syzbot


possible deadlock in __rmqueue_pcplist

Status: upstream: reported on 2025/03/12 04:34
Reported-by: syzbot+be97fa4f64dab3714067@syzkaller.appspotmail.com
First crash: 7h03m, last: 7h03m

Sample crash report:
======================================================
WARNING: possible circular locking dependency detected
6.1.130-syzkaller #0 Not tainted
------------------------------------------------------
syz.1.91/4640 is trying to acquire lock:
ffff88813fffacd8 (&zone->lock){-.-.}-{2:2}, at: rmqueue_bulk mm/page_alloc.c:3131 [inline]
ffff88813fffacd8 (&zone->lock){-.-.}-{2:2}, at: __rmqueue_pcplist+0x2ac/0x2310 mm/page_alloc.c:3785

but task is already holding lock:
ffff888053a4f238 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem+0xc6/0xdc0 kernel/bpf/lpm_trie.c:335

which lock already depends on the new lock.


the existing dependency chain (in reverse order) is:

-> #1 (&trie->lock){-.-.}-{2:2}:
       lock_acquire+0x1f8/0x5a0 kernel/locking/lockdep.c:5662
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
       _raw_spin_lock_irqsave+0xd1/0x120 kernel/locking/spinlock.c:162
       trie_delete_elem+0x90/0x690 kernel/bpf/lpm_trie.c:467
       0xffffffffa000205a
       bpf_dispatcher_nop_func include/linux/bpf.h:1000 [inline]
       __bpf_prog_run include/linux/filter.h:603 [inline]
       bpf_prog_run include/linux/filter.h:610 [inline]
       __bpf_trace_run kernel/trace/bpf_trace.c:2284 [inline]
       bpf_trace_run2+0x1fd/0x410 kernel/trace/bpf_trace.c:2323
       trace_contention_end+0x14c/0x190 include/trace/events/lock.h:122
       __pv_queued_spin_lock_slowpath+0x935/0xc50 kernel/locking/qspinlock.c:560
       pv_queued_spin_lock_slowpath arch/x86/include/asm/paravirt.h:591 [inline]
       queued_spin_lock_slowpath+0x42/0x50 arch/x86/include/asm/qspinlock.h:51
       queued_spin_lock include/asm-generic/qspinlock.h:114 [inline]
       do_raw_spin_lock+0x269/0x370 kernel/locking/spinlock_debug.c:115
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:111 [inline]
       _raw_spin_lock_irqsave+0xdd/0x120 kernel/locking/spinlock.c:162
       rmqueue_bulk mm/page_alloc.c:3131 [inline]
       __rmqueue_pcplist+0x2ac/0x2310 mm/page_alloc.c:3785
       rmqueue_pcplist mm/page_alloc.c:3827 [inline]
       rmqueue mm/page_alloc.c:3870 [inline]
       get_page_from_freelist+0x880/0x38d0 mm/page_alloc.c:4325
       __alloc_pages+0x28d/0x770 mm/page_alloc.c:5605
       __pte_alloc_one include/asm-generic/pgalloc.h:63 [inline]
       pte_alloc_one+0x86/0x360 arch/x86/mm/pgtable.c:33
       __pte_alloc+0x75/0x220 mm/memory.c:468
       copy_pte_range mm/memory.c:1042 [inline]
       copy_pmd_range mm/memory.c:1177 [inline]
       copy_pud_range mm/memory.c:1214 [inline]
       copy_p4d_range mm/memory.c:1238 [inline]
       copy_page_range+0x3e3e/0x4660 mm/memory.c:1336
       dup_mmap kernel/fork.c:697 [inline]
       dup_mm kernel/fork.c:1541 [inline]
       copy_mm+0xf42/0x1990 kernel/fork.c:1590
       copy_process+0x19fb/0x40a0 kernel/fork.c:2266
       kernel_clone+0x222/0x920 kernel/fork.c:2681
       __do_sys_clone kernel/fork.c:2822 [inline]
       __se_sys_clone kernel/fork.c:2806 [inline]
       __x64_sys_clone+0x242/0x2c0 kernel/fork.c:2806
       do_syscall_x64 arch/x86/entry/common.c:51 [inline]
       do_syscall_64+0x3b/0xb0 arch/x86/entry/common.c:81
       entry_SYSCALL_64_after_hwframe+0x68/0xd2

