate NACK received, we drop back to fast recovery
mode, by setting the both the slow start threshold to and the
congestion window to (current_congestion_window / 2).
- If the timeout handler finds that the transmit queue has not moved
since the previous timeout, it drops the link back to slow start
and forces a probe containing the last sent sequence number to the
sent to the peer, so that this can discover the stale situation.
This change does in reality have effect only on unicast ethernet
transport, as we have seen that there is no room whatsoever for
increasing the window max size for the UDP bearer.
For now, we also choose to keep the limits for the broadcast link
unchanged and equal.
This algorithm seems to give a 50-100% throughput improvement for
messages larger than MTU.
Suggested-by: Xin Long <lucien.xin@gmail.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Maloy [Mon, 9 Dec 2019 23:52:45 +0000 (00:52 +0100)]
tipc: eliminate more unnecessary nacks and retransmissions
When we increase the link tranmsit window we often observe the following
scenario:
1) A STATE message bypasses a sequence of traffic packets and arrives
far ahead of those to the receiver. STATE messages contain a
'peers_nxt_snt' field to indicate which was the last packet sent
from the peer. This mechanism is intended as a last resort for the
receiver to detect missing packets, e.g., during very low traffic
when there is no packet flow to help early loss detection.
3) The receiving link compares the 'peer_nxt_snt' field to its own
'rcv_nxt', finds that there is a gap, and immediately sends a
NACK message back to the peer.
4) When this NACKs arrives at the sender, all the requested
retransmissions are performed, since it is a first-time request.
Just like in the scenario described in the previous commit this leads
to many redundant retransmissions, with decreased throughput as a
consequence.
We fix this by adding two more conditions before we send a NACK in
this sitution. First, the deferred queue must be empty, so we cannot
assume that the potential packet loss has already been detected by
other means. Second, we check the 'peers_snd_nxt' field only in probe/
probe_reply messages, thus turning this into a true mechanism of last
resort as it was really meant to be.
Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jon Maloy [Mon, 9 Dec 2019 23:52:44 +0000 (00:52 +0100)]
tipc: eliminate gap indicator from ACK messages
When we increase the link send window we sometimes observe the
following scenario:
1) A packet #N arrives out of order far ahead of a sequence of older
packets which are still under way. The packet is added to the
deferred queue.
2) The missing packets arrive in sequence, and for each 16th of them
an ACK is sent back to the receiver, as it should be.
3) When building those ACK messages, it is checked if there is a gap
between the link's 'rcv_nxt' and the first packet in the deferred
queue. This is always the case until packet number #N-1 arrives, and
a 'gap' indicator is added, effectively turning them into NACK
messages.
4) When those NACKs arrive at the sender, all the requested
retransmissions are done, since it is a first-time request.
This sometimes leads to a huge amount of redundant retransmissions,
causing a drop in max throughput. This problem gets worse when we
in a later commit introduce variable window congestion control,
since it drops the link back to 'fast recovery' much more often
than necessary.
We now fix this by not sending any 'gap' indicator in regular ACK
messages. We already have a mechanism for sending explicit NACKs
in place, and this is sufficient to keep up the packet flow.
Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
../drivers/net/ppp/ppp_async.c:877:6: warning: misleading indentation;
statement is not part of the previous 'if' [-Wmisleading-indentation]
ap->rpkt = skb;
^
../drivers/net/ppp/ppp_async.c:875:5: note: previous statement is here
if (!skb)
^
1 warning generated.
This warning occurs because there is a space before the tab on this
line. Clean up this entire block's indentation so that it is consistent
with the Linux kernel coding style and clang no longer warns.
Fixes: 6722e78c9005 ("[PPP]: handle misaligned accesses") Link: https://github.com/ClangBuiltLinux/linux/issues/800 Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: smc911x: Adjust indentation in smc911x_phy_configure
Clang warns:
../drivers/net/ethernet/smsc/smc911x.c:939:3: warning: misleading
indentation; statement is not part of the previous 'if'
[-Wmisleading-indentation]
if (!lp->ctl_rfduplx)
^
../drivers/net/ethernet/smsc/smc911x.c:936:2: note: previous statement
is here
if (lp->ctl_rspeed != 100)
^
1 warning generated.
This warning occurs because there is a space after the tab on this line.
Remove it so that the indentation is consistent with the Linux kernel
coding style and clang no longer warns.
