mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 08:28:13 +00:00
636b5284d8
- selftest compilation fix for non-x86 - KVM: avoid warning on s390 in mark_page_dirty x86: - fix page write-protection bug and improve comments - use binary search to lookup the PMU event filter, add test - enable_pmu module parameter support for Intel CPUs - switch blocked_vcpu_on_cpu_lock to raw spinlock - cleanups of blocked vCPU logic - partially allow KVM_SET_CPUID{,2} after KVM_RUN (5.16 regression) - various small fixes -----BEGIN PGP SIGNATURE----- iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmHpmT0UHHBib256aW5p QHJlZGhhdC5jb20ACgkQv/vSX3jHroOstggAi1VSpT43oGslQjXNDZacHEARoYQs b0XpoW7HXicGSGRMWspCmiAPdJyYTsioEACttAmXUMs7brAgHb9n/vzdlcLh1ymL rQw2YFQlfqqB1Ki1iRhNkWlH9xOECsu28WLng6ylrx51GuT/pzWRt+V3EGUFTxIT ldW9HgZg2oFJIaLjg2hQVR/8EbBf0QdsAD3KV3tyvhBlXPkyeLOMcGe9onfjZ/NE JQeW7FtKtP4SsIFt1KrJpDPjtiwFt3bRM0gfgGw7//clvtKIqt1LYXZiq4C3b7f5 tfYiC8lO2vnOoYcfeYEmvybbSsoS/CgSliZB32qkwoVvRMIl82YmxtDD+Q== =/Mak -----END PGP SIGNATURE----- Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm Pull more kvm updates from Paolo Bonzini: "Generic: - selftest compilation fix for non-x86 - KVM: avoid warning on s390 in mark_page_dirty x86: - fix page write-protection bug and improve comments - use binary search to lookup the PMU event filter, add test - enable_pmu module parameter support for Intel CPUs - switch blocked_vcpu_on_cpu_lock to raw spinlock - cleanups of blocked vCPU logic - partially allow KVM_SET_CPUID{,2} after KVM_RUN (5.16 regression) - various small fixes" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (46 commits) docs: kvm: fix WARNINGs from api.rst selftests: kvm/x86: Fix the warning in lib/x86_64/processor.c selftests: kvm/x86: Fix the warning in pmu_event_filter_test.c kvm: selftests: Do not indent with spaces kvm: selftests: sync uapi/linux/kvm.h with Linux header selftests: kvm: add amx_test to .gitignore KVM: SVM: Nullify vcpu_(un)blocking() hooks if AVIC is disabled KVM: SVM: Move svm_hardware_setup() and its helpers below svm_x86_ops KVM: SVM: Drop AVIC's intermediate avic_set_running() helper KVM: VMX: Don't do full kick when handling posted interrupt wakeup KVM: VMX: Fold fallback path into triggering posted IRQ helper KVM: VMX: Pass desired vector instead of bool for triggering posted IRQ KVM: VMX: Don't do full kick when triggering posted interrupt "fails" KVM: SVM: Skip AVIC and IRTE updates when loading blocking vCPU KVM: SVM: Use kvm_vcpu_is_blocking() in AVIC load to handle preemption KVM: SVM: Remove unnecessary APICv/AVIC update in vCPU unblocking path KVM: SVM: Don't bother checking for "running" AVIC when kicking for IPIs KVM: SVM: Signal AVIC doorbell iff vCPU is in guest mode KVM: x86: Remove defunct pre_block/post_block kvm_x86_ops hooks KVM: x86: Unexport LAPIC's switch_to_{hv,sw}_timer() helpers ...
597 lines
16 KiB
C
597 lines
16 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Kernel-based Virtual Machine -- Performance Monitoring Unit support
|
|
*
|
|
* Copyright 2015 Red Hat, Inc. and/or its affiliates.
|
|
*
|
|
* Authors:
|
|
* Avi Kivity <avi@redhat.com>
|
|
* Gleb Natapov <gleb@redhat.com>
|
|
* Wei Huang <wei@redhat.com>
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/kvm_host.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/bsearch.h>
|
|
#include <linux/sort.h>
|
|
#include <asm/perf_event.h>
|
|
#include "x86.h"
|
|
#include "cpuid.h"
|
|
#include "lapic.h"
|
|
#include "pmu.h"
|
|
|
|
/* This is enough to filter the vast majority of currently defined events. */
|
|
#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300
|
|
|
|
/* NOTE:
|
|
* - Each perf counter is defined as "struct kvm_pmc";
|
|
* - There are two types of perf counters: general purpose (gp) and fixed.
