summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMiaohe Lin <linmiaohe@huawei.com>2022-03-22 14:44:44 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-22 15:57:07 -0700
commit888af2701db79b9b27c7e37f9ede528a5ca53b76 (patch)
tree407681cc93ae20b77e553816228978e38c2cb132
parenta06ad3c0c75297f0b0999b1a981e50224e690ee9 (diff)
mm/memory-failure.c: fix race with changing page compound again
Patch series "A few fixup patches for memory failure", v2. This series contains a few patches to fix the race with changing page compound page, make non-LRU movable pages unhandlable and so on. More details can be found in the respective changelogs. There is a race window where we got the compound_head, the hugetlb page could be freed to buddy, or even changed to another compound page just before we try to get hwpoison page. Think about the below race window: CPU 1 CPU 2 memory_failure_hugetlb struct page *head = compound_head(p); hugetlb page might be freed to buddy, or even changed to another compound page. get_hwpoison_page -- page is not what we want now... If this race happens, just bail out. Also MF_MSG_DIFFERENT_PAGE_SIZE is introduced to record this event. [akpm@linux-foundation.org: s@/**@/*@, per Naoya Horiguchi] Link: https://lkml.kernel.org/r/20220312074613.4798-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220312074613.4798-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin <linmiaohe@huawei.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/mm.h1
-rw-r--r--include/ras/ras_event.h1
-rw-r--r--mm/memory-failure.c12
3 files changed, 14 insertions, 0 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d0978235775f..45a449e8c209 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3239,6 +3239,7 @@ enum mf_action_page_type {
MF_MSG_BUDDY,
MF_MSG_DAX,
MF_MSG_UNSPLIT_THP,
+ MF_MSG_DIFFERENT_PAGE_SIZE,
MF_MSG_UNKNOWN,
};
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index d0337a41141c..1e694fd239b9 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -374,6 +374,7 @@ TRACE_EVENT(aer_event,
EM ( MF_MSG_BUDDY, "free buddy page" ) \
EM ( MF_MSG_DAX, "dax page" ) \
EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \
+ EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" ) \
EMe ( MF_MSG_UNKNOWN, "unknown page" )
/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 086ae4eb3421..7ec855149393 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -732,6 +732,7 @@ static const char * const action_page_types[] = {
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_DAX] = "dax page",
[MF_MSG_UNSPLIT_THP] = "unsplit thp",
+ [MF_MSG_DIFFERENT_PAGE_SIZE] = "different page size",
[MF_MSG_UNKNOWN] = "unknown page",
};
@@ -1532,6 +1533,17 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
}
lock_page(head);
+
+ /*
+ * The page could have changed compound pages due to race window.
+ * If this happens just bail out.
+ */
+ if (!PageHuge(p) || compound_head(p) != head) {
+ action_result(pfn, MF_MSG_DIFFERENT_PAGE_SIZE, MF_IGNORED);
+ res = -EBUSY;
+ goto out;
+ }
+
page_flags = head->flags;
if (hwpoison_filter(p)) {