Fixes: 0a0c72c9118c ("[PATCH] RE: [PATCH 1/1] net driver: Add support for SMSC LAN911x line of ethernet chips") Link: https://github.com/ClangBuiltLinux/linux/issues/796 Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
net: tulip: Adjust indentation in {dmfe, uli526x}_init_module
Clang warns:
../drivers/net/ethernet/dec/tulip/uli526x.c:1812:3: warning: misleading
indentation; statement is not part of the previous 'if'
[-Wmisleading-indentation]
switch (mode) {
^
../drivers/net/ethernet/dec/tulip/uli526x.c:1809:2: note: previous
statement is here
if (cr6set)
^
1 warning generated.
../drivers/net/ethernet/dec/tulip/dmfe.c:2217:3: warning: misleading
indentation; statement is not part of the previous 'if'
[-Wmisleading-indentation]
switch(mode) {
^
../drivers/net/ethernet/dec/tulip/dmfe.c:2214:2: note: previous
statement is here
if (cr6set)
^
1 warning generated.
This warning occurs because there is a space before the tab on these
lines. Remove them so that the indentation is consistent with the Linux
kernel coding style and clang no longer warns.
While we are here, adjust the default block in dmfe_init_module to have
a proper break between the label and assignment and add a space between
the switch and opening parentheses to avoid a checkpatch warning.
Fixes: e1c3e5014040 ("[PATCH] initialisation cleanup for ULI526x-net-driver") Link: https://github.com/ClangBuiltLinux/linux/issues/795 Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 10 Dec 2019 04:19:10 +0000 (20:19 -0800)]
Merge branch 'dp83867-fix-fifo-depth'
Dan Murphy says:
====================
Fix Tx/Rx FIFO depth for DP83867
The DP83867 supports both the RGMII and SGMII modes. The Tx and Rx FIFO depths
are configurable in these modes but may not applicable for both modes.
When the device is configured for RGMII mode the Tx FIFO depth is applicable
and for SGMII mode both Tx and Rx FIFO depth settings are applicable. When
the driver was originally written only the RGMII device was available and there
were no standard fifo-depth DT properties.
The patchset converts the special ti,fifo-depth property to the standard
tx-fifo-depth property while still allowing the ti,fifo-depth property to be
set as to maintain backward compatibility.
In addition to this change the rx-fifo-depth property support was added and only
written when the device is configured for SGMII mode.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan Murphy [Mon, 9 Dec 2019 20:10:25 +0000 (14:10 -0600)]
net: phy: dp83867: Add rx-fifo-depth and tx-fifo-depth
This code changes the TI specific ti,fifo-depth to the common
tx-fifo-depth property. The tx depth is applicable for both RGMII and
SGMII modes of operation.
rx-fifo-depth was added as well but this is only applicable for SGMII
mode.
So in summary
if RGMII mode write tx fifo depth only
if SGMII mode write both rx and tx fifo depths
If the property is not populated in the device tree then set the value
to the default values.
Signed-off-by: Dan Murphy <dmurphy@ti.com> Reported-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Dan Murphy [Mon, 9 Dec 2019 20:10:24 +0000 (14:10 -0600)]
dt-bindings: dp83867: Convert fifo-depth to common fifo-depth and make optional
Convert the ti,fifo-depth from a TI specific property to the common
tx-fifo-depth property. Also add support for the rx-fifo-depth.
These are optional properties for this device and if these are not
available then the fifo depths are set to device default values.
Signed-off-by: Dan Murphy <dmurphy@ti.com> Reported-by: Adrian Bunk <bunk@kernel.org> CC: Rob Herring <robh@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
net-tcp: Disable TCP ssthresh metrics cache by default
This patch introduces a sysctl knob "net.ipv4.tcp_no_ssthresh_metrics_save"
that disables TCP ssthresh metrics cache by default. Other parts of TCP
metrics cache, e.g. rtt, cwnd, remain unchanged.
As modern networks becoming more and more dynamic, TCP metrics cache
today often causes more harm than benefits. For example, the same IP
address is often shared by different subscribers behind NAT in residential
networks. Even if the IP address is not shared by different users,
caching the slow-start threshold of a previous short flow using loss-based
congestion control (e.g. cubic) often causes the future longer flows of
the same network path to exit slow-start prematurely with abysmal
throughput.
Caching ssthresh is very risky and can lead to terrible performance.
Therefore it makes sense to make disabling ssthresh caching by
default and opt-in for specific networks by the administrators.
This practice also has worked well for several years of deployment with
CUBIC congestion control at Google.
Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Kevin(Yudong) Yang <yyd@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long [Mon, 9 Dec 2019 05:45:18 +0000 (13:45 +0800)]
sctp: get netns from asoc and ep base
Commit 312434617cb1 ("sctp: cache netns in sctp_ep_common") set netns
in asoc and ep base since they're created, and it will never change.
It's a better way to get netns from asoc and ep base, comparing to
calling sock_net().
This patch is to replace them.
v1->v2:
- no change.
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Russell King [Mon, 9 Dec 2019 13:40:23 +0000 (13:40 +0000)]
net: sfp: avoid tx-fault with Nokia GPON module
The Nokia GPON module can hold tx-fault active while it is initialising
which can take up to 60s. Avoid this causing the module to be declared
faulty after the SFP MSA defined non-cooled module timeout.
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Colin Ian King [Mon, 9 Dec 2019 13:16:07 +0000 (13:16 +0000)]
qed: remove redundant assignments to rc
The variable rc is assigned with a value that is never read and
it is re-assigned a new value later on. The assignment is redundant
and can be removed. Clean up multiple occurrances of this pattern.
Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Here's the first bluetooth-next pull request for 5.6:
- Devicetree bindings updates for Broadcom controllers
- Add support for PCM configuration for Broadcom controllers
- btusb: Fixes for Realtek devices
- butsb: A few other smaller fixes (mem leak & non-atomic allocation issue)
Please let me know if there are any issues pulling. Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
WireGuard is a layer 3 secure networking tunnel made specifically for
the kernel, that aims to be much simpler and easier to audit than IPsec.
Extensive documentation and description of the protocol and
considerations, along with formal proofs of the cryptography, are
available at:
This commit implements WireGuard as a simple network device driver,
accessible in the usual RTNL way used by virtual network drivers. It
makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of
networking subsystem APIs. It has a somewhat novel multicore queueing
system designed for maximum throughput and minimal latency of encryption
operations, but it is implemented modestly using workqueues and NAPI.
Configuration is done via generic Netlink, and following a review from
the Netlink maintainer a year ago, several high profile userspace tools
have already implemented the API.
This commit also comes with several different tests, both in-kernel
tests and out-of-kernel tests based on network namespaces, taking profit
of the fact that sockets used by WireGuard intentionally stay in the
namespace the WireGuard interface was originally created, exactly like
the semantics of userspace tun devices. See wireguard.com/netns/ for
pictures and examples.
The source code is fairly short, but rather than combining everything
into a single file, WireGuard is developed as cleanly separable files,
making auditing and comprehension easier. Things are laid out as
follows:
* noise.[ch], cookie.[ch], messages.h: These implement the bulk of the
cryptographic aspects of the protocol, and are mostly data-only in
nature, taking in buffers of bytes and spitting out buffers of
bytes. They also handle reference counting for their various shared
pieces of data, like keys and key lists.
* ratelimiter.[ch]: Used as an integral part of cookie.[ch] for
ratelimiting certain types of cryptographic operations in accordance
with particular WireGuard semantics.
* allowedips.[ch], peerlookup.[ch]: The main lookup structures of
WireGuard, the former being trie-like with particular semantics, an
integral part of the design of the protocol, and the latter just
being nice helper functions around the various hashtables we use.
* device.[ch]: Implementation of functions for the netdevice and for
rtnl, responsible for maintaining the life of a given interface and
wiring it up to the rest of WireGuard.
* peer.[ch]: Each interface has a list of peers, with helper functions
available here for creation, destruction, and reference counting.
* socket.[ch]: Implementation of functions related to udp_socket and
the general set of kernel socket APIs, for sending and receiving
ciphertext UDP packets, and taking care of WireGuard-specific sticky
socket routing semantics for the automatic roaming.
* netlink.[ch]: Userspace API entry point for configuring WireGuard
peers and devices. The API has been implemented by several userspace
tools and network management utility, and the WireGuard project
distributes the basic wg(8) tool.
* queueing.[ch]: Shared function on the rx and tx path for handling
the various queues used in the multicore algorithms.
* send.c: Handles encrypting outgoing packets in parallel on
multiple cores, before sending them in order on a single core, via
workqueues and ring buffers. Also handles sending handshake and cookie
messages as part of the protocol, in parallel.
* receive.c: Handles decrypting incoming packets in parallel on
multiple cores, before passing them off in order to be ingested via
the rest of the networking subsystem with GRO via the typical NAPI
poll function. Also handles receiving handshake and cookie messages
as part of the protocol, in parallel.
