virtio, vhost, pc: fixes

Most notably this fixes a regression with vhost introduced by the pull before
 last.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJYLyObAAoJECgfDbjSjVRptPoIAK/4SdEAqS9pnXPekPZpIddV
 KHCFjj4Q68s22i0jpA1hxSXk1yQZIl56dnynU0DIAbCD1NYQIEmWx7uOJjppre9O
 L64V2s2ItEagFBGFwQDoJnUDIyEhth8KRqsa36V2YWJXYOaH1Rx1QNb9tX9R0aeb
 2lVwYE+yig1Gc/2PAYJrcKWwM3iwWrYW6ssycP2LEOGOhBCIrGZwDJkqv7ayDVL9
 j4tH2eBRrOAzm8c3fybC3OZkeLqcQJnbVONmD8kV0Q0IphcFvloJQCvcefb/3Ox1
 HAz57JxZfpxMZPVtvgU8Q+xzElz8noCXg+6lF/dx71CKicwXxg4lsMF1LyKHUoU=
 =cuAn
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'mst/tags/for_upstream' into staging

virtio, vhost, pc: fixes

Most notably this fixes a regression with vhost introduced by the pull before
last.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 18 Nov 2016 03:51:55 PM GMT
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* mst/tags/for_upstream:
  acpi: Use apic_id_limit when calculating legacy ACPI table size
  ipmi: fix qemu crash while migrating with ipmi
  ivshmem: Fix 64 bit memory bar configuration
  virtio: set ISR on dataplane notifications
  virtio: access ISR atomically
  virtio: introduce grab/release_ioeventfd to fix vhost
  virtio-crypto: fix virtio_queue_set_notification() race

Message-id: 1479484366-7977-1-git-send-email-mst@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

hw/block/dataplane/virtio-blk.c

@@ -68,9 +68,7 @@ static void notify_guest_bh(void *opaque)
             unsigned i = j + ctzl(bits);
             VirtQueue *vq = virtio_get_queue(s->vdev, i);
 
-            if (virtio_should_notify(s->vdev, vq)) {
+            virtio_notify_irqfd(s->vdev, vq);
-                event_notifier_set(virtio_queue_get_guest_notifier(vq));
-            }
 
             bits &= bits - 1; /* clear right-most bit */
         }

hw/i386/acpi-build.c

@@ -2860,7 +2860,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
          */
         int legacy_aml_len =
             pcmc->legacy_acpi_table_size +
-            ACPI_BUILD_LEGACY_CPU_AML_SIZE * max_cpus;
+            ACPI_BUILD_LEGACY_CPU_AML_SIZE * pcms->apic_id_limit;
         int legacy_table_size =
             ROUND_UP(tables_blob->len - aml_len + legacy_aml_len,
                      ACPI_BUILD_ALIGN_SIZE);

hw/ipmi/isa_ipmi_kcs.c

@@ -433,10 +433,8 @@ const VMStateDescription vmstate_ISAIPMIKCSDevice = {
         VMSTATE_BOOL(kcs.use_irq, ISAIPMIKCSDevice),
         VMSTATE_BOOL(kcs.irqs_enabled, ISAIPMIKCSDevice),
         VMSTATE_UINT32(kcs.outpos, ISAIPMIKCSDevice),
-        VMSTATE_VBUFFER_UINT32(kcs.outmsg, ISAIPMIKCSDevice, 1, NULL, 0,
+        VMSTATE_UINT8_ARRAY(kcs.outmsg, ISAIPMIKCSDevice, MAX_IPMI_MSG_SIZE),
-                               kcs.outlen),
+        VMSTATE_UINT8_ARRAY(kcs.inmsg, ISAIPMIKCSDevice, MAX_IPMI_MSG_SIZE),
-        VMSTATE_VBUFFER_UINT32(kcs.inmsg, ISAIPMIKCSDevice, 1, NULL, 0,
-                               kcs.inlen),
         VMSTATE_BOOL(kcs.write_end, ISAIPMIKCSDevice),
         VMSTATE_UINT8(kcs.status_reg, ISAIPMIKCSDevice),
         VMSTATE_UINT8(kcs.data_out_reg, ISAIPMIKCSDevice),

hw/scsi/virtio-scsi-dataplane.c

@@ -95,13 +95,6 @@ static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n,
     return 0;
 }
 
-void virtio_scsi_dataplane_notify(VirtIODevice *vdev, VirtIOSCSIReq *req)
-{
-    if (virtio_should_notify(vdev, req->vq)) {
-        event_notifier_set(virtio_queue_get_guest_notifier(req->vq));
-    }
-}
-
 /* assumes s->ctx held */
 static void virtio_scsi_clear_aio(VirtIOSCSI *s)
 {

hw/scsi/virtio-scsi.c

@@ -69,7 +69,7 @@ static void virtio_scsi_complete_req(VirtIOSCSIReq *req)
     qemu_iovec_from_buf(&req->resp_iov, 0, &req->resp, req->resp_size);
     virtqueue_push(vq, &req->elem, req->qsgl.size + req->resp_iov.size);
     if (s->dataplane_started && !s->dataplane_fenced) {
-        virtio_scsi_dataplane_notify(vdev, req);
+        virtio_notify_irqfd(vdev, vq);
     } else {
         virtio_notify(vdev, vq);
     }

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"
 

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.

