linux-kernel - [PATCH v2 03/59] KVM: SVM: Delete IRTE link from previous vCPU before setting new IRTE

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: <20250523010004.3240643-4-seanjc@google.com>
Date: Thu, 22 May 2025 17:59:08 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>, 
	Joerg Roedel <joro@...tes.org>, David Woodhouse <dwmw2@...radead.org>, 
	Lu Baolu <baolu.lu@...ux.intel.com>
Cc: kvm@...r.kernel.org, iommu@...ts.linux.dev, linux-kernel@...r.kernel.org, 
	Sairaj Kodilkar <sarunkod@....com>, Vasant Hegde <vasant.hegde@....com>, 
	Maxim Levitsky <mlevitsk@...hat.com>, Joao Martins <joao.m.martins@...cle.com>, 
	Francesco Lavra <francescolavra.fl@...il.com>, David Matlack <dmatlack@...gle.com>
Subject: [PATCH v2 03/59] KVM: SVM: Delete IRTE link from previous vCPU before
 setting new IRTE

Delete the previous per-vCPU IRTE link prior to modifying the IRTE.  If
forcing the IRTE back to remapped mode fails, the IRQ is already broken;
keeping stale metadata won't change that, and the IOMMU should be
sufficiently paranoid to sanitize the IRTE when the IRQ is freed and
reallocated.

This will allow hoisting the vCPU tracking to common x86, which in turn
will allow most of the IRTE update code to be deduplicated.

Tested-by: Sairaj Kodilkar <sarunkod@....com>
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/svm/avic.c   | 60 +++++++++------------------------------
 include/linux/kvm_irqfd.h |  1 +
 2 files changed, 14 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index d33c01379421..ed7374f0bd5a 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -766,23 +766,19 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 	return ret;
 }
 
-static void svm_ir_list_del(struct vcpu_svm *svm,
-			    struct kvm_kernel_irqfd *irqfd,
-			    struct amd_iommu_pi_data *pi)
+static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
 {
+	struct kvm_vcpu *vcpu = irqfd->irq_bypass_vcpu;
 	unsigned long flags;
-	struct kvm_kernel_irqfd *cur;
 
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-	list_for_each_entry(cur, &svm->ir_list, vcpu_list) {
-		if (cur->irq_bypass_data != pi->ir_data)
-			continue;
-		if (WARN_ON_ONCE(cur != irqfd))
-			continue;
-		list_del(&irqfd->vcpu_list);
-		break;
-	}
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	if (!vcpu)
+		return;
+
+	spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+	list_del(&irqfd->vcpu_list);
+	spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
+
+	irqfd->irq_bypass_vcpu = NULL;
 }
 
 static int svm_ir_list_add(struct vcpu_svm *svm,
@@ -795,24 +791,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm,
 	if (WARN_ON_ONCE(!pi->ir_data))
 		return -EINVAL;
 
-	/**
-	 * In some cases, the existing irte is updated and re-set,
-	 * so we need to check here if it's already been * added
-	 * to the ir_list.
-	 */
-	if (pi->prev_ga_tag) {
-		struct kvm *kvm = svm->vcpu.kvm;
-		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
-		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
-		struct vcpu_svm *prev_svm;
-
-		if (!prev_vcpu)
-			return -EINVAL;
-
-		prev_svm = to_svm(prev_vcpu);
-		svm_ir_list_del(prev_svm, irqfd, pi);
-	}
-
+	irqfd->irq_bypass_vcpu = &svm->vcpu;
 	irqfd->irq_bypass_data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
@@ -904,6 +883,8 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 
 		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
 
+		svm_ir_list_del(irqfd);
+
 		/**
 		 * Here, we setup with legacy mode in the following cases:
 		 * 1. When cannot target interrupt to a specific vcpu.
@@ -962,21 +943,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		pi.prev_ga_tag = 0;
 		pi.is_guest_mode = false;
 		ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-		/**
-		 * Check if the posted interrupt was previously
-		 * setup with the guest_mode by checking if the ga_tag
-		 * was cached. If so, we need to clean up the per-vcpu
-		 * ir_list.
-		 */
-		if (!ret && pi.prev_ga_tag) {
-			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-			struct kvm_vcpu *vcpu;
-
-			vcpu = kvm_get_vcpu_by_id(kvm, id);
-			if (vcpu)
-				svm_ir_list_del(to_svm(vcpu), irqfd, &pi);
-		}
 	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 6510a48e62aa..361c07f4466d 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -60,6 +60,7 @@ struct kvm_kernel_irqfd {
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
 
+	struct kvm_vcpu *irq_bypass_vcpu;
 	struct list_head vcpu_list;
 	void *irq_bypass_data;
 };
-- 
2.49.0.1151.ga128411c76-goog