KASAN: stack-out-of-bounds Read in csd_lock_record
syzbot
syzbotHello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xcb/0xe0 kernel/smp.c:118
Read of size 8 at addr ffffc90001727710 by task syz-executor.0/10721
CPU: 1 PID: 10721 Comm: syz-executor.0 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x18f/0x20d lib/dump_stack.c:118
print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383
__kasan_report mm/kasan/report.c:513 [inline]
kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
csd_lock_record+0xcb/0xe0 kernel/smp.c:118
flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391
__sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248
asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706
</IRQ>
__run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline]
run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline]
sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243
asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604
RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:765 [inline]
RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline]
RIP: 0010:_raw_spin_unlock_irqrestore+0x8c/0xe0 kernel/locking/spinlock.c:191
Code: 48 c7 c0 00 ff b4 89 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 75 37 48 83 3d 9b 74 c8 01 00 74 22 48 89 df 57 9d <0f> 1f 44 00 00 bf 01 00 00 00 e8 95 fb 62 f9 65 8b 05 fe 73 15 78
RSP: 0018:ffffc900016e7558 EFLAGS: 00000282
RAX: 1ffffffff1369fe0 RBX: 0000000000000282 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000282
RBP: ffffffff8cb02508 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: 1ffffffff19604a0
R13: 0000000000000000 R14: dead000000000100 R15: dffffc0000000000
__debug_check_no_obj_freed lib/debugobjects.c:977 [inline]
debug_check_no_obj_freed+0x20c/0x41c lib/debugobjects.c:998
free_pages_prepare mm/page_alloc.c:1219 [inline]
__free_pages_ok+0x20b/0xc90 mm/page_alloc.c:1471
release_pages+0x5ec/0x17a0 mm/swap.c:880
tlb_batch_pages_flush mm/mmu_gather.c:49 [inline]
tlb_flush_mmu_free mm/mmu_gather.c:242 [inline]
tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:249
zap_pte_range mm/memory.c:1155 [inline]
zap_pmd_range mm/memory.c:1193 [inline]
zap_pud_range mm/memory.c:1222 [inline]
zap_p4d_range mm/memory.c:1243 [inline]
unmap_page_range+0x1e22/0x2b20 mm/memory.c:1264
unmap_single_vma+0x198/0x300 mm/memory.c:1309
unmap_vmas+0x16f/0x2f0 mm/memory.c:1341
exit_mmap+0x2b1/0x530 mm/mmap.c:3165
__mmput+0x122/0x470 kernel/fork.c:1075
mmput+0x53/0x60 kernel/fork.c:1096
exit_mm kernel/exit.c:483 [inline]
do_exit+0xa8f/0x2a40 kernel/exit.c:793
do_group_exit+0x125/0x310 kernel/exit.c:904
get_signal+0x40b/0x1ee0 kernel/signal.c:2743
do_signal+0x82/0x2520 arch/x86/kernel/signal.c:810
exit_to_usermode_loop arch/x86/entry/common.c:218 [inline]
__prepare_exit_to_usermode+0x156/0x1f0 arch/x86/entry/common.c:252
do_syscall_64+0x6c/0xe0 arch/x86/entry/common.c:376
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45cb29
Code: Bad RIP value.
RSP: 002b:00007fb154b96cf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
RAX: 0000000000000001 RBX: 000000000078bf08 RCX: 000000000045cb29
RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 000000000078bf0c
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000078bf0c
R13: 00007ffd3933f26f R14: 00007fb154b979c0 R15: 000000000078bf0c
Memory state around the buggy address:
ffffc90001727600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffffc90001727680: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00
>ffffc90001727700: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00
^
ffffc90001727780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffffc90001727800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================---
This bug is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot. syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches
syzbot
syzbotsyzbot has found a reproducer for the following crash on:
syzbot has found a reproducer for the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1224dc83100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=170442d5100000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=162ef66d100000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xd2/0xe0 kernel/smp.c:119
Read of size 8 at addr ffffc900016d75f8 by task swapper/1/0
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x18f/0x20d lib/dump_stack.c:118
print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383
__kasan_report mm/kasan/report.c:513 [inline]
kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
csd_lock_record+0xd2/0xe0 kernel/smp.c:119
flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391
__sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248
asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706
</IRQ>
__run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline]
run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline]
sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243
asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: ff 4c 89 ef e8 33 30 c7 f9 e9 8e fe ff ff 48 89 df e8 26 30 c7 f9 eb 8a cc cc cc cc e9 07 00 00 00 0f 00 2d 14 4b 5c 00 fb f4 <c3> 90 e9 07 00 00 00 0f 00 2d 04 4b 5c 00 f4 c3 cc cc 55 53 e8 c9
RSP: 0018:ffffc90000d3fd18 EFLAGS: 00000293
