Remove continue statement which does not have real effect
as no actions are to be taken post continue.
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240318114057.3831274-1-tejas.upadhyay@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Added new compression flag that was recently documented, in
addition fix some typos and clarify the sid_attr_data struct
definition.
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
The offset field in the compression header is 32 bits not 16.
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Reported-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
Move the following:
extern mempool_t *cifs_sm_req_poolp;
extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
extern bool disable_legacy_dialects;
from various .c files to cifsglob.h.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
-----BEGIN PGP SIGNATURE-----
iQEzBAABCAAdFiEEIw+MvkEiF49krdp9F0NaE2wMflgFAmX6tp4ACgkQF0NaE2wM
flgzWQf/VV3cQmOGjgegxSyi//kq5jmy6T8trYd4jeIicYFxAW1Xjq9cO7iEFTQZ
N4efTnqo0kku/HW/3wMgoznDEise6z8E/RpbuS9pCBkCj+a4vnFP/4IemDlb58RU
oA0bgClk73b2xbF2x+btYLBmzszikSzGLD9CQkBHDanVV3FhipbrIRUI2qjK+F2L
/OWHQ02n3g7u7xuK3Fn7GMCQ8z8ZKM5le4Tlip4y2VvHmacLJ6tgXl8phodK1HPq
NpHRDUDzZnYVHeP9BaH66Z0eddzA6v74kpKoobk5ybbYEfS3VeBJzXl63C+NW/oG
u9xpWI+sNWbrPDfTtiCVaKu4F6RoKg==
=y1I0
-----END PGP SIGNATURE-----
Merge tag 'docs-6.9-2' of git://git.lwn.net/linux
Pull more documentation updates from Jonathan Corbet:
"A handful of late-arriving documentation fixes and enhancements"
* tag 'docs-6.9-2' of git://git.lwn.net/linux:
docs: verify/bisect: remove a level of indenting
docs: verify/bisect: drop 'v' prefix, EOL aspect, and assorted fixes
docs: verify/bisect: check taint flag
docs: verify/bisect: improve install instructions
docs: handling-regressions.rst: Update regzbot command fixed-by to fix
docs: *-regressions.rst: Add colon to regzbot commands
doc: Fix typo in admin-guide/cifs/introduction.rst
README: Fix spelling
Charlie Jenkins <charlie@rivosinc.com> says:
On riscv, mmap currently returns an address from the largest address
space that can fit entirely inside of the hint address. This makes it
such that the hint address is almost never returned. This patch raises
the mappable area up to and including the hint address. This allows mmap
to often return the hint address, which allows a performance improvement
over searching for a valid address as well as making the behavior more
similar to other architectures.
Note that a previous patch introduced stronger semantics compared to
other architectures for riscv mmap. On riscv, mmap will not use bits in
the upper bits of the virtual address depending on the hint address. On
other architectures, a random address is returned in the address space
requested. On all architectures the hint address will be returned if it
is available. This allows riscv applications to configure how many bits
in the virtual address should be left empty. This has the two benefits
of being able to request address spaces that are smaller than the
default and doesn't require the application to know the page table
layout of riscv.
* b4-shazam-merge:
docs: riscv: Define behavior of mmap
selftests: riscv: Generalize mm selftests
riscv: mm: Use hint address in mmap if available
Link: https://lore.kernel.org/r/20240130-use_mmap_hint_address-v3-0-8a655cfa8bcb@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Add an implementation of cts(cbc(aes)) accelerated using the Zvkned
RISC-V vector crypto extension. This is mainly useful for fscrypt,
where cts(cbc(aes)) is the "default" filenames encryption algorithm. In
that use case, typically most messages are short and are block-aligned.
The CBC-CTS variant implemented is CS3; this is the variant Linux uses.
