[PATCH v3 05/17] KVM: x86/pmu: Reprogram guest PEBS event to emulate guest PEBS counter

[Like Xu]

When a guest counter is configured as a PEBS counter through
IA32_PEBS_ENABLE, a guest PEBS event will be reprogrammed by
configuring a non-zero precision level in the perf_event_attr.

The guest PEBS overflow PMI bit would be set in the guest
GLOBAL_STATUS MSR when PEBS facility generates a PEBS
overflow PMI based on guest IA32_DS_AREA MSR.

The attr.precise_ip would be adjusted to a special precision
level when the new PEBS-PDIR feature is supported later which
would affect the host counters scheduling.

The guest PEBS event would not be reused for non-PEBS
guest event even with the same guest counter index.

Originally-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Co-developed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/pmu.c              | 29 +++++++++++++++++++++++++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 94c8bfee4a82..09dacda33fb8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -449,6 +449,8 @@ struct kvm_pmu {
 	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
 	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
 
+	u64 pebs_enable;
+
 	/*
 	 * The gate to release perf_events not marked in
 	 * pmc_in_use only once in a vcpu time slice.
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 67741d2a0308..2e81c50323e2 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -76,7 +76,12 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
 	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
-		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+		if (perf_event->attr.precise_ip) {
+			/* Indicate PEBS overflow PMI to guest. */
+			__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);
 
 		/*
@@ -99,6 +104,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 				  bool exclude_kernel, bool intr,
 				  bool in_tx, bool in_tx_cp)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
 	struct perf_event *event;
 	struct perf_event_attr attr = {
 		.type = type,
@@ -110,6 +116,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+	bool pebs = test_bit(pmc->idx, (unsigned long *)&pmu->pebs_enable);
 
 	attr.sample_period = get_sample_period(pmc, pmc->counter);
 
@@ -124,9 +131,23 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		attr.sample_period = 0;
 		attr.config |= HSW_IN_TX_CHECKPOINTED;
 	}
+	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.
+		 */
+		attr.precise_ip = 1;
+	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
-						 intr ? kvm_perf_overflow_intr :
+						 (intr || pebs) ? kvm_perf_overflow_intr :
 						 kvm_perf_overflow, pmc);
 	if (IS_ERR(event)) {
 		pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
@@ -161,6 +182,10 @@ 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);
 
-- 
2.29.2