diff options
| author | zhong jiang <[email protected]> | 2016-08-11 22:32:55 +0000 |
|---|---|---|
| committer | Linus Torvalds <[email protected]> | 2016-08-11 23:58:13 +0000 |
| commit | c1470b33bb6e18cddd361fef339ef225b8339fe7 (patch) | |
| tree | 9689ae48f5c43edd37a8f472980817eb23485c17 /drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | |
| parent | Merge branch 'akpm' (patches from Andrew) (diff) | |
| download | kernel-c1470b33bb6e18cddd361fef339ef225b8339fe7.tar.gz kernel-c1470b33bb6e18cddd361fef339ef225b8339fe7.zip | |
mm/hugetlb: fix incorrect hugepages count during mem hotplug
When memory hotplug operates, free hugepages will be freed if the
movable node is offline. Therefore, /proc/sys/vm/nr_hugepages will be
incorrect.
Fix it by reducing max_huge_pages when the node is offlined.
[email protected] said:
: dissolve_free_huge_page intends to break a hugepage into buddy, and the
: destination hugepage is supposed to be allocated from the pool of the
: destination node, so the system-wide pool size is reduced. So adding
: h->max_huge_pages-- makes sense to me.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: zhong jiang <[email protected]>
Cc: Mike Kravetz <[email protected]>
Acked-by: Naoya Horiguchi <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c')
0 files changed, 0 insertions, 0 deletions