perf, x86: Try to handle unknown nmis with an enabled PMU

When the PMU is enabled it is valid to have unhandled nmis, two
events could trigger 'simultaneously' raising two back-to-back
NMIs. If the first NMI handles both, the latter will be empty
and daze the CPU.

The solution to avoid an 'unknown nmi' massage in this case was
simply to stop the nmi handler chain when the PMU is enabled by
stating the nmi was handled. This has the drawback that a) we
can not detect unknown nmis anymore, and b) subsequent nmi
handlers are not called.

This patch addresses this. Now, we check this unknown NMI if it
could be a PMU back-to-back NMI. Otherwise we pass it and let
the kernel handle the unknown nmi.

This is a debug log:

 cpu #6, nmi #32333, skip_nmi #32330, handled = 1, time = 1934364430
 cpu #6, nmi #32334, skip_nmi #32330, handled = 1, time = 1934704616
 cpu #6, nmi #32335, skip_nmi #32336, handled = 2, time = 1936032320
 cpu #6, nmi #32336, skip_nmi #32336, handled = 0, time = 1936034139
 cpu #6, nmi #32337, skip_nmi #32336, handled = 1, time = 1936120100
 cpu #6, nmi #32338, skip_nmi #32336, handled = 1, time = 1936404607
 cpu #6, nmi #32339, skip_nmi #32336, handled = 1, time = 1937983416
 cpu #6, nmi #32340, skip_nmi #32341, handled = 2, time = 1938201032
 cpu #6, nmi #32341, skip_nmi #32341, handled = 0, time = 1938202830
 cpu #6, nmi #32342, skip_nmi #32341, handled = 1, time = 1938443743
 cpu #6, nmi #32343, skip_nmi #32341, handled = 1, time = 1939956552
 cpu #6, nmi #32344, skip_nmi #32341, handled = 1, time = 1940073224
 cpu #6, nmi #32345, skip_nmi #32341, handled = 1, time = 1940485677
 cpu #6, nmi #32346, skip_nmi #32347, handled = 2, time = 1941947772
 cpu #6, nmi #32347, skip_nmi #32347, handled = 1, time = 1941949818
 cpu #6, nmi #32348, skip_nmi #32347, handled = 0, time = 1941951591
 Uhhuh. NMI received for unknown reason 00 on CPU 6.
 Do you have a strange power saving mode enabled?
 Dazed and confused, but trying to continue

Deltas:

 nmi #32334 340186
 nmi #32335 1327704
 nmi #32336 1819      <<<< back-to-back nmi [1]
 nmi #32337 85961
 nmi #32338 284507
 nmi #32339 1578809
 nmi #32340 217616
 nmi #32341 1798      <<<< back-to-back nmi [2]
 nmi #32342 240913
 nmi #32343 1512809
 nmi #32344 116672
 nmi #32345 412453
 nmi #32346 1462095   <<<< 1st nmi (standard) handling 2 counters
 nmi #32347 2046      <<<< 2nd nmi (back-to-back) handling one
 counter nmi #32348 1773      <<<< 3rd nmi (back-to-back)
 handling no counter! [3]

For  back-to-back nmi detection there are the following rules:

The PMU nmi handler was handling more than one counter and no
counter was handled in the subsequent nmi (see [1] and [2]
above).

There is another case if there are two subsequent back-to-back
nmis [3]. The 2nd is detected as back-to-back because the first
handled more than one counter. If the second handles one counter
and the 3rd handles nothing, we drop the 3rd nmi because it
could be a back-to-back nmi.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ renamed nmi variable to pmu_nmi to avoid clash with .nmi in entry.S ]
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: peterz@infradead.org
Cc: gorcunov@gmail.com
Cc: fweisbec@gmail.com
Cc: ying.huang@intel.com
Cc: ming.m.lin@intel.com
Cc: eranian@google.com
LKML-Reference: <1283454469-1909-3-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event.c

@@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		/*
 		 * event overflow
 		 */
-		handled		= 1;
+		handled++;
 		data.period	= event->hw.last_period;
 
 		if (!x86_perf_event_set_period(event))
@@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
+struct pmu_nmi_state {
+	unsigned int	marked;
+	int		handled;
+};
+
+static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
+
 static int __kprobes
 perf_event_nmi_handler(struct notifier_block *self,
 			 unsigned long cmd, void *__args)
 {
 	struct die_args *args = __args;
-	struct pt_regs *regs;
+	unsigned int this_nmi;
+	int handled;
 
 	if (!atomic_read(&active_events))
 		return NOTIFY_DONE;
@@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self,
 	case DIE_NMI:
 	case DIE_NMI_IPI:
 		break;
-
+	case DIE_NMIUNKNOWN:
+		this_nmi = percpu_read(irq_stat.__nmi_count);
+		if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+			/* let the kernel handle the unknown nmi */
+			return NOTIFY_DONE;
+		/*
+		 * This one is a PMU back-to-back nmi. Two events
+		 * trigger 'simultaneously' raising two back-to-back
+		 * NMIs. If the first NMI handles both, the latter
+		 * will be empty and daze the CPU. So, we drop it to
+		 * avoid false-positive 'unknown nmi' messages.
+		 */
+		return NOTIFY_STOP;
 	default:
 		return NOTIFY_DONE;
 	}
 
-	regs = args->regs;
-
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+	handled = x86_pmu.handle_irq(args->regs);
+	if (!handled)
+		return NOTIFY_DONE;
+
+	this_nmi = percpu_read(irq_stat.__nmi_count);
+	if ((handled > 1) ||
+		/* the next nmi could be a back-to-back nmi */
+	    ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
+	     (__get_cpu_var(pmu_nmi).handled > 1))) {
 		/*
-	 * Can't rely on the handled return value to say it was our NMI, two
-	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
+		 * We could have two subsequent back-to-back nmis: The
+		 * first handles more than one counter, the 2nd
+		 * handles only one counter and the 3rd handles no
+		 * counter.
 		 *
-	 * If the first NMI handles both, the latter will be empty and daze
-	 * the CPU.
+		 * This is the 2nd nmi because the previous was
+		 * handling more than one counter. We will mark the
+		 * next (3rd) and then drop it if unhandled.
 		 */
-	x86_pmu.handle_irq(regs);
+		__get_cpu_var(pmu_nmi).marked	= this_nmi + 1;
+		__get_cpu_var(pmu_nmi).handled	= handled;
+	}
 
 	return NOTIFY_STOP;
 }