Merge tag 'kvm-x86-pmu-6.9' of https://github.com/kvm-x86/linux into HEAD

KVM x86 PMU changes for 6.9:

 - Fix several bugs where KVM speciously prevents the guest from utilizing
   fixed counters and architectural event encodings based on whether or not
   guest CPUID reports support for the _architectural_ encoding.

 - Fix a variety of bugs in KVM's emulation of RDPMC, e.g. for "fast" reads,
   priority of VMX interception vs #GP, PMC types in architectural PMUs, etc.

 - Add a selftest to verify KVM correctly emulates RDMPC, counter availability,
   and a variety of other PMC-related behaviors that depend on guest CPUID,
   i.e. are difficult to validate via KVM-Unit-Tests.

 - Zero out PMU metadata on AMD if the virtual PMU is disabled to avoid wasting
   cycles, e.g. when checking if a PMC event needs to be synthesized when
   skipping an instruction.

 - Optimize triggering of emulated events, e.g. for "count instructions" events
   when skipping an instruction, which yields a ~10% performance improvement in
   VM-Exit microbenchmarks when a vPMU is exposed to the guest.

 - Tighten the check for "PMI in guest" to reduce false positives if an NMI
   arrives in the host while KVM is handling an IRQ VM-Exit.

Author: bonzini

arch/x86/include/asm/kvm-x86-pmu-ops.h

@@ -12,11 +12,9 @@ BUILD_BUG_ON(1)
  * a NULL definition, for example if "static_call_cond()" will be used
  * at the call sites.
  */
-KVM_X86_PMU_OP(hw_event_available)
-KVM_X86_PMU_OP(pmc_idx_to_pmc)
 KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
 KVM_X86_PMU_OP(msr_idx_to_pmc)
-KVM_X86_PMU_OP(is_valid_rdpmc_ecx)
+KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early)
 KVM_X86_PMU_OP(is_valid_msr)
 KVM_X86_PMU_OP(get_msr)
 KVM_X86_PMU_OP(set_msr)

arch/x86/include/asm/kvm_host.h

@@ -536,6 +536,7 @@ struct kvm_pmc {
 #define KVM_PMC_MAX_FIXED	3
 #define MSR_ARCH_PERFMON_FIXED_CTR_MAX	(MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1)
 #define KVM_AMD_PMC_MAX_GENERIC	6
+
 struct kvm_pmu {
 	u8 version;
 	unsigned nr_arch_gp_counters;
@@ -1889,8 +1890,16 @@ static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
 }
 #endif /* CONFIG_HYPERV */
 
+enum kvm_intr_type {
+	/* Values are arbitrary, but must be non-zero. */
+	KVM_HANDLING_IRQ = 1,
+	KVM_HANDLING_NMI,
+};
+
+/* Enable perf NMI and timer modes to work, and minimise false positives. */
 #define kvm_arch_pmi_in_guest(vcpu) \
-	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
+	((vcpu) && (vcpu)->arch.handling_intr_from_guest && \
+	 (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI)))
 
 void __init kvm_mmu_x86_module_init(void);
 int kvm_mmu_vendor_module_init(void);

arch/x86/kvm/emulate.c

@@ -3955,7 +3955,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 	 * protected mode.
 	 */
 	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
-	    ctxt->ops->check_pmc(ctxt, rcx))
+	    ctxt->ops->check_rdpmc_early(ctxt, rcx))
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;

arch/x86/kvm/kvm_emulate.h

@@ -208,7 +208,7 @@ struct x86_emulate_ops {
 	int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
-	int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
+	int (*check_rdpmc_early)(struct x86_emulate_ctxt *ctxt, u32 pmc);
 	int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);

arch/x86/kvm/pmu.c

@@ -29,6 +29,9 @@
 struct x86_pmu_capability __read_mostly kvm_pmu_cap;
 EXPORT_SYMBOL_GPL(kvm_pmu_cap);
 
+struct kvm_pmu_emulated_event_selectors __read_mostly kvm_pmu_eventsel;
+EXPORT_SYMBOL_GPL(kvm_pmu_eventsel);
+
 /* Precise Distribution of Instructions Retired (PDIR) */
 static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL),
@@ -67,7 +70,7 @@ static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = {
  *        all perf counters (both gp and fixed). The mapping relationship
  *        between pmc and perf counters is as the following:
  *        * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters
- *                 [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
+ *                 [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed
  *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
  *          and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
  */
@@ -411,7 +414,7 @@ static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f,
 static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter,
 				   int idx)
 {
-	int fixed_idx = idx - INTEL_PMC_IDX_FIXED;
+	int fixed_idx = idx - KVM_FIXED_PMC_BASE_IDX;
 
 	if (filter->action == KVM_PMU_EVENT_DENY &&
 	    test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap))
@@ -441,11 +444,10 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 static bool pmc_event_is_allowed(struct kvm_pmc *pmc)
 {
 	return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) &&
-	       static_call(kvm_x86_pmu_hw_event_available)(pmc) &&
 	       check_pmu_event_filter(pmc);
 }
 
