| 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: <20251204082123.2792067-16-ruanjinjie@huawei.com>
Date: Thu, 4 Dec 2025 16:21:22 +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>, <deller@....de>,
<macro@...am.me.uk>, <charlie@...osinc.com>, <kevin.brodsky@....com>,
<ldv@...ace.io>, <mark.rutland@....com>, <song@...nel.org>,
<ryan.roberts@....com>, <ada.coupriediaz@....com>,
<anshuman.khandual@....com>, <broonie@...nel.org>, <pengcan@...inos.cn>,
<dvyukov@...gle.com>, <linux-arm-kernel@...ts.infradead.org>,
<linux-kernel@...r.kernel.org>, <linux-kselftest@...r.kernel.org>
CC: <ruanjinjie@...wei.com>
Subject: [PATCH v9 15/16] entry: Inline syscall_exit_work()
After switch arm64 to Generic Entry, a new hotspot syscall_exit_work()
appeared because syscall_exit_work() is no longer inlined. so inline
syscall_exit_work(), and it has 2.6% performance uplift on perf bench
basic syscall on kunpeng920 as below.
| Metric | W/O this patch | With this patch | Change |
| ---------- | -------------- | --------------- | --------- |
| Total time | 2.171 [sec] | 2.114 [sec] | ↓2.6% |
| usecs/op | 0.217192 | 0.211453 | ↓2.6% |
| ops/sec | 4,604,225 | 4,729,178 | ↑2.7% |
Signed-off-by: Jinjie Ruan <ruanjinjie@...wei.com>
---
include/linux/entry-common.h | 63 ++++++++++++++++++++++++++++++++++-
kernel/entry/syscall-common.c | 59 ++------------------------------
2 files changed, 64 insertions(+), 58 deletions(-)
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index cd6dacb2d8bf..2f84377fb016 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/ptrace.h>
#include <linux/seccomp.h>
@@ -128,6 +129,41 @@ 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.
+ *
+ * Invoked from syscall_exit_work() to wrap ptrace_report_syscall_exit().
+ *
+ * The main purpose is to support arch-specific ptrace_report_syscall_exit
+ * implementation.
+ */
+static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
+ int step);
+
+#ifndef arch_ptrace_report_syscall_exit
+static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
+ int step)
+{
+ ptrace_report_syscall_exit(regs, step);
+}
+#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
@@ -135,7 +171,32 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
*
* 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/syscall-common.c b/kernel/entry/syscall-common.c
index 27310e611567..1636f49c58d2 100644
--- a/kernel/entry/syscall-common.c
+++ b/kernel/entry/syscall-common.c
@@ -90,62 +90,7 @@ noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
instrumentation_end();
}
-/*
- * 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;
-}
-
-/**
- * arch_ptrace_report_syscall_exit - Architecture specific
- * ptrace_report_syscall_exit.
- *
- * Invoked from syscall_exit_work() to wrap ptrace_report_syscall_exit().
- *
- * The main purpose is to support arch-specific ptrace_report_syscall_exit
- * implementation.
- */
-static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
- int step);
-
-#ifndef arch_ptrace_report_syscall_exit
-static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
- int step)
+void __trace_sys_exit(struct pt_regs *regs, long ret)
{
- ptrace_report_syscall_exit(regs, step);
-}
-#endif
-
-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);
}
--
2.34.1
Powered by blists - more mailing lists