1 files changed, 51 insertions, 8 deletions

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index cfc8ab773025..2092db892d7d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -791,6 +791,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	int ret = 0;
 	unsigned long flags;
 	struct amd_svm_iommu_ir *ir;
+	u64 entry;
 
 	/**
 	 * In some cases, the existing irte is updated and re-set,
@@ -824,6 +825,18 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 	ir->data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
+	/*
+	 * Update the target pCPU for IOMMU doorbells if the vCPU is running.
+	 * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM
+	 * will update the pCPU info when the vCPU awkened and/or scheduled in.
+	 * See also avic_vcpu_load().
+	 */
+	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
+				    true, pi->ir_data);
+
 	list_add(&ir->node, &svm->ir_list);
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 out:
@@ -986,10 +999,11 @@ static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
 	int ret = 0;
-	unsigned long flags;
 	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_held(&svm->ir_list_lock);
+
 	if (!kvm_arch_has_assigned_device(vcpu->kvm))
 		return 0;
 
@@ -997,19 +1011,15 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 	 * Here, we go through the per-vcpu ir_list to update all existing
 	 * interrupt remapping table entry targeting this vcpu.
 	 */
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-
 	if (list_empty(&svm->ir_list))
-		goto out;
+		return 0;
 
 	list_for_each_entry(ir, &svm->ir_list, node) {
 		ret = amd_iommu_update_ga(cpu, r, ir->data);
 		if (ret)
-			break;
+			return ret;
 	}
-out:
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-	return ret;
+	return 0;
 }
 
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1017,6 +1027,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	u64 entry;
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long flags;
 
 	lockdep_assert_preemption_disabled();
 
@@ -1033,6 +1044,15 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (kvm_vcpu_is_blocking(vcpu))
 		return;
 
+	/*
+	 * Grab the per-vCPU interrupt remapping lock even if the VM doesn't
+	 * _currently_ have assigned devices, as that can change.  Holding
+	 * ir_list_lock ensures that either svm_ir_list_add() will consume
+	 * up-to-date entry information, or that this task will wait until
+	 * svm_ir_list_add() completes to set the new target pCPU.
+	 */
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
@@ -1042,25 +1062,48 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long flags;
 
 	lockdep_assert_preemption_disabled();
 
+	/*
+	 * Note, reading the Physical ID entry outside of ir_list_lock is safe
+	 * as only the pCPU that has loaded (or is loading) the vCPU is allowed
+	 * to modify the entry, and preemption is disabled.  I.e. the vCPU
+	 * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
+	 * recursively.
+	 */
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 
 	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
 	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
 		return;
 
+	/*
+	 * Take and hold the per-vCPU interrupt remapping lock while updating
+	 * the Physical ID entry even though the lock doesn't protect against
+	 * multiple writers (see above).  Holding ir_list_lock ensures that
+	 * either svm_ir_list_add() will consume up-to-date entry information,
+	 * or that this task will wait until svm_ir_list_add() completes to
+	 * mark the vCPU as not running.
+	 */
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+
 	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+
 }
 
 void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)