Re: Memory corruption & SCSI in 2.6.15

[Nathan Lynch <ntl@pobox.com>]

Linus Torvalds wrote:
> 
> On Mon, 12 Dec 2005, Benjamin Herrenschmidt wrote:
> > 
> > Current -git as of today (that is 2.6.15-rc5 + the batch of fixes Linus
> > pulled after his return) was dying in weird ways for me on POWER5. I had
> > the good idea to activate slab debugging, and I now see it detecting
> > slab corruption as soon as the IPR driver initializes.
> > 
> > Since I remember seeing a discussion somewhere on a list between Brian
> > King and Jens Axboe about use-after-free problems in SCSI and possible
> > other niceties of that sort, I though it might be related...
> > 
> > Anything I can do to help track this down ?
> 
> If it's easily repeatable, doing a "git bisect" to see when it starts 
> happening is the obvious big sledge-hammer thing to try. Even if you don't 
> bisect all the way, just narrowing it down a bit more might help.

I manually narrowed this down to between 2.6.14-git14 (good) and
2.6.15-rc1 (bad).  Will try git bisection later today.

> There's a raid1 use-after-free bugfix that I just merged and pushed out, 
> but I doubt that one is relevant. But you might try to update.

FWIW, I'm hitting this in a non-raid setup.