[syzbot] [bpf?] [net?] possible deadlock in sock_hash_delete_elem (2)

[syzbot] [bpf?] [net?] possible deadlock in sock_hash_delete_elem (2)

[syzbot]

Hello,

syzbot found the following issue on:

HEAD commit:    0740b6427e90 Merge branch 'bpf-arena-followups'
git tree:       bpf
console output: https://syzkaller.appspot.com/x/log.txt?x=11b90ac9180000
kernel config:  https://syzkaller.appspot.com/x/.config?x=6fb1be60a193d440
dashboard link: https://syzkaller.appspot.com/bug?extid=ec941d6e24f633a59172
compiler:       Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40

Unfortunately, I don't have any reproducer for this issue yet.

Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/c9e6e9f97566/disk-0740b642.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/78476a588b62/vmlinux-0740b642.xz
kernel image: https://storage.googleapis.com/syzbot-assets/50cd6fab9ead/bzImage-0740b642.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com

============================================
WARNING: possible recursive locking detected
6.8.0-syzkaller-05226-g0740b6427e90 #0 Not tainted
--------------------------------------------
syz-executor.4/13471 is trying to acquire lock:
ffff888034bc90f8 (&htab->buckets[i].lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
ffff888034bc90f8 (&htab->buckets[i].lock){+.-.}-{2:2}, at: sock_hash_delete_elem+0xb0/0x300 net/core/sock_map.c:939

but task is already holding lock:
ffff888063a77968 (&htab->buckets[i].lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
ffff888063a77968 (&htab->buckets[i].lock){+.-.}-{2:2}, at: sock_hash_update_common+0x20c/0xa30 net/core/sock_map.c:1007

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&htab->buckets[i].lock);
  lock(&htab->buckets[i].lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

5 locks held by syz-executor.4/13471:
 #0: ffff888065685258 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1671 [inline]
 #0: ffff888065685258 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sock_map_sk_acquire net/core/sock_map.c:117 [inline]
 #0: ffff888065685258 (sk_lock-AF_UNIX){+.+.}-{0:0}, at: sock_map_update_elem_sys+0x1cc/0x910 net/core/sock_map.c:575
 #1: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
 #1: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
 #1: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: sock_map_sk_acquire net/core/sock_map.c:118 [inline]
 #1: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: sock_map_update_elem_sys+0x1d8/0x910 net/core/sock_map.c:575
 #2: ffff888063a77968 (&htab->buckets[i].lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 #2: ffff888063a77968 (&htab->buckets[i].lock){+.-.}-{2:2}, at: sock_hash_update_common+0x20c/0xa30 net/core/sock_map.c:1007
 #3: ffff88803bbbc290 (&psock->link_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 #3: ffff88803bbbc290 (&psock->link_lock){+...}-{2:2}, at: sock_map_del_link net/core/sock_map.c:145 [inline]
 #3: ffff88803bbbc290 (&psock->link_lock){+...}-{2:2}, at: sock_map_unref+0xcc/0x5e0 net/core/sock_map.c:180
 #4: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
 #4: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
 #4: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: __bpf_trace_run kernel/trace/bpf_trace.c:2380 [inline]
 #4: ffffffff8e131920 (rcu_read_lock){....}-{1:2}, at: bpf_trace_run2+0x114/0x420 kernel/trace/bpf_trace.c:2420

stack backtrace:
CPU: 0 PID: 13471 Comm: syz-executor.4 Not tainted 6.8.0-syzkaller-05226-g0740b6427e90 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/29/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x1e7/0x2e0 lib/dump_stack.c:106
 check_deadlock kernel/locking/lockdep.c:3062 [inline]
 validate_chain+0x15c1/0x58e0 kernel/locking/lockdep.c:3856
 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
 lock_acquire+0x1e4/0x530 kernel/locking/lockdep.c:5754
 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
 _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178
 spin_lock_bh include/linux/spinlock.h:356 [inline]
 sock_hash_delete_elem+0xb0/0x300 net/core/sock_map.c:939
 bpf_prog_2c29ac5cdc6b1842+0x42/0x46
 bpf_dispatcher_nop_func include/linux/bpf.h:1234 [inline]
 __bpf_prog_run include/linux/filter.h:657 [inline]
 bpf_prog_run include/linux/filter.h:664 [inline]
 __bpf_trace_run kernel/trace/bpf_trace.c:2381 [inline]
 bpf_trace_run2+0x204/0x420 kernel/trace/bpf_trace.c:2420
 trace_kfree include/trace/events/kmem.h:94 [inline]
 kfree+0x291/0x380 mm/slub.c:4396
 sk_psock_free_link include/linux/skmsg.h:421 [inline]
 sock_map_del_link net/core/sock_map.c:158 [inline]
 sock_map_unref+0x3ac/0x5e0 net/core/sock_map.c:180
 sock_hash_update_common+0x915/0xa30 net/core/sock_map.c:1030
 sock_map_update_elem_sys+0x5a4/0x910 net/core/sock_map.c:581
 map_update_elem+0x53a/0x6f0 kernel/bpf/syscall.c:1641
 __sys_bpf+0x76f/0x810 kernel/bpf/syscall.c:5619
 __do_sys_bpf kernel/bpf/syscall.c:5738 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5736 [inline]
 __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5736
 do_syscall_64+0xfb/0x240
 entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7f9112c7dda9
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:00007f9113a9f0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 00007f9112dabf80 RCX: 00007f9112c7dda9
RDX: 0000000000000020 RSI: 0000000020000180 RDI: 0000000000000002
RBP: 00007f9112cca47a R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f9112dabf80 R15: 00007ffdf604c018
 </TASK>


