From 79352894b28550ee0eee919149f57626ec1b3572 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Thu, 19 Jul 2007 01:47:22 -0700
Subject: [PATCH] mm: fix clear_page_dirty_for_io vs fault race
Fix msync data loss and (less importantly) dirty page accounting
inaccuracies due to the race remaining in clear_page_dirty_for_io().
The deleted comment explains what the race was, and the added comments
explain how it is fixed.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/memory.c | 9 +++++++++
mm/page-writeback.c | 17 ++++++++++++-----
2 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 61d51da7e17c7..50dd3d1f4d183 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1765,6 +1765,15 @@ gotten:
unlock:
pte_unmap_unlock(page_table, ptl);
if (dirty_page) {
+ /*
+ * Yes, Virginia, this is actually required to prevent a race
+ * with clear_page_dirty_for_io() from clearing the page dirty
+ * bit after it clear all dirty ptes, but before a racing
+ * do_wp_page installs a dirty pte.
+ *
+ * do_no_page is protected similarly.
+ */
+ wait_on_page_locked(dirty_page);
set_page_dirty_balance(dirty_page);
put_page(dirty_page);
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 886ea0d5a1368..e624827180127 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -918,6 +918,8 @@ int clear_page_dirty_for_io(struct page *page)
{
struct address_space *mapping = page_mapping(page);
+ BUG_ON(!PageLocked(page));
+
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
@@ -943,14 +945,19 @@ int clear_page_dirty_for_io(struct page *page)
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
- *
- * FIXME! We still have a race here: if somebody
- * adds the page back to the page tables in
- * between the "page_mkclean()" and the "TestClearPageDirty()",
- * we might have it mapped without the dirty bit set.
*/
if (page_mkclean(page))
set_page_dirty(page);
+ /*
+ * We carefully synchronise fault handlers against
+ * installing a dirty pte and marking the page dirty
+ * at this point. We do this by having them hold the
+ * page lock at some point after installing their
+ * pte, but before marking the page dirty.
+ * Pages are always locked coming in here, so we get
+ * the desired exclusion. See mm/memory.c:do_wp_page()
+ * for more comments.
+ */
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
return 1;
--
2.30.2