-static void reprogram_counter(struct kvm_pmc *pmc)
+static int reprogram_counter(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 eventsel = pmc->eventsel;
@@ -456,7 +458,7 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	emulate_overflow = pmc_pause_counter(pmc);
 
 	if (!pmc_event_is_allowed(pmc))
-		goto reprogram_complete;
+		return 0;
 
 	if (emulate_overflow)
 		__kvm_perf_overflow(pmc, false);
@@ -466,7 +468,7 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 
 	if (pmc_is_fixed(pmc)) {
 		fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl,
-						  pmc->idx - INTEL_PMC_IDX_FIXED);
+						  pmc->idx - KVM_FIXED_PMC_BASE_IDX);
 		if (fixed_ctr_ctrl & 0x1)
 			eventsel |= ARCH_PERFMON_EVENTSEL_OS;
 		if (fixed_ctr_ctrl & 0x2)
@@ -477,43 +479,45 @@ static void reprogram_counter(struct kvm_pmc *pmc)
 	}
 
 	if (pmc->current_config == new_config && pmc_resume_counter(pmc))
-		goto reprogram_complete;
+		return 0;
 
 	pmc_release_perf_event(pmc);
 
 	pmc->current_config = new_config;
 
-	/*
-	 * If reprogramming fails, e.g. due to contention, leave the counter's
-	 * regprogram bit set, i.e. opportunistically try again on the next PMU
-	 * refresh.  Don't make a new request as doing so can stall the guest
-	 * if reprogramming repeatedly fails.
-	 */
-	if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
-				  (eventsel & pmu->raw_event_mask),
-				  !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
-				  !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-				  eventsel & ARCH_PERFMON_EVENTSEL_INT))
-		return;
-
-reprogram_complete:
-	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+	return pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
+				     (eventsel & pmu->raw_event_mask),
+				     !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+				     !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+				     eventsel & ARCH_PERFMON_EVENTSEL_INT);
 }
 
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
+	DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
 	int bit;
 
-	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);
+	bitmap_copy(bitmap, pmu->reprogram_pmi, X86_PMC_IDX_MAX);
 
-		if (unlikely(!pmc)) {
-			clear_bit(bit, pmu->reprogram_pmi);
-			continue;
-		}
+	/*
+	 * The reprogramming bitmap can be written asynchronously by something
+	 * other than the task that holds vcpu->mutex, take care to clear only
+	 * the bits that will actually processed.
+	 */
+	BUILD_BUG_ON(sizeof(bitmap) != sizeof(atomic64_t));
+	atomic64_andnot(*(s64 *)bitmap, &pmu->__reprogram_pmi);
 
-		reprogram_counter(pmc);
+	kvm_for_each_pmc(pmu, pmc, bit, bitmap) {
+		/*
+		 * If reprogramming fails, e.g. due to contention, re-set the
+		 * regprogram bit set, i.e. opportunistically try again on the
+		 * next PMU refresh.  Don't make a new request as doing so can
+		 * stall the guest if reprogramming repeatedly fails.
+		 */
+		if (reprogram_counter(pmc))
+			set_bit(pmc->idx, pmu->reprogram_pmi);
 	}
 
 	/*
@@ -525,10 +529,20 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 		kvm_pmu_cleanup(vcpu);
 }
 
-/* check if idx is a valid index to access PMU */
-bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
 {
-	return static_call(kvm_x86_pmu_is_valid_rdpmc_ecx)(vcpu, idx);
+	/*
+	 * On Intel, VMX interception has priority over RDPMC exceptions that
+	 * aren't already handled by the emulator, i.e. there are no additional
+	 * check needed for Intel PMUs.
+	 *
+	 * On AMD, _all_ exceptions on RDPMC have priority over SVM intercepts,
+	 * i.e. an invalid PMC results in a #GP, not #VMEXIT.
+	 */
+	if (!kvm_pmu_ops.check_rdpmc_early)
+		return 0;
+
+	return static_call(kvm_x86_pmu_check_rdpmc_early)(vcpu, idx);
 }
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -567,10 +581,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
-	bool fast_mode = idx & (1u << 31);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 mask = fast_mode ? ~0u : ~0ull;
+	u64 mask = ~0ull;
 
 	if (!pmu->version)
 		return 1;
@@ -716,11 +729,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 
 	bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX);
 
