[14/23] ext4: Use our own write_cache_pages()

[14/23] ext4: Use our own write_cache_pages()

[Greg KH]

2.6.27-stable review patch.  If anyone has any objections, please let us know.

------------------


From: Theodore Ts'o <tytso@mit.edu>

commit 8e48dcfbd7c0892b4cfd064d682cc4c95a29df32 upstream.

Make a copy of write_cache_pages() for the benefit of
ext4_da_writepages().  This allows us to simplify the code some, and
will allow us to further customize the code in future patches.

There are some nasty hacks in write_cache_pages(), which Linus has
(correctly) characterized as vile.  I've just copied it into
write_cache_pages_da(), without trying to clean those bits up lest I
break something in the ext4's delalloc implementation, which is a bit
fragile right now.  This will allow Dave Chinner to clean up
write_cache_pages() in mm/page-writeback.c, without worrying about
breaking ext4.  Eventually write_cache_pages_da() will go away when I
rewrite ext4's delayed allocation and create a general
ext4_writepages() which is used for all of ext4's writeback.  Until
now this is the lowest risk way to clean up the core
write_cache_pages() function.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: Dave Chinner <david@fromorbit.com>
[dev@jaysonking.com: Dropped the hunks which reverted the use of no_nrwrite_index_update, since those lines weren't ever created on 2.6.27.y]
[dev@jaysonking.com: Copied from 2.6.27.y's version of write_cache_pages(), plus the changes to it from patch "vfs: Add no_nrwrite_index_update writeback control flag"]
Signed-off-by: Jayson R. King <dev@jaysonking.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ext4/inode.c |  144 +++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 132 insertions(+), 12 deletions(-)

--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2059,17 +2059,6 @@ static int __mpage_da_writepage(struct p
 	struct buffer_head *bh, *head, fake;
 	sector_t logical;
 
-	if (mpd->io_done) {
-		/*
-		 * Rest of the page in the page_vec
-		 * redirty then and skip then. We will
-		 * try to to write them again after
-		 * starting a new transaction
-		 */
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return MPAGE_DA_EXTENT_TAIL;
-	}
 	/*
 	 * Can we merge this page to current extent?
 	 */
@@ -2160,6 +2149,137 @@ static int __mpage_da_writepage(struct p
 }
 
 /*
+ * write_cache_pages_da - walk the list of dirty pages of the given
+ * address space and call the callback function (which usually writes
+ * the pages).
+ *
+ * This is a forked version of write_cache_pages().  Differences:
+ *	Range cyclic is ignored.
+ *	no_nrwrite_index_update is always presumed true
+ */
+static int write_cache_pages_da(struct address_space *mapping,
+				struct writeback_control *wbc,
+				struct mpage_da_data *mpd)
+{
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	int ret = 0;
+	int done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;		/* Inclusive */
+	long nr_to_write = wbc->nr_to_write;
+
+	if (wbc->nonblocking && bdi_write_congested(bdi)) {
+		wbc->encountered_congestion = 1;
+		return 0;
+	}
+
+	pagevec_init(&pvec, 0);
+	index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end = wbc->range_end >> PAGE_CACHE_SHIFT;
+
+	while (!done && (index <= end)) {
+		int i;
+
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+			      PAGECACHE_TAG_DIRTY,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping. However, page->index will not change
+			 * because we have a reference on the page.
+			 */
+			if (page->index > end) {
+				done = 1;
+				break;
+			}
+
+			lock_page(page);
+
+			/*
+			 * Page truncated or invalidated. We can freely skip it
+			 * then, even for data integrity operations: the page
+			 * has disappeared concurrently, so there could be no
+			 * real expectation of this data interity operation
+			 * even if there is now a new, dirty page at the same
+			 * pagecache address.
+			 */
+			if (unlikely(page->mapping != mapping)) {
+continue_unlock:
+				unlock_page(page);
+				continue;
+			}
+
+			if (!PageDirty(page)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			if (PageWriteback(page)) {
+				if (wbc->sync_mode != WB_SYNC_NONE)
+					wait_on_page_writeback(page);
+				else
+					goto continue_unlock;
+			}
+
+			BUG_ON(PageWriteback(page));
+			if (!clear_page_dirty_for_io(page))
+				goto continue_unlock;
+
+			ret = __mpage_da_writepage(page, wbc, mpd);
+
+			if (unlikely(ret)) {
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+				} else {
+					done = 1;
+					break;
+				}
+ 			}
+
+			if (nr_to_write > 0) {
+				nr_to_write--;
+				if (nr_to_write == 0 &&
+				    wbc->sync_mode == WB_SYNC_NONE) {
+					/*
+					 * We stop writing back only if we are
+					 * not doing integrity sync. In case of
+					 * integrity sync we have to keep going
+					 * because someone may be concurrently
+					 * dirtying pages, and we might have
+					 * synced a lot of newly appeared dirty
+					 * pages, but have not synced all of the
+					 * old dirty pages.
+					 */
+					done = 1;
+					break;
+				}
+			}
+
+			if (wbc->nonblocking && bdi_write_congested(bdi)) {
+				wbc->encountered_congestion = 1;
+				done = 1;
+				break;
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	return ret;
+}
+
+
+/*
  * mpage_da_writepages - walk the list of dirty pages of the given
  * address space, allocates non-allocated blocks, maps newly-allocated
  * blocks to existing bhs and issue IO them
@@ -2192,7 +2312,7 @@ static int mpage_da_writepages(struct ad
 