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) {
+    /* Only set our notifier if we have ownership.  */
-        error_report("%s: failed. Fallback to userspace (slower).", __func__);
+    if (!bus->ioeventfd_grabbed) {
-        return r;
+        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);
+    /* Only remove our notifier if we have ownership.  */
-    vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
+    if (!bus->ioeventfd_grabbed) {
-    vdc->stop_ioeventfd(vdev);
+        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);
     }
 

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);
+    for (;;) {
-    virtio_queue_set_notification(q->dataq, 1);
+        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

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);
 }

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;
+        ret = atomic_xchg(&vdev->isr, 0);
-        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;
+    uint64_t val = atomic_xchg(&vdev->isr, 0);
-
-    vdev->isr = 0;
     pci_irq_deassert(&proxy->pci_dev);
 
     return val;

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);
+    uint8_t old = atomic_read(&vdev->isr);
-    vq->vdev->isr |= 0x01;
+
-    virtio_notify_vector(vq->vdev, vq->vector);
+    /* 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. */

include/hw/virtio/virtio-bus.h

@@ -97,6 +97,16 @@ struct VirtioBusState {
      * Set if ioeventfd has been started.
      */
     bool ioeventfd_started;
+
+    /*
+     * Set if ioeventfd has been grabbed by vhost.  When ioeventfd
+     * is grabbed by vhost, we track its started/stopped state (which
+     * depends in turn on the virtio status register), but do not
+     * register a handler for the ioeventfd.  When ioeventfd is
+     * released, if ioeventfd_started is true we finally register
+     * the handler so that QEMU's device model can use ioeventfd.
+     */
+    int ioeventfd_grabbed;
 };
 
 void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp);
@@ -131,6 +141,10 @@ bool virtio_bus_ioeventfd_enabled(VirtioBusState *bus);
 int virtio_bus_start_ioeventfd(VirtioBusState *bus);
 /* Stop the ioeventfd. */
 void virtio_bus_stop_ioeventfd(VirtioBusState *bus);
+/* Tell the bus that vhost is grabbing the ioeventfd. */
+int virtio_bus_grab_ioeventfd(VirtioBusState *bus);
+/* bus that vhost is not using the ioeventfd anymore. */
+void virtio_bus_release_ioeventfd(VirtioBusState *bus);
 /* Switch from/to the generic ioeventfd handler */
 int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign);
 

include/hw/virtio/virtio-scsi.h

@@ -137,6 +137,5 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
 void virtio_scsi_dataplane_setup(VirtIOSCSI *s, Error **errp);
 int virtio_scsi_dataplane_start(VirtIODevice *s);
 void virtio_scsi_dataplane_stop(VirtIODevice *s);
-void virtio_scsi_dataplane_notify(VirtIODevice *vdev, VirtIOSCSIReq *req);
 
 #endif /* QEMU_VIRTIO_SCSI_H */

include/hw/virtio/virtio.h

@@ -181,6 +181,7 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
                                unsigned max_in_bytes, unsigned max_out_bytes);
 
 bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq);
+void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq);
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq);
 
 void virtio_save(VirtIODevice *vdev, QEMUFile *f);
@@ -272,13 +273,14 @@ void virtio_queue_set_guest_notifier_fd_handler(VirtQueue *vq, bool assign,
                                                 bool with_irqfd);
 int virtio_device_start_ioeventfd(VirtIODevice *vdev);
 void virtio_device_stop_ioeventfd(VirtIODevice *vdev);
+int virtio_device_grab_ioeventfd(VirtIODevice *vdev);
+void virtio_device_release_ioeventfd(VirtIODevice *vdev);
 bool virtio_device_ioeventfd_enabled(VirtIODevice *vdev);
 EventNotifier *virtio_queue_get_host_notifier(VirtQueue *vq);
 void virtio_queue_host_notifier_read(EventNotifier *n);
 void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx,
                                                 void (*fn)(VirtIODevice *,
                                                            VirtQueue *));
-void virtio_irq(VirtQueue *vq);
 VirtQueue *virtio_vector_first_queue(VirtIODevice *vdev, uint16_t vector);
 VirtQueue *virtio_vector_next_queue(VirtQueue *vq);