On 01/04/2014 03:25 PM, Sasha Levin wrote:

On 12/23/2013 04:28 PM, Sasha Levin wrote:

quoted

On 12/23/2013 03:02 PM, Kirill A. Shutemov wrote:

quoted

quoted

[  265.474585] kernel BUG at mm/huge_memory.c:1440!

Could you dump_page() on the bug?

[  469.007946] page:ffffea0005bd8000 count:3 mapcount:0 mapping:ffff8800bcd3d171 index: 0x7fca81000
[  469.009362] page flags: 0x2afffff80090018(uptodate|dirty|swapcache|swapbacked)

Ping? It still shows up in 3.13-rc6.

Could you verify if a version before split PMD locks is affected or not? 
I.e. 3.12 (IIRC)? I've checked if there can be race with THP splitting 
and it seems there shouldn't be thanks to pmd_lock() protection. So that 
could be a candidate. Given the recent trinity improvements it would be 
good to determine if it's a new bug or another years old one...

Thanks,
Vlastimil

Thanks,
Sasha

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>