af_unix: Read sk->sk_hash under bindlock during bind().

[ Upstream commit 51d1b25a720982324871338b1a36b197ec9bd6f0 ]

syzkaller reported data-race of sk->sk_hash in unix_autobind() [0],
and the same ones exist in unix_bind_bsd() and unix_bind_abstract().

The three bind() functions prefetch sk->sk_hash locklessly and
use it later after validating that unix_sk(sk)->addr is NULL under
unix_sk(sk)->bindlock.

The prefetched sk->sk_hash is the hash value of unbound socket set
in unix_create1() and does not change until bind() completes.

There could be a chance that sk->sk_hash changes after the lockless
read.  However, in such a case, non-NULL unix_sk(sk)->addr is visible
under unix_sk(sk)->bindlock, and bind() returns -EINVAL without using
the prefetched value.

The KCSAN splat is false-positive, but let's silence it by reading
sk->sk_hash under unix_sk(sk)->bindlock.

[0]:
BUG: KCSAN: data-race in unix_autobind / unix_autobind

write to 0xffff888034a9fb88 of 4 bytes by task 4468 on cpu 0:
 __unix_set_addr_hash net/unix/af_unix.c:331 [inline]
 unix_autobind+0x47a/0x7d0 net/unix/af_unix.c:1185
 unix_dgram_connect+0x7e3/0x890 net/unix/af_unix.c:1373
 __sys_connect_file+0xd7/0xe0 net/socket.c:2048
 __sys_connect+0x114/0x140 net/socket.c:2065
 __do_sys_connect net/socket.c:2075 [inline]
 __se_sys_connect net/socket.c:2072 [inline]
 __x64_sys_connect+0x40/0x50 net/socket.c:2072
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

read to 0xffff888034a9fb88 of 4 bytes by task 4465 on cpu 1:
 unix_autobind+0x28/0x7d0 net/unix/af_unix.c:1134
 unix_dgram_connect+0x7e3/0x890 net/unix/af_unix.c:1373
 __sys_connect_file+0xd7/0xe0 net/socket.c:2048
 __sys_connect+0x114/0x140 net/socket.c:2065
 __do_sys_connect net/socket.c:2075 [inline]
 __se_sys_connect net/socket.c:2072 [inline]
 __x64_sys_connect+0x40/0x50 net/socket.c:2072
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x46/0x4e

value changed: 0x000000e4 -> 0x000001e3

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 4465 Comm: syz-executor.0 Not tainted 6.8.0-12822-gcd51db110a7e #12
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014

Fixes: afd20b9290e1 ("af_unix: Replace the big lock with small locks.")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240522154218.78088-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 6 insertions, 3 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index df6bddca08f8..d01314dc86ec 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1145,8 +1145,8 @@ static struct sock *unix_find_other(struct net *net,
 
 static int unix_autobind(struct sock *sk)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	u32 lastnum, ordernum;
@@ -1169,6 +1169,7 @@ static int unix_autobind(struct sock *sk)
 	addr->name->sun_family = AF_UNIX;
 	refcount_set(&addr->refcnt, 1);
 
+	old_hash = sk->sk_hash;
 	ordernum = get_random_u32();
 	lastnum = ordernum & 0xFFFFF;
 retry:
@@ -1209,8 +1210,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 {
 	umode_t mode = S_IFSOCK |
 	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct mnt_idmap *idmap;
 	struct unix_address *addr;
@@ -1248,6 +1249,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 	if (u->addr)
 		goto out_unlock;
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_bsd_hash(d_backing_inode(dentry));
 	unix_table_double_lock(net, old_hash, new_hash);
 	u->path.mnt = mntget(parent.mnt);
@@ -1275,8 +1277,8 @@ out:
 static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 			      int addr_len)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	int err;
@@ -1294,6 +1296,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 		goto out_mutex;
 	}
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
 	unix_table_double_lock(net, old_hash, new_hash);