1 files changed, 102 insertions, 110 deletions

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 3f868fed9114..02f9e4f245bd 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -16,6 +16,7 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 #include <asm/perf_event.h>
+#include <asm/cpu_device_id.h>
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
@@ -24,6 +25,15 @@
 /* This is enough to filter the vast majority of currently defined events. */
 #define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300
 
+struct x86_pmu_capability __read_mostly kvm_pmu_cap;
+EXPORT_SYMBOL_GPL(kvm_pmu_cap);
+
+static const struct x86_cpu_id vmx_icl_pebs_cpu[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, NULL),
+	{}
+};
+
 /* NOTE:
  * - Each perf counter is defined as "struct kvm_pmc";
  * - There are two types of perf counters: general purpose (gp) and fixed.
@@ -34,7 +44,9 @@
  *   However AMD doesn't support fixed-counters;
  * - There are three types of index to access perf counters (PMC):
  *     1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD
- *        has MSR_K7_PERFCTRn.
+ *        has MSR_K7_PERFCTRn and, for families 15H and later,
+ *        MSR_F15H_PERF_CTRn, where MSR_F15H_PERF_CTR[0-3] are
+ *        aliased to MSR_K7_PERFCTRn.
  *     2. MSR Index (named idx): This normally is used by RDPMC instruction.
  *        For instance AMD RDPMC instruction uses 0000_0003h in ECX to access
  *        C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except
@@ -46,7 +58,8 @@
  *        between pmc and perf counters is as the following:
  *        * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters
  *                 [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
- *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters
+ *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
+ *          and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
  */
 
 static struct kvm_pmu_ops kvm_pmu_ops __read_mostly;
@@ -86,15 +99,22 @@ static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
 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. */
 	if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi))
 		return;
 
-	__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+	if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
+		/* Indicate PEBS overflow PMI to guest. */
+		skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
+					      (unsigned long *)&pmu->global_status);
+	} else {
+		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+	}
 	kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 
-	if (!pmc->intr)
+	if (!pmc->intr || skip_pmi)
 		return;
 
 	/*
@@ -124,6 +144,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 				  u64 config, bool exclude_user,
 				  bool exclude_kernel, bool intr)
 {
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	struct perf_event *event;
 	struct perf_event_attr attr = {
 		.type = type,
@@ -135,9 +156,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
-
-	if (type == PERF_TYPE_HARDWARE && config >= PERF_COUNT_HW_MAX)
-		return;
+	bool pebs = test_bit(pmc->idx, (unsigned long *)&pmu->pebs_enable);
 
 	attr.sample_period = get_sample_period(pmc, pmc->counter);
 
@@ -150,6 +169,25 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		 */
 		attr.sample_period = 0;
 	}
+	if (pebs) {
+		/*
+		 * The non-zero precision level of guest event makes the ordinary
+		 * guest event becomes a guest PEBS event and triggers the host
+		 * PEBS PMI handler to determine whether the PEBS overflow PMI
+		 * comes from the host counters or the guest.
+		 *
+		 * For most PEBS hardware events, the difference in the software
+		 * precision levels of guest and host PEBS events will not affect
+		 * the accuracy of the PEBS profiling result, because the "event IP"
+		 * in the PEBS record is calibrated on the guest side.
+		 *
+		 * On Icelake everything is fine. Other hardware (GLC+, TNT+) that
+		 * could possibly care here is unsupported and needs changes.
+		 */
+		attr.precise_ip = 1;
+		if (x86_match_cpu(vmx_icl_pebs_cpu) && pmc->idx == 32)
+			attr.precise_ip = 3;
+	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_perf_overflow, pmc);
@@ -163,7 +201,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	pmc_to_pmu(pmc)->event_count++;
 	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
 	pmc->is_paused = false;
-	pmc->intr = intr;
+	pmc->intr = intr || pebs;
 }
 
 static void pmc_pause_counter(struct kvm_pmc *pmc)
@@ -189,6 +227,10 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 			      get_sample_period(pmc, pmc->counter)))
 		return false;
 
+	if (!test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) &&
+	    pmc->perf_event->attr.precise_ip)
+		return false;
+
 	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
 	perf_event_enable(pmc->perf_event);
 	pmc->is_paused = false;
@@ -205,115 +247,83 @@ static int cmp_u64(const void *pa, const void *pb)
 	return (a > b) - (a < b);
 }
 
-void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
+static bool check_pmu_event_filter(struct kvm_pmc *pmc)
 {
-	u64 config;
-	u32 type = PERF_TYPE_RAW;
-	struct kvm *kvm = pmc->vcpu->kvm;
 	struct kvm_pmu_event_filter *filter;
-	struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
+	struct kvm *kvm = pmc->vcpu->kvm;
 	bool allow_event = true;
+	__u64 key;
+	int idx;
 
-	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
-		printk_once("kvm pmu: pin control bit is ignored\n");
-
-	pmc->eventsel = eventsel;
-
-	pmc_pause_counter(pmc);
-
-	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
-		return;
+	if (!static_call(kvm_x86_pmu_hw_event_available)(pmc))
+		return false;
 
 	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
-	if (filter) {
-		__u64 key = eventsel & AMD64_RAW_EVENT_MASK_NB;
+	if (!filter)
+		goto out;
 
