linux-kernel - [PATCH v14 09/11] KVM: vmx/pmu: Release guest LBR event via lazy release mechanism

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210201051039.255478-10-like.xu@linux.intel.com>
Date:   Mon,  1 Feb 2021 13:10:37 +0800
From:   Like Xu <like.xu@...ux.intel.com>
To:     Paolo Bonzini <pbonzini@...hat.com>,
        Sean Christopherson <seanjc@...gle.com>
Cc:     Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, ak@...ux.intel.com,
        wei.w.wang@...el.com, kan.liang@...el.com,
        alex.shi@...ux.alibaba.com, kvm@...r.kernel.org, x86@...nel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH v14 09/11] KVM: vmx/pmu: Release guest LBR event via lazy release mechanism

The vPMU uses GUEST_LBR_IN_USE_IDX (bit 58) in 'pmu->pmc_in_use' to
indicate whether a guest LBR event is still needed by the vcpu. If the
vcpu no longer accesses LBR related registers within a scheduling time
slice, and the enable bit of LBR has been unset, vPMU will treat the
guest LBR event as a bland event of a vPMC counter and release it
as usual. Also, the pass-through state of LBR records msrs is cancelled.

Signed-off-by: Like Xu <like.xu@...ux.intel.com>
---
 arch/x86/kvm/pmu.c           |  3 +++
 arch/x86/kvm/pmu.h           |  1 +
 arch/x86/kvm/vmx/pmu_intel.c | 21 ++++++++++++++++++++-
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 405890c723a1..136dc2f3c5d3 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -476,6 +476,9 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
 			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);
 }
 
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 742a4e98df8c..7b30bc967af3 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -40,6 +40,7 @@ struct kvm_pmu_ops {
 	void (*init)(struct kvm_vcpu *vcpu);
 	void (*reset)(struct kvm_vcpu *vcpu);
 	void (*deliver_pmi)(struct kvm_vcpu *vcpu);
+	void (*cleanup)(struct kvm_vcpu *vcpu);
 };
 
 static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 51edd9c1adfa..23cd31b849f4 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -288,8 +288,10 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
 					PERF_SAMPLE_BRANCH_USER,
 	};
 
-	if (unlikely(lbr_desc->event))
+	if (unlikely(lbr_desc->event)) {
+		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
 		return 0;
+	}
 
 	event = perf_event_create_kernel_counter(&attr, -1,
 						current, NULL, NULL);
@@ -300,6 +302,7 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
 	}
 	lbr_desc->event = event;
 	pmu->event_count++;
+	__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
 	return 0;
 }
 
@@ -332,9 +335,11 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu,
 			rdmsrl(index, msr_info->data);
 		else
 			wrmsrl(index, msr_info->data);
+		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
 		local_irq_enable();
 		return true;
 	}
+	clear_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
 	local_irq_enable();
 
 dummy:
@@ -463,6 +468,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
 
 	pmu->nr_arch_gp_counters = 0;
 	pmu->nr_arch_fixed_counters = 0;
@@ -482,6 +488,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		return;
 
 	perf_get_x86_pmu_capability(&x86_pmu);
+	if (lbr_desc->records.nr)
+		bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1);
 
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
 					 x86_pmu.num_counters_gp);
@@ -658,17 +666,21 @@ static inline void vmx_enable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu)
  */
 void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
 
 	if (!lbr_desc->event) {
 		vmx_disable_lbr_msrs_passthrough(vcpu);
 		if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
 			goto warn;
+		if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
+			goto warn;
 		return;
 	}
 
 	if (lbr_desc->event->state < PERF_EVENT_STATE_ACTIVE) {
 		vmx_disable_lbr_msrs_passthrough(vcpu);
+		__clear_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
 		goto warn;
 	} else
 		vmx_enable_lbr_msrs_passthrough(vcpu);
@@ -680,6 +692,12 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
 		vcpu->vcpu_id);
 }
 
+static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+	if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+		intel_pmu_release_guest_lbr_event(vcpu);
+}
+
 struct kvm_pmu_ops intel_pmu_ops = {
 	.find_arch_event = intel_find_arch_event,
 	.find_fixed_event = intel_find_fixed_event,
@@ -695,4 +713,5 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.init = intel_pmu_init,
 	.reset = intel_pmu_reset,
 	.deliver_pmi = intel_pmu_deliver_pmi,
+	.cleanup = intel_pmu_cleanup,
 };
-- 
2.29.2