INFO: rcu detected stall in perf_event_open

Status: fixed on 2025/10/06 10:09
Reported-by: syzbot+0c40b0eae227145b6069@syzkaller.appspotmail.com
Fix commit: b41642c87716 rcu: Fix rcu_read_unlock() deadloop due to IRQ work
First crash: 381d, last: 367d
Fix bisection: fixed by (bisect log) :
commit e7a375453cca2b8a0d2fa1b82b913f3fed7c0507
Author: Joel Fernandes <joelagnelf@nvidia.com>
Date: Tue Jul 8 14:22:19 2025 +0000

  rcu: Fix rcu_read_unlock() deadloop due to IRQ work

  
▶ ▼ Bug presence (1)
Date Name Commit Repro Result
2025/09/07 upstream (ToT) b236920731dd C Didn't crash
▶ ▼ Similar bugs (17)
Kernel Title Rank 🛈 Repro Cause bisect Fix bisect Count Last Reported Patched Status
linux-5.15 INFO: rcu detected stall in sys_perf_event_open (2) origin:lts-only 1 syz, C error 119 5d03h 963d 0/3 upstream: reported C repro on 2024/01/09 18:19
upstream BUG: soft lockup in perf_event_open (2) net prio:high 1 syz 10 65d 175d 0/29 upstream: reported syz repro on 2026/03/08 04:57
linux-6.6 INFO: rcu detected stall in perf_event_open (2) origin:lts-only 1 syz, C inconclusive 102 11h21m 293d 0/2 upstream: reported C repro on 2025/11/10 01:14
upstream INFO: rcu detected stall in perf_event_open (2) perf 1 1 1797d 1797d 0/29 auto-closed as invalid on 2021/11/26 20:49
upstream INFO: rcu detected stall in perf_event_open kernel 1 1 1894d 1894d 0/29 auto-closed as invalid on 2021/09/21 01:14
linux-6.1 INFO: rcu detected stall in sys_perf_event_open (2) origin:lts-only 1 syz, C done 104 2d14h 706d 0/3 upstream: reported C repro on 2024/09/23 05:55
upstream BUG: soft lockup in perf_event_open trace bpf 1 2 431d 427d 0/29 auto-obsoleted due to no activity on 2025/09/23 09:29
upstream INFO: rcu detected stall in __se_sys_perf_event_open perf 1 1 2248d 2248d 0/29 auto-closed as invalid on 2020/10/02 02:08
upstream INFO: rcu detected stall in sys_perf_event_open (3) perf 1 1 2426d 2426d 0/29 closed as invalid on 2020/01/08 05:23
upstream INFO: rcu detected stall in sys_perf_event_open (4) perf 1 1 2426d 2425d 0/29 closed as invalid on 2020/01/09 08:13
upstream INFO: rcu detected stall in sys_perf_event_open (2) perf 1 8 2461d 2462d 0/29 closed as invalid on 2019/12/04 14:14
linux-6.1 INFO: rcu detected stall in sys_perf_event_open 1 1 810d 810d 0/3 auto-obsoleted due to no activity on 2024/09/19 01:45
linux-5.15 INFO: rcu detected stall in sys_perf_event_open 1 1 1229d 1229d 0/3 auto-obsoleted due to no activity on 2023/08/17 04:33
upstream INFO: rcu detected stall in sys_perf_event_open perf 1 1 2905d 2903d 0/29 auto-closed as invalid on 2019/03/14 17:19
android-5-15 BUG: soft lockup in sys_perf_event_open 1 1 846d 846d 0/2 auto-obsoleted due to no activity on 2024/08/04 07:07
upstream BUG: soft lockup in sys_perf_event_open perf 1 1 821d 817d 0/29 auto-obsoleted due to no activity on 2024/08/29 01:52
upstream BUG: soft lockup in sys_perf_event_open (2) kvm fs 1 6 589d 696d 0/29 auto-obsoleted due to no activity on 2025/04/18 04:31

