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

Pull networking fixes from David Miller:
 "This pull request is dedicated to the upcoming snowpocalypse parts 2
  and 3 in the Pacific Northwest:

   1) Drop profiles are broken because some drivers use dev_kfree_skb*
      instead of dev_consume_skb*, from Yang Wei.

   2) Fix IWLWIFI kconfig deps, from Luca Coelho.

   3) Fix percpu maps updating in bpftool, from Paolo Abeni.

   4) Missing station release in batman-adv, from Felix Fietkau.

   5) Fix some networking compat ioctl bugs, from Johannes Berg.

   6) ucc_geth must reset the BQL queue state when stopping the device,
      from Mathias Thore.

   7) Several XDP bug fixes in virtio_net from Toshiaki Makita.

   8) TSO packets must be sent always on queue 0 in stmmac, from Jose
      Abreu.

   9) Fix socket refcounting bug in RDS, from Eric Dumazet.

  10) Handle sparse cpu allocations in bpf selftests, from Martynas
      Pumputis.

  11) Make sure mgmt frames have enough tailroom in mac80211, from Felix
      Feitkau.

  12) Use safe list walking in sctp_sendmsg() asoc list traversal, from
      Greg Kroah-Hartman.

  13) Make DCCP's ccid_hc_[rt]x_parse_options always check for NULL
      ccid, from Eric Dumazet.

  14) Need to reload WoL password into bcmsysport device after deep
      sleeps, from Florian Fainelli.

  15) Remove filter from mask before freeing in cls_flower, from Petr
      Machata.

  16) Missing release and use after free in error paths of s390 qeth
      code, from Julian Wiedmann.

  17) Fix lockdep false positive in dsa code, from Marc Zyngier.

  18) Fix counting of ATU violations in mv88e6xxx, from Andrew Lunn.

  19) Fix EQ firmware assert in qed driver, from Manish Chopra.

  20) Don't default Caivum PTP to Y in kconfig, from Bjorn Helgaas"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  net: dsa: b53: Fix for failure when irq is not defined in dt
  sit: check if IPv6 enabled before calling ip6_err_gen_icmpv6_unreach()
  geneve: should not call rt6_lookup() when ipv6 was disabled
  net: Don't default Cavium PTP driver to 'y'
  net: broadcom: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: via-velocity: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: tehuti: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: sun: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: fsl_ucc_hdlc: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: fec_mpc52xx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: smsc: epic100: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: dscc4: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: tulip: de2104x: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net: defxx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles
  net/mlx5e: Don't overwrite pedit action when multiple pedit used
  net/mlx5e: Update hw flows when encap source mac changed
  qed*: Advance drivers version to 8.37.0.20
  qed: Change verbosity for coalescing message.
  qede: Fix system crash on configuring channels.
  qed: Consider TX tcs while deriving the max num_queues for PF.
  ...

1 files changed, 124 insertions, 47 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8fadd8eaf601..4cfceb789eea 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644);
 #define VIRTIO_XDP_TX		BIT(0)
 #define VIRTIO_XDP_REDIR	BIT(1)
 
+#define VIRTIO_XDP_FLAG	BIT(0)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -252,6 +254,21 @@ struct padded_vnet_hdr {
 	char padding[4];
 };
 
+static bool is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
+}
+
+static void *xdp_to_ptr(struct xdp_frame *ptr)
+{
+	return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
+}
+
+static struct xdp_frame *ptr_to_xdp(void *ptr)
+{
+	return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
+}
+
 /* Converting between virtqueue no. and kernel tx/rx queue no.
  * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
  */
@@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 
 	sg_init_one(sq->sg, xdpf->data, xdpf->len);
 
-	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC);
+	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
+				   GFP_ATOMIC);
 	if (unlikely(err))
 		return -ENOSPC; /* Caller handle free/refcnt */
 
@@ -482,36 +500,47 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct receive_queue *rq = vi->rq;
-	struct xdp_frame *xdpf_sent;
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
+	int packets = 0;
+	int bytes = 0;
 	int drops = 0;
 	int kicks = 0;
 	int ret, err;
+	void *ptr;
 	int i;
 
