[PATCH 7/7] x86_64,entry: Use split-phase syscall_trace_enter for 64-bit syscalls

From: Andy Lutomirski
Date: Tue Jul 15 2014 - 15:33:33 EST


On KVM on my box, this reduces the overhead from an always-accept
seccomp filter from ~130ns to ~17ns. Most of that comes from
avoiding IRET on every syscall when seccomp is enabled.

In extremely approximate hacked-up benchmarking, just bypassing IRET
saves about 80ns, so there's another 43ns of savings here from
simplifying the seccomp path.

The diffstat is also rather nice :)

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
---
arch/x86/kernel/entry_64.S | 40 ++++++++++++++++------------------------
1 file changed, 16 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 432c190..13e0c1d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -479,22 +479,6 @@ sysret_signal:

#ifdef CONFIG_AUDITSYSCALL
/*
- * Fast path for syscall audit without full syscall trace.
- * We just call __audit_syscall_entry() directly, and then
- * jump back to the normal fast path.
- */
-auditsys:
- movq %r10,%r9 /* 6th arg: 4th syscall arg */
- movq %rdx,%r8 /* 5th arg: 3rd syscall arg */
- movq %rsi,%rcx /* 4th arg: 2nd syscall arg */
- movq %rdi,%rdx /* 3rd arg: 1st syscall arg */
- movq %rax,%rsi /* 2nd arg: syscall number */
- movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */
- call __audit_syscall_entry
- LOAD_ARGS 0 /* reload call-clobbered registers */
- jmp system_call_fastpath
-
- /*
* Return fast path for syscall audit. Call __audit_syscall_exit()
* directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
* masked off.
@@ -511,17 +495,25 @@ sysret_audit:

/* Do syscall tracing */
tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- jz auditsys
-#endif
+ leaq -REST_SKIP(%rsp), %rdi
+ movq $AUDIT_ARCH_X86_64, %rsi
+ call syscall_trace_enter_phase1
+ test %rax, %rax
+ jnz tracesys_phase2 /* if needed, run the slow path */
+ LOAD_ARGS 0 /* else restore clobbered regs */
+ jmp system_call_fastpath /* and return to the fast path */
+
+tracesys_phase2:
SAVE_REST
FIXUP_TOP_OF_STACK %rdi
- movq %rsp,%rdi
- call syscall_trace_enter
+ movq %rsp, %rdi
+ movq $AUDIT_ARCH_X86_64, %rsi
+ movq %rax,%rdx
+ call syscall_trace_enter_phase2
+
/*
* Reload arg registers from stack in case ptrace changed them.
- * We don't reload %rax because syscall_trace_enter() returned
+ * We don't reload %rax because syscall_trace_entry_phase2() returned
* the value it wants us to use in the table lookup.
*/
LOAD_ARGS ARGOFFSET, 1
@@ -532,7 +524,7 @@ tracesys:
andl $__SYSCALL_MASK,%eax
cmpl $__NR_syscall_max,%eax
#endif
- ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
+ ja int_ret_from_sys_call /* RAX(%rsp) is already set */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
movq %rax,RAX-ARGOFFSET(%rsp)
--
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/