summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorNick Piggin <nickpiggin@yahoo.com.au>2006-09-27 12:50:02 +0400
committerLinus Torvalds <torvalds@g5.osdl.org>2006-09-27 19:26:12 +0400
commit0fd0e6b05aa096622f151cac2f81f2e6844fb1bb (patch)
tree4fd336eaea48b320f69e970323eef5dc77c62f20 /mm
parent5b99cd0effaf846240a15441aec459a592577eaf (diff)
downloadlinux-0fd0e6b05aa096622f151cac2f81f2e6844fb1bb.tar.xz
[PATCH] page invalidation cleanup
Clean up the invalidate code, and use a common function to safely remove the page from pagecache. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/truncate.c25
-rw-r--r--mm/vmscan.c27
2 files changed, 31 insertions, 21 deletions
diff --git a/mm/truncate.c b/mm/truncate.c
index c6ab55ec6883..a654928323dc 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/swap.h>
#include <linux/module.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
@@ -52,36 +53,26 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
/*
* This is for invalidate_inode_pages(). That function can be called at
* any time, and is not supposed to throw away dirty pages. But pages can
- * be marked dirty at any time too. So we re-check the dirtiness inside
- * ->tree_lock. That provides exclusion against the __set_page_dirty
- * functions.
+ * be marked dirty at any time too, so use remove_mapping which safely
+ * discards clean, unused pages.
*
* Returns non-zero if the page was successfully invalidated.
*/
static int
invalidate_complete_page(struct address_space *mapping, struct page *page)
{
+ int ret;
+
if (page->mapping != mapping)
return 0;
if (PagePrivate(page) && !try_to_release_page(page, 0))
return 0;
- write_lock_irq(&mapping->tree_lock);
- if (PageDirty(page))
- goto failed;
- if (page_count(page) != 2) /* caller's ref + pagecache ref */
- goto failed;
-
- BUG_ON(PagePrivate(page));
- __remove_from_page_cache(page);
- write_unlock_irq(&mapping->tree_lock);
+ ret = remove_mapping(mapping, page);
ClearPageUptodate(page);
- page_cache_release(page); /* pagecache ref */
- return 1;
-failed:
- write_unlock_irq(&mapping->tree_lock);
- return 0;
+
+ return ret;
}
/**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 87d340999ce8..eca70310adb2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -384,11 +384,30 @@ int remove_mapping(struct address_space *mapping, struct page *page)
BUG_ON(mapping != page_mapping(page));
write_lock_irq(&mapping->tree_lock);
-
/*
- * The non-racy check for busy page. It is critical to check
- * PageDirty _after_ making sure that the page is freeable and
- * not in use by anybody. (pagecache + us == 2)
+ * The non racy check for a busy page.
+ *
+ * Must be careful with the order of the tests. When someone has
+ * a ref to the page, it may be possible that they dirty it then
+ * drop the reference. So if PageDirty is tested before page_count
+ * here, then the following race may occur:
+ *
+ * get_user_pages(&page);
+ * [user mapping goes away]
+ * write_to(page);
+ * !PageDirty(page) [good]
+ * SetPageDirty(page);
+ * put_page(page);
+ * !page_count(page) [good, discard it]
+ *
+ * [oops, our write_to data is lost]
+ *
+ * Reversing the order of the tests ensures such a situation cannot
+ * escape unnoticed. The smp_rmb is needed to ensure the page->flags
+ * load is not satisfied before that of page->_count.
+ *
+ * Note that if SetPageDirty is always performed via set_page_dirty,
+ * and thus under tree_lock, then this ordering is not required.
*/
if (unlikely(page_count(page) != 2))
goto cannot_free;