Skip to contentSkip to conversation

KVM: x86/pmu: Clear reserved bit PERF_CTL2[43] for AMD erratum 1292

PATCH New Like Xu 5 participants 22 messages Jan 17, 2022 – Feb 10, 2022

Subsystems (4)
lore
Share & tools
lore

Like Xu

author
#0 lore raw

PATCH 1/1 KVM: x86/pmu: Clear reserved bit PERF_CTL2[43] for AMD erratum 1292

From: Like Xu <[email protected]>

The AMD Family 19h Models 00h-0Fh Processors may experience sampling inaccuracies that cause the following performance counters to overcount retire-based events. To count the non-FP affected PMC events correctly, a patched guest with a target vCPU model would:

- Use Core::X86::Msr::PERF_CTL2 to count the events, and
- Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
- Program Core::X86::Msr::PERF_CTL2[20] to 0b.

To support this use of AMD guests, KVM should not reserve bit 43 only for counter #2. Treatment of other cases remains unchanged.

Note, the host's perf subsystem will decide which hardware counter will be used for the guest counter, based on its own physical CPU model and its own workaround(s) in the host perf context.

---
 arch/x86/kvm/svm/pmu.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)
arch/x86/kvm/svm/pmu.c +16 -1
index 12d8b301065a..1111b12adcca 100644
@@ -18,6 +18,17 @@
 #include "pmu.h"
 #include "svm.h"
 
+/*
+ * As a workaround of "Retire Based Events May Overcount" for erratum 1292,
+ * some patched guests may set PERF_CTL2[43] to 1b and PERF_CTL2[20] to 0b
+ * to count the non-FP affected PMC events correctly.
+ */
+static inline bool vcpu_overcount_retire_events(struct kvm_vcpu *vcpu)
+{
+	return guest_cpuid_family(vcpu) == 0x19 &&
+		guest_cpuid_model(vcpu) < 0x10;
+}
+
 enum pmu_type {
 	PMU_TYPE_COUNTER = 0,
 	PMU_TYPE_EVNTSEL,
@@ -252,6 +263,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct kvm_pmc *pmc;
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
+	u64 reserved_bits;
 
 	/* MSR_PERFCTRn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
@@ -264,7 +276,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	if (pmc) {
 		if (data == pmc->eventsel)
 			return 0;
-		if (!(data & pmu->reserved_bits)) {
+		reserved_bits = pmu->reserved_bits;
+		if (pmc->idx == 2 && vcpu_overcount_retire_events(vcpu))
+			reserved_bits &= ~BIT_ULL(43);
+		if (!(data & reserved_bits)) {
 			reprogram_gp_counter(pmc, data);
 			return 0;
 		}
Signature · 1 line
2.33.1
#1 lore raw

PATCH 1/1 perf/amd: Implement errata #1292 workaround for F19h M00-0Fh

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Above workaround suggests to clear PERF_CTL2[20], but that will disable sampling mode. Given the fact that, there is already a skew between actual counter overflow vs PMI hit, we are anyway not getting accurate count for sampling events. Also, using PMC2 with both bit43 and bit20 set can result in additional issues. Hence Linux implementation of workaround uses non-PMC2 counter for sampling events.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

---
 arch/x86/events/amd/core.c | 75 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)
arch/x86/events/amd/core.c +74 -1
index 9687a8aef01c..e2f172e75ce8 100644
@@ -874,8 +874,78 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 	}
 }
 
+/* Errata 1292: Overcounting of Retire Based Events */
+static struct event_constraint retire_event_count_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC2, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC3, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC4, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC8, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC9, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT_END
+};
+
+#define SAMPLE_IDX_MASK	(((1ULL << AMD64_NUM_COUNTERS_CORE) - 1) & ~0x4ULL)
+
+static struct event_constraint retire_event_sample_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT(0xC0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC1, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC2, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC3, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC4, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC5, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC8, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC9, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCA, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint pair_constraint;
 
+/*
+ * Although 'Overcounting of Retire Based Events' errata exists
+ * for older generation cpus, workaround to set bit 43 works only
+ * for Family 19h Model 00-0Fh as per the Revision Guide.
+ */
+static struct event_constraint *
+amd_get_event_constraints_f19h_m00_0fh(struct cpu_hw_events *cpuc, int idx,
+				       struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (amd_is_pair_event_code(&event->hw))
+		return &pair_constraint;
+
+	if (is_sampling_event(event)) {
+		for_each_event_constraint(c, retire_event_sample_constraints) {
+			if (constraint_match(c, event->hw.config))
+				return c;
+		}
+	} else {
+		for_each_event_constraint(c, retire_event_count_constraints) {
+			if (constraint_match(c, event->hw.config)) {
+				event->hw.config |= (1ULL << 43);
+				event->hw.config &= ~(1ULL << 20);
+				return c;
+			}
+		}
+	}
+
+	return &unconstrained;
+}
+
 static struct event_constraint *
 amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
 			       struct perf_event *event)
@@ -983,7 +1053,10 @@ static int __init amd_core_pmu_init(void)
 				    x86_pmu.num_counters / 2, 0,
 				    PERF_X86_EVENT_PAIR);
 
