diff options
| author | Alexei Starovoitov <ast@fb.com> | 2016-04-07 03:43:22 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-04-08 03:04:26 +0200 |
| commit | ec5e099d6e941668d121ea9ca7057f4fa00830b0 (patch) | |
| tree | 4ec273d88501a68ce23eb53649530161a7fa8440 /kernel/trace/trace_event_perf.c | |
| parent | net: Fix build failure due to lockdep_sock_is_held(). (diff) | |
| download | linux-ec5e099d6e941668d121ea9ca7057f4fa00830b0.tar.xz linux-ec5e099d6e941668d121ea9ca7057f4fa00830b0.zip | |
perf: optimize perf_fetch_caller_regs
avoid memset in perf_fetch_caller_regs, since it's the critical path of all tracepoints.
It's called from perf_sw_event_sched, perf_event_task_sched_in and all of perf_trace_##call
with this_cpu_ptr(&__perf_regs[..]) which are zero initialized by perpcu init logic and
subsequent call to perf_arch_fetch_caller_regs initializes the same fields on all archs,
so we can safely drop memset from all of the above cases and move it into
perf_ftrace_function_call that calls it with stack allocated pt_regs.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/trace/trace_event_perf.c')
| -rw-r--r-- | kernel/trace/trace_event_perf.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 00df25fd86ef..7a68afca8249 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -316,6 +316,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE); + memset(®s, 0, sizeof(regs)); perf_fetch_caller_regs(®s); entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); |