Merge branch 'vhost_net-rx-batch-dequeuing'

Jason Wang says:

====================
vhost_net rx batch dequeuing

This series tries to implement rx batching for vhost-net. This is done
by batching the dequeuing from skb_array which was exported by
underlayer socket and pass the sbk back through msg_control to finish
userspace copying. This is also the requirement for more batching
implemention on rx path.

Tests shows at most 7.56% improvment bon rx pps on top of batch
zeroing and no obvious changes for TCP_STREAM/TCP_RR result.

Please review.

Thanks

Changes from V4:
- drop batch zeroing patch
- renew the performance numbers
- move skb pointer array out of vhost_net structure

Changes from V3:
- add batch zeroing patch to fix the build warnings

Changes from V2:
- rebase to net-next HEAD
- use unconsume helpers to put skb back on releasing
- introduce and use vhost_net internal buffer helpers
- renew performance numbers on top of batch zeroing

Changes from V1:
- switch to use for() in __ptr_ring_consume_batched()
- rename peek_head_len_batched() to fetch_skbs()
- use skb_array_consume_batched() instead of
  skb_array_consume_batched_bh() since no consumer run in bh
- drop the lockless peeking patch since skb_array could be resized, so
  it's not safe to call lockless one
====================

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 21 insertions, 4 deletions

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 4d4173d25dd0..9af3239d6ad5 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -824,15 +824,17 @@ done:
 
 static ssize_t tap_do_read(struct tap_queue *q,
 			   struct iov_iter *to,
-			   int noblock)
+			   int noblock, struct sk_buff *skb)
 {
 	DEFINE_WAIT(wait);
-	struct sk_buff *skb;
 	ssize_t ret = 0;
 
 	if (!iov_iter_count(to))
 		return 0;
 
+	if (skb)
+		goto put;
+
 	while (1) {
 		if (!noblock)
 			prepare_to_wait(sk_sleep(&q->sk), &wait,
@@ -856,6 +858,7 @@ static ssize_t tap_do_read(struct tap_queue *q,
 	if (!noblock)
 		finish_wait(sk_sleep(&q->sk), &wait);
 
+put:
 	if (skb) {
 		ret = tap_put_user(q, skb, to);
 		if (unlikely(ret < 0))
@@ -872,7 +875,7 @@ static ssize_t tap_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct tap_queue *q = file->private_data;
 	ssize_t len = iov_iter_count(to), ret;
 
-	ret = tap_do_read(q, to, file->f_flags & O_NONBLOCK);
+	ret = tap_do_read(q, to, file->f_flags & O_NONBLOCK, NULL);
 	ret = min_t(ssize_t, ret, len);
 	if (ret > 0)
 		iocb->ki_pos = ret;
@@ -1155,7 +1158,8 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m,
 	int ret;
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
 		return -EINVAL;
-	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT);
+	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT,
+			  m->msg_control);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
@@ -1193,6 +1197,19 @@ struct socket *tap_get_socket(struct file *file)
 }
 EXPORT_SYMBOL_GPL(tap_get_socket);
 
+struct skb_array *tap_get_skb_array(struct file *file)
+{
+	struct tap_queue *q;
+
+	if (file->f_op != &tap_fops)
+		return ERR_PTR(-EINVAL);
+	q = file->private_data;
+	if (!q)
+		return ERR_PTR(-EBADFD);
+	return &q->skb_array;
+}
+EXPORT_SYMBOL_GPL(tap_get_skb_array);
+
 int tap_queue_resize(struct tap_dev *tap)
 {
 	struct net_device *dev = tap->dev;