| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1320323498-10233-3-git-send-email-gleb@redhat.com>
Date: Thu, 3 Nov 2011 14:31:31 +0200
From: Gleb Natapov <gleb@...hat.com>
To: kvm@...r.kernel.org
Cc: avi@...hat.com, mtosatti@...hat.com, linux-kernel@...r.kernel.org,
mingo@...e.hu, a.p.zijlstra@...llo.nl, acme@...stprotocols.net
Subject: [PATCH 2/9] KVM: Expose a version 2 architectural PMU to a guests
From: Avi Kivity <avi@...hat.com>
Use perf_events to emulate an architectural PMU, version 2.
Signed-off-by: Avi Kivity <avi@...hat.com>
Signed-off-by: Gleb Natapov <gleb@...hat.com>
---
arch/x86/include/asm/kvm_host.h | 43 ++++
arch/x86/kvm/Makefile | 2 +-
arch/x86/kvm/pmu.c | 513 +++++++++++++++++++++++++++++++++++++++
arch/x86/kvm/x86.c | 20 +-
include/linux/kvm_host.h | 1 +
5 files changed, 570 insertions(+), 9 deletions(-)
create mode 100644 arch/x86/kvm/pmu.c
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c1f19de..53caa94 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -20,6 +20,7 @@
#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>
@@ -296,6 +297,36 @@ struct kvm_mmu {
u64 pdptrs[4]; /* pae */
};
+enum pmc_type {
+ KVM_PMC_GP,
+ KVM_PMC_FIXED,
+};
+
+struct kvm_pmc {
+ enum pmc_type type;
+ 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 gp_counter_bitmask;
+ u64 fixed_counter_bitmask;
+ u64 global_ctrl_mask;
+ u8 version;
+ struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
+ struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+ u64 reprogram_pmi;
+};
+
struct kvm_vcpu_arch {
/*
* rip and regs accesses must go through
@@ -433,6 +464,8 @@ 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;
@@ -894,4 +927,14 @@ 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);
+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);
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index f15501f..cfca03f 100644
--- a/arch/x86/kvm/Makefile
+++ b/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
+ i8254.o timer.o pmu.o
kvm-intel-y += vmx.o
kvm-amd-y += svm.o
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
new file mode 100644
index 0000000..66b64a7
--- /dev/null
+++ b/arch/x86/kvm/pmu.c
@@ -0,0 +1,513 @@
+/*
+ * Kernel-based Virtual Machine -- Performane Monitoring Unit support
+ *
+ * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ * Avi Kivity <avi@...hat.com>
+ * Gleb Natapov <gleb@...hat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include "x86.h"
+#include "lapic.h"
+
+static struct kvm_arch_event_perf_mapping {
+ u8 eventsel;
+ u8 unit_mask;
+ unsigned event_type;
+ bool inexact;
+} arch_events[] = {
+ /* Index must match CPUID 0x0A.EBX bit vector */
+ [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
+ [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
+ [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES },
+ [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES },
+ [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
+ [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+ [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+};
+
+/* mapping between fixed pmc index and arch_events array */
+int fixed_pmc_events[] = {1, 0, 2};
+
+static bool pmc_is_gp(struct kvm_pmc *pmc)
+{
+ return pmc->type == KVM_PMC_GP;
+}
+
+static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
+
+ return pmc_is_gp(pmc) ? pmu->gp_counter_bitmask :
+ pmu->fixed_counter_bitmask;
+}
+
+static inline int pmc_to_global_idx(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
+ struct kvm_pmc *counters;
+ int shift;
+
+ if (pmc_is_gp(pmc)) {
+ counters = pmu->gp_counters;
+ shift = X86_PMC_IDX_GENERIC;
+ } else {
+ counters = pmu->fixed_counters;
+ shift = X86_PMC_IDX_FIXED;
+ }
+
+ return pmc - counters + shift;
+}
+
+static inline bool pmc_enabled(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
+ return test_bit(pmc_to_global_idx(pmc),
+ (unsigned long *)&pmu->global_ctrl);
+}
+
+static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
