From 56667da7399eb19af857e30f41bea89aa6fa812c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 19 Feb 2024 14:12:20 +0000 Subject: net: implement lockless setsockopt(SO_PEEK_OFF) syzbot reported a lockdep violation [1] involving af_unix support of SO_PEEK_OFF. Since SO_PEEK_OFF is inherently not thread safe (it uses a per-socket sk_peek_off field), there is really no point to enforce a pointless thread safety in the kernel. After this patch : - setsockopt(SO_PEEK_OFF) no longer acquires the socket lock. - skb_consume_udp() no longer has to acquire the socket lock. - af_unix no longer needs a special version of sk_set_peek_off(), because it does not lock u->iolock anymore. As a followup, we could replace prot->set_peek_off to be a boolean and avoid an indirect call, since we always use sk_set_peek_off(). [1] WARNING: possible circular locking dependency detected 6.8.0-rc4-syzkaller-00267-g0f1dd5e91e2b #0 Not tainted syz-executor.2/30025 is trying to acquire lock: ffff8880765e7d80 (&u->iolock){+.+.}-{3:3}, at: unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789 but task is already holding lock: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1691 [inline] ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sockopt_lock_sock net/core/sock.c:1060 [inline] ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sk_setsockopt+0xe52/0x3360 net/core/sock.c:1193 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (sk_lock-AF_UNIX){+.+.}-{0:0}: lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 lock_sock_nested+0x48/0x100 net/core/sock.c:3524 lock_sock include/net/sock.h:1691 [inline] __unix_dgram_recvmsg+0x1275/0x12c0 net/unix/af_unix.c:2415 sock_recvmsg_nosec+0x18e/0x1d0 net/socket.c:1046 ____sys_recvmsg+0x3c0/0x470 net/socket.c:2801 ___sys_recvmsg net/socket.c:2845 [inline] do_recvmmsg+0x474/0xae0 net/socket.c:2939 __sys_recvmmsg net/socket.c:3018 [inline] __do_sys_recvmmsg net/socket.c:3041 [inline] __se_sys_recvmmsg net/socket.c:3034 [inline] __x64_sys_recvmmsg+0x199/0x250 net/socket.c:3034 do_syscall_64+0xf9/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 -> #0 (&u->iolock){+.+.}-{3:3}: check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 __mutex_lock_common kernel/locking/mutex.c:608 [inline] __mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752 unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789 sk_setsockopt+0x207e/0x3360 do_sock_setsockopt+0x2fb/0x720 net/socket.c:2307 __sys_setsockopt+0x1ad/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xf9/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(sk_lock-AF_UNIX); lock(&u->iolock); lock(sk_lock-AF_UNIX); lock(&u->iolock); *** DEADLOCK *** 1 lock held by syz-executor.2/30025: #0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1691 [inline] #0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sockopt_lock_sock net/core/sock.c:1060 [inline] #0: ffff8880765e7930 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sk_setsockopt+0xe52/0x3360 net/core/sock.c:1193 stack backtrace: CPU: 0 PID: 30025 Comm: syz-executor.2 Not tainted 6.8.0-rc4-syzkaller-00267-g0f1dd5e91e2b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2e0 lib/dump_stack.c:106 check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2187 check_prev_add kernel/locking/lockdep.c:3134 [inline] check_prevs_add kernel/locking/lockdep.c:3253 [inline] validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869 __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137 lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754 __mutex_lock_common kernel/locking/mutex.c:608 [inline] __mutex_lock+0x136/0xd70 kernel/locking/mutex.c:752 unix_set_peek_off+0x26/0xa0 net/unix/af_unix.c:789 sk_setsockopt+0x207e/0x3360 do_sock_setsockopt+0x2fb/0x720 net/socket.c:2307 __sys_setsockopt+0x1ad/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xf9/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7f78a1c7dda9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f78a0fde0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00007f78a1dac050 RCX: 00007f78a1c7dda9 RDX: 000000000000002a RSI: 0000000000000001 RDI: 0000000000000006 RBP: 00007f78a1cca47a R08: 0000000000000004 R09: 0000000000000000 R10: 0000000020000180 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000006e R14: 00007f78a1dac050 R15: 00007ffe5cd81ae8 Fixes: 859051dd165e ("bpf: Implement cgroup sockaddr hooks for unix sockets") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Cc: Daan De Meyer Cc: Kuniyuki Iwashima Cc: Martin KaFai Lau Cc: David Ahern Reviewed-by: Willem de Bruijn Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/unix/af_unix.