KVM: Expose a version 2 architectural PMU to a guests

Use perf_events to emulate an architectural PMU, version 2.

Based on PMU version 1 emulation by Avi Kivity.

[avi: adjust for cpuid.c]
[jan: fix anonymous field initialization for older gcc]

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -16,10 +16,12 @@
 #include <linux/mmu_notifier.h>
 #include <linux/tracepoint.h>
 #include <linux/cpumask.h>
+#include <linux/irq_work.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
+#include <linux/perf_event.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -291,6 +293,37 @@ struct kvm_mmu {
 	u64 pdptrs[4]; /* pae */
 };
 
+enum pmc_type {
+	KVM_PMC_GP = 0,
+	KVM_PMC_FIXED,
+};
+
+struct kvm_pmc {
+	enum pmc_type type;
+	u8 idx;
+	u64 counter;
+	u64 eventsel;
+	struct perf_event *perf_event;
+	struct kvm_vcpu *vcpu;
+};
+
+struct kvm_pmu {
+	unsigned nr_arch_gp_counters;
+	unsigned nr_arch_fixed_counters;
+	unsigned available_event_types;
+	u64 fixed_ctr_ctrl;
+	u64 global_ctrl;
+	u64 global_status;
+	u64 global_ovf_ctrl;
+	u64 counter_bitmask[2];
+	u64 global_ctrl_mask;
+	u8 version;
+	struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
+	struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+	struct irq_work irq_work;
+	u64 reprogram_pmi;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -424,6 +457,8 @@ struct kvm_vcpu_arch {
 	unsigned access;
 	gfn_t mmio_gfn;
 
+	struct kvm_pmu pmu;
+
 	/* used for guest single stepping over the given code position */
 	unsigned long singlestep_rip;
 
@@ -891,4 +926,17 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
+int kvm_is_in_guest(void);
+
+void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+void kvm_pmu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
+bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
+void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
+void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
+
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/kvm/Kconfig

@@ -35,6 +35,7 @@ config KVM
 	select KVM_MMIO
 	select TASKSTATS
 	select TASK_DELAY_ACCT
+	select PERF_EVENTS
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/Makefile

@@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(addprefix ../../../virt/kvm/, async_pf.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o timer.o cpuid.o
+			   i8254.o timer.o cpuid.o pmu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 

arch/x86/kvm/cpuid.c

@@ -45,6 +45,8 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 		else
 			apic->lapic_timer.timer_mode_mask = 1 << 17;
 	}
+
+	kvm_pmu_cpuid_update(vcpu);
 }
 
 static int is_efer_nx(void)

arch/x86/kvm/x86.c

@@ -1602,8 +1602,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	 * which we perfectly emulate ;-). Any other value should be at least
 	 * reported, some guests depend on them.
 	 */
-	case MSR_P6_EVNTSEL0:
-	case MSR_P6_EVNTSEL1:
 	case MSR_K7_EVNTSEL0:
 	case MSR_K7_EVNTSEL1:
 	case MSR_K7_EVNTSEL2:
@@ -1615,8 +1613,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	/* at least RHEL 4 unconditionally writes to the perfctr registers,
 	 * so we ignore writes to make it happy.
 	 */
-	case MSR_P6_PERFCTR0:
-	case MSR_P6_PERFCTR1:
 	case MSR_K7_PERFCTR0:
 	case MSR_K7_PERFCTR1:
 	case MSR_K7_PERFCTR2:
@@ -1653,6 +1649,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
+		if (kvm_pmu_msr(vcpu, msr))
+			return kvm_pmu_set_msr(vcpu, msr, data);
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
 				msr, data);
@@ -1815,10 +1813,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_K8_SYSCFG:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
-	case MSR_P6_PERFCTR0:
-	case MSR_P6_PERFCTR1:
-	case MSR_P6_EVNTSEL0:
-	case MSR_P6_EVNTSEL1:
 	case MSR_K7_EVNTSEL0:
 	case MSR_K7_PERFCTR0:
 	case MSR_K8_INT_PENDING_MSG:
@@ -1929,6 +1923,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data = 0xbe702111;
 		break;
 	default:
+		if (kvm_pmu_msr(vcpu, msr))
+			return kvm_pmu_get_msr(vcpu, msr, pdata);
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
 			return 1;
@@ -4650,7 +4646,7 @@ static void kvm_timer_init(void)
 
 static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
 
-static int kvm_is_in_guest(void)
+int kvm_is_in_guest(void)
 {
 	return __this_cpu_read(current_vcpu) != NULL;
 }
@@ -5114,6 +5110,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			process_nmi(vcpu);
 		req_immediate_exit =
 			kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu);
+		if (kvm_check_request(KVM_REQ_PMU, vcpu))
+			kvm_handle_pmu_event(vcpu);
+		if (kvm_check_request(KVM_REQ_PMI, vcpu))
+			kvm_deliver_pmi(vcpu);
 	}
 
 	r = kvm_mmu_reload(vcpu);
@@ -5850,6 +5850,8 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 	kvm_async_pf_hash_reset(vcpu);
 	vcpu->arch.apf.halted = false;
 
+	kvm_pmu_reset(vcpu);
+
 	return kvm_x86_ops->vcpu_reset(vcpu);
 }
 
@@ -5934,6 +5936,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_mce_banks;
 
 	kvm_async_pf_hash_reset(vcpu);
+	kvm_pmu_init(vcpu);
 
 	return 0;
 fail_free_mce_banks:
@@ -5952,6 +5955,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
+	kvm_pmu_destroy(vcpu);
 	kfree(vcpu->arch.mce_banks);
 	kvm_free_lapic(vcpu);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);

include/linux/kvm_host.h

@@ -52,6 +52,8 @@
 #define KVM_REQ_STEAL_UPDATE      13
 #define KVM_REQ_NMI               14
 #define KVM_REQ_IMMEDIATE_EXIT    15
+#define KVM_REQ_PMU               16
+#define KVM_REQ_PMI               17
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0