Messages in this thread | | | Date | Tue, 13 May 2014 15:44:55 -0700 | From | Dave Hansen <> | Subject | Re: [PATCH] x86, hugetlb: add missing TLB page invalidation for hugetlb_cow() |
| |
On 05/14/2014 02:29 AM, Anthony Iliopoulos wrote: > The invalidation is required in order to maintain proper semantics > under CoW conditions. In scenarios where a process clones several > threads, a thread operating on a core whose DTLB entry for a > particular hugepage has not been invalidated, will be reading from > the hugepage that belongs to the forked child process, even after > hugetlb_cow(). > > The thread will not see the updated page as long as the stale DTLB > entry remains cached, the thread attempts to write into the page, > the child process exits, or the thread gets migrated to a different > processor.
No to be too nitpicky, but this applies to ITLB too, right?
I believe this bug came all the way back from:
> commit 1e8f889b10d8d2223105719e36ce45688fedbd59 > Author: David Gibson <david@gibson.dropbear.id.au> > Date: Fri Jan 6 00:10:44 2006 -0800 > > [PATCH] Hugetlb: Copy on Write support
It was probably the first time that we ever changed an _existing_ hugetlbfs pte, and that patch probably just missed the TLB flush because none of the other pte-setting hugetlb.c code needed TLB flushes.
The bogus x86 version of huge_ptep_clear_flush() came from the s390 guys, so double-shame on IBM! :P
> commit 8fe627ec5b7c47b1654dff50536d9709863295a3 > Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> > Date: Mon Apr 28 02:13:28 2008 -0700 > > hugetlbfs: add missing TLB flush to hugetlb_cow()
This is probably an opportunity for all the other architecture maintainers to make sure that they have proper copies of huge_ptep_clear_flush().
I went through the hugetlb code on x86 and couldn't find another TLB flush that fixes this issue, and I believe this is correct, so:
Acked-by: Dave Hansen <dave.hansen@intel.com>
| |