Merge tag 'net-next-6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "This is slightly smaller than usual, with the most interesting work
  being still around RTNL scope reduction.

  Core:

   - More core refactoring to reduce the RTNL lock contention, including
     preparatory work for the per-network namespace RTNL lock, replacing
     RTNL lock with a per device-one to protect NAPI-related net device
     data and moving synchronize_net() calls outside such lock.

   - Extend drop reasons usage, adding net scheduler, AF_UNIX, bridge
     and more specific TCP coverage.

   - Reduce network namespace tear-down time by removing per-subsystems
     synchronize_net() in tipc and sched.

   - Add flow label selector support for fib rules, allowing traffic
     redirection based on such header field.

  Netfilter:

   - Do not remove netdev basechain when last device is gone, allowing
     netdev basechains without devices.

   - Revisit the flowtable teardown strategy, dealing better with fin,
     reset and re-open events.

   - Scale-up IP-vs connection dumping by avoiding linear search on each
     restart.

  Protocols:

   - A significant XDP socket refactor, consolidating and optimizing
     several helpers into the core

   - Better scaling of ICMP rate-limiting, by removing false-sharing in
     inet peers handling.

   - Introduces netlink notifications for multicast IPv4 and IPv6
     address changes.

   - Add ipsec support for IP-TFS/AggFrag encapsulation, allowing
     aggregation and fragmentation of the inner IP.

   - Add sysctl to configure TIME-WAIT reuse delay for TCP sockets, to
     avoid local port exhaustion issues when the average connection
     lifetime is very short.

   - Support updating keys (re-keying) for connections using kernel TLS
     (for TLS 1.3 only).

   - Support ipv4-mapped ipv6 address clients in smc-r v2.

   - Add support for jumbo data packet transmission in RxRPC sockets,
     gluing multiple data packets in a single UDP packet.

   - Support RxRPC RACK-TLP to manage packet loss and retransmission in
     conjunction with the congestion control algorithm.

  Driver API:

   - Introduce a unified and structured interface for reporting PHY
     statistics, exposing consistent data across different H/W via
     ethtool.

   - Make timestamping selectable, allow the user to select the desired
     hwtstamp provider (PHY or MAC) administratively.

   - Add support for configuring a header-data-split threshold (HDS)
     value via ethtool, to deal with partial or buggy H/W
     implementation.

   - Consolidate DSA drivers Energy Efficiency Ethernet support.

   - Add EEE management to phylink, making use of the phylib
     implementation.

   - Add phylib support for in-band capabilities negotiation.

   - Simplify how phylib-enabled mac drivers expose the supported
     interfaces.

  Tests and tooling:

   - Make the YNL tool package-friendly to make it easier to deploy it
     separately from the kernel.

   - Increase TCP selftest coverage importing several packetdrill
     test-cases.

   - Regenerate the ethtool uapi header from the YNL spec, to ease
     maintenance and future development.

   - Add YNL support for decoding the link types used in net self-tests,
     allowing a single build to run both net and drivers/net.

  Drivers:

   - Ethernet high-speed NICs:
      - nVidia/Mellanox (mlx5):
         - add cross E-Switch QoS support
         - add SW Steering support for ConnectX-8
         - implement support for HW-Managed Flow Steering, improving the
           rule deletion/insertion rate
         - support for multi-host LAG
      - Intel (ixgbe, ice, igb):
         - ice: add support for devlink health events
         - ixgbe: add initial support for E610 chipset variant
         - igb: add support for AF_XDP zero-copy
      - Meta:
         - add support for basic RSS config
         - allow changing the number of channels
         - add hardware monitoring support
      - Broadcom (bnxt):
         - implement TCP data split and HDS threshold ethtool support,
           enabling Device Memory TCP.
      - Marvell Octeon:
         - implement egress ipsec offload support for the cn10k family
      - Hisilicon (HIBMC):
         - implement unicast MAC filtering

   - Ethernet NICs embedded and virtual:
      - Convert UDP tunnel drivers to NETDEV_PCPU_STAT_DSTATS, avoiding
        contented atomic operations for drop counters
      - Freescale:
         - quicc: phylink conversion
         - enetc: support Tx and Rx checksum offload and improve TSO
           performances
      - MediaTek:
         - airoha: introduce support for ETS and HTB Qdisc offload
      - Microchip:
         - lan78XX USB: preparation work for phylink conversion
      - Synopsys (stmmac):
         - support DWMAC IP on NXP Automotive SoCs S32G2xx/S32G3xx/S32R45
         - refactor EEE support to leverage the new driver API
         - optimize DMA and cache access to increase raw RX performances
           by 40%
      - TI:
         - icssg-prueth: add multicast filtering support for VLAN
           interface
      - netkit:
         - add ability to configure head/tailroom
      - VXLAN:
         - accepts packets with user-defined reserved bit

