Re: [PATCH 29/67] KVM: SVM: Stop walking list of routing table entries when updating IRTE

[Paolo Bonzini <pbonzini@redhat.com>]

On 4/4/25 21:38, Sean Christopherson wrote:
> Now that KVM SVM simply uses the provided routing entry, stop walking the
> routing table to find that entry.  KVM, via setup_routing_entry() and
> sanity checked by kvm_get_msi_route(), disallows having a GSI configured
> to trigger multiple MSIs.

I would squash this with the previous patch.  It's not large when shown 
with -b, and the coexistence of "e" and "new" after patch 28 is weird.

Paolo

> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>   arch/x86/kvm/svm/avic.c | 106 ++++++++++++++++------------------------
>   1 file changed, 43 insertions(+), 63 deletions(-)
> 
> diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
> index eb6017b01c5f..685a7b01194b 100644
> --- a/arch/x86/kvm/svm/avic.c
> +++ b/arch/x86/kvm/svm/avic.c
> @@ -852,10 +852,10 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
>   			unsigned int host_irq, uint32_t guest_irq,
>   			struct kvm_kernel_irq_routing_entry *new)
>   {
> -	struct kvm_kernel_irq_routing_entry *e;
> -	struct kvm_irq_routing_table *irq_rt;
>   	bool enable_remapped_mode = true;
> -	int idx, ret = 0;
> +	struct vcpu_data vcpu_info;
> +	struct vcpu_svm *svm = NULL;
> +	int ret = 0;
>   
>   	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
>   		return 0;
> @@ -869,70 +869,51 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
>   	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
>   		 __func__, host_irq, guest_irq, !!new);
>   
> -	idx = srcu_read_lock(&kvm->irq_srcu);
> -	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
> +	/**
> +	 * Here, we setup with legacy mode in the following cases:
> +	 * 1. When cannot target interrupt to a specific vcpu.
> +	 * 2. Unsetting posted interrupt.
> +	 * 3. APIC virtualization is disabled for the vcpu.
> +	 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
> +	 */
> +	if (new && new->type == KVM_IRQ_ROUTING_MSI &&
> +	    !get_pi_vcpu_info(kvm, new, &vcpu_info, &svm) &&
> +	    kvm_vcpu_apicv_active(&svm->vcpu)) {
> +		struct amd_iommu_pi_data pi;
>   
> -	if (guest_irq >= irq_rt->nr_rt_entries ||
> -		hlist_empty(&irq_rt->map[guest_irq])) {
> -		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
> -			     guest_irq, irq_rt->nr_rt_entries);
> -		goto out;
> -	}
> +		enable_remapped_mode = false;
>   
> -	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
> -		struct vcpu_data vcpu_info;
> -		struct vcpu_svm *svm = NULL;
> -
> -		if (e->type != KVM_IRQ_ROUTING_MSI)
> -			continue;
> -
> -		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
> +		/*
> +		 * Try to enable guest_mode in IRTE.  Note, the address
> +		 * of the vCPU's AVIC backing page is passed to the
> +		 * IOMMU via vcpu_info->pi_desc_addr.
> +		 */
> +		pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
> +					     svm->vcpu.vcpu_id);
> +		pi.is_guest_mode = true;
> +		pi.vcpu_data = &vcpu_info;
> +		ret = irq_set_vcpu_affinity(host_irq, &pi);
>   
>   		/**
> -		 * Here, we setup with legacy mode in the following cases:
> -		 * 1. When cannot target interrupt to a specific vcpu.
> -		 * 2. Unsetting posted interrupt.
> -		 * 3. APIC virtualization is disabled for the vcpu.
> -		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
> +		 * Here, we successfully setting up vcpu affinity in
> +		 * IOMMU guest mode. Now, we need to store the posted
> +		 * interrupt information in a per-vcpu ir_list so that
> +		 * we can reference to them directly when we update vcpu
> +		 * scheduling information in IOMMU irte.
>   		 */
> -		if (new && !get_pi_vcpu_info(kvm, new, &vcpu_info, &svm) &&
> -		    kvm_vcpu_apicv_active(&svm->vcpu)) {
> -			struct amd_iommu_pi_data pi;
> -
> -			enable_remapped_mode = false;
> -
> -			/*
> -			 * Try to enable guest_mode in IRTE.  Note, the address
> -			 * of the vCPU's AVIC backing page is passed to the
> -			 * IOMMU via vcpu_info->pi_desc_addr.
> -			 */
> -			pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
> -						     svm->vcpu.vcpu_id);
> -			pi.is_guest_mode = true;
> -			pi.vcpu_data = &vcpu_info;
> -			ret = irq_set_vcpu_affinity(host_irq, &pi);
> -
> -			/**
> -			 * Here, we successfully setting up vcpu affinity in
> -			 * IOMMU guest mode. Now, we need to store the posted
> -			 * interrupt information in a per-vcpu ir_list so that
> -			 * we can reference to them directly when we update vcpu
> -			 * scheduling information in IOMMU irte.
> -			 */
> -			if (!ret && pi.is_guest_mode)
> -				svm_ir_list_add(svm, irqfd, &pi);
> -		}
> -
> -		if (!ret && svm) {
> -			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
> -						 e->gsi, vcpu_info.vector,
> -						 vcpu_info.pi_desc_addr, !!new);
> -		}
> -
> -		if (ret < 0) {
> -			pr_err("%s: failed to update PI IRTE\n", __func__);
> -			goto out;
> -		}
> +		if (!ret)
> +			ret = svm_ir_list_add(svm, irqfd, &pi);
> +	}
> +
> +	if (!ret && svm) {
> +		trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
> +					 guest_irq, vcpu_info.vector,
> +					 vcpu_info.pi_desc_addr, !!new);
> +	}
> +
> +	if (ret < 0) {
> +		pr_err("%s: failed to update PI IRTE\n", __func__);
> +		goto out;
>   	}
>   
>   	if (enable_remapped_mode)
> @@ -940,7 +921,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
>   	else
>   		ret = 0;
>   out:
> -	srcu_read_unlock(&kvm->irq_srcu, idx);
>   	return ret;
>   }
>