The definitions of REFCOUNT_MAX and REFCOUNT_SATURATED are the same,
regardless of CONFIG_REFCOUNT_FULL, so consolidate them into a single
pair of definitions.
Will Deacon [Thu, 21 Nov 2019 11:58:58 +0000 (11:58 +0000)]
locking/refcount: Move saturation warnings out of line
Having the refcount saturation and warnings inline bloats the text,
despite the fact that these paths should never be executed in normal
operation.
Move the refcount saturation and warnings out of line to reduce the
image size when refcount_t checking is enabled. Relative to an x86_64
defconfig, the sizes reported by bloat-o-meter are:
# defconfig+REFCOUNT_FULL, inline saturation (i.e. before this patch)
Total: Before=14762076, After=14915442, chg +1.04%
# defconfig+REFCOUNT_FULL, out-of-line saturation (i.e. after this patch)
Total: Before=14762076, After=14835497, chg +0.50%
A side-effect of this change is that we now only get one warning per
refcount saturation type, rather than one per problematic call-site.
Will Deacon [Thu, 21 Nov 2019 11:58:57 +0000 (11:58 +0000)]
locking/refcount: Improve performance of generic REFCOUNT_FULL code
Rewrite the generic REFCOUNT_FULL implementation so that the saturation
point is moved to INT_MIN / 2. This allows us to defer the sanity checks
until after the atomic operation, which removes many uses of cmpxchg()
in favour of atomic_fetch_{add,sub}().
Some crude perf results obtained from lkdtm show substantially less
overhead, despite the checking:
$ perf stat -r 3 -B -- echo {ATOMIC,REFCOUNT}_TIMING >/sys/kernel/debug/provoke-crash/DIRECT
# arm64
ATOMIC_TIMING: 46.50451 +- 0.00134 seconds time elapsed ( +- 0.00% )
REFCOUNT_TIMING (REFCOUNT_FULL, mainline): 77.57522 +- 0.00982 seconds time elapsed ( +- 0.01% )
REFCOUNT_TIMING (REFCOUNT_FULL, this series): 48.7181 +- 0.0256 seconds time elapsed ( +- 0.05% )
# x86
ATOMIC_TIMING: 31.6225 +- 0.0776 seconds time elapsed ( +- 0.25% )
REFCOUNT_TIMING (!REFCOUNT_FULL, mainline/x86 asm): 31.6689 +- 0.0901 seconds time elapsed ( +- 0.28% )
REFCOUNT_TIMING (REFCOUNT_FULL, mainline): 53.203 +- 0.138 seconds time elapsed ( +- 0.26% )
REFCOUNT_TIMING (REFCOUNT_FULL, this series): 31.7408 +- 0.0486 seconds time elapsed ( +- 0.15% )
Signed-off-by: Will Deacon <will@kernel.org> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Hanjun Guo <guohanjun@huawei.com> Tested-by: Jan Glauber <jglauber@marvell.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191121115902.2551-6-will@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
Will Deacon [Thu, 21 Nov 2019 11:58:56 +0000 (11:58 +0000)]
locking/refcount: Move the bulk of the REFCOUNT_FULL implementation into the <linux/refcount.h> header
In an effort to improve performance of the REFCOUNT_FULL implementation,
move the bulk of its functions into linux/refcount.h. This allows them
to be inlined in the same way as if they had been provided via
CONFIG_ARCH_HAS_REFCOUNT.
The full-fat refcount implementation is exposed via a set of functions
suffixed with "_checked()", the idea being that code can choose to use
the more expensive, yet more secure implementation on a case-by-case
basis.
In reality, this hasn't happened, so with a grand total of zero users,
let's remove the checked variants for now by simply dropping the suffix
and predicating the out-of-line functions on CONFIG_REFCOUNT_FULL=y.
Will Deacon [Thu, 21 Nov 2019 11:58:54 +0000 (11:58 +0000)]
locking/refcount: Ensure integer operands are treated as signed
In preparation for changing the saturation point of REFCOUNT_FULL to
INT_MIN/2, change the type of integer operands passed into the API
from 'unsigned int' to 'int' so that we can avoid casting during
comparisons when we don't want to fall foul of C integral conversion
rules for signed and unsigned types.
Since the kernel is compiled with '-fno-strict-overflow', we don't need
to worry about the UB introduced by signed overflow here. Furthermore,
we're already making heavy use of the atomic_t API, which operates
exclusively on signed types.
Will Deacon [Thu, 21 Nov 2019 11:58:53 +0000 (11:58 +0000)]
locking/refcount: Define constants for saturation and max refcount values
The REFCOUNT_FULL implementation uses a different saturation point than
the x86 implementation, which means that the shared refcount code in
lib/refcount.c (e.g. refcount_dec_not_one()) needs to be aware of the
difference.
Rather than duplicate the definitions from the lkdtm driver, instead
move them into <linux/refcount.h> and update all references accordingly.
Ingo Molnar [Sun, 24 Nov 2019 10:21:44 +0000 (11:21 +0100)]
x86/pti/32: Calculate the various PTI cpu_entry_area sizes correctly, make the CPU_ENTRY_AREA_PAGES assert precise
When two recent commits that increased the size of the 'struct cpu_entry_area'
were merged in -tip, the 32-bit defconfig build started failing on the following
build time assert:
./include/linux/compiler.h:391:38: error: call to ‘__compiletime_assert_189’ declared with attribute error: BUILD_BUG_ON failed: CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE
arch/x86/mm/cpu_entry_area.c:189:2: note: in expansion of macro ‘BUILD_BUG_ON’
In function ‘setup_cpu_entry_area_ptes’,
Which corresponds to the following build time assert:
The purpose of this assert is to sanity check the fixed-value definition of
CPU_ENTRY_AREA_PAGES arch/x86/include/asm/pgtable_32_types.h:
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 41)
The '41' is supposed to match sizeof(struct cpu_entry_area)/PAGE_SIZE, which value
we didn't want to define in such a low level header, because it would cause
dependency hell.
Every time the size of cpu_entry_area is changed, we have to adjust CPU_ENTRY_AREA_PAGES
accordingly - and this assert is checking that constraint.
But the assert is both imprecise and buggy, primarily because it doesn't
include the single readonly IDT page that is mapped at CPU_ENTRY_AREA_BASE
(which begins at a PMD boundary).
This bug was hidden by the fact that by accident CPU_ENTRY_AREA_PAGES is defined
too large upstream (v5.4-rc8):
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
While 'struct cpu_entry_area' is 155648 bytes, or 38 pages. So we had two extra
pages, which hid the bug.
The following commit (not yet upstream) increased the size to 40 pages:
x86/iopl: ("Restrict iopl() permission scope")
... but increased CPU_ENTRY_AREA_PAGES only 41 - i.e. shortening the gap
to just 1 extra page.