   - Ethernet switches:
      - Microchip:
         - lan969x: add RGMII support
         - lan969x: improve TX and RX performance using the FDMA engine
      - nVidia/Mellanox:
         - move Tx header handling to PCI driver, to ease XDP support

   - Ethernet PHYs:
      - Texas Instruments DP83822:
         - add support for GPIO2 clock output
      - Realtek:
         - 8169: add support for RTL8125D rev.b
         - rtl822x: add hwmon support for the temperature sensor
      - Microchip:
         - add support for RDS PTP hardware
         - consolidate periodic output signal generation

   - CAN:
      - several DT-bindings to DT schema conversions
      - tcan4x5x:
         - add HW standby support
         - support nWKRQ voltage selection
      - kvaser:
         - allowing Bus Error Reporting runtime configuration

   - WiFi:
      - the on-going Multi-Link Operation (MLO) effort continues,
        affecting both the stack and in drivers
      - mac80211/cfg80211:
         - Emergency Preparedness Communication Services (EPCS) station
           mode support
         - support for adding and removing station links for MLO
         - add support for WiFi 7/EHT mesh over 320 MHz channels
         - report Tx power info for each link
      - RealTek (rtw88):
         - enable USB Rx aggregation and USB 3 to improve performance
         - LED support
      - RealTek (rtw89):
         - refactor power save to support Multi-Link Operations
         - add support for RTL8922AE-VS variant
      - MediaTek (mt76):
         - single wiphy multiband support (preparation for MLO)
         - p2p device support
         - add TP-Link TXE50UH USB adapter support
      - Qualcomm (ath10k):
         - support for the QCA6698AQ IP core
      - Qualcomm (ath12k):
         - enable MLO for QCN9274

   - Bluetooth:
      - Allow sysfs to trigger hdev reset, to allow recovering devices
        not responsive from user-space
      - MediaTek: add support for MT7922, MT7925, MT7921e devices
      - Realtek: add support for RTL8851BE devices
      - Qualcomm: add support for WCN785x devices
      - ISO: allow BIG re-sync"

* tag 'net-next-6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1386 commits)
  net/rose: prevent integer overflows in rose_setsockopt()
  net: phylink: fix regression when binding a PHY
  net: ethernet: ti: am65-cpsw: streamline TX queue creation and cleanup
  net: ethernet: ti: am65-cpsw: streamline RX queue creation and cleanup
  net: ethernet: ti: am65-cpsw: ensure proper channel cleanup in error path
  ipv6: Convert inet6_rtm_deladdr() to per-netns RTNL.
  ipv6: Convert inet6_rtm_newaddr() to per-netns RTNL.
  ipv6: Move lifetime validation to inet6_rtm_newaddr().
  ipv6: Set cfg.ifa_flags before device lookup in inet6_rtm_newaddr().
  ipv6: Pass dev to inet6_addr_add().
  ipv6: Convert inet6_ioctl() to per-netns RTNL.
  ipv6: Hold rtnl_net_lock() in addrconf_init() and addrconf_cleanup().
  ipv6: Hold rtnl_net_lock() in addrconf_dad_work().
  ipv6: Hold rtnl_net_lock() in addrconf_verify_work().
  ipv6: Convert net.ipv6.conf.${DEV}.XXX sysctl to per-netns RTNL.
  ipv6: Add __in6_dev_get_rtnl_net().
  net: stmmac: Drop redundant skb_mark_for_recycle() for SKB frags
  net: mii: Fix the Speed display when the network cable is not connected
  sysctl net: Remove macro checks for CONFIG_SYSCTL
  eth: bnxt: update header sizing defaults
  ...

