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