Re: [PATCH] perf, x86: catch spurious interrupts after disablingcounters

[Peter Zijlstra]

On Wed, 2010-09-15 at 18:20 +0200, Robert Richter wrote:
> Some cpus still deliver spurious interrupts after disabling a counter.
> This caused 'undelivered NMI' messages. This patch fixes this.
> 
I tried the below and that also seems to work.. So yeah, looks like
we're getting late NMIs.

---
 arch/x86/kernel/cpu/perf_event.c |   21 ++++++++++++++++++++-
 1 files changed, 20 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0fb1705..9a261ac 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1145,6 +1145,22 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	perf_event_update_userpage(event);
 }
 
+static int fixup_overflow(int idx)
+{
+	u64 val;
+
+	rdmsrl(x86_pmu.perfctr + idx, val);
+	if (!(val & (1ULL << (x86_pmu.cntval_bits - 1)))) {
+		val = (u64)(-x86_pmu.max_period);
+		val &= x86_pmu.cntval_mask;
+		wrmsrl(x86_pmu.perfctr + idx, val);
+
+		return 1;
+	}
+
+	return 0;
+}
+
 static int x86_pmu_handle_irq(struct pt_regs *regs)
 {
 	struct perf_sample_data data;
@@ -1159,8 +1175,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+	       		if (fixup_overflow(idx))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/