summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@woody.linux-foundation.org>2007-01-26 12:47:06 -0800
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-01-26 12:47:06 -0800
commitecdfc9787fe527491baefc22dce8b2dbd5b2908d (patch)
tree31e7ddac0339498095c40444f81c0b03751434ae
parent5ad0d383ddbf0d2fce43b8aac267a6c299fd2dff (diff)
Resurrect 'try_to_free_buffers()' VM hackery
It's not pretty, but it appears that ext3 with data=journal will clean pages without ever actually telling the VM that they are clean. This, in turn, will result in the VM (and balance_dirty_pages() in particular) to never realize that the pages got cleaned, and wait forever for an event that already happened. Technically, this seems to be a problem with ext3 itself, but it used to be hidden by 'try_to_free_buffers()' noticing this situation on its own, and just working around the filesystem problem. This commit re-instates that hack, in order to avoid a regression for the 2.6.20 release. This fixes bugzilla 7844: http://bugzilla.kernel.org/show_bug.cgi?id=7844 Peter Zijlstra points out that we should probably retain the debugging code that this removes from cancel_dirty_page(), and I agree, but for the imminent release we might as well just silence the warning too (since it's not a new bug: anything that triggers that warning has been around forever). Acked-by: Randy Dunlap <rdunlap@xenotime.net> Acked-by: Jens Axboe <jens.axboe@oracle.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/buffer.c15
-rw-r--r--mm/truncate.c21
2 files changed, 28 insertions, 8 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index 3b116078b4c3..460f1c43238e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2834,7 +2834,7 @@ int try_to_free_buffers(struct page *page)
int ret = 0;
BUG_ON(!PageLocked(page));
- if (PageDirty(page) || PageWriteback(page))
+ if (PageWriteback(page))
return 0;
if (mapping == NULL) { /* can this still happen? */
@@ -2845,6 +2845,19 @@ int try_to_free_buffers(struct page *page)
spin_lock(&mapping->private_lock);
ret = drop_buffers(page, &buffers_to_free);
spin_unlock(&mapping->private_lock);
+
+ /*
+ * If the filesystem writes its buffers by hand (eg ext3)
+ * then we can have clean buffers against a dirty page. We
+ * clean the page here; otherwise the VM will never notice
+ * that the filesystem did any IO at all.
+ *
+ * Also, during truncate, discard_buffer will have marked all
+ * the page's buffers clean. We discover that here and clean
+ * the page also.
+ */
+ if (ret)
+ cancel_dirty_page(page, PAGE_CACHE_SIZE);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
diff --git a/mm/truncate.c b/mm/truncate.c
index 6c79ca4a1ca7..3262740aa059 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -51,15 +51,22 @@ static inline void truncate_partial_page(struct page *page, unsigned partial)
do_invalidatepage(page, partial);
}
+/*
+ * This cancels just the dirty bit on the kernel page itself, it
+ * does NOT actually remove dirty bits on any mmap's that may be
+ * around. It also leaves the page tagged dirty, so any sync
+ * activity will still find it on the dirty lists, and in particular,
+ * clear_page_dirty_for_io() will still look at the dirty bits in
+ * the VM.
+ *
+ * Doing this should *normally* only ever be done when a page
+ * is truncated, and is not actually mapped anywhere at all. However,
+ * fs/buffer.c does this when it notices that somebody has cleaned
+ * out all the buffers on a page without actually doing it through
+ * the VM. Can you say "ext3 is horribly ugly"? Tought you could.
+ */
void cancel_dirty_page(struct page *page, unsigned int account_size)
{
- /* If we're cancelling the page, it had better not be mapped any more */
- if (page_mapped(page)) {
- static unsigned int warncount;
-
- WARN_ON(++warncount < 5);
- }
-
if (TestClearPageDirty(page)) {
struct address_space *mapping = page->mapping;
if (mapping && mapping_cap_account_dirty(mapping)) {