linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stefano Garzarella <sgarzare@redhat.com>
To: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	virtualization@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Jason Wang <jasowang@redhat.com>
Subject: [PATCH v2 5/8] vhost/vsock: split packets to send using multiple buffers
Date: Fri, 10 May 2019 14:58:40 +0200	[thread overview]
Message-ID: <20190510125843.95587-6-sgarzare@redhat.com> (raw)
In-Reply-To: <20190510125843.95587-1-sgarzare@redhat.com>

If the packets to sent to the guest are bigger than the buffer
available, we can split them, using multiple buffers and fixing
the length in the packet header.
This is safe since virtio-vsock supports only stream sockets.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/vhost/vsock.c                   | 51 +++++++++++++++++++------
 net/vmw_vsock/virtio_transport_common.c | 15 ++++++--
 2 files changed, 52 insertions(+), 14 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 7964e2daee09..fb731d09f5f1 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -94,7 +94,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		struct iov_iter iov_iter;
 		unsigned out, in;
 		size_t nbytes;
-		size_t len;
+		size_t iov_len, payload_len;
 		int head;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
@@ -139,8 +139,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		len = iov_length(&vq->iov[out], in);
-		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len);
+		iov_len = iov_length(&vq->iov[out], in);
+		if (iov_len < sizeof(pkt->hdr)) {
+			virtio_transport_free_pkt(pkt);
+			vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
+			break;
+		}
+
+		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len);
+		payload_len = pkt->len - pkt->off;
+
+		/* If the packet is greater than the space available in the
+		 * buffer, we split it using multiple buffers.
+		 */
+		if (payload_len > iov_len - sizeof(pkt->hdr))
+			payload_len = iov_len - sizeof(pkt->hdr);
+
+		/* Set the correct length in the header */
+		pkt->hdr.len = cpu_to_le32(payload_len);
 
 		nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
 		if (nbytes != sizeof(pkt->hdr)) {
@@ -149,16 +165,34 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter);
-		if (nbytes != pkt->len) {
+		nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len,
+				      &iov_iter);
+		if (nbytes != payload_len) {
 			virtio_transport_free_pkt(pkt);
 			vq_err(vq, "Faulted on copying pkt buf\n");
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
+		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
 		added = true;
 
+		/* Deliver to monitoring devices all correctly transmitted
+		 * packets.
+		 */
+		virtio_transport_deliver_tap_pkt(pkt);
+
+		pkt->off += payload_len;
+
+		/* If we didn't send all the payload we can requeue the packet
+		 * to send it with the next available buffer.
+		 */
+		if (pkt->off < pkt->len) {
+			spin_lock_bh(&vsock->send_pkt_list_lock);
+			list_add(&pkt->list, &vsock->send_pkt_list);
+			spin_unlock_bh(&vsock->send_pkt_list_lock);
+			continue;
+		}
+
 		if (pkt->reply) {
 			int val;
 
@@ -169,11 +203,6 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 				restart_tx = true;
 		}
 
-		/* Deliver to monitoring devices all correctly transmitted
-		 * packets.
-		 */
-		virtio_transport_deliver_tap_pkt(pkt);
-
 		virtio_transport_free_pkt(pkt);
 	}
 	if (added)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index b61fd5e29a1f..3f313bcd6a26 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -135,8 +135,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 	struct virtio_vsock_pkt *pkt = opaque;
 	struct af_vsockmon_hdr *hdr;
 	struct sk_buff *skb;
+	size_t payload_len;
+	void *payload_buf;
 
-	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len,
+	/* A packet could be split to fit the RX buffer, so we can retrieve
+	 * the payload length from the header and the buffer pointer taking
+	 * care of the offset in the original packet.
+	 */
+	payload_len = le32_to_cpu(pkt->hdr.len);
+	payload_buf = pkt->buf + pkt->off;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len,
 			GFP_ATOMIC);
 	if (!skb)
 		return NULL;
@@ -176,8 +185,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 
 	skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr));
 
-	if (pkt->len) {
-		skb_put_data(skb, pkt->buf, pkt->len);
+	if (payload_len) {
+		skb_put_data(skb, payload_buf, payload_len);
 	}
 
 	return skb;
-- 
2.20.1


  parent reply	other threads:[~2019-05-10 12:59 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-10 12:58 [PATCH v2 0/8] vsock/virtio: optimizations to increase the throughput Stefano Garzarella
2019-05-10 12:58 ` [PATCH v2 1/8] vsock/virtio: limit the memory used per-socket Stefano Garzarella
2019-05-12 16:57   ` Michael S. Tsirkin
2019-05-13 16:40     ` Stefano Garzarella
2019-05-13  9:58   ` Jason Wang
2019-05-13 17:23     ` Stefano Garzarella
2019-05-14  3:25       ` Jason Wang
2019-05-14  3:40         ` Jason Wang
2019-05-14 16:35         ` Stefano Garzarella
2019-05-15  2:48           ` Jason Wang
2019-05-28 16:45             ` Stefano Garzarella
2019-05-29  0:59               ` Jason Wang
2019-05-16 15:25   ` Stefan Hajnoczi
2019-05-17  8:25     ` Stefano Garzarella
2019-05-20  8:57       ` Stefan Hajnoczi
2019-05-10 12:58 ` [PATCH v2 2/8] vsock/virtio: free packets during the socket release Stefano Garzarella
2019-05-10 22:20   ` David Miller
2019-05-11  8:27     ` Stefano Garzarella
2019-05-16 15:32   ` Stefan Hajnoczi
2019-05-17  8:26     ` Stefano Garzarella
2019-05-10 12:58 ` [PATCH v2 3/8] vsock/virtio: fix locking for fwd_cnt and buf_alloc Stefano Garzarella
2019-05-10 12:58 ` [PATCH v2 4/8] vsock/virtio: reduce credit update messages Stefano Garzarella
2019-05-10 12:58 ` Stefano Garzarella [this message]
2019-05-10 12:58 ` [PATCH v2 6/8] vsock/virtio: change the maximum packet size allowed Stefano Garzarella
2019-05-10 12:58 ` [PATCH v2 7/8] vsock/virtio: increase RX buffer size to 64 KiB Stefano Garzarella
2019-05-13 10:01   ` Jason Wang
2019-05-13 17:51     ` Stefano Garzarella
2019-05-14  3:38       ` Jason Wang
2019-05-14 16:20         ` Stefano Garzarella
2019-05-15  2:50           ` Jason Wang
2019-05-15  8:22             ` Stefano Garzarella
2019-05-10 12:58 ` [PATCH v2 8/8] vsock/virtio: make the RX buffer size tunable Stefano Garzarella
2019-05-13 10:05   ` Jason Wang
2019-05-13 12:46     ` Jason Wang
2019-05-14 16:10       ` Stefano Garzarella
2019-05-13  9:33 ` [PATCH v2 0/8] vsock/virtio: optimizations to increase the throughput Jason Wang
2019-05-13 16:49   ` Stefano Garzarella
2019-05-20 14:09   ` Stefano Garzarella

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190510125843.95587-6-sgarzare@redhat.com \
    --to=sgarzare@redhat.com \
    --cc=davem@davemloft.net \
    --cc=jasowang@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).