summaryrefslogtreecommitdiff
path: root/mm/swap.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2011-11-02 13:36:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-11-02 16:06:57 -0700
commit70b50f94f1644e2aa7cb374819cfd93f3c28d725 (patch)
tree79198cd9a92600140827a670d1ed5eefdcd23d79 /mm/swap.c
parent994c0e992522c123298b4a91b72f5e67ba2d1123 (diff)
mm: thp: tail page refcounting fix
Michel while working on the working set estimation code, noticed that calling get_page_unless_zero() on a random pfn_to_page(random_pfn) wasn't safe, if the pfn ended up being a tail page of a transparent hugepage under splitting by __split_huge_page_refcount(). He then found the problem could also theoretically materialize with page_cache_get_speculative() during the speculative radix tree lookups that uses get_page_unless_zero() in SMP if the radix tree page is freed and reallocated and get_user_pages is called on it before page_cache_get_speculative has a chance to call get_page_unless_zero(). So the best way to fix the problem is to keep page_tail->_count zero at all times. This will guarantee that get_page_unless_zero() can never succeed on any tail page. page_tail->_mapcount is guaranteed zero and is unused for all tail pages of a compound page, so we can simply account the tail page references there and transfer them to tail_page->_count in __split_huge_page_refcount() (in addition to the head_page->_mapcount). While debugging this s/_count/_mapcount/ change I also noticed get_page is called by direct-io.c on pages returned by get_user_pages. That wasn't entirely safe because the two atomic_inc in get_page weren't atomic. As opposed to other get_user_page users like secondary-MMU page fault to establish the shadow pagetables would never call any superflous get_page after get_user_page returns. It's safer to make get_page universally safe for tail pages and to use get_page_foll() within follow_page (inside get_user_pages()). get_page_foll() is safe to do the refcounting for tail pages without taking any locks because it is run within PT lock protected critical sections (PT lock for pte and page_table_lock for pmd_trans_huge). The standard get_page() as invoked by direct-io instead will now take the compound_lock but still only for tail pages. The direct-io paths are usually I/O bound and the compound_lock is per THP so very finegrined, so there's no risk of scalability issues with it. A simple direct-io benchmarks with all lockdep prove locking and spinlock debugging infrastructure enabled shows identical performance and no overhead. So it's worth it. Ideally direct-io should stop calling get_page() on pages returned by get_user_pages(). The spinlock in get_page() is already optimized away for no-THP builds but doing get_page() on tail pages returned by GUP is generally a rare operation and usually only run in I/O paths. This new refcounting on page_tail->_mapcount in addition to avoiding new RCU critical sections will also allow the working set estimation code to work without any further complexity associated to the tail page refcounting with THP. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reported-by: Michel Lespinasse <walken@google.com> Reviewed-by: Michel Lespinasse <walken@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: <stable@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/swap.c')
-rw-r--r--mm/swap.c83
1 files changed, 53 insertions, 30 deletions
diff --git a/mm/swap.c b/mm/swap.c
index 3a442f18b0b3..87627f181c3f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,39 +78,22 @@ static void put_compound_page(struct page *page)
{
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
- struct page *page_head = page->first_page;
- smp_rmb();
- /*
- * If PageTail is still set after smp_rmb() we can be sure
- * that the page->first_page we read wasn't a dangling pointer.
- * See __split_huge_page_refcount() smp_wmb().
- */
- if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+ struct page *page_head = compound_trans_head(page);
+
+ if (likely(page != page_head &&
+ get_page_unless_zero(page_head))) {
unsigned long flags;
/*
- * Verify that our page_head wasn't converted
- * to a a regular page before we got a
- * reference on it.
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
*/
- if (unlikely(!PageHead(page_head))) {
- /* PageHead is cleared after PageTail */
- smp_rmb();
- VM_BUG_ON(PageTail(page));
- goto out_put_head;
- }
- /*
- * Only run compound_lock on a valid PageHead,
- * after having it pinned with
- * get_page_unless_zero() above.
- */
- smp_mb();
- /* page_head wasn't a dangling pointer */
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
VM_BUG_ON(PageHead(page_head));
- out_put_head:
if (put_page_testzero(page_head))
__put_single_page(page_head);
out_put_single:
@@ -121,16 +104,17 @@ static void put_compound_page(struct page *page)
VM_BUG_ON(page_head != page->first_page);
/*
* We can release the refcount taken by
- * get_page_unless_zero now that
- * split_huge_page_refcount is blocked on the
- * compound_lock.
+ * get_page_unless_zero() now that
+ * __split_huge_page_refcount() is blocked on
+ * the compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON(1);
/* __split_huge_page_refcount will wait now */
- VM_BUG_ON(atomic_read(&page->_count) <= 0);
- atomic_dec(&page->_count);
+ VM_BUG_ON(page_mapcount(page) <= 0);
+ atomic_dec(&page->_mapcount);
VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+ VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
@@ -160,6 +144,45 @@ void put_page(struct page *page)
}
EXPORT_SYMBOL(put_page);
+/*
+ * This function is exported but must not be called by anything other
+ * than get_page(). It implements the slow path of get_page().
+ */
+bool __get_page_tail(struct page *page)
+{
+ /*
+ * This takes care of get_page() if run on a tail page
+ * returned by one of the get_user_pages/follow_page variants.
+ * get_user_pages/follow_page itself doesn't need the compound
+ * lock because it runs __get_page_tail_foll() under the
+ * proper PT lock that already serializes against
+ * split_huge_page().
+ */
+ unsigned long flags;
+ bool got = false;
+ struct page *page_head = compound_trans_head(page);
+
+ if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ /*
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
+ */
+ flags = compound_lock_irqsave(page_head);
+ /* here __split_huge_page_refcount won't run anymore */
+ if (likely(PageTail(page))) {
+ __get_page_tail_foll(page, false);
+ got = true;
+ }
+ compound_unlock_irqrestore(page_head, flags);
+ if (unlikely(!got))
+ put_page(page_head);
+ }
+ return got;
+}
+EXPORT_SYMBOL(__get_page_tail);
+
/**
* put_pages_list() - release a list of pages
* @pages: list of pages threaded on page->lru