Merge tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter, wifi and ipsec.

  A little more changes than usual, but it's pretty normal for us that
  the rc3/rc4 PRs are oversized as people start testing in earnest.

  Possibly an extra boost from people deploying the 6.1 LTS but that's
  more of an unscientific hunch.

  Current release - regressions:

   - phy: mscc: fix deadlock in phy_ethtool_{get,set}_wol()

   - virtio: vsock: don't use skbuff state to account credit

   - virtio: vsock: don't drop skbuff on copy failure

   - virtio_net: fix page_to_skb() miscalculating the memory size

  Current release - new code bugs:

   - eth: correct xdp_features after device reconfig

   - wifi: nl80211: fix the puncturing bitmap policy

   - net/mlx5e: flower:
      - fix raw counter initialization
      - fix missing error code
      - fix cloned flow attribute

   - ipa:
      - fix some register validity checks
      - fix a surprising number of bad offsets
      - kill FILT_ROUT_CACHE_CFG IPA register

  Previous releases - regressions:

   - tcp: fix bind() conflict check for dual-stack wildcard address

   - veth: fix use after free in XDP_REDIRECT when skb headroom is small

   - ipv4: fix incorrect table ID in IOCTL path

   - ipvlan: make skb->skb_iif track skb->dev for l3s mode

   - mptcp:
      - fix possible deadlock in subflow_error_report
      - fix UaFs when destroying unaccepted and listening sockets

   - dsa: mv88e6xxx: fix max_mtu of 1492 on 6165, 6191, 6220, 6250, 6290

  Previous releases - always broken:

   - tcp: tcp_make_synack() can be called from process context, don't
     assume preemption is disabled when updating stats

   - netfilter: correct length for loading protocol registers

   - virtio_net: add checking sq is full inside xdp xmit

   - bonding: restore IFF_MASTER/SLAVE flags on bond enslave Ethertype
     change

   - phy: nxp-c45-tja11xx: fix MII_BASIC_CONFIG_REV bit number

   - eth: i40e: fix crash during reboot when adapter is in recovery mode

   - eth: ice: avoid deadlock on rtnl lock when auxiliary device
     plug/unplug meets bonding

   - dsa: mt7530:
      - remove now incorrect comment regarding port 5
      - set PLL frequency and trgmii only when trgmii is used

   - eth: mtk_eth_soc: reset PCS state when changing interface types

  Misc:

   - ynl: another license adjustment

   - move the TCA_EXT_WARN_MSG attribute for tc action"

* tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (108 commits)
  selftests: bonding: add tests for ether type changes
  bonding: restore bond's IFF_SLAVE flag if a non-eth dev enslave fails
  bonding: restore IFF_MASTER/SLAVE flags on bond enslave ether type change
  net: renesas: rswitch: Fix GWTSDIE register handling
  net: renesas: rswitch: Fix the output value of quote from rswitch_rx()
  ethernet: sun: add check for the mdesc_grab()
  net: ipa: fix some register validity checks
  net: ipa: kill FILT_ROUT_CACHE_CFG IPA register
  net: ipa: add two missing declarations
  net: ipa: reg: include <linux/bug.h>
  net: xdp: don't call notifiers during driver init
  net/sched: act_api: add specific EXT_WARN_MSG for tc action
  Revert "net/sched: act_api: move TCA_EXT_WARN_MSG to the correct hierarchy"
  net: dsa: microchip: fix RGMII delay configuration on KSZ8765/KSZ8794/KSZ8795
  ynl: make the tooling check the license
  ynl: broaden the license even more
  tools: ynl: make definitions optional again
  hsr: ratelimit only when errors are printed
  qed/qed_mng_tlv: correctly zero out ->min instead of ->hour
  selftests: net: devlink_port_split.py: skip test if no suitable device available
  ...

