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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 44 insertions, 24 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9524ee16878a..9c3f8160ef24 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -89,7 +89,7 @@ struct vhost_net_ubuf_ref {
 
 #define VHOST_RX_BATCH 64
 struct vhost_net_buf {
-	struct sk_buff **queue;
+	void **queue;
 	int tail;
 	int head;
 };
@@ -108,7 +108,7 @@ struct vhost_net_virtqueue {
 	/* Reference counting for outstanding ubufs.
 	 * Protected by vq mutex. Writers must also take device mutex. */
 	struct vhost_net_ubuf_ref *ubufs;
-	struct skb_array *rx_array;
+	struct ptr_ring *rx_ring;
 	struct vhost_net_buf rxq;
 };
 
@@ -158,7 +158,7 @@ static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq)
 	struct vhost_net_buf *rxq = &nvq->rxq;
 
 	rxq->head = 0;
-	rxq->tail = skb_array_consume_batched(nvq->rx_array, rxq->queue,
+	rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
 					      VHOST_RX_BATCH);
 	return rxq->tail;
 }
@@ -167,13 +167,25 @@ static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq)
 {
 	struct vhost_net_buf *rxq = &nvq->rxq;
 
-	if (nvq->rx_array && !vhost_net_buf_is_empty(rxq)) {
-		skb_array_unconsume(nvq->rx_array, rxq->queue + rxq->head,
-				    vhost_net_buf_get_size(rxq));
+	if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) {
+		ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head,
+				   vhost_net_buf_get_size(rxq),
+				   __skb_array_destroy_skb);
 		rxq->head = rxq->tail = 0;
 	}
 }
 
+static int vhost_net_buf_peek_len(void *ptr)
+{
+	if (tun_is_xdp_buff(ptr)) {
+		struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+
+		return xdp->data_end - xdp->data;
+	}
+
+	return __skb_array_len_with_tag(ptr);
+}
+
 static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
 {
 	struct vhost_net_buf *rxq = &nvq->rxq;
@@ -185,7 +197,7 @@ static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
 		return 0;
 
 out:
-	return __skb_array_len_with_tag(vhost_net_buf_get_ptr(rxq));
+	return vhost_net_buf_peek_len(vhost_net_buf_get_ptr(rxq));
 }
 
 static void vhost_net_buf_init(struct vhost_net_buf *rxq)
@@ -583,7 +595,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
 	int len = 0;
 	unsigned long flags;
 
-	if (rvq->rx_array)
+	if (rvq->rx_ring)
 		return vhost_net_buf_peek(rvq);
 
 	spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
@@ -744,7 +756,7 @@ static void handle_rx(struct vhost_net *net)
 	};
 	size_t total_len = 0;
 	int err, mergeable;
-	s16 headcount;
+	s16 headcount, nheads = 0;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	struct socket *sock;
@@ -772,7 +784,7 @@ static void handle_rx(struct vhost_net *net)
 	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
-		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
+		headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
 					&in, vq_log, &log,
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
@@ -790,7 +802,7 @@ static void handle_rx(struct vhost_net *net)
 			 * they refilled. */
 			goto out;
 		}
-		if (nvq->rx_array)
+		if (nvq->rx_ring)
 			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
 		/* On overrun, truncate and discard */
 		if (unlikely(headcount > UIO_MAXIOV)) {
@@ -844,8 +856,12 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			goto out;
 		}
-		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
-					    headcount);
+		nheads += headcount;
+		if (nheads > VHOST_RX_BATCH) {
+			vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+						    nheads);
+			nheads = 0;
+		}
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
@@ -856,6 +872,9 @@ static void handle_rx(struct vhost_net *net)
 	}
 	vhost_net_enable_vq(net, vq);
 out:
+	if (nheads)
+		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+					    nheads);
 	mutex_unlock(&vq->mutex);
 }
 
@@ -896,7 +915,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	struct vhost_net *n;
 	struct vhost_dev *dev;
 	struct vhost_virtqueue **vqs;
-	struct sk_buff **queue;
+	void **queue;
 	int i;
 
 	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
@@ -908,7 +927,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		return -ENOMEM;
 	}
 
-	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(struct sk_buff *),
+	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(void *),
 			      GFP_KERNEL);
 	if (!queue) {
 		kfree(vqs);
@@ -1046,23 +1065,23 @@ err:
 	return ERR_PTR(r);
 }
 
-static struct skb_array *get_tap_skb_array(int fd)
+static struct ptr_ring *get_tap_ptr_ring(int fd)
 {
-	struct skb_array *array;
+	struct ptr_ring *ring;
 	struct file *file = fget(fd);
 
 	if (!file)
 		return NULL;
-	array = tun_get_skb_array(file);
-	if (!IS_ERR(array))
+	ring = tun_get_tx_ring(file);
+	if (!IS_ERR(ring))
 		goto out;
-	array = tap_get_skb_array(file);
-	if (!IS_ERR(array))
+	ring = tap_get_ptr_ring(file);
+	if (!IS_ERR(ring))
 		goto out;
-	array = NULL;
+	ring = NULL;
 out:
 	fput(file);
-	return array;
+	return ring;
 }
 
 static struct socket *get_tap_socket(int fd)
@@ -1143,7 +1162,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 		vq->private_data = sock;
 		vhost_net_buf_unproduce(nvq);
 		if (index == VHOST_NET_VQ_RX)
-			nvq->rx_array = get_tap_skb_array(fd);
+			nvq->rx_ring = get_tap_ptr_ring(fd);
 		r = vhost_vq_init_access(vq);
 		if (r)
 			goto err_used;
@@ -1208,6 +1227,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	}
 	vhost_net_stop(n, &tx_sock, &rx_sock);
 	vhost_net_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_reset_owner(&n->dev, umem);
 	vhost_net_vq_reset(n);
 done: