aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>2015-08-06 15:47:08 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-08-07 04:39:42 +0300
commitf4c18e6f7b5bbb5b528b3334115806b0d76f50f9 (patch)
tree08e934ca7a74761a3d88ef6c494b93284c918b0c
parent98ed2b0052e68420f1bad6c81e3f2600d25023e7 (diff)
downloadlinux-stericsson-f4c18e6f7b5bbb5b528b3334115806b0d76f50f9.tar.gz
mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_*
The race condition addressed in commit add05cecef80 ("mm: soft-offline: don't free target page in successful page migration") was not closed completely, because that can happen not only for soft-offline, but also for hard-offline. Consider that a slab page is about to be freed into buddy pool, and then an uncorrected memory error hits the page just after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not necessary because the data on the affected page is not consumed. To solve it, this patch drops __PG_HWPOISON from page flag checks at allocation/free time. I think it's justified because __PG_HWPOISON flags is defined to prevent the page from being reused, and setting it outside the page's alloc-free cycle is a designed behavior (not a bug.) For recent months, I was annoyed about BUG_ON when soft-offlined page remains on lru cache list for a while, which is avoided by calling put_page() instead of putback_lru_page() in page migration's success path. This means that this patch reverts a major change from commit add05cecef80 about the new refcounting rule of soft-offlined pages, so "reuse window" revives. This will be closed by a subsequent patch. Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Dean Nelson <dnelson@redhat.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/page-flags.h10
-rw-r--r--mm/huge_memory.c7
-rw-r--r--mm/migrate.c5
-rw-r--r--mm/page_alloc.c4
4 files changed, 16 insertions, 10 deletions
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f34e040b34e9..41c93844fb1d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -631,15 +631,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
1 << PG_private | 1 << PG_private_2 | \
1 << PG_writeback | 1 << PG_reserved | \
1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \
- 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
+ 1 << PG_unevictable | __PG_MLOCKED | \
__PG_COMPOUND_LOCK)
/*
* Flags checked when a page is prepped for return by the page allocator.
- * Pages being prepped should not have any flags set. It they are set,
+ * Pages being prepped should not have these flags set. It they are set,
* there has been a kernel bug or struct page corruption.
+ *
+ * __PG_HWPOISON is exceptional because it needs to be kept beyond page's
+ * alloc-free cycle to prevent from reusing the page.
*/
-#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1)
+#define PAGE_FLAGS_CHECK_AT_PREP \
+ (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
#define PAGE_FLAGS_PRIVATE \
(1 << PG_private | 1 << PG_private_2)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c107094f79ba..097c7a4bfbd9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page,
/* after clearing PageTail the gup refcount can be released */
smp_mb__after_atomic();
- /*
- * retain hwpoison flag of the poisoned tail page:
- * fix for the unsuitable process killed on Guest Machine(KVM)
- * by the memory-failure.
- */
- page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
+ page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
page_tail->flags |= (page->flags &
((1L << PG_referenced) |
(1L << PG_swapbacked) |
diff --git a/mm/migrate.c b/mm/migrate.c
index ee401e4e5ef1..f2415be7d93b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -950,7 +950,10 @@ out:
list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
- if (reason != MR_MEMORY_FAILURE)
+ /* Soft-offlined page shouldn't go through lru cache list */
+ if (reason == MR_MEMORY_FAILURE)
+ put_page(page);
+ else
putback_lru_page(page);
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cb61f44eb3fc..beda41710802 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1296,6 +1296,10 @@ static inline int check_new_page(struct page *page)
bad_reason = "non-NULL mapping";
if (unlikely(atomic_read(&page->_count) != 0))
bad_reason = "nonzero _count";
+ if (unlikely(page->flags & __PG_HWPOISON)) {
+ bad_reason = "HWPoisoned (hardware-corrupted)";
+ bad_flags = __PG_HWPOISON;
+ }
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
bad_flags = PAGE_FLAGS_CHECK_AT_PREP;