-> #0 (&zone->lock){-.-.}-{2:2}:
       check_prev_add kernel/locking/lockdep.c:3090 [inline]
       check_prevs_add kernel/locking/lockdep.c:3209 [inline]
       validate_chain+0x1661/0x5950 kernel/locking/lockdep.c:3825
       __lock_acquire+0x125b/0x1f80 kernel/locking/lockdep.c:5049
       lock_acquire+0x1f8/0x5a0 kernel/locking/lockdep.c:5662
       __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
       _raw_spin_lock_irqsave+0xd1/0x120 kernel/locking/spinlock.c:162
       rmqueue_bulk mm/page_alloc.c:3131 [inline]
       __rmqueue_pcplist+0x2ac/0x2310 mm/page_alloc.c:3785
       rmqueue_pcplist mm/page_alloc.c:3827 [inline]
       rmqueue mm/page_alloc.c:3870 [inline]
       get_page_from_freelist+0x880/0x38d0 mm/page_alloc.c:4325
       __alloc_pages+0x28d/0x770 mm/page_alloc.c:5605
       alloc_slab_page+0x6a/0x150 mm/slub.c:1794
       allocate_slab mm/slub.c:1939 [inline]
       new_slab+0x84/0x2d0 mm/slub.c:1992
       ___slab_alloc+0xc20/0x1270 mm/slub.c:3180
       __slab_alloc mm/slub.c:3279 [inline]
       slab_alloc_node mm/slub.c:3364 [inline]
       __kmem_cache_alloc_node+0x19f/0x260 mm/slub.c:3437
       __do_kmalloc_node mm/slab_common.c:935 [inline]
       __kmalloc_node+0xa2/0x230 mm/slab_common.c:943
       kmalloc_node include/linux/slab.h:589 [inline]
       bpf_map_kmalloc_node+0xce/0x1c0 kernel/bpf/syscall.c:452
       lpm_trie_node_alloc kernel/bpf/lpm_trie.c:291 [inline]
       trie_update_elem+0x175/0xdc0 kernel/bpf/lpm_trie.c:338
       bpf_map_update_value+0x5cf/0x6f0 kernel/bpf/syscall.c:226
       generic_map_update_batch+0x579/0x920 kernel/bpf/syscall.c:1699
       bpf_map_do_batch+0x4d0/0x620
       __sys_bpf+0x658/0x6c0
       __do_sys_bpf kernel/bpf/syscall.c:5121 [inline]
       __se_sys_bpf kernel/bpf/syscall.c:5119 [inline]
       __x64_sys_bpf+0x78/0x90 kernel/bpf/syscall.c:5119
       do_syscall_x64 arch/x86/entry/common.c:51 [inline]
       do_syscall_64+0x3b/0xb0 arch/x86/entry/common.c:81
       entry_SYSCALL_64_after_hwframe+0x68/0xd2

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&trie->lock);
                               lock(&zone->lock);
                               lock(&trie->lock);
  lock(&zone->lock);

 *** DEADLOCK ***

3 locks held by syz.1.91/4640:
 #0: ffffffff8d32e680 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:350 [inline]
 #0: ffffffff8d32e680 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:791 [inline]
 #0: ffffffff8d32e680 (rcu_read_lock){....}-{1:2}, at: bpf_map_update_value+0x207/0x6f0 kernel/bpf/syscall.c:225
 #1: ffff888053a4f238 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem+0xc6/0xdc0 kernel/bpf/lpm_trie.c:335
 #2: ffff8880b8f41198 (&pcp->lock){+.+.}-{2:2}, at: spin_trylock include/linux/spinlock.h:361 [inline]
 #2: ffff8880b8f41198 (&pcp->lock){+.+.}-{2:2}, at: rmqueue_pcplist mm/page_alloc.c:3814 [inline]
 #2: ffff8880b8f41198 (&pcp->lock){+.+.}-{2:2}, at: rmqueue mm/page_alloc.c:3870 [inline]
 #2: ffff8880b8f41198 (&pcp->lock){+.+.}-{2:2}, at: get_page_from_freelist+0x7c2/0x38d0 mm/page_alloc.c:4325

