On 05/23/2012 06:48 PM, Christoph Lameter wrote:
On Wed, 23 May 2012, James Bottomley wrote:
So, why not simply patch slab to rely on the string lifetime being the
cache lifetime (or beyond) and therefore not having it take a copy?
Well thats they way it was for a long time. There must be some reason that
someone started to add this copying business.... Pekka?
From git:
commit 84c1cf62465e2fb0a692620dcfeb52323ab03d48
Author: Pekka Enberg <penberg@xxxxxxxxxx>
Date: Tue Sep 14 23:21:12 2010 +0300
SLUB: Fix merged slab cache names
As explained by Linus "I'm Proud to be an American" Torvalds:
Looking at the merging code, I actually think it's totally
buggy. If you have something like this:
- load module A: create slab cache A
- load module B: create slab cache B that can merge with A
- unload module A
- "cat /proc/slabinfo": BOOM. Oops.
exactly because the name is not handled correctly, and you'll have
module B holding open a slab cache that has a name pointer that points
to module A that no longer exists.
So if I understand it correctly, this is mostly because the name string
outlives the cache in the slub case, because of merging ?
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>