Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

1 files changed, 50 insertions, 18 deletions

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 6a50e1d0529c..9f57736fe15e 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -102,7 +102,7 @@ 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);
@@ -147,8 +147,24 @@ 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)) {
@@ -157,33 +173,47 @@ 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;
 
-		if (pkt->reply) {
-			int val;
-
-			val = atomic_dec_return(&vsock->queued_replies);
-
-			/* Do we have resources to resume tx processing? */
-			if (val + 1 == tx_vq->num)
-				restart_tx = true;
-		}
-
 		/* Deliver to monitoring devices all correctly transmitted
 		 * packets.
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
-		total_len += pkt->len;
-		virtio_transport_free_pkt(pkt);
+		pkt->off += payload_len;
+		total_len += 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);
+		} else {
+			if (pkt->reply) {
+				int val;
+
+				val = atomic_dec_return(&vsock->queued_replies);
+
+				/* Do we have resources to resume tx
+				 * processing?
+				 */
+				if (val + 1 == tx_vq->num)
+					restart_tx = true;
+			}
+
+			virtio_transport_free_pkt(pkt);
+		}
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
@@ -329,6 +359,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
+	pkt->buf_len = pkt->len;
+
 	nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter);
 	if (nbytes != pkt->len) {
 		vq_err(vq, "Expected %u byte payload, got %zu bytes\n",