The patch titled
fix migration_entry_wait() for speculative page cache
has been removed from the -mm tree. Its filename was
mm-speculative-page-references-fix-migration_entry_wait-for-speculative-page-cache.patch
This patch was dropped because it was folded into mm-speculative-page-references.patch
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: fix migration_entry_wait() for speculative page cache
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
In speculative page cache lookup protocol, page_count(page) is set to 0
while radix-tree modification is going on, truncation, migration, etc...
While page migration, a page fault to page under migration should wait
unlock_page() and migration_entry_wait() waits for the page from its pte
entry. It does get_page() -> wait_on_page_locked() -> put_page() now.
In page migration, page_freeze_refs() -> page_unfreeze_refs() is called.
Here, page_unfreeze_refs() expects page_count(page) == 0 and panics if
page_count(page) != 0. To avoid this, we shouldn't touch page_count() if
it is zero. This patch uses page_cache_get_speculative() to avoid the
panic.
Signed-off-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/migrate.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff -puN mm/migrate.c~mm-speculative-page-references-fix-migration_entry_wait-for-speculative-page-cache mm/migrate.c
--- a/mm/migrate.c~mm-speculative-page-references-fix-migration_entry_wait-for-speculative-page-cache
+++ a/mm/migrate.c
@@ -285,7 +285,15 @@ void migration_entry_wait(struct mm_stru
page = migration_entry_to_page(entry);
- get_page(page);
+ /*
+ * Once radix-tree replacement of page migration started, page_count
+ * *must* be zero. And, we don't want to call wait_on_page_locked()
+ * against a page without get_page().
+ * So, we use get_page_unless_zero(), here. Even failed, page fault
+ * will occur again.
+ */
+ if (!get_page_unless_zero(page))
+ goto out;
pte_unmap_unlock(ptep, ptl);
wait_on_page_locked(page);
put_page(page);
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
mm-speculative-page-references.patch
mm-speculative-page-references-fix-migration_entry_wait-for-speculative-page-cache.patch
define-page_file_cache-function-fix-splitlru-shmem_getpage-setpageswapbacked-sooner.patch
vmscan-split-lru-lists-into-anon-file-sets-splitlru-memcg-swapbacked-pages-active.patch
vmscan-second-chance-replacement-for-anonymous-pages-fix.patch
vmscan-second-chance-replacement-for-anonymous-pages-memcg-lru-scan-fix.patch
unevictable-lru-infrastructure-putback_lru_page-unevictable-page-handling-rework.patch
mlock-mlocked-pages-are-unevictable-fix-truncate-race-and-sevaral-comments.patch
fix-double-unlock_page-in-2626-rc5-mm3-kernel-bug-at-mm-filemapc-575.patch
restore-patch-failure-of-vmstat-unevictable-and-mlocked-pages-vm-eventspatch.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
