summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
authorSteven Rostedt <srostedt@redhat.com>2009-10-13 16:33:50 -0400
committerIngo Molnar <mingo@elte.hu>2009-10-14 08:13:53 +0200
commit194ec34184869f0de1cf255c924fc5299e1b3d27 (patch)
tree7eb411e56f381b65bcafd0aa750f6f6705f3e451 /arch/x86
parent1bac0497ef9af8d933860672223e38bd6ac4934a (diff)
downloadop-kernel-dev-194ec34184869f0de1cf255c924fc5299e1b3d27.zip
op-kernel-dev-194ec34184869f0de1cf255c924fc5299e1b3d27.tar.gz
function-graph/x86: Replace unbalanced ret with jmp
The function graph tracer replaces the return address with a hook to trace the exit of the function call. This hook will finish by returning to the real location the function should return to. But the current implementation uses a ret to jump to the real return location. This causes a imbalance between calls and ret. That is the original function does a call, the ret goes to the handler and then the handler does a ret without a matching call. Although the function graph tracer itself still breaks the branch predictor by replacing the original ret, by using a second ret and causing an imbalance, it breaks the predictor even more. This patch replaces the ret with a jmp to keep the calls and ret balanced. I tested this on one box and it showed a 1.7% increase in performance. Another box only showed a small 0.3% increase. But no box that I tested this on showed a decrease in performance by making this change. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <20091013203425.042034383@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/kernel/entry_32.S7
-rw-r--r--arch/x86/kernel/entry_64.S6
2 files changed, 5 insertions, 8 deletions
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c097e7d..7d52e9d 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1185,17 +1185,14 @@ END(ftrace_graph_caller)
.globl return_to_handler
return_to_handler:
- pushl $0
pushl %eax
- pushl %ecx
pushl %edx
movl %ebp, %eax
call ftrace_return_to_handler
- movl %eax, 0xc(%esp)
+ movl %eax, %ecx
popl %edx
- popl %ecx
popl %eax
- ret
+ jmp *%ecx
#endif
.section .rodata,"a"
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b5c061f..bd5bbdd 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -155,11 +155,11 @@ GLOBAL(return_to_handler)
call ftrace_return_to_handler
- movq %rax, 16(%rsp)
+ movq %rax, %rdi
movq 8(%rsp), %rdx
movq (%rsp), %rax
- addq $16, %rsp
- retq
+ addq $24, %rsp
+ jmp *%rdi
#endif
OpenPOWER on IntegriCloud