|
|
* gp counters are stored in gp_counters[] and fixed counters are stored
|
|
* in fixed_counters[] respectively. Both of them are part of "struct
|
|
* kvm_pmu";
|
|
* - pmu.c understands the difference between gp counters and fixed counters.
|
|
* 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.
|
|
* 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
|
|
* that it also supports fixed counters. idx can be used to as index to
|
|
* gp and fixed counters.
|
|
* 3. Global PMC Index (named pmc): pmc is an index specific to PMU
|
|
* code. Each pmc, stored in kvm_pmc.idx field, is unique across
|
|
* all perf counters (both gp and fixed). The mapping relationship
|
|
* 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
|
|
*/
|
|
|
|
static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
|
|
{
|
|
struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
|
|
struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
|
|
|
|
kvm_pmu_deliver_pmi(vcpu);
|
|
}
|
|
|
|
static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
|
|
{
|
|
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
|
|
|
|
/* 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);
|
|
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
|
|
|
|
if (!pmc->intr)
|
|
return;
|
|
|
|
/*
|
|
* Inject PMI. If vcpu was in a guest mode during NMI PMI
|
|
* can be ejected on a guest mode re-entry. Otherwise we can't
|
|
* be sure that vcpu wasn't executing hlt instruction at the
|
|
* time of vmexit and is not going to re-enter guest mode until
|
|
* woken up. So we should wake it, but this is impossible from
|
|
* NMI context. Do it from irq work instead.
|
|
*/
|
|
if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu))
|
|
irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
|
|
else
|
|
kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
|
|
}
|
|
|
|
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;
|
|
|
|
__kvm_perf_overflow(pmc, true);
|
|
}
|
|
|
|
static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
|
|
unsigned config, bool exclude_user,
|
|
bool exclude_kernel, bool intr,
|
|
bool in_tx, bool in_tx_cp)
|
|
{
|
|
struct perf_event *event;
|
|
struct perf_event_attr attr = {
|
|
.type = type,
|
|
.size = sizeof(attr),
|
|
.pinned = true,
|
|
.exclude_idle = true,
|
|
.exclude_host = 1,
|
|
.exclude_user = exclude_user,
|
|
.exclude_kernel = exclude_kernel,
|
|
.config = config,
|
|
};
|
|
|
|
if (type == PERF_TYPE_HARDWARE && config >= PERF_COUNT_HW_MAX)
|
|
return;
|
|
|
|
attr.sample_period = get_sample_period(pmc, pmc->counter);
|
|
|
|
if (in_tx)
|
|
attr.config |= HSW_IN_TX;
|
|
if (in_tx_cp) {
|
|
/*
|
|
* HSW_IN_TX_CHECKPOINTED is not supported with nonzero
|
|
* period. Just clear the sample period so at least
|
|
* allocating the counter doesn't fail.
|
|
*/
|
|
attr.sample_period = 0;
|
|
attr.config |= HSW_IN_TX_CHECKPOINTED;
|
|
}
|
|
|
|
event = perf_event_create_kernel_counter(&attr, -1, current,
|
|
kvm_perf_overflow, pmc);
|
|
if (IS_ERR(event)) {
|
|
pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
|
|
PTR_ERR(event), pmc->idx);
|
|
return;
|
|
}
|
|
|
|
pmc->perf_event = event;
|
|
pmc_to_pmu(pmc)->event_count++;
|
|
clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
|
|
pmc->is_paused = false;
|
|
pmc->intr = intr;
|
|
}
|
|
|
|
static void pmc_pause_counter(struct kvm_pmc *pmc)
|
|
{
|
|
u64 counter = pmc->counter;
|
|
|
|
if (!pmc->perf_event || pmc->is_paused)
|
|
return;
|
|
|
|
/* update counter, reset event value to avoid redundant accumulation */
|
|
counter += perf_event_pause(pmc->perf_event, true);
|
|
pmc->counter = counter & pmc_bitmask(pmc);
|
|
pmc->is_paused = true;
|
|
}
|
|
|
|
static bool pmc_resume_counter(struct kvm_pmc *pmc)
|
|
{
|
|
if (!pmc->perf_event)
|
|
return false;
|
|
|
|
/* recalibrate sample period and check if it's accepted by perf core */
|
|
if (perf_event_period(pmc->perf_event,
|
|
get_sample_period(pmc, pmc->counter)))
|
|
return false;
|
|
|
|
/* reuse perf_event to serve as pmc_reprogram_counter() does*/
|
|
perf_event_enable(pmc->perf_event);
|
|
pmc->is_paused = false;
|
|
|
|
clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
|
|
return true;
|
|
}
|
|
|
|
static int cmp_u64(const void *a, const void *b)
|
|
{
|
|
return *(__u64 *)a - *(__u64 *)b;
|
|
}
|
|
|
|
void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
|
|
{
|
|
unsigned config, type = PERF_TYPE_RAW;
|
|
struct kvm *kvm = pmc->vcpu->kvm;
|
|
struct kvm_pmu_event_filter *filter;
|
|
bool allow_event = true;
|
|
|
|
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;
|
|
|
|
filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
|
|
if (filter) {
|
|
__u64 key = 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;
|
