On Wed, Jun 25, 2025 at 1:30 PM K R <daharmaster...@gmail.com> wrote:
>
> [...]
> > Hi Alexander,
> >
> > The good news: I can consistently reproduce the hang problem. But the
> > bad news is that even with a WITNESS kernel and kern.witness.watch=2
> > (or even 3) I don't see any message or kernel panic.
> >
> > Any additional suggestion in order to increase debug information or
> > force the machine to go into ddb?
>
> I tried a MP_LOCKDEBUG kernel and finally got a panic, shown below.
> Sorry for not including 'show locks' and all the cpus, but my serial
Another hang, now with show locks:
ddb{2}> show locks
exclusive rwlock amaplk r = 0 (0xfffffd9a244e4e78)
exclusive rwlock vmmaplk r = 0 (0xfffffd9c93c4ca90)
--
ddb{2}> ps /o
TID PID UID PRFLAGS PFLAGS CPU COMMAND
322239 87810 0 0x3 0x4000000 0 semaphore
86705 31331 0 0x3 0x4000000 11 semaphore
383438 44550 0 0x3 0x4000000 14 semaphore
257640 77711 0 0x3 0x4000000 13 semaphore
450354 41159 0 0x3 0x4000000 7 semaphore
427275 25212 0 0x3 0x4000000 12 semaphore
227039 47648 0 0x3 0x4000000 8 semaphore
28812 15439 0 0x3 0x4000000 6 semaphore
37644 76378 0 0x100003 0 3K top
*305600 7089 0 0x3 0 2 nfdump
192362 7089 0 0x3 0x4000000 9 nfdump
160550 56545 0 0x3 0x4000000 4 nfdump
367292 98858 0 0x3 0x4000000 1 nfdump
--
ddb{2}> trace
db_enter() at db_enter+0x14
pmap_do_remove(fffffd9c7aa25100,d6734d0000,d6734e0000,0) at pmap_do_remove+0x4a9
uvm_unmap_kill_entry_withlock(fffffd9c93c4c990,fffffd9c80c83258,1) at
uvm_unmap_kill_entry_withlock+0x133
uvm_unmap_remove(fffffd9c93c4c990,d6734a0000,d6739a0000,ffff800055feaed0,0,1,7ff574ce4a271e31)
at uvm_unmap_remove+0x32f
sys_munmap(ffff8000fffe6070,ffff800055feafd0,ffff800055feaf50) at
sys_munmap+0x10b
syscall(ffff800055feafd0) at syscall+0x5f9
Xsyscall() at Xsyscall+0x128
end of kernel
end trace frame: 0x7365c97d4f10, count: -7
--
ddb{2}> machine ddbcpu 0
Stopped at x86_ipi_db+0x16: leave
ddb{0}> trace
x86_ipi_db(ffffffff829e6ff0) at x86_ipi_db+0x16
x86_ipi_handler() at x86_ipi_handler+0x80
Xresume_lapic_ipi() at Xresume_lapic_ipi+0x27
__mp_lock(ffffffff82b2d348) at __mp_lock+0xbe
softintr_dispatch(0) at softintr_dispatch+0xeb
dosoftint(0) at dosoftint+0x3f
Xsoftclock() at Xsoftclock+0x27
end of kernel
end trace frame: 0x71789b60c60, count: -7
--
ddb{1}> machine ddbcpu 2
Stopped at db_enter+0x14: popq %rbp
ddb{2}> trace
db_enter() at db_enter+0x14
pmap_do_remove(fffffd9c7aa25100,d6734d0000,d6734e0000,0) at pmap_do_remove+0x4a9
uvm_unmap_kill_entry_withlock(fffffd9c93c4c990,fffffd9c80c83258,1) at
uvm_unmap_kill_entry_withlock+0x133
uvm_unmap_remove(fffffd9c93c4c990,d6734a0000,d6739a0000,ffff800055feaed0,0,1,7ff574ce4a271e31)
at uvm_unmap_remove+0x32f
sys_munmap(ffff8000fffe6070,ffff800055feafd0,ffff800055feaf50) at
sys_munmap+0x10b
syscall(ffff800055feafd0) at syscall+0x5f9
Xsyscall() at Xsyscall+0x128
end of kernel
end trace frame: 0x7365c97d4f10, count: -7
--
> console session froze before that.
