Re: per-cpu related?

["Vegard Nossum" <vegard.nossum@gmail.com>]

On Sun, Jul 13, 2008 at 11:26 AM, Ingo Molnar <mingo@elte.hu> wrote:
> [    9.270000] BUG: unable to handle kernel paging request at ffff88080101c1f8
> [    9.270000] IP: [<ffffffff80230576>] dequeue_task+0x73/0xf0

[...]

> [    9.270000] RIP: 0010:[<ffffffff80230576>]  [<ffffffff80230576>] dequeue_task+0x73/0xf0
> [    9.270000] RSP: 0018:ffff88003f9b7420  EFLAGS: 00010046
> [    9.270000] RAX: ffff88000101c200 RBX: ffff88003f9b4000 RCX: ffffffff80db5d40
> [    9.270000] RDX: 00000000ffffffff RSI: ffff88003f9b6000 RDI: ffff880001026d40

I don't think this is per-cpu related.

It seems that task_thread_info(p)->cpu returns -1. This is the number
that is loaded into %rdx:

mov    0x1c(%rsi),%edx
mov    (%rax,%rdx,8),%rax <-- faulting instruction

You also had this:

[    9.270000] Thread overran stack, or stack corrupted

so it seems likely that your thread_info was corrupted as well.


Vegard

-- 
"The animistic metaphor of the bug that maliciously sneaked in while
the programmer was not looking is intellectually dishonest as it
disguises that the error is the programmer's own creation."
	-- E. W. Dijkstra, EWD1036