1 files changed, 68 insertions, 47 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 831eb4fd197..8dae2f724a3 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -17,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <linux/net.h>
 #include <linux/if_packet.h>
@@ -70,7 +71,12 @@ enum {
 };
 
 struct vhost_net_ubuf_ref {
-	struct kref kref;
+	/* refcount follows semantics similar to kref:
+	 *  0: object is released
+	 *  1: no outstanding ubufs
+	 * >1: outstanding ubufs
+	 */
+	atomic_t refcount;
 	wait_queue_head_t wait;
 	struct vhost_virtqueue *vq;
 };
@@ -116,14 +122,6 @@ static void vhost_net_enable_zcopy(int vq)
 	vhost_net_zcopy_mask |= 0x1 << vq;
 }
 
-static void vhost_net_zerocopy_done_signal(struct kref *kref)
-{
-	struct vhost_net_ubuf_ref *ubufs;
-
-	ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref);
-	wake_up(&ubufs->wait);
-}
-
 static struct vhost_net_ubuf_ref *
 vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 {
@@ -134,21 +132,24 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 	ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL);
 	if (!ubufs)
 		return ERR_PTR(-ENOMEM);
-	kref_init(&ubufs->kref);
+	atomic_set(&ubufs->refcount, 1);
 	init_waitqueue_head(&ubufs->wait);
 	ubufs->vq = vq;
 	return ubufs;
 }
 
-static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
+static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
 {
-	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
+	int r = atomic_sub_return(1, &ubufs->refcount);
+	if (unlikely(!r))
+		wake_up(&ubufs->wait);
+	return r;
 }
 
 static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
 {
-	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
-	wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+	vhost_net_ubuf_put(ubufs);
+	wait_event(ubufs->wait, !atomic_read(&ubufs->refcount));
 }
 
 static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
@@ -306,23 +307,26 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
 {
 	struct vhost_net_ubuf_ref *ubufs = ubuf->ctx;
 	struct vhost_virtqueue *vq = ubufs->vq;
-	int cnt = atomic_read(&ubufs->kref.refcount);
+	int cnt;
+
+	rcu_read_lock_bh();
 
 	/* set len to mark this desc buffers done DMA */
 	vq->heads[ubuf->desc].len = success ?
 		VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
-	vhost_net_ubuf_put(ubufs);
+	cnt = vhost_net_ubuf_put(ubufs);
 
 	/*
 	 * Trigger polling thread if guest stopped submitting new buffers:
-	 * in this case, the refcount after decrement will eventually reach 1
-	 * so here it is 2.
+	 * in this case, the refcount after decrement will eventually reach 1.
 	 * We also trigger polling periodically after each 16 packets
 	 * (the value 16 here is more or less arbitrary, it's tuned to trigger
 	 * less than 10% of times).
 	 */
-	if (cnt <= 2 || !(cnt % 16))
+	if (cnt <= 1 || !(cnt % 16))
 		vhost_poll_queue(&vq->poll);
+
+	rcu_read_unlock_bh();
 }
 
 /* Expects to be always run from workqueue - which acts as
@@ -370,7 +374,7 @@ static void handle_tx(struct vhost_net *net)
 			      % UIO_MAXIOV == nvq->done_idx))
 			break;
 
-		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
+		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov),
 					 &out, &in,
 					 NULL, NULL);
@@ -420,7 +424,7 @@ static void handle_tx(struct vhost_net *net)
 			msg.msg_control = ubuf;
 			msg.msg_controllen = sizeof(ubuf);
 			ubufs = nvq->ubufs;
-			kref_get(&ubufs->kref);
+			atomic_inc(&ubufs->refcount);
 			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
 		} else {
 			msg.msg_control = NULL;
@@ -502,9 +506,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;
@@ -529,6 +537,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -571,9 +585,9 @@ static void handle_rx(struct vhost_net *net)
 	vhost_hlen = nvq->vhost_hlen;
 	sock_hlen = nvq->sock_hlen;
 
-	vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
+	vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
 		vq->log : NULL;
-	mergeable = vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF);
+	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
 	while ((sock_len = peek_head_len(sock->sk))) {
 		sock_len += sock_hlen;
@@ -584,6 +598,14 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -680,16 +702,20 @@ static void handle_rx_net(struct vhost_work *work)
 
 static int vhost_net_open(struct inode *inode, struct file *f)
 {
-	struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
+	struct vhost_net *n;
 	struct vhost_dev *dev;
 	struct vhost_virtqueue **vqs;
-	int r, i;
+	int i;
 
-	if (!n)
-		return -ENOMEM;
+	n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!n) {
+		n = vmalloc(sizeof *n);
+		if (!n)
+			return -ENOMEM;
+	}
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
-		kfree(n);
+		kvfree(n);
 		return -ENOMEM;
 	}
 
@@ -706,12 +732,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].vhost_hlen = 0;
 		n->vqs[i].sock_hlen = 0;
 	}
-	r = vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
-	if (r < 0) {
-		kfree(n);
-		kfree(vqs);
-		return r;
-	}
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
@@ -785,7 +806,7 @@ static void vhost_net_flush(struct vhost_net *n)
 		vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs);
 		mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
 		n->tx_flush = false;
-		kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref);
+		atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1);
 		mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
 	}
 }
@@ -802,14 +823,16 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 	vhost_dev_cleanup(&n->dev, false);
 	vhost_net_vq_reset(n);
 	if (tx_sock)
-		fput(tx_sock->file);
+		sockfd_put(tx_sock);
 	if (rx_sock)
-		fput(rx_sock->file);
+		sockfd_put(rx_sock);
+	/* Make sure no callbacks are outstanding */
+	synchronize_rcu_bh();
 	/* We do an extra flush before freeing memory,
 	 * since jobs can re-queue themselves. */
 	vhost_net_flush(n);
 	kfree(n->dev.vqs);
-	kfree(n);
+	kvfree(n);
 	return 0;
 }
 
@@ -842,7 +865,7 @@ static struct socket *get_raw_socket(int fd)
 	}
 	return sock;
 err:
-	fput(sock->file);
+	sockfd_put(sock);
 	return ERR_PTR(r);
 }
 
@@ -948,7 +971,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 
 	if (oldsock) {
 		vhost_net_flush_vq(n, index);
-		fput(oldsock->file);
+		sockfd_put(oldsock);
 	}
 
 	mutex_unlock(&n->dev.mutex);
@@ -960,7 +983,7 @@ err_used:
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
 err_ubufs:
-	fput(sock->file);
+	sockfd_put(sock);
 err_vq:
 	mutex_unlock(&vq->mutex);
 err:
@@ -991,9 +1014,9 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 done:
 	mutex_unlock(&n->dev.mutex);
 	if (tx_sock)
-		fput(tx_sock->file);
+		sockfd_put(tx_sock);
 	if (rx_sock)
-		fput(rx_sock->file);
+		sockfd_put(rx_sock);
 	return err;
 }
 
@@ -1020,15 +1043,13 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 		mutex_unlock(&n->dev.mutex);
 		return -EFAULT;
 	}
-	n->dev.acked_features = features;
-	smp_wmb();
 	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
 		mutex_lock(&n->vqs[i].vq.mutex);
+		n->vqs[i].vq.acked_features = features;
 		n->vqs[i].vhost_hlen = vhost_hlen;
 		n->vqs[i].sock_hlen = sock_hlen;
 		mutex_unlock(&n->vqs[i].vq.mutex);
 	}
-	vhost_net_flush(n);
 	mutex_unlock(&n->dev.mutex);
 	return 0;
 }