Then another not-yet-upstream commit changed the size again:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Which increased the cpu_entry_area size from 38 to 39 pages, but
didn't change CPU_ENTRY_AREA_PAGES (kept it at 40). This worked
fine, because we still had a page left from the accidental 'reserve'.
But when these two commits were merged into the same tree, the
combined size of cpu_entry_area grew from 38 to 40 pages, while
CPU_ENTRY_AREA_PAGES finally caught up to 40 as well.
Which is fine in terms of functionality, but the assert broke:
This takes the IDT page into account, and also connects the size-based
define of CPU_ENTRY_AREA_TOTAL_SIZE with the address-subtraction based
define of CPU_ENTRY_AREA_MAP_SIZE.
Also clean up some of the names which made it rather confusing:
- 'CPU_ENTRY_AREA_TOT_SIZE' wasn't actually the 'total' size of
the cpu-entry-area, but the per-cpu array size, so rename this
to CPU_ENTRY_AREA_ARRAY_SIZE.
- Introduce CPU_ENTRY_AREA_TOTAL_SIZE that _is_ the total mapping
size, with the IDT included.
- Add comments where '+1' denotes the IDT mapping - it wasn't
obvious and took me about 3 hours to decode...
Finally, because this particular commit is actually applied after
this patch:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Fix the CPU_ENTRY_AREA_PAGES value from 40 pages to the correct 39 pages.
All future commits that change cpu_entry_area will have to adjust
this value precisely.
As a side note, we should probably attempt to remove CPU_ENTRY_AREA_PAGES
and derive its value directly from the structure, without causing
header hell - but that is an adventure for another day! :-)
Fixes: 880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit") Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: stable@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
Here's one last bluetooth-next pull request for the 5.5 kernel:
- Fix BDADDR_PROPERTY & INVALID_BDADDR quirk handling
- Added support for BCM4334B0 and BCM4335A0 controllers
- A few other smaller fixes related to locking and memory leaks
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
ax88179_178a uses the usbnet transmit function usbnet_start_xmit() which
implements software timestamping. ax88179_178a overrides ethtool_ops but
missed to set .get_ts_info. This caused SOF_TIMESTAMPING_TX_SOFTWARE
capability to be not available.
Signed-off-by: Andreas K. Besslein <besslein.andreas@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Jakub Kicinski [Mon, 25 Nov 2019 02:35:05 +0000 (18:35 -0800)]
Merge branch 'mlxsw-Two-small-updates'
Ido Schimmel says:
====================
mlxsw: Two small updates
Patch #1 from Petr handles a corner case in GRE tunnel offload.
Patch #2 from Amit fixes a recent issue where the driver was programming
the device to use an adjacency index (for a nexthop) that was not
properly initialized.
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Amit Cohen [Sun, 24 Nov 2019 07:48:03 +0000 (09:48 +0200)]
mlxsw: spectrum_router: Fix use of uninitialized adjacency index
When mlxsw_sp_adj_discard_write() is called for the first time, the
value stored in 'mlxsw_sp->router->adj_discard_index' is invalid, as
indicated by 'mlxsw_sp->router->adj_discard_index_valid' being set to
'false'.
In this case, we should not use the value initially stored in
'mlxsw_sp->router->adj_discard_index' (0) and instead use the value
allocated later in the function.
Fixes: 983db6198f0d ("mlxsw: spectrum_router: Allocate discard adjacency entry when needed") Signed-off-by: Amit Cohen <amitc@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Petr Machata [Sun, 24 Nov 2019 07:48:02 +0000 (09:48 +0200)]
mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
When a GRE tunnel is bound to an underlay netdevice and that netdevice is
moved to a different VRF, that could cause two tunnels to have the same
underlay local address in the same VRF. Linux in this situation dispatches
the traffic according to the tunnel key (or lack thereof), but that cannot
be offloaded to Spectrum devices.
Detect this situation and unoffload the two impacted tunnels when it
happens.
Signed-off-by: Petr Machata <petrm@mellanox.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Daniel Borkmann [Sun, 24 Nov 2019 00:39:42 +0000 (01:39 +0100)]
bpf: Simplify __bpf_arch_text_poke poke type handling
Given that we have BPF_MOD_NOP_TO_{CALL,JUMP}, BPF_MOD_{CALL,JUMP}_TO_NOP
and BPF_MOD_{CALL,JUMP}_TO_{CALL,JUMP} poke types and that we also pass in
old_addr as well as new_addr, it's a bit redundant and unnecessarily
complicates __bpf_arch_text_poke() itself since we can derive the same from
the *_addr that were passed in. Hence simplify and use BPF_MOD_{CALL,JUMP}
as types which also allows to clean up call-sites.
In addition to that, __bpf_arch_text_poke() currently verifies that text
matches expected old_insn before we invoke text_poke_bp(). Also add a check
on new_insn and skip rewrite if it already matches. Reason why this is rather
useful is that it avoids making any special casing in prog_array_map_poke_run()
when old and new prog were NULL and has the benefit that also for this case
we perform a check on text whether it really matches our expectations.
Martin KaFai Lau [Sat, 23 Nov 2019 20:25:04 +0000 (12:25 -0800)]
bpf: Introduce BPF_TRACE_x helper for the tracing tests
For BPF_PROG_TYPE_TRACING, the bpf_prog's ctx is an array of u64.
This patch borrows the idea from BPF_CALL_x in filter.h to
convert a u64 to the arg type of the traced function.
The new BPF_TRACE_x has an arg to specify the return type of a bpf_prog.
It will be used in the future TCP-ops bpf_prog that may return "void".
The new macros are defined in the new header file "bpf_trace_helpers.h".
It is under selftests/bpf/ for now. It could be moved to libbpf later
after seeing more upcoming non-tracing use cases.
The tests are changed to use these new macros also. Hence,
the k[s]u8/16/32/64 are no longer needed and they are removed
from the bpf_helpers.h.
Daniel Borkmann [Sat, 23 Nov 2019 20:37:31 +0000 (21:37 +0100)]
bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
Add a definition of bpf_jit_blinding_enabled() when CONFIG_BPF_JIT is not set
in order to fix a recent build regression:
[...]
CC kernel/bpf/verifier.o
CC kernel/bpf/inode.o
kernel/bpf/verifier.c: In function ‘fixup_bpf_calls’:
kernel/bpf/verifier.c:9132:25: error: implicit declaration of function ‘bpf_jit_blinding_enabled’; did you mean ‘bpf_jit_kallsyms_enabled’? [-Werror=implicit-function-declaration]
9132 | bool expect_blinding = bpf_jit_blinding_enabled(prog);
| ^~~~~~~~~~~~~~~~~~~~~~~~
| bpf_jit_kallsyms_enabled
CC kernel/bpf/helpers.o
CC kernel/bpf/hashtab.o
[...]
====================
This gets rid of indirect jumps for BPF tail calls whenever possible.
The series adds emission for *direct* jumps for tail call maps in order
to avoid the retpoline overhead from a493a87f38cf ("bpf, x64: implement
retpoline for tail call") for situations that allow for it, meaning,
for known constant keys at verification time which are used as index
into the tail call map. See patch 7/8 for more general details.
Thanks!
v1 -> v2:
- added more test cases
- u8 ip_stable -> bool (Andrii)
- removed bpf_map_poke_{un,}lock and simplified the code (Andrii)
- added break into prog_array_map_poke_untrack since there's just
one prog (Andrii)
- fixed typo: for for in commit msg (Andrii)
- reworked __bpf_arch_text_poke (Andrii)
- added subtests, and comment on tests themselves, NULL-NULL
transistion (Andrii)
- in constant map key tracking I've moved the map_poke_track callback
to once we've finished creating the poke tab as otherwise concurrent
access from tail call map would blow up (since we realloc the table)
rfc -> v1:
- Applied Alexei's and Andrii's feeback from
https://lore.kernel.org/bpf/cover.1573779287.git.daniel@iogearbox.net/T/#t
====================
Daniel Borkmann [Fri, 22 Nov 2019 20:08:01 +0000 (21:08 +0100)]
bpf, testing: Add various tail call test cases
Add several BPF kselftest cases for tail calls which test the various
patch directions, and that multiple locations are patched in same and
different programs.
Daniel Borkmann [Fri, 22 Nov 2019 20:08:00 +0000 (21:08 +0100)]
bpf, x86: Emit patchable direct jump as tail call
Add initial code emission for *direct* jumps for tail call maps in
order to avoid the retpoline overhead from a493a87f38cf ("bpf, x64:
implement retpoline for tail call") for situations that allow for
it, meaning, for known constant keys at verification time which are
used as index into the tail call map. In case of Cilium which makes
heavy use of tail calls, constant keys are used in the vast majority,
only for a single occurrence we use a dynamic key.
High level outline is that if the target prog is NULL in the map, we
emit a 5-byte nop for the fall-through case and if not, we emit a
5-byte direct relative jmp to the target bpf_func + skipped prologue
offset. Later during runtime, we patch these 5-byte nop/jmps upon
tail call map update or deletions dynamically. Note that on x86-64
the direct jmp works as we reuse the same stack frame and skip
prologue (as opposed to some other JIT implementations).
One of the issues is that the tail call map slots can change at any
given time even during JITing. Therefore, we have two passes: i) emit
nops for all patchable locations during main JITing phase until we
declare prog->jited = 1 eventually. At this point the image is stable,
not public yet and with all jmps disabled. While JITing, we collect
additional info like poke->ip in order to remember the patch location
for later modifications. In ii) bpf_tail_call_direct_fixup() walks
over the progs poke_tab, locks the tail call maps poke_mutex to
prevent from parallel updates and patches in the right locations via
__bpf_arch_text_poke(). Note, the main bpf_arch_text_poke() cannot
be used at this point since we're not yet exposed to kallsyms. For
the update we use plain memcpy() since the image is not public and
still in read-write mode. After patching, we activate that poke entry
through poke->ip_stable. Meaning, at this point any tail call map
updates/deletions are not going to ignore that poke entry anymore.
Then, bpf_arch_text_poke() might still occur on the read-write image
until we finally locked it as read-only. Both modifications on the
given image are under text_mutex to avoid interference with each
other when update requests come in in parallel for different tail
call maps (current one we have locked in JIT and different one where
poke->ip_stable was already set).
Example prog:
# ./bpftool p d x i 1655
0: (b7) r3 = 0
1: (18) r2 = map[id:526]
3: (85) call bpf_tail_call#12
4: (b7) r0 = 1
5: (95) exit
Daniel Borkmann [Fri, 22 Nov 2019 20:07:59 +0000 (21:07 +0100)]
bpf: Constant map key tracking for prog array pokes
Add tracking of constant keys into tail call maps. The signature of
bpf_tail_call_proto is that arg1 is ctx, arg2 map pointer and arg3
is a index key. The direct call approach for tail calls can be enabled
if the verifier asserted that for all branches leading to the tail call
helper invocation, the map pointer and index key were both constant
and the same.
Tracking of map pointers we already do from prior work via c93552c443eb
("bpf: properly enforce index mask to prevent out-of-bounds speculation")
and 09772d92cd5a ("bpf: avoid retpoline for lookup/update/ delete calls
on maps").
Given the tail call map index key is not on stack but directly in the
register, we can add similar tracking approach and later in fixup_bpf_calls()
add a poke descriptor to the progs poke_tab with the relevant information
for the JITing phase.
We internally reuse insn->imm for the rewritten BPF_JMP | BPF_TAIL_CALL
instruction in order to point into the prog's poke_tab, and keep insn->imm
as 0 as indicator that current indirect tail call emission must be used.
Note that publishing to the tracker must happen at the end of fixup_bpf_calls()
since adding elements to the poke_tab reallocates its memory, so we need
to wait until its in final state.
Future work can generalize and add similar approach to optimize plain
array map lookups. Difference there is that we need to look into the key
value that sits on stack. For clarity in bpf_insn_aux_data, map_state
has been renamed into map_ptr_state, so we get map_{ptr,key}_state as
trackers.
Daniel Borkmann [Fri, 22 Nov 2019 20:07:58 +0000 (21:07 +0100)]
bpf: Add poke dependency tracking for prog array maps
This work adds program tracking to prog array maps. This is needed such
that upon prog array updates/deletions we can fix up all programs which
make use of this tail call map. We add ops->map_poke_{un,}track()
helpers to maps to maintain the list of programs and ops->map_poke_run()
for triggering the actual update.
bpf_array_aux is extended to contain the list head and poke_mutex in
order to serialize program patching during updates/deletions.
bpf_free_used_maps() will untrack the program shortly before dropping
the reference to the map. For clearing out the prog array once all urefs
are dropped we need to use schedule_work() to have a sleepable context.
The prog_array_map_poke_run() is triggered during updates/deletions and
walks the maintained prog list. It checks in their poke_tabs whether the
map and key is matching and runs the actual bpf_arch_text_poke() for
patching in the nop or new jmp location. Depending on the type of update,
we use one of BPF_MOD_{NOP_TO_JUMP,JUMP_TO_NOP,JUMP_TO_JUMP}.
Daniel Borkmann [Fri, 22 Nov 2019 20:07:57 +0000 (21:07 +0100)]
bpf: Add initial poke descriptor table for jit images
Add initial poke table data structures and management to the BPF
prog that can later be used by JITs. Also add an instance of poke
specific data for tail call maps; plan for later work is to extend
this also for BPF static keys.
Daniel Borkmann [Fri, 22 Nov 2019 20:07:56 +0000 (21:07 +0100)]
bpf: Move owner type, jited info into array auxiliary data
We're going to extend this with further information which is only
relevant for prog array at this point. Given this info is not used
in critical path, move it into its own structure such that the main
array map structure can be kept on diet.
Daniel Borkmann [Fri, 22 Nov 2019 20:07:55 +0000 (21:07 +0100)]
bpf: Move bpf_free_used_maps into sleepable section
We later on are going to need a sleepable context as opposed to plain
RCU callback in order to untrack programs we need to poke at runtime
and tracking as well as image update is performed under mutex.
Daniel Borkmann [Fri, 22 Nov 2019 20:07:54 +0000 (21:07 +0100)]
bpf, x86: Generalize and extend bpf_arch_text_poke for direct jumps
Add BPF_MOD_{NOP_TO_JUMP,JUMP_TO_JUMP,JUMP_TO_NOP} patching for x86
JIT in order to be able to patch direct jumps or nop them out. We need
this facility in order to patch tail call jumps and in later work also
BPF static keys.
selftests/bpf: Add BPF trampoline performance test
Add a test that benchmarks different ways of attaching BPF program to a kernel function.
Here are the results for 2.4Ghz x86 cpu on a kernel without mitigations:
$ ./test_progs -n 49 -v|grep events
task_rename base 2743K events per sec
task_rename kprobe 2419K events per sec
task_rename kretprobe 1876K events per sec
task_rename raw_tp 2578K events per sec
task_rename fentry 2710K events per sec
task_rename fexit 2685K events per sec
On a kernel with retpoline:
$ ./test_progs -n 49 -v|grep events
task_rename base 2401K events per sec
task_rename kprobe 1930K events per sec
task_rename kretprobe 1485K events per sec
task_rename raw_tp 2053K events per sec
task_rename fentry 2351K events per sec
task_rename fexit 2185K events per sec
All 5 approaches:
- kprobe/kretprobe in __set_task_comm()
- raw tracepoint in trace_task_rename()
- fentry/fexit in __set_task_comm()
are roughly equivalent.
__set_task_comm() by itself is quite fast, so any extra instructions add up.
Until BPF trampoline was introduced the fastest mechanism was raw tracepoint.
kprobe via ftrace was second best. kretprobe is slow due to trap. New
fentry/fexit methods via BPF trampoline are clearly the fastest and the
difference is more pronounced with retpoline on, since BPF trampoline doesn't
use indirect jumps.
====================
With latest llvm, bpf selftest test_progs, which has +alu32 enabled, failed for
strobemeta.o and a few other subtests. The reason is due to that
verifier did not provide better var_off.mask after jmp32 instructions.
This patch set addressed this issue and after the fix, test_progs passed
with alu32.
Patch #1 provided detailed explanation of the problem and the fix.
Patch #2 added three tests in test_verifier.
Changelog:
v1 -> v2:
- do not directly manipulate tnum.{value,mask} in __reg_bound_offset32(),
using tnum_lshift/tnum_rshift functions instead
- do __reg_bound_offset32() after regular 64bit __reg_bound_offset()
since the latter may give a better upper 32bit var_off, which can
be inherited by __reg_bound_offset32().
====================
Andrii Nakryiko [Thu, 21 Nov 2019 17:59:00 +0000 (09:59 -0800)]
selftests/bpf: Ensure core_reloc_kernel is reading test_progs's data only
test_core_reloc_kernel.c selftest is the only CO-RE test that reads and
returns for validation calling thread's information (pid, tgid, comm). Thus it
has to make sure that only test_prog's invocations are honored.
Yonghong Song [Thu, 21 Nov 2019 17:06:51 +0000 (09:06 -0800)]
selftests/bpf: Add verifier tests for better jmp32 register bounds
Three test cases are added.
Test 1: jmp32 'reg op imm'.
Test 2: jmp32 'reg op reg' where dst 'reg' has unknown constant
and src 'reg' has known constant
Test 3: jmp32 'reg op reg' where dst 'reg' has known constant
and src 'reg' has unknown constant
Andrii Nakryiko [Fri, 22 Nov 2019 00:35:27 +0000 (16:35 -0800)]
libbpf: Fix bpf_object name determination for bpf_object__open_file()
If bpf_object__open_file() gets path like "some/dir/obj.o", it should derive
BPF object's name as "obj" (unless overriden through opts->object_name).
Instead, due to using `path` as a fallback value for opts->obj_name, path is
used as is for object name, so for above example BPF object's name will be
verbatim "some/dir/obj", which leads to all sorts of troubles, especially when
internal maps are concern (they are using up to 8 characters of object name).
Fix that by ensuring object_name stays NULL, unless overriden.
Yonghong Song [Thu, 21 Nov 2019 17:06:50 +0000 (09:06 -0800)]
bpf: Provide better register bounds after jmp32 instructions
With latest llvm (trunk https://github.com/llvm/llvm-project),
test_progs, which has +alu32 enabled, failed for strobemeta.o.
The verifier output looks like below with edit to replace large
decimal numbers with hex ones.
193: (85) call bpf_probe_read_user_str#114
R0=inv(id=0)
194: (26) if w0 > 0x1 goto pc+4
R0_w=inv(id=0,umax_value=0xffffffff00000001)
195: (6b) *(u16 *)(r7 +80) = r0
196: (bc) w6 = w0
R6_w=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
197: (67) r6 <<= 32
R6_w=inv(id=0,smax_value=0x7fffffff00000000,umax_value=0xffffffff00000000,
var_off=(0x0; 0xffffffff00000000))
198: (77) r6 >>= 32
R6=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
201: (79) r8 = *(u64 *)(r10 -416)
R8_w=map_value(id=0,off=40,ks=4,vs=13872,imm=0)
202: (0f) r8 += r6
R8_w=map_value(id=0,off=40,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
203: (07) r8 += 9696
R8_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
255: (bf) r1 = r8
R1_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=0xffffffff,var_off=(0x0; 0xffffffff))
...
257: (85) call bpf_probe_read_user_str#114
R1 unbounded memory access, make sure to bounds check any array access into a map
The value range for register r6 at insn 198 should be really just 0/1.
The umax_value=0xffffffff caused later verification failure.
After jmp instructions, the current verifier already tried to use just
obtained information to get better register range. The current mechanism is
for 64bit register only. This patch implemented to tighten the range
for 32bit sub-registers after jmp32 instructions.
