[EMAIL PROTECTED] wrote on 06.11.2007 23:31:19:
> We should cut this down to the bare necessary and fold it into the
> libhugetlbfs testsuite.
Well, this testcase is already pretty close to the bare minimum
what's needed to run IB/RDMA queues.
You can compare this to for example ibv_rc_pingpong
On Tue, Nov 06, 2007 at 04:06:04PM +0100, Hoang-Nam Nguyen wrote:
> Hello Roland!
> > We currently see this when testing Infiniband on ppc64 with ehca +
> > hugetlbfs.
> > From reading the code this should also be an issue on other architectures.
> > Roland, Adam, are you aware of anything in this
Hi Adam!
On Tuesday 06 November 2007 16:05, aglitke wrote:
> Please try this patch and see if it helps.
Tested on 2.6.22 (don't have the system with 2.6.23 at the moment) and
the testcase ran perfectly.
Thanks!
Nam
___
Linuxppc-dev mailing list
Linuxppc-
Hello Roland!
> We currently see this when testing Infiniband on ppc64 with ehca +
> hugetlbfs.
> From reading the code this should also be an issue on other architectures.
> Roland, Adam, are you aware of anything in this area with mellanox
> Infiniband cards or other usages with I/O adapters?
Bel
Please try this patch and see if it helps.
commit 6decbd17d6fb70d50f6db2c348bb41d7246a67d1
Author: Adam Litke <[EMAIL PROTECTED]>
Date: Tue Nov 6 06:59:12 2007 -0800
hugetlb: follow_hugetlb_page for write access
When calling get_user_pages(), a write flag is passed in by the caller
Hello,
if get_user_pages is used on a hugetlb vma, and there was no previous write
to the pages,
follow_hugetlb_page will call
ret = hugetlb_fault(mm, vma, vaddr, 0),
although the page should be used for write access in get_user_pages.
We currently see this when testing Infiniband on ppc64 with e