1 files changed, 116 insertions, 123 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6b1762300443..34945de1fb1f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -286,14 +286,9 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
-static inline int unix_our_peer(struct sock *sk, struct sock *osk)
-{
-	return unix_peer(osk) == sk;
-}
-
 static inline int unix_may_send(struct sock *sk, struct sock *osk)
 {
-	return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
+	return !unix_peer(osk) || unix_peer(osk) == sk;
 }
 
 static inline int unix_recvq_full_lockless(const struct sock *sk)
@@ -627,7 +622,9 @@ static void unix_write_space(struct sock *sk)
 static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
 {
 	if (!skb_queue_empty(&sk->sk_receive_queue)) {
-		skb_queue_purge(&sk->sk_receive_queue);
+		skb_queue_purge_reason(&sk->sk_receive_queue,
+				       SKB_DROP_REASON_UNIX_DISCONNECT);
+
 		wake_up_interruptible_all(&unix_sk(sk)->peer_wait);
 
 		/* If one link of bidirectional dgram pipe is disconnected,
@@ -645,7 +642,7 @@ static void unix_sock_destructor(struct sock *sk)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge_reason(&sk->sk_receive_queue, SKB_DROP_REASON_SOCKET_CLOSE);
 
 	DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
 	DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk));
@@ -720,8 +717,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		if (state == TCP_LISTEN)
 			unix_release_sock(skb->sk, 1);
 
-		/* passed fds are erased in the kfree_skb hook	      */
-		kfree_skb(skb);
+		/* passed fds are erased in the kfree_skb hook */
+		kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE);
 	}
 
 	if (path.dentry)
@@ -1563,32 +1560,30 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
 
 	/* First of all allocate resources.
-	   If we will make it after state is locked,
-	   we will have to recheck all again in any case.
+	 * If we will make it after state is locked,
+	 * we will have to recheck all again in any case.
 	 */
 
 	/* create new sock for complete connection */
 	newsk = unix_create1(net, NULL, 0, sock->type);
 	if (IS_ERR(newsk)) {
 		err = PTR_ERR(newsk);
-		newsk = NULL;
 		goto out;
 	}
 
-	err = -ENOMEM;
-
 	/* Allocate skb for sending to listening sock */
 	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
-	if (skb == NULL)
-		goto out;
+	if (!skb) {
+		err = -ENOMEM;
+		goto out_free_sk;
+	}
 
 restart:
 	/*  Find listening sock. */
 	other = unix_find_other(net, sunaddr, addr_len, sk->sk_type);
 	if (IS_ERR(other)) {
 		err = PTR_ERR(other);
-		other = NULL;
-		goto out;
+		goto out_free_skb;
 	}
 
 	unix_state_lock(other);
@@ -1600,23 +1595,25 @@ restart:
 		goto restart;
 	}
 
-	err = -ECONNREFUSED;
-	if (other->sk_state != TCP_LISTEN)
-		goto out_unlock;
-	if (other->sk_shutdown & RCV_SHUTDOWN)
+	if (other->sk_state != TCP_LISTEN ||
+	    other->sk_shutdown & RCV_SHUTDOWN) {
+		err = -ECONNREFUSED;
 		goto out_unlock;
+	}
 
 	if (unix_recvq_full_lockless(other)) {
-		err = -EAGAIN;
-		if (!timeo)
+		if (!timeo) {
+			err = -EAGAIN;
 			goto out_unlock;
+		}
 
 		timeo = unix_wait_for_peer(other, timeo);
+		sock_put(other);
 
 		err = sock_intr_errno(timeo);
 		if (signal_pending(current))
-			goto out;
-		sock_put(other);
+			goto out_free_skb;
+
 		goto restart;
 	}
 
@@ -1701,15 +1698,13 @@ restart:
 	return 0;
 
 out_unlock:
-	if (other)
-		unix_state_unlock(other);
-
+	unix_state_unlock(other);
+	sock_put(other);
+out_free_skb:
+	consume_skb(skb);
+out_free_sk:
+	unix_release_sock(newsk, 0);
 out:
-	kfree_skb(skb);
-	if (newsk)
-		unix_release_sock(newsk, 0);
-	if (other)
-		sock_put(other);
 	return err;
 }
 
@@ -1964,7 +1959,6 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
 static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			      size_t len)
 {
-	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	struct sock *sk = sock->sk, *other = NULL;
 	struct unix_sock *u = unix_sk(sk);
 	struct scm_cookie scm;
@@ -1980,12 +1974,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	wait_for_unix_gc(scm.fp);
 
-	err = -EOPNOTSUPP;
-	if (msg->msg_flags&MSG_OOB)
+	if (msg->msg_flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	if (msg->msg_namelen) {
-		err = unix_validate_addr(sunaddr, msg->msg_namelen);
+		err = unix_validate_addr(msg->msg_name, msg->msg_namelen);
 		if (err)
 			goto out;
 
@@ -1995,12 +1990,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 							    NULL);
 		if (err)
 			goto out;
-	} else {
-		sunaddr = NULL;
-		err = -ENOTCONN;
-		other = unix_peer_get(sk);
-		if (!other)
-			goto out;
 	}
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
@@ -2011,9 +2000,10 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out;
 	}
 
