Merge branch 'vhost-net-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Michael S. Tsirkin says:

--------------------
There are mostly bugfixes here.
I hope to merge some more patches by 3.5, in particular
vlan support fixes are waiting for Eric's ack,
and a version of tracepoint patch might be
ready in time, but let's merge what's ready so it's testable.

This includes a ton of zerocopy fixes by Jason -
good stuff but too intrusive for 3.4 and zerocopy is experimental
anyway.

virtio supported delayed interrupt for a while now
so adding support to the virtio tool made sense
--------------------

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 69 insertions, 23 deletions

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0427c6561c84..163559c16988 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -505,10 +505,11 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
 		if (copy > size) {
 			++from;
 			--count;
-		}
+			offset = 0;
+		} else
+			offset += size;
 		copy -= size;
 		offset1 += size;
-		offset = 0;
 	}
 
 	if (len == offset1)
@@ -518,24 +519,29 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
 		struct page *page[MAX_SKB_FRAGS];
 		int num_pages;
 		unsigned long base;
+		unsigned long truesize;
 
-		len = from->iov_len - offset1;
+		len = from->iov_len - offset;
 		if (!len) {
-			offset1 = 0;
+			offset = 0;
 			++from;
 			continue;
 		}
-		base = (unsigned long)from->iov_base + offset1;
+		base = (unsigned long)from->iov_base + offset;
 		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		if (i + size > MAX_SKB_FRAGS)
+			return -EMSGSIZE;
 		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
-		if ((num_pages != size) ||
-		    (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags))
-			/* put_page is in skb free */
+		if (num_pages != size) {
+			for (i = 0; i < num_pages; i++)
+				put_page(page[i]);
 			return -EFAULT;
+		}
+		truesize = size * PAGE_SIZE;
 		skb->data_len += len;
 		skb->len += len;
-		skb->truesize += len;
-		atomic_add(len, &skb->sk->sk_wmem_alloc);
+		skb->truesize += truesize;
+		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
 		while (len) {
 			int off = base & ~PAGE_MASK;
 			int size = min_t(int, len, PAGE_SIZE - off);
@@ -546,7 +552,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
 			len -= size;
 			i++;
 		}
-		offset1 = 0;
+		offset = 0;
 		++from;
 	}
 	return 0;
@@ -646,7 +652,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	int err;
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int vnet_hdr_len = 0;
-	int copylen;
+	int copylen = 0;
 	bool zerocopy = false;
 
 	if (q->flags & IFF_VNET_HDR) {
@@ -675,15 +681,31 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	if (unlikely(len < ETH_HLEN))
 		goto err;
 
+	err = -EMSGSIZE;
+	if (unlikely(count > UIO_MAXIOV))
+		goto err;
+
 	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
 		zerocopy = true;
 
 	if (zerocopy) {
+		/* Userspace may produce vectors with count greater than
+		 * MAX_SKB_FRAGS, so we need to linearize parts of the skb
+		 * to let the rest of data to be fit in the frags.
+		 */
+		if (count > MAX_SKB_FRAGS) {
+			copylen = iov_length(iv, count - MAX_SKB_FRAGS);
+			if (copylen < vnet_hdr_len)
+				copylen = 0;
+			else
+				copylen -= vnet_hdr_len;
+		}
 		/* There are 256 bytes to be copied in skb, so there is enough
 		 * room for skb expand head in case it is used.
 		 * The rest buffer is mapped from userspace.
 		 */
-		copylen = vnet_hdr.hdr_len;
+		if (copylen < vnet_hdr.hdr_len)
+			copylen = vnet_hdr.hdr_len;
 		if (!copylen)
 			copylen = GOODCOPY_LEN;
 	} else
@@ -694,10 +716,9 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	if (!skb)
 		goto err;
 