+ u32 base)
+{
+ if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
+ return &pmu->gp_counters[msr - base];
+ return NULL;
+}
+
+static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
+{
+ int base = MSR_CORE_PERF_FIXED_CTR0;
+ if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
+ return &pmu->fixed_counters[msr - base];
+ return NULL;
+}
+
+static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx)
+{
+ if (idx < X86_PMC_IDX_FIXED)
+ return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0);
+ else
+ return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx -
+ X86_PMC_IDX_FIXED);
+}
+
+static void kvm_perf_overflow(struct perf_event *perf_event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+ struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
+ __set_bit(pmc_to_global_idx(pmc),
+ (unsigned long *)&pmu->global_status);
+}
+
+static void kvm_perf_overflow_intr(struct perf_event *perf_event,
+ struct perf_sample_data *data, struct pt_regs *regs)
+{
+ struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+ struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
+ if (!__test_and_set_bit(pmc_to_global_idx(pmc),
+ (unsigned long *)&pmu->reprogram_pmi)) {
+ kvm_perf_overflow(perf_event, data, regs);
+ kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+ }
+}
+
+static u64 read_pmc(struct kvm_pmc *pmc)
+{
+ u64 counter, enabled, running;
+
+ counter = pmc->counter;
+
+ if (pmc->perf_event)
+ counter += perf_event_read_value(pmc->perf_event,
+ &enabled, &running);
+
+ /* FIXME: Scaling needed? */
+
+ return counter & pmc_bitmask(pmc);
+}
+
+static void stop_counter(struct kvm_pmc *pmc)
+{
+ if (pmc->perf_event) {
+ pmc->counter = read_pmc(pmc);
+ perf_event_release_kernel(pmc->perf_event);
+ pmc->perf_event = NULL;
+ }
+}
+
+static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
+ unsigned config, bool exclude_user, bool exclude_kernel,
+ bool intr)
+{
+ struct perf_event *event;
+ struct perf_event_attr attr = {
+ .type = type,
+ .size = sizeof(attr),
+ .exclude_idle = true,
+ .exclude_host = 1,
+ .exclude_user = exclude_user,
+ .exclude_kernel = exclude_kernel,
+ .sample_period = (-pmc->counter) & pmc_bitmask(pmc),
+ .config = config,
+ };
+
+ event = perf_event_create_kernel_counter(&attr, -1, current,
+ intr ? kvm_perf_overflow_intr :
+ kvm_perf_overflow, pmc);
+ if (IS_ERR(event)) {
+ printk_once("kvm: pmu event creation failed %ld\n",
+ PTR_ERR(event));
+ return;
+ }
+
+ pmc->perf_event = event;
+ __clear_bit(pmc_to_global_idx(pmc),
+ (unsigned long *)&pmc->vcpu->arch.pmu.reprogram_pmi);
+}
+
+static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select,
+ u8 unit_mask)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(arch_events); i++)
+ if (arch_events[i].eventsel == event_select
+ && arch_events[i].unit_mask == unit_mask
+ && (pmu->available_event_types & (1 << i)))
+ break;
+
+ if (i == ARRAY_SIZE(arch_events))
+ return PERF_COUNT_HW_MAX;
+
+ return arch_events[i].event_type;
+}
+
+static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
+{
+ unsigned config, type = PERF_TYPE_RAW;
+ u8 event_select, unit_mask;
+
+ pmc->eventsel = eventsel;
+
+ stop_counter(pmc);
+
+ if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc))
+ return;
+
+ event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
+ unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
+
+ if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE |
+ ARCH_PERFMON_EVENTSEL_INV |
+ ARCH_PERFMON_EVENTSEL_CMASK))) {
+ config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
+ unit_mask);
+ if (config != PERF_COUNT_HW_MAX)
+ type = PERF_TYPE_HARDWARE;
+ }
+
+ if (type == PERF_TYPE_RAW)
+ config = eventsel & X86_RAW_EVENT_MASK;
+
+ reprogram_counter(pmc, type, config,
+ !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+ eventsel & ARCH_PERFMON_EVENTSEL_INT);
+}
+
+static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