Sample crash report:
rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
rcu: 	1-....: (4 ticks this GP) idle=1604/1/0x4000000000000000 softirq=13664/13665 fqs=5247
rcu: 	         hardirqs   softirqs   csw/system
rcu: 	 number: 13093390          0            0
rcu: 	cputime:     5589      46937            0   ==> 52510(ms)
rcu: 	(detected by 0, t=10502 jiffies, g=10245, q=3222 ncpus=2)
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 6125 Comm: syz.0.154 Not tainted 6.6.102-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:match_held_lock+0xc/0xb0 kernel/locking/lockdep.c:5203
Code: c7 c6 a0 b8 aa 8a e8 83 be e2 f6 0f 0b eb b6 e8 ba f9 ff ff 66 2e 0f 1f 84 00 00 00 00 00 b9 01 00 00 00 48 39 77 10 74 6c 53 <81> 7f 20 00 00 20 00 72 5f 48 8b 46 08 48 85 c0 75 17 48 89 fb 48
RSP: 0018:ffffc900001efc68 EFLAGS: 00000006
RAX: 0000000000000009 RBX: ffff88802c9fbc00 RCX: 0000000000000001
RDX: ffff88802c9fbc00 RSI: ffffffff8cd2fbe0 RDI: ffff88802c9fc758
RBP: 00000000ffffffff R08: dffffc0000000000 R09: 1ffffffff21b46a0
R10: dffffc0000000000 R11: fffffbfff21b46a1 R12: 0000000000000003
R13: 0000000000000046 R14: ffffffff8cd2fbe0 R15: ffff88802c9fc758
FS:  0000555587b5c500(0000) GS:ffff8880b8f00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2d763fff CR3: 000000007c25c000 CR4: 00000000003506e0
Call Trace:
 <IRQ>
 __lock_is_held kernel/locking/lockdep.c:5495 [inline]
 lock_is_held_type+0xaa/0x190 kernel/locking/lockdep.c:5825
 __perf_output_begin kernel/events/ring_buffer.c:170 [inline]
 perf_output_begin_forward+0x1a8/0xa20 kernel/events/ring_buffer.c:273
 __perf_event_output kernel/events/core.c:7974 [inline]
 perf_event_output_forward+0x22b/0x3a0 kernel/events/core.c:7992
 __perf_event_overflow+0x447/0x630 kernel/events/core.c:9717
 perf_swevent_overflow kernel/events/core.c:9793 [inline]
 perf_swevent_event+0x2f5/0x5c0 kernel/events/core.c:-1
 perf_tp_event+0x4f9/0x13a0 kernel/events/core.c:10343
 perf_trace_run_bpf_submit+0xf4/0x1c0 kernel/events/core.c:10267
 perf_trace_preemptirq_template+0x281/0x340 include/trace/events/preemptirq.h:14
 trace_irq_enable+0xbf/0xe0 include/trace/events/preemptirq.h:40
 trace_hardirqs_on+0x18/0x40 kernel/trace/trace_preemptirq.c:56
 asm_sysvec_irq_work+0x1a/0x20 arch/x86/include/asm/idtentry.h:723
RIP: 0010:rcu_read_unlock_special+0x88/0x4c0 kernel/rcu/tree_plugin.h:682
Code: f1 f1 f1 00 f2 f2 f2 4a 89 04 2b 66 42 c7 44 2b 09 f3 f3 42 c6 44 2b 0b f3 65 44 8b 35 39 58 93 7e 41 f7 c6 00 00 f0 00 74 45 <48> c7 44 24 40 0e 36 e0 45 4a c7 04 2b 00 00 00 00 66 42 c7 44 2b
RSP: 0018:ffffc900001f0500 EFLAGS: 00000206
RAX: 2faca621a8eac400 RBX: 1ffff9200003e0a8 RCX: 2faca621a8eac400
RDX: dffffc0000000000 RSI: ffffffff8aaab9c0 RDI: ffffffff8afc66c0
RBP: ffffc900001f0600 R08: ffffffff90da35c7 R09: 1ffffffff21b46b8
R10: dffffc0000000000 R11: fffffbfff21b46b9 R12: ffffffff8cd35400
R13: dffffc0000000000 R14: 0000000000000246 R15: 0000000000000002
 __rcu_read_unlock+0x7c/0xd0 kernel/rcu/tree_plugin.h:426
 rcu_read_unlock include/linux/rcupdate.h:818 [inline]
 dev_queue_xmit_nit+0xa84/0xbb0 net/core/dev.c:2376
 xmit_one net/core/dev.c:3603 [inline]
 dev_hard_start_xmit+0x148/0x740 net/core/dev.c:3623