-		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
+		if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model <= 0xf)
+			x86_pmu.get_event_constraints = amd_get_event_constraints_f19h_m00_0fh;
+		else
+			x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
 		x86_pmu.put_event_constraints = amd_put_event_constraints_f17h;
 		x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE;
 		x86_pmu.flags |= PMU_FL_PAIR;
Signature · 1 line
2.27.0
#2 lore raw

Re: [PATCH] perf/amd: Implement errata #1292 workaround for F19h M00-0Fh

Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 7 lines

Above workaround suggests to clear PERF_CTL2[20], but that will disable sampling mode. Given the fact that, there is already a skew between actual counter overflow vs PMI hit, we are anyway not getting accurate count for sampling events. Also, using PMC2 with both bit43 and bit20 set can result in additional issues. Hence Linux implementation of workaround uses non-PMC2 counter for sampling events.

Something is missing from your description here. If you are not clearing bit[20] and
not setting bit[43], then how does running on CTL2 by itself improve the count. Is that
enough to make the counter count correctly?

For sampling events, your patch makes CTL2 not available. That seems to contradict the
workaround. Are you doing this to free CTL2 for counting mode events instead? If you are
not using CTL2, then you are not correcting the count. Are you saying this is okay in sampling mode
because of the skid, anyway?

Quoted 111 lines

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

---
 arch/x86/events/amd/core.c | 75 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)
arch/x86/events/amd/core.c +74 -2
index 9687a8aef01c..e2f172e75ce8 100644
@@ -874,8 +874,78 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
        }
 }
 
+/* Errata 1292: Overcounting of Retire Based Events */
+static struct event_constraint retire_event_count_constraints[] __read_mostly = {
+       EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC1, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC2, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC3, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC4, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC8, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC9, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT_END
+};
+
+#define SAMPLE_IDX_MASK        (((1ULL << AMD64_NUM_COUNTERS_CORE) - 1) & ~0x4ULL)
+
+static struct event_constraint retire_event_sample_constraints[] __read_mostly = {
+       EVENT_CONSTRAINT(0xC0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC1, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC2, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC3, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC4, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC5, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC8, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xC9, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xCA, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xCC, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0xD1, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0x1000000C7, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT(0x1000000D0, SAMPLE_IDX_MASK, AMD64_EVENTSEL_EVENT),
+       EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint pair_constraint;
 
+/*
+ * Although 'Overcounting of Retire Based Events' errata exists
+ * for older generation cpus, workaround to set bit 43 works only
+ * for Family 19h Model 00-0Fh as per the Revision Guide.
+ */
+static struct event_constraint *
+amd_get_event_constraints_f19h_m00_0fh(struct cpu_hw_events *cpuc, int idx,
+                                      struct perf_event *event)
+{
+       struct event_constraint *c;
+
+       if (amd_is_pair_event_code(&event->hw))
+               return &pair_constraint;
+
+       if (is_sampling_event(event)) {
+               for_each_event_constraint(c, retire_event_sample_constraints) {
+                       if (constraint_match(c, event->hw.config))
+                               return c;
+               }
+       } else {
+               for_each_event_constraint(c, retire_event_count_constraints) {
+                       if (constraint_match(c, event->hw.config)) {
+                               event->hw.config |= (1ULL << 43);
+                               event->hw.config &= ~(1ULL << 20);
+                               return c;
+                       }
+               }
+       }
+
+       return &unconstrained;
+}
+
 static struct event_constraint *
 amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
                               struct perf_event *event)
@@ -983,7 +1053,10 @@ static int __init amd_core_pmu_init(void)
                                    x86_pmu.num_counters / 2, 0,
                                    PERF_X86_EVENT_PAIR);
 
-               x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
+               if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model <= 0xf)
+                       x86_pmu.get_event_constraints = amd_get_event_constraints_f19h_m00_0fh;
+               else
+                       x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
                x86_pmu.put_event_constraints = amd_put_event_constraints_f17h;
                x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE;
                x86_pmu.flags |= PMU_FL_PAIR;
--

2.27.0

#3 lore raw

Re: [PATCH] perf/amd: Implement errata #1292 workaround for F19h M00-0Fh

Hi Stephane,

Quoted 18 lines · Stephane Eranian
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 7 lines

Above workaround suggests to clear PERF_CTL2[20], but that will disable sampling mode. Given the fact that, there is already a skew between actual counter overflow vs PMI hit, we are anyway not getting accurate count for sampling events. Also, using PMC2 with both bit43 and bit20 set can result in additional issues. Hence Linux implementation of workaround uses non-PMC2 counter for sampling events.

