perf/x86/intel/pt: Do not force sync packets on every schedule-in
Currently, the PT driver zeroes out the status register every time before starting the event. However, all the writable bits are already taken care of in pt_handle_status() function, except the new PacketByteCnt field, which in new versions of PT contains the number of packet bytes written since the last sync (PSB) packet. Zeroing it out before enabling PT forces a sync packet to be written. This means that, with the existing code, a sync packet (PSB and PSBEND, 18 bytes in total) will be generated every time a PT event is scheduled in. To avoid these unnecessary syncs and save a WRMSR in the fast path, this patch changes the default behavior to not clear PacketByteCnt field, so that the sync packets will be generated with the period specified as "psb_period" attribute config field. This has little impact on the trace data as the other packets that are normally sent within PSB+ (between PSB and PSBEND) have their own generation scenarios which do not depend on the sync packets. One exception where we do need to force PSB like this when tracing starts, so that the decoder has a clear sync point in the trace. For this purpose we aready have hw::itrace_started flag, which we are currently using to output PERF_RECORD_ITRACE_START. This patch moves setting itrace_started from perf core to the pmu::start, where it should still be 0 on the very first run. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: hpa@zytor.com Link: http://lkml.kernel.org/r/1438264104-16189-1-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
27747f8bc3
commit
9a6694cfa2
|
@ -191,6 +191,11 @@ static void pt_config(struct perf_event *event)
|
|||
{
|
||||
u64 reg;
|
||||
|
||||
if (!event->hw.itrace_started) {
|
||||
event->hw.itrace_started = 1;
|
||||
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
|
||||
}
|
||||
|
||||
reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
|
||||
|
||||
if (!event->attr.exclude_kernel)
|
||||
|
@ -910,7 +915,6 @@ void intel_pt_interrupt(void)
|
|||
|
||||
pt_config_buffer(buf->cur->table, buf->cur_idx,
|
||||
buf->output_off);
|
||||
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
|
||||
pt_config(event);
|
||||
}
|
||||
}
|
||||
|
@ -934,7 +938,6 @@ static void pt_event_start(struct perf_event *event, int mode)
|
|||
|
||||
pt_config_buffer(buf->cur->table, buf->cur_idx,
|
||||
buf->output_off);
|
||||
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
|
||||
pt_config(event);
|
||||
}
|
||||
|
||||
|
|
|
@ -6139,8 +6139,6 @@ static void perf_log_itrace_start(struct perf_event *event)
|
|||
event->hw.itrace_started)
|
||||
return;
|
||||
|
||||
event->hw.itrace_started = 1;
|
||||
|
||||
rec.header.type = PERF_RECORD_ITRACE_START;
|
||||
rec.header.misc = 0;
|
||||
rec.header.size = sizeof(rec);
|
||||
|
|
Loading…
Reference in New Issue