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff8880a95f0340 RSI: ffffffff87ec78c8 RDI: ffffffff87ec789e
RBP: ffff88821af4d864 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88821af4d864
R13: 1ffff920001a7fad R14: ffff88821af4d865 R15: 0000000000000001
arch_safe_halt arch/x86/include/asm/paravirt.h:150 [inline]
acpi_safe_halt+0x8d/0x110 drivers/acpi/processor_idle.c:111
acpi_idle_do_entry+0x15c/0x1b0 drivers/acpi/processor_idle.c:525
acpi_idle_enter+0x3f9/0xab0 drivers/acpi/processor_idle.c:651
cpuidle_enter_state+0xff/0x960 drivers/cpuidle/cpuidle.c:235
cpuidle_enter+0x4a/0xa0 drivers/cpuidle/cpuidle.c:346
call_cpuidle kernel/sched/idle.c:126 [inline]
cpuidle_idle_call kernel/sched/idle.c:214 [inline]
do_idle+0x431/0x6d0 kernel/sched/idle.c:276
cpu_startup_entry+0x14/0x20 kernel/sched/idle.c:372
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243
Memory state around the buggy address:
ffffc900016d7480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffffc900016d7500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffffc900016d7580: 00 00 00 00 f1 f1 f1 f1 00 00 00 00 f3 f3 f3 f3
^
ffffc900016d7600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffffc900016d7680: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]
Good catch! A call to csd_lock_record() was on the wrong side of a call to csd_unlock().
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
Thanx, Paul
Quoted 88 lines
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xcb/0xe0 kernel/smp.c:118 Read of size 8 at addr ffffc90001727710 by task syz-executor.0/10721 CPU: 1 PID: 10721 Comm: syz-executor.0 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x18f/0x20d lib/dump_stack.c:118 print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530 csd_lock_record+0xcb/0xe0 kernel/smp.c:118 flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391 __sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248 asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706 </IRQ> __run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline] sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243 asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604 RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:765 [inline] RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline] RIP: 0010:_raw_spin_unlock_irqrestore+0x8c/0xe0 kernel/locking/spinlock.c:191 Code: 48 c7 c0 00 ff b4 89 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 75 37 48 83 3d 9b 74 c8 01 00 74 22 48 89 df 57 9d <0f> 1f 44 00 00 bf 01 00 00 00 e8 95 fb 62 f9 65 8b 05 fe 73 15 78 RSP: 0018:ffffc900016e7558 EFLAGS: 00000282 RAX: 1ffffffff1369fe0 RBX: 0000000000000282 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000282 RBP: ffffffff8cb02508 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 1ffffffff19604a0 R13: 0000000000000000 R14: dead000000000100 R15: dffffc0000000000 __debug_check_no_obj_freed lib/debugobjects.c:977 [inline] debug_check_no_obj_freed+0x20c/0x41c lib/debugobjects.c:998 free_pages_prepare mm/page_alloc.c:1219 [inline] __free_pages_ok+0x20b/0xc90 mm/page_alloc.c:1471 release_pages+0x5ec/0x17a0 mm/swap.c:880 tlb_batch_pages_flush mm/mmu_gather.c:49 [inline] tlb_flush_mmu_free mm/mmu_gather.c:242 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:249 zap_pte_range mm/memory.c:1155 [inline] zap_pmd_range mm/memory.c:1193 [inline] zap_pud_range mm/memory.c:1222 [inline] zap_p4d_range mm/memory.c:1243 [inline] unmap_page_range+0x1e22/0x2b20 mm/memory.c:1264 unmap_single_vma+0x198/0x300 mm/memory.c:1309 unmap_vmas+0x16f/0x2f0 mm/memory.c:1341 exit_mmap+0x2b1/0x530 mm/mmap.c:3165 __mmput+0x122/0x470 kernel/fork.c:1075 mmput+0x53/0x60 kernel/fork.c:1096 exit_mm kernel/exit.c:483 [inline] do_exit+0xa8f/0x2a40 kernel/exit.c:793 do_group_exit+0x125/0x310 kernel/exit.c:904 get_signal+0x40b/0x1ee0 kernel/signal.c:2743 do_signal+0x82/0x2520 arch/x86/kernel/signal.c:810 exit_to_usermode_loop arch/x86/entry/common.c:218 [inline] __prepare_exit_to_usermode+0x156/0x1f0 arch/x86/entry/common.c:252 do_syscall_64+0x6c/0xe0 arch/x86/entry/common.c:376 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45cb29 Code: Bad RIP value. RSP: 002b:00007fb154b96cf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 000000000078bf08 RCX: 000000000045cb29 RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 000000000078bf0c RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000078bf0c R13: 00007ffd3933f26f R14: 00007fb154b979c0 R15: 000000000078bf0c Memory state around the buggy address: ffffc90001727600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727680: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00 >ffffc90001727700: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffc90001727780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ==================================================================---
This bug is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot. syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches
Quoted 14 lines · Paul E. McKenney
Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000
Quoted 5 lines
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]Good catch! A call to
csd_lock_record()was on the wrong side of a call tocsd_unlock().
