Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 475113d9 authored by Jiri Olsa's avatar Jiri Olsa Committed by Ingo Molnar
Browse files

perf/x86/intel: Account interrupts for PEBS errors 



It's possible to set up PEBS events to get only errors and not
any data, like on SNB-X (model 45) and IVB-EP (model 62)
via 2 perf commands running simultaneously:

    taskset -c 1 ./perf record -c 4 -e branches:pp -j any -C 10

This leads to a soft lock up, because the error path of the
intel_pmu_drain_pebs_nhm() does not account event->hw.interrupt
for error PEBS interrupts, so in case you're getting ONLY
errors you don't have a way to stop the event when it's over
the max_samples_per_tick limit:

  NMI watchdog: BUG: soft lockup - CPU#22 stuck for 22s! [perf_fuzzer:5816]
  ...
  RIP: 0010:[<ffffffff81159232>]  [<ffffffff81159232>] smp_call_function_single+0xe2/0x140
  ...
  Call Trace:
   ? trace_hardirqs_on_caller+0xf5/0x1b0
   ? perf_cgroup_attach+0x70/0x70
   perf_install_in_context+0x199/0x1b0
   ? ctx_resched+0x90/0x90
   SYSC_perf_event_open+0x641/0xf90
   SyS_perf_event_open+0x9/0x10
   do_syscall_64+0x6c/0x1f0
   entry_SYSCALL64_slow_path+0x25/0x25

Add perf_event_account_interrupt() which does the interrupt
and frequency checks and call it from intel_pmu_drain_pebs_nhm()'s
error path.

We keep the pending_kill and pending_wakeup logic only in the
__perf_event_overflow() path, because they make sense only if
there's any data to deliver.

Signed-off-by: default avatarJiri Olsa <jolsa@kernel.org>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vince@deater.net>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1482931866-6018-2-git-send-email-jolsa@kernel.org


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 321027c1

arch/x86/events/intel/ds.c

+5 −1
Original line number Diff line number Diff line
@@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) 
			continue;



		/* log dropped samples number */

		if (error[bit])

		if (error[bit]) {

			perf_log_lost_samples(event, error[bit]);



			if (perf_event_account_interrupt(event))

				x86_pmu_stop(event, 0);

		}



		if (counts[bit]) {

			__intel_pmu_pebs_event(event, iregs, base,

					       top, bit, counts[bit]);

include/linux/perf_event.h

+1 −0
Original line number Diff line number Diff line
@@ -1259,6 +1259,7 @@ extern void perf_event_disable(struct perf_event *event); 
extern void perf_event_disable_local(struct perf_event *event);

extern void perf_event_disable_inatomic(struct perf_event *event);

extern void perf_event_task_tick(void);

extern int perf_event_account_interrupt(struct perf_event *event);

#else /* !CONFIG_PERF_EVENTS: */

static inline void *

perf_aux_output_begin(struct perf_output_handle *handle,

kernel/events/core.c

+31 −16
Original line number Diff line number Diff line
@@ -7060,25 +7060,12 @@ static void perf_log_itrace_start(struct perf_event *event) 
	perf_output_end(&handle);

}



/*

 * Generic event overflow handling, sampling.

 */



static int __perf_event_overflow(struct perf_event *event,

				   int throttle, struct perf_sample_data *data,

				   struct pt_regs *regs)

static int

__perf_event_account_interrupt(struct perf_event *event, int throttle)

{

	int events = atomic_read(&event->event_limit);

	struct hw_perf_event *hwc = &event->hw;

	u64 seq;

	int ret = 0;



	/*

	 * Non-sampling counters might still use the PMI to fold short

	 * hardware counters, ignore those.

	 */

	if (unlikely(!is_sampling_event(event)))

		return 0;

	u64 seq;



	seq = __this_cpu_read(perf_throttled_seq);

	if (seq != hwc->interrupts_seq) {
@@ -7106,6 +7093,34 @@ static int __perf_event_overflow(struct perf_event *event, 
			perf_adjust_period(event, delta, hwc->last_period, true);

	}



	return ret;

}



int perf_event_account_interrupt(struct perf_event *event)

{

	return __perf_event_account_interrupt(event, 1);

}



/*

 * Generic event overflow handling, sampling.

 */



static int __perf_event_overflow(struct perf_event *event,

				   int throttle, struct perf_sample_data *data,

				   struct pt_regs *regs)

{

	int events = atomic_read(&event->event_limit);

	int ret = 0;



	/*

	 * Non-sampling counters might still use the PMI to fold short

	 * hardware counters, ignore those.

	 */

	if (unlikely(!is_sampling_event(event)))

		return 0;



	ret = __perf_event_account_interrupt(event, throttle);



	/*

	 * XXX event_limit might not quite work as expected on inherited

	 * events