BUG: soft lockup in arp

Kernel	Title	Repro	Cause bisect	Fix bisect	Count	Last	Reported	Patched	Status
upstream	INFO: rcu detected stall in arp_rcv net				1	1011d	1011d	0/27	closed as invalid on 2022/02/08 10:10
watchdog: BUG: soft lockup - CPU#0 stuck for 114s! [syz.3.255:1622]
Modules linked in:
CPU: 0 PID: 1622 Comm: syz.3.255 Not tainted 6.1.90-syzkaller-00107-gf21999db6a00 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/07/2024
RIP: 0010:update_stack_state+0x289/0x460 arch/x86/kernel/unwind_frame.c:261
Code: 00 74 08 4c 89 f7 e8 26 d5 84 00 49 83 3e 00 48 8b 45 a8 4c 8b ad 78 ff ff ff 74 22 44 3b 7d a4 75 1c 48 3b 45 98 73 16 31 db <89> d8 48 81 c4 90 00 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 4d 85
RSP: 0018:ffffc90000006490 EFLAGS: 00000282
RAX: 1ffff92000000cc5 RBX: ffffc90000006601 RCX: 1ffff92000000cc7
RDX: 1ffff92000000cbe RSI: ffffc900038bf070 RDI: ffffc90000006638
RBP: ffffc90000006548 R08: ffffc900000066c8 R09: 0000000000000027
R10: ffffc900000066d0 R11: dffffc0000000001 R12: 1ffff92000000cc4
R13: 0000000000000000 R14: ffffc90000006620 R15: dffffc0000000000
FS:  0000000000000000(0000) GS:ffff8881f7000000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000562923f73d78 CR3: 000000010e7ef000 CR4: 00000000003506b0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 unwind_next_frame+0x3cb/0x700 arch/x86/kernel/unwind_frame.c:315
 arch_stack_walk+0x10d/0x140 arch/x86/kernel/stacktrace.c:25
 stack_trace_save+0x113/0x1c0 kernel/stacktrace.c:122
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:516
 ____kasan_slab_free+0x131/0x180 mm/kasan/common.c:241
 __kasan_slab_free+0x11/0x20 mm/kasan/common.c:249
 kasan_slab_free include/linux/kasan.h:178 [inline]
 slab_free_hook mm/slub.c:1745 [inline]
 slab_free_freelist_hook mm/slub.c:1771 [inline]
 slab_free mm/slub.c:3684 [inline]
 kmem_cache_free+0x291/0x510 mm/slub.c:3706
 kfree_skbmem+0x104/0x170
 __kfree_skb net/core/skbuff.c:871 [inline]
 consume_skb+0xb4/0x250 net/core/skbuff.c:1035
 __dev_kfree_skb_any+0x159/0x180 net/core/dev.c:3186
 dev_consume_skb_any include/linux/netdevice.h:3876 [inline]
 napi_consume_skb+0x155/0x2d0 net/core/skbuff.c:1095
 free_old_xmit_skbs+0x119/0x290 drivers/net/virtio_net.c:1609
 start_xmit+0x185/0x1670 drivers/net/virtio_net.c:1871
 __netdev_start_xmit include/linux/netdevice.h:4908 [inline]
 netdev_start_xmit include/linux/netdevice.h:4922 [inline]
 xmit_one net/core/dev.c:3634 [inline]
 dev_hard_start_xmit+0x1de/0x630 net/core/dev.c:3650
 sch_direct_xmit+0x298/0x9b0 net/sched/sch_generic.c:342
 __dev_xmit_skb net/core/dev.c:3861 [inline]
 __dev_queue_xmit+0x17c2/0x36e0 net/core/dev.c:4266
 dev_queue_xmit include/linux/netdevice.h:3076 [inline]
 arp_xmit_finish net/ipv4/arp.c:653 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 arp_xmit+0xc7/0x280 net/ipv4/arp.c:662
 arp_send_dst+0x236/0x330 net/ipv4/arp.c:320
 arp_process+0x138b/0x1ee0 net/ipv4/arp.c:851
 nf_hook_state_init include/linux/netfilter.h:160 [inline]
 nf_hook include/linux/netfilter.h:257 [inline]
 NF_HOOK+0x207/0x280 include/linux/netfilter.h:303
 arp_rcv+0x2df/0x490 net/ipv4/arp.c:988
