From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/arch/x86/kvm/pmu.c | 265 ++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 224 insertions(+), 41 deletions(-)
diff --git a/kernel/arch/x86/kvm/pmu.c b/kernel/arch/x86/kvm/pmu.c
index ad3d39c..e5322a0 100644
--- a/kernel/arch/x86/kvm/pmu.c
+++ b/kernel/arch/x86/kvm/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine -- Performance Monitoring Unit support
*
@@ -7,20 +8,21 @@
* Avi Kivity <avi@redhat.com>
* Gleb Natapov <gleb@redhat.com>
* Wei Huang <wei@redhat.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 <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";
@@ -62,8 +64,7 @@
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- if (!test_and_set_bit(pmc->idx,
- (unsigned long *)&pmu->reprogram_pmi)) {
+ if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
@@ -76,8 +77,7 @@
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- if (!test_and_set_bit(pmc->idx,
- (unsigned long *)&pmu->reprogram_pmi)) {
+ if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
@@ -97,7 +97,7 @@
}
static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
- unsigned config, bool exclude_user,
+ u64 config, bool exclude_user,
bool exclude_kernel, bool intr,
bool in_tx, bool in_tx_cp)
{
@@ -113,7 +113,7 @@
.config = config,
};
- attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
+ attr.sample_period = get_sample_period(pmc, pmc->counter);
if (in_tx)
attr.config |= HSW_IN_TX;
@@ -137,42 +137,98 @@
}
pmc->perf_event = event;
- clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
+ pmc_to_pmu(pmc)->event_count++;
+ clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+}
+
+static void pmc_pause_counter(struct kvm_pmc *pmc)
+{
+ u64 counter = pmc->counter;
+
+ if (!pmc->perf_event)
+ return;
+
+ /* update counter, reset event value to avoid redundant accumulation */
+ counter += perf_event_pause(pmc->perf_event, true);
+ pmc->counter = counter & pmc_bitmask(pmc);
+}
+
+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);
+
+ clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+ return true;
+}
+
+static int cmp_u64(const void *pa, const void *pb)
+{
+ u64 a = *(u64 *)pa;
+ u64 b = *(u64 *)pb;
+
+ return (a > b) - (a < b);
}
void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
{
- unsigned config, type = PERF_TYPE_RAW;
- u8 event_select, unit_mask;
+ 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);
+ 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_stop_counter(pmc);
+ pmc_pause_counter(pmc);
if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
return;
- event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
- unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
+ 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->find_arch_event(pmc_to_pmu(pmc),
- event_select,
- unit_mask);
+ 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 & AMD64_RAW_EVENT_MASK;
+ 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),
@@ -186,14 +242,32 @@
{
unsigned en_field = ctrl & 0x3;
bool pmi = ctrl & 0x8;
+ struct kvm_pmu_event_filter *filter;
+ struct kvm *kvm = pmc->vcpu->kvm;
- pmc_stop_counter(pmc);
+ 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->find_fixed_event(idx),
+ kvm_x86_ops.pmu_ops->find_fixed_event(idx),
!(en_field & 0x2), /* exclude user */
!(en_field & 0x1), /* exclude kernel */
pmi, false, false);
@@ -202,7 +276,7 @@
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);
+ struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx);
if (!pmc)
return;
@@ -221,27 +295,32 @@
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- u64 bitmask;
int bit;
- bitmask = pmu->reprogram_pmi;
-
- for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
- struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, 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, (unsigned long *)&pmu->reprogram_pmi);
+ 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 */
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
{
- return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
+ return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
}
bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -264,10 +343,10 @@
ctr_val = rdtsc();
break;
case VMWARE_BACKDOOR_PMC_REAL_TIME:
- ctr_val = ktime_get_boot_ns();
+ ctr_val = ktime_get_boottime_ns();
break;
case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
- ctr_val = ktime_get_boot_ns() +
+ ctr_val = ktime_get_boottime_ns() +
vcpu->kvm->arch.kvmclock_offset;
break;
default:
@@ -281,14 +360,23 @@
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->msr_idx_to_pmc(vcpu, idx, &mask);
+ 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) &&
+ (kvm_x86_ops.get_cpl(vcpu) != 0) &&
+ (kvm_read_cr0(vcpu) & X86_CR0_PE))
return 1;
*data = pmc_read_counter(pmc) & mask;
@@ -303,17 +391,28 @@
bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
{
- return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+ return kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
+ kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, msr);
}
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
{
- return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data);
+ 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)
{
- return kvm_x86_ops->pmu_ops->set_msr(vcpu, 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
@@ -322,7 +421,7 @@
*/
void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
{
- kvm_x86_ops->pmu_ops->refresh(vcpu);
+ kvm_x86_ops.pmu_ops->refresh(vcpu);
}
void kvm_pmu_reset(struct kvm_vcpu *vcpu)
@@ -330,7 +429,7 @@
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
irq_work_sync(&pmu->irq_work);
- kvm_x86_ops->pmu_ops->reset(vcpu);
+ kvm_x86_ops.pmu_ops->reset(vcpu);
}
void kvm_pmu_init(struct kvm_vcpu *vcpu)
@@ -338,12 +437,96 @@
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
memset(pmu, 0, sizeof(*pmu));
- kvm_x86_ops->pmu_ops->init(vcpu);
+ 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);
+ }
+
+ bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
}
void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
{
kvm_pmu_reset(vcpu);
}
+
+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;
+}
--
Gitblit v1.6.2