iommu/amd: KVM: SVM: Set pCPU info in IRTE when setting vCPU affinity

Now that setting vCPU affinity is guarded with ir_list_lock, i.e. now that
avic_physical_id_entry can be safely accessed, set the pCPU info
straight-away when setting vCPU affinity.  Putting the IRTE into posted
mode, and then immediately updating the IRTE a second time if the target
vCPU is running is wasteful and confusing.

This also fixes a flaw where a posted IRQ that arrives between putting
the IRTE into guest_mode and setting the correct destination could cause
the IOMMU to ring the doorbell on the wrong pCPU.

Link: https://lore.kernel.org/r/20250611224604.313496-44-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 2dbc9cb61c2fe61ac83cdd14c30b09ffbc209844..4c75a17632f6068ed30aaf7eb0e0402cf72ff01d 100644 (file)
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -35,6 +35,7 @@ struct amd_iommu_pi_data {
        u64 vapic_addr;         /* Physical address of the vCPU's vAPIC. */
        u32 ga_tag;
        u32 vector;             /* Guest vector of the interrupt */
+       int cpu;
        bool is_guest_mode;
        void *ir_data;
 };

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 1960bb06c4b94243f0d8c206f06bc5a28592e526..35c5fb831c289f4ad01fbe7481d45341182cd0e8 100644 (file)
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -727,6 +727,7 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 
 static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
+       int apic_id = kvm_cpu_get_apicid(vcpu->cpu);
        int ret = 0;
        unsigned long flags;
        struct vcpu_svm *svm = to_svm(vcpu);
@@ -746,7 +747,7 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 
        list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
                if (activate)
-                       ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data);
+                       ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data, apic_id);
                else
                        ret = amd_iommu_deactivate_guest_mode(irqfd->irq_bypass_data);
                if (ret)
@@ -810,6 +811,18 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
                 */
                guard(spinlock_irqsave)(&svm->ir_list_lock);
 
+               /*
+                * 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
+                * is awakened and/or scheduled in.  See also avic_vcpu_load().
+                */
+               entry = svm->avic_physical_id_entry;
+               if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+                       pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+               else
+                       pi_data.cpu = -1;
+
                ret = irq_set_vcpu_affinity(host_irq, &pi_data);
                if (ret)
                        return ret;
@@ -824,17 +837,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
                        return -EIO;
                }
 
-               /*
-                * 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
-                * is awakened and/or scheduled in.  See also avic_vcpu_load().
-                */
-               entry = svm->avic_physical_id_entry;
-               if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
-                       amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
-                                           pi_data.ir_data);
-
                irqfd->irq_bypass_data = pi_data.ir_data;
                list_add(&irqfd->vcpu_list, &svm->ir_list);
                return 0;

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 2eaba64be68ab7316d00249ed04d0133311d7a25..6352930ad0115000fb498434a219d2c2c0ea332a 100644 (file)
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3850,7 +3850,7 @@ int amd_iommu_update_ga(int cpu, void *data)
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 
-int amd_iommu_activate_guest_mode(void *data)
+int amd_iommu_activate_guest_mode(void *data, int cpu)
 {
        struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
        struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -3871,6 +3871,8 @@ int amd_iommu_activate_guest_mode(void *data)
        entry->hi.fields.vector            = ir_data->ga_vector;
        entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
+       __amd_iommu_update_ga(entry, cpu);
+
        return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
                              ir_data->irq_2_irte.index, entry);
 }
@@ -3937,7 +3939,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
                ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12);
                ir_data->ga_vector = pi_data->vector;
                ir_data->ga_tag = pi_data->ga_tag;
-               ret = amd_iommu_activate_guest_mode(ir_data);
+               ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu);
        } else {
                ret = amd_iommu_deactivate_guest_mode(ir_data);
        }

diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index fe0e16ffe0e5c3891f1e296415ef6d885bbaed66..c9f2df0c4596cb67633f1062e7e46e678c23e945 100644 (file)
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -32,7 +32,7 @@ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 
 extern int amd_iommu_update_ga(int cpu, void *data);
 
-extern int amd_iommu_activate_guest_mode(void *data);
+extern int amd_iommu_activate_guest_mode(void *data, int cpu);
 extern int amd_iommu_deactivate_guest_mode(void *data);
 
 #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
@@ -48,7 +48,7 @@ static inline int amd_iommu_update_ga(int cpu, void *data)
        return 0;
 }
 
-static inline int amd_iommu_activate_guest_mode(void *data)
+static inline int amd_iommu_activate_guest_mode(void *data, int cpu)
 {
        return 0;
 }