On 3/20/15 4:49 PM, David Ahern wrote:
On 3/20/15 3:17 PM, Linus Torvalds wrote:
In other words, if I read that sparc asm right (and it is very likely
that I do *not*), then "objp" is NULL, and that's why you crash.
That does appear to be why. I put a WARN_ON before
clear_obj_pfmemalloc() if objpp[i] is NULL. I got 2 splats during an
'allyesconfig' build and the system stayed up.
That's odd, because we know that objp cannot be NULL in
kmem_slab_free() (even if we allowed it, like with kfree(),
remove_vma() cannot possibly have a NULL vma, since ti dereferences it
multiple times).
So I must be misreading this completely. Somebody with better sparc
debugging mojo should double-check my logic. How would objp be NULL?
I'll add checks to higher layers and see if it reveals anything.
I did ask around and apparently this bug is hit only with the new M7
processors. DaveM: that's why you are not hitting this.
Here's another data point: If I disable NUMA I don't see the problem.
Performance drops, but no NULL pointer splats which would have been panics.
The 128 cpu ldom with NUMA enabled shows the problem every single time I
do a kernel compile (-j 128). With NUMA disabled I have done 3
allyesconfig compiles without hitting the problem. I'll put the compiles
into a loop while I head out for dinner.
--
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/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>