-	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
-		if (!pmc)
-			continue;
-
+	kvm_for_each_pmc(pmu, pmc, i, pmu->all_valid_pmc_idx) {
 		pmc_stop_counter(pmc);
 		pmc->counter = 0;
 		pmc->emulated_counter = 0;
@@ -741,6 +750,8 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
  */
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm))
 		return;
 
@@ -750,8 +761,22 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 	 */
 	kvm_pmu_reset(vcpu);
 
-	bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX);
-	static_call(kvm_x86_pmu_refresh)(vcpu);
+	pmu->version = 0;
+	pmu->nr_arch_gp_counters = 0;
+	pmu->nr_arch_fixed_counters = 0;
+	pmu->counter_bitmask[KVM_PMC_GP] = 0;
+	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
+	pmu->global_ctrl_mask = ~0ull;
+	pmu->global_status_mask = ~0ull;
+	pmu->fixed_ctr_ctrl_mask = ~0ull;
+	pmu->pebs_enable_mask = ~0ull;
+	pmu->pebs_data_cfg_mask = ~0ull;
+	bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
+
+	if (vcpu->kvm->arch.enable_pmu)
+		static_call(kvm_x86_pmu_refresh)(vcpu);
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
@@ -776,10 +801,8 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
 	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
 		      pmu->pmc_in_use, X86_PMC_IDX_MAX);
 
-	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
-
-		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+	kvm_for_each_pmc(pmu, pmc, i, bitmask) {
+		if (pmc->perf_event && !pmc_speculative_in_use(pmc))
 			pmc_stop_counter(pmc);
 	}
 
@@ -799,13 +822,6 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 	kvm_pmu_request_counter_reprogram(pmc);
 }
 
-static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
-	unsigned int perf_hw_id)
-{
-	return !((pmc->eventsel ^ perf_get_hw_event_config(perf_hw_id)) &
-		AMD64_RAW_EVENT_MASK_NB);
-}
-
 static inline bool cpl_is_matched(struct kvm_pmc *pmc)
 {
 	bool select_os, select_user;
@@ -817,29 +833,56 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc)
 		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);
+					  pmc->idx - KVM_FIXED_PMC_BASE_IDX);
 		select_os = config & 0x1;
 		select_user = config & 0x2;
 	}
 
+	/*
+	 * Skip the CPL lookup, which isn't free on Intel, if the result will
+	 * be the same regardless of the CPL.
+	 */
+	if (select_os == select_user)
+		return select_os;
+
 	return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user;
 }
 
-void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id)
+void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel)
 {
+	DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
 	int i;
 
-	for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) {
-		pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i);
+	BUILD_BUG_ON(sizeof(pmu->global_ctrl) * BITS_PER_BYTE != X86_PMC_IDX_MAX);
 
-		if (!pmc || !pmc_event_is_allowed(pmc))
+	if (!kvm_pmu_has_perf_global_ctrl(pmu))
+		bitmap_copy(bitmap, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	else if (!bitmap_and(bitmap, pmu->all_valid_pmc_idx,
+			     (unsigned long *)&pmu->global_ctrl, X86_PMC_IDX_MAX))
+		return;
+
+	kvm_for_each_pmc(pmu, pmc, i, bitmap) {
+		/*
+		 * Ignore checks for edge detect (all events currently emulated
+		 * but KVM are always rising edges), pin control (unsupported
+		 * by modern CPUs), and counter mask and its invert flag (KVM
+		 * doesn't emulate multiple events in a single clock cycle).
+		 *
+		 * Note, the uppermost nibble of AMD's mask overlaps Intel's
+		 * IN_TX (bit 32) and IN_TXCP (bit 33), as well as two reserved
+		 * bits (bits 35:34).  Checking the "in HLE/RTM transaction"
+		 * flags is correct as the vCPU can't be in a transaction if
+		 * KVM is emulating an instruction.  Checking the reserved bits
+		 * might be wrong if they are defined in the future, but so
+		 * could ignoring them, so do the simple thing for now.
+		 */
+		if (((pmc->eventsel ^ eventsel) & AMD64_RAW_EVENT_MASK_NB) ||
+		    !pmc_event_is_allowed(pmc) || !cpl_is_matched(pmc))
 			continue;
 
-		/* Ignore checks for edge detect, pin control, invert and CMASK bits */
-		if (eventsel_match_perf_hw_id(pmc, perf_hw_id) && cpl_is_matched(pmc))
-			kvm_pmu_incr_counter(pmc);
+		kvm_pmu_incr_counter(pmc);
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);