-	sq = virtnet_xdp_sq(vi);
-
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
-		ret = -EINVAL;
-		drops = n;
-		goto out;
-	}
-
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
 	 */
 	xdp_prog = rcu_dereference(rq->xdp_prog);
-	if (!xdp_prog) {
-		ret = -ENXIO;
+	if (!xdp_prog)
+		return -ENXIO;
+
+	sq = virtnet_xdp_sq(vi);
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
+		ret = -EINVAL;
 		drops = n;
 		goto out;
 	}
 
 	/* Free up any pending old buffers before queueing new ones. */
-	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
-		xdp_return_frame(xdpf_sent);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(is_xdp_frame(ptr))) {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		} else {
+			struct sk_buff *skb = ptr;
+
+			bytes += skb->len;
+			napi_consume_skb(skb, false);
+		}
+		packets++;
+	}
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
@@ -530,6 +559,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 out:
 	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
 	sq->stats.xdp_tx += n;
 	sq->stats.xdp_tx_drops += drops;
 	sq->stats.kicks += kicks;
@@ -1332,18 +1363,26 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 
 static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
-	struct sk_buff *skb;
 	unsigned int len;
 	unsigned int packets = 0;
 	unsigned int bytes = 0;
+	void *ptr;
 
-	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		pr_debug("Sent skb %p\n", skb);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(!is_xdp_frame(ptr))) {
+			struct sk_buff *skb = ptr;
 
-		bytes += skb->len;
-		packets++;
+			pr_debug("Sent skb %p\n", skb);
+
+			bytes += skb->len;
+			napi_consume_skb(skb, in_napi);
+		} else {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
 
-		napi_consume_skb(skb, in_napi);
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		}
+		packets++;
 	}
 
 	/* Avoid overhead when no packets have been processed
@@ -1358,6 +1397,16 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 	u64_stats_update_end(&sq->stats.syncp);
 }
 
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
 static void virtnet_poll_cleantx(struct receive_queue *rq)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1365,7 +1414,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 	struct send_queue *sq = &vi->sq[index];
 	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
 
-	if (!sq->napi.weight)
+	if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index))
 		return;
 
 	if (__netif_tx_trylock(txq)) {
@@ -1442,8 +1491,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct send_queue *sq = container_of(napi, struct send_queue, napi);
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq));
+	unsigned int index = vq2txq(sq->vq);
+	struct netdev_queue *txq;
 
+	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
+		/* We don't need to enable cb for XDP */
+		napi_complete_done(napi, 0);
+		return 0;
+	}
+
+	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
 	free_old_xmit_skbs(sq, true);
 	__netif_tx_unlock(txq);
@@ -2395,6 +2452,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		return -ENOMEM;
 	}
 
+	old_prog = rtnl_dereference(vi->rq[0].xdp_prog);
+	if (!prog && !old_prog)
+		return 0;
+
 	if (prog) {
 		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
 		if (IS_ERR(prog))
@@ -2402,36 +2463,62 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	}
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
-	if (netif_running(dev))
-		for (i = 0; i < vi->max_queue_pairs; i++)
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			napi_disable(&vi->rq[i].napi);
+			virtnet_napi_tx_disable(&vi->sq[i].napi);
+		}
+	}
+
+	if (!prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0)
+				virtnet_restore_guest_offloads(vi);
+		}
+		synchronize_net();
+	}
 
-	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
 	if (err)
 		goto err;
+	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	vi->xdp_queue_pairs = xdp_qp;
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
-		rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
-		if (i == 0) {
-			if (!old_prog)
+	if (prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
-			if (!prog)
-				virtnet_restore_guest_offloads(vi);
 		}
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev))
+		if (netif_running(dev)) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 
 	return 0;
 
 err:
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+	if (!prog) {
+		virtnet_clear_guest_offloads(vi);
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
+	}
+
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
+	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
 	return err;
@@ -2613,16 +2700,6 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
-	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
-		return false;
-	else if (q < vi->curr_queue_pairs)
-		return true;
-	else
-		return false;
-}
-
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -2631,10 +2708,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_raw_buffer_queue(vi, i))
+			if (!is_xdp_frame(buf))
 				dev_kfree_skb(buf);
 			else
-				put_page(virt_to_head_page(buf));
+				xdp_return_frame(ptr_to_xdp(buf));
 		}
 	}