+{
+ unsigned en = en_pmi & 0x3;
+ bool pmi = en_pmi & 0x8;
+
+ stop_counter(pmc);
+
+ if (!en || !pmc_enabled(pmc))
+ return;
+
+ reprogram_counter(pmc, PERF_TYPE_HARDWARE,
+ arch_events[fixed_pmc_events[idx]].event_type,
+ !(en & 0x2), /* exclude user */
+ !(en & 0x1), /* exclude kernel */
+ pmi);
+}
+
+#define FIXED_EN_PMI(R, I) (((R) >> ((I) * 4)) & 0xf)
+
+static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
+{
+ int i;
+
+ for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+ u8 en_pmi = FIXED_EN_PMI(data, i);
+ struct kvm_pmc *pmc = get_fixed_pmc(pmu,
+ MSR_CORE_PERF_FIXED_CTR0 + i);
+
+ if (FIXED_EN_PMI(pmu->fixed_ctr_ctrl, i) == en_pmi)
+ continue;
+
+ reprogram_fixed_counter(pmc, en_pmi, i);
+ }
+
+ pmu->fixed_ctr_ctrl = data;
+}
+
+static void reprogram_idx(struct kvm_pmu *pmu, int idx)
+{
+ struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx);
+
+ if (!pmc)
+ return;
+
+ if (pmc_is_gp(pmc))
+ reprogram_gp_counter(pmc, pmc->eventsel);
+ else {
+ int fidx = idx - X86_PMC_IDX_FIXED;
+ reprogram_fixed_counter(pmc,
+ FIXED_EN_PMI(pmu->fixed_ctr_ctrl, fidx), fidx);
+ }
+}
+
+static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+{
+ int bit;
+ u64 diff = pmu->global_ctrl ^ data;
+
+ pmu->global_ctrl = data;
+
+ for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
+ reprogram_idx(pmu, bit);
+}
+
+bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ int ret;
+
+ switch (msr) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ ret = pmu->version > 1;
+ break;
+ default:
+ ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)
+ || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0)
+ || get_fixed_pmc(pmu, msr);
+ break;
+ }
+ return ret;
+}
+
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ struct kvm_pmc *pmc;
+
+ switch (index) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ *data = pmu->fixed_ctr_ctrl;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ *data = pmu->global_status;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ *data = pmu->global_ctrl;
+ return 0;
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ *data = pmu->global_ovf_ctrl;
+ return 0;
+ default:
+ if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
+ (pmc = get_fixed_pmc(pmu, index))) {
+ *data = read_pmc(pmc);
+ return 0;
+ } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
+ *data = pmc->eventsel;
+ return 0;
+ }
+ }
+ return 1;
+}
+
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ struct kvm_pmc *pmc;
+
+ switch (index) {
+ case MSR_CORE_PERF_FIXED_CTR_CTRL:
+ if (pmu->fixed_ctr_ctrl == data)
+ return 0;
+ if (!(data & 0xfffffffffffff444)) {
+ reprogram_fixed_counters(pmu, data);
+ return 0;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_STATUS:
+ break; /* RO MSR */
+ case MSR_CORE_PERF_GLOBAL_CTRL:
+ if (pmu->global_ctrl == data)
+ return 0;
+ if (!(data & pmu->global_ctrl_mask)) {
+ global_ctrl_changed(pmu, data);
+ return 0;
+ }
+ break;
+ case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+ if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
+ pmu->global_status &= ~data;
+ pmu->global_ovf_ctrl = data;
+ return 0;
+ }
+ break;
+ default:
+ if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
+ (pmc = get_fixed_pmc(pmu, index))) {
+ data = (s64)(s32)data;
+ pmc->counter += data - read_pmc(pmc);
+ return 0;
+ } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
+ if (data == pmc->eventsel)
+ return 0;
+ if (!(data & 0xffffffff00200000ull)) {
+ reprogram_gp_counter(pmc, data);
+ return 0;
+ }
+ }
+ }
+ return 1;
+}
+
+int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ bool fast_mode = pmc & (1u << 31);
+ bool fixed = pmc & (1u << 30);
+ struct kvm_pmc *counters;
+ u64 ctr;
+
+ pmc &= (3u << 30) - 1;
+ if (!fixed && pmc >= pmu->nr_arch_gp_counters)
+ return 1;
+ if (fixed && pmc >= pmu->nr_arch_fixed_counters)
+ return 1;
+ counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+ ctr = read_pmc(&counters[pmc]);