Thanks for taking a look.
Quoted 7 lines
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
[ paulmck: Fix for [email protected] ]
This should work, as far as I remember sybot looks for the email+hash anywhere in the commit.
FWIW Tested-by can make sense as well.
Quoted 95 lines
Thanx, Paul
Quoted 84 lines
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xcb/0xe0 kernel/smp.c:118 Read of size 8 at addr ffffc90001727710 by task syz-executor.0/10721 CPU: 1 PID: 10721 Comm: syz-executor.0 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x18f/0x20d lib/dump_stack.c:118 print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530 csd_lock_record+0xcb/0xe0 kernel/smp.c:118 flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391 __sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248 asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706 </IRQ> __run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline] sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243 asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604 RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:765 [inline] RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline] RIP: 0010:_raw_spin_unlock_irqrestore+0x8c/0xe0 kernel/locking/spinlock.c:191 Code: 48 c7 c0 00 ff b4 89 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 75 37 48 83 3d 9b 74 c8 01 00 74 22 48 89 df 57 9d <0f> 1f 44 00 00 bf 01 00 00 00 e8 95 fb 62 f9 65 8b 05 fe 73 15 78 RSP: 0018:ffffc900016e7558 EFLAGS: 00000282 RAX: 1ffffffff1369fe0 RBX: 0000000000000282 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000282 RBP: ffffffff8cb02508 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 1ffffffff19604a0 R13: 0000000000000000 R14: dead000000000100 R15: dffffc0000000000 __debug_check_no_obj_freed lib/debugobjects.c:977 [inline] debug_check_no_obj_freed+0x20c/0x41c lib/debugobjects.c:998 free_pages_prepare mm/page_alloc.c:1219 [inline] __free_pages_ok+0x20b/0xc90 mm/page_alloc.c:1471 release_pages+0x5ec/0x17a0 mm/swap.c:880 tlb_batch_pages_flush mm/mmu_gather.c:49 [inline] tlb_flush_mmu_free mm/mmu_gather.c:242 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:249 zap_pte_range mm/memory.c:1155 [inline] zap_pmd_range mm/memory.c:1193 [inline] zap_pud_range mm/memory.c:1222 [inline] zap_p4d_range mm/memory.c:1243 [inline] unmap_page_range+0x1e22/0x2b20 mm/memory.c:1264 unmap_single_vma+0x198/0x300 mm/memory.c:1309 unmap_vmas+0x16f/0x2f0 mm/memory.c:1341 exit_mmap+0x2b1/0x530 mm/mmap.c:3165 __mmput+0x122/0x470 kernel/fork.c:1075 mmput+0x53/0x60 kernel/fork.c:1096 exit_mm kernel/exit.c:483 [inline] do_exit+0xa8f/0x2a40 kernel/exit.c:793 do_group_exit+0x125/0x310 kernel/exit.c:904 get_signal+0x40b/0x1ee0 kernel/signal.c:2743 do_signal+0x82/0x2520 arch/x86/kernel/signal.c:810 exit_to_usermode_loop arch/x86/entry/common.c:218 [inline] __prepare_exit_to_usermode+0x156/0x1f0 arch/x86/entry/common.c:252 do_syscall_64+0x6c/0xe0 arch/x86/entry/common.c:376 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45cb29 Code: Bad RIP value. RSP: 002b:00007fb154b96cf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 000000000078bf08 RCX: 000000000045cb29 RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 000000000078bf0c RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000078bf0c R13: 00007ffd3933f26f R14: 00007fb154b979c0 R15: 000000000078bf0c Memory state around the buggy address: ffffc90001727600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727680: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00 >ffffc90001727700: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffc90001727780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ==================================================================---
This bug is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].Quoted 4 lines
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot. syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches--
You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/20200704164522.GO9247%40paulmck-ThinkPad-P72.
Quoted 28 lines · Dmitry Vyukov
Quoted 14 lines · Paul E. McKenney
Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000Quoted 5 lines
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]Good catch! A call to
csd_lock_record()was on the wrong side of a call tocsd_unlock().Thanks for taking a look.
Quoted 4 lines
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
Quoted 7 lines
Quoted 3 lines
[ paulmck: Fix for [email protected] ]This should work, as far as I remember sybot looks for the email+hash anywhere in the commit.
FWIW Tested-by can make sense as well.
Paul, there is also some spike of stalls in smp_call_function, if you look at the top ones at:
https://syzkaller.appspot.com/upstream#open
Can these be caused by the same root cause?
I am not sure what trees the bug was/is present... This seems to only happen on linux-next and nowhere else. But these stalls equally happen on mainline...
Quoted 95 lines
Quoted 95 lines
Thanx, Paul
Quoted 84 lines
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xcb/0xe0 kernel/smp.c:118 Read of size 8 at addr ffffc90001727710 by task syz-executor.0/10721 CPU: 1 PID: 10721 Comm: syz-executor.0 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x18f/0x20d lib/dump_stack.c:118 print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530 csd_lock_record+0xcb/0xe0 kernel/smp.c:118 flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391 __sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248 asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706 </IRQ> __run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline] sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243 asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604 RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:765 [inline] RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline] RIP: 0010:_raw_spin_unlock_irqrestore+0x8c/0xe0 kernel/locking/spinlock.c:191 Code: 48 c7 c0 00 ff b4 89 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 75 37 48 83 3d 9b 74 c8 01 00 74 22 48 89 df 57 9d <0f> 1f 44 00 00 bf 01 00 00 00 e8 95 fb 62 f9 65 8b 05 fe 73 15 78 RSP: 0018:ffffc900016e7558 EFLAGS: 00000282 RAX: 1ffffffff1369fe0 RBX: 0000000000000282 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000282 RBP: ffffffff8cb02508 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 1ffffffff19604a0 R13: 0000000000000000 R14: dead000000000100 R15: dffffc0000000000 __debug_check_no_obj_freed lib/debugobjects.c:977 [inline] debug_check_no_obj_freed+0x20c/0x41c lib/debugobjects.c:998 free_pages_prepare mm/page_alloc.c:1219 [inline] __free_pages_ok+0x20b/0xc90 mm/page_alloc.c:1471 release_pages+0x5ec/0x17a0 mm/swap.c:880 tlb_batch_pages_flush mm/mmu_gather.c:49 [inline] tlb_flush_mmu_free mm/mmu_gather.c:242 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:249 zap_pte_range mm/memory.c:1155 [inline] zap_pmd_range mm/memory.c:1193 [inline] zap_pud_range mm/memory.c:1222 [inline] zap_p4d_range mm/memory.c:1243 [inline] unmap_page_range+0x1e22/0x2b20 mm/memory.c:1264 unmap_single_vma+0x198/0x300 mm/memory.c:1309 unmap_vmas+0x16f/0x2f0 mm/memory.c:1341 exit_mmap+0x2b1/0x530 mm/mmap.c:3165 __mmput+0x122/0x470 kernel/fork.c:1075 mmput+0x53/0x60 kernel/fork.c:1096 exit_mm kernel/exit.c:483 [inline] do_exit+0xa8f/0x2a40 kernel/exit.c:793 do_group_exit+0x125/0x310 kernel/exit.c:904 get_signal+0x40b/0x1ee0 kernel/signal.c:2743 do_signal+0x82/0x2520 arch/x86/kernel/signal.c:810 exit_to_usermode_loop arch/x86/entry/common.c:218 [inline] __prepare_exit_to_usermode+0x156/0x1f0 arch/x86/entry/common.c:252 do_syscall_64+0x6c/0xe0 arch/x86/entry/common.c:376 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45cb29 Code: Bad RIP value. RSP: 002b:00007fb154b96cf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 000000000078bf08 RCX: 000000000045cb29 RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 000000000078bf0c RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000078bf0c R13: 00007ffd3933f26f R14: 00007fb154b979c0 R15: 000000000078bf0c Memory state around the buggy address: ffffc90001727600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727680: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00 >ffffc90001727700: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffc90001727780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ==================================================================---
This bug is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].Quoted 4 lines
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot. syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches--
You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/20200704164522.GO9247%40paulmck-ThinkPad-P72.
Quoted 37 lines · Dmitry Vyukov
Quoted 28 lines · Dmitry Vyukov
Quoted 14 lines · Paul E. McKenney
Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000Quoted 5 lines
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]Good catch! A call to
csd_lock_record()was on the wrong side of a call tocsd_unlock().Thanks for taking a look.
Quoted 4 lines
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
Quoted 7 lines
Quoted 3 lines
[ paulmck: Fix for [email protected] ]This should work, as far as I remember sybot looks for the email+hash anywhere in the commit.
FWIW Tested-by can make sense as well.
Quoted 8 lines
Paul, there is also some spike of stalls in
smp_call_function, if you look at the top ones at:
https://syzkaller.appspot.com/upstream#openCan these be caused by the same root cause?
I am not sure what trees the bug was/is present... This seems to only happen on linux-next and nowhere else. But these stalls equally happen on mainline...
I would be surprised, given that the csd_unlock() was before the faulting reference. But then again, I have been surprised before.
You aren't running scftorture with its longwait parameter set to a non-zero value, are you? In that case, stalls are expected behavior. This is to support test the CSD lock diagnostics in -rcu. Which isn't in mainline yet, so maybe I am asking a stupid question.
If these are repeatable, one thing to try is to build the kernel with CSD_LOCK_WAIT_DEBUG=y. This requires c6c67d89c059 ("smp: Add source and destination CPUs to __call_single_data") and 216d15e0d870 ("kernel/smp:
Provide CSD lock timeout diagnostics") from the -rcu tree's "dev" branch. This will dump out the smp_call_function() function that was to be invoked, on the off-chance that the problem is something like lock contention in that function.
Thanx, Paul
Quoted 93 lines
Quoted 93 lines
Quoted 93 lines
Quoted 84 lines
==================================================================
BUG: KASAN: stack-out-of-bounds in csd_lock_record+0xcb/0xe0 kernel/smp.c:118 Read of size 8 at addr ffffc90001727710 by task syz-executor.0/10721 CPU: 1 PID: 10721 Comm: syz-executor.0 Not tainted 5.8.0-rc3-next-20200703-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x18f/0x20d lib/dump_stack.c:118 print_address_description.constprop.0.cold+0x5/0x436 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530 csd_lock_record+0xcb/0xe0 kernel/smp.c:118 flush_smp_call_function_queue+0x285/0x730 kernel/smp.c:391 __sysvec_call_function_single+0x98/0x490 arch/x86/kernel/smp.c:248 asm_call_on_stack+0xf/0x20 arch/x86/entry/entry_64.S:706 </IRQ> __run_on_irqstack arch/x86/include/asm/irq_stack.h:22 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:48 [inline] sysvec_call_function_single+0xe0/0x120 arch/x86/kernel/smp.c:243 asm_sysvec_call_function_single+0x12/0x20 arch/x86/include/asm/idtentry.h:604 RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:765 [inline] RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline] RIP: 0010:_raw_spin_unlock_irqrestore+0x8c/0xe0 kernel/locking/spinlock.c:191 Code: 48 c7 c0 00 ff b4 89 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 75 37 48 83 3d 9b 74 c8 01 00 74 22 48 89 df 57 9d <0f> 1f 44 00 00 bf 01 00 00 00 e8 95 fb 62 f9 65 8b 05 fe 73 15 78 RSP: 0018:ffffc900016e7558 EFLAGS: 00000282 RAX: 1ffffffff1369fe0 RBX: 0000000000000282 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000282 RBP: ffffffff8cb02508 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 1ffffffff19604a0 R13: 0000000000000000 R14: dead000000000100 R15: dffffc0000000000 __debug_check_no_obj_freed lib/debugobjects.c:977 [inline] debug_check_no_obj_freed+0x20c/0x41c lib/debugobjects.c:998 free_pages_prepare mm/page_alloc.c:1219 [inline] __free_pages_ok+0x20b/0xc90 mm/page_alloc.c:1471 release_pages+0x5ec/0x17a0 mm/swap.c:880 tlb_batch_pages_flush mm/mmu_gather.c:49 [inline] tlb_flush_mmu_free mm/mmu_gather.c:242 [inline] tlb_flush_mmu+0xe9/0x6b0 mm/mmu_gather.c:249 zap_pte_range mm/memory.c:1155 [inline] zap_pmd_range mm/memory.c:1193 [inline] zap_pud_range mm/memory.c:1222 [inline] zap_p4d_range mm/memory.c:1243 [inline] unmap_page_range+0x1e22/0x2b20 mm/memory.c:1264 unmap_single_vma+0x198/0x300 mm/memory.c:1309 unmap_vmas+0x16f/0x2f0 mm/memory.c:1341 exit_mmap+0x2b1/0x530 mm/mmap.c:3165 __mmput+0x122/0x470 kernel/fork.c:1075 mmput+0x53/0x60 kernel/fork.c:1096 exit_mm kernel/exit.c:483 [inline] do_exit+0xa8f/0x2a40 kernel/exit.c:793 do_group_exit+0x125/0x310 kernel/exit.c:904 get_signal+0x40b/0x1ee0 kernel/signal.c:2743 do_signal+0x82/0x2520 arch/x86/kernel/signal.c:810 exit_to_usermode_loop arch/x86/entry/common.c:218 [inline] __prepare_exit_to_usermode+0x156/0x1f0 arch/x86/entry/common.c:252 do_syscall_64+0x6c/0xe0 arch/x86/entry/common.c:376 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45cb29 Code: Bad RIP value. RSP: 002b:00007fb154b96cf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 000000000078bf08 RCX: 000000000045cb29 RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 000000000078bf0c RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000078bf0c R13: 00007ffd3933f26f R14: 00007fb154b979c0 R15: 000000000078bf0c Memory state around the buggy address: ffffc90001727600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727680: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 00 >ffffc90001727700: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffc90001727780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffc90001727800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ==================================================================---
This bug is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].Quoted 4 lines
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot. syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches--
You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/20200704164522.GO9247%40paulmck-ThinkPad-P72.
Quoted 43 lines · Paul E. McKenney
Quoted 41 lines · Dmitry Vyukov
Quoted 28 lines · Dmitry Vyukov
Quoted 14 lines · Paul E. McKenney
Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000Quoted 5 lines
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]Good catch! A call to
csd_lock_record()was on the wrong side of a call tocsd_unlock().Thanks for taking a look.
Quoted 4 lines
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
Quoted 7 lines
Quoted 3 lines
[ paulmck: Fix for [email protected] ]This should work, as far as I remember sybot looks for the email+hash anywhere in the commit.
FWIW Tested-by can make sense as well.Paul, there is also some spike of stalls in
smp_call_function, if you look at the top ones at:
https://syzkaller.appspot.com/upstream#open
Quoted 7 lines
Quoted 4 lines
Can these be caused by the same root cause?
I am not sure what trees the bug was/is present... This seems to only happen on linux-next and nowhere else. But these stalls equally happen on mainline...I would be surprised, given that the
csd_unlock()was before the faulting reference. But then again, I have been surprised before.
Yes, it seems unrelated.
It looks like something broken in the kernel recently and now instead of diagnosing a stall on one CPU, it diagnoses it as a stall in smp_call_function on another CPU. This produces large number of assorted stall reports which are not too actionable...
Quoted 4 lines
You aren't running scftorture with its longwait parameter set to a non-zero value, are you? In that case, stalls are expected behavior. This is to support test the CSD lock diagnostics in -rcu. Which isn't in mainline yet, so maybe I am asking a stupid question.
Since I don't know what is scftorture/longwait, I guess I am not running it :)
Quoted 7 lines
If these are repeatable, one thing to try is to build the kernel with CSD_LOCK_WAIT_DEBUG=y. This requires
c6c67d89c059("smp: Add source and destination CPUs to__call_single_data") and216d15e0d870("kernel/smp:
Provide CSD lock timeout diagnostics") from the -rcu tree's "dev" branch. This will dump out thesmp_call_function()function that was to be invoked, on the off-chance that the problem is something like lock contention in that function.
Here are some with reproducers:
https://syzkaller.appspot.com/bug?id=8a1e95291152ce5afea43c103a1fd62a257fcf4b
https://syzkaller.appspot.com/bug?id=5e3ac329b6304aacc6304cfaab1a514bca12ce82
https://syzkaller.appspot.com/bug?id=a01b4478f89e19cee91531f7c2b7751f0caf8c0c
https://syzkaller.appspot.com/bug?id=e4caef9fc41d0c019c532a4257faec129699a42e
But the question is if this CSD_LOCK_WAIT_DEBUG=y is useful in general? Should we enable it all the time?
Quoted 74 lines · Dmitry Vyukov
Quoted 43 lines · Paul E. McKenney
Quoted 41 lines · Dmitry Vyukov
Quoted 28 lines · Dmitry Vyukov
Quoted 14 lines · Paul E. McKenney
Quoted 12 lines · syzbot
Hello,
syzbot found the following crash on:
HEAD commit: 9e50b94b Add linux-next specific files for 20200703 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1024b405100000 kernel config: https://syzkaller.appspot.com/x/.config?x=f99cc0faa1476ed6 dashboard link: https://syzkaller.appspot.com/bug?extid=0f719294463916a3fc0e compiler: gcc (GCC) 10.1.0-syz 20200507 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16dc490f100000Quoted 5 lines
Quoted 2 lines
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by [email protected]Good catch! A call to
csd_lock_record()was on the wrong side of a call tocsd_unlock().Thanks for taking a look.
Quoted 4 lines
But is folded into another commit for bisectability reasons, so "Reported-by" would not make sense. I have instead added this to the commit log:
Quoted 7 lines
Quoted 3 lines
[ paulmck: Fix for [email protected] ]This should work, as far as I remember sybot looks for the email+hash anywhere in the commit.
FWIW Tested-by can make sense as well.Paul, there is also some spike of stalls in
smp_call_function, if you look at the top ones at:
https://syzkaller.appspot.com/upstream#openQuoted 7 lines
Quoted 4 lines
Can these be caused by the same root cause?
I am not sure what trees the bug was/is present... This seems to only happen on linux-next and nowhere else. But these stalls equally happen on mainline...I would be surprised, given that the
csd_unlock()was before the faulting reference. But then again, I have been surprised before.Yes, it seems unrelated.