-	err = -EMSGSIZE;
-	if (len > READ_ONCE(sk->sk_sndbuf) - 32)
+	if (len > READ_ONCE(sk->sk_sndbuf) - 32) {
+		err = -EMSGSIZE;
 		goto out;
+	}
 
 	if (len > SKB_MAX_ALLOC) {
 		data_len = min_t(size_t,
@@ -2027,7 +2017,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	skb = sock_alloc_send_pskb(sk, len - data_len, data_len,
 				   msg->msg_flags & MSG_DONTWAIT, &err,
 				   PAGE_ALLOC_COSTLY_ORDER);
-	if (skb == NULL)
+	if (!skb)
 		goto out;
 
 	err = unix_scm_to_skb(&scm, skb, true);
@@ -2043,17 +2033,18 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
-restart:
-	if (!other) {
-		err = -ECONNRESET;
-		if (sunaddr == NULL)
-			goto out_free;
-
-		other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen,
-					sk->sk_type);
+	if (msg->msg_namelen) {
+lookup:
+		other = unix_find_other(sock_net(sk), msg->msg_name,
+					msg->msg_namelen, sk->sk_type);
 		if (IS_ERR(other)) {
 			err = PTR_ERR(other);
-			other = NULL;
+			goto out_free;
+		}
+	} else {
+		other = unix_peer_get(sk);
+		if (!other) {
+			err = -ENOTCONN;
 			goto out_free;
 		}
 	}
@@ -2061,36 +2052,37 @@ restart:
 	if (sk_filter(other, skb) < 0) {
 		/* Toss the packet but do not return any error to the sender */
 		err = len;
-		goto out_free;
+		goto out_sock_put;
 	}
 
+restart:
 	sk_locked = 0;
 	unix_state_lock(other);
 restart_locked:
-	err = -EPERM;
-	if (!unix_may_send(sk, other))
+
+	if (!unix_may_send(sk, other)) {
+		err = -EPERM;
 		goto out_unlock;
+	}
 
 	if (unlikely(sock_flag(other, SOCK_DEAD))) {
-		/*
-		 *	Check with 1003.1g - what should
-		 *	datagram error
-		 */
-		unix_state_unlock(other);
-		sock_put(other);
+		/* Check with 1003.1g - what should datagram error */
 
-		if (!sk_locked)
-			unix_state_lock(sk);
+		unix_state_unlock(other);
 
-		err = 0;
 		if (sk->sk_type == SOCK_SEQPACKET) {
 			/* We are here only when racing with unix_release_sock()
 			 * is clearing @other. Never change state to TCP_CLOSE
 			 * unlike SOCK_DGRAM wants.
 			 */
-			unix_state_unlock(sk);
 			err = -EPIPE;
-		} else if (unix_peer(sk) == other) {
+			goto out_sock_put;
+		}
+
+		if (!sk_locked)
+			unix_state_lock(sk);
+
+		if (unix_peer(sk) == other) {
 			unix_peer(sk) = NULL;
 			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
 
@@ -2100,19 +2092,23 @@ restart_locked:
 			unix_dgram_disconnected(sk, other);
 			sock_put(other);
 			err = -ECONNREFUSED;
-		} else {
-			unix_state_unlock(sk);
+			goto out_sock_put;
 		}
 
-		other = NULL;
-		if (err)
-			goto out_free;
-		goto restart;
+		unix_state_unlock(sk);
+
+		if (!msg->msg_namelen) {
+			err = -ECONNRESET;
+			goto out_sock_put;
+		}
+
+		goto lookup;
 	}
 
-	err = -EPIPE;
-	if (other->sk_shutdown & RCV_SHUTDOWN)
+	if (other->sk_shutdown & RCV_SHUTDOWN) {
+		err = -EPIPE;
 		goto out_unlock;
+	}
 
 	if (sk->sk_type != SOCK_SEQPACKET) {
 		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
@@ -2132,7 +2128,7 @@ restart_locked:
 
 			err = sock_intr_errno(timeo);
 			if (signal_pending(current))
-				goto out_free;
+				goto out_sock_put;
 
 			goto restart;
 		}
@@ -2173,11 +2169,11 @@ out_unlock:
 	if (sk_locked)
 		unix_state_unlock(sk);
 	unix_state_unlock(other);
+out_sock_put:
+	sock_put(other);
 out_free:
-	kfree_skb(skb);
+	consume_skb(skb);
 out:
-	if (other)
-		sock_put(other);
 	scm_destroy(&scm);
 	return err;
 }
@@ -2193,7 +2189,7 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 {
 	struct unix_sock *ousk = unix_sk(other);
 	struct sk_buff *skb;
-	int err = 0;
+	int err;
 
 	skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err);
 