|
}
|
|
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 = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc);
|
|
if (config != PERF_COUNT_HW_MAX)
|
|
type = PERF_TYPE_HARDWARE;
|
|
}
|
|
|
|
if (type == PERF_TYPE_RAW)
|
|
config = eventsel & X86_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,
|
|
(eventsel & HSW_IN_TX),
|
|
(eventsel & HSW_IN_TX_CHECKPOINTED));
|
|
}
|
|
EXPORT_SYMBOL_GPL(reprogram_gp_counter);
|
|
|
|
void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
|
|
{
|
|
unsigned en_field = ctrl & 0x3;
|
|
bool pmi = ctrl & 0x8;
|
|
struct kvm_pmu_event_filter *filter;
|
|
struct kvm *kvm = pmc->vcpu->kvm;
|
|
|
|
pmc_pause_counter(pmc);
|
|
|
|
if (!en_field || !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))
|
|
return;
|
|
|
|
pmc_release_perf_event(pmc);
|
|
|
|
pmc->current_config = (u64)ctrl;
|
|
pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
|
|
kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
|
|
!(en_field & 0x2), /* exclude user */
|
|
!(en_field & 0x1), /* exclude kernel */
|
|
pmi, false, false);
|
|
}
|
|
EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
|
|
|
|
void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
|
|
{
|
|
struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx);
|
|
|
|
if (!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);
|
|
|
|
reprogram_fixed_counter(pmc, ctrl, idx);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(reprogram_counter);
|
|
|
|
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
|
|
{
|
|
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
|
|
int bit;
|
|
|
|
for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
|
|
struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit);
|
|
|
|
if (unlikely(!pmc || !pmc->perf_event)) {
|
|
clear_bit(bit, pmu->reprogram_pmi);
|
|
continue;
|
|
}
|
|
|
|
reprogram_counter(pmu, bit);
|
|
}
|
|
|
|
/*
|
|
* Unused perf_events are only released if the corresponding MSRs
|
|
* weren't accessed during the last vCPU time slice. kvm_arch_sched_in
|
|
* triggers KVM_REQ_PMU if cleanup is needed.
|
|
*/
|
|
if (unlikely(pmu->need_cleanup))
|
|
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)
|
|
{
|
|
return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
|
|
}
|
|
|
|
bool is_vmware_backdoor_pmc(u32 pmc_idx)
|
|
{
|
|
switch (pmc_idx) {
|
|
case VMWARE_BACKDOOR_PMC_HOST_TSC:
|
|
case VMWARE_BACKDOOR_PMC_REAL_TIME:
|
|
case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
|
|
{
|
|
u64 ctr_val;
|
|
|
|
switch (idx) {
|
|
case VMWARE_BACKDOOR_PMC_HOST_TSC:
|
|
ctr_val = rdtsc();
|
|
break;
|
|
case VMWARE_BACKDOOR_PMC_REAL_TIME:
|
|
ctr_val = ktime_get_boottime_ns();
|
|
break;
|
|
case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
|
|
ctr_val = ktime_get_boottime_ns() +
|
|
vcpu->kvm->arch.kvmclock_offset;
|
|
break;
|
|
default:
|
|
return 1;
|
|
}
|
|
|
|
*data = ctr_val;
|
|
return 0;
|
|
}
|
|
|
|
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;
|
|
|
|
if (!pmu->version)
|
|
return 1;
|
|
|
|
if (is_vmware_backdoor_pmc(idx))
|
|
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
|
|
|
|
pmc = kvm_x86_ops.pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
|
|
if (!pmc)
|
|
return 1;
|
|
|
|
if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) &&
|
|
(static_call(kvm_x86_get_cpl)(vcpu) != 0) &&
|
|
(kvm_read_cr0(vcpu) & X86_CR0_PE))
|
|
return 1;
|
|
|
|
*data = pmc_read_counter(pmc) & mask;
|
|
return 0;
|
|
}
|
|
|
|
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
|
|
{
|
|
if (lapic_in_kernel(vcpu)) {
|
|
if (kvm_x86_ops.pmu_ops->deliver_pmi)
|
|
kvm_x86_ops.pmu_ops->deliver_pmi(vcpu);
|
|
kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
|
|
}
|
|
}
|
|
|
|
bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
|
|
{
|
|
return kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
|
|
kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, msr);
|
|
}
|
|
|
|
static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
|
|
{
|
|
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
|
|
struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr);
|
|
|
|
if (pmc)
|
|
__set_bit(pmc->idx, pmu->pmc_in_use);
|
|
}
|
|
|
|
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
|
|
{
|
|
return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr_info);
|
|
}
|
|
|
|
int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
|
|
{
|
|
kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
|
|
return kvm_x86_ops.pmu_ops->set_msr(vcpu, msr_info);
|
|
}
|
|
|
|
/* refresh PMU settings. This function generally is called when underlying
|
|
* settings are changed (such as changes of PMU CPUID by guest VMs), which
|
|
* should rarely happen.
