Merge tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Quite smaller than usual. Notably it includes the fix for the unix
  regression from the past weeks. The TCP window fix will require some
  follow-up, already queued.

  Current release - regressions:

   - af_unix: fix garbage collection of embryos

  Previous releases - regressions:

   - af_unix: fix race between GC and receive path

   - ipv6: sr: fix missing sk_buff release in seg6_input_core

   - tcp: remove 64 KByte limit for initial tp->rcv_wnd value

   - eth: r8169: fix rx hangup

   - eth: lan966x: remove ptp traps in case the ptp is not enabled

   - eth: ixgbe: fix link breakage vs cisco switches

   - eth: ice: prevent ethtool from corrupting the channels

  Previous releases - always broken:

   - openvswitch: set the skbuff pkt_type for proper pmtud support

   - tcp: Fix shift-out-of-bounds in dctcp_update_alpha()

  Misc:

   - a bunch of selftests stabilization patches"

* tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (25 commits)
  r8169: Fix possible ring buffer corruption on fragmented Tx packets.
  idpf: Interpret .set_channels() input differently
  ice: Interpret .set_channels() input differently
  nfc: nci: Fix handling of zero-length payload packets in nci_rx_work()
  net: relax socket state check at accept time.
  tcp: remove 64 KByte limit for initial tp->rcv_wnd value
  net: ti: icssg_prueth: Fix NULL pointer dereference in prueth_probe()
  tls: fix missing memory barrier in tls_init
  net: fec: avoid lock evasion when reading pps_enable
  Revert "ixgbe: Manual AN-37 for troublesome link partners for X550 SFI"
  testing: net-drv: use stats64 for testing
  net: mana: Fix the extra HZ in mana_hwc_send_request
  net: lan966x: Remove ptp traps in case the ptp is not enabled.
  openvswitch: Set the skbuff pkt_type for proper pmtud support.
  selftest: af_unix: Make SCM_RIGHTS into OOB data.
  af_unix: Fix garbage collection of embryos carrying OOB with SCM_RIGHTS
  tcp: Fix shift-out-of-bounds in dctcp_update_alpha().
  selftests/net: use tc rule to filter the na packet
  ipv6: sr: fix memleak in seg6_hmac_init_algo
  af_unix: Update unix_sk(sk)->oob_skb under sk_receive_queue lock.
  ...

2 files changed, 36 insertions, 15 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d5f10783c251..e4af6616e1df 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2170,13 +2170,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	maybe_add_creds(skb, sock, other);
 	skb_get(skb);
 
+	scm_stat_add(other, skb);
+
+	spin_lock(&other->sk_receive_queue.lock);
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
-
 	WRITE_ONCE(ousk->oob_skb, skb);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	spin_unlock(&other->sk_receive_queue.lock);
 
-	scm_stat_add(other, skb);
-	skb_queue_tail(&other->sk_receive_queue, skb);
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
@@ -2567,8 +2569,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
+	spin_lock(&sk->sk_receive_queue.lock);
 
 	if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) {
+		spin_unlock(&sk->sk_receive_queue.lock);
 		unix_state_unlock(sk);
 		mutex_unlock(&u->iolock);
 		return -EINVAL;
@@ -2580,6 +2584,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 		WRITE_ONCE(u->oob_skb, NULL);
 	else
 		skb_get(oob_skb);
+
+	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
@@ -2608,6 +2614,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		consume_skb(skb);
 		skb = NULL;
 	} else {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
@@ -2619,13 +2629,19 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			} else if (flags & MSG_PEEK) {
 				skb = NULL;
 			} else {
-				skb_unlink(skb, &sk->sk_receive_queue);
+				__skb_unlink(skb, &sk->sk_receive_queue);
 				WRITE_ONCE(u->oob_skb, NULL);
-				if (!WARN_ON_ONCE(skb_unref(skb)))
-					kfree_skb(skb);
+				unlinked_skb = skb;
 				skb = skb_peek(&sk->sk_receive_queue);
 			}
 		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		if (unlinked_skb) {
+			WARN_ON_ONCE(skb_unref(unlinked_skb));
+			kfree_skb(unlinked_skb);
+		}
 	}
 	return skb;
 }
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 1f8b8cdfcdc8..dfe94a90ece4 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -342,6 +342,18 @@ enum unix_recv_queue_lock_class {
 	U_RECVQ_LOCK_EMBRYO,
 };
 
+static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist)
+{
+	skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (u->oob_skb) {
+		WARN_ON_ONCE(skb_unref(u->oob_skb));
+		u->oob_skb = NULL;
+	}
+#endif
+}
+
 static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist)
 {
 	struct unix_vertex *vertex;
@@ -365,18 +377,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist
 
 				/* listener -> embryo order, the inversion never happens. */
 				spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO);
-				skb_queue_splice_init(embryo_queue, hitlist);
+				unix_collect_queue(unix_sk(skb->sk), hitlist);
 				spin_unlock(&embryo_queue->lock);
 			}
 		} else {
-			skb_queue_splice_init(queue, hitlist);
-
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-			if (u->oob_skb) {
-				kfree_skb(u->oob_skb);
-				u->oob_skb = NULL;
-			}
-#endif
+			unix_collect_queue(u, hitlist);
 		}
 
 		spin_unlock(&queue->lock);