stack backtrace:
CPU: 1 PID: 4640 Comm: syz.1.91 Not tainted 6.1.130-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106
 check_noncircular+0x2fa/0x3b0 kernel/locking/lockdep.c:2170
 check_prev_add kernel/locking/lockdep.c:3090 [inline]
 check_prevs_add kernel/locking/lockdep.c:3209 [inline]
 validate_chain+0x1661/0x5950 kernel/locking/lockdep.c:3825
 __lock_acquire+0x125b/0x1f80 kernel/locking/lockdep.c:5049
 lock_acquire+0x1f8/0x5a0 kernel/locking/lockdep.c:5662
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0xd1/0x120 kernel/locking/spinlock.c:162
 rmqueue_bulk mm/page_alloc.c:3131 [inline]
 __rmqueue_pcplist+0x2ac/0x2310 mm/page_alloc.c:3785
 rmqueue_pcplist mm/page_alloc.c:3827 [inline]
 rmqueue mm/page_alloc.c:3870 [inline]
 get_page_from_freelist+0x880/0x38d0 mm/page_alloc.c:4325
 __alloc_pages+0x28d/0x770 mm/page_alloc.c:5605
 alloc_slab_page+0x6a/0x150 mm/slub.c:1794
 allocate_slab mm/slub.c:1939 [inline]
 new_slab+0x84/0x2d0 mm/slub.c:1992
 ___slab_alloc+0xc20/0x1270 mm/slub.c:3180
 __slab_alloc mm/slub.c:3279 [inline]
 slab_alloc_node mm/slub.c:3364 [inline]
 __kmem_cache_alloc_node+0x19f/0x260 mm/slub.c:3437
 __do_kmalloc_node mm/slab_common.c:935 [inline]
 __kmalloc_node+0xa2/0x230 mm/slab_common.c:943
 kmalloc_node include/linux/slab.h:589 [inline]
 bpf_map_kmalloc_node+0xce/0x1c0 kernel/bpf/syscall.c:452
 lpm_trie_node_alloc kernel/bpf/lpm_trie.c:291 [inline]
 trie_update_elem+0x175/0xdc0 kernel/bpf/lpm_trie.c:338
 bpf_map_update_value+0x5cf/0x6f0 kernel/bpf/syscall.c:226
 generic_map_update_batch+0x579/0x920 kernel/bpf/syscall.c:1699
 bpf_map_do_batch+0x4d0/0x620
 __sys_bpf+0x658/0x6c0
 __do_sys_bpf kernel/bpf/syscall.c:5121 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5119 [inline]
 __x64_sys_bpf+0x78/0x90 kernel/bpf/syscall.c:5119
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x3b/0xb0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2
RIP: 0033:0x7fd91e58d169
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:00007fd91f316038 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 00007fd91e7a5fa0 RCX: 00007fd91e58d169
RDX: 0000000000000038 RSI: 0000400000000000 RDI: 000000000000001a
RBP: 00007fd91e60e2a0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007fd91e7a5fa0 R15: 00007ffea3153358
 </TASK>

Crashes (1):
Time Kernel Commit Syzkaller Config Log Report Syz repro C repro VM info Assets (help?) Manager Title
2025/03/12 04:33 linux-6.1.y 6ae7ac5c4251 ee70e6db .config console log report info [disk image] [vmlinux] [kernel image] ci2-linux-6-1-kasan-perf possible deadlock in __rmqueue_pcplist
* Struck through repros no longer work on HEAD.