>
> Hope it helps,
> --Kor
>
> pmap_tlb_shootwait: spun out
> Stopped at db_enter+0x14: popq %rbp
> ddb{13}>
> --
> ddb{13}> show panic
> the kernel did not panic
> --
> ddb{13}> ps /o
> TID PID UID PRFLAGS PFLAGS CPU COMMAND
> 307801 52176 0 0x2 0x4000000 10 semaphore
> 410431 54690 0 0x2 0x4000000 15 semaphore
> 257513 26918 0 0x2 0x4000000 11 semaphore
> 138054 68532 0 0x2 0x4000000 5 semaphore
> 203059 2408 0 0x2 0x4000000 9 semaphore
> 89141 5998 0 0x2 0x4000000 8 semaphore
> 263439 99498 0 0x2 0x4000000 7 semaphore
> 477129 15941 0 0x2 0x4000000 12 semaphore
> 41845 21800 0 0x3 0x4000000 2 nfdump
> 371022 21800 0 0x3 0x4000000 0 nfdump
> *391905 66338 0 0x3 0x4000000 13 nfdump
> 367615 66338 0 0x3 0x4000000 6 nfdump
> 394180 56727 0 0x3 0x4000000 3 nfdump
> 46184 33300 0 0x100003 0 1K top
> --
> ddb{13}> trace
> db_enter() at db_enter+0x14
> pmap_page_remove(fffffd8184bdc408) at pmap_page_remove+0x38e
> uvm_anfree_list(fffffd9c88e2be50,0) at uvm_anfree_list+0x63
> amap_wipeout(fffffd9ca390fc88) at amap_wipeout+0x198
> uvm_unmap_detach(ffff80005608fcc0,0) at uvm_unmap_detach+0xbe
> sys_munmap(ffff800055cda540,ffff80005608fdc0,ffff80005608fd40) at
> sys_munmap+0x185
> syscall(ffff80005608fdc0) at syscall+0x5f9
> Xsyscall() at Xsyscall+0x128
> end of kernel
> end trace frame: 0x123cf0e2b80, count: -8
> --
> ddb{13}> machine ddbcpu 1
> Stopped at x86_ipi_db+0x16: leave
>
> ddb{1}> trace
> x86_ipi_db(ffff8000552aaff0) at x86_ipi_db+0x16
> x86_ipi_handler() at x86_ipi_handler+0x80
> Xresume_lapic_ipi() at Xresume_lapic_ipi+0x27
> pmap_enter(fffffd9cd8988d00,7103880b6000,1c7767a000,3,33) at pmap_enter+0x703
> uvm_fault_upper(ffff800055da4928,ffff800055da4960,ffff800055da4820) at
> uvm_fault_upper+0x1e0
> uvm_fault(fffffd9ca1ab8b58,7103880b6000,2,3) at uvm_fault+0xce
> uvm_fault_wire(fffffd9ca1ab8b58,7103880b6000,7103880b7000,3) at
> uvm_fault_wire+0x58
> uvm_map_pageable_wire(fffffd9ca1ab8b58,fffffd9c8f522700,fffffd9ca0915ab8,0,3,0)
> at uvm_map_pageable_wire+0x19d
> sysctl_vslock(7103880b6d68,18) at sysctl_vslock+0x9b
> sys_sysctl(ffff800055d61c60,ffff800055da4c80,ffff800055da4c00) at
> sys_sysctl+0x187
> syscall(ffff800055da4c80) at syscall+0x5f9
> Xsyscall() at Xsyscall+0x128
> end of kernel
> end trace frame: 0x7103880b6dc0, count: -12
> --
>
> [...]
