Re: WARNING: at mm/slub.c:3357, kernel BUG at mm/slub.c:3413

[Eric Dumazet]

Le mardi 22 novembre 2011 Ã 09:45 +0100, Markus Trippelsdorf a Ãcrit :
> On 2011.11.21 at 21:18 -0600, Christoph Lameter wrote:
> > On Mon, 21 Nov 2011, Christian Kujau wrote:
> > 
> > > On Tue, 22 Nov 2011 at 07:27, Benjamin Herrenschmidt wrote:
> > > > Note that I hit a similar looking crash (sorry, I couldn't capture a
> > > > backtrace back then) on a PowerMac G5 (ppc64) while doing a large rsync
> > > > transfer yesterday with -rc2-something (cfcfc9ec) and
> > > > Christian Kujau (CC) seems to be able to reproduce something similar on
> > > > some other ppc platform (Christian, what is your setup ?)
> > >
> > > I seem to hit it with heavy disk & cpu IO is in progress on this PowerBook
> > > G4. Full dmesg & .config: http://nerdbynature.de/bits/3.2.0-rc1/oops/
> > >
> > > I've enabled some debug options and now it really points to slub.c:2166
> > 
> 
> I sometimes see the following pattern. Is this a false positive?
> 
> 
> =============================================================================
> BUG anon_vma: Redzone overwritten
> -----------------------------------------------------------------------------
> 
> INFO: 0xffff88020f347c80-0xffff88020f347c87. First byte 0xbb instead of 0xcc
> INFO: Allocated in anon_vma_fork+0x51/0x140 age=1 cpu=2 pid=1826
> 	__slab_alloc.constprop.70+0x1ac/0x1e8
> 	kmem_cache_alloc+0x12e/0x160
> 	anon_vma_fork+0x51/0x140
> 	dup_mm+0x1f2/0x4a0
> 	copy_process+0xd10/0xf70
> 	do_fork+0x100/0x2b0
> 	sys_clone+0x23/0x30
> 	stub_clone+0x13/0x20
> INFO: Freed in __put_anon_vma+0x54/0xa0 age=0 cpu=1 pid=1827
> 	__slab_free+0x33/0x2d0
> 	kmem_cache_free+0x10e/0x120
> 	__put_anon_vma+0x54/0xa0
> 	unlink_anon_vmas+0x12f/0x1c0
> 	free_pgtables+0x83/0xe0
> 	exit_mmap+0xee/0x140
> 	mmput+0x43/0xf0
> 	flush_old_exec+0x33f/0x630
> 	load_elf_binary+0x340/0x1960
> 	search_binary_handler+0x8f/0x180
> 	do_execve+0x2d3/0x370
> 	sys_execve+0x42/0x70
> 	stub_execve+0x6c/0xc0
> INFO: Slab 0xffffea00083cd1c0 objects=10 used=9 fp=0xffff88020f347ab8 flags=0x4000000000000081
> INFO: Object 0xffff88020f347c40 @offset=3136 fp=0xffff88020f347ab8

One thing you could do is to disable slub merge, with following
additional boot param : "slub_nomerge=1"



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/