aboutsummaryrefslogtreecommitdiff
path: root/include/linux/ksm.h
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2013-02-22 16:35:08 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-23 17:50:19 -0800
commitcbf86cfe04a66471f23b9e62e5eba4e525f38855 (patch)
tree5572b238db52f238e3291354a4bba161f4495627 /include/linux/ksm.h
parent8aafa6a485ae77ce4a49eb1280f3d2c6074a03fb (diff)
downloadlinux-linaro-stable-cbf86cfe04a66471f23b9e62e5eba4e525f38855.tar.gz
ksm: remove old stable nodes more thoroughly
Switching merge_across_nodes after running KSM is liable to oops on stale nodes still left over from the previous stable tree. It's not something that people will often want to do, but it would be lame to demand a reboot when they're trying to determine which merge_across_nodes setting is best. How can this happen? We only permit switching merge_across_nodes when pages_shared is 0, and usually set run 2 to force that beforehand, which ought to unmerge everything: yet oopses still occur when you then run 1. Three causes: 1. The old stable tree (built according to the inverse merge_across_nodes) has not been fully torn down. A stable node lingers until get_ksm_page() notices that the page it references no longer references it: but the page is not necessarily freed as soon as expected, particularly when swapcache. Fix this with a pass through the old stable tree, applying get_ksm_page() to each of the remaining nodes (most found stale and removed immediately), with forced removal of any left over. Unless the page is still mapped: I've not seen that case, it shouldn't occur, but better to WARN_ON_ONCE and EBUSY than BUG. 2. __ksm_enter() has a nice little optimization, to insert the new mm just behind ksmd's cursor, so there's a full pass for it to stabilize (or be removed) before ksmd addresses it. Nice when ksmd is running, but not so nice when we're trying to unmerge all mms: we were missing those mms forked and inserted behind the unmerge cursor. Easily fixed by inserting at the end when KSM_RUN_UNMERGE. 3. It is possible for a KSM page to be faulted back from swapcache into an mm, just after unmerge_and_remove_all_rmap_items() scanned past it. Fix this by copying on fault when KSM_RUN_UNMERGE: but that is private to ksm.c, so dissolve the distinction between ksm_might_need_to_copy() and ksm_does_need_to_copy(), doing it all in the one call into ksm.c. A long outstanding, unrelated bugfix sneaks in with that third fix: ksm_does_need_to_copy() would copy from a !PageUptodate page (implying I/O error when read in from swap) to a page which it then marks Uptodate. Fix this case by not copying, letting do_swap_page() discover the error. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Petr Holasek <pholasek@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Izik Eidus <izik.eidus@ravellosystems.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/ksm.h')
-rw-r--r--include/linux/ksm.h18
1 files changed, 4 insertions, 14 deletions
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 3319a6967626..45c9b6a17bcb 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -16,9 +16,6 @@
struct stable_node;
struct mem_cgroup;
-struct page *ksm_does_need_to_copy(struct page *page,
- struct vm_area_struct *vma, unsigned long address);
-
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags);
@@ -73,15 +70,8 @@ static inline void set_page_stable_node(struct page *page,
* We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
* but what if the vma was unmerged while the page was swapped out?
*/
-static inline int ksm_might_need_to_copy(struct page *page,
- struct vm_area_struct *vma, unsigned long address)
-{
- struct anon_vma *anon_vma = page_anon_vma(page);
-
- return anon_vma &&
- (anon_vma->root != vma->anon_vma->root ||
- page->index != linear_page_index(vma, address));
-}
+struct page *ksm_might_need_to_copy(struct page *page,
+ struct vm_area_struct *vma, unsigned long address);
int page_referenced_ksm(struct page *page,
struct mem_cgroup *memcg, unsigned long *vm_flags);
@@ -113,10 +103,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
return 0;
}
-static inline int ksm_might_need_to_copy(struct page *page,
+static inline struct page *ksm_might_need_to_copy(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
- return 0;
+ return page;
}
static inline int page_referenced_ksm(struct page *page,