summary refs log tree commit diff stats
path: root/hw/virtio
diff options
context:
space:
mode:
Diffstat (limited to 'hw/virtio')
-rw-r--r--hw/virtio/trace-events2
-rw-r--r--hw/virtio/vhost.c14
-rw-r--r--hw/virtio/virtio-bus.c58
-rw-r--r--hw/virtio/virtio-crypto.c13
-rw-r--r--hw/virtio/virtio-mmio.c6
-rw-r--r--hw/virtio/virtio-pci.c9
-rw-r--r--hw/virtio/virtio.c66
7 files changed, 129 insertions, 39 deletions
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 8756cefa79..7b6f55e70e 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -5,7 +5,7 @@ virtqueue_fill(void *vq, const void *elem, unsigned int len, unsigned int idx) "
 virtqueue_flush(void *vq, unsigned int count) "vq %p count %u"
 virtqueue_pop(void *vq, void *elem, unsigned int in_num, unsigned int out_num) "vq %p elem %p in_num %u out_num %u"
 virtio_queue_notify(void *vdev, int n, void *vq) "vdev %p n %d vq %p"
-virtio_irq(void *vq) "vq %p"
+virtio_notify_irqfd(void *vdev, void *vq) "vdev %p vq %p"
 virtio_notify(void *vdev, void *vq) "vdev %p vq %p"
 virtio_set_status(void *vdev, uint8_t val) "vdev %p val %u"
 
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 30aee88a3e..f7f70237db 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -1214,17 +1214,17 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
 int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
 {
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
-    VirtioBusState *vbus = VIRTIO_BUS(qbus);
-    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
     int i, r, e;
 
-    if (!k->ioeventfd_assign) {
+    /* We will pass the notifiers to the kernel, make sure that QEMU
+     * doesn't interfere.
+     */
+    r = virtio_device_grab_ioeventfd(vdev);
+    if (r < 0) {
         error_report("binding does not support host notifiers");
-        r = -ENOSYS;
         goto fail;
     }
 
-    virtio_device_stop_ioeventfd(vdev);
     for (i = 0; i < hdev->nvqs; ++i) {
         r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
                                          true);
@@ -1244,7 +1244,7 @@ fail_vq:
         }
         assert (e >= 0);
     }
-    virtio_device_start_ioeventfd(vdev);
+    virtio_device_release_ioeventfd(vdev);
 fail:
     return r;
 }
@@ -1267,7 +1267,7 @@ void vhost_dev_disable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
         }
         assert (r >= 0);
     }
-    virtio_device_start_ioeventfd(vdev);
+    virtio_device_release_ioeventfd(vdev);
 }
 
 /* Test and clear event pending status.
diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c
index bf61f66a04..d6c0c72bd2 100644
--- a/hw/virtio/virtio-bus.c
+++ b/hw/virtio/virtio-bus.c
@@ -147,6 +147,39 @@ void virtio_bus_set_vdev_config(VirtioBusState *bus, uint8_t *config)
     }
 }
 
+/* On success, ioeventfd ownership belongs to the caller.  */
+int virtio_bus_grab_ioeventfd(VirtioBusState *bus)
+{
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
+
+    /* vhost can be used even if ioeventfd=off in the proxy device,
+     * so do not check k->ioeventfd_enabled.
+     */
+    if (!k->ioeventfd_assign) {
+        return -ENOSYS;
+    }
+
+    if (bus->ioeventfd_grabbed == 0 && bus->ioeventfd_started) {
+        virtio_bus_stop_ioeventfd(bus);
+        /* Remember that we need to restart ioeventfd
+         * when ioeventfd_grabbed becomes zero.
+         */
+        bus->ioeventfd_started = true;
+    }
+    bus->ioeventfd_grabbed++;
+    return 0;
+}
+
+void virtio_bus_release_ioeventfd(VirtioBusState *bus)
+{
+    assert(bus->ioeventfd_grabbed != 0);
+    if (--bus->ioeventfd_grabbed == 0 && bus->ioeventfd_started) {
+        /* Force virtio_bus_start_ioeventfd to act.  */
+        bus->ioeventfd_started = false;
+        virtio_bus_start_ioeventfd(bus);
+    }
+}
+
 int virtio_bus_start_ioeventfd(VirtioBusState *bus)
 {
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
@@ -161,10 +194,14 @@ int virtio_bus_start_ioeventfd(VirtioBusState *bus)
     if (bus->ioeventfd_started) {
         return 0;
     }
-    r = vdc->start_ioeventfd(vdev);
-    if (r < 0) {
-        error_report("%s: failed. Fallback to userspace (slower).", __func__);
-        return r;
+
+    /* Only set our notifier if we have ownership.  */
+    if (!bus->ioeventfd_grabbed) {
+        r = vdc->start_ioeventfd(vdev);
+        if (r < 0) {
+            error_report("%s: failed. Fallback to userspace (slower).", __func__);
+            return r;
+        }
     }
     bus->ioeventfd_started = true;
     return 0;
@@ -179,9 +216,12 @@ void virtio_bus_stop_ioeventfd(VirtioBusState *bus)
         return;
     }
 