+	if (pmc_is_gp(pmc)) {
+		key = pmc->eventsel & AMD64_RAW_EVENT_MASK_NB;
 		if (bsearch(&key, filter->events, filter->nevents,
 			    sizeof(__u64), cmp_u64))
 			allow_event = filter->action == KVM_PMU_EVENT_ALLOW;
 		else
 			allow_event = filter->action == KVM_PMU_EVENT_DENY;
+	} else {
+		idx = pmc->idx - INTEL_PMC_IDX_FIXED;
+		if (filter->action == KVM_PMU_EVENT_DENY &&
+		    test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
+			allow_event = false;
+		if (filter->action == KVM_PMU_EVENT_ALLOW &&
+		    !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
+			allow_event = false;
 	}
-	if (!allow_event)
-		return;
-
-	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
-			  ARCH_PERFMON_EVENTSEL_INV |
-			  ARCH_PERFMON_EVENTSEL_CMASK |
-			  HSW_IN_TX |
-			  HSW_IN_TX_CHECKPOINTED))) {
-		config = static_call(kvm_x86_pmu_pmc_perf_hw_id)(pmc);
-		if (config != PERF_COUNT_HW_MAX)
-			type = PERF_TYPE_HARDWARE;
-	}
-
-	if (type == PERF_TYPE_RAW)
-		config = eventsel & pmu->raw_event_mask;
-
-	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
-		return;
-
-	pmc_release_perf_event(pmc);
 
-	pmc->current_config = eventsel;
-	pmc_reprogram_counter(pmc, type, config,
-			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
-			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			      eventsel & ARCH_PERFMON_EVENTSEL_INT);
+out:
+	return allow_event;
 }
-EXPORT_SYMBOL_GPL(reprogram_gp_counter);
 
-void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
+void reprogram_counter(struct kvm_pmc *pmc)
 {
-	unsigned en_field = ctrl & 0x3;
-	bool pmi = ctrl & 0x8;
-	struct kvm_pmu_event_filter *filter;
-	struct kvm *kvm = pmc->vcpu->kvm;
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+	u64 eventsel = pmc->eventsel;
+	u64 new_config = eventsel;
+	u8 fixed_ctr_ctrl;
 
 	pmc_pause_counter(pmc);
 
-	if (!en_field || !pmc_is_enabled(pmc))
+	if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc))
 		return;
 
-	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
-	if (filter) {
-		if (filter->action == KVM_PMU_EVENT_DENY &&
-		    test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
-			return;
-		if (filter->action == KVM_PMU_EVENT_ALLOW &&
-		    !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
-			return;
-	}
-
-	if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
+	if (!check_pmu_event_filter(pmc))
 		return;
 
-	pmc_release_perf_event(pmc);
-
-	pmc->current_config = (u64)ctrl;
-	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
-			      static_call(kvm_x86_pmu_pmc_perf_hw_id)(pmc),
-			      !(en_field & 0x2), /* exclude user */
-			      !(en_field & 0x1), /* exclude kernel */
-			      pmi);
-}
-EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
+	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
+		printk_once("kvm pmu: pin control bit is ignored\n");
 
-void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
-{
-	struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, pmc_idx);
+	if (pmc_is_fixed(pmc)) {
+		fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+						  pmc->idx - INTEL_PMC_IDX_FIXED);
+		if (fixed_ctr_ctrl & 0x1)
+			eventsel |= ARCH_PERFMON_EVENTSEL_OS;
+		if (fixed_ctr_ctrl & 0x2)
+			eventsel |= ARCH_PERFMON_EVENTSEL_USR;
+		if (fixed_ctr_ctrl & 0x8)
+			eventsel |= ARCH_PERFMON_EVENTSEL_INT;
+		new_config = (u64)fixed_ctr_ctrl;
+	}
 
-	if (!pmc)
+	if (pmc->current_config == new_config && pmc_resume_counter(pmc))
 		return;
 
-	if (pmc_is_gp(pmc))
-		reprogram_gp_counter(pmc, pmc->eventsel);
-	else {
-		int idx = pmc_idx - INTEL_PMC_IDX_FIXED;
-		u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx);
+	pmc_release_perf_event(pmc);
 
-		reprogram_fixed_counter(pmc, ctrl, idx);
-	}
+	pmc->current_config = new_config;
+	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);
 }
 EXPORT_SYMBOL_GPL(reprogram_counter);
 
@@ -329,8 +339,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 			clear_bit(bit, pmu->reprogram_pmi);
 			continue;
 		}
-
-		reprogram_counter(pmu, bit);
+		reprogram_counter(pmc);
 	}
 
 	/*
@@ -471,17 +480,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 	kvm_pmu_refresh(vcpu);
 }
 
-static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
-{
-	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
-
-	if (pmc_is_fixed(pmc))
-		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
-			pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
-
-	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
-}
-
 /* Release perf_events for vPMCs that have been unused for a full time slice.  */
 void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
 {
@@ -514,13 +512,12 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 
 static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 {
-	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 	u64 prev_count;
 
 	prev_count = pmc->counter;
 	pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc);
 
-	reprogram_counter(pmu, pmc->idx);
+	reprogram_counter(pmc);
 	if (pmc->counter < prev_count)
 		__kvm_perf_overflow(pmc, false);
 }
@@ -528,13 +525,8 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
 static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
 	unsigned int perf_hw_id)
 {
-	u64 old_eventsel = pmc->eventsel;
-	unsigned int config;
-
-	pmc->eventsel &= (ARCH_PERFMON_EVENTSEL_EVENT | ARCH_PERFMON_EVENTSEL_UMASK);
-	config = static_call(kvm_x86_pmu_pmc_perf_hw_id)(pmc);
-	pmc->eventsel = old_eventsel;
-	return config == 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)