From ec5e099d6e941668d121ea9ca7057f4fa00830b0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Apr 2016 18:43:22 -0700 Subject: 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) Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/perf_event.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f291275ffd71..e89f7199c223 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -882,8 +882,6 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { - memset(regs, 0, sizeof(*regs)); - perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } -- cgit v1.2.3