@@ -2201,25 +2197,22 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 		return err;
 
 	err = unix_scm_to_skb(scm, skb, !fds_sent);
-	if (err < 0) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (err < 0)
+		goto out;
+
 	skb_put(skb, 1);
 	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1);
 
-	if (err) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (err)
+		goto out;
 
 	unix_state_lock(other);
 
 	if (sock_flag(other, SOCK_DEAD) ||
 	    (other->sk_shutdown & RCV_SHUTDOWN)) {
 		unix_state_unlock(other);
-		kfree_skb(skb);
-		return -EPIPE;
+		err = -EPIPE;
+		goto out;
 	}
 
 	maybe_add_creds(skb, sock, other);
@@ -2234,6 +2227,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
 
+	return 0;
+out:
+	consume_skb(skb);
 	return err;
 }
 #endif
@@ -2242,13 +2238,11 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			       size_t len)
 {
 	struct sock *sk = sock->sk;
+	struct sk_buff *skb = NULL;
 	struct sock *other = NULL;
-	int err, size;
-	struct sk_buff *skb;
-	int sent = 0;
 	struct scm_cookie scm;
 	bool fds_sent = false;
-	int data_len;
+	int err, sent = 0;
 
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
@@ -2256,8 +2250,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	wait_for_unix_gc(scm.fp);
 
-	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 		if (len)
 			len--;
@@ -2270,17 +2264,19 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out_err;
 	} else {
-		err = -ENOTCONN;
 		other = unix_peer(sk);
-		if (!other)
+		if (!other) {
+			err = -ENOTCONN;
 			goto out_err;
+		}
 	}
 
 	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
-		goto pipe_err;
+		goto out_pipe;
 
 	while (sent < len) {
-		size = len - sent;
+		int size = len - sent;
+		int data_len;
 
 		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
 			skb = sock_alloc_send_pskb(sk, 0, 0,
@@ -2306,20 +2302,18 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 		/* Only send the fds in the first buffer */
 		err = unix_scm_to_skb(&scm, skb, !fds_sent);
-		if (err < 0) {
-			kfree_skb(skb);
-			goto out_err;
-		}
+		if (err < 0)
+			goto out_free;
+
 		fds_sent = true;
 
 		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			err = skb_splice_from_iter(skb, &msg->msg_iter, size,
 						   sk->sk_allocation);
-			if (err < 0) {
-				kfree_skb(skb);
-				goto out_err;
-			}
+			if (err < 0)
+				goto out_free;
+
 			size = err;
 			refcount_add(size, &sk->sk_wmem_alloc);
 		} else {
@@ -2327,17 +2321,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			skb->data_len = data_len;
 			skb->len = size;
 			err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
-			if (err) {
-				kfree_skb(skb);
-				goto out_err;
-			}
+			if (err)
+				goto out_free;
 		}
 
 		unix_state_lock(other);
 
 		if (sock_flag(other, SOCK_DEAD) ||
 		    (other->sk_shutdown & RCV_SHUTDOWN))
-			goto pipe_err_free;
+			goto out_pipe_unlock;
 
 		maybe_add_creds(skb, sock, other);
 		scm_stat_add(other, skb);
@@ -2360,13 +2352,14 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	return sent;
 
-pipe_err_free:
+out_pipe_unlock:
 	unix_state_unlock(other);
-	kfree_skb(skb);
-pipe_err:
-	if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL))
+out_pipe:
+	if (!sent && !(msg->msg_flags & MSG_NOSIGNAL))
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
+out_free:
+	consume_skb(skb);
 out_err:
 	scm_destroy(&scm);
 	return sent ? : err;
@@ -2699,7 +2692,7 @@ unlock:
 	spin_unlock(&sk->sk_receive_queue.lock);
 
 	consume_skb(read_skb);
-	kfree_skb(unread_skb);
+	kfree_skb_reason(unread_skb, SKB_DROP_REASON_UNIX_SKIP_OOB);
 
 	return skb;
 }
@@ -2728,7 +2721,7 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 
 		if (sock_flag(sk, SOCK_DEAD)) {
 			unix_state_unlock(sk);
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE);
 			return -ECONNRESET;
 		}
 
@@ -2742,7 +2735,7 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		unix_state_unlock(sk);
 
 		if (drop) {
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_UNIX_SKIP_OOB);
 			return -EAGAIN;
 		}
 	}