syzbot


possible deadlock in smc_sendmsg

Status: upstream: reported on 2025/02/22 21:28
Subsystems: net s390
[Documentation on labels]
Reported-by: syzbot+6cc62f8d77a830dba3a7@syzkaller.appspotmail.com
First crash: 4d15h, last: 15h42m
Discussions (1)
Title Replies (including bot) Last reply
[syzbot] [net?] [s390?] possible deadlock in smc_sendmsg 0 (1) 2025/02/22 21:28

Sample crash report:
block nbd4: NBD_DISCONNECT
======================================================
WARNING: possible circular locking dependency detected
6.14.0-rc3-syzkaller-00060-g6537cfb395f3 #0 Not tainted
------------------------------------------------------
syz.4.3048/15507 is trying to acquire lock:
ffff88804ed2bbd8 (sk_lock-AF_SMC){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1624 [inline]
ffff88804ed2bbd8 (sk_lock-AF_SMC){+.+.}-{0:0}, at: smc_sendmsg+0x47/0x520 net/smc/af_smc.c:2775

but task is already holding lock:
ffff888028f74e70 (&nsock->tx_lock){+.+.}-{4:4}, at: send_disconnects drivers/block/nbd.c:1394 [inline]
ffff888028f74e70 (&nsock->tx_lock){+.+.}-{4:4}, at: nbd_disconnect+0x321/0x540 drivers/block/nbd.c:1410

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #6 (&nsock->tx_lock){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730
       sock_shutdown+0x16f/0x280 drivers/block/nbd.c:410
       nbd_clear_sock drivers/block/nbd.c:1416 [inline]
       nbd_config_put+0x1e6/0x750 drivers/block/nbd.c:1440
       nbd_release+0xb7/0x190 drivers/block/nbd.c:1735
       blkdev_put_whole+0xad/0xf0 block/bdev.c:679
       bdev_release+0x47e/0x6d0 block/bdev.c:1102
       blkdev_release+0x15/0x20 block/fops.c:660
       __fput+0x3ff/0xb70 fs/file_table.c:464
       task_work_run+0x14e/0x250 kernel/task_work.c:227
       resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
       exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
       exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
       __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
       syscall_exit_to_user_mode+0x27b/0x2a0 kernel/entry/common.c:218
       do_syscall_64+0xda/0x250 arch/x86/entry/common.c:89
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #5 (&nbd->config_lock){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730
       refcount_dec_and_mutex_lock+0x51/0xc0 lib/refcount.c:118
       nbd_config_put+0x31/0x750 drivers/block/nbd.c:1423
       nbd_release+0xb7/0x190 drivers/block/nbd.c:1735
       blkdev_put_whole+0xad/0xf0 block/bdev.c:679
       bdev_release+0x47e/0x6d0 block/bdev.c:1102
       blkdev_release+0x15/0x20 block/fops.c:660
       __fput+0x3ff/0xb70 fs/file_table.c:464
       __fput_sync+0xa1/0xc0 fs/file_table.c:550
       __do_sys_close fs/open.c:1580 [inline]
       __se_sys_close fs/open.c:1565 [inline]
       __x64_sys_close+0x86/0x100 fs/open.c:1565
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #4 (&disk->open_mutex){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730
       bdev_open+0x41a/0xe20 block/bdev.c:903
       bdev_file_open_by_dev block/bdev.c:1017 [inline]
       bdev_file_open_by_dev+0x17d/0x210 block/bdev.c:992
       disk_scan_partitions+0x1ed/0x320 block/genhd.c:374
       add_disk_fwnode+0x1006/0x1320 block/genhd.c:526
       pmem_attach_disk+0x9a1/0x13e0 drivers/nvdimm/pmem.c:576
       nd_pmem_probe+0x1a9/0x1f0 drivers/nvdimm/pmem.c:649
       nvdimm_bus_probe+0x169/0x5d0 drivers/nvdimm/bus.c:94
       call_driver_probe drivers/base/dd.c:579 [inline]
       really_probe+0x23e/0xa90 drivers/base/dd.c:658
       __driver_probe_device+0x1de/0x440 drivers/base/dd.c:800
       driver_probe_device+0x4c/0x1b0 drivers/base/dd.c:830
       __driver_attach+0x283/0x580 drivers/base/dd.c:1216
       bus_for_each_dev+0x13c/0x1d0 drivers/base/bus.c:370
       bus_add_driver+0x2e9/0x690 drivers/base/bus.c:678
       driver_register+0x15c/0x4b0 drivers/base/driver.c:249
       __nd_driver_register+0x103/0x1a0 drivers/nvdimm/bus.c:622
       do_one_initcall+0x128/0x700 init/main.c:1257
       do_initcall_level init/main.c:1319 [inline]
       do_initcalls init/main.c:1335 [inline]
       do_basic_setup init/main.c:1354 [inline]
       kernel_init_freeable+0x5c7/0x900 init/main.c:1568
       kernel_init+0x1c/0x2b0 init/main.c:1457
       ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:148
       ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