|
|
*/
|
|
void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
|
|
{
|
|
kvm_x86_ops.pmu_ops->refresh(vcpu);
|
|
}
|
|
|
|
void kvm_pmu_reset(struct kvm_vcpu *vcpu)
|
|
{
|
|
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
|
|
|
|
irq_work_sync(&pmu->irq_work);
|
|
kvm_x86_ops.pmu_ops->reset(vcpu);
|
|
}
|
|
|
|
void kvm_pmu_init(struct kvm_vcpu *vcpu)
|
|
{
|
|
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
|
|
|
|
memset(pmu, 0, sizeof(*pmu));
|
|
kvm_x86_ops.pmu_ops->init(vcpu);
|
|
init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
|
|
pmu->event_count = 0;
|
|
pmu->need_cleanup = false;
|
|
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)
|
|
{
|
|
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
|
|
struct kvm_pmc *pmc = NULL;
|
|
DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
|
|
int i;
|
|
|
|
pmu->need_cleanup = false;
|
|
|
|
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 = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i);
|
|
|
|
if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
|
|
pmc_stop_counter(pmc);
|
|
}
|
|
|
|
if (kvm_x86_ops.pmu_ops->cleanup)
|
|
kvm_x86_ops.pmu_ops->cleanup(vcpu);
|
|
|
|
bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
|
|
}
|
|
|
|
void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
|
|
{
|
|
kvm_pmu_reset(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);
|
|
if (pmc->counter < prev_count)
|
|
__kvm_perf_overflow(pmc, false);
|
|
}
|
|
|
|
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 = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc);
|
|
pmc->eventsel = old_eventsel;
|
|
return config == perf_hw_id;
|
|
}
|
|
|
|
static inline bool cpl_is_matched(struct kvm_pmc *pmc)
|
|
{
|
|
bool select_os, select_user;
|
|
u64 config = pmc->current_config;
|
|
|
|
if (pmc_is_gp(pmc)) {
|
|
select_os = config & ARCH_PERFMON_EVENTSEL_OS;
|
|
select_user = config & ARCH_PERFMON_EVENTSEL_USR;
|
|
} else {
|
|
select_os = config & 0x1;
|
|
select_user = config & 0x2;
|
|
}
|
|
|
|
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)
|
|
{
|
|
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 = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i);
|
|
|
|
if (!pmc || !pmc_is_enabled(pmc) || !pmc_speculative_in_use(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);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);
|
|
|
|
int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
|
|
{
|
|
struct kvm_pmu_event_filter tmp, *filter;
|
|
size_t size;
|
|
int r;
|
|
|
|
if (copy_from_user(&tmp, argp, sizeof(tmp)))
|
|
return -EFAULT;
|
|
|
|
if (tmp.action != KVM_PMU_EVENT_ALLOW &&
|
|
tmp.action != KVM_PMU_EVENT_DENY)
|
|
return -EINVAL;
|
|
|
|
if (tmp.flags != 0)
|
|
return -EINVAL;
|
|
|
|
if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS)
|
|
return -E2BIG;
|
|
|
|
size = struct_size(filter, events, tmp.nevents);
|
|
filter = kmalloc(size, GFP_KERNEL_ACCOUNT);
|
|
if (!filter)
|
|
return -ENOMEM;
|
|
|
|
r = -EFAULT;
|
|
if (copy_from_user(filter, argp, size))
|
|
goto cleanup;
|
|
|
|
/* Ensure nevents can't be changed between the user copies. */
|
|
*filter = tmp;
|
|
|
|
/*
|
|
* Sort the in-kernel list so that we can search it with bsearch.
|
|
*/
|
|
sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL);
|
|
|
|
mutex_lock(&kvm->lock);
|
|
filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
|
|
mutex_is_locked(&kvm->lock));
|
|
mutex_unlock(&kvm->lock);
|
|
|
|
synchronize_srcu_expedited(&kvm->srcu);
|
|
r = 0;
|
|
cleanup:
|
|
kfree(filter);
|
|
return r;
|
|
}
|