With the patch, we have the below range ranges for the
above code sequence:
193: (85) call bpf_probe_read_user_str#114
R0=inv(id=0)
194: (26) if w0 > 0x1 goto pc+4
R0_w=inv(id=0,smax_value=0x7fffffff00000001,umax_value=0xffffffff00000001,
var_off=(0x0; 0xffffffff00000001))
195: (6b) *(u16 *)(r7 +80) = r0
196: (bc) w6 = w0
R6_w=inv(id=0,umax_value=0xffffffff,var_off=(0x0; 0x1))
197: (67) r6 <<= 32
R6_w=inv(id=0,umax_value=0x100000000,var_off=(0x0; 0x100000000))
198: (77) r6 >>= 32
R6=inv(id=0,umax_value=1,var_off=(0x0; 0x1))
...
201: (79) r8 = *(u64 *)(r10 -416)
R8_w=map_value(id=0,off=40,ks=4,vs=13872,imm=0)
202: (0f) r8 += r6
R8_w=map_value(id=0,off=40,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
203: (07) r8 += 9696
R8_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
...
255: (bf) r1 = r8
R1_w=map_value(id=0,off=9736,ks=4,vs=13872,umax_value=1,var_off=(0x0; 0x1))
...
257: (85) call bpf_probe_read_user_str#114
...
At insn 194, the register R0 has better var_off.mask and smax_value.
Especially, the var_off.mask ensures later lshift and rshift
maintains proper value range.
xdp: Fix cleanup on map free for devmap_hash map type
Tetsuo pointed out that it was not only the device unregister hook that was
broken for devmap_hash types, it was also cleanup on map free. So better
fix this as well.
While we're at it, there's no reason to allocate the netdev_map array for
DEVMAP_HASH, so skip that and adjust the cost accordingly.
Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
====================
This patch set salvages all the non-extern-specific changes out of blocked
externs patch set ([0]). In addition to small clean ups, it also refactors
libbpf's handling of relocations and allows support for global (non-static)
variables.
Andrii Nakryiko [Wed, 20 Nov 2019 00:35:48 +0000 (16:35 -0800)]
selftests/bpf: Integrate verbose verifier log into test_progs
Add exra level of verboseness, activated by -vvv argument. When -vv is
specified, verbose libbpf and verifier log (level 1) is output, even for
successful tests. With -vvv, verifier log goes to level 2.
This is extremely useful to debug verifier failures, as well as just see the
state and flow of verification. Before this, you'd have to go and modify
load_program()'s source code inside libbpf to specify extra log_level flags,
which is suboptimal to say the least.
Currently -vv and -vvv triggering verifier output is integrated into
test_stub's bpf_prog_load as well as bpf_verif_scale.c tests.
Andrii Nakryiko [Thu, 21 Nov 2019 07:07:43 +0000 (23:07 -0800)]
libbpf: Support initialized global variables
Initialized global variables are no different in ELF from static variables,
and don't require any extra support from libbpf. But they are matching
semantics of global data (backed by BPF maps) more closely, preventing
LLVM/Clang from aggressively inlining constant values and not requiring
volatile incantations to prevent those. This patch enables global variables.
It still disables uninitialized variables, which will be put into special COM
(common) ELF section, because BPF doesn't allow uninitialized data to be
accessed.
Jakub Kicinski [Tue, 19 Nov 2019 10:50:10 +0000 (10:50 +0000)]
selftests, bpftool: Skip the build test if not in tree
If selftests are copied over to another machine/location
for execution the build test of bpftool will obviously
not work, since the sources are not copied.
Skip it if we can't find bpftool's Makefile.
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20191119105010.19189-3-quentin.monnet@netronome.com
Quentin Monnet [Tue, 19 Nov 2019 10:50:09 +0000 (10:50 +0000)]
selftests, bpftool: Set EXIT trap after usage function
The trap on EXIT is used to clean up any temporary directory left by the
build attempts. It is not needed when the user simply calls the script
with its --help option, and may not be needed either if we add checks
(e.g. on the availability of bpftool files) before the build attempts.
Let's move this trap and related variables lower down in the code, so
that we don't accidentally change the value returned from the script
on early exits at pre-checks.
Andrii Nakryiko [Thu, 21 Nov 2019 07:07:41 +0000 (23:07 -0800)]
libbpf: Refactor relocation handling
Relocation handling code is convoluted and unnecessarily deeply nested. Split
out per-relocation logic into separate function. Also refactor the logic to be
more a sequence of per-relocation type checks and processing steps, making it
simpler to follow control flow. This makes it easier to further extends it to
new kinds of relocations (e.g., support for extern variables).
This patch also makes relocation's section verification more robust.
Previously relocations against not yet supported externs were silently ignored
because of obj->efile.text_shndx was zero, when all BPF programs had custom
section names and there was no .text section. Also, invalid LDIMM64 relocations
against non-map sections were passed through, if they were pointing to a .text
section (or 0, which is invalid section). All these bugs are fixed within this
refactoring and checks are made more appropriate for each type of relocation.
Quentin Monnet [Tue, 19 Nov 2019 10:56:26 +0000 (10:56 +0000)]
tools, bpf: Fix build for 'make -s tools/bpf O=<dir>'
Building selftests with 'make TARGETS=bpf kselftest' was fixed in commit 55d554f5d140 ("tools: bpf: Use !building_out_of_srctree to determine
srctree"). However, by updating $(srctree) in tools/bpf/Makefile for
in-tree builds only, we leave out the case where we pass an output
directory to build BPF tools, but $(srctree) is not set. This
typically happens for:
$ make -s tools/bpf O=/tmp/foo
Makefile:40: /tools/build/Makefile.feature: No such file or directory
Fix it by updating $(srctree) in the Makefile not only for out-of-tree
builds, but also if $(srctree) is empty.
Detected with test_bpftool_build.sh.
Fixes: 55d554f5d140 ("tools: bpf: Use !building_out_of_srctree to determine srctree") Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Link: https://lore.kernel.org/bpf/20191119105626.21453-1-quentin.monnet@netronome.com
Andrii Nakryiko [Thu, 21 Nov 2019 07:07:40 +0000 (23:07 -0800)]
selftests/bpf: Ensure no DWARF relocations for BPF object files
Add -mattr=dwarfris attribute to llc to avoid having relocations against DWARF
data. These relocations make it impossible to inspect DWARF contents: all
strings are invalid.
Quentin Monnet [Tue, 19 Nov 2019 11:17:06 +0000 (11:17 +0000)]
tools, bpftool: Fix warning on ignored return value for 'read'
When building bpftool, a warning was introduced by commit a94364603610
("bpftool: Allow to read btf as raw data"), because the return value
from a call to 'read()' is ignored. Let's address it.