 __netif_receive_skb_list_ptype net/core/dev.c:5583 [inline]
 __netif_receive_skb_list_core+0x4ce/0x890 net/core/dev.c:5616
 __netif_receive_skb_list net/core/dev.c:5678 [inline]
 netif_receive_skb_list_internal+0x967/0xcc0 net/core/dev.c:5769
 gro_normal_list include/net/gro.h:433 [inline]
 gro_normal_one include/net/gro.h:446 [inline]
 napi_skb_finish net/core/gro.c:628 [inline]
 napi_gro_receive+0x45f/0x920 net/core/gro.c:658
 receive_buf+0x22e7/0x4ee0 drivers/net/virtio_net.c:1297
 virtnet_receive drivers/net/virtio_net.c:1562 [inline]
 virtnet_poll+0x6d3/0x1470 drivers/net/virtio_net.c:1680
 __napi_poll+0xbe/0x5c0 net/core/dev.c:6544
 napi_poll net/core/dev.c:6611 [inline]
 net_rx_action+0x595/0xdd0 net/core/dev.c:6725
 __do_softirq+0x1d8/0x661 kernel/softirq.c:617
 invoke_softirq kernel/softirq.c:472 [inline]
 __irq_exit_rcu+0x50/0xf0 kernel/softirq.c:700
 irq_exit_rcu+0x9/0x10 kernel/softirq.c:712
 sysvec_apic_timer_interrupt+0x9a/0xc0 arch/x86/kernel/apic/apic.c:1106
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1b/0x20 arch/x86/include/asm/idtentry.h:653
RIP: 0010:unwind_next_frame+0x4/0x700 arch/x86/kernel/unwind_frame.c:265
Code: 41 5e 41 5f 5d c3 44 89 f1 80 e1 07 80 c1 03 38 c1 7c 99 4c 89 f7 e8 8b de 84 00 eb 8f 66 0f 1f 84 00 00 00 00 00 55 48 89 e5 <41> 57 41 56 41 55 41 54 53 48 83 ec 50 49 89 fe 48 ba 00 00 00 00
RSP: 0018:ffffc900038bea50 EFLAGS: 00000287
RAX: ffffc900038beb70 RBX: ffffc900038beae0 RCX: 1ffff92000717d63
RDX: 1ffff92000717d63 RSI: ffffc900038bead0 RDI: ffffc900038beae0
RBP: ffffc900038bea50 R08: dffffc0000000001 R09: ffffc900038beae0
R10: 0000000000000000 R11: dffffc0000000001 R12: ffffc900038beaf0
R13: ffffc900038b8000 R14: ffffc900038beae8 R15: 1ffff92000717d5e
 __unwind_start+0x318/0x3a0 arch/x86/kernel/unwind_frame.c:417
 unwind_start arch/x86/include/asm/unwind.h:64 [inline]
 arch_stack_walk+0xdb/0x140 arch/x86/kernel/stacktrace.c:24
 stack_trace_save+0x113/0x1c0 kernel/stacktrace.c:122
 kasan_save_stack+0x3b/0x60 mm/kasan/common.c:45
 __kasan_record_aux_stack+0xb4/0xc0 mm/kasan/generic.c:486
 kasan_record_aux_stack_noalloc+0xb/0x10 mm/kasan/generic.c:496
 __call_rcu_common kernel/rcu/tree.c:2806 [inline]
 call_rcu+0xee/0x1340 kernel/rcu/tree.c:2925
 put_task_struct_rcu_user+0x58/0x90 kernel/exit.c:233
 finish_task_switch+0x343/0x7b0 kernel/sched/core.c:5331
 context_switch kernel/sched/core.c:5421 [inline]
 __schedule+0xcaf/0x1550 kernel/sched/core.c:6744
 preempt_schedule_common+0x9b/0xf0 kernel/sched/core.c:6913
 preempt_schedule+0xd9/0xe0 kernel/sched/core.c:6937
 preempt_schedule_thunk+0x16/0x18 arch/x86/entry/thunk_64.S:34
 __raw_spin_unlock include/linux/spinlock_api_smp.h:143 [inline]
 _raw_spin_unlock+0x5f/0x70 kernel/locking/spinlock.c:186
 spin_unlock include/linux/spinlock.h:391 [inline]
 zap_pte_range mm/memory.c:1530 [inline]
 zap_pmd_range mm/memory.c:1589 [inline]
 zap_pud_range mm/memory.c:1618 [inline]
 zap_p4d_range mm/memory.c:1639 [inline]
 unmap_page_range+0xaae/0x2480 mm/memory.c:1660
 unmap_single_vma mm/memory.c:1706 [inline]
 unmap_vmas+0x4e4/0x660 mm/memory.c:1746
 exit_mmap+0x2d1/0x940 mm/mmap.c:3336