-	if (zerocopy) {
+	if (zerocopy)
 		err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
-		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
-	} else
+	else
 		err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
 						   len);
 	if (err)
@@ -716,8 +737,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	rcu_read_lock_bh();
 	vlan = rcu_dereference_bh(q->vlan);
 	/* copy skb_ubuf_info for callback when skb has no error */
-	if (zerocopy)
+	if (zerocopy) {
 		skb_shinfo(skb)->destructor_arg = m->msg_control;
+		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+	}
 	if (vlan)
 		macvlan_start_xmit(skb, vlan->dev);
 	else
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 1f21d2a1e528..853db7a08a26 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -166,7 +166,7 @@ static void handle_tx(struct vhost_net *net)
 	if (wmem < sock->sk->sk_sndbuf / 2)
 		tx_poll_stop(net);
 	hdr_size = vq->vhost_hlen;
-	zcopy = vhost_sock_zcopy(sock);
+	zcopy = vq->ubufs;
 
 	for (;;) {
 		/* Release DMAs done buffers first */
@@ -257,7 +257,8 @@ static void handle_tx(struct vhost_net *net)
 					UIO_MAXIOV;
 			}
 			vhost_discard_vq_desc(vq, 1);
-			tx_poll_start(net, sock);
+			if (err == -EAGAIN || err == -ENOBUFS)
+				tx_poll_start(net, sock);
 			break;
 		}
 		if (err != len)
@@ -265,6 +266,8 @@ static void handle_tx(struct vhost_net *net)
 				 " len %d != %zd\n", err, len);
 		if (!zcopy)
 			vhost_add_used_and_signal(&net->dev, vq, head, 0);
+		else
+			vhost_zerocopy_signal_used(vq);
 		total_len += len;
 		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 51e4c1eeec4f..94dbd25caa30 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1603,6 +1603,7 @@ void vhost_zerocopy_callback(struct ubuf_info *ubuf)
 	struct vhost_ubuf_ref *ubufs = ubuf->ctx;
 	struct vhost_virtqueue *vq = ubufs->vq;
 
+	vhost_poll_queue(&vq->poll);
 	/* set len = 1 to mark this desc buffers done DMA */
 	vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
 	kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 7579f19e61e0..81847dd08bd0 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -203,6 +203,7 @@ void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
 void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
+bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
 
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 struct virtqueue *vring_new_virtqueue(unsigned int num,
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index 6bf95f995364..e626fa553c5a 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -144,7 +144,8 @@ static void wait_for_interrupt(struct vdev_info *dev)
 		}
 }
 
-static void run_test(struct vdev_info *dev, struct vq_info *vq, int bufs)
+static void run_test(struct vdev_info *dev, struct vq_info *vq,
+		     bool delayed, int bufs)
 {
 	struct scatterlist sl;
 	long started = 0, completed = 0;
@@ -183,8 +184,12 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, int bufs)
 		assert(started <= bufs);
 		if (completed == bufs)
 			break;
-		if (virtqueue_enable_cb(vq->vq)) {
-			wait_for_interrupt(dev);
+		if (delayed) {
+			if (virtqueue_enable_cb_delayed(vq->vq))
+				wait_for_interrupt(dev);
+		} else {
+			if (virtqueue_enable_cb(vq->vq))
+				wait_for_interrupt(dev);
 		}
 	}
 	test = 0;
@@ -216,6 +221,14 @@ const struct option longopts[] = {
 		.val = 'i',
 	},
 	{
+		.name = "delayed-interrupt",
+		.val = 'D',
+	},
+	{
+		.name = "no-delayed-interrupt",
+		.val = 'd',
+	},
+	{
 	}
 };
 
@@ -224,6 +237,7 @@ static void help()
 	fprintf(stderr, "Usage: virtio_test [--help]"
 		" [--no-indirect]"
 		" [--no-event-idx]"
+		" [--delayed-interrupt]"
 		"\n");
 }
 
@@ -233,6 +247,7 @@ int main(int argc, char **argv)
 	unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
 		(1ULL << VIRTIO_RING_F_EVENT_IDX);
 	int o;
+	bool delayed = false;
 
 	for (;;) {
 		o = getopt_long(argc, argv, optstring, longopts, NULL);
@@ -251,6 +266,9 @@ int main(int argc, char **argv)
 		case 'i':
 			features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC);
 			break;
+		case 'D':
+			delayed = true;
+			break;
 		default:
 			assert(0);
 			break;
@@ -260,6 +278,6 @@ int main(int argc, char **argv)
 done:
 	vdev_info_init(&dev, features);
 	vq_info_add(&dev, 256);
-	run_test(&dev, &dev.vqs[0], 0x100000);
+	run_test(&dev, &dev.vqs[0], delayed, 0x100000);
 	return 0;
 }