To perform well on short messages, the new implementation processes the
full message in one call to the assembly function if the data is
contiguous. Otherwise it falls back to CBC operations followed by CTS
at the end. For decryption, to further improve performance on short
messages, especially block-aligned messages, the CBC-CTS assembly
function parallelizes the AES decryption of all full blocks. This
improves on the arm64 implementation of cts(cbc(aes)), which always
splits the CBC part(s) from the CTS part, doing the AES decryptions for
the last two blocks serially and usually loading the round keys twice.
Tested in QEMU with CONFIG_CRYPTO_MANAGER_EXTRA_TESTS=y.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20240213055442.35954-1-ebiggers@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Since CBC decryption is parallelizable, make the RISC-V implementation
of AES-CBC decryption process multiple blocks at a time, instead of
processing the blocks one by one. This should improve performance.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20240208060851.154129-1-ebiggers@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
We used to emit a flush_icache_all() whenever a dirty executable
mapping is set in the page table but we can instead call
flush_icache_mm() which will only send IPIs to cores that currently run
this mm and add a deferred icache flush to the others.
The number of calls to sbi_remote_fence_i() (tested without IPI
support):
With a simple buildroot rootfs:
* Before: ~5k
* After : 4 (!)
Tested on HW, the boot to login is ~4.5% faster.
With an ubuntu rootfs:
* Before: ~24k
* After : ~13k
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240202124711.256146-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
As noted in the "Deprecated Interfaces, Language Features, Attributes,
and Conventions" documentation [1], size calculations (especially
multiplication) should not be performed in memory allocator (or similar)
function arguments due to the risk of them overflowing. This could lead
to values wrapping around and a smaller allocation being made than the
caller was expecting. Using those allocations could lead to linear
overflows of heap memory and other misbehaviors.
So, use the purpose specific kcalloc() function instead of the argument
count * size in the kzalloc() function.
Also, it is preferred to use sizeof(*pointer) instead of sizeof(type)
due to the type of the variable can change and one needs not change the
former (unlike the latter).
Link: https://www.kernel.org/doc/html/next/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments [1]
Link: https://github.com/KSPP/linux/issues/162
Signed-off-by: Erick Archer <erick.archer@gmx.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20240120135400.4710-1-erick.archer@gmx.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Leonardo Bras <leobras@redhat.com> says:
I just saw the opportunity of optimizing the helper is_compat_task() by
introducing a compile-time test, and it made possible to remove some
#ifdef's without any loss of performance.
I also saw the possibility of removing the direct check of task flags from
general code, and concentrated it in asm/compat.h by creating a few more
helpers, which in the end helped optimize code.
arch_get_mmap_end() just got a simple improvement and some extra docs.
* b4-shazam-merge:
riscv: Introduce set_compat_task() in asm/compat.h
riscv: Introduce is_compat_thread() into compat.h
riscv: add compile-time test into is_compat_task()
riscv: Replace direct thread flag check with is_compat_task()
riscv: Improve arch_get_mmap_end() macro
Link: https://lore.kernel.org/r/20240103160024.70305-2-leobras@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Our definitions for bit 7 and bit 0 of ICL_PORT_TX_DW6 are
swapped. Functionally it doesn't matter as we always set both
bits, but let's rename the bits to match bspec 100%.
And while at it, add the definition for bits 1-6 as well, just
to have it all fully documented.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240308072400.28918-1-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Commit:
68fb3ca0e4 ("x86/percpu: Disable named address spaces for KASAN")
... disabled support for named address spaces with KASAN due to
the incompatibility issue between named AS and KASAN.
GCC 13.3 has fixed this issue (GCC PR sanitizer/111736) so the
support for named address spaces can be re-enabled with KASAN
for GCC compiler version >= 13.3.
Note that the patch considers GCC 14 to be fixed - if somebody is
using snapshots of the GCC 14 before the fix, they should upgrade.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20240320124603.566923-1-ubizjak@gmail.com
Move raw_percpu_xchg_op() together with this_percpu_xchg_op()
and trivially rename some internal variables to harmonize them
between macro implementations.