Eric Dumazet [Wed, 20 Nov 2019 01:14:51 +0000 (12:14 +1100)]
powerpc: Add const qual to local_read() parameter
A patch in net-next triggered a compile error on powerpc:
include/linux/u64_stats_sync.h: In function 'u64_stats_read':
include/asm-generic/local64.h:30:37: warning: passing argument 1 of 'local_read' discards 'const' qualifier from pointer target type
This seems reasonable to relax powerpc local_read() requirements.
Fixes: 316580b69d0a ("u64_stats: provide u64_stats_t type") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: kbuild test robot <lkp@intel.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Tested-by: Stephen Rothwell <sfr@canb.auug.org.au> # build only Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Jakub Kicinski [Sun, 24 Nov 2019 22:50:43 +0000 (14:50 -0800)]
Merge branch 'bnxt_en-Updates'
Michael Chan says:
====================
bnxt_en: Updates.
This patchset contains these main features:
1. Add the proper logic to support suspend/resume on the new 57500
chips.
2. Allow Phy configurations from user on a Multihost function if
supported by fw.
3. devlink NVRAM flashing support.
4. Add a couple of chip IDs, PHY loopback enhancement, and provide
more RSS contexts to VFs.
v2: Dropped the devlink info patches to address some feedback
and resubmit for the 5.6 kernel.
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:49 +0000 (22:30 -0500)]
bnxt_en: Allow PHY settings on multi-function or NPAR PFs if allowed by FW.
Currently, the driver does not allow PHY settings on a multi-function or
NPAR NIC whose port is shared by more than one function. Newer
firmware now allows PHY settings on some of these NICs. Check for
this new firmware setting and allow the user to set the PHY settings
accordingly.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:48 +0000 (22:30 -0500)]
bnxt_en: Add async. event logic for PHY configuration changes.
If the link settings have been changed by another function sharing the
port, firmware will send us an async. message. In response, we will
call the new bnxt_init_ethtool_link_settings() function to update
the current settings.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:47 +0000 (22:30 -0500)]
bnxt_en: Refactor the initialization of the ethtool link settings.
Refactor this logic in bnxt_probe_phy() into a separate function
bnxt_init_ethtool_link_settings(). It used to be that the settable
link settings will never be changed without going through ethtool.
So we only needed to do this once in bnxt_probe_phy(). Now, another
function sharing the port may change it and we may need to re-initialize
the ethtool settings again in run-time.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:46 +0000 (22:30 -0500)]
bnxt_en: Skip disabling autoneg before PHY loopback when appropriate.
New firmware allows PHY loopback to be set without disabling autoneg
first. Check this capability and skip disabling autoneg when
it is supported by firmware. Using this scheme, loopback will
always work even if the PHY only supports autoneg.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:45 +0000 (22:30 -0500)]
bnxt_en: Assign more RSS context resources to the VFs.
The driver currently only assignes 1 RSS context to each VF. This works
for the Linux VF driver. But other drivers, such as DPDK, can make use
of additional RSS contexts. Modify the code to divide up and assign
RSS contexts to VFs just like other resources.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:44 +0000 (22:30 -0500)]
bnxt_en: Initialize context memory to the value specified by firmware.
Some chips that need host context memory as a backing store requires
the memory to be initialized to a non-zero value. Query the
value from firmware and initialize the context memory accordingly.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Vasundhara Volam [Sun, 24 Nov 2019 03:30:43 +0000 (22:30 -0500)]
bnxt_en: Fix suspend/resume path on 57500 chips
Driver calls HWRM_FUNC_RESET firmware call while resuming the device
which clears the context memory backing store. Because of which
allocating firmware resources would eventually fail. Fix it by freeing
all context memory during suspend and reallocate the memory during resume.
Call bnxt_hwrm_queue_qportcfg() in resume path. This firmware call
is needed on the 57500 chips so that firmware will set up the proper
queue mapping in relation to the context memory.
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Vasundhara Volam [Sun, 24 Nov 2019 03:30:42 +0000 (22:30 -0500)]
bnxt_en: Send FUNC_RESOURCE_QCAPS command in bnxt_resume()
After driver unregister, firmware is erasing the information that
driver supports new resource management. Send FUNC_RESOURCE_QCAPS
command to inform the firmware that driver supports new resource
management while resuming from hibernation. Otherwise, we fallback
to the older resource allocation scheme.
Also, move driver register after sending FUNC_RESOURCE_QCAPS command
to be consistent with the normal initialization sequence.
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Vasundhara Volam [Sun, 24 Nov 2019 03:30:41 +0000 (22:30 -0500)]
bnxt_en: Combine 2 functions calling the same HWRM_DRV_RGTR fw command.
Everytime driver registers with firmware, driver is required to
register for async event notifications as well. These 2 calls
are done using the same firmware command and can be combined.
We are also missing the 2nd step to register for async events
in the suspend/resume path and this will fix it. Prior to this,
we were getting only default notifications.
ULP can register for additional async events for the RDMA driver,
so we add a parameter to the new function to only do step 2 when
it is called from ULP.
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Vasundhara Volam [Sun, 24 Nov 2019 03:30:40 +0000 (22:30 -0500)]
bnxt_en: Do driver unregister cleanup in bnxt_init_one() failure path.
In the bnxt_init_one() failure path, if the driver has already called
firmware to register the driver, it is not undoing the driver
registration. Add this missing step to unregister for correctness,
so that the firmware knows that the driver has unloaded.
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:39 +0000 (22:30 -0500)]
bnxt_en: Disable/enable Bus master during suspend/resume.
Disable Bus master during suspend to prevent DMAs after the device
goes into D3hot state. The new 57500 devices may continue to DMA
from context memory after the system goes into D3hot state. This
may cause some PCIe errors on some system. Re-enable it during resume.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Michael Chan [Sun, 24 Nov 2019 03:30:38 +0000 (22:30 -0500)]
bnxt_en: Add chip IDs for 57452 and 57454 chips.
Fix BNXT_CHIP_NUM_5645X() to include 57452 and 56454 chip IDs, so
that these chips will be properly classified as P4 chips to take
advantage of the P4 fixes and features.
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Maxime Bizon [Sat, 19 Oct 2019 19:24:11 +0000 (15:24 -0400)]
cramfs: fix usage on non-MTD device
When both CONFIG_CRAMFS_MTD and CONFIG_CRAMFS_BLOCKDEV are enabled, if
we fail to mount on MTD, we don't try on block device.
Note: this relies upon cramfs_mtd_fill_super() leaving no side
effects on fc state in case of failure; in general, failing
get_tree_...() does *not* mean "fine to try again"; e.g. parsed
options might've been consumed by fill_super callback and freed
on failure.
