syzbot

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
rcu: 	0-....: (1 GPs behind) idle=6fb/1/0x4000000000000000 softirq=21555/21556 fqs=2100 
	(detected by 1, t=10505 jiffies, g=39953, q=181464)
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 PID: 7925 Comm: syz-executor260 Not tainted 5.15.167-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
RIP: 0010:perf_swevent_event+0x18f/0x550
Code: ff ff ff ff 48 89 de e8 cf 4e de ff 48 83 fb ff 0f 84 93 01 00 00 e8 e0 4a de ff e9 5d 01 00 00 4c 89 64 24 08 e8 d1 4a de ff <4c> 89 2c 24 4d 8d a5 f0 01 00 00 4d 89 e5 49 c1 ed 03 48 b8 00 00
RSP: 0018:ffffc90004c5eda8 EFLAGS: 00000093
RAX: ffffffff81a20ec5 RBX: 0000000000000000 RCX: ffff888017e69dc0
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: ffffffff81a20eb6 R09: ffffed1002fcd3b9
R10: 0000000000000000 R11: dffffc0000000001 R12: ffffc90004c5ee80
R13: ffff88807b1617e0 R14: 0000000000000001 R15: ffff8880b90350d0
FS:  0000000000000000(0000) GS:ffff8880b9000000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f4ff7269c38 CR3: 000000007b7a5000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <TASK>
 perf_tp_event+0x363/0xc40 kernel/events/core.c:10018
 perf_trace_run_bpf_submit+0xf7/0x1d0 kernel/events/core.c:9992
 perf_trace_preemptirq_template+0x31d/0x430 include/trace/events/preemptirq.h:14
 trace_irq_enable_rcuidle+0x10e/0x190 include/trace/events/preemptirq.h:40
 trace_hardirqs_on+0x57/0x80 kernel/trace/trace_preemptirq.c:44
 asm_sysvec_irq_work+0x16/0x20 arch/x86/include/asm/idtentry.h:664
RIP: 0010:rcu_read_unlock_special+0x84/0x520 kernel/rcu/tree_plugin.h:671
Code: f1 f1 f1 00 f2 f2 f2 49 89 04 17 66 41 c7 44 17 09 f3 f3 41 c6 44 17 0b f3 65 44 8b 25 9d a2 96 7e 41 f7 c4 00 00 f0 00 74 45 <48> c7 44 24 20 0e 36 e0 45 4a c7 04 3a 00 00 00 00 66 42 c7 44 3a
RSP: 0018:ffffc90004c5f2c0 EFLAGS: 00000206
RAX: faf37f2eb5afb300 RBX: 1ffff9200098be60 RCX: ffffffff81631ae8
RDX: dffffc0000000000 RSI: ffffffff8a8b2b00 RDI: ffffffff8ad904c0
RBP: ffffc90004c5f398 R08: dffffc0000000000 R09: fffffbfff20e2419
R10: 0000000000000000 R11: dffffc0000000001 R12: ffffffff8c923c00
R13: ffff888017e6a218 R14: ffffc90004c5f300 R15: 1ffff9200098be5c
 __rcu_read_unlock+0x92/0x100 kernel/rcu/tree_plugin.h:422
 rcu_read_unlock include/linux/rcupdate.h:771 [inline]
 __unlock_page_memcg+0xfd/0x110 mm/memcontrol.c:2090
 zap_pte_range mm/memory.c:1373 [inline]
 zap_pmd_range mm/memory.c:1494 [inline]
 zap_pud_range mm/memory.c:1523 [inline]
 zap_p4d_range mm/memory.c:1544 [inline]
 unmap_page_range+0xffa/0x2630 mm/memory.c:1565
 unmap_vmas+0x1f8/0x390 mm/memory.c:1642
 exit_mmap+0x3b6/0x670 mm/mmap.c:3186
 __mmput+0x112/0x3b0 kernel/fork.c:1126
 exit_mm+0x688/0x7f0 kernel/exit.c:550
 do_exit+0x626/0x2480 kernel/exit.c:861
 do_group_exit+0x144/0x310 kernel/exit.c:996
 get_signal+0xc66/0x14e0 kernel/signal.c:2897
 arch_do_signal_or_restart+0xc3/0x1890 arch/x86/kernel/signal.c:867
 handle_signal_work kernel/entry/common.c:154 [inline]
 exit_to_user_mode_loop+0x97/0x130 kernel/entry/common.c:178
 exit_to_user_mode_prepare+0xb1/0x140 kernel/entry/common.c:214
 __syscall_exit_to_user_mode_work kernel/entry/common.c:296 [inline]
 syscall_exit_to_user_mode+0x5d/0x240 kernel/entry/common.c:307
 do_syscall_64+0x47/0xb0 arch/x86/entry/common.c:86
 entry_SYSCALL_64_after_hwframe+0x66/0xd0
RIP: 0033:0x7f4ff72135d9
Code: Unable to access opcode bytes at RIP 0x7f4ff72135af.
RSP: 002b:00007f4ff71d4238 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
RAX: 0000000000000001 RBX: 00007f4ff729d308 RCX: 00007f4ff72135d9
RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00007f4ff729d30c
RBP: 00007f4ff729d300 R08: 00007f4ff71d46c0 R09: 00007f4ff71d46c0
R10: 0000000000000003 R11: 0000000000000246 R12: fffffffeffffffff
R13: 0000000000000000 R14: 00007fff18982bc0 R15: 00007fff18982ca8
 </TASK>
INFO: NMI handler (nmi_cpu_backtrace_handler) took too long to run: 1.545 msecs