---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.

syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.

If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title

If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)

If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report

If you want to undo deduplication, reply with:
#syz undup

Re: [syzbot] [net?] [bpf?] possible deadlock in sock_hash_delete_elem (2)

[syzbot]

syzbot has found a reproducer for the following issue on:

HEAD commit:    b2ff42c6d3ab Merge tag 'for-netdev' of https://git.kernel...
git tree:       bpf
console+strace: https://syzkaller.appspot.com/x/log.txt?x=157ea5e8980000
kernel config:  https://syzkaller.appspot.com/x/.config?x=98d5a8e00ed1044a
dashboard link: https://syzkaller.appspot.com/bug?extid=ec941d6e24f633a59172
compiler:       Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=145682f8980000
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=13c06aa0980000

Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/bbdf1d091619/disk-b2ff42c6.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/4bf7c5b24257/vmlinux-b2ff42c6.xz
kernel image: https://storage.googleapis.com/syzbot-assets/41fcb792fc43/bzImage-b2ff42c6.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com

============================================
WARNING: possible recursive locking detected
6.9.0-rc5-syzkaller-00171-gb2ff42c6d3ab #0 Not tainted
--------------------------------------------
syz-executor361/5090 is trying to acquire lock:
ffff888022c83260 (&htab->buckets[i].lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
ffff888022c83260 (&htab->buckets[i].lock){+...}-{2:2}, at: sock_hash_delete_elem+0x17c/0x400 net/core/sock_map.c:945

but task is already holding lock:
ffff88807b2af8f8 (&htab->buckets[i].lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
ffff88807b2af8f8 (&htab->buckets[i].lock){+...}-{2:2}, at: sock_hash_delete_elem+0x17c/0x400 net/core/sock_map.c:945

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&htab->buckets[i].lock);
  lock(&htab->buckets[i].lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

4 locks held by syz-executor361/5090:
 #0: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:329 [inline]
 #0: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:781 [inline]
 #0: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: map_delete_elem+0x388/0x5e0 kernel/bpf/syscall.c:1695
 #1: ffff88807b2af8f8 (&htab->buckets[i].lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 #1: ffff88807b2af8f8 (&htab->buckets[i].lock){+...}-{2:2}, at: sock_hash_delete_elem+0x17c/0x400 net/core/sock_map.c:945
 #2: ffff88801c2a4290 (&psock->link_lock){+...}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:356 [inline]
 #2: ffff88801c2a4290 (&psock->link_lock){+...}-{2:2}, at: sock_map_del_link net/core/sock_map.c:145 [inline]
 #2: ffff88801c2a4290 (&psock->link_lock){+...}-{2:2}, at: sock_map_unref+0xcc/0x5e0 net/core/sock_map.c:180
 #3: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:329 [inline]
 #3: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:781 [inline]
 #3: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: __bpf_trace_run kernel/trace/bpf_trace.c:2380 [inline]
 #3: ffffffff8e334d20 (rcu_read_lock){....}-{1:2}, at: bpf_trace_run2+0x114/0x420 kernel/trace/bpf_trace.c:2420

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor361 Not tainted 6.9.0-rc5-syzkaller-00171-gb2ff42c6d3ab #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
 check_deadlock kernel/locking/lockdep.c:3062 [inline]
 validate_chain+0x15c1/0x58e0 kernel/locking/lockdep.c:3856
 __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5754
 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline]
 _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178
 spin_lock_bh include/linux/spinlock.h:356 [inline]
 sock_hash_delete_elem+0x17c/0x400 net/core/sock_map.c:945
 bpf_prog_174bfe9d52de9121+0x4f/0x53
 bpf_dispatcher_nop_func include/linux/bpf.h:1234 [inline]
 __bpf_prog_run include/linux/filter.h:657 [inline]
 bpf_prog_run include/linux/filter.h:664 [inline]
 __bpf_trace_run kernel/trace/bpf_trace.c:2381 [inline]
 bpf_trace_run2+0x204/0x420 kernel/trace/bpf_trace.c:2420
 trace_kfree include/trace/events/kmem.h:94 [inline]
 kfree+0x2af/0x3a0 mm/slub.c:4377
 sk_psock_free_link include/linux/skmsg.h:421 [inline]
 sock_map_del_link net/core/sock_map.c:158 [inline]
 sock_map_unref+0x3ac/0x5e0 net/core/sock_map.c:180
 sock_hash_delete_elem+0x392/0x400 net/core/sock_map.c:949
 map_delete_elem+0x464/0x5e0 kernel/bpf/syscall.c:1696
 __sys_bpf+0x598/0x810 kernel/bpf/syscall.c:5651
 __do_sys_bpf kernel/bpf/syscall.c:5767 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5765 [inline]
 __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5765
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f1dbe94ce29
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 c1 17 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 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffff608ae88 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1dbe94ce29
RDX: 0000000000000020 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000000f4240 R08: 00000000000000a0 R09: 00000000000000a0
R10: 00000000000000a0 R11: 0000000000000246 R12: 0000000000000001
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>


---
If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

Re: [syzbot] [net?] [bpf?] possible deadlock in sock_hash_delete_elem (2)

[Hillf Danton]

On Fri, 26 Apr 2024 23:08:19 -0700
> syzbot has found a reproducer for the following issue on:
> 
> HEAD commit:    b2ff42c6d3ab Merge tag 'for-netdev' of https://git.kernel...
> git tree:       bpf
> C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=13c06aa0980000

#syz test https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git  b2ff42c6d3ab

--- x/net/core/sock_map.c
+++ y/net/core/sock_map.c
@@ -928,6 +928,7 @@ static void sock_hash_delete_from_link(s
 	spin_unlock_bh(&bucket->lock);
 }
 
+static DEFINE_PER_CPU(int, subclass);
 static long sock_hash_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map);
@@ -935,6 +936,7 @@ static long sock_hash_delete_elem(struct
 	struct bpf_shtab_bucket *bucket;
 	struct bpf_shtab_elem *elem;
 	int ret = -ENOENT;
+	int *class;
 
 	if (irqs_disabled())
 		return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
@@ -942,7 +944,10 @@ static long sock_hash_delete_elem(struct
 	hash = sock_hash_bucket_hash(key, key_size);
 	bucket = sock_hash_select_bucket(htab, hash);
 
-	spin_lock_bh(&bucket->lock);
+	local_bh_disable();
+	class = this_cpu_ptr(&subclass);
+	*class += 1;
+	spin_lock_nested(&bucket->lock, *class);
 	elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size);
 	if (elem) {
 		hlist_del_rcu(&elem->node);
@@ -950,6 +955,7 @@ static long sock_hash_delete_elem(struct
 		sock_hash_free_elem(htab, elem);
 		ret = 0;
 	}
+	*class -= 1;
 	spin_unlock_bh(&bucket->lock);
 	return ret;
 }
--

Re: [syzbot] [net?] [bpf?] possible deadlock in sock_hash_delete_elem (2)

[syzbot]

Hello,

syzbot has tested the proposed patch and the reproducer did not trigger any issue:

Reported-and-tested-by: syzbot+ec941d6e24f633a59172@syzkaller.appspotmail.com

Tested on:

commit:         b2ff42c6 Merge tag 'for-netdev' of https://git.kernel...
git tree:       https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
console output: https://syzkaller.appspot.com/x/log.txt?x=141a3d30980000
kernel config:  https://syzkaller.appspot.com/x/.config?x=98d5a8e00ed1044a
dashboard link: https://syzkaller.appspot.com/bug?extid=ec941d6e24f633a59172
compiler:       Debian clang version 15.0.6, GNU ld (GNU Binutils for Debian) 2.40
patch:          https://syzkaller.appspot.com/x/patch.diff?x=118d1937180000

Note: testing is done by a robot and is best-effort only.