Fixes: 74f78fc5ef43 ("vfs: Convert cramfs to use the new mount API") Signed-off-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
hv_netvsc: make recording RSS hash depend on feature flag
The recording of RSS hash should be controlled by NETIF_F_RXHASH.
Fixes: 1fac7ca4e63b ("hv_netvsc: record hardware hash in skb") Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Xin Long [Sat, 23 Nov 2019 03:56:49 +0000 (11:56 +0800)]
sctp: cache netns in sctp_ep_common
This patch is to fix a data-race reported by syzbot:
BUG: KCSAN: data-race in sctp_assoc_migrate / sctp_hash_obj
write to 0xffff8880b67c0020 of 8 bytes by task 18908 on cpu 1:
sctp_assoc_migrate+0x1a6/0x290 net/sctp/associola.c:1091
sctp_sock_migrate+0x8aa/0x9b0 net/sctp/socket.c:9465
sctp_accept+0x3c8/0x470 net/sctp/socket.c:4916
inet_accept+0x7f/0x360 net/ipv4/af_inet.c:734
__sys_accept4+0x224/0x430 net/socket.c:1754
__do_sys_accept net/socket.c:1795 [inline]
__se_sys_accept net/socket.c:1792 [inline]
__x64_sys_accept+0x4e/0x60 net/socket.c:1792
do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x44/0xa9
read to 0xffff8880b67c0020 of 8 bytes by task 12003 on cpu 0:
sctp_hash_obj+0x4f/0x2d0 net/sctp/input.c:894
rht_key_get_hash include/linux/rhashtable.h:133 [inline]
rht_key_hashfn include/linux/rhashtable.h:159 [inline]
rht_head_hashfn include/linux/rhashtable.h:174 [inline]
head_hashfn lib/rhashtable.c:41 [inline]
rhashtable_rehash_one lib/rhashtable.c:245 [inline]
rhashtable_rehash_chain lib/rhashtable.c:276 [inline]
rhashtable_rehash_table lib/rhashtable.c:316 [inline]
rht_deferred_worker+0x468/0xab0 lib/rhashtable.c:420
process_one_work+0x3d4/0x890 kernel/workqueue.c:2269
worker_thread+0xa0/0x800 kernel/workqueue.c:2415
kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352
It was caused by rhashtable access asoc->base.sk when sctp_assoc_migrate
is changing its value. However, what rhashtable wants is netns from asoc
base.sk, and for an asoc, its netns won't change once set. So we can
simply fix it by caching netns since created.
Fixes: d6c0256a60e6 ("sctp: add the rhashtable apis for sctp global transport hashtable") Reported-by: syzbot+e3b35fe7918ff0ee474e@syzkaller.appspotmail.com Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Navid Emamdoost [Fri, 22 Nov 2019 22:17:56 +0000 (16:17 -0600)]
sctp: Fix memory leak in sctp_sf_do_5_2_4_dupcook
In the implementation of sctp_sf_do_5_2_4_dupcook() the allocated
new_asoc is leaked if security_sctp_assoc_request() fails. Release it
via sctp_association_free().
Russell King [Thu, 21 Nov 2019 00:36:22 +0000 (00:36 +0000)]
net: phylink: rename mac_link_state() op to mac_pcs_get_state()
Rename the mac_link_state() method to mac_pcs_get_state() to make it
clear that it should be returning the MACs PCS current state, which
is used for inband negotiation rather than just reading back what the
MAC has been configured for. Update the documentation to explicitly
mention that this is for inband.
We drop the return value as well; most of phylink doesn't check the
return value and it is not clear what it should do on error - instead
arrange for state->link to be false.
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Linus Torvalds [Sat, 23 Nov 2019 21:02:18 +0000 (13:02 -0800)]
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull last minute virtio bugfixes from Michael Tsirkin:
"Minor bugfixes all over the place"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
virtio_balloon: fix shrinker count
virtio_balloon: fix shrinker scan number of pages
virtio_console: allocate inbufs in add_port() only if it is needed
virtio_ring: fix return code on DMA mapping fails
Taehee Yoo [Fri, 22 Nov 2019 08:15:19 +0000 (08:15 +0000)]
net: use rhashtable_lookup() instead of rhashtable_lookup_fast()
rhashtable_lookup_fast() internally calls rcu_read_lock() then,
calls rhashtable_lookup(). So if rcu_read_lock() is already held,
rhashtable_lookup() is enough.
Signed-off-by: Taehee Yoo <ap420073@gmail.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Jakub Kicinski [Sat, 23 Nov 2019 20:00:54 +0000 (12:00 -0800)]
Merge tag 'wireless-drivers-next-2019-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next
Kalle Valo says:
====================
wireless-drivers-next patches for v5.5
Last set of patches for v5.5. Major features here 802.11ax support for
qtnfmac and airtime fairness support to mt76. And naturally smaller
fixes and improvements all over.
Major changes:
qtnfmac
* add 802.11ax support in AP mode
* enable offload bridging support
iwlwifi
* support TX/RX antennas reporting
mt76
* mt7615 smart carrier sense support
* aggregation statistics via debugfs
* airtime fairness (ATF) support
* mt76x0 OF mac address support
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Robert Schwebel [Fri, 22 Nov 2019 07:43:02 +0000 (08:43 +0100)]
docs: networking: nfc: change headlines to sphinx syntax
The headlines in this file do are not in the standard kernel docu-
mentation headline format. Change it, so this file can be switched to
rst in the future.
Signed-off-by: Robert Schwebel <r.schwebel@pengutronix.de> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Russell King [Fri, 22 Nov 2019 15:23:23 +0000 (15:23 +0000)]
net: phy: initialise phydev speed and duplex sanely
When a phydev is created, the speed and duplex are set to zero and
-1 respectively, rather than using the predefined SPEED_UNKNOWN and
DUPLEX_UNKNOWN constants.
There is a window at initialisation time where we may report link
down using the 0/-1 values. Tidy this up and use the predefined
constants, so debug doesn't complain with:
Russell King [Fri, 22 Nov 2019 12:37:08 +0000 (12:37 +0000)]
net: phy: remove phy_ethtool_sset()
There are no users of phy_ethtool_sset() in the kernel anymore, and
as of commit 3c1bcc8614db ("net: ethernet: Convert phydev advertize
and supported from u32 to link mode"), the implementation is slightly
buggy - it doesn't correctly check the masked advertising mask as it
used to.
Remove it, and update the phy documentation to refer to its replacement
function.