* timers.[ch]: Uses the timer wheel to implement protocol particular
event timeouts, and gives a set of very simple event-driven entry
point functions for callers.
* main.c, version.h: Initialization and deinitialization of the module.
* selftest/*.h: Runtime unit tests for some of the most security
sensitive functions.
* tools/testing/selftests/wireguard/netns.sh: Aforementioned testing
script using network namespaces.
This commit aims to be as self-contained as possible, implementing
WireGuard as a standalone module not needing much special handling or
coordination from the network subsystem. I expect for future
optimizations to the network stack to positively improve WireGuard, and
vice-versa, but for the time being, this exists as intentionally
standalone.
We introduce a menu option for CONFIG_WIREGUARD, as well as providing a
verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Cc: David Miller <davem@davemloft.net> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
1) More jumbo frame fixes in r8169, from Heiner Kallweit.
2) Fix bpf build in minimal configuration, from Alexei Starovoitov.
3) Use after free in slcan driver, from Jouni Hogander.
4) Flower classifier port ranges don't work properly in the HW offload
case, from Yoshiki Komachi.
5) Use after free in hns3_nic_maybe_stop_tx(), from Yunsheng Lin.
6) Out of bounds access in mqprio_dump(), from Vladyslav Tarasiuk.
7) Fix flow dissection in dsa TX path, from Alexander Lobakin.
8) Stale syncookie timestampe fixes from Guillaume Nault.
[ Did an evil merge to silence a warning introduced by this pull - Linus ]
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (84 commits)
r8169: fix rtl_hw_jumbo_disable for RTL8168evl
net_sched: validate TCA_KIND attribute in tc_chain_tmplt_add()
r8169: add missing RX enabling for WoL on RTL8125
vhost/vsock: accept only packets with the right dst_cid
net: phy: dp83867: fix hfs boot in rgmii mode
net: ethernet: ti: cpsw: fix extra rx interrupt
inet: protect against too small mtu values.
gre: refetch erspan header from skb->data after pskb_may_pull()
pppoe: remove redundant BUG_ON() check in pppoe_pernet
tcp: Protect accesses to .ts_recent_stamp with {READ,WRITE}_ONCE()
tcp: tighten acceptance of ACKs not matching a child socket
tcp: fix rejected syncookies due to stale timestamps
lpc_eth: kernel BUG on remove
tcp: md5: fix potential overestimation of TCP option space
net: sched: allow indirect blocks to bind to clsact in TC
net: core: rename indirect block ingress cb function
net-sysfs: Call dev_hold always in netdev_queue_add_kobject
net: dsa: fix flow dissection on Tx path
net/tls: Fix return values to avoid ENOTSUPP
net: avoid an indirect call in ____sys_recvmsg()
...
Linus Torvalds [Sun, 8 Dec 2019 20:23:42 +0000 (12:23 -0800)]
Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull more SCSI updates from James Bottomley:
"Eleven patches, all in drivers (no core changes) that are either minor
cleanups or small fixes.
They were late arriving, but still safe for -rc1"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
scsi: MAINTAINERS: Add the linux-scsi mailing list to the ISCSI entry
scsi: megaraid_sas: Make poll_aen_lock static
scsi: sd_zbc: Improve report zones error printout
scsi: qla2xxx: Fix qla2x00_request_irqs() for MSI
scsi: qla2xxx: unregister ports after GPN_FT failure
scsi: qla2xxx: fix rports not being mark as lost in sync fabric scan
scsi: pm80xx: Remove unused include of linux/version.h
scsi: pm80xx: fix logic to break out of loop when register value is 2 or 3
scsi: scsi_transport_sas: Fix memory leak when removing devices
scsi: lpfc: size cpu map by last cpu id set
scsi: ibmvscsi_tgt: Remove unneeded variable rc
Linus Torvalds [Sun, 8 Dec 2019 20:12:18 +0000 (12:12 -0800)]
Merge tag '5.5-rc-smb3-fixes-part2' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs fixes from Steve French:
"Nine cifs/smb3 fixes:
- one fix for stable (oops during oplock break)
- two timestamp fixes including important one for updating mtime at
close to avoid stale metadata caching issue on dirty files (also
improves perf by using SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB over the
wire)
- two fixes for "modefromsid" mount option for file create (now
allows mode bits to be set more atomically and accurately on create
by adding "sd_context" on create when modefromsid specified on
mount)
- two fixes for multichannel found in testing this week against
different servers
- two small cleanup patches"
* tag '5.5-rc-smb3-fixes-part2' of git://git.samba.org/sfrench/cifs-2.6:
smb3: improve check for when we send the security descriptor context on create
smb3: fix mode passed in on create for modetosid mount option
cifs: fix possible uninitialized access and race on iface_list
cifs: Fix lookup of SMB connections on multichannel
smb3: query attributes on file close
smb3: remove unused flag passed into close functions
cifs: remove redundant assignment to pointer pneg_ctxt
fs: cifs: Fix atime update check vs mtime
CIFS: Fix NULL-pointer dereference in smb2_push_mandatory_locks
Linus Torvalds [Sun, 8 Dec 2019 19:08:28 +0000 (11:08 -0800)]
Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull misc vfs cleanups from Al Viro:
"No common topic, just three cleanups".
* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
make __d_alloc() static
fs/namespace: add __user to open_tree and move_mount syscalls
fs/fnctl: fix missing __user in fcntl_rw_hint()
Linus Torvalds [Sun, 8 Dec 2019 01:07:18 +0000 (17:07 -0800)]
Merge tag 'iomap-5.5-merge-14' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull iomap fixes from Darrick Wong:
"Fix a race condition and a use-after-free error:
- Fix a UAF when reporting writeback errors
- Fix a race condition when handling page uptodate on fragmented file
with blocksize < pagesize"
* tag 'iomap-5.5-merge-14' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
iomap: stop using ioend after it's been freed in iomap_finish_ioend()
iomap: fix sub-page uptodate handling
Linus Torvalds [Sun, 8 Dec 2019 01:05:33 +0000 (17:05 -0800)]
Merge tag 'xfs-5.5-merge-17' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull xfs fixes from Darrick Wong:
"Fix a couple of resource management errors and a hang:
- fix a crash in the log setup code when log mounting fails
- fix a hang when allocating space on the realtime device
- fix a block leak when freeing space on the realtime device"
* tag 'xfs-5.5-merge-17' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
xfs: fix mount failure crash on invalid iclog memory access
xfs: don't check for AG deadlock for realtime files in bunmapi
xfs: fix realtime file data space leak
Linus Torvalds [Sun, 8 Dec 2019 00:59:25 +0000 (16:59 -0800)]
Merge tag 'for-linus-5.5-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux
Pull orangefs update from Mike Marshall:
"orangefs: posix open permission checking...
Orangefs has no open, and orangefs checks file permissions on each
file access. Posix requires that file permissions be checked on open
and nowhere else. Orangefs-through-the-kernel needs to seem posix
compliant.
The VFS opens files, even if the filesystem provides no method. We can
see if a file was successfully opened for read and or for write by
looking at file->f_mode.
When writes are flowing from the page cache, file is no longer
available. We can trust the VFS to have checked file->f_mode before
writing to the page cache.
The mode of a file might change between when it is opened and IO
commences, or it might be created with an arbitrary mode.
We'll make sure we don't hit EACCES during the IO stage by using
UID 0"
[ This is "posixish", but not a great solution in the long run, since a
proper secure network server shouldn't really trust the client like this.
But proper and secure POSIX behavior requires an open method and a
resulting cookie for IO of some kind, or similar. - Linus ]
* tag 'for-linus-5.5-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux:
orangefs: posix open permission checking...
Linus Torvalds [Sun, 8 Dec 2019 00:56:00 +0000 (16:56 -0800)]
Merge tag 'nfsd-5.5' of git://linux-nfs.org/~bfields/linux
Pull nfsd updates from Bruce Fields:
"This is a relatively quiet cycle for nfsd, mainly various bugfixes.
Possibly most interesting is Trond's fixes for some callback races
that were due to my incomplete understanding of rpc client shutdown.