Quoted 5 lines

Something is missing from your description here. If you are not clearing bit[20] and
not setting bit[43], then how does running on CTL2 by itself improve the count. Is that
enough to make the counter count correctly?

Yes. For counting retire based events, we need PMC2[43] set and PMC2[20] clear so that it will not overcount.

Quoted 8 lines

For sampling events, your patch makes CTL2 not available. That seems to contradict the
workaround. Are you doing this to free CTL2 for counting mode events instead? If you are
not using CTL2, then you are not correcting the count. Are you saying this is okay in sampling mode
because of the skid, anyway?

Correct. The constraint I am placing is to count retire events on PMC2 and sample retire events on other counters.

Thanks,
Ravi

#4 lore raw

Re: [PATCH] perf/amd: Implement errata #1292 workaround for F19h M00-0Fh

Quoted 22 lines · Ravi Bangoria

Hi Stephane,

Quoted 18 lines · Stephane Eranian
Quoted 17 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Above workaround suggests to clear PERF_CTL2[20], but that will disable sampling mode. Given the fact that, there is already a skew between actual counter overflow vs PMI hit, we are anyway not getting accurate count for sampling events. Also, using PMC2 with both bit43 and bit20 set can result in additional issues. Hence Linux implementation of workaround uses non-PMC2 counter for sampling events.

Quoted 9 lines
Quoted 5 lines

Something is missing from your description here. If you are not clearing bit[20] and
not setting bit[43], then how does running on CTL2 by itself improve the count. Is that
enough to make the counter count correctly?

Yes. For counting retire based events, we need PMC2[43] set and PMC2[20] clear so that it will not overcount.

Ok, I get that part now. You are forcing the bits in the get_constraint() function.

Quoted 9 lines
Quoted 8 lines

For sampling events, your patch makes CTL2 not available. That seems to contradict the
workaround. Are you doing this to free CTL2 for counting mode events instead? If you are
not using CTL2, then you are not correcting the count. Are you saying this is okay in sampling mode
because of the skid, anyway?

Quoted 3 lines

Correct. The constraint I am placing is to count retire events on PMC2 and sample retire events on other counters.

Why do you need to permanently exclude CTL2 for retired events given you are forcing the bits
in the get_constraints() for counting events config only, i.e., as opposed to in CTL2 itself.
If the sampling retired events are unconstrained, they can use any counters. If a counting retired
event is added, it has a "stronger" constraints and will be scheduled before the unconstrained events,
yield the same behavior you wanted, except on demand which is preferable.

Quoted 2 lines

Thanks,
Ravi

#5 lore raw

Re: [PATCH] perf/amd: Implement errata #1292 workaround for F19h M00-0Fh

Hi Stephane,

Quoted 47 lines · Stephane Eranian
Quoted 22 lines · Ravi Bangoria

Hi Stephane,

Quoted 18 lines · Stephane Eranian
Quoted 17 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Above workaround suggests to clear PERF_CTL2[20], but that will disable sampling mode. Given the fact that, there is already a skew between actual counter overflow vs PMI hit, we are anyway not getting accurate count for sampling events. Also, using PMC2 with both bit43 and bit20 set can result in additional issues. Hence Linux implementation of workaround uses non-PMC2 counter for sampling events.

Quoted 9 lines
Quoted 5 lines

Something is missing from your description here. If you are not clearing bit[20] and
not setting bit[43], then how does running on CTL2 by itself improve the count. Is that
enough to make the counter count correctly?

Yes. For counting retire based events, we need PMC2[43] set and PMC2[20] clear so that it will not overcount.

Ok, I get that part now. You are forcing the bits in the get_constraint() function.

Quoted 9 lines
Quoted 8 lines

For sampling events, your patch makes CTL2 not available. That seems to contradict the
workaround. Are you doing this to free CTL2 for counting mode events instead? If you are
not using CTL2, then you are not correcting the count. Are you saying this is okay in sampling mode
because of the skid, anyway?

Quoted 3 lines

Correct. The constraint I am placing is to count retire events on PMC2 and sample retire events on other counters.

Quoted 9 lines

Why do you need to permanently exclude CTL2 for retired events given you are forcing the bits
in the get_constraints() for counting events config only, i.e., as opposed to in CTL2 itself.
If the sampling retired events are unconstrained, they can use any counters. If a counting retired
event is added, it has a "stronger" constraints and will be scheduled before the unconstrained events,
yield the same behavior you wanted, except on demand which is preferable.

Got it. Let me respin.

