[PATCH 1/4] perf/x86/intel: Account interrupts for PEBS errors

[Jiri Olsa <jolsa@kernel.org>]

It's possible to setup PEBS events to get only errors and not
a single 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 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 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

Adding perf_event_account_interrupt which does the interrupt
and frequency checks and calling it from drain_pebs's error
path.

Keeping pending_kill and pending_wakeup logic only in
__perf_event_overflow path, abecause they make sense only if
there's any data to deliver.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/events/intel/ds.c |  6 +++++-
 include/linux/perf_event.h |  1 +
 kernel/events/core.c       | 47 ++++++++++++++++++++++++++++++----------------
 3 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index be202390bbd3..9dfeeeca0ea8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -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]);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4741ecdb9817..78ed8105e64d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -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,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index faf073d0287f..38f4baef5df5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7034,25 +7034,12 @@ 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) {
@@ -7080,6 +7067,34 @@ 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
-- 
2.7.4