-> #3 (&nvdimm_namespace_key){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730
       device_lock include/linux/device.h:1030 [inline]
       uevent_show+0x188/0x3b0 drivers/base/core.c:2729
       dev_attr_show+0x53/0xe0 drivers/base/core.c:2423
       sysfs_kf_seq_show+0x23e/0x410 fs/sysfs/file.c:59
       seq_read_iter+0x4f4/0x12b0 fs/seq_file.c:230
       kernfs_fop_read_iter+0x414/0x580 fs/kernfs/file.c:279
       new_sync_read fs/read_write.c:484 [inline]
       vfs_read+0x886/0xbf0 fs/read_write.c:565
       ksys_read+0x12b/0x250 fs/read_write.c:708
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #2 (kn->active#5){++++}-{0:0}:
       kernfs_drain+0x48f/0x590 fs/kernfs/dir.c:500
       __kernfs_remove+0x281/0x670 fs/kernfs/dir.c:1487
       kernfs_remove_by_name_ns+0xb2/0x130 fs/kernfs/dir.c:1695
       sysfs_remove_file include/linux/sysfs.h:794 [inline]
       device_remove_file drivers/base/core.c:3047 [inline]
       device_remove_file drivers/base/core.c:3043 [inline]
       device_del+0x381/0x9f0 drivers/base/core.c:3852
       unregister_netdevice_many_notify+0x13aa/0x1f30 net/core/dev.c:11838
       unregister_netdevice_many net/core/dev.c:11866 [inline]
       unregister_netdevice_queue+0x307/0x3f0 net/core/dev.c:11736
       unregister_netdevice include/linux/netdevice.h:3335 [inline]
       unregister_netdev+0x21/0x30 net/core/dev.c:11886
       sixpack_close+0x1e7/0x2f0 drivers/net/hamradio/6pack.c:661
       tty_ldisc_close+0x111/0x1a0 drivers/tty/tty_ldisc.c:455
       tty_ldisc_kill+0x8e/0x150 drivers/tty/tty_ldisc.c:613
       tty_ldisc_release+0x116/0x2a0 drivers/tty/tty_ldisc.c:781
       tty_release_struct+0x23/0xe0 drivers/tty/tty_io.c:1690
       tty_release+0xe25/0x1410 drivers/tty/tty_io.c:1861
       __fput+0x3ff/0xb70 fs/file_table.c:464
       task_work_run+0x14e/0x250 kernel/task_work.c:227
       resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
       exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
       exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
       __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
       syscall_exit_to_user_mode+0x27b/0x2a0 kernel/entry/common.c:218
       do_syscall_64+0xda/0x250 arch/x86/entry/common.c:89
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #1 (rtnl_mutex){+.+.}-{4:4}:
       __mutex_lock_common kernel/locking/mutex.c:585 [inline]
       __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730
       smc_vlan_by_tcpsk+0x251/0x620 net/smc/smc_core.c:1908
       __smc_connect+0x44d/0x4890 net/smc/af_smc.c:1520
       smc_connect+0x2fc/0x760 net/smc/af_smc.c:1696
       __sys_connect_file+0x13e/0x1a0 net/socket.c:2045
       __sys_connect+0x14f/0x170 net/socket.c:2064
       __do_sys_connect net/socket.c:2070 [inline]
       __se_sys_connect net/socket.c:2067 [inline]
       __x64_sys_connect+0x72/0xb0 net/socket.c:2067
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

-> #0 (sk_lock-AF_SMC){+.+.}-{0:0}:
       check_prev_add kernel/locking/lockdep.c:3163 [inline]
       check_prevs_add kernel/locking/lockdep.c:3282 [inline]
       validate_chain kernel/locking/lockdep.c:3906 [inline]
       __lock_acquire+0x249e/0x3c40 kernel/locking/lockdep.c:5228
       lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5851
       lock_sock_nested+0x3a/0xf0 net/core/sock.c:3645
       lock_sock include/net/sock.h:1624 [inline]
       smc_sendmsg+0x47/0x520 net/smc/af_smc.c:2775
       sock_sendmsg_nosec net/socket.c:718 [inline]
       __sock_sendmsg net/socket.c:733 [inline]
       sock_sendmsg+0x3d3/0x490 net/socket.c:756
       __sock_xmit+0x1e8/0x4f0 drivers/block/nbd.c:574
       sock_xmit drivers/block/nbd.c:602 [inline]
       send_disconnects drivers/block/nbd.c:1395 [inline]
       nbd_disconnect+0x390/0x540 drivers/block/nbd.c:1410
       __nbd_ioctl drivers/block/nbd.c:1580 [inline]
       nbd_ioctl+0x8d1/0xd60 drivers/block/nbd.c:1642
       blkdev_ioctl+0x276/0x6d0 block/ioctl.c:693
       vfs_ioctl fs/ioctl.c:51 [inline]
       __do_sys_ioctl fs/ioctl.c:906 [inline]
       __se_sys_ioctl fs/ioctl.c:892 [inline]
       __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
       do_syscall_x64 arch/x86/entry/common.c:52 [inline]
       do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

other info that might help us debug this:

Chain exists of:
  sk_lock-AF_SMC --> &nbd->config_lock --> &nsock->tx_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&nsock->tx_lock);
                               lock(&nbd->config_lock);
                               lock(&nsock->tx_lock);
  lock(sk_lock-AF_SMC);

 *** DEADLOCK ***

2 locks held by syz.4.3048/15507:
 #0: ffff888026642198 (&nbd->config_lock){+.+.}-{4:4}, at: nbd_ioctl+0x151/0xd60 drivers/block/nbd.c:1635
 #1: ffff888028f74e70 (&nsock->tx_lock){+.+.}-{4:4}, at: send_disconnects drivers/block/nbd.c:1394 [inline]
 #1: ffff888028f74e70 (&nsock->tx_lock){+.+.}-{4:4}, at: nbd_disconnect+0x321/0x540 drivers/block/nbd.c:1410

stack backtrace:
CPU: 1 UID: 0 PID: 15507 Comm: syz.4.3048 Not tainted 6.14.0-rc3-syzkaller-00060-g6537cfb395f3 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 print_circular_bug+0x490/0x760 kernel/locking/lockdep.c:2076
 check_noncircular+0x31a/0x400 kernel/locking/lockdep.c:2208
 check_prev_add kernel/locking/lockdep.c:3163 [inline]
 check_prevs_add kernel/locking/lockdep.c:3282 [inline]
 validate_chain kernel/locking/lockdep.c:3906 [inline]
 __lock_acquire+0x249e/0x3c40 kernel/locking/lockdep.c:5228
 lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5851
 lock_sock_nested+0x3a/0xf0 net/core/sock.c:3645
 lock_sock include/net/sock.h:1624 [inline]
 smc_sendmsg+0x47/0x520 net/smc/af_smc.c:2775
 sock_sendmsg_nosec net/socket.c:718 [inline]
 __sock_sendmsg net/socket.c:733 [inline]
 sock_sendmsg+0x3d3/0x490 net/socket.c:756
 __sock_xmit+0x1e8/0x4f0 drivers/block/nbd.c:574
 sock_xmit drivers/block/nbd.c:602 [inline]
 send_disconnects drivers/block/nbd.c:1395 [inline]
 nbd_disconnect+0x390/0x540 drivers/block/nbd.c:1410
 __nbd_ioctl drivers/block/nbd.c:1580 [inline]
 nbd_ioctl+0x8d1/0xd60 drivers/block/nbd.c:1642
 blkdev_ioctl+0x276/0x6d0 block/ioctl.c:693
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:906 [inline]
 __se_sys_ioctl fs/ioctl.c:892 [inline]
 __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f0b5198cde9
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 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 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f0b52883038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007f0b51ba6080 RCX: 00007f0b5198cde9
RDX: 0000000000000000 RSI: 000000000000ab08 RDI: 0000000000000006
RBP: 00007f0b51a0e2a0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007f0b51ba6080 R15: 00007ffce7c4c0d8
 </TASK>
block nbd4: Send disconnect failed -107
block nbd4: Disconnected due to user request.
block nbd4: shutting down sockets

Crashes (2):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2025/02/18 21:18 upstream 6537cfb395f3 c37c7249 .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream possible deadlock in smc_sendmsg
2025/02/22 21:02 upstream 5cf80612d3f7 d34966d1 .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream-386 possible deadlock in smc_sendmsg
* Struck through repros no longer work on HEAD.