-    vdev = virtio_bus_get_device(bus);
-    vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
-    vdc->stop_ioeventfd(vdev);
+    /* Only remove our notifier if we have ownership.  */
+    if (!bus->ioeventfd_grabbed) {
+        vdev = virtio_bus_get_device(bus);
+        vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
+        vdc->stop_ioeventfd(vdev);
+    }
     bus->ioeventfd_started = false;
 }
 
@@ -211,7 +251,6 @@ int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)
     }
 
     if (assign) {
-        assert(!bus->ioeventfd_started);
         r = event_notifier_init(notifier, 1);
         if (r < 0) {
             error_report("%s: unable to init event notifier: %s (%d)",
@@ -225,9 +264,6 @@ int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)
         }
         return 0;
     } else {
-        if (!bus->ioeventfd_started) {
-            return 0;
-        }
         k->ioeventfd_assign(proxy, notifier, n, false);
     }
 
diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c
index 32938433b7..847dc9dafd 100644
--- a/hw/virtio/virtio-crypto.c
+++ b/hw/virtio/virtio-crypto.c
@@ -692,8 +692,17 @@ static void virtio_crypto_dataq_bh(void *opaque)
         return;
     }
 
-    virtio_crypto_handle_dataq(vdev, q->dataq);
-    virtio_queue_set_notification(q->dataq, 1);
+    for (;;) {
+        virtio_crypto_handle_dataq(vdev, q->dataq);
+        virtio_queue_set_notification(q->dataq, 1);
+
+        /* Are we done or did the guest add more buffers? */
+        if (virtio_queue_empty(q->dataq)) {
+            break;
+        }
+
+        virtio_queue_set_notification(q->dataq, 0);
+    }
 }
 
 static void
diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
index a30270f902..17412cb7b5 100644
--- a/hw/virtio/virtio-mmio.c
+++ b/hw/virtio/virtio-mmio.c
@@ -191,7 +191,7 @@ static uint64_t virtio_mmio_read(void *opaque, hwaddr offset, unsigned size)
         return virtio_queue_get_addr(vdev, vdev->queue_sel)
             >> proxy->guest_page_shift;
     case VIRTIO_MMIO_INTERRUPTSTATUS:
-        return vdev->isr;
+        return atomic_read(&vdev->isr);
     case VIRTIO_MMIO_STATUS:
         return vdev->status;
     case VIRTIO_MMIO_HOSTFEATURESSEL:
@@ -299,7 +299,7 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
         }
         break;
     case VIRTIO_MMIO_INTERRUPTACK:
-        vdev->isr &= ~value;
+        atomic_and(&vdev->isr, ~value);
         virtio_update_irq(vdev);
         break;
     case VIRTIO_MMIO_STATUS:
@@ -347,7 +347,7 @@ static void virtio_mmio_update_irq(DeviceState *opaque, uint16_t vector)
     if (!vdev) {
         return;
     }
-    level = (vdev->isr != 0);
+    level = (atomic_read(&vdev->isr) != 0);
     DPRINTF("virtio_mmio setting IRQ %d\n", level);
     qemu_set_irq(proxy->irq, level);
 }
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 97b32febaf..521ba0b415 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -73,7 +73,7 @@ static void virtio_pci_notify(DeviceState *d, uint16_t vector)
         msix_notify(&proxy->pci_dev, vector);
     else {
         VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-        pci_set_irq(&proxy->pci_dev, vdev->isr & 1);
+        pci_set_irq(&proxy->pci_dev, atomic_read(&vdev->isr) & 1);
     }
 }
 
@@ -449,8 +449,7 @@ static uint32_t virtio_ioport_read(VirtIOPCIProxy *proxy, uint32_t addr)
         break;
     case VIRTIO_PCI_ISR:
         /* reading from the ISR also clears it. */
-        ret = vdev->isr;
-        vdev->isr = 0;
+        ret = atomic_xchg(&vdev->isr, 0);
         pci_irq_deassert(&proxy->pci_dev);
         break;
     case VIRTIO_MSI_CONFIG_VECTOR:
@@ -1379,9 +1378,7 @@ static uint64_t virtio_pci_isr_read(void *opaque, hwaddr addr,
 {
     VirtIOPCIProxy *proxy = opaque;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    uint64_t val = vdev->isr;
-
-    vdev->isr = 0;
+    uint64_t val = atomic_xchg(&vdev->isr, 0);
     pci_irq_deassert(&proxy->pci_dev);
 
     return val;
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 55a00cdf9e..1af2de2714 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -945,7 +945,7 @@ void virtio_reset(void *opaque)
     vdev->guest_features = 0;
     vdev->queue_sel = 0;
     vdev->status = 0;
-    vdev->isr = 0;
+    atomic_set(&vdev->isr, 0);
     vdev->config_vector = VIRTIO_NO_VECTOR;
     virtio_notify_vector(vdev, vdev->config_vector);
 
