virtio_net: fix race in RX VQ processing
Michael S. Tsirkin says:
====================
Jason Wang reported a race in RX VQ processing:
virtqueue_enable_cb is called outside napi lock,
violating virtio serialization rules.
The race has been there from day 1, but it got especially nasty in 3.0
when commit a5c262c5fd
"virtio_ring: support event idx feature"
added more dependency on vq state.
Please review, and consider for 3.11 and stable.
Changes from v1:
- Added Jason's Tested-by tag
- minor coding style fix
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
@@ -602,7 +602,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
|
|||||||
container_of(napi, struct receive_queue, napi);
|
container_of(napi, struct receive_queue, napi);
|
||||||
struct virtnet_info *vi = rq->vq->vdev->priv;
|
struct virtnet_info *vi = rq->vq->vdev->priv;
|
||||||
void *buf;
|
void *buf;
|
||||||
unsigned int len, received = 0;
|
unsigned int r, len, received = 0;
|
||||||
|
|
||||||
again:
|
again:
|
||||||
while (received < budget &&
|
while (received < budget &&
|
||||||
@@ -619,8 +619,9 @@ again:
|
|||||||
|
|
||||||
/* Out of packets? */
|
/* Out of packets? */
|
||||||
if (received < budget) {
|
if (received < budget) {
|
||||||
|
r = virtqueue_enable_cb_prepare(rq->vq);
|
||||||
napi_complete(napi);
|
napi_complete(napi);
|
||||||
if (unlikely(!virtqueue_enable_cb(rq->vq)) &&
|
if (unlikely(virtqueue_poll(rq->vq, r)) &&
|
||||||
napi_schedule_prep(napi)) {
|
napi_schedule_prep(napi)) {
|
||||||
virtqueue_disable_cb(rq->vq);
|
virtqueue_disable_cb(rq->vq);
|
||||||
__napi_schedule(napi);
|
__napi_schedule(napi);
|
||||||
|
@@ -606,6 +606,55 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
|
|||||||
}
|
}
|
||||||
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
|
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
|
||||||
|
|
||||||
|
/**
|
||||||
|
* virtqueue_enable_cb_prepare - restart callbacks after disable_cb
|
||||||
|
* @vq: the struct virtqueue we're talking about.
|
||||||
|
*
|
||||||
|
* This re-enables callbacks; it returns current queue state
|
||||||
|
* in an opaque unsigned value. This value should be later tested by
|
||||||
|
* virtqueue_poll, to detect a possible race between the driver checking for
|
||||||
|
* more work, and enabling callbacks.
|
||||||
|
*
|
||||||
|
* Caller must ensure we don't call this with other virtqueue
|
||||||
|
* operations at the same time (except where noted).
|
||||||
|
*/
|
||||||
|
unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
|
||||||
|
{
|
||||||
|
struct vring_virtqueue *vq = to_vvq(_vq);
|
||||||
|
u16 last_used_idx;
|
||||||
|
|
||||||
|
START_USE(vq);
|
||||||
|
|
||||||
|
/* We optimistically turn back on interrupts, then check if there was
|
||||||
|
* more to do. */
|
||||||
|
/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
|
||||||
|
* either clear the flags bit or point the event index at the next
|
||||||
|
* entry. Always do both to keep code simple. */
|
||||||
|
vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
|
||||||
|
vring_used_event(&vq->vring) = last_used_idx = vq->last_used_idx;
|
||||||
|
END_USE(vq);
|
||||||
|
return last_used_idx;
|
||||||
|
}
|
||||||
|
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
|
||||||
|
|
||||||
|
/**
|
||||||
|
* virtqueue_poll - query pending used buffers
|
||||||
|
* @vq: the struct virtqueue we're talking about.
|
||||||
|
* @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
|
||||||
|
*
|
||||||
|
* Returns "true" if there are pending used buffers in the queue.
|
||||||
|
*
|
||||||
|
* This does not need to be serialized.
|
||||||
|
*/
|
||||||
|
bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
|
||||||
|
{
|
||||||
|
struct vring_virtqueue *vq = to_vvq(_vq);
|
||||||
|
|
||||||
|
virtio_mb(vq->weak_barriers);
|
||||||
|
return (u16)last_used_idx != vq->vring.used->idx;
|
||||||
|
}
|
||||||
|
EXPORT_SYMBOL_GPL(virtqueue_poll);
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* virtqueue_enable_cb - restart callbacks after disable_cb.
|
* virtqueue_enable_cb - restart callbacks after disable_cb.
|
||||||
* @vq: the struct virtqueue we're talking about.
|
* @vq: the struct virtqueue we're talking about.
|
||||||
@@ -619,25 +668,8 @@ EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
|
|||||||
*/
|
*/
|
||||||
bool virtqueue_enable_cb(struct virtqueue *_vq)
|
bool virtqueue_enable_cb(struct virtqueue *_vq)
|
||||||
{
|
{
|
||||||
struct vring_virtqueue *vq = to_vvq(_vq);
|
unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
|
||||||
|
return !virtqueue_poll(_vq, last_used_idx);
|
||||||
START_USE(vq);
|
|
||||||
|
|
||||||
/* We optimistically turn back on interrupts, then check if there was
|
|
||||||
* more to do. */
|
|
||||||
/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
|
|
||||||
* either clear the flags bit or point the event index at the next
|
|
||||||
* entry. Always do both to keep code simple. */
|
|
||||||
vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
|
|
||||||
vring_used_event(&vq->vring) = vq->last_used_idx;
|
|
||||||
virtio_mb(vq->weak_barriers);
|
|
||||||
if (unlikely(more_used(vq))) {
|
|
||||||
END_USE(vq);
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
|
|
||||||
END_USE(vq);
|
|
||||||
return true;
|
|
||||||
}
|
}
|
||||||
EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
|
EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
|
||||||
|
|
||||||
|
@@ -70,6 +70,10 @@ void virtqueue_disable_cb(struct virtqueue *vq);
|
|||||||
|
|
||||||
bool virtqueue_enable_cb(struct virtqueue *vq);
|
bool virtqueue_enable_cb(struct virtqueue *vq);
|
||||||
|
|
||||||
|
unsigned virtqueue_enable_cb_prepare(struct virtqueue *vq);
|
||||||
|
|
||||||
|
bool virtqueue_poll(struct virtqueue *vq, unsigned);
|
||||||
|
|
||||||
bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
|
bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
|
||||||
|
|
||||||
void *virtqueue_detach_unused_buf(struct virtqueue *vq);
|
void *virtqueue_detach_unused_buf(struct virtqueue *vq);
|
||||||
|
Reference in New Issue
Block a user