Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 41 insertions, 28 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 237488b1b..224b1fdc8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -817,11 +817,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	sk->sk_write_space	= unix_write_space;
 	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
 	sk->sk_destruct		= unix_sock_destructor;
-	u	  = unix_sk(sk);
+	u = unix_sk(sk);
+	u->inflight = 0;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
-	atomic_long_set(&u->inflight, 0);
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
@@ -1126,13 +1126,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
-		unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
+	unix_state_lock(sk1);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1352,7 +1350,7 @@ restart:
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 951b33fa8..2975e7a06 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -83,7 +83,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 			 * queue lock. With the other's queue locked it's
 			 * OK to lock the state.
 			 */
-			unix_state_lock_nested(req);
+			unix_state_lock_nested(req, U_LOCK_DIAG);
 			peer = unix_sk(req)->peer;
 			buf[i++] = (peer ? sock_i_ino(peer) : 0);
 			unix_state_unlock(req);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index dc2763540..133ba5be4 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
 
 static void dec_inflight(struct unix_sock *usk)
 {
-	atomic_long_dec(&usk->inflight);
+	usk->inflight--;
 }
 
 static void inc_inflight(struct unix_sock *usk)
 {
-	atomic_long_inc(&usk->inflight);
+	usk->inflight++;
 }
 
 static void inc_inflight_move_tail(struct unix_sock *u)
 {
-	atomic_long_inc(&u->inflight);
+	u->inflight++;
+
 	/* If this still might be part of a cycle, move it to the end
 	 * of the list, so that it's checked even if it was already
 	 * passed over
@@ -198,7 +199,7 @@ void wait_for_unix_gc(void)
 	if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC &&
 	    !READ_ONCE(gc_in_progress))
 		unix_gc();
-	wait_event(unix_gc_wait, gc_in_progress == false);
+	wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress));
 }
 
 /* The external entry point: unix_gc() */
@@ -234,20 +235,34 @@ void unix_gc(void)
 	 * receive queues.  Other, non candidate sockets _can_ be
 	 * added to queue, so we must make sure only to touch
 	 * candidates.
+	 *
+	 * Embryos, though never candidates themselves, affect which
+	 * candidates are reachable by the garbage collector.  Before
+	 * being added to a listener's queue, an embryo may already
+	 * receive data carrying SCM_RIGHTS, potentially making the
+	 * passed socket a candidate that is not yet reachable by the
+	 * collector.  It becomes reachable once the embryo is
+	 * enqueued.  Therefore, we must ensure that no SCM-laden
+	 * embryo appears in a (candidate) listener's queue between
+	 * consecutive scan_children() calls.
 	 */
 	list_for_each_entry_safe(u, next, &gc_inflight_list, link) {
+		struct sock *sk = &u->sk;
 		long total_refs;
-		long inflight_refs;
 
-		total_refs = file_count(u->sk.sk_socket->file);
-		inflight_refs = atomic_long_read(&u->inflight);
+		total_refs = file_count(sk->sk_socket->file);
 
-		BUG_ON(inflight_refs < 1);
-		BUG_ON(total_refs < inflight_refs);
-		if (total_refs == inflight_refs) {
+		BUG_ON(!u->inflight);
+		BUG_ON(total_refs < u->inflight);
+		if (total_refs == u->inflight) {
 			list_move_tail(&u->link, &gc_candidates);
 			__set_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
 			__set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
+
+			if (sk->sk_state == TCP_LISTEN) {
+				unix_state_lock_nested(sk, U_LOCK_GC_LISTENER);
+				unix_state_unlock(sk);
+			}
 		}
 	}
 
@@ -271,7 +286,7 @@ void unix_gc(void)
 		/* Move cursor to after the current position. */
 		list_move(&cursor, &u->link);
 
-		if (atomic_long_read(&u->inflight) > 0) {
+		if (u->inflight) {
 			list_move_tail(&u->link, &not_cycle_list);
 			__clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
 			scan_children(&u->sk, inc_inflight_move_tail, NULL);
diff --git a/net/unix/scm.c b/net/unix/scm.c
index e8e2a00bb..4eff7da9f 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -34,10 +34,8 @@ struct sock *unix_get_socket(struct file *filp)
 		/* PF_UNIX ? */
 		if (s && sock->ops && sock->ops->family == PF_UNIX)
 			u_sock = s;
-	} else {
-		/* Could be an io_uring instance */
-		u_sock = io_uring_get_socket(filp);
 	}
+
 	return u_sock;
 }
 EXPORT_SYMBOL(unix_get_socket);
@@ -54,12 +52,13 @@ void unix_inflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		if (atomic_long_inc_return(&u->inflight) == 1) {
+		if (!u->inflight) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
 		} else {
 			BUG_ON(list_empty(&u->link));
 		}
+		u->inflight++;
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
 	}
@@ -76,10 +75,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		BUG_ON(!atomic_long_read(&u->inflight));
+		BUG_ON(!u->inflight);
 		BUG_ON(list_empty(&u->link));
 
-		if (atomic_long_dec_and_test(&u->inflight))
+		u->inflight--;
+		if (!u->inflight)
 			list_del_init(&u->link);
 		/* Paired with READ_ONCE() in wait_for_unix_gc() */
 		WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);