| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20251222114737.1334364-16-ruanjinjie@huawei.com>
Date: Mon, 22 Dec 2025 19:47:36 +0800
From: Jinjie Ruan <ruanjinjie@...wei.com>
To: <catalin.marinas@....com>, <will@...nel.org>, <oleg@...hat.com>,
<tglx@...utronix.de>, <peterz@...radead.org>, <luto@...nel.org>,
<shuah@...nel.org>, <kees@...nel.org>, <wad@...omium.org>,
<ruanjinjie@...wei.com>, <kevin.brodsky@....com>, <macro@...am.me.uk>,
<charlie@...osinc.com>, <akpm@...ux-foundation.org>, <ldv@...ace.io>,
<anshuman.khandual@....com>, <mark.rutland@....com>, <thuth@...hat.com>,
<song@...nel.org>, <ryan.roberts@....com>, <ada.coupriediaz@....com>,
<broonie@...nel.org>, <liqiang01@...inos.cn>, <pengcan@...inos.cn>,
<kmal@...k.li>, <dvyukov@...gle.com>, <richard.weiyang@...il.com>,
<reddybalavignesh9979@...il.com>, <linux-arm-kernel@...ts.infradead.org>,
<linux-kernel@...r.kernel.org>, <linux-kselftest@...r.kernel.org>
Subject: [PATCH v10 15/16] entry: Inline syscall_exit_work() and syscall_trace_enter()
After switch arm64 to Generic Entry, a new hotspot syscall_exit_work()
appeared because syscall_exit_work() is not inlined, so inline
syscall_exit_work(). Also inline syscall_trace_enter() to align with
syscall_exit_work().
On v6.19-rc1 with audit on, inline both syscall_trace_enter() and
syscall_exit_work() has 4% performance uplift on perf bench basic
syscall on kunpeng920 as below:
| Metric | W/O this patch | With this patch | 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% |
Signed-off-by: Jinjie Ruan <ruanjinjie@...wei.com>
---
include/linux/entry-common.h | 102 ++++++++++++++++++++++++++-
kernel/entry/common.h | 7 --
kernel/entry/syscall-common.c | 96 ++-----------------------
kernel/entry/syscall_user_dispatch.c | 4 +-
4 files changed, 106 insertions(+), 103 deletions(-)
delete mode 100644 kernel/entry/common.h
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 17171e8873fc..ad61a13bf24f 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -2,6 +2,7 @@
#ifndef __LINUX_ENTRYCOMMON_H
#define __LINUX_ENTRYCOMMON_H
+#include <linux/audit.h>
#include <linux/irq-entry-common.h>
#include <linux/livepatch.h>
#include <linux/ptrace.h>
@@ -64,7 +65,64 @@ static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs
}
#endif
-long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work);
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+ if (unlikely(audit_context())) {
+ unsigned long args[6];
+
+ syscall_get_arguments(current, regs, args);
+ audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+ }
+}
+
+void __trace_sys_enter(struct pt_regs *regs, long syscall);
+bool syscall_user_dispatch(struct pt_regs *regs);
+
+static __always_inline long syscall_trace_enter(struct pt_regs *regs, long syscall,
+ unsigned long work)
+{
+ long ret = 0;
+
+ /*
+ * Handle Syscall User Dispatch. This must comes first, since
+ * the ABI here can be something that doesn't make sense for
+ * other syscall_work features.
+ */
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (syscall_user_dispatch(regs))
+ return -1L;
+ }
+
+ /* Handle ptrace */
+ if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
+ ret = arch_ptrace_report_syscall_entry(regs);
+ if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
+ return -1L;
+ }
+
+ /* Do seccomp after ptrace, to catch any tracer changes. */
+ if (work & SYSCALL_WORK_SECCOMP) {
+ ret = __secure_computing();
+ if (ret == -1L)
+ return ret;
+ }
+
+ /* Either of the above might have changed the syscall number */
+ syscall = syscall_get_nr(current, regs);
+
+ if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
+ __trace_sys_enter(regs, syscall);
+ /*
+ * Probes or BPF hooks in the tracepoint may have changed the
+ * system call number as well.
+ */
+ syscall = syscall_get_nr(current, regs);
+ }
+
+ syscall_enter_audit(regs, syscall);
+
+ return ret ? : syscall;
+}
/**
* syscall_enter_from_user_mode_work - Check and handle work before invoking
@@ -131,6 +189,19 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
return ret;
}
+/*
+ * If SYSCALL_EMU is set, then the only reason to report is when
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
+ * instruction has been already reported in syscall_enter_from_user_mode().