@@ -1318,11 +1318,16 @@ void virtio_del_queue(VirtIODevice *vdev, int n)
     vdev->vq[n].vring.num_default = 0;
 }
 
-void virtio_irq(VirtQueue *vq)
+static void virtio_set_isr(VirtIODevice *vdev, int value)
 {
-    trace_virtio_irq(vq);
-    vq->vdev->isr |= 0x01;
-    virtio_notify_vector(vq->vdev, vq->vector);
+    uint8_t old = atomic_read(&vdev->isr);
+
+    /* Do not write ISR if it does not change, so that its cacheline remains
+     * shared in the common case where the guest does not read it.
+     */
+    if ((old & value) != value) {
+        atomic_or(&vdev->isr, value);
+    }
 }
 
 bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq)
@@ -1348,6 +1353,33 @@ bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq)
     return !v || vring_need_event(vring_get_used_event(vq), new, old);
 }
 
+void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq)
+{
+    if (!virtio_should_notify(vdev, vq)) {
+        return;
+    }
+
+    trace_virtio_notify_irqfd(vdev, vq);
+
+    /*
+     * virtio spec 1.0 says ISR bit 0 should be ignored with MSI, but
+     * windows drivers included in virtio-win 1.8.0 (circa 2015) are
+     * incorrectly polling this bit during crashdump and hibernation
+     * in MSI mode, causing a hang if this bit is never updated.
+     * Recent releases of Windows do not really shut down, but rather
+     * log out and hibernate to make the next startup faster.  Hence,
+     * this manifested as a more serious hang during shutdown with
+     *
+     * Next driver release from 2016 fixed this problem, so working around it
+     * is not a must, but it's easy to do so let's do it here.
+     *
+     * Note: it's safe to update ISR from any thread as it was switched
+     * to an atomic operation.
+     */
+    virtio_set_isr(vq->vdev, 0x1);
+    event_notifier_set(&vq->guest_notifier);
+}
+
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
 {
     if (!virtio_should_notify(vdev, vq)) {
@@ -1355,7 +1387,7 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
     }
 
     trace_virtio_notify(vdev, vq);
-    vdev->isr |= 0x01;
+    virtio_set_isr(vq->vdev, 0x1);
     virtio_notify_vector(vdev, vq->vector);
 }
 
@@ -1364,7 +1396,7 @@ void virtio_notify_config(VirtIODevice *vdev)
     if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
         return;
 
-    vdev->isr |= 0x03;
+    virtio_set_isr(vdev, 0x3);
     vdev->generation++;
     virtio_notify_vector(vdev, vdev->config_vector);
 }
@@ -1895,7 +1927,7 @@ void virtio_init(VirtIODevice *vdev, const char *name,
 
     vdev->device_id = device_id;
     vdev->status = 0;
-    vdev->isr = 0;
+    atomic_set(&vdev->isr, 0);
     vdev->queue_sel = 0;
     vdev->config_vector = VIRTIO_NO_VECTOR;
     vdev->vq = g_malloc0(sizeof(VirtQueue) * VIRTIO_QUEUE_MAX);
@@ -1982,7 +2014,7 @@ static void virtio_queue_guest_notifier_read(EventNotifier *n)
 {
     VirtQueue *vq = container_of(n, VirtQueue, guest_notifier);
     if (event_notifier_test_and_clear(n)) {
-        virtio_irq(vq);
+        virtio_notify_vector(vq->vdev, vq->vector);
     }
 }
 
@@ -2191,6 +2223,22 @@ void virtio_device_stop_ioeventfd(VirtIODevice *vdev)
     virtio_bus_stop_ioeventfd(vbus);
 }
 
+int virtio_device_grab_ioeventfd(VirtIODevice *vdev)
+{
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusState *vbus = VIRTIO_BUS(qbus);
+
+    return virtio_bus_grab_ioeventfd(vbus);
+}
+
+void virtio_device_release_ioeventfd(VirtIODevice *vdev)
+{
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusState *vbus = VIRTIO_BUS(qbus);
+
+    virtio_bus_release_ioeventfd(vbus);
+}
+
 static void virtio_device_class_init(ObjectClass *klass, void *data)
 {
     /* Set the default value here. */