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Jakub Kicinski [Sat, 23 Nov 2019 17:54:58 +0000 (09:54 -0800)]
Revert "bpf: Emit audit messages upon successful prog load and unload"
This commit reverts commit 91e6015b082b ("bpf: Emit audit messages
upon successful prog load and unload") and its follow up commit 7599a896f2e4 ("audit: Move audit_log_task declaration under
CONFIG_AUDITSYSCALL") as requested by Paul Moore. The change needs
close review on linux-audit, tests etc.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Commit 37e4c997dadf ("KVM: VMX: validate individual bits of guest
MSR_IA32_FEATURE_CONTROL") broke the KVM_SET_MSRS ABI by instituting
new constraints on the data values that kvm would accept for the guest
MSR, IA32_FEATURE_CONTROL. Perhaps these constraints should have been
opt-in via a new KVM capability, but they were applied
indiscriminately, breaking at least one existing hypervisor.
Relax the constraints to allow either or both of
FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX and
FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX to be set when nVMX is
enabled. This change is sufficient to fix the aforementioned breakage.
Fixes: 37e4c997dadf ("KVM: VMX: validate individual bits of guest MSR_IA32_FEATURE_CONTROL") Signed-off-by: Jim Mattson <jmattson@google.com> Reviewed-by: Liran Alon <liran.alon@oracle.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: x86: Grab KVM's srcu lock when setting nested state
Acquire kvm->srcu for the duration of ->set_nested_state() to fix a bug
where nVMX derefences ->memslots without holding ->srcu or ->slots_lock.
The other half of nested migration, ->get_nested_state(), does not need
to acquire ->srcu as it is a purely a dump of internal KVM (and CPU)
state to userspace.
Detected as an RCU lockdep splat that is 100% reproducible by running
KVM's state_test selftest with CONFIG_PROVE_LOCKING=y. Note that the
failing function, kvm_is_visible_gfn(), is only checking the validity of
a gfn, it's not actually accessing guest memory (which is more or less
unsupported during vmx_set_nested_state() due to incorrect MMU state),
i.e. vmx_set_nested_state() itself isn't fundamentally broken. In any
case, setting nested state isn't a fast path so there's no reason to go
out of our way to avoid taking ->srcu.
KVM: x86: Open code shared_msr_update() in its only caller
Fold shared_msr_update() into its sole user to eliminate its pointless
bounds check, its godawful printk, its misleading comment (it's called
under a global lock), and its woefully inaccurate name.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: x86: Remove a spurious export of a static function
A recent change inadvertently exported a static function, which results
in modpost throwing a warning. Fix it.
Fixes: cbbaa2727aa3 ("KVM: x86: fix presentation of TSX feature in ARCH_CAPABILITIES") Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com> Cc: stable@vger.kernel.org Reviewed-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We need to improve this to show the source code line numbers in the
annotation view, so one can go from that program block to the annotation view
and see those source code line numbers straight away.
auxtrace/Intel PT:
Adrian Hunter:
- Add support for AUX area sampling, requires new functionality that
will land in 5.5, its already in tip.
This includes kernel capability querying so that it fails gracefully
with older kernels, duimping aux area samples in 'perf report -D' and
'perf script'.
perf.data:
Alexey Budankov:
- Fix decompression of PERF_RECORD_COMPRESSED records.
core:
Arnaldo Carvalho de Melo:
- Use the 'dcacheline' cmp routine to find the right DSOs taking into
account the 'maj', 'min', 'ino' and 'ino_generation', that got moved
from 'struct map' to 'struct dso', where it belongs.
This further reduces the size of 'struct map', there is still more
work to do to maybe get it to max one cacheline.
libtraceevent:
Hewenliang:
- Fix memory leakage in copy_filter_type().
Sudip Mukherjee:
- Fix header installation.
perf parse:
Ian Rogers :
- Fix potential memory leak when handling tracepoint errors, found using
LLVM's libFuzzer.
perf probe:
Colin Ian King:
- Fix spelling mistake "addrees" -> "address".
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Part of the documentation is taken from the README of the userspace
utils (https://github.com/vitorafsr/i8kutils). The license is GPL-2+
and the author Massimo Dal Zotto is already credited as author of
the module. Therefore there should be no copyright problem.
I also added a paragraph with specific information on the experimental
support for automatic BIOS fan control.
hwmon: (dell-smm) Add support for disabling automatic BIOS fan control
This patch exports standard hwmon pwmX_enable sysfs attribute for
enabling or disabling automatic fan control by BIOS. Standard value
"1" is for disabling automatic BIOS fan control and value "2" for
enabling.
By default BIOS auto mode is enabled by laptop firmware.
When BIOS auto mode is enabled, custom fan speed value (set via hwmon
pwmX sysfs attribute) is overwritten by SMM in few seconds and
therefore any custom settings are without effect. So this is reason
why implementing option for disabling BIOS auto mode is needed.
So finally this patch allows kernel to set and control fan speed on
laptops, but it can be dangerous (like setting speed of other fans).
The SMM commands to enable or disable automatic fan control are not
documented and are not the same on all Dell laptops. Therefore a
whitelist is used to send the correct codes only on laptopts for which
they are known.
This patch was originally developed by Pali Rohár; later Giovanni
Mascellani implemented the whitelist.
Jakub Kicinski [Sat, 23 Nov 2019 01:51:14 +0000 (17:51 -0800)]
Merge branch 'sfc-ARFS-expiry-improvements'
Edward Cree says:
====================
A series of changes to how we check filters for expiry, manage how much
of that work to do & when, etc.
Prompted by some pathological behaviour under heavy load, which was Reported-by: David Ahern <dahern@digitalocean.com>
====================
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Edward Cree [Fri, 22 Nov 2019 17:57:40 +0000 (17:57 +0000)]
sfc: do ARFS expiry work occasionally even without NAPI poll
If there's no traffic on a channel, its ARFS expiry work will never get
scheduled by efx_poll() as that isn't being run.
So make efx_filter_rfs_expire() reschedule itself to run after 30 seconds.
Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Edward Cree [Fri, 22 Nov 2019 17:57:19 +0000 (17:57 +0000)]
sfc: suppress MCDI errors from ARFS
In high connection count usage, the NIC's filter table may be filled with
sufficiently many ARFS filters that further insertions fail. As this
does not represent a correctness issue, do not log the resulting MCDI
errors. Add a debug-level message under the (by default disabled)
rx_status category instead; and take the opportunity to do a little extra
expiry work.
Since there are now multiple workitems able to call __efx_filter_rfs_expire
on a given channel, it is possible for them to race and thus pass quotas
which, combined, exceed rfs_filter_count. Thus, don't WARN_ON if we loop
all the way around the table with quota left over.
Signed-off-by: Edward Cree <ecree@solarflare.com> Tested-by: David Ahern <dahern@digitalocean.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>