No functional changes intended.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20240320083127.493250-2-ubizjak@gmail.com
Rewrite percpu_xchg_op() using generic percpu primitives instead
of using asm. The new implementation is similar to local_xchg() and
allows the compiler to perform various optimizations: e.g. the
compiler is able to create fast path through the loop, according
to likely/unlikely annotations in percpu_try_cmpxchg_op().
No functional changes intended.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20240320083127.493250-1-ubizjak@gmail.com
Subbaraya Sundeep says:
====================
octeontx2-pf: RVU Mailbox fixes
This patchset fixes the problems related to RVU mailbox.
During long run tests some times VF commands like setting
MTU or toggling interface fails because VF mailbox is timedout
waiting for response from PF.
Below are the fixes
Patch 1: There are two types of messages in RVU mailbox namely up and down
messages. Down messages are synchronous messages where a PF/VF sends
a message to AF and AF replies back with response. UP messages are
notifications and are asynchronous like AF sending link events to
PF. When VF sends a down message to PF, PF forwards to AF and sends
the response from AF back to VF. PF has to forward VF messages since
there is no path in hardware for VF to send directly to AF.
There is one mailbox interrupt from AF to PF when raised could mean
two scenarios one is where AF sending reply to PF for a down message
sent by PF and another one is AF sending up message asynchronously
when link changed for that PF. Receiving the up message interrupt while
PF is in middle of forwarding down message causes mailbox errors.
Fix this by receiver detecting the type of message from the mbox data register
set by sender.
Patch 2:
During VF driver remove, VF has to wait until last message is
completed and then turn off mailbox interrupts from PF.
Patch 3:
Do not use ordered workqueue for message processing since multiple works are
queued simultaneously by all the VFs and PF link UP messages.
Patch 4:
When sending link event to VF by PF check whether VF is really up to
receive this message.
Patch 5:
In AF driver, use separate interrupt handlers for the AF-VF interrupt and
AF-PF interrupt. Sometimes both interrupts are raised to two CPUs at same
time and both CPUs execute same function at same time corrupting the data.
v2 changes:
Added missing mutex unlock in error path in patch 1
Refactored if else logic in patch 1 as suggested by Paolo Abeni
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
For PF to AF interrupt vector and VF to AF vector same
interrupt handler is registered which is causing race condition.
When two interrupts are raised to two CPUs at same time
then two cores serve same event corrupting the data.
Fixes: 7304ac4567 ("octeontx2-af: Add mailbox IRQ and msg handlers")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When PF sending link status messages to VF, it is possible
that by the time link_event_task work function is executed
VF might have brought down. Hence before sending VF link
status message check whether VF is up to receive it.
Fixes: ad513ed938 ("octeontx2-vf: Link event notification support")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Only one execution context for the workqueue used for PF and
VFs mailbox communication is incorrect since multiple works are
queued simultaneously by all the VFs and PF link UP messages.
Hence use default number of execution contexts by passing zero
as max_active to alloc_workqueue function. With this fix in place,
modify UP messages also to wait until completion.
Fixes: d424b6c024 ("octeontx2-pf: Enable SRIOV and added VF mbox handling")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
During VF driver remove, a message is sent to detach VF
resources to PF but VF is not waiting until message is
complete. Also mailbox interrupts need to be turned off
after the detach resource message is complete. This patch
fixes that problem.
Fixes: 05fcc9e089 ("octeontx2-pf: Attach NIX and NPA block LFs")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A single line of interrupt is used to receive up notifications
and down reply messages from AF to PF (similarly from PF to its VF).
PF acts as bridge and forwards VF messages to AF and sends respsones
back from AF to VF. When an async event like link event is received
by up message when PF is in middle of forwarding VF message then
mailbox errors occur because PF state machine is corrupted.
Since VF is a separate driver or VF driver can be in a VM it is
not possible to serialize from the start of communication at VF.
Hence to differentiate between type of messages at PF this patch makes
sender to set mbox data register with distinct values for up and down
messages. Sender also checks whether previous interrupt is received
before triggering current interrupt by waiting for mailbox data register
to become zero.
