diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1bff6bc8161a..015abf333c62 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -480,33 +480,94 @@ signal_used: nvq->batched_xdp = 0; } +static int sock_has_rx_data(struct socket *sock) +{ + if (unlikely(!sock)) + return 0; + + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + + return skb_queue_empty(&sock->sk->sk_receive_queue); +} + +static void vhost_net_busy_poll_try_queue(struct vhost_net *net, + struct vhost_virtqueue *vq) +{ + if (!vhost_vq_avail_empty(&net->dev, vq)) { + vhost_poll_queue(&vq->poll); + } else if (unlikely(vhost_enable_notify(&net->dev, vq))) { + vhost_disable_notify(&net->dev, vq); + vhost_poll_queue(&vq->poll); + } +} + +static void vhost_net_busy_poll(struct vhost_net *net, + struct vhost_virtqueue *rvq, + struct vhost_virtqueue *tvq, + bool *busyloop_intr, + bool poll_rx) +{ + unsigned long busyloop_timeout; + unsigned long endtime; + struct socket *sock; + struct vhost_virtqueue *vq = poll_rx ? tvq : rvq; + + mutex_lock_nested(&vq->mutex, poll_rx ? VHOST_NET_VQ_TX: VHOST_NET_VQ_RX); + vhost_disable_notify(&net->dev, vq); + sock = rvq->private_data; + + busyloop_timeout = poll_rx ? rvq->busyloop_timeout: + tvq->busyloop_timeout; + + preempt_disable(); + endtime = busy_clock() + busyloop_timeout; + + while (vhost_can_busy_poll(endtime)) { + if (vhost_has_work(&net->dev)) { + *busyloop_intr = true; + break; + } + + if ((sock_has_rx_data(sock) && + !vhost_vq_avail_empty(&net->dev, rvq)) || + !vhost_vq_avail_empty(&net->dev, tvq)) + break; + + cpu_relax(); + } + + preempt_enable(); + + if (poll_rx || sock_has_rx_data(sock)) + vhost_net_busy_poll_try_queue(net, vq); + else if (!poll_rx) /* On tx here, sock has no rx data. */ + vhost_enable_notify(&net->dev, rvq); + + mutex_unlock(&vq->mutex); +} + static int vhost_net_tx_get_vq_desc(struct vhost_net *net, - struct vhost_net_virtqueue *nvq, + struct vhost_net_virtqueue *tnvq, unsigned int *out_num, unsigned int *in_num, struct msghdr *msghdr, bool *busyloop_intr) { - struct vhost_virtqueue *vq = &nvq->vq; - unsigned long uninitialized_var(endtime); - int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), + struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; + struct vhost_virtqueue *rvq = &rnvq->vq; + struct vhost_virtqueue *tvq = &tnvq->vq; + + int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); - if (r == vq->num && vq->busyloop_timeout) { + if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ - if (!vhost_sock_zcopy(vq->private_data)) - vhost_tx_batch(net, nvq, vq->private_data, msghdr); - preempt_disable(); - endtime = busy_clock() + vq->busyloop_timeout; - while (vhost_can_busy_poll(endtime)) { - if (vhost_has_work(vq->dev)) { - *busyloop_intr = true; - break; - } - if (!vhost_vq_avail_empty(vq->dev, vq)) - break; - cpu_relax(); - } - preempt_enable(); - r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), + if (!vhost_sock_zcopy(tvq->private_data)) + // vhost_net_signal_used(tnvq); + vhost_tx_batch(net, tnvq, tvq->private_data, msghdr); + + vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); + + r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), out_num, in_num, NULL, NULL); } @@ -856,7 +917,7 @@ static void handle_tx(struct vhost_net *net) struct vhost_virtqueue *vq = &nvq->vq; struct socket *sock; - mutex_lock(&vq->mutex); + mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX); sock = vq->private_data; if (!sock) goto out; @@ -897,16 +958,6 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk) return len; } -static int sk_has_rx_data(struct sock *sk) -{ - struct socket *sock = sk->sk_socket; - - if (sock->ops->peek_len) - return sock->ops->peek_len(sock); - - return skb_queue_empty(&sk->sk_receive_queue); -} - static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, bool *busyloop_intr) { @@ -914,41 +965,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk, struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; - unsigned long uninitialized_var(endtime); int len = peek_head_len(rnvq, sk); - if (!len && tvq->busyloop_timeout) { + if (!len && rvq->busyloop_timeout) { /* Flush batched heads first */ vhost_net_signal_used(rnvq); /* Both tx vq and rx socket were polled here */ - mutex_lock_nested(&tvq->mutex, 1); - vhost_disable_notify(&net->dev, tvq); - - preempt_disable(); - endtime = busy_clock() + tvq->busyloop_timeout; - - while (vhost_can_busy_poll(endtime)) { - if (vhost_has_work(&net->dev)) { - *busyloop_intr = true; - break; - } - if ((sk_has_rx_data(sk) && - !vhost_vq_avail_empty(&net->dev, rvq)) || - !vhost_vq_avail_empty(&net->dev, tvq)) - break; - cpu_relax(); - } - - preempt_enable(); - - if (!vhost_vq_avail_empty(&net->dev, tvq)) { - vhost_poll_queue(&tvq->poll); - } else if (unlikely(vhost_enable_notify(&net->dev, tvq))) { - vhost_disable_notify(&net->dev, tvq); - vhost_poll_queue(&tvq->poll); - } - - mutex_unlock(&tvq->mutex); + vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true); len = peek_head_len(rnvq, sk); } @@ -1063,7 +1086,7 @@ static void handle_rx(struct vhost_net *net) __virtio16 num_buffers; int recv_pkts = 0; - mutex_lock_nested(&vq->mutex, 0); + mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); sock = vq->private_data; if (!sock) goto out; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index b13c6b4b2c66..f52008bb8df7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -294,8 +294,11 @@ static void vhost_vq_meta_reset(struct vhost_dev *d) { int i; - for (i = 0; i < d->nvqs; ++i) + for (i = 0; i < d->nvqs; ++i) { + mutex_lock(&d->vqs[i]->mutex); __vhost_vq_meta_reset(d->vqs[i]); + mutex_unlock(&d->vqs[i]->mutex); + } } static void vhost_vq_reset(struct vhost_dev *dev, @@ -891,20 +894,6 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, #define vhost_get_used(vq, x, ptr) \ vhost_get_user(vq, x, ptr, VHOST_ADDR_USED) -static void vhost_dev_lock_vqs(struct vhost_dev *d) -{ - int i = 0; - for (i = 0; i < d->nvqs; ++i) - mutex_lock_nested(&d->vqs[i]->mutex, i); -} - -static void vhost_dev_unlock_vqs(struct vhost_dev *d) -{ - int i = 0; - for (i = 0; i < d->nvqs; ++i) - mutex_unlock(&d->vqs[i]->mutex); -} - static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) @@ -954,7 +943,10 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d, if (msg->iova <= vq_msg->iova && msg->iova + msg->size - 1 >= vq_msg->iova && vq_msg->type == VHOST_IOTLB_MISS) { + mutex_lock(&node->vq->mutex); vhost_poll_queue(&node->vq->poll); + mutex_unlock(&node->vq->mutex); + list_del(&node->node); kfree(node); } @@ -986,7 +978,6 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, int ret = 0; mutex_lock(&dev->mutex); - vhost_dev_lock_vqs(dev); switch (msg->type) { case VHOST_IOTLB_UPDATE: if (!dev->iotlb) { @@ -1020,7 +1011,6 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, break; } - vhost_dev_unlock_vqs(dev); mutex_unlock(&dev->mutex); return ret;