KVM: Allow host IRQ sharing for assigned PCI 2.3 devices

PCI 2.3 allows to generically disable IRQ sources at device level. This
enables us to share legacy IRQs of such devices with other host devices
when passing them to a guest.

The new IRQ sharing feature introduced here is optional, user space has
to request it explicitly. Moreover, user space can inform us about its
view of PCI_COMMAND_INTX_DISABLE so that we can avoid unmasking the
interrupt and signaling it if the guest masked it via the virtualized
PCI config space.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 180 insertions, 29 deletions

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index ece80612b594..08e05715df72 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -55,22 +55,66 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
         return index;
 }
 
-static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
+static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id)
 {
         struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+        int ret;
 
-        if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_INTX) {
-                spin_lock(&assigned_dev->intx_lock);
+        spin_lock(&assigned_dev->intx_lock);
+        if (pci_check_and_mask_intx(assigned_dev->dev)) {
+                assigned_dev->host_irq_disabled = true;
+                ret = IRQ_WAKE_THREAD;
+        } else
+                ret = IRQ_NONE;
+        spin_unlock(&assigned_dev->intx_lock);
+
+        return ret;
+}
+
+static void
+kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
+                                 int vector)
+{
+        if (unlikely(assigned_dev->irq_requested_type &
+                     KVM_DEV_IRQ_GUEST_INTX)) {
+                mutex_lock(&assigned_dev->intx_mask_lock);
+                if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
+                        kvm_set_irq(assigned_dev->kvm,
+                                    assigned_dev->irq_source_id, vector, 1);
+                mutex_unlock(&assigned_dev->intx_mask_lock);
+        } else
+                kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+                            vector, 1);
+}
+
+static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
+{
+        struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+        if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+                spin_lock_irq(&assigned_dev->intx_lock);
                 disable_irq_nosync(irq);
                 assigned_dev->host_irq_disabled = true;
-                spin_unlock(&assigned_dev->intx_lock);
+                spin_unlock_irq(&assigned_dev->intx_lock);
         }
 
-        kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-                    assigned_dev->guest_irq, 1);
+        kvm_assigned_dev_raise_guest_irq(assigned_dev,
+                                         assigned_dev->guest_irq);
+
+        return IRQ_HANDLED;
+}
+
+#ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
+{
+        struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+        kvm_assigned_dev_raise_guest_irq(assigned_dev,
+                                         assigned_dev->guest_irq);
 
         return IRQ_HANDLED;
 }
+#endif
 
 #ifdef __KVM_HAVE_MSIX
 static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
@@ -81,8 +125,7 @@ static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
 
         if (index >= 0) {
                 vector = assigned_dev->guest_msix_entries[index].vector;
-                kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-                            vector, 1);
+                kvm_assigned_dev_raise_guest_irq(assigned_dev, vector);
         }
 
         return IRQ_HANDLED;
@@ -98,15 +141,31 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 
         kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
 
-        /* The guest irq may be shared so this ack may be
-         * from another device.
-         */
-        spin_lock(&dev->intx_lock);
-        if (dev->host_irq_disabled) {
-                enable_irq(dev->host_irq);
-                dev->host_irq_disabled = false;
+        mutex_lock(&dev->intx_mask_lock);
+
+        if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) {
+                bool reassert = false;
+
+                spin_lock_irq(&dev->intx_lock);
+                /*
+                 * The guest IRQ may be shared so this ack can come from an
+                 * IRQ for another guest device.
+                 */
+                if (dev->host_irq_disabled) {
+                        if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3))
+                                enable_irq(dev->host_irq);
+                        else if (!pci_check_and_unmask_intx(dev->dev))
+                                reassert = true;
+                        dev->host_irq_disabled = reassert;
+                }
+                spin_unlock_irq(&dev->intx_lock);
+
+                if (reassert)
+                        kvm_set_irq(dev->kvm, dev->irq_source_id,
+                                    dev->guest_irq, 1);
         }
-        spin_unlock(&dev->intx_lock);
+
+        mutex_unlock(&dev->intx_mask_lock);
 }
 
 static void deassign_guest_irq(struct kvm *kvm,
@@ -154,7 +213,15 @@ static void deassign_host_irq(struct kvm *kvm,
                 pci_disable_msix(assigned_dev->dev);
         } else {
                 /* Deal with MSI and INTx */
-                disable_irq(assigned_dev->host_irq);
+                if ((assigned_dev->irq_requested_type &
+                     KVM_DEV_IRQ_HOST_INTX) &&
+                    (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+                        spin_lock_irq(&assigned_dev->intx_lock);
+                        pci_intx(assigned_dev->dev, false);
+                        spin_unlock_irq(&assigned_dev->intx_lock);
+                        synchronize_irq(assigned_dev->host_irq);
+                } else
+                        disable_irq(assigned_dev->host_irq);
 
                 free_irq(assigned_dev->host_irq, assigned_dev);
 
@@ -235,15 +302,34 @@ void kvm_free_all_assigned_devices(struct kvm *kvm)
 static int assigned_device_enable_host_intx(struct kvm *kvm,
                                             struct kvm_assigned_dev_kernel *dev)
 {
+        irq_handler_t irq_handler;
+        unsigned long flags;
+
         dev->host_irq = dev->dev->irq;
-        /* Even though this is PCI, we don't want to use shared
-         * interrupts. Sharing host devices with guest-assigned devices
-         * on the same interrupt line is not a happy situation: there
-         * are going to be long delays in accepting, acking, etc.
+
+        /*
+         * We can only share the IRQ line with other host devices if we are
+         * able to disable the IRQ source at device-level - independently of
+         * the guest driver. Otherwise host devices may suffer from unbounded
+         * IRQ latencies when the guest keeps the line asserted.
          */
-        if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-                                 IRQF_ONESHOT, dev->irq_name, dev))
+        if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+                irq_handler = kvm_assigned_dev_intx;
+                flags = IRQF_SHARED;
+        } else {
+                irq_handler = NULL;
+                flags = IRQF_ONESHOT;
+        }
+        if (request_threaded_irq(dev->host_irq, irq_handler,
+                                 kvm_assigned_dev_thread_intx, flags,
+                                 dev->irq_name, dev))
                 return -EIO;
+
+        if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+                spin_lock_irq(&dev->intx_lock);
+                pci_intx(dev->dev, true);
+                spin_unlock_irq(&dev->intx_lock);
+        }
         return 0;
 }
 
@@ -260,8 +346,9 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
         }
 
         dev->host_irq = dev->dev->irq;
-        if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-                                 0, dev->irq_name, dev)) {
+        if (request_threaded_irq(dev->host_irq, NULL,
+                                 kvm_assigned_dev_thread_msi, 0,
+                                 dev->irq_name, dev)) {