Fixes: 5a6d7c9dae ("octeontx2-pf: Mailbox communication with AF")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The BOs in a bulk move must share all the same reservation object
to make sure that we lock the whole bulk during eviction.
Actually document and enforce that with a warning.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240312105555.3065-1-christian.koenig@amd.com
Due to an error during rebasing the patchset 320 MHz channel support got
broken. ath12k was setting the QoS bit instead of the correct flag.
WMI_PEER_EXT_320MHZ (0x2) is defined as an extended flag, replace
peer_flags by peer_flags_ext while sending peer data.
This affected both QCN9274 and WCN7850 which use the same flag.
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Fixes: 6734cf9b4c ("wifi: ath12k: peer assoc for 320 MHz")
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240314204651.11075-1-quic_alokad@quicinc.com
Some of the backported intel_uncore_read*() functions used the wrong
types. Change the function declarations accordingly.
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240314065221.1181158-1-luciano.coelho@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
There are some duplicate definitions in wmi.h, remove them.
No functional changes, compile tested only.
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240314021830.305021-1-quic_kangyang@quicinc.com
In tx completion, status desc is obtained from offsetting the address
from wbm ring. Having HTT_TX_WBM_COMP_STATUS_OFFSET(8) and reserved 8
bytes in status desc offsets the address twice and read the values
from the incorrect address. Hence, remove the
HTT_TX_WBM_COMP_STATUS_OFFSET from wbm completion address calculation.
Also this patch is applicable for WCN7850.
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Signed-off-by: Thiraviyam Mariyappan <quic_tmariyap@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://msgid.link/20240311180708.9334-1-quic_tmariyap@quicinc.com
Considering the caller of the GGTT functions should keep the
backing storage alive before the function completes, it's not
necessary to invalidate with the GGTT lock held. This just adds
latency for every user of the GGTT.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240306052002.311196-5-matthew.brost@intel.com
Add XE_BO_GGTT_INVALIDATE flag which indicates the GGTT should be
invalidated when a BO is added / removed from the GGTT. This is
typically set when a BO is used by the GuC as the GuC has GGTT TLBs.
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
[mlankhorst: Small fix to only inherit GGTT_INVALIDATE from src bo]
[mlankhorst: Remove _BIT from name]
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240306052002.311196-4-matthew.brost@intel.com
Only buffers mapped in the GGTT used by the GuC require an invalidation.
Display buffers do not require an invalidation. Delete the invalidatio
from display code and make invalidation a static function in xe_ggtt.c.
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240306052002.311196-3-matthew.brost@intel.com
The OV7251 sensor only has a single data lane, so 2 entries is not valid.
Fix this to be 1 entry as the schema specifies.
The schema validation doesn't catch this currently due to some limitations
in handling of arrays vs. matrices, but a fix is being worked on.
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
If due to a memory allocation failure mock_chain() returns NULL, it is
passed to dma_fence_enable_sw_signaling() resulting in NULL pointer
dereference there.
Call dma_fence_enable_sw_signaling() only if mock_chain() succeeds.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: d62c43a953 ("dma-buf: Enable signaling on fence for selftests")
Signed-off-by: Pavel Sakharov <p.sakharov@ispras.ru>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240319231527.1821372-1-p.sakharov@ispras.ru
Add git tree to manage all Realtek WiFi drivers except RTL8180 which is
old and orphan.
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240319011925.6855-1-pkshih@realtek.com
Some hardware designs with multiple PCA954x devices use a reset GPIO
connected to all the muxes. Support this configuration by making use of
the reset controller framework which can deal with the shared reset
GPIOs. Fall back to the old GPIO descriptor method if the reset
controller framework is not enabled.
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Peter Rosin <peda@axentia.se>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
This patch is followed by eight commits featuring improvements to
the Nomadik controller, such as simplification of the IRQ logic,
renaming of the private data structure, more efficient use of
FIELD_PREP/GET, GENMASK, etc., better time measurement with
ktime, and more.
