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 <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
6e3d8330ae
commit
a4234bfcf4
@ -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)
|
||||
|
Loading…
Reference in New Issue
Block a user