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 30b178ebba60..0748e7ea5210 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_set_peek_off(struct sock *sk, int val) -{ - struct unix_sock *u = unix_sk(sk); - - if (mutex_lock_interruptible(&u->iolock)) - return -EINTR; - - WRITE_ONCE(sk->sk_peek_off, val); - mutex_unlock(&u->iolock); - - return 0; -} - #ifdef CONFIG_PROC_FS static int unix_count_nr_fds(struct sock *sk) { @@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = { .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, .splice_read = unix_stream_splice_read, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = { .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; -- cgit v1.2.3 From aa82ac51d63328714645c827775d64dbfd9941f3 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 19 Feb 2024 09:46:57 -0800 Subject: af_unix: Drop oob_skb ref before purging queue in GC. syzbot reported another task hung in __unix_gc(). [0] The current while loop assumes that all of the left candidates have oob_skb and calling kfree_skb(oob_skb) releases the remaining candidates. However, I missed a case that oob_skb has self-referencing fd and another fd and the latter sk is placed before the former in the candidate list. Then, the while loop never proceeds, resulting the task hung. __unix_gc() has the same loop just before purging the collected skb, so we can call kfree_skb(oob_skb) there and let __skb_queue_purge() release all inflight sockets. [0]: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 2784 Comm: kworker/u4:8 Not tainted 6.8.0-rc4-syzkaller-01028-g71b605d32017 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Workqueue: events_unbound __unix_gc RIP: 0010:__sanitizer_cov_trace_pc+0x0/0x70 kernel/kcov.c:200 Code: 89 fb e8 23 00 00 00 48 8b 3d 84 f5 1a 0c 48 89 de 5b e9 43 26 57 00 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1e fa 48 8b 04 24 65 48 8b 0d 90 52 70 7e 65 8b 15 91 52 70 RSP: 0018:ffffc9000a17fa78 EFLAGS: 00000287 RAX: ffffffff8a0a6108 RBX: ffff88802b6c2640 RCX: ffff88802c0b3b80 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000000 RBP: ffffc9000a17fbf0 R08: ffffffff89383f1d R09: 1ffff1100ee5ff84 R10: dffffc0000000000 R11: ffffed100ee5ff85 R12: 1ffff110056d84ee R13: ffffc9000a17fae0 R14: 0000000000000000 R15: ffffffff8f47b840 FS: 0000000000000000(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffef5687ff8 CR3: 0000000029b34000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __unix_gc+0xe69/0xf40 net/unix/garbage.c:343 process_one_work kernel/workqueue.c:2633 [inline] process_scheduled_works+0x913/0x1420 kernel/workqueue.c:2706 worker_thread+0xa5f/0x1000 kernel/workqueue.c:2787 kthread+0x2ef/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:242 Reported-and-tested-by: syzbot+ecab4d36f920c3574bf9@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ecab4d36f920c3574bf9 Fixes: 25236c91b5ab ("af_unix: Fix task hung while purging oob_skb in GC.") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/unix/garbage.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'net/unix') diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2ff7ddbaa782..2a81880dac7b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -284,9 +284,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -314,18 +322,6 @@ void unix_gc(void) /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - while (!list_empty(&gc_candidates)) { - u = list_entry(gc_candidates.next, struct unix_sock, link); - if (u->oob_skb) { - struct sk_buff *skb = u->oob_skb; - - u->oob_skb = NULL; - kfree_skb(skb); - } - } -#endif - spin_lock(&unix_gc_lock); /* There could be io_uring registered files, just push them back to -- cgit v1.2.3