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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 53 insertions, 18 deletions

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ed3114556fda..96c1d8400822 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -315,6 +315,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_addr = -1ull;
 	vq->private_data = NULL;
 	vq->acked_features = 0;
+	vq->acked_backend_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->kick = NULL;
@@ -1027,28 +1028,40 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 			     struct iov_iter *from)
 {
-	struct vhost_msg_node node;
-	unsigned size = sizeof(struct vhost_msg);
-	size_t ret;
-	int err;
+	struct vhost_iotlb_msg msg;
+	size_t offset;
+	int type, ret;
 
-	if (iov_iter_count(from) < size)
-		return 0;
-	ret = copy_from_iter(&node.msg, size, from);
-	if (ret != size)
+	ret = copy_from_iter(&type, sizeof(type), from);
+	if (ret != sizeof(type))
 		goto done;
 
-	switch (node.msg.type) {
+	switch (type) {
 	case VHOST_IOTLB_MSG:
-		err = vhost_process_iotlb_msg(dev, &node.msg.iotlb);
-		if (err)
-			ret = err;
+		/* There maybe a hole after type for V1 message type,
+		 * so skip it here.
+		 */
+		offset = offsetof(struct vhost_msg, iotlb) - sizeof(int);
+		break;
+	case VHOST_IOTLB_MSG_V2:
+		offset = sizeof(__u32);
 		break;
 	default:
 		ret = -EINVAL;
-		break;
+		goto done;
+	}
+
+	iov_iter_advance(from, offset);
+	ret = copy_from_iter(&msg, sizeof(msg), from);
+	if (ret != sizeof(msg))
+		goto done;
+	if (vhost_process_iotlb_msg(dev, &msg)) {
+		ret = -EFAULT;
+		goto done;
 	}
 
+	ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) :
+	      sizeof(struct vhost_msg_v2);
 done:
 	return ret;
 }
@@ -1107,13 +1120,28 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
 		finish_wait(&dev->wait, &wait);
 
 	if (node) {
-		ret = copy_to_iter(&node->msg, size, to);
+		struct vhost_iotlb_msg *msg;
+		void *start = &node->msg;
+
+		switch (node->msg.type) {
+		case VHOST_IOTLB_MSG:
+			size = sizeof(node->msg);
+			msg = &node->msg.iotlb;
+			break;
+		case VHOST_IOTLB_MSG_V2:
+			size = sizeof(node->msg_v2);
+			msg = &node->msg_v2.iotlb;
+			break;
+		default:
+			BUG();
+			break;
+		}
 
-		if (ret != size || node->msg.type != VHOST_IOTLB_MISS) {
+		ret = copy_to_iter(start, size, to);
+		if (ret != size || msg->type != VHOST_IOTLB_MISS) {
 			kfree(node);
 			return ret;
 		}
-
 		vhost_enqueue_msg(dev, &dev->pending_list, node);
 	}
 
@@ -1126,12 +1154,19 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
 	struct vhost_dev *dev = vq->dev;
 	struct vhost_msg_node *node;
 	struct vhost_iotlb_msg *msg;
+	bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2);
 
-	node = vhost_new_msg(vq, VHOST_IOTLB_MISS);
+	node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG);
 	if (!node)
 		return -ENOMEM;
 
-	msg = &node->msg.iotlb;
+	if (v2) {
+		node->msg_v2.type = VHOST_IOTLB_MSG_V2;
+		msg = &node->msg_v2.iotlb;
+	} else {
+		msg = &node->msg.iotlb;
+	}
+
 	msg->type = VHOST_IOTLB_MISS;
 	msg->iova = iova;
 	msg->perm = access;