It looks like something broken in the kernel recently and now instead of diagnosing a stall on one CPU, it diagnoses it as a stall insmp_call_functionon another CPU. This produces large number of assorted stall reports which are not too actionable...Quoted 4 lines
You aren't running scftorture with its longwait parameter set to a non-zero value, are you? In that case, stalls are expected behavior. This is to support test the CSD lock diagnostics in -rcu. Which isn't in mainline yet, so maybe I am asking a stupid question.
Since I don't know what is scftorture/longwait, I guess I am not running it :)
Quoted 7 lines
If these are repeatable, one thing to try is to build the kernel with CSD_LOCK_WAIT_DEBUG=y. This requires
c6c67d89c059("smp: Add source and destination CPUs to__call_single_data") and216d15e0d870("kernel/smp:
Provide CSD lock timeout diagnostics") from the -rcu tree's "dev" branch. This will dump out thesmp_call_function()function that was to be invoked, on the off-chance that the problem is something like lock contention in that function.
Quoted 8 lines
Here are some with reproducers:
https://syzkaller.appspot.com/bug?id=8a1e95291152ce5afea43c103a1fd62a257fcf4b
https://syzkaller.appspot.com/bug?id=5e3ac329b6304aacc6304cfaab1a514bca12ce82
https://syzkaller.appspot.com/bug?id=a01b4478f89e19cee91531f7c2b7751f0caf8c0c
https://syzkaller.appspot.com/bug?id=e4caef9fc41d0c019c532a4257faec129699a42eBut the question is if this CSD_LOCK_WAIT_DEBUG=y is useful in general? Should we enable it all the time?
The CSD_LOCK_WAIT_DEBUG functionality is quite new, so it is quite possible that it is causing rather than detecting problems. ;-)
But once it is stable, then yes, it might be quite generally useful.
Thanx, Paul
[tip: core/rcu] kernel/smp: Provide CSD lock timeout diagnostics
In reply to syzbotThe following commit has been merged into the core/rcu branch of tip:
The following commit has been merged into the core/rcu branch of tip:
Commit-ID: 35feb60474bf4f7fa7840e14fc7fd344996b919d Gitweb: https://git.kernel.org/tip/35feb60474bf4f7fa7840e14fc7fd344996b919d Author: Paul E. McKenney <[email protected]> AuthorDate: Tue, 30 Jun 2020 13:22:54 -07:00 Committer: Paul E. McKenney <[email protected]> CommitterDate: Fri, 04 Sep 2020 11:52:50 -07:00
kernel/smp: Provide CSD lock timeout diagnostics
This commit causes csd_lock_wait() to emit diagnostics when a CPU fails to respond quickly enough to one of the smp_call_function() family of function calls. These diagnostics are enabled by a new CSD_LOCK_WAIT_DEBUG Kconfig option that depends on DEBUG_KERNEL.
This commit was inspired by an earlier patch by Josef Bacik.
--- kernel/smp.c | 132 ++++++++++++++++++++++++++++++++++++++++++++- lib/Kconfig.debug | 11 ++++- 2 files changed, 141 insertions(+), 2 deletions(-)
kernel/smp.c +130 -2
@@ -20,6 +20,9 @@#include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> +#include <linux/sched/clock.h> +#include <linux/nmi.h> +#include <linux/sched/debug.h> #include "smpboot.h" #include "sched/smp.h"
@@ -96,6 +99,103 @@ void __init call_function_init(void)smpcfd_prepare_cpu (smp_processor_id ()); } +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG + +static DEFINE_PER_CPU(call_single_data_t *, cur_csd); +static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); +static DEFINE_PER_CPU(void *, cur_csd_info); + +#define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC) +atomic_t csd_bug_count =ATOMIC_INIT (0 ); + +/* Record current CSD work for current CPU, NULL to erase. */ +static void csd_lock_record (call_single_data_t *csd) +{ +if (!csd) { +smp_mb ();/* NULL cur_csd after unlock. */ +__this_cpu_write (cur_csd,NULL ); +return ; + } +__this_cpu_write (cur_csd_func, csd->func); +__this_cpu_write (cur_csd_info, csd->info); +smp_wmb ();/* func and info before csd. */ +__this_cpu_write (cur_csd, csd); +smp_mb ();/* Update cur_csd before function call. */ +/* Or before unlock, as the case may be. */ +} + +static __always_inline int csd_lock_wait_getcpu(call_single_data_t *csd) +{ +unsigned int csd_type; + + csd_type =CSD_TYPE (csd); +if (csd_type ==CSD_TYPE_ASYNC || csd_type ==CSD_TYPE_SYNC ) +return csd->dst;/* Other CSD_TYPE_ values might not have ->dst. */ +return -1 ; +} + +/* +* Complain if too much time spent waiting. Note that only +* the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, +* so waiting on other types gets much less information. +*/ +static __always_inline bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) +{ +int cpu =-1 ; +int cpux; +bool firsttime; +u64 ts2, ts_delta; +call_single_data_t *cpu_cur_csd; +unsigned int flags =READ_ONCE (csd->flags); + +if (!