Thanks,
Ravi

#6 lore raw

PATCH v2 1/1 perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

---
v1: https://lore.kernel.org/r/[email protected]
v1->v2:
- Don't put any constraint on sampling events
- s/errata/erratum/

 arch/x86/events/amd/core.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)
arch/x86/events/amd/core.c +38 -0
index 9687a8aef01c..d4dc5ff35366 100644
@@ -874,6 +874,24 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 	}
 }
 
+/* Overcounting of Retire Based Events Erratum */
+static struct event_constraint retire_event_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC2, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC3, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC4, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC8, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC9, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint pair_constraint;
 
 static struct event_constraint *
@@ -881,10 +899,30 @@ amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
 			       struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct event_constraint *c;
 
 	if (amd_is_pair_event_code(hwc))
 		return &pair_constraint;
 
+	/*
+	 * Although 'Overcounting of Retire Based Events' erratum exists
+	 * for older generation cpus, workaround to set bit 43 works only
+	 * for Family 19h Model 00-0Fh as per the Revision Guide.
+	 */
+	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model <= 0xf) {
+		if (is_sampling_event(event))
+			goto out;
+
+		for_each_event_constraint(c, retire_event_constraints) {
+			if (constraint_match(c, event->hw.config)) {
+				event->hw.config |= (1ULL << 43);
+				event->hw.config &= ~(1ULL << 20);
+				return c;
+			}
+		}
+	}
+
+out:
 	return &unconstrained;
 }
 
Signature · 1 line
2.27.0
maintainer
#7 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 5 lines · Ravi Bangoria
arch/x86/events/amd/core.c +5 -0
+/* Overcounting of Retire Based Events Erratum */
+static struct event_constraint retire_event_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC2, 0x4, AMD64_EVENTSEL_EVENT),

arch/x86/events/amd/core.c amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, · line 891

Quoted 10 lines
arch/x86/events/amd/core.c +10 -0
+	EVENT_CONSTRAINT(0xC3, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC4, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC8, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC9, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),

Can't this be encoded nicer? Something like:

	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT & ~0xF).

To match all of 0xCn ?

Quoted 2 lines
arch/x86/events/amd/core.c +2 -0
+	EVENT_CONSTRAINT_END
+};
#8 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Hi Peter,

Quoted 19 lines · Peter Zijlstra
Quoted 5 lines · Ravi Bangoria
arch/x86/events/amd/core.c +5 -0
+/* Overcounting of Retire Based Events Erratum */
+static struct event_constraint retire_event_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC2, 0x4, AMD64_EVENTSEL_EVENT),

arch/x86/events/amd/core.c amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, · line 891

Quoted 10 lines
arch/x86/events/amd/core.c +10 -0
+	EVENT_CONSTRAINT(0xC3, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC4, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC8, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xC9, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),

Can't this be encoded nicer? Something like:

Quoted 3 lines
	EVENT_CONSTRAINT(0xC0, 0x4, AMD64_EVENTSEL_EVENT & ~0xF).

To match all of 0xCn ?

I don't think so as not all 0xCn events are constrained.

But I can probably use EVENT_CONSTRAINT_RANGE() for continuous event codes:

	EVENT_CONSTRAINT_RANGE(0xC0, 0xC5, 0x4, AMD64_EVENTSEL_EVENT),
	EVENT_CONSTRAINT_RANGE(0xC8, 0xCA, 0x4, AMD64_EVENTSEL_EVENT),

Thanks,
Ravi

#9 lore raw

PATCH v3 1/1 perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

---
v2: https://lore.kernel.org/r/[email protected]
v2->v3:
- Use EVENT_CONSTRAINT_RANGE() for continuous event codes.

 arch/x86/events/amd/core.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
arch/x86/events/amd/core.c +31 -0
index 9687a8aef01c..124ec15851bc 100644
@@ -874,6 +874,17 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 	}
 }
 
+/* Overcounting of Retire Based Events Erratum */
+static struct event_constraint retire_event_constraints[] __read_mostly = {
+	EVENT_CONSTRAINT_RANGE(0xC0, 0xC5, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT_RANGE(0xC8, 0xCA, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xCC, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0xD1, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000C7, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT(0x1000000D0, 0x4, AMD64_EVENTSEL_EVENT),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint pair_constraint;
 
 static struct event_constraint *
@@ -881,10 +892,30 @@ amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
 			       struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct event_constraint *c;
 
 	if (amd_is_pair_event_code(hwc))
 		return &pair_constraint;
 
+	/*
+	 * Although 'Overcounting of Retire Based Events' erratum exists
+	 * for older generation cpus, workaround to set bit 43 works only
+	 * for Family 19h Model 00-0Fh as per the Revision Guide.
+	 */
+	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model <= 0xf) {
+		if (is_sampling_event(event))
+			goto out;
+
+		for_each_event_constraint(c, retire_event_constraints) {
+			if (constraint_match(c, event->hw.config)) {
+				event->hw.config |= (1ULL << 43);
+				event->hw.config &= ~(1ULL << 20);
+				return c;
+			}
+		}
+	}
+
+out:
 	return &unconstrained;
 }
 
Signature · 1 line
2.27.0
maintainer
#10 lore raw

Re: [PATCH v3] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 16 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

Quoted 6 lines

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

Thanks!