+ */
+static __always_inline bool report_single_step(unsigned long work)
+{
+ if (work & SYSCALL_WORK_SYSCALL_EMU)
+ return false;
+
+ return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
+}
+
/**
* arch_ptrace_report_syscall_exit - Architecture specific
* ptrace_report_syscall_exit.
@@ -151,6 +222,8 @@ static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs
}
#endif
+void __trace_sys_exit(struct pt_regs *regs, long ret);
+
/**
* syscall_exit_work - Handle work before returning to user mode
* @regs: Pointer to current pt_regs
@@ -158,7 +231,32 @@ static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs
*
* Do one-time syscall specific work.
*/
-void syscall_exit_work(struct pt_regs *regs, unsigned long work);
+static __always_inline void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+{
+ bool step;
+
+ /*
+ * If the syscall was rolled back due to syscall user dispatching,
+ * then the tracers below are not invoked for the same reason as
+ * the entry side was not invoked in syscall_trace_enter(): The ABI
+ * of these syscalls is unknown.
+ */
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (unlikely(current->syscall_dispatch.on_dispatch)) {
+ current->syscall_dispatch.on_dispatch = false;
+ return;
+ }
+ }
+
+ audit_syscall_exit(regs);
+
+ if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
+ __trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+ step = report_single_step(work);
+ if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
+ arch_ptrace_report_syscall_exit(regs, step);
+}
/*
* Syscall specific exit to user mode preparation. Runs with interrupts
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
deleted file mode 100644
index f6e6d02f07fe..000000000000
--- a/kernel/entry/common.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _COMMON_H
-#define _COMMON_H
-
-bool syscall_user_dispatch(struct pt_regs *regs);
-
-#endif
diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c
index fe38f84dfff3..10231d30405e 100644
--- a/kernel/entry/syscall-common.c
+++ b/kernel/entry/syscall-common.c
@@ -1,104 +1,16 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/audit.h>
#include <linux/entry-common.h>
-#include "common.h"
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
-static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+void __trace_sys_enter(struct pt_regs *regs, long syscall)
{
- if (unlikely(audit_context())) {
- unsigned long args[6];
-
- syscall_get_arguments(current, regs, args);
- audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
- }
+ trace_sys_enter(regs, syscall);
}
-long syscall_trace_enter(struct pt_regs *regs, long syscall,
- unsigned long work)
+void __trace_sys_exit(struct pt_regs *regs, long ret)
{
- long ret = 0;
-
- /*
- * Handle Syscall User Dispatch. This must comes first, since
- * the ABI here can be something that doesn't make sense for
- * other syscall_work features.
- */
- if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
- if (syscall_user_dispatch(regs))
- return -1L;
- }
-
- /* Handle ptrace */
- if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
- ret = arch_ptrace_report_syscall_entry(regs);
- if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
- return -1L;
- }
-
- /* Do seccomp after ptrace, to catch any tracer changes. */
- if (work & SYSCALL_WORK_SECCOMP) {
- ret = __secure_computing();
- if (ret == -1L)
- return ret;
- }
-
- /* Either of the above might have changed the syscall number */
- syscall = syscall_get_nr(current, regs);
-
- if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
- trace_sys_enter(regs, syscall);
- /*
- * Probes or BPF hooks in the tracepoint may have changed the
- * system call number as well.
- */
- syscall = syscall_get_nr(current, regs);
- }
-
- syscall_enter_audit(regs, syscall);
-
- return ret ? : syscall;
-}
-
-/*
- * If SYSCALL_EMU is set, then the only reason to report is when
- * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
- * instruction has been already reported in syscall_enter_from_user_mode().
- */
-static inline bool report_single_step(unsigned long work)
-{
- if (work & SYSCALL_WORK_SYSCALL_EMU)
- return false;
-
- return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
-}
-
-void syscall_exit_work(struct pt_regs *regs, unsigned long work)
-{
- bool step;
-
- /*
- * If the syscall was rolled back due to syscall user dispatching,
- * then the tracers below are not invoked for the same reason as
- * the entry side was not invoked in syscall_trace_enter(): The ABI
- * of these syscalls is unknown.
- */
- if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
- if (unlikely(current->syscall_dispatch.on_dispatch)) {
- current->syscall_dispatch.on_dispatch = false;
- return;
- }
- }
-
- audit_syscall_exit(regs);
-
- if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
- step = report_single_step(work);
- if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
- arch_ptrace_report_syscall_exit(regs, step);
+ trace_sys_exit(regs, ret);
}
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;
--
2.34.1
Powered by blists - more mailing lists