(flags &CSD_FLAG_LOCK )) { +if (!unlikely (*bug_id)) +return true; + cpu =csd_lock_wait_getcpu (csd); +pr_alert ("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n" , + *bug_id,raw_smp_processor_id (), cpu); +return true; + } + + ts2 =sched_clock (); + ts_delta = ts2 - *ts1; +if (likely (ts_delta <=CSD_LOCK_TIMEOUT )) +return false; + + firsttime = !*bug_id; +if (firsttime) + *bug_id =atomic_inc_return (&csd_bug_count); + cpu =csd_lock_wait_getcpu (csd); +if (WARN_ONCE (cpu <0 || cpu >= nr_cpu_ids,"%s: cpu = %d\n" , __func__, cpu)) + cpux =0 ; +else + cpux = cpu; + cpu_cur_csd =smp_load_acquire (&per_cpu (cur_csd, cpux));/* Before func and info. */ +pr_alert ("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n" , + firsttime ?"Detected" :"Continued" , *bug_id,raw_smp_processor_id (), ts2 - ts0, + cpu, csd->func, csd->info); +if (cpu_cur_csd && csd != cpu_cur_csd) { +pr_alert ("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n" , + *bug_id,READ_ONCE (per_cpu (cur_csd_func, cpux)), +READ_ONCE (per_cpu (cur_csd_info, cpux))); + }else { +pr_alert ("\tcsd: CSD lock (#%d) %s.\n" , + *bug_id, !cpu_cur_csd ?"unresponsive" :"handling this request" ); + } +if (cpu >=0 ) { +if (!trigger_single_cpu_backtrace (cpu)) +dump_cpu_task (cpu); +if (!cpu_cur_csd) { +pr_alert ("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n" , *bug_id,raw_smp_processor_id (), cpu); +arch_send_call_function_single_ipi (cpu); + } + } +dump_stack (); + *ts1 = ts2; + +return false; +} +/* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources *
@@ -105,8 +205,28 @@ void __init call_function_init(void)*/ static __always_inline void csd_lock_wait(call_single_data_t *csd) { +int bug_id =0 ; +u64 ts0, ts1; + + ts1 = ts0 =sched_clock (); +for (;;) { +if (csd_lock_wait_toolong (csd, ts0, &ts1, &bug_id)) +break ; +cpu_relax (); + } +smp_acquire__after_ctrl_dep (); +} + +#else +static void csd_lock_record (call_single_data_t *csd) +{ +} + +static __always_inline void csd_lock_wait(call_single_data_t *csd) +{smp_cond_load_acquire (&csd->flags, !(VAL &CSD_FLAG_LOCK )); } +#endif static __always_inline void csd_lock(call_single_data_t *csd) {
@@ -166,9 +286,11 @@ static int generic_exec_single(int cpu, call_single_data_t *csd)* We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ +csd_lock_record (csd);csd_unlock (csd);local_irq_save (flags);func (info); +csd_lock_record (NULL );local_irq_restore (flags);return 0 ; }
@@ -268,8 +390,10 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) entry = &csd_next->llist; } +csd_lock_record (csd);func (info);csd_unlock (csd); +csd_lock_record (NULL ); }else { prev = &csd->llist; }
@@ -296,8 +420,10 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)smp_call_func_t func = csd->func;void *info = csd->info; +csd_lock_record (csd);csd_unlock (csd);func (info); +csd_lock_record (NULL ); }else if (type ==CSD_TYPE_IRQ_WORK ) {irq_work_single (csd); }
@@ -375,7 +501,8 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, csd->func = func; csd->info = info; -#ifdef CONFIG_64BIT +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG + csd->src =smp_processor_id (); csd->dst = cpu;#endif
@@ -543,7 +670,8 @@ static void smp_call_function_many_cond(const struct cpumask *mask, csd->flags |=CSD_TYPE_SYNC ; csd->func = func; csd->info = info; -#ifdef CONFIG_64BIT +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG + csd->src =smp_processor_id (); csd->dst = cpu;#endif if (llist_add (&csd->llist, &per_cpu (call_single_queue, cpu)))
lib/Kconfig.debug +11 -0
@@ -1367,6 +1367,17 @@ config WW_MUTEX_SELFTEST Say M if you want these self tests to build as a module. Say N if you are unsure. +config CSD_LOCK_WAIT_DEBUG + bool "Debugging for csd_lock_wait(), called from smp_call_function*()" + depends on DEBUG_KERNEL + depends on 64BIT + default n + help + This option enables debug prints when CPUs are slow to respond + to the smp_call_function*() IPI wrappers. These debug prints + include the IPI handler function currently executing (if any) + and relevant stack traces. + endmenu # lock debugging config TRACE_IRQFLAGS