[PATCH] perf, x86: Avoid checkpointed counters causing excessive TSX aborts v5
From: Andi Kleen
With checkpointed counters there can be a situation where the counter
is overflowing, aborts the transaction, is set back to a non overflowing
checkpoint, causes interupt. The interrupt doesn't see the overflow
because it has been checkpointed. This is then a spurious PMI, typically with
a ugly NMI message. It can also lead to excessive aborts.
Avoid this problem by:
- Using the full counter width for counting counters (earlier patch)
- Forbid sampling for checkpointed counters. It's not too useful anyways,
checkpointing is mainly for counting. The check is approximate
(to still handle KVM), but should catch the majority of cases.
- On a PMI always set back checkpointed counters to zero.
v2: Add unlikely. Add comment
v3: Allow large sampling periods with CP for KVM
v4: Use event_is_checkpointed. Use EOPNOTSUPP. (Stephane Eranian)
v5: Remove comment.
Signed-off-by: Andi Kleen
---
arch/x86/kernel/cpu/perf_event_intel.c | 37 ++
1 file changed, 37 insertions(+)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c
b/arch/x86/kernel/cpu/perf_event_intel.c
index a45d8d4..91e3f8c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,6 +1134,11 @@ static void intel_pmu_enable_event(struct perf_event
*event)
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+ return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
/*
* Save and restart an expired event. Called by NMI contexts,
* so it has to be careful about preempting normal event ops:
@@ -1141,6 +1146,17 @@ static void intel_pmu_enable_event(struct perf_event
*event)
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
+ /*
+* For a checkpointed counter always reset back to 0. This
+* avoids a situation where the counter overflows, aborts the
+* transaction and is then set back to shortly before the
+* overflow, and overflows and aborts again.
+*/
+ if (unlikely(event_is_checkpointed(event))) {
+ /* No race with NMIs because the counter should not be armed */
+ wrmsrl(event->hw.event_base, 0);
+ local64_set(>hw.prev_count, 0);
+ }
return x86_perf_event_set_period(event);
}
@@ -1224,6 +1240,13 @@ again:
x86_pmu.drain_pebs(regs);
}
+ /*
+* To avoid spurious interrupts with perf stat always reset checkpointed
+* counters.
+*/
+ if (cpuc->events[2] && event_is_checkpointed(cpuc->events[2]))
+ status |= (1ULL << 2);
+
for_each_set_bit(bit, (unsigned long *), X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
@@ -1689,6 +1712,20 @@ static int hsw_hw_config(struct perf_event *event)
event->attr.precise_ip > 0))
return -EOPNOTSUPP;
+ if (event_is_checkpointed(event)) {
+ /*
+* Sampling of checkpointed events can cause situations where
+* the CPU constantly aborts because of a overflow, which is
+* then checkpointed back and ignored. Forbid checkpointing
+* for sampling.
+*
+* But still allow a long sampling period, so that perf stat
+* from KVM works.
+*/
+ if (event->attr.sample_period > 0 &&
+ event->attr.sample_period < 0x7fff)
+ return -EOPNOTSUPP;
+ }
return 0;
}
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[PATCH] perf, x86: Avoid checkpointed counters causing excessive TSX aborts v5
From: Andi Kleen a...@linux.intel.com
With checkpointed counters there can be a situation where the counter
is overflowing, aborts the transaction, is set back to a non overflowing
checkpoint, causes interupt. The interrupt doesn't see the overflow
because it has been checkpointed. This is then a spurious PMI, typically with
a ugly NMI message. It can also lead to excessive aborts.
Avoid this problem by:
- Using the full counter width for counting counters (earlier patch)
- Forbid sampling for checkpointed counters. It's not too useful anyways,
checkpointing is mainly for counting. The check is approximate
(to still handle KVM), but should catch the majority of cases.
- On a PMI always set back checkpointed counters to zero.
v2: Add unlikely. Add comment
v3: Allow large sampling periods with CP for KVM
v4: Use event_is_checkpointed. Use EOPNOTSUPP. (Stephane Eranian)
v5: Remove comment.
Signed-off-by: Andi Kleen a...@linux.intel.com
---
arch/x86/kernel/cpu/perf_event_intel.c | 37 ++
1 file changed, 37 insertions(+)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c
b/arch/x86/kernel/cpu/perf_event_intel.c
index a45d8d4..91e3f8c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,6 +1134,11 @@ static void intel_pmu_enable_event(struct perf_event
*event)
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+ return (event-hw.config HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
/*
* Save and restart an expired event. Called by NMI contexts,
* so it has to be careful about preempting normal event ops:
@@ -1141,6 +1146,17 @@ static void intel_pmu_enable_event(struct perf_event
*event)
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
+ /*
+* For a checkpointed counter always reset back to 0. This
+* avoids a situation where the counter overflows, aborts the
+* transaction and is then set back to shortly before the
+* overflow, and overflows and aborts again.
+*/
+ if (unlikely(event_is_checkpointed(event))) {
+ /* No race with NMIs because the counter should not be armed */
+ wrmsrl(event-hw.event_base, 0);
+ local64_set(event-hw.prev_count, 0);
+ }
return x86_perf_event_set_period(event);
}
@@ -1224,6 +1240,13 @@ again:
x86_pmu.drain_pebs(regs);
}
+ /*
+* To avoid spurious interrupts with perf stat always reset checkpointed
+* counters.
+*/
+ if (cpuc-events[2] event_is_checkpointed(cpuc-events[2]))
+ status |= (1ULL 2);
+
for_each_set_bit(bit, (unsigned long *)status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc-events[bit];
@@ -1689,6 +1712,20 @@ static int hsw_hw_config(struct perf_event *event)
event-attr.precise_ip 0))
return -EOPNOTSUPP;
+ if (event_is_checkpointed(event)) {
+ /*
+* Sampling of checkpointed events can cause situations where
+* the CPU constantly aborts because of a overflow, which is
+* then checkpointed back and ignored. Forbid checkpointing
+* for sampling.
+*
+* But still allow a long sampling period, so that perf stat
+* from KVM works.
+*/
+ if (event-attr.sample_period 0
+ event-attr.sample_period 0x7fff)
+ return -EOPNOTSUPP;
+ }
return 0;
}
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
