hw/virtio: propagate vhost_virtqueue_mask() errors from start path
PATCH v2 1/1 hw/virtio: propagate vhost_virtqueue_mask() errors from start path
vhost_virtqueue_start() unmasks the call notifier by calling vhost_virtqueue_mask(), whose vhost_set_vring_call ioctl can fail (closed vhost-user socket, kernel ENOMEM, revoked guest_notifier fd) but whose void signature throws the error away. vhost_dev_start() then reports success while the backend has no valid call eventfd for that vq, leaving the guest with a working kick path but no virtqueue interrupts -- a half-up state harder to diagnose than a clean failure.
Make vhost_virtqueue_mask() return int and handle the error in the start path via the existing fail unwind. Other callers reach the function through VirtioDeviceClass.guest_notifier_mask, whose void signature offers no upward error channel; they invoke it as a statement and remain unchanged.
--- hw/virtio/vhost.c | 9 ++++++--- include/hw/virtio/vhost.h | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-)
hw/virtio/vhost.c +6 -3
@@ -1470,8 +1470,10 @@ int vhost_virtqueue_start(struct vhost_dev *dev,* will do it later. */ if (!vdev->use_guest_notifier_mask) { -/* TODO: check and handle errors. */ -vhost_virtqueue_mask (dev, vdev, idx, false); + r =vhost_virtqueue_mask (dev, vdev, idx, false); +if (r <0 ) { + goto fail; + } } if (k->query_guest_notifiers &&
@@ -1918,7 +1920,7 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n) }/* Mask/unmask events from this vq. */ -void vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n, +int vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n,bool mask) {struct VirtQueue *vvq =virtio_get_queue (vdev, n);
@@ -1940,6 +1942,7 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,if (r <0 ) {error_report ("vhost_set_vring_call failed %d" , -r); } +return r; }bool vhost_config_pending (struct vhost_dev *hdev)
include/hw/virtio/vhost.h +1 -1
@@ -312,7 +312,7 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n);/* Mask/unmask events from this vq. */ -void vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n, +int vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n,bool mask);/**
Signature · 1 line
2.50.1 (Apple Git-155)
Quoted 7 lines · Bin Guo
vhost_virtqueue_start()unmasks the call notifier by callingvhost_virtqueue_mask(), whosevhost_set_vring_callioctl can fail (closed vhost-user socket, kernel ENOMEM, revokedguest_notifierfd) but whose void signature throws the error away.vhost_dev_start()then reports success while the backend has no valid call eventfd for that vq, leaving the guest with a working kick path but no virtqueue interrupts -- a half-up state harder to diagnose than a clean failure.
Is there a real problem though?
So what if socket closed one second after we sent the fd, does it matter?
And what does it mean for a guest_notifier fd to be revoked? Is qemu likely to survive long after we started getting ENOMEM for allocations of a hundred of bytes from the kernel?
I do not object to the patch on principle but let's get it clear how it was tested, what is being fixed and why?
Quoted 61 lines
Make
vhost_virtqueue_mask()return int and handle the error in the start path via the existing fail unwind. Other callers reach the function through VirtioDeviceClass.guest_notifier_mask, whose void signature offers no upward error channel; they invoke it as a statement and remain unchanged.Signed-off-by Bin Guo <[email protected]>--- hw/virtio/vhost.c | 9 ++++++--- include/hw/virtio/vhost.h | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-)hw/virtio/vhost.c +6
-3@@ -1470,8 +1470,10 @@ int vhost_virtqueue_start(struct vhost_dev *dev,* will do it later. */ if (!vdev->use_guest_notifier_mask) { -/* TODO: check and handle errors. */ -vhost_virtqueue_mask (dev, vdev, idx, false); + r =vhost_virtqueue_mask (dev, vdev, idx, false); +if (r <0 ) { + goto fail; + } } if (k->query_guest_notifiers &&@@ -1918,7 +1920,7 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n) }/* Mask/unmask events from this vq. */ -void vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n, +int vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n,bool mask) {struct VirtQueue *vvq =virtio_get_queue (vdev, n);@@ -1940,6 +1942,7 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,if (r <0 ) {error_report ("vhost_set_vring_call failed %d" , -r); } +return r; }bool vhost_config_pending (struct vhost_dev *hdev)include/hw/virtio/vhost.h +1
-1@@ -312,7 +312,7 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n);/* Mask/unmask events from this vq. */ -void vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n, +int vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n,bool mask);/** Signature · 1 line
2.50.1 (Apple Git-155)
Hi,
Quoted 26 lines · Bin Guo
vhost_virtqueue_start()unmasks the call notifier by callingvhost_virtqueue_mask(), whosevhost_set_vring_callioctl can fail (closed vhost-user socket, kernel ENOMEM, revokedguest_notifierfd) but whose void signature throws the error away.vhost_dev_start()then reports success while the backend has no valid call eventfd for that vq, leaving the guest with a working kick path but no virtqueue interrupts -- a half-up state harder to diagnose than a clean failure.Make
vhost_virtqueue_mask()return int and handle the error in the start path via the existing fail unwind. Other callers reach the function through VirtioDeviceClass.guest_notifier_mask, whose void signature offers no upward error channel; they invoke it as a statement and remain unchanged.Signed-off-by Bin Guo <[email protected]>--- hw/virtio/vhost.c | 9 ++++++--- include/hw/virtio/vhost.h | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-)include/hw/virtio/vhost.h +0
-0
include/hw/virtio/vhost.h bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n); · line 313
Quoted 2 lines
include/hw/virtio/vhost.h +0
-0@@ -312,7 +312,7 @@ bool vhost_virtqueue_pending(struct vhost_dev *hdev, int n);/* Mask/unmask events from this vq.
Please document the new returned value, i.e.:
" * Return 0 on success, negative errno on failure."
(Good opportunity to convert to a proper docstring describing arguments)
Quoted 6 lines
include/hw/virtio/vhost.h +1
-1*/ -void vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n, +int vhost_virtqueue_mask (struct vhost_dev *hdev,VirtIODevice *vdev,int n,bool mask);/**