[Cluster-devel] [PATCH v2 2/2] gfs2: writeout truncated pages

[Benjamin Marzinski]

When gfs2 attempts to write a page to a file that is being truncated,
and notices that the page is completely outside of the file size, it
tries to invalidate it.  However, this may require a transaction for
journaled data files to revoke any buffers from the page on the active
items list. Unfortunately, this can happen inside a log flush, where a
transaction cannot be started. Also, gfs2 may need to be able to remove
the buffer from the ail1 list before it can finish the log flush.

To deal with this, when writing a page of a file with data journalling
enabled gfs2 now skips the check to see if the write is outside the file
size, and simply writes it anyway. This situation can only occur when
the truncate code still has the file locked exclusively, and hasn't
marked this block as free in the metadata (which happens later in
truc_dealloc).  After gfs2 writes this page out, the truncation code
will shortly invalidate it and write out any revokes if necessary.

To do this, gfs2 now implements its own version of block_write_full_page
without the check, and calls the newly exported __block_write_full_page.
It also no longer calls gfs2_writepage_common from gfs2_jdata_writepage.

Signed-off-by: Benjamin Marzinski <bmarzins at redhat.com>
---
 fs/gfs2/aops.c | 49 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 15 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 37b7bc1..82df368 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -140,6 +140,32 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
 	return nobh_writepage(page, gfs2_get_block_noalloc, wbc);
 }
 
+/* This is the same as calling block_write_full_page, but it also
+ * writes pages outside of i_size
+ */
+int gfs2_write_full_page(struct page *page, get_block_t *get_block,
+			 struct writeback_control *wbc)
+{
+	struct inode * const inode = page->mapping->host;
+	loff_t i_size = i_size_read(inode);
+	const pgoff_t end_index = i_size >> PAGE_SHIFT;
+	unsigned offset;
+
+	/*
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the  page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	offset = i_size & (PAGE_SIZE-1);
+	if (page->index == end_index && offset)
+		zero_user_segment(page, offset, PAGE_SIZE);
+
+	return __block_write_full_page(inode, page, get_block, wbc,
+				       end_buffer_async_write);
+}
+
 /**
  * __gfs2_jdata_writepage - The core of jdata writepage
  * @page: The page to write
@@ -165,7 +191,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w
 		}
 		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
 	}
-	return block_write_full_page(page, gfs2_get_block_noalloc, wbc);
+	return gfs2_write_full_page(page, gfs2_get_block_noalloc, wbc);
 }
 
 /**
@@ -180,27 +206,20 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w
 static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	int ret;
-	int done_trans = 0;
 
-	if (PageChecked(page)) {
-		if (wbc->sync_mode != WB_SYNC_ALL)
-			goto out_ignore;
-		ret = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
-		if (ret)
-			goto out_ignore;
-		done_trans = 1;
-	}
-	ret = gfs2_writepage_common(page, wbc);
-	if (ret > 0)
-		ret = __gfs2_jdata_writepage(page, wbc);
-	if (done_trans)
-		gfs2_trans_end(sdp);
+	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
+		goto out;
+	if (PageChecked(page) || current->journal_info)
+		goto out_ignore;
+	ret = __gfs2_jdata_writepage(page, wbc);
 	return ret;
 
 out_ignore:
 	redirty_page_for_writepage(wbc, page);
+out:
 	unlock_page(page);
 	return 0;
 }
-- 
1.8.3.1