#11 lore raw

Re: [PATCH v3] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 17 lines · Peter Zijlstra
Quoted 16 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

Quoted 8 lines
Quoted 6 lines

This patch needs Like's patch[2] to make it work on kvm guest.

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

Thanks!

Peter, On subsequent tests, I found that this 'fix' is still not optimal. Please drop this patch from your queue for now. Really sorry for the noise.

Thanks,
Ravi

maintainer
#12 lore raw

Re: [PATCH v3] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 3 lines · Ravi Bangoria

Peter, On subsequent tests, I found that this 'fix' is still not optimal. Please drop this patch from your queue for now. Really sorry for the noise.

Just in time, and done.

#13 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

In reply to Ravi Bangoria
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Quoted 4 lines

[1] https://bugzilla.kernel.org/attachment.cgi?id=298241
[2] https://lore.kernel.org/lkml/[email protected]

#14 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

  $ ./perf stat -e branch-instructions,branch-misses -- ./branch-misses
   Performance counter stats for './branch-misses':
    19,847,153,209      branch-instructions:u                                         (50.03%)
       950,410,251      branch-misses:u           #    4.79% of all branches          (49.97%)
  $ cat branch-misses.c
  #include <stdlib.h>
  int main()
  {
          long i = 1000000000;
          long j = 0;
          while(i--) {
                  switch(rand() % 20) {
                  case 0:  j += 0; break;
                  case 1:  j += 1; break;
                  case 2:  j += 2; break;
                  case 3:  j += 3; break;
                  case 4:  j += 4; break;
                  case 5:  j += 5; break;
                  case 6:  j += 6; break;
                  case 7:  j += 7; break;
                  case 8:  j += 8; break;
                  case 9:  j += 9; break;
                  case 10: j += 10; break;
                  case 11: j += 11; break;
                  case 12: j += 12; break;
                  case 13: j += 13; break;
                  case 14: j += 14; break;
                  case 15: j += 15; break;
                  case 16: j += 16; break;
                  case 17: j += 17; break;
                  case 18: j += 18; break;
                  case 19: j += 19; break;
                  default: j += 20; break;
                  }
          }
          return 0;

}

Thanks,
Ravi

#15 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 35 lines · Ravi Bangoria

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 8 lines
Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Your guest may be multiplexing the counters. The guest I posited does not.

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

#16 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 41 lines · Jim Mattson
Quoted 40 lines · Ravi Bangoria

Hi Jim,

Quoted 35 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Quoted 5 lines
Quoted 3 lines

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Quoted 3 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

IIUC, multiplexing happens inside the guest.

Thanks,
Ravi

#17 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 45 lines · Ravi Bangoria
Quoted 41 lines · Jim Mattson
Quoted 40 lines · Ravi Bangoria

Hi Jim,

Quoted 35 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Perf on any current Linux distro (i.e. without your fix).

Quoted 5 lines
Quoted 3 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

IIUC, multiplexing happens inside the guest.

I'm not sure that multiplexing is the answer. Extrapolation may introduce greater imprecision than the erratum.

If you count something like "instructions retired" three ways:
1) Unfixed counter
2) PMC2 with the fix
3) Multiplexed on PMC2 with the fix

Is (3) always more accurate than (1)?

Quoted 2 lines

Thanks,
Ravi

author
#18 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 50 lines · Jim Mattson
Quoted 49 lines · Ravi Bangoria
Quoted 45 lines · Jim Mattson
Quoted 43 lines · Ravi Bangoria

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Perf on any current Linux distro (i.e. without your fix).

The patch for errata #1292 (like most hw issues or vulnerabilities) should be applied to both the host and guest.

For non-patched guests on a patched host, the KVM-created perf_events will be true for is_sampling_event() due to get_sample_period().

I think we (KVM) have a congenital defect in distinguishing whether guest counters are used in counting mode or sampling mode, which is just a different use of pure software.

Quoted 9 lines
Quoted 6 lines
Quoted 4 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

IIUC, multiplexing happens inside the guest.

I'm not sure that multiplexing is the answer. Extrapolation may introduce greater imprecision than the erratum.

If you run the same test on the patched host, the PMC2 will be used in a multiplexing way. This is no different.

Quoted 7 lines

If you count something like "instructions retired" three ways:
1) Unfixed counter
2) PMC2 with the fix
3) Multiplexed on PMC2 with the fix

Is (3) always more accurate than (1)?

The loss of accuracy is due to a reduction in the number of trustworthy counters, not to these two workaround patches. Any multiplexing (whatever on the host or the guest) will result in a loss of accuracy. Right ?

