Re: frequent slab corruption (since a long time)

From: Dave Jones
Date: Wed Aug 02 2006 - 00:19:55 EST

On Wed, Aug 02, 2006 at 05:37:28AM +0200, Andi Kleen wrote:
> Dave Jones <davej@xxxxxxxxxx> writes:
> > Every so often, I see a slab corruption bug reported against
> > the Fedora kernels (going back as far as 2.6.11), and it's
> > still plagueing us.
> >
> > It seems to have turned up in a number of different scenarios,
> > which makes it all the more complicated, but the footprint is
> > always the same. We write ffffffff00000000 to freed memory.
> DEBUG_PAGEALLOC + a small slab patch to force the 2k slab to be
> only a single object per page (so that a kfree() immediately
> triggers an unmap) would catch it I guess.

Problem with that approach is that DEBUG_PAGEALLOC makes things
so damned slow that it's pretty much unusable, and this bug
doesn't seem to want to repeat itself to order, so I doubt
many people would put up with the slowdown long enough to chase it down.


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at