Merging upstream version 6.1.90.

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

1 files changed, 25 insertions, 10 deletions

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 9bfffe2a7..d2fc79539 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
@@ -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);