diff options
| author | Jinjie Ruan <ruanjinjie@huawei.com> | 2026-01-28 11:19:33 +0800 |
|---|---|---|
| committer | Thomas Gleixner <tglx@kernel.org> | 2026-01-30 15:38:10 +0100 |
| commit | 31c9387d0d84bc1d643a0c30155b6d92d05c92fc (patch) | |
| tree | 455198e1fcb8e9381fd02fc444a1113ddb0a4979 /kernel/entry/syscall_user_dispatch.c | |
| parent | 578b21fd3ab2d9901ce40ed802e428a41a40610d (diff) | |
entry: Inline syscall_exit_work() and syscall_trace_enter()
After switching ARM64 to the generic entry code, a syscall_exit_work()
appeared as a profiling hotspot because it is not inlined.
Inlining both syscall_trace_enter() and syscall_exit_work() provides a
performance gain when any of the work items is enabled. With audit enabled
this results in a ~4% performance gain for perf bench basic syscall on
a kunpeng920 system:
| Metric | Baseline | Inlined | Change |
| ---------- | ----------- | ----------- | ------ |
| Total time | 2.353 [sec] | 2.264 [sec] | ↓3.8% |
| usecs/op | 0.235374 | 0.226472 | ↓3.8% |
| ops/sec | 4,248,588 | 4,415,554 | ↑3.9% |
Small gains can be observed on x86 as well, though the generated code
optimizes for the work case, which is counterproductive for high
performance scenarios where such entry/exit work is usually avoided.
Avoid this by marking the work check in syscall_enter_from_user_mode_work()
unlikely, which is what the corresponding check in the exit path does
already.
[ tglx: Massage changelog and add the unlikely() ]
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260128031934.3906955-14-ruanjinjie@huawei.com
Diffstat (limited to 'kernel/entry/syscall_user_dispatch.c')
| -rw-r--r-- | kernel/entry/syscall_user_dispatch.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index a9055eccb27e..d89dffcc2d64 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -2,6 +2,8 @@ /* * Copyright (C) 2020 Collabora Ltd. */ + +#include <linux/entry-common.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/ptrace.h> @@ -15,8 +17,6 @@ #include <asm/syscall.h> -#include "common.h" - static void trigger_sigsys(struct pt_regs *regs) { struct kernel_siginfo info; |