+ if (fast_mode)
+ ctr = (u32)ctr;
+ *data = ctr;
+
+ return 0;
+}
+
+void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ struct kvm_cpuid_entry2 *entry;
+ unsigned bitmap_len;
+
+ pmu->nr_arch_gp_counters = 0;
+ pmu->nr_arch_fixed_counters = 0;
+ pmu->fixed_counter_bitmask = 0;
+ pmu->version = 0;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return;
+
+ pmu->version = entry->eax & 0xff;
+ if (!pmu->version)
+ return;
+
+ pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff,
+ X86_PMC_MAX_GENERIC);
+ pmu->gp_counter_bitmask = ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1;
+ bitmap_len = (entry->eax >> 24) & 0xff;
+ pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
+
+ if (pmu->version > 1) {
+ pmu->nr_arch_fixed_counters = min((int)(entry->edx) & 0x1f,
+ X86_PMC_MAX_FIXED);
+ pmu->fixed_counter_bitmask =
+ ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
+ pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1)
+ | (((1ull << pmu->nr_arch_fixed_counters) - 1)
+ << X86_PMC_IDX_FIXED));
+ } else
+ pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1;
+}
+
+void kvm_pmu_init(struct kvm_vcpu *vcpu)
+{
+ int i;
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+ memset(pmu, 0, sizeof(*pmu));
+ for (i = 0; i < X86_PMC_MAX_GENERIC; i++) {
+ pmu->gp_counters[i].type = KVM_PMC_GP;
+ pmu->gp_counters[i].vcpu = vcpu;
+ }
+ for (i = 0; i < X86_PMC_MAX_FIXED; i++) {
+ pmu->fixed_counters[i].type = KVM_PMC_FIXED;
+ pmu->fixed_counters[i].vcpu = vcpu;
+ }
+ kvm_pmu_cpuid_update(vcpu);
+}
+
+void kvm_pmu_reset(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ int i;
+
+ for (i = 0; i < X86_PMC_MAX_GENERIC; i++) {
+ struct kvm_pmc *pmc = &pmu->gp_counters[i];
+ stop_counter(pmc);
+ pmc->counter = pmc->eventsel = 0;
+ }
+
+ for (i = 0; i < X86_PMC_MAX_FIXED; i++)
+ stop_counter(&pmu->fixed_counters[i]);
+
+ pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
+ pmu->global_ovf_ctrl = 0;
+}
+
+void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_pmu_reset(vcpu);
+}
+
+void kvm_handle_pmu_event(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+ u64 bitmask;
+ int bit;
+
+ if (vcpu->arch.apic)
+ kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
+
+ bitmask = pmu->reprogram_pmi;
+
+ for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+ struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit);
+
+ if (unlikely(!pmc || !pmc->perf_event)) {
+ __clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+ continue;
+ }
+
+ reprogram_idx(pmu, bit);
+ }
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b1c526..eb60363 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -623,6 +623,8 @@ static void update_cpuid(struct kvm_vcpu *vcpu)
if (apic)
apic->lapic_timer.timer_mode_mask = timer_mode_mask;
+
+ kvm_pmu_cpuid_update(vcpu);
}
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -1655,8 +1657,6 @@ 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:
@@ -1668,8 +1668,6 @@ 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:
@@ -1706,6 +1704,8 @@ 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);
@@ -1868,10 +1868,6 @@ 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:
@@ -1982,6 +1978,8 @@ 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;
@@ -5730,6 +5728,8 @@ 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);
}
r = kvm_mmu_reload(vcpu);
@@ -6470,6 +6470,8 @@ 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);
}
@@ -6558,6 +6560,7 @@ 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:
@@ -6576,6 +6579,7 @@ 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);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c6a2ec9..7ad40d5 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -52,6 +52,7 @@
#define KVM_REQ_STEAL_UPDATE 13
#define KVM_REQ_NMI 14
#define KVM_REQ_IMMEDIATE_EXIT 15
+#define KVM_REQ_PMU 16
#define KVM_USERSPACE_IRQ_SOURCE_ID 0
--
1.7.5.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists