mm: failslab: Add support to force slab alloc failures based on size.
authorKrishna Reddy <vdumpa@nvidia.com>
Wed, 18 Jul 2012 21:06:50 +0000 (14:06 -0700)
committerSimone Willett <swillett@nvidia.com>
Sat, 28 Jul 2012 01:18:57 +0000 (18:18 -0700)
commitc4a16ddeba4bd015d0d761780414800dbb013b55
treebf8685b1661a69ec29e07e5ebf0c7108b9456988
parentdc251e8eb5a55ec2acd3f2bccaf3d5d5c1e8bed2
mm: failslab: Add support to force slab alloc failures based on size.

Any alloc request, with  size greater than PAGE_SIZE, to
slab allocator is not guarnateed to succeed, even though
enough memory is available, as memory can get fully fragmented
over the time.
This allows finding the slab allocator requests with size
greater than PAGE_SIZE early and avoid finding issues much late
in product life cyle.

Change-Id: Ibf13e626a671d41569415a56e775ac5e96b90ba3
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Reviewed-on: http://git-master/r/116855
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
(cherry picked from commit 604a65f8e3c9472886b48b1a287f78f11235d1ce)
Reviewed-on: http://git-master/r/118193
Reviewed-by: Alex Waterman <alexw@nvidia.com>
mm/failslab.c