I'm not sure if we should provide a sysfs knob for (1), is there a precedent for this ?

Quoted 3 lines
Quoted 3 lines

Thanks,
Ravi

#19 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 52 lines · Like Xu
Quoted 50 lines · Jim Mattson
Quoted 49 lines · Ravi Bangoria
Quoted 45 lines · Jim Mattson
Quoted 43 lines · Ravi Bangoria

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Perf on any current Linux distro (i.e. without your fix).

The patch for errata #1292 (like most hw issues or vulnerabilities) should be applied to both the host and guest.

As I'm sure you are aware, guests are often not patched. For example, we have a lot of Debian-9 guests running on Milan, despite the fact that it has to be booted with "nopcid" due to a bug introduced on 4.9-stable. We submitted the fix and notified Debian about a year ago, but they have not seen fit to cut a new kernel. Do you think they will cut a new kernel for this patch?

Quoted 6 lines

For non-patched guests on a patched host, the KVM-created perf_events will be true for is_sampling_event() due to get_sample_period().

I think we (KVM) have a congenital defect in distinguishing whether guest counters are used in counting mode or sampling mode, which is just a different use of pure software.

I have no idea what you are saying. However, when kvm sees a guest counter used in sampling mode, it will just request a PERF_TYPE_RAW perf event with the INT bit set in 'config.' If it sees a guest counter used in counting mode, it will either request a PERF_TYPE_RAW perf event or a PERF_TYPE_HARDWARE perf event, depending on whether or not it finds the requested event in amd_event_mapping[].

Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 4 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

Quoted 15 lines
Quoted 4 lines
Quoted 1 line

IIUC, multiplexing happens inside the guest.

I'm not sure that multiplexing is the answer. Extrapolation may introduce greater imprecision than the erratum.

If you run the same test on the patched host, the PMC2 will be used in a multiplexing way. This is no different.

Quoted 7 lines

If you count something like "instructions retired" three ways:
1) Unfixed counter
2) PMC2 with the fix
3) Multiplexed on PMC2 with the fix

Is (3) always more accurate than (1)?

Since Ravi has gone dark, I will answer my own question.

For better reproducibility, I simplified his program to:

int main() { return 0;}

On an unpatched Milan host, I get instructions retired between 21911 and 21915. I get branch instructions retired between 5565 and 5566. It does not matter if I count them separately or at the same time.

After applying v3 of Ravi's patch, if I try to count these events at the same time, I get 36869 instructions retired and 4962 branch instructions on the first run. On subsequent runs, perf refuses to count both at the same time. I get branch instructions retired between 5565 and 5567, but no instructions retired. Instead, perf tells me:

Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog

If I just count one thing at a time (on the patched kernel), I get between 21911 and 21916 instructions retired, and I get between 5565 and 5566 branch instructions retired.

I don't know under what circumstances the unfixed counters overcount or by how much. However, for this simple test case, the fixed PMC2 yields the same results as any unfixed counter. Ravi's patch, however makes counting two of these events simultaneously either (a) impossible, or (b) highly inaccurate (from 10% under to 68% over).

Quoted 3 lines

The loss of accuracy is due to a reduction in the number of trustworthy counters, not to these two workaround patches. Any multiplexing (whatever on the host or the guest) will result in a loss of accuracy. Right ?

Yes, that's my point. Fixing one inaccuracy by using a mechanism that introduces another inaccuracy only makes sense if the inaccuracy you are fixing is worse than the inaccuracy you are introducing. That does not appear to be the case here, but I am not privy to all of the details of this erratum.

#20 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Hi Jim,

Quoted 97 lines · Jim Mattson
Quoted 52 lines · Like Xu
Quoted 50 lines · Jim Mattson
Quoted 49 lines · Ravi Bangoria
Quoted 45 lines · Jim Mattson
Quoted 43 lines · Ravi Bangoria

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Perf on any current Linux distro (i.e. without your fix).

The patch for errata #1292 (like most hw issues or vulnerabilities) should be applied to both the host and guest.

As I'm sure you are aware, guests are often not patched. For example, we have a lot of Debian-9 guests running on Milan, despite the fact that it has to be booted with "nopcid" due to a bug introduced on 4.9-stable. We submitted the fix and notified Debian about a year ago, but they have not seen fit to cut a new kernel. Do you think they will cut a new kernel for this patch?

Quoted 6 lines

For non-patched guests on a patched host, the KVM-created perf_events will be true for is_sampling_event() due to get_sample_period().

I think we (KVM) have a congenital defect in distinguishing whether guest counters are used in counting mode or sampling mode, which is just a different use of pure software.

I have no idea what you are saying. However, when kvm sees a guest counter used in sampling mode, it will just request a PERF_TYPE_RAW perf event with the INT bit set in 'config.' If it sees a guest counter used in counting mode, it will either request a PERF_TYPE_RAW perf event or a PERF_TYPE_HARDWARE perf event, depending on whether or not it finds the requested event in amd_event_mapping[].

