LOR: sched lock vs. sio + panic in sched_choose() [ULE + SMP panic]

[David P. Reese Jr.]

Hm...  Getting a core wont be that easy.  After the previously mentionsed
sched_choose() panic:

db> call doadump
Dumping 383 MB
ata0: resetting devices ..
panic: blockable sleep lock (sleep mutex) PCPU 512 @ /usr/src/sys/vm/uma_core.c:1343
cpuid = 0; lapic.id = 00000000
Debugger("panic")


Fatal trap 3: breakpoint instruction fault while in kernel mode
cpuid = 0; lapic.id = 00000000
instruction pointer     = 0x8:0xc039a615
stack pointer           = 0x10:0xd79ae618
frame pointer           = 0x10:0xd79ae624
code segment            = base 0x0, limit 0xfffff, type 0x1b
                        = DPL 0, pres 1, def32 1, gran 1
processor eflags        = IOPL = 0
current process         = 4649 (sysctl)
Stopped at      sched_choose+0x77:      movl    0x38(%eax),%eax

Nice.

-- 

   David P. Reese Jr.                                      daver at gomerbud.com
   --------------------------------------------------------------------------
   It can be argued that returning a NULL pointer when asked to allocate
   zero bytes is a silly response to a silly question.
                                         -- FreeBSD manual page for malloc(3)