> Date: Thu, 5 Aug 1999 21:20:44 +1000
> From: Anton Blanchard <anton@progsoc.uts.edu.au>
> To: Robert Dinse <nanook@eskimo.com>
> Cc: linux-kernel@vger.rutgers.edu
> Subject: Re: 2.2.10 SMP spin_lock bug....
>
>
> > spin_lock (f0165514) CPU#1 stuck at f00554d8, owner PC(f0043cac):CPU3
> > spin_lock (f0165514) CPU#2 stuck at f00554d8, owner PC(f0043cac):CPU3
> > write_lock_irq (f0165514) CPU3 stuck at f0035470, owner PC(00000000):CPU(0)
> > reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i]
> > = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000
> > reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i]
> > = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000
> > reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i]
> > = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000
> > reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i]
> > = 00000000 reader [i] = 00000000 reader [i] = 00000000 reader [i] = 00000000
>
> Bad karma here. Can you lookup the hex numbers in your System.map? We can't
> use a spinlock as a rwlock, but perhaps it is one of the srmmu races.
>
> Anton
Relevant Entries (Included with original message):
f0165514 D kernel_flag
-----
f00554d8 - As close as I can come is between these two symbols:
f005546c T do_select
f00556e4 T sys_select
Does this mean it's in the do_select() function?
-----
f0043cac - As close as I can come is between these two symbols:
f0043c80 t do_try_to_free_pages
f0043d7c T kswapd
Again, this is on Sun SS-10 with quad Hypersparc CPUs.
Anybody that can elaborate on the correct interpretation, please do. As
I've previously stated, I'm not very knowledgable in the arena of Linux kernel
hacking.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/