Quoted 14 lines
Quoted 9 lines
Quoted 6 lines
Quoted 4 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

IIUC, multiplexing happens inside the guest.

I'm not sure that multiplexing is the answer. Extrapolation may introduce greater imprecision than the erratum.

If you run the same test on the patched host, the PMC2 will be used in a multiplexing way. This is no different.

Quoted 1 line
Quoted 8 lines
Quoted 6 lines
Quoted 6 lines

If you count something like "instructions retired" three ways:
1) Unfixed counter
2) PMC2 with the fix
3) Multiplexed on PMC2 with the fix

Is (3) always more accurate than (1)?

Since Ravi has gone dark, I will answer my own question.

Sorry about the delay. I was discussing this internally with hw folks.

Quoted 24 lines

For better reproducibility, I simplified his program to:

int main() { return 0;}

On an unpatched Milan host, I get instructions retired between 21911 and 21915. I get branch instructions retired between 5565 and 5566. It does not matter if I count them separately or at the same time.

After applying v3 of Ravi's patch, if I try to count these events at the same time, I get 36869 instructions retired and 4962 branch instructions on the first run. On subsequent runs, perf refuses to count both at the same time. I get branch instructions retired between 5565 and 5567, but no instructions retired. Instead, perf tells me:

Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog

If I just count one thing at a time (on the patched kernel), I get between 21911 and 21916 instructions retired, and I get between 5565 and 5566 branch instructions retired.

Quoted 5 lines

I don't know under what circumstances the unfixed counters overcount or by how much. However, for this simple test case, the fixed PMC2 yields the same results as any unfixed counter. Ravi's patch, however makes counting two of these events simultaneously either (a) impossible, or (b) highly inaccurate (from 10% under to 68% over).

In further discussions with our hardware team, I am given to understand that the conditions under which the overcounting can happen, is quite rare. In my tests, I've found that the patched vs. unpatched cases are not significantly different to warrant the restriction introduced by this fix. I have requested Peter to hold off pushing this fix.

Quoted 10 lines
Quoted 4 lines

The loss of accuracy is due to a reduction in the number of trustworthy counters, not to these two workaround patches. Any multiplexing (whatever on the host or the guest) will result in a loss of accuracy. Right ?

Yes, that's my point. Fixing one inaccuracy by using a mechanism that introduces another inaccuracy only makes sense if the inaccuracy you are fixing is worse than the inaccuracy you are introducing. That does not appear to be the case here, but I am not privy to all of the details of this erratum.

Thanks,
Ravi

author
#21 lore raw

Re: [PATCH v2] perf/amd: Implement erratum #1292 workaround for F19h M00-0Fh

Quoted 66 lines · Ravi Bangoria

Hi Jim,

Quoted 63 lines · Jim Mattson
Quoted 52 lines · Like Xu
Quoted 50 lines · Jim Mattson
Quoted 49 lines · Ravi Bangoria
Quoted 45 lines · Jim Mattson
Quoted 43 lines · Ravi Bangoria

Hi Jim,

Quoted 31 lines · Jim Mattson
Quoted 10 lines · Ravi Bangoria

Perf counter may overcount for a list of Retire Based Events. Implement workaround for Zen3 Family 19 Model 00-0F processors as suggested in Revision Guide[1]:

To count the non-FP affected PMC events correctly:
o Use Core::X86::Msr::PERF_CTL2 to count the events, and
o Program Core::X86::Msr::PERF_CTL2[43] to 1b, and
o Program Core::X86::Msr::PERF_CTL2[20] to 0b.

Quoted 8 lines

Note that the specified workaround applies only to counting events and not to sampling events. Thus sampling event will continue functioning as is.

Although the issue exists on all previous Zen revisions, the workaround is different and thus not included in this patch.

This patch needs Like's patch[2] to make it work on kvm guest.

IIUC, this patch along with Like's patch actually breaks PMU virtualization for a kvm guest.

Suppose I have some code which counts event 0xC2 [Retired Branch Instructions] on PMC0 and event 0xC4 [Retired Taken Branch Instructions] on PMC1. I then divide PMC1 by PMC0 to see what percentage of my branch instructions are taken. On hardware that suffers from erratum 1292, both counters may overcount, but if the inaccuracy is small, then my final result may still be fairly close to reality.

Quoted 4 lines

With these patches, if I run that same code in a kvm guest, it looks like one of those events will be counted on PMC2 and the other won't be counted at all. So, when I calculate the percentage of branch instructions taken, I either get 0 or infinity.

Events get multiplexed internally. See below quick test I ran inside guest. My host is running with my+Like's patch and guest is running with only my patch.