 __mmput+0x95/0x310 kernel/fork.c:1298
 mmput+0x56/0x170 kernel/fork.c:1321
 exit_mm kernel/exit.c:566 [inline]
 do_exit+0xb29/0x2b80 kernel/exit.c:862
 do_group_exit+0x21a/0x2d0 kernel/exit.c:1025
 get_signal+0x169d/0x1820 kernel/signal.c:2880
 arch_do_signal_or_restart+0xb0/0x16f0 arch/x86/kernel/signal.c:871
 exit_to_user_mode_loop+0x74/0xa0 kernel/entry/common.c:174
 exit_to_user_mode_prepare+0x5a/0xa0 kernel/entry/common.c:210
 __syscall_exit_to_user_mode_work kernel/entry/common.c:292 [inline]
 syscall_exit_to_user_mode+0x26/0x130 kernel/entry/common.c:303
 do_syscall_64+0x47/0xb0 arch/x86/entry/common.c:87
 entry_SYSCALL_64_after_hwframe+0x68/0xd2
RIP: 0033:0x7fda5b975f19
Code: Unable to access opcode bytes at 0x7fda5b975eef.
RSP: 002b:00007fda5c7d9048 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: 0000000000000000 RBX: 00007fda5bb05f60 RCX: 00007fda5b975f19
RDX: 00000000200015c0 RSI: 0000000000005452 RDI: 000000000000000a
RBP: 00007fda5b9e4e68 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007fda5bb05f60 R15: 00007ffece035068
 </TASK>
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 37 Comm: kworker/u4:2 Not tainted 6.1.90-syzkaller-00107-gf21999db6a00 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/07/2024
Workqueue: events_unbound toggle_allocation_gate
RIP: 0010:csd_lock_wait kernel/smp.c:453 [inline]
RIP: 0010:smp_call_function_many_cond+0x851/0x930 kernel/smp.c:998
Code: 3e 44 89 fe 83 e6 01 31 ff e8 4b 9f 09 00 41 83 e7 01 49 bf 00 00 00 00 00 fc ff df 75 0a e8 86 9b 09 00 e9 2f ff ff ff f3 90 <42> 0f b6 04 3b 84 c0 75 14 41 f7 06 01 00 00 00 0f 84 12 ff ff ff
RSP: 0018:ffffc9000026f840 EFLAGS: 00000293
RAX: ffffffff816c062c RBX: 1ffff1103ee07a99 RCX: ffff88810080e540
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000
RBP: ffffc9000026f958 R08: ffffffff816c05f5 R09: ffffed103ee271fb
R10: 0000000000000000 R11: dffffc0000000001 R12: 0000000000000000
R13: 0000000800000000 R14: ffff8881f703d4c8 R15: dffffc0000000000
FS:  0000000000000000(0000) GS:ffff8881f7100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0ca70732af CR3: 0000000006e0f000 CR4: 00000000003506a0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <TASK>
 on_each_cpu_cond_mask+0x40/0x80 kernel/smp.c:1166
 on_each_cpu include/linux/smp.h:71 [inline]
 text_poke_sync arch/x86/kernel/alternative.c:1334 [inline]
 text_poke_bp_batch+0x1e9/0x730 arch/x86/kernel/alternative.c:1534
 text_poke_flush arch/x86/kernel/alternative.c:1725 [inline]
 text_poke_finish+0x1a/0x30 arch/x86/kernel/alternative.c:1732
 arch_jump_label_transform_apply+0x15/0x30 arch/x86/kernel/jump_label.c:146
 __jump_label_update+0x36a/0x380 kernel/jump_label.c:455
 jump_label_update+0x3af/0x450 kernel/jump_label.c:801
 static_key_enable_cpuslocked+0x12f/0x250 kernel/jump_label.c:177
 static_key_enable+0x1a/0x30 kernel/jump_label.c:190
 toggle_allocation_gate+0xbf/0x450 mm/kfence/core.c:804
 process_one_work+0x73d/0xcb0 kernel/workqueue.c:2299
 worker_thread+0xa60/0x1260 kernel/workqueue.c:2446
 kthread+0x26d/0x300 kernel/kthread.c:386
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308
 </TASK>