Two device trees have been added, but those need to be applied
elsewhere.
-----BEGIN PGP SIGNATURE-----
iIwEABYIADQWIQScDfrjQa34uOld1VLaeAVmJtMtbgUCZfLnNBYcYW5kaS5zaHl0
aUBrZXJuZWwub3JnAAoJENp4BWYm0y1uSSkBAKl75gzjiN2AglPaTUDfhCeux8yf
mISgvl4MWKCXXsZ5AQDjRiG+whrV7knOjS7L/r5owb30uF+Bv3d29sG4LVNsBQ==
=RubU
-----END PGP SIGNATURE-----
Merge tag 'i2c-host-6.9-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux into i2c/for-mergewindow
Théo adds support for the Mobileye EyeQ5-I2C in the bindings.
This patch is followed by eight commits featuring improvements to
the Nomadik controller, such as simplification of the IRQ logic,
renaming of the private data structure, more efficient use of
FIELD_PREP/GET, GENMASK, etc., better time measurement with
ktime, and more.
When benchmarking with multiple threads (-pN, where N>1), we start
contending on single atomic counter that both BPF trigger benchmarks are
using, as well as "baseline" tests in user space (trig-base and
trig-uprobe-base benchmarks). As such, we start bottlenecking on
something completely irrelevant to benchmark at hand.
Scale counting up by using per-CPU counters on BPF side. On use space
side we do the next best thing: hash thread ID to approximate per-CPU
behavior. It seems to work quite well in practice.
To demonstrate the difference, I ran three benchmarks with 1, 2, 4, 8,
16, and 32 threads:
- trig-uprobe-base (no syscalls, pure tight counting loop in user-space);
- trig-base (get_pgid() syscall, atomic counter in user-space);
- trig-fentry (syscall to trigger fentry program, atomic uncontended per-CPU
counter on BPF side).
Command used:
for b in uprobe-base base fentry; do \
for p in 1 2 4 8 16 32; do \
printf "%-11s %2d: %s\n" $b $p \
"$(sudo ./bench -w2 -d5 -a -p$p trig-$b | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)"; \
done; \
done
Before these changes, aggregate throughput across all threads doesn't
scale well with number of threads, it actually even falls sharply for
uprobe-base due to a very high contention:
uprobe-base 1: 138.998 ± 0.650M/s
uprobe-base 2: 70.526 ± 1.147M/s
uprobe-base 4: 63.114 ± 0.302M/s
uprobe-base 8: 54.177 ± 0.138M/s
uprobe-base 16: 45.439 ± 0.057M/s
uprobe-base 32: 37.163 ± 0.242M/s
base 1: 16.940 ± 0.182M/s
base 2: 19.231 ± 0.105M/s
base 4: 21.479 ± 0.038M/s
base 8: 23.030 ± 0.037M/s
base 16: 22.034 ± 0.004M/s
base 32: 18.152 ± 0.013M/s
fentry 1: 14.794 ± 0.054M/s
fentry 2: 17.341 ± 0.055M/s
fentry 4: 23.792 ± 0.024M/s
fentry 8: 21.557 ± 0.047M/s
fentry 16: 21.121 ± 0.004M/s
fentry 32: 17.067 ± 0.023M/s
After these changes, we see almost perfect linear scaling, as expected.
The sub-linear scaling when going from 8 to 16 threads is interesting
and consistent on my test machine, but I haven't investigated what is
causing it this peculiar slowdown (across all benchmarks, could be due
to hyperthreading effects, not sure).