Unfortunately at the last minute I've started noticing a new
intermittent failure to send callbacks. As the logic seems basically
correct, I'm leaving Trond's patches in for now, and hope to find a
fix in the next week so I don't have to revert those patches"
* tag 'nfsd-5.5' of git://linux-nfs.org/~bfields/linux: (24 commits)
nfsd: depend on CRYPTO_MD5 for legacy client tracking
NFSD fixing possible null pointer derefering in copy offload
nfsd: check for EBUSY from vfs_rmdir/vfs_unink.
nfsd: Ensure CLONE persists data and metadata changes to the target file
SUNRPC: Fix backchannel latency metrics
nfsd: restore NFSv3 ACL support
nfsd: v4 support requires CRYPTO_SHA256
nfsd: Fix cld_net->cn_tfm initialization
lockd: remove __KERNEL__ ifdefs
sunrpc: remove __KERNEL__ ifdefs
race in exportfs_decode_fh()
nfsd: Drop LIST_HEAD where the variable it declares is never used.
nfsd: document callback_wq serialization of callback code
nfsd: mark cb path down on unknown errors
nfsd: Fix races between nfsd4_cb_release() and nfsd4_shutdown_callback()
nfsd: minor 4.1 callback cleanup
SUNRPC: Fix svcauth_gss_proxy_init()
SUNRPC: Trace gssproxy upcall results
sunrpc: fix crash when cache_head become valid before update
nfsd: remove private bin2hex implementation
...
Linus Torvalds [Sun, 8 Dec 2019 00:50:55 +0000 (16:50 -0800)]
Merge tag 'nfs-for-5.5-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client updates from Trond Myklebust:
"Highlights include:
Features:
- NFSv4.2 now supports cross device offloaded copy (i.e. offloaded
copy of a file from one source server to a different target
server).
- New RDMA tracepoints for debugging congestion control and Local
Invalidate WRs.
Bugfixes and cleanups
- Drop the NFSv4.1 session slot if nfs4_delegreturn_prepare waits for
layoutreturn
- Handle bad/dead sessions correctly in nfs41_sequence_process()
- Various bugfixes to the delegation return operation.
- Various bugfixes pertaining to delegations that have been revoked.
- Cleanups to the NFS timespec code to avoid unnecessary conversions
between timespec and timespec64.
- Fix unstable RDMA connections after a reconnect
- Close race between waking an RDMA sender and posting a receive
- Wake pending RDMA tasks if connection fails
- Fix MR list corruption, and clean up MR usage
- Fix another RPCSEC_GSS issue with MIC buffer space"
* tag 'nfs-for-5.5-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (79 commits)
SUNRPC: Capture completion of all RPC tasks
SUNRPC: Fix another issue with MIC buffer space
NFS4: Trace lock reclaims
NFS4: Trace state recovery operation
NFSv4.2 fix memory leak in nfs42_ssc_open
NFSv4.2 fix kfree in __nfs42_copy_file_range
NFS: remove duplicated include from nfs4file.c
NFSv4: Make _nfs42_proc_copy_notify() static
NFS: Fallocate should use the nfs4_fattr_bitmap
NFS: Return -ETXTBSY when attempting to write to a swapfile
fs: nfs: sysfs: Remove NULL check before kfree
NFS: remove unneeded semicolon
NFSv4: add declaration of current_stateid
NFSv4.x: Drop the slot if nfs4_delegreturn_prepare waits for layoutreturn
NFSv4.x: Handle bad/dead sessions correctly in nfs41_sequence_process()
nfsv4: Move NFSPROC4_CLNT_COPY_NOTIFY to end of list
SUNRPC: Avoid RPC delays when exiting suspend
NFS: Add a tracepoint in nfs_fh_to_dentry()
NFSv4: Don't retry the GETATTR on old stateid in nfs4_delegreturn_done()
NFSv4: Handle NFS4ERR_OLD_STATEID in delegreturn
...
Steve French [Sat, 7 Dec 2019 23:38:22 +0000 (17:38 -0600)]
smb3: improve check for when we send the security descriptor context on create
We had cases in the previous patch where we were sending the security
descriptor context on SMB3 open (file create) in cases when we hadn't
mounted with with "modefromsid" mount option.
Add check for that mount flag before calling ad_sd_context in
open init.
Signed-off-by: Steve French <stfrench@microsoft.com> Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Linus Torvalds [Sat, 7 Dec 2019 22:51:04 +0000 (14:51 -0800)]
Merge tag 'vfio-v5.5-rc1' of git://github.com/awilliam/linux-vfio
Pull VFIO updates from Alex Williamson:
- Remove hugepage checks for reserved pfns (Ben Luo)
- Fix irq-bypass unregister ordering (Jiang Yi)
* tag 'vfio-v5.5-rc1' of git://github.com/awilliam/linux-vfio:
vfio/pci: call irq_bypass_unregister_producer() before freeing irq
vfio/type1: remove hugepage checks in is_invalid_reserved_pfn()