From 524fca1e7356f8f9f92c51ca52727187872fc5f5 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 22 Feb 2013 16:35:51 -0800 Subject: HWPOISON: fix misjudgement of page_action() for errors on mlocked pages memory_failure() can't handle memory errors on mlocked pages correctly, because page_action() judges such errors as ones on "unknown pages" instead of ones on "unevictable LRU page" or "mlocked LRU page". In order to determine page_state page_action() checks page flags at the timing of the judgement, but such page flags are not the same with those just after memory_failure() is called, because memory_failure() does unmapping of the error pages before doing page_action(). This unmapping changes the page state, especially page_remove_rmap() (called from try_to_unmap_one()) clears PG_mlocked, so page_action() can't catch mlocked pages after that. With this patch, we store the page flag of the error page before doing unmap, and (only) if the first check with page flags at the time decided the error page is unknown, we do the second check with the stored page flag. This implementation doesn't change error handling for the page types for which the first check can determine the page state correctly. [akpm@linux-foundation.org: tweak comments] Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Tony Luck Cc: Chen Gong Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e4683459ab26..8f13b26a5b93 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1021,6 +1021,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) struct page *hpage; int res; unsigned int nr_pages; + unsigned long page_flags; if (!sysctl_memory_failure_recovery) panic("Memory failure from trap %d on page %lx", trapno, pfn); @@ -1128,6 +1129,15 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ lock_page(hpage); + /* + * We use page flags to determine what action should be taken, but + * the flags can be modified by the error containment action. One + * example is an mlocked page, where PG_mlocked is cleared by + * page_remove_rmap() in try_to_unmap_one(). So to determine page status + * correctly, we save a copy of the page flags at this time. + */ + page_flags = p->flags; + /* * unpoison always clear PG_hwpoison inside page lock */ @@ -1186,12 +1196,19 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } res = -EBUSY; - for (ps = error_states;; ps++) { - if ((p->flags & ps->mask) == ps->res) { - res = page_action(ps, p, pfn); + /* + * The first check uses the current page flags which may not have any + * relevant information. The second check with the saved page flagss is + * carried out only if the first check can't determine the page status. + */ + for (ps = error_states;; ps++) + if ((p->flags & ps->mask) == ps->res) break; - } - } + if (!ps->mask) + for (ps = error_states;; ps++) + if ((page_flags & ps->mask) == ps->res) + break; + res = page_action(ps, p, pfn); out: unlock_page(hpage); return res; -- cgit v1.2.3