syzbot


possible deadlock in smc_shutdown

Status: upstream: reported on 2024/07/06 09:00
Subsystems: net s390
[Documentation on labels]
Reported-by: syzbot+60e37f9e2f4575eab889@syzkaller.appspotmail.com
First crash: 95d, last: 72d
Discussions (1)
Title Replies (including bot) Last reply
[syzbot] [net?] [s390?] possible deadlock in smc_shutdown 0 (1) 2024/07/06 09:00

Sample crash report:
======================================================
WARNING: possible circular locking dependency detected
6.10.0-syzkaller-12381-gc33ffdb70cc6 #0 Not tainted
------------------------------------------------------
syz.1.2313/11912 is trying to acquire lock:
ffff88803faca358 (sk_lock-AF_SMC){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline]
ffff88803faca358 (sk_lock-AF_SMC){+.+.}-{0:0}, at: smc_shutdown+0x65/0x800 net/smc/af_smc.c:2921

but task is already holding lock:
ffff888025a78c70 (&nsock->tx_lock){+.+.}-{3:3}, at: sock_shutdown+0x16f/0x280 drivers/block/nbd.c:403

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #6 (&nsock->tx_lock){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:608 [inline]
       __mutex_lock+0x175/0x9c0 kernel/locking/mutex.c:752
       sock_shutdown+0x16f/0x280 drivers/block/nbd.c:403
       nbd_clear_sock drivers/block/nbd.c:1333 [inline]
       nbd_config_put+0x1e6/0x750 drivers/block/nbd.c:1357
       nbd_release+0xb7/0x190 drivers/block/nbd.c:1652
       blkdev_put_whole+0xad/0xf0 block/bdev.c:673
       bdev_release+0x496/0x6f0 block/bdev.c:1096
       blkdev_release+0x15/0x20 block/fops.c:638
       __fput+0x408/0xbb0 fs/file_table.c:422
       task_work_run+0x14e/0x250 kernel/task_work.c:222
       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:328 [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){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:608 [inline]
       __mutex_lock+0x175/0x9c0 kernel/locking/mutex.c:752
       refcount_dec_and_mutex_lock+0x51/0xe0 lib/refcount.c:118
       nbd_config_put+0x31/0x750 drivers/block/nbd.c:1340
       nbd_release+0xb7/0x190 drivers/block/nbd.c:1652
       blkdev_put_whole+0xad/0xf0 block/bdev.c:673
       bdev_release+0x496/0x6f0 block/bdev.c:1096
       blkdev_release+0x15/0x20 block/fops.c:638
       __fput+0x408/0xbb0 fs/file_table.c:422
       __fput_sync+0x47/0x50 fs/file_table.c:507
       __do_sys_close fs/open.c:1566 [inline]
       __se_sys_close fs/open.c:1551 [inline]
       __x64_sys_close+0x86/0x100 fs/open.c:1551
       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){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:608 [inline]
       __mutex_lock+0x175/0x9c0 kernel/locking/mutex.c:752
       bdev_open+0x41a/0xe40 block/bdev.c:897
       bdev_file_open_by_dev block/bdev.c:1011 [inline]
       bdev_file_open_by_dev+0x17d/0x210 block/bdev.c:986
       disk_scan_partitions+0x1ed/0x320 block/genhd.c:367
       device_add_disk+0xfbb/0x12d0 block/genhd.c:510
       pmem_attach_disk+0x9ab/0x13c0 drivers/nvdimm/pmem.c:576
       nd_pmem_probe+0x1a9/0x1f0 drivers/nvdimm/pmem.c:649
       nvdimm_bus_probe+0x169/0x5d0 drivers/nvdimm/bus.c:91
       call_driver_probe drivers/base/dd.c:578 [inline]
       really_probe+0x23e/0xa90 drivers/base/dd.c:656
       __driver_probe_device+0x1de/0x440 drivers/base/dd.c:798
       driver_probe_device+0x4c/0x1b0 drivers/base/dd.c:828
       __driver_attach+0x283/0x580 drivers/base/dd.c:1214
       bus_for_each_dev+0x13c/0x1d0 drivers/base/bus.c:368
       bus_add_driver+0x2e9/0x690 drivers/base/bus.c:673
       driver_register+0x15c/0x4b0 drivers/base/driver.c:246
       __nd_driver_register+0x103/0x1a0 drivers/nvdimm/bus.c:619
       do_one_initcall+0x128/0x700 init/main.c:1267
       do_initcall_level init/main.c:1329 [inline]
       do_initcalls init/main.c:1345 [inline]
       do_basic_setup init/main.c:1364 [inline]
       kernel_init_freeable+0x69d/0xca0 init/main.c:1578
       kernel_init+0x1c/0x2b0 init/main.c:1467
       ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
       ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

-> #3 (&nvdimm_namespace_key){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:608 [inline]
       __mutex_lock+0x175/0x9c0 kernel/locking/mutex.c:752
       device_lock include/linux/device.h:1009 [inline]
       uevent_show+0x188/0x3b0 drivers/base/core.c:2743
       dev_attr_show+0x53/0xe0 drivers/base/core.c:2437
       sysfs_kf_seq_show+0x23e/0x410 fs/sysfs/file.c:59
       seq_read_iter+0x4fa/0x12c0 fs/seq_file.c:230
       kernfs_fop_read_iter+0x41a/0x590 fs/kernfs/file.c:279
       new_sync_read fs/read_write.c:395 [inline]
       vfs_read+0x869/0xbd0 fs/read_write.c:476
       ksys_read+0x12f/0x260 fs/read_write.c:619
       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:1486
       kernfs_remove_by_name_ns+0xb2/0x130 fs/kernfs/dir.c:1694
       sysfs_remove_file include/linux/sysfs.h:773 [inline]
       device_remove_file drivers/base/core.c:3061 [inline]
       device_remove_file drivers/base/core.c:3057 [inline]
       device_del+0x381/0x9f0 drivers/base/core.c:3866
       unregister_netdevice_many_notify+0x103b/0x1e40 net/core/dev.c:11377
       unregister_netdevice_many net/core/dev.c:11405 [inline]
       unregister_netdevice_queue+0x307/0x3f0 net/core/dev.c:11280
       unregister_netdevice include/linux/netdevice.h:3129 [inline]
       unregister_netdev+0x1c/0x30 net/core/dev.c:11423
       slcan_close+0x76/0x1a0 drivers/net/can/slcan/slcan-core.c:866
       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:1696
       tty_release+0xe33/0x1420 drivers/tty/tty_io.c:1867
       __fput+0x408/0xbb0 fs/file_table.c:422
       task_work_run+0x14e/0x250 kernel/task_work.c:222
       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:328 [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){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:608 [inline]
       __mutex_lock+0x175/0x9c0 kernel/locking/mutex.c:752
       smc_vlan_by_tcpsk+0x251/0x620 net/smc/smc_core.c:1853
       __smc_connect+0x44d/0x4830 net/smc/af_smc.c:1522
       smc_connect+0x2fc/0x760 net/smc/af_smc.c:1702
       __sys_connect_file+0x15f/0x1a0 net/socket.c:2061
       __sys_connect+0x149/0x170 net/socket.c:2078
       __do_sys_connect net/socket.c:2088 [inline]
       __se_sys_connect net/socket.c:2085 [inline]
       __x64_sys_connect+0x72/0xb0 net/socket.c:2085
       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:3133 [inline]
       check_prevs_add kernel/locking/lockdep.c:3252 [inline]
       validate_chain kernel/locking/lockdep.c:3868 [inline]
       __lock_acquire+0x24ed/0x3cb0 kernel/locking/lockdep.c:5142
       lock_acquire kernel/locking/lockdep.c:5759 [inline]
       lock_acquire+0x1b1/0x560 kernel/locking/lockdep.c:5724
       lock_sock_nested+0x3a/0xf0 net/core/sock.c:3543
       lock_sock include/net/sock.h:1607 [inline]
       smc_shutdown+0x65/0x800 net/smc/af_smc.c:2921
       nbd_mark_nsock_dead+0xae/0x5d0 drivers/block/nbd.c:303
       sock_shutdown+0x17c/0x280 drivers/block/nbd.c:404
       nbd_clear_sock drivers/block/nbd.c:1333 [inline]
       nbd_clear_sock_ioctl drivers/block/nbd.c:1471 [inline]
       __nbd_ioctl drivers/block/nbd.c:1499 [inline]
       nbd_ioctl+0x49b/0xfd0 drivers/block/nbd.c:1559
       blkdev_ioctl+0x27c/0x6e0 block/ioctl.c:676
       vfs_ioctl fs/ioctl.c:51 [inline]
       __do_sys_ioctl fs/ioctl.c:907 [inline]
       __se_sys_ioctl fs/ioctl.c:893 [inline]
       __x64_sys_ioctl+0x193/0x220 fs/ioctl.c:893
       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.1.2313/11912:
 #0: ffff888021036998 (&nbd->config_lock){+.+.}-{3:3}, at: nbd_ioctl+0x151/0xfd0 drivers/block/nbd.c:1552
 #1: ffff888025a78c70 (&nsock->tx_lock){+.+.}-{3:3}, at: sock_shutdown+0x16f/0x280 drivers/block/nbd.c:403

stack backtrace:
CPU: 0 UID: 0 PID: 11912 Comm: syz.1.2313 Not tainted 6.10.0-syzkaller-12381-gc33ffdb70cc6 #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:93 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:119
 check_noncircular+0x31a/0x400 kernel/locking/lockdep.c:2186
 check_prev_add kernel/locking/lockdep.c:3133 [inline]
 check_prevs_add kernel/locking/lockdep.c:3252 [inline]
 validate_chain kernel/locking/lockdep.c:3868 [inline]
 __lock_acquire+0x24ed/0x3cb0 kernel/locking/lockdep.c:5142
 lock_acquire kernel/locking/lockdep.c:5759 [inline]
 lock_acquire+0x1b1/0x560 kernel/locking/lockdep.c:5724
 lock_sock_nested+0x3a/0xf0 net/core/sock.c:3543
 lock_sock include/net/sock.h:1607 [inline]
 smc_shutdown+0x65/0x800 net/smc/af_smc.c:2921
 nbd_mark_nsock_dead+0xae/0x5d0 drivers/block/nbd.c:303
 sock_shutdown+0x17c/0x280 drivers/block/nbd.c:404
 nbd_clear_sock drivers/block/nbd.c:1333 [inline]
 nbd_clear_sock_ioctl drivers/block/nbd.c:1471 [inline]
 __nbd_ioctl drivers/block/nbd.c:1499 [inline]
 nbd_ioctl+0x49b/0xfd0 drivers/block/nbd.c:1559
 blkdev_ioctl+0x27c/0x6e0 block/ioctl.c:676
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:907 [inline]
 __se_sys_ioctl fs/ioctl.c:893 [inline]
 __x64_sys_ioctl+0x193/0x220 fs/ioctl.c:893
 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: 0033:0x7f67b0775f19
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:00007f67b14b0048 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007f67b0905f60 RCX: 00007f67b0775f19
RDX: 0000000000000000 RSI: 000000000000ab04 RDI: 0000000000000003
RBP: 00007f67b07e4e68 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f67b0905f60 R15: 00007fff57b266b8
 </TASK>
block nbd1: shutting down sockets

Crashes (3):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2024/07/24 22:24 upstream c33ffdb70cc6 d1a1b0ca .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream possible deadlock in smc_shutdown
2024/07/02 08:57 upstream 1dfe225e9af5 dc6047a3 .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream possible deadlock in smc_shutdown
2024/07/21 15:19 upstream 2c9b3512402e b88348e9 .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream-386 possible deadlock in smc_shutdown
* Struck through repros no longer work on HEAD.