From a4234bfcf4d72a10a99176cdef007345e9c3b4aa Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 23 Nov 2009 10:57:59 +0100 Subject: [PATCH] perf_events: Optimize the swcounter hotpath The structure init creates a bit memcpy, which shows up big time in perf annotate output: : ffffffff810a859d <__perf_sw_event>: 1.68 : ffffffff810a859d: 55 push %rbp 1.69 : ffffffff810a859e: 41 89 fa mov %edi,%r10d 0.01 : ffffffff810a85a1: 49 89 c9 mov %rcx,%r9 0.00 : ffffffff810a85a4: 31 c0 xor %eax,%eax 1.71 : ffffffff810a85a6: b9 16 00 00 00 mov $0x16,%ecx 0.00 : ffffffff810a85ab: 48 89 e5 mov %rsp,%rbp 0.00 : ffffffff810a85ae: 48 83 ec 60 sub $0x60,%rsp 1.52 : ffffffff810a85b2: 48 8d 7d a0 lea -0x60(%rbp),%rdi 85.20 : ffffffff810a85b6: f3 ab rep stos %eax,%es:(%rdi) None of the callees depends on the structure being pre-initialized, so only initialize ->addr. This gets rid of the memcpy overhead. Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/perf_event.c b/kernel/perf_event.c index abe1ef47496c..20df8aba8da5 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3954,12 +3954,12 @@ out: void __perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { - struct perf_sample_data data = { - .addr = addr, - }; + struct perf_sample_data data; - do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, - &data, regs); + data.addr = addr; + data.raw = NULL; + + do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); } static void perf_swevent_read(struct perf_event *event) -- 2.30.2