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Your guest may be multiplexing the counters. The guest I posited does not.

It would be helpful if you can provide an example.

Perf on any current Linux distro (i.e. without your fix).

The patch for errata #1292 (like most hw issues or vulnerabilities) should be applied to both the host and guest.

As I'm sure you are aware, guests are often not patched. For example,

It's true. What a real world.

Quoted 5 lines
Quoted 5 lines

we have a lot of Debian-9 guests running on Milan, despite the fact that it has to be booted with "nopcid" due to a bug introduced on 4.9-stable. We submitted the fix and notified Debian about a year ago, but they have not seen fit to cut a new kernel. Do you think they will cut a new kernel for this patch?

Indeed, thanks for your user stories.

Quoted 11 lines
Quoted 11 lines
Quoted 7 lines

For non-patched guests on a patched host, the KVM-created perf_events will be true for is_sampling_event() due to get_sample_period().

I think we (KVM) have a congenital defect in distinguishing whether guest counters are used in counting mode or sampling mode, which is just a different use of pure software.

I have no idea what you are saying. However, when kvm sees a guest counter used in sampling mode, it will just request a PERF_TYPE_RAW perf event with the INT bit set in 'config.' If it sees a guest

The counters work very simply: increments until it overflows.

The use of INT bit is not related to counting or sampling mode. A pmu driver can set the INT bit, but set a very small ctr value and not expect it to overflow, and it can be used for counting mode as well, right?

We don't know under what circumstances the overcount will occur, maybe it's related to the INT bit and maybe bot, but absolutely it's nothing to do with the software check is_sampling_event().

Quoted 59 lines
Quoted 18 lines

counter used in counting mode, it will either request a PERF_TYPE_RAW perf event or a PERF_TYPE_HARDWARE perf event, depending on whether or not it finds the requested event in amd_event_mapping[].

Quoted 14 lines
Quoted 9 lines
Quoted 6 lines
Quoted 4 lines

I hope that you are not saying that kvm's *thread-pinned* perf events are not being multiplexed at the host level, because that completely breaks PMU virtualization.

IIUC, multiplexing happens inside the guest.

I'm not sure that multiplexing is the answer. Extrapolation may introduce greater imprecision than the erratum.

If you run the same test on the patched host, the PMC2 will be used in a multiplexing way. This is no different.

Quoted 1 line
Quoted 8 lines
Quoted 6 lines
Quoted 6 lines

If you count something like "instructions retired" three ways:
1) Unfixed counter
2) PMC2 with the fix
3) Multiplexed on PMC2 with the fix

Is (3) always more accurate than (1)?

Since Ravi has gone dark, I will answer my own question.

Sorry about the delay. I was discussing this internally with hw folks.

Quoted 24 lines

For better reproducibility, I simplified his program to:

int main() { return 0;}

On an unpatched Milan host, I get instructions retired between 21911 and 21915. I get branch instructions retired between 5565 and 5566. It does not matter if I count them separately or at the same time.

After applying v3 of Ravi's patch, if I try to count these events at the same time, I get 36869 instructions retired and 4962 branch instructions on the first run. On subsequent runs, perf refuses to count both at the same time. I get branch instructions retired between 5565 and 5567, but no instructions retired. Instead, perf tells me:

Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog

If I just count one thing at a time (on the patched kernel), I get between 21911 and 21916 instructions retired, and I get between 5565 and 5566 branch instructions retired.

Quoted 5 lines

I don't know under what circumstances the unfixed counters overcount or by how much. However, for this simple test case, the fixed PMC2 yields the same results as any unfixed counter. Ravi's patch, however makes counting two of these events simultaneously either (a) impossible, or (b) highly inaccurate (from 10% under to 68% over).

Quoted 4 lines

In further discussions with our hardware team, I am given to understand that the conditions under which the overcounting can happen, is quite rare. In my tests, I've found that the patched vs. unpatched cases are not significantly different to warrant the restriction introduced by

That's cute and thank you both.

I hope we can come to this conclusion before the code is committed.

But the kvm's patch may have made those PMU driver developers who read the erratum #1292 a little happier, wouldn't it ?

Quoted 10 lines

this fix. I have requested Peter to hold off pushing this fix.

Quoted 8 lines
Quoted 4 lines

The loss of accuracy is due to a reduction in the number of trustworthy counters, not to these two workaround patches. Any multiplexing (whatever on the host or the guest) will result in a loss of accuracy. Right ?

Yes, that's my point. Fixing one inaccuracy by using a mechanism that introduces another inaccuracy only makes sense if the inaccuracy you are fixing is worse than the inaccuracy you are introducing. That does

Couldn't agree more, and in response to similar issues, we may adopt a quantitative-first strategy in the future.

Quoted 5 lines
Quoted 2 lines

not appear to be the case here, but I am not privy to all of the details of this erratum.

Thanks,
Ravi