uprobe-base 1: 139.980 ± 0.648M/s
uprobe-base 2: 270.244 ± 0.379M/s
uprobe-base 4: 532.044 ± 1.519M/s
uprobe-base 8: 1004.571 ± 3.174M/s
uprobe-base 16: 1720.098 ± 0.744M/s
uprobe-base 32: 3506.659 ± 8.549M/s
base 1: 16.869 ± 0.071M/s
base 2: 33.007 ± 0.092M/s
base 4: 64.670 ± 0.203M/s
base 8: 121.969 ± 0.210M/s
base 16: 207.832 ± 0.112M/s
base 32: 424.227 ± 1.477M/s
fentry 1: 14.777 ± 0.087M/s
fentry 2: 28.575 ± 0.146M/s
fentry 4: 56.234 ± 0.176M/s
fentry 8: 106.095 ± 0.385M/s
fentry 16: 181.440 ± 0.032M/s
fentry 32: 369.131 ± 0.693M/s
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240315213329.1161589-1-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The recent conversion to the automatic kfree() forgot to mark a
variable with __free(kfree), leading to memory leaks. Fix it.
Fixes: 1052d98822 ("ALSA: control: Use automatic cleanup of kfree()")
Reported-by: Mirsad Todorovac <mirsad.todorovac@alu.unizg.hr>
Closes: https://lore.kernel.org/r/c1e2ef3c-164f-4840-9b1c-f7ca07ca422a@alu.unizg.hr
Message-ID: <20240320062722.31325-1-tiwai@suse.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Commit d510296d33 ("bpftool: Use syscall/loader program in "prog load"
and "gen skeleton" command.") added new files to the list of objects to
compile in order to build the bootstrap version of bpftool. As far as I
can tell, these objects are unnecessary and were added by mistake; maybe
a draft version intended to add support for loading loader programs from
the bootstrap version. Anyway, we can remove these object files from the
list to make the bootstrap bpftool binary a tad smaller and faster to
build.
Fixes: d510296d33 ("bpftool: Use syscall/loader program in "prog load" and "gen skeleton" command.")
Signed-off-by: Quentin Monnet <qmo@kernel.org>
Message-ID: <20240320013457.44808-1-qmo@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When trying to load the pid_iter BPF program used to iterate over the
PIDs of the processes holding file descriptors to BPF links, we would
unconditionally silence libbpf in order to keep the output clean if the
kernel does not support iterators and loading fails.
Although this is the desirable behaviour in most cases, this may hide
bugs in the pid_iter program that prevent it from loading, and it makes
it hard to debug such load failures, even in "debug" mode. Instead, it
makes more sense to print libbpf's logs when we pass the -d|--debug flag
to bpftool, so that users get the logs to investigate failures without
having to edit bpftool's source code.
Signed-off-by: Quentin Monnet <qmo@kernel.org>
Message-ID: <20240320012241.42991-1-qmo@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Andrii Nakryiko says:
====================
BPF raw tracepoint support for BPF cookie
Add ability to specify and retrieve BPF cookie for raw tracepoint programs.
Both BTF-aware (SEC("tp_btf")) and non-BTF-aware (SEC("raw_tp")) are
supported, as they are exactly the same at runtime.
This issue recently came up in production use cases, where custom tried to
switch from slower classic tracepoints to raw tracepoints and ran into this
limitation. Luckily, it's not that hard to support this for raw_tp programs.
v2->v3:
- s/bpf_raw_tp_open/bpf_raw_tracepoint_open_opts/ (Alexei, Eduard);
v1->v2:
- fixed type definition for stubs of bpf_probe_{register,unregister};
- added __u32 :u32 and aligned raw_tp fields (Jiri);
- added Stanislav's ack.
====================
Link: https://lore.kernel.org/r/20240319233852.1977493-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add test validating BPF cookie can be passed during raw_tp/tp_btf
attachment and can be retried at runtime with bpf_get_attach_cookie()
helper.
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240319233852.1977493-6-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Wire up BPF cookie passing or raw_tp and tp_btf programs, both in
low-level and high-level APIs.
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240319233852.1977493-5-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Wire up BPF cookie for raw tracepoint programs (both BTF and non-BTF
aware variants). This brings them up to part w.r.t. BPF cookie usage
with classic tracepoint and fentry/fexit programs.
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240319233852.1977493-4-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>