1 files changed, 95 insertions, 76 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index fb5e68ed3ec2..2396c28c0122 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -446,7 +446,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
-				   unsigned int len, unsigned int truesize)
+				   unsigned int len, unsigned int truesize,
+				   unsigned int headroom)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -464,11 +465,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	buf = p;
+	buf = p - headroom;
 	len -= hdr_len;
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
-	tailroom = truesize - hdr_padded_len - len;
+	tailroom = truesize - headroom  - hdr_padded_len - len;
 
 	shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
@@ -545,6 +546,87 @@ ok:
 	return skb;
 }
 
+static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
+{
+	unsigned int len;
+	unsigned int packets = 0;
+	unsigned int bytes = 0;
+	void *ptr;
+
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(!is_xdp_frame(ptr))) {
+			struct sk_buff *skb = ptr;
+
+			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);
+
+			bytes += xdp_get_frame_len(frame);
+			xdp_return_frame(frame);
+		}
+		packets++;
+	}
+
+	/* Avoid overhead when no packets have been processed
+	 * happens when called speculatively from start_xmit.
+	 */
+	if (!packets)
+		return;
+
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
+	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 check_sq_full_and_disable(struct virtnet_info *vi,
+				      struct net_device *dev,
+				      struct send_queue *sq)
+{
+	bool use_napi = sq->napi.weight;
+	int qnum;
+
+	qnum = sq - vi->sq;
+
+	/* If running out of space, stop queue to avoid getting packets that we
+	 * are then unable to transmit.
+	 * An alternative would be to force queuing layer to requeue the skb by
+	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
+	 * returned in a normal path of operation: it means that driver is not
+	 * maintaining the TX queue stop/start state properly, and causes
+	 * the stack to do a non-trivial amount of useless work.
+	 * Since most packets only take 1 or 2 ring slots, stopping the queue
+	 * early means 16 slots are typically wasted.
+	 */
+	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+		netif_stop_subqueue(dev, qnum);
+		if (use_napi) {
+			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+				virtqueue_napi_schedule(&sq->napi, sq->vq);
+		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+			/* More just got used, free them then recheck. */
+			free_old_xmit_skbs(sq, false);
+			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+				netif_start_subqueue(dev, qnum);
+				virtqueue_disable_cb(sq->vq);
+			}
+		}
+	}
+}
+
 static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 				   struct send_queue *sq,
 				   struct xdp_frame *xdpf)
@@ -686,6 +768,9 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 	ret = nxmit;
 
+	if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq))
+		check_sq_full_and_disable(vi, dev, sq);
+
 	if (flags & XDP_XMIT_FLUSH) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
 			kicks = 1;
@@ -925,7 +1010,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
 {
 	struct page *page = buf;
 	struct sk_buff *skb =
-		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -1188,9 +1273,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 		switch (act) {
 		case XDP_PASS:
+			head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
+			if (unlikely(!head_skb))
+				goto err_xdp_frags;
+
 			if (unlikely(xdp_page != page))
 				put_page(page);
-			head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
 			rcu_read_unlock();
 			return head_skb;
 		case XDP_TX:
@@ -1248,7 +1336,7 @@ err_xdp_frags:
 	rcu_read_unlock();
 
 skip_xdp:
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1714,52 +1802,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	return stats.packets;
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
-{
-	unsigned int len;
-	unsigned int packets = 0;
-	unsigned int bytes = 0;
-	void *ptr;
-
-	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(!is_xdp_frame(ptr))) {
-			struct sk_buff *skb = ptr;
-
-			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);
-
-			bytes += xdp_get_frame_len(frame);
-			xdp_return_frame(frame);
-		}
-		packets++;
-	}
-
-	/* Avoid overhead when no packets have been processed
-	 * happens when called speculatively from start_xmit.
-	 */
-	if (!packets)
-		return;
-
-	u64_stats_update_begin(&sq->stats.syncp);
-	sq->stats.bytes += bytes;
-	sq->stats.packets += packets;
-	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;
@@ -1989,30 +2031,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		nf_reset_ct(skb);
 	}
 
-	/* If running out of space, stop queue to avoid getting packets that we
-	 * are then unable to transmit.
-	 * An alternative would be to force queuing layer to requeue the skb by
-	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
-	 * returned in a normal path of operation: it means that driver is not
-	 * maintaining the TX queue stop/start state properly, and causes
-	 * the stack to do a non-trivial amount of useless work.
-	 * Since most packets only take 1 or 2 ring slots, stopping the queue
-	 * early means 16 slots are typically wasted.
-	 */
-	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
-		netif_stop_subqueue(dev, qnum);
-		if (use_napi) {
-			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
-				virtqueue_napi_schedule(&sq->napi, sq->vq);
-		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
-			/* More just got used, free them then recheck. */
-			free_old_xmit_skbs(sq, false);
-			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
-				netif_start_subqueue(dev, qnum);
-				virtqueue_disable_cb(sq->vq);
-			}
-		}
-	}
+	check_sq_full_and_disable(vi, dev, sq);
 
 	if (kick || netif_xmit_stopped(txq)) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {