syzbot


possible deadlock in deactivate_slab

Status: upstream: reported on 2024/06/07 01:17
Subsystems: bpf
[Documentation on labels]
Reported-by: syzbot+a4acbb99845d381e5e2f@syzkaller.appspotmail.com
First crash: 12d, last: 12d
Discussions (1)
Title Replies (including bot) Last reply
[syzbot] [bpf?] possible deadlock in deactivate_slab 0 (1) 2024/06/07 01:17
Similar bugs (1)
Kernel Title Repro Cause bisect Fix bisect Count Last Reported Patched Status
linux-6.1 possible deadlock in deactivate_slab 1 41d 41d 0/3 upstream: reported on 2024/05/04 06:46

Sample crash report:
======================================================
WARNING: possible circular locking dependency detected
6.10.0-rc2-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor.1/23904 is trying to acquire lock:
ffff888040002018 (&n->list_lock){-.-.}-{2:2}, at: deactivate_slab+0x2b4/0x4a0 mm/slub.c:2948

but task is already holding lock:
ffff88802792d9f8 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem+0xc7/0xdb0 kernel/bpf/lpm_trie.c:333

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #1 (&trie->lock){-.-.}-{2:2}:
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
       _raw_spin_lock_irqsave+0x3a/0x60 kernel/locking/spinlock.c:162
       trie_delete_elem+0xb0/0x820 kernel/bpf/lpm_trie.c:462
       0xffffffffa0001fd2
       bpf_dispatcher_nop_func include/linux/bpf.h:1243 [inline]
       __bpf_prog_run include/linux/filter.h:691 [inline]
       bpf_prog_run include/linux/filter.h:698 [inline]
       __bpf_trace_run kernel/trace/bpf_trace.c:2403 [inline]
       bpf_trace_run2+0x231/0x590 kernel/trace/bpf_trace.c:2444
       trace_contention_end.constprop.0+0xea/0x170 include/trace/events/lock.h:122
       __pv_queued_spin_lock_slowpath+0x28e/0xcc0 kernel/locking/qspinlock.c:557
       pv_queued_spin_lock_slowpath arch/x86/include/asm/paravirt.h:584 [inline]
       queued_spin_lock_slowpath arch/x86/include/asm/qspinlock.h:51 [inline]
       queued_spin_lock include/asm-generic/qspinlock.h:114 [inline]
       do_raw_spin_lock+0x210/0x2c0 kernel/locking/spinlock_debug.c:116
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:111 [inline]
       _raw_spin_lock_irqsave+0x42/0x60 kernel/locking/spinlock.c:162
       get_partial_node.part.0+0x20/0x350 mm/slub.c:2675
       get_partial_node mm/slub.c:2672 [inline]
       get_any_partial mm/slub.c:2759 [inline]
       get_partial mm/slub.c:2793 [inline]
       ___slab_alloc+0xd36/0x1870 mm/slub.c:3646
       __slab_alloc.constprop.0+0x56/0xb0 mm/slub.c:3756
       __slab_alloc_node mm/slub.c:3809 [inline]
       slab_alloc_node mm/slub.c:3988 [inline]
       kmem_cache_alloc_noprof+0x2ae/0x2f0 mm/slub.c:4007
       getname_flags.part.0+0x50/0x4f0 fs/namei.c:139
       getname_flags include/linux/audit.h:322 [inline]
       getname+0x8f/0xe0 fs/namei.c:218
       do_sys_openat2+0x104/0x1e0 fs/open.c:1399
       do_sys_open fs/open.c:1420 [inline]
       __do_sys_openat fs/open.c:1436 [inline]
       __se_sys_openat fs/open.c:1431 [inline]
       __x64_sys_openat+0x175/0x210 fs/open.c:1431
       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 (&n->list_lock){-.-.}-{2:2}:
       check_prev_add kernel/locking/lockdep.c:3134 [inline]
       check_prevs_add kernel/locking/lockdep.c:3253 [inline]
       validate_chain kernel/locking/lockdep.c:3869 [inline]
       __lock_acquire+0x2478/0x3b30 kernel/locking/lockdep.c:5137
       lock_acquire kernel/locking/lockdep.c:5754 [inline]
       lock_acquire+0x1b1/0x560 kernel/locking/lockdep.c:5719
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
       _raw_spin_lock_irqsave+0x3a/0x60 kernel/locking/spinlock.c:162
       deactivate_slab+0x2b4/0x4a0 mm/slub.c:2948
       ___slab_alloc+0xc0b/0x1870 mm/slub.c:3591
       __slab_alloc.constprop.0+0x56/0xb0 mm/slub.c:3756
       __slab_alloc_node mm/slub.c:3809 [inline]
       slab_alloc_node mm/slub.c:3988 [inline]
       __do_kmalloc_node mm/slub.c:4120 [inline]
       __kmalloc_node_noprof+0x36c/0x450 mm/slub.c:4128
       kmalloc_node_noprof include/linux/slab.h:681 [inline]
       bpf_map_kmalloc_node+0x98/0x4a0 kernel/bpf/syscall.c:422
       lpm_trie_node_alloc kernel/bpf/lpm_trie.c:299 [inline]
       trie_update_elem+0x1ef/0xdb0 kernel/bpf/lpm_trie.c:342
       bpf_map_update_value+0x2c1/0x6c0 kernel/bpf/syscall.c:203
       generic_map_update_batch+0x454/0x5f0 kernel/bpf/syscall.c:1889
       bpf_map_do_batch+0x615/0x6e0 kernel/bpf/syscall.c:5196
       __sys_bpf+0x18cb/0x5830 kernel/bpf/syscall.c:5751
       __do_sys_bpf kernel/bpf/syscall.c:5794 [inline]
       __se_sys_bpf kernel/bpf/syscall.c:5792 [inline]
       __ia32_sys_bpf+0x76/0xe0 kernel/bpf/syscall.c:5792
       do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline]
       __do_fast_syscall_32+0x73/0x120 arch/x86/entry/common.c:386
       do_fast_syscall_32+0x32/0x80 arch/x86/entry/common.c:411
       entry_SYSENTER_compat_after_hwframe+0x84/0x8e

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&trie->lock);
                               lock(&n->list_lock);
                               lock(&trie->lock);
  lock(&n->list_lock);

 *** DEADLOCK ***

2 locks held by syz-executor.1/23904:
 #0: ffffffff8dbb5160 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:329 [inline]
 #0: ffffffff8dbb5160 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:781 [inline]
 #0: ffffffff8dbb5160 (rcu_read_lock){....}-{1:2}, at: bpf_map_update_value+0x24b/0x6c0 kernel/bpf/syscall.c:202
 #1: ffff88802792d9f8 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem+0xc7/0xdb0 kernel/bpf/lpm_trie.c:333

stack backtrace:
CPU: 3 PID: 23904 Comm: syz-executor.1 Not tainted 6.10.0-rc2-syzkaller #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:114
 check_noncircular+0x31a/0x400 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 kernel/locking/lockdep.c:3869 [inline]
 __lock_acquire+0x2478/0x3b30 kernel/locking/lockdep.c:5137
 lock_acquire kernel/locking/lockdep.c:5754 [inline]
 lock_acquire+0x1b1/0x560 kernel/locking/lockdep.c:5719
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x3a/0x60 kernel/locking/spinlock.c:162
 deactivate_slab+0x2b4/0x4a0 mm/slub.c:2948
 ___slab_alloc+0xc0b/0x1870 mm/slub.c:3591
 __slab_alloc.constprop.0+0x56/0xb0 mm/slub.c:3756
 __slab_alloc_node mm/slub.c:3809 [inline]
 slab_alloc_node mm/slub.c:3988 [inline]
 __do_kmalloc_node mm/slub.c:4120 [inline]
 __kmalloc_node_noprof+0x36c/0x450 mm/slub.c:4128
 kmalloc_node_noprof include/linux/slab.h:681 [inline]
 bpf_map_kmalloc_node+0x98/0x4a0 kernel/bpf/syscall.c:422
 lpm_trie_node_alloc kernel/bpf/lpm_trie.c:299 [inline]
 trie_update_elem+0x1ef/0xdb0 kernel/bpf/lpm_trie.c:342
 bpf_map_update_value+0x2c1/0x6c0 kernel/bpf/syscall.c:203
 generic_map_update_batch+0x454/0x5f0 kernel/bpf/syscall.c:1889
 bpf_map_do_batch+0x615/0x6e0 kernel/bpf/syscall.c:5196
 __sys_bpf+0x18cb/0x5830 kernel/bpf/syscall.c:5751
 __do_sys_bpf kernel/bpf/syscall.c:5794 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5792 [inline]
 __ia32_sys_bpf+0x76/0xe0 kernel/bpf/syscall.c:5792
 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline]
 __do_fast_syscall_32+0x73/0x120 arch/x86/entry/common.c:386
 do_fast_syscall_32+0x32/0x80 arch/x86/entry/common.c:411
 entry_SYSENTER_compat_after_hwframe+0x84/0x8e
RIP: 0023:0xf731f579
Code: b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 00 00 00 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d b4 26 00 00 00 00 8d b4 26 00 00 00 00
RSP: 002b:00000000f5f115ac EFLAGS: 00000292 ORIG_RAX: 0000000000000165
RAX: ffffffffffffffda RBX: 000000000000001a RCX: 0000000020000100
RDX: 0000000000000038 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000292 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>
----------------
Code disassembly (best guess), 2 bytes skipped:
   0:	10 06                	adc    %al,(%rsi)
   2:	03 74 b4 01          	add    0x1(%rsp,%rsi,4),%esi
   6:	10 07                	adc    %al,(%rdi)
   8:	03 74 b0 01          	add    0x1(%rax,%rsi,4),%esi
   c:	10 08                	adc    %cl,(%rax)
   e:	03 74 d8 01          	add    0x1(%rax,%rbx,8),%esi
  1e:	00 51 52             	add    %dl,0x52(%rcx)
  21:	55                   	push   %rbp
  22:	89 e5                	mov    %esp,%ebp
  24:	0f 34                	sysenter
  26:	cd 80                	int    $0x80
* 28:	5d                   	pop    %rbp <-- trapping instruction
  29:	5a                   	pop    %rdx
  2a:	59                   	pop    %rcx
  2b:	c3                   	ret
  2c:	90                   	nop
  2d:	90                   	nop
  2e:	90                   	nop
  2f:	90                   	nop
  30:	8d b4 26 00 00 00 00 	lea    0x0(%rsi,%riz,1),%esi
  37:	8d b4 26 00 00 00 00 	lea    0x0(%rsi,%riz,1),%esi

Crashes (1):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2024/06/03 01:13 upstream c3f38fa61af7 c2e07261 .config console log report info [disk image (non-bootable)] [vmlinux] [kernel image] ci-qemu-upstream-386 possible deadlock in deactivate_slab
* Struck through repros no longer work on HEAD.