[PATCH 3/4] KVM: x86/pmu: Defer reprogram_counter() to kvm_pmu_handle_event()

[Sean Christopherson]

From: Like Xu <likexu@xxxxxxxxxxx>

Batch reprogramming PMU counters by setting KVM_REQ_PMU and thus
deferring reprogramming kvm_pmu_handle_event() to avoid reprogramming
a counter multiple times during a single VM-Exit.

Deferring programming will also allow KVM to fix a bug where immediately
reprogramming a counter can result in sleeping (taking a mutex) while
interrupts are disabled in the VM-Exit fastpath.

Introduce kvm_pmu_request_counter_reprogam() to make it obvious that
KVM is _requesting_ a reprogram and not actually doing the reprogram.

Opportunistically refine related comments to avoid misunderstandings.

Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
Link: https://lore.kernel.org/r/20220831085328.45489-5-likexu@xxxxxxxxxxx
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/pmu.c              | 17 ++++++++++++-----
 arch/x86/kvm/pmu.h              |  6 +++++-
 arch/x86/kvm/svm/pmu.c          |  2 +-
 arch/x86/kvm/vmx/pmu_intel.c    |  6 +++---
 5 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 462f041ede9f..12dcfc9330e7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -493,6 +493,7 @@ struct kvm_pmc {
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
 	/*
+	 * only for creating or reusing perf_event,
 	 * eventsel value for general purpose counters,
 	 * ctrl value for fixed counters.
 	 */
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 4cd99320019b..d8330e6064ab 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -101,7 +101,11 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	bool skip_pmi = false;
 
-	/* Ignore counters that have been reprogrammed already. */
+	/*
+	 * Ignore overflow events for counters that are scheduled to be
+	 * reprogrammed, e.g. if a PMI for the previous event races with KVM's
+	 * handling of a related guest WRMSR.
+	 */
 	if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi))
 		return;
 
@@ -292,7 +296,7 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 	return allow_event;
 }
 
-void reprogram_counter(struct kvm_pmc *pmc)
+static void reprogram_counter(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 eventsel = pmc->eventsel;
@@ -345,7 +349,6 @@ void reprogram_counter(struct kvm_pmc *pmc)
 reprogram_complete:
 	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
 }
-EXPORT_SYMBOL_GPL(reprogram_counter);
 
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
@@ -355,10 +358,11 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
 		struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit);
 
-		if (unlikely(!pmc || !pmc->perf_event)) {
+		if (unlikely(!pmc)) {
 			clear_bit(bit, pmu->reprogram_pmi);
 			continue;
 		}
+
 		reprogram_counter(pmc);
 	}
 
@@ -552,12 +556,15 @@ static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
 static inline bool cpl_is_matched(struct kvm_pmc *pmc)
 {
 	bool select_os, select_user;
-	u64 config = pmc->current_config;
+	u64 config;
 
 	if (pmc_is_gp(pmc)) {
+		config = pmc->eventsel;
 		select_os = config & ARCH_PERFMON_EVENTSEL_OS;
 		select_user = config & ARCH_PERFMON_EVENTSEL_USR;
 	} else {
+		config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl,
+					  pmc->idx - INTEL_PMC_IDX_FIXED);
 		select_os = config & 0x1;
 		select_user = config & 0x2;
 	}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 5cc5721f260b..85ff3c0588ba 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -183,7 +183,11 @@ static inline void kvm_init_pmu_capability(void)
 					     KVM_PMC_MAX_FIXED);
 }
 
-void reprogram_counter(struct kvm_pmc *pmc);
+static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc)
+{
+	set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+	kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+}
 
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index b68956299fa8..041aa898e1bc 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -159,7 +159,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		data &= ~pmu->reserved_bits;
 		if (data != pmc->eventsel) {
 			pmc->eventsel = data;
-			reprogram_counter(pmc);
+			kvm_pmu_request_counter_reprogam(pmc);
 		}
 		return 0;
 	}
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 25b70a85bef5..e38518afc265 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -52,7 +52,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 		pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
 
 		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
-		reprogram_counter(pmc);
+		kvm_pmu_request_counter_reprogam(pmc);
 	}
 }
 
@@ -76,7 +76,7 @@ static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
 	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
 		pmc = intel_pmc_idx_to_pmc(pmu, bit);
 		if (pmc)
-			reprogram_counter(pmc);
+			kvm_pmu_request_counter_reprogam(pmc);
 	}
 }
 
@@ -477,7 +477,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
 			if (!(data & reserved_bits)) {
 				pmc->eventsel = data;
-				reprogram_counter(pmc);
+				kvm_pmu_request_counter_reprogam(pmc);
 				return 0;
 			}
 		} else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false))
-- 
2.37.3.998.g577e59143f-goog