Merge branch 'af_unix-set-skb-drop-reason-in-every-kfree_skb-path'

Kuniyuki Iwashima says:

====================
af_unix: Set skb drop reason in every kfree_skb() path.

There is a potential user for skb drop reason for AF_UNIX.

This series replaces some kfree_skb() in connect() and
sendmsg() paths and sets skb drop reason for the rest of
kfree_skb() in AF_UNIX.

Link: https://lore.kernel.org/netdev/CAAf2ycmZHti95WaBR3s+L5Epm1q7sXmvZ-EqCK=-oZj=45tOwQ@mail.gmail.com/

v2: https://lore.kernel.org/20250112040810.14145-1-kuniyu@amazon.com/
v1: https://lore.kernel.org/20250110092641.85905-1-kuniyu@amazon.com/
====================

Link: https://patch.msgid.link/20250116053441.5758-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/dropreason-core.h

@@ -6,9 +6,13 @@
 #define DEFINE_DROP_REASON(FN, FNe)	\
 	FN(NOT_SPECIFIED)		\
 	FN(NO_SOCKET)			\
+	FN(SOCKET_CLOSE)		\
+	FN(SOCKET_FILTER)		\
+	FN(SOCKET_RCVBUFF)		\
+	FN(UNIX_DISCONNECT)		\
+	FN(UNIX_SKIP_OOB)		\
 	FN(PKT_TOO_SMALL)		\
 	FN(TCP_CSUM)			\
-	FN(SOCKET_FILTER)		\
 	FN(UDP_CSUM)			\
 	FN(NETFILTER_DROP)		\
 	FN(OTHERHOST)			\
@@ -18,7 +22,6 @@
 	FN(UNICAST_IN_L2_MULTICAST)	\
 	FN(XFRM_POLICY)			\
 	FN(IP_NOPROTO)			\
-	FN(SOCKET_RCVBUFF)		\
 	FN(PROTO_MEM)			\
 	FN(TCP_AUTH_HDR)		\
 	FN(TCP_MD5NOTFOUND)		\
@@ -138,12 +141,27 @@ enum skb_drop_reason {
 	 * 3) no valid child socket during 3WHS process
 	 */
 	SKB_DROP_REASON_NO_SOCKET,
+	/** @SKB_DROP_REASON_SOCKET_CLOSE: socket is close()d */
+	SKB_DROP_REASON_SOCKET_CLOSE,
+	/** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
+	SKB_DROP_REASON_SOCKET_FILTER,
+	/** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
+	SKB_DROP_REASON_SOCKET_RCVBUFF,
+	/**
+	 * @SKB_DROP_REASON_UNIX_DISCONNECT: recv queue is purged when SOCK_DGRAM
+	 * or SOCK_SEQPACKET socket re-connect()s to another socket or notices
+	 * during send() that the peer has been close()d.
+	 */
+	SKB_DROP_REASON_UNIX_DISCONNECT,
+	/**
+	 * @SKB_DROP_REASON_UNIX_SKIP_OOB: Out-Of-Band data is skipped by
+	 * recv() without MSG_OOB so dropped.
+	 */
+	SKB_DROP_REASON_UNIX_SKIP_OOB,
 	/** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */
 	SKB_DROP_REASON_PKT_TOO_SMALL,
 	/** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */
 	SKB_DROP_REASON_TCP_CSUM,
-	/** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */
-	SKB_DROP_REASON_SOCKET_FILTER,
 	/** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */
 	SKB_DROP_REASON_UDP_CSUM,
 	/** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */
@@ -174,8 +192,6 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_XFRM_POLICY,
 	/** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */
 	SKB_DROP_REASON_IP_NOPROTO,
-	/** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
-	SKB_DROP_REASON_SOCKET_RCVBUFF,
 	/**
 	 * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as
 	 * udp packet drop out of udp_memory_allocated.

net/unix/af_unix.c

@@ -622,7 +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,
@@ -640,7 +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));
@@ -715,8 +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)
@@ -1699,7 +1701,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	unix_state_unlock(other);
 	sock_put(other);
 out_free_skb:
-	kfree_skb(skb);
+	consume_skb(skb);
 out_free_sk:
 	unix_release_sock(newsk, 0);
 out:
@@ -2170,7 +2172,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 out_sock_put:
 	sock_put(other);
 out_free:
-	kfree_skb(skb);
+	consume_skb(skb);
 out:
 	scm_destroy(&scm);
 	return err;
@@ -2187,7 +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);
 
@@ -2195,25 +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);
@@ -2228,6 +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
@@ -2236,13 +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)
@@ -2271,16 +2271,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		}
 	}
 
-	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) {
-		if (!(msg->msg_flags & MSG_NOSIGNAL))
-			send_sig(SIGPIPE, current, 0);
-
-		err = -EPIPE;
-		goto out_err;
-	}
+	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
+		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,
@@ -2333,7 +2329,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 		if (sock_flag(other, SOCK_DEAD) ||
 		    (other->sk_shutdown & RCV_SHUTDOWN))
-			goto out_pipe;
+			goto out_pipe_unlock;
 
 		maybe_add_creds(skb, sock, other);
 		scm_stat_add(other, skb);
@@ -2356,13 +2352,14 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	return sent;
 
-out_pipe:
+out_pipe_unlock:
 	unix_state_unlock(other);
+out_pipe:
 	if (!sent && !(msg->msg_flags & MSG_NOSIGNAL))
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
 out_free:
-	kfree_skb(skb);
+	consume_skb(skb);
 out_err:
 	scm_destroy(&scm);
 	return sent ? : err;
@@ -2695,7 +2692,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 	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;
 }
@@ -2724,7 +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;
 		}
 
@@ -2738,7 +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;
 		}
 	}

net/unix/garbage.c

@@ -573,7 +573,7 @@ static void __unix_gc(struct work_struct *work)
 			UNIXCB(skb).fp->dead = true;
 	}
 
-	__skb_queue_purge(&hitlist);
+	__skb_queue_purge_reason(&hitlist, SKB_DROP_REASON_SOCKET_CLOSE);
 skip_gc:
 	WRITE_ONCE(gc_in_progress, false);
 }