aboutsummaryrefslogtreecommitdiff
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorJin Dongming <jin.dongming@np.css.fujitsu.com>2011-02-01 15:52:39 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2011-02-02 16:03:19 -0800
commitefeda7a41e09efce506a68c3549b60b16dd7dedd (patch)
treeaac3a6e4b1635dd4652bac9e4c3a94ff3962fe2e /mm/memory-failure.c
parentb16957c643de958ef731c03e0b24c5537490f196 (diff)
downloadlinux-efeda7a41e09efce506a68c3549b60b16dd7dedd.tar.gz
thp: fix splitting of hwpoisoned hugepages
The poisoned THP is now split with split_huge_page() in collect_procs_anon(). If kmalloc() is failed in collect_procs(), split_huge_page() could not be called. And the work after split_huge_page() for collecting the processes using poisoned page will not be done, too. So the processes using the poisoned page could not be killed. The condition becomes worse when CONFIG_DEBUG_VM == "Y". Because the poisoned THP could not be split, system panic will be caused by VM_BUG_ON(PageTransHuge(page)) in try_to_unmap(). This patch does: 1. move split_huge_page() to the place before collect_procs(). This can be sure the failure of splitting THP is caused by itself. 2. when splitting THP is failed, stop the operations after it. This can avoid unexpected system panic or non sense works. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com> Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c30
1 files changed, 28 insertions, 2 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 237aaa488f4..1e9c30b241c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -386,8 +386,6 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
struct task_struct *tsk;
struct anon_vma *av;
- if (!PageHuge(page) && unlikely(split_huge_page(page)))
- return;
read_lock(&tasklist_lock);
av = page_lock_anon_vma(page);
if (av == NULL) /* Not actually mapped anymore */
@@ -896,6 +894,34 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
}
}
+ if (PageTransHuge(hpage)) {
+ /*
+ * Verify that this isn't a hugetlbfs head page, the check for
+ * PageAnon is just for avoid tripping a split_huge_page
+ * internal debug check, as split_huge_page refuses to deal with
+ * anything that isn't an anon page. PageAnon can't go away fro
+ * under us because we hold a refcount on the hpage, without a
+ * refcount on the hpage. split_huge_page can't be safely called
+ * in the first place, having a refcount on the tail isn't
+ * enough * to be safe.
+ */
+ if (!PageHuge(hpage) && PageAnon(hpage)) {
+ if (unlikely(split_huge_page(hpage))) {
+ /*
+ * FIXME: if splitting THP is failed, it is
+ * better to stop the following operation rather
+ * than causing panic by unmapping. System might
+ * survive if the page is freed later.
+ */
+ printk(KERN_INFO
+ "MCE %#lx: failed to split THP\n", pfn);
+
+ BUG_ON(!PageHWPoison(p));
+ return SWAP_FAIL;
+ }
+ }
+ }
+
/*
* First collect all the processes that have the page
* mapped in dirty form. This has to be done before try_to_unmap,