 sch_direct_xmit+0x252/0x4a0 net/sched/sch_generic.c:342
 __dev_xmit_skb net/core/dev.c:3844 [inline]
 __dev_queue_xmit+0x173e/0x35a0 net/core/dev.c:4379
 lapb_data_transmit+0x8a/0xa0 net/lapb/lapb_iface.c:447
 lapb_transmit_buffer+0x163/0x200 net/lapb/lapb_out.c:149
 lapb_t1timer_expiry+0x699/0xab0 net/lapb/lapb_timer.c:-1
 call_timer_fn+0x16e/0x530 kernel/time/timer.c:1700
 expire_timers kernel/time/timer.c:1751 [inline]
 __run_timers+0x52d/0x7d0 kernel/time/timer.c:2022
 run_timer_softirq+0x67/0xf0 kernel/time/timer.c:2035
 handle_softirqs+0x280/0x820 kernel/softirq.c:578
 __do_softirq kernel/softirq.c:612 [inline]
 invoke_softirq kernel/softirq.c:452 [inline]
 __irq_exit_rcu+0xc7/0x190 kernel/softirq.c:661
 irq_exit_rcu+0x9/0x20 kernel/softirq.c:673
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1088 [inline]
 sysvec_apic_timer_interrupt+0xa4/0xc0 arch/x86/kernel/apic/apic.c:1088
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:687
RIP: 0010:lock_acquire+0x1f2/0x410 kernel/locking/lockdep.c:5758
Code: 00 9c 8f 84 24 80 00 00 00 f6 84 24 81 00 00 00 02 0f 85 f5 00 00 00 41 f7 c6 00 02 00 00 74 01 fb 48 c7 44 24 60 0e 36 e0 45 <4b> c7 04 3c 00 00 00 00 66 43 c7 44 3c 09 00 00 43 c6 44 3c 0b 00
RSP: 0018:ffffc9000430fac0 EFLAGS: 00000206
RAX: 0000000000000001 RBX: 0000000000000000 RCX: 2faca621a8eac400
RDX: 0000000000000000 RSI: ffffffff8aaacb40 RDI: ffffffff8afc66c0
RBP: ffffc9000430fbc8 R08: dffffc0000000000 R09: 1ffffffff21b46a8
R10: dffffc0000000000 R11: fffffbfff21b46a9 R12: 1ffff92000861f64
R13: ffff88802c9fd090 R14: 0000000000000246 R15: dffffc0000000000
 __mutex_lock_common kernel/locking/mutex.c:603 [inline]
 __mutex_lock+0x129/0xcc0 kernel/locking/mutex.c:747
 __do_sys_perf_event_open kernel/events/core.c:12924 [inline]
 __se_sys_perf_event_open+0x1878/0x1c20 kernel/events/core.c:12566
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x55/0xb0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2
RIP: 0033:0x7f4c0b78ebe9
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:00007ffd92c43b08 EFLAGS: 00000246 ORIG_RAX: 000000000000012a
RAX: ffffffffffffffda RBX: 00007f4c0b9b5fa0 RCX: 00007f4c0b78ebe9
RDX: ffffffffffffffff RSI: 0000000000000000 RDI: 00002000000003c0
RBP: 00007f4c0b811e19 R08: 0000000000000002 R09: 0000000000000000
R10: ffffffffffffffff R11: 0000000000000246 R12: 0000000000000000
R13: 00007f4c0b9b5fa0 R14: 00007f4c0b9b5fa0 R15: 0000000000000005
 </TASK>

Crashes (4):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2025/08/28 05:58 linux-6.6.y bb9c90ab9c5a e12e5ba4 .config console log report syz / log C [disk image] [vmlinux] [kernel image] ci2-linux-6-6-kasan-perf INFO: rcu detected stall in perf_event_open
2025/08/28 02:59 linux-6.6.y bb9c90ab9c5a e12e5ba4 .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-6-6-kasan-perf INFO: rcu detected stall in perf_event_open
2025/08/26 05:33 linux-6.6.y bb9c90ab9c5a bf27483f .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-6-6-kasan-perf INFO: rcu detected stall in perf_event_open
2025/08/14 11:07 linux-6.6.y 3a8ababb8b6a 22ec1469 .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-6-6-kasan-perf INFO: rcu detected stall in perf_event_open
* Struck through repros no longer work on HEAD.