Re: [PATCH 05/32] perf, kvm: Support the intx/intx_cp modifiers inKVM arch perfmon emulation v3

[Andi Kleen]

Here's an updated version addressing Gleb's comments. 
I won't repost the full series this week, but I have updated the git tree.
Let me know if anyone wants a full repost.

-Andi

---

perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v4

This is not arch perfmon, but older CPUs will just ignore it. This makes
it possible to do at least some TSX measurements from a KVM guest

Cc: avi@xxxxxxxxxx
Cc: gleb@xxxxxxxxxx
v2: Various fixes to address review feedback
v3: Ignore the bits when no CPUID. No #GP. Force raw events with TSX bits.
v4: Use reserved bits for #GP
Cc: gleb@xxxxxxxxxx
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b2e11f4..63d4be4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -318,6 +318,7 @@ struct kvm_pmu {
 	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
+	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index cfc258a..89405d0 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
 
 static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		unsigned config, bool exclude_user, bool exclude_kernel,
-		bool intr)
+		bool intr, bool intx, bool intx_cp)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+	if (intx)
+		attr.config |= HSW_INTX;
+	if (intx_cp)
+		attr.config |= HSW_INTX_CHECKPOINTED;
 
 	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
 
@@ -206,7 +210,8 @@ static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select,
 	return arch_events[i].event_type;
 }
 
-static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
+static void reprogram_gp_counter(struct kvm_pmu *pmu, struct kvm_pmc *pmc, 
+				 u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
@@ -226,7 +231,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 				ARCH_PERFMON_EVENTSEL_INV |
-				ARCH_PERFMON_EVENTSEL_CMASK))) {
+				ARCH_PERFMON_EVENTSEL_CMASK |
+				HSW_INTX |
+				HSW_INTX_CHECKPOINTED))) {
 		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
 				unit_mask);
 		if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +246,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	reprogram_counter(pmc, type, config,
 			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			eventsel & ARCH_PERFMON_EVENTSEL_INT);
+			eventsel & ARCH_PERFMON_EVENTSEL_INT,
+			(eventsel & HSW_INTX),
+			(eventsel & HSW_INTX_CHECKPOINTED));
 }
 
 static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +265,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
 			arch_events[fixed_pmc_events[idx]].event_type,
 			!(en & 0x2), /* exclude user */
 			!(en & 0x1), /* exclude kernel */
-			pmi);
+			pmi, false, false);
 }
 
 static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -289,7 +298,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx)
 		return;
 
 	if (pmc_is_gp(pmc))
-		reprogram_gp_counter(pmc, pmc->eventsel);
+		reprogram_gp_counter(pmu, pmc, pmc->eventsel);
 	else {
 		int fidx = idx - INTEL_PMC_IDX_FIXED;
 		reprogram_fixed_counter(pmc,
@@ -400,8 +409,8 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
 				return 0;
-			if (!(data & 0xffffffff00200000ull)) {
-				reprogram_gp_counter(pmc, data);
+			if (!(data & pmu->reserved_bits)) {
+				reprogram_gp_counter(pmu, pmc, data);
 				return 0;
 			}
 		}
@@ -442,6 +451,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_GP] = 0;
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -470,6 +480,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (entry &&
+	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+		pmu->reserved_bits ^= HSW_INTX|HSW_INTX_CHECKPOINTED;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
--
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/