 	to_write = wbc->nr_to_write;
 
-	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
+	ret = write_cache_pages_da(mapping, wbc, mpd);
 
 	/*
 	 * Handle last extent of pages

[15/23] ext4: Fix file fragmentation during large file write.

[Greg KH]

2.6.27-stable review patch.  If anyone has any objections, please let us know.

------------------


From: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

commit 22208dedbd7626e5fc4339c417f8d24cc21f79d7 upstream.

The range_cyclic writeback mode uses the address_space writeback_index
as the start index for writeback.  With delayed allocation we were
updating writeback_index wrongly resulting in highly fragmented file.
This patch reduces the number of extents reduced from 4000 to 27 for a
3GB file.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
[dev@jaysonking.com: Some changed lines from the original version of this patch were dropped, since they were rolled up with another cherry-picked patch applied to 2.6.27.y earlier.]
[dev@jaysonking.com: Use of wbc->no_nrwrite_index_update was dropped, since write_cache_pages_da() implies it.]
Signed-off-by: Jayson R. King <dev@jaysonking.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ext4/inode.c |   79 ++++++++++++++++++++++++++++++++------------------------
 1 file changed, 46 insertions(+), 33 deletions(-)

--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1721,7 +1721,11 @@ static int mpage_da_submit_io(struct mpa
 
 			pages_skipped = mpd->wbc->pages_skipped;
 			err = mapping->a_ops->writepage(page, mpd->wbc);
-			if (!err)
+			if (!err && (pages_skipped == mpd->wbc->pages_skipped))
+				/*
+				 * have successfully written the page
+				 * without skipping the same
+				 */
 				mpd->pages_written++;
 			/*
 			 * In error case, we have to continue because
@@ -2295,7 +2299,6 @@ static int mpage_da_writepages(struct ad
 			       struct writeback_control *wbc,
 			       struct mpage_da_data *mpd)
 {
-	long to_write;
 	int ret;
 
 	if (!mpd->get_block)
@@ -2310,19 +2313,18 @@ static int mpage_da_writepages(struct ad
 	mpd->pages_written = 0;
 	mpd->retval = 0;
 
-	to_write = wbc->nr_to_write;
-
 	ret = write_cache_pages_da(mapping, wbc, mpd);
-
 	/*
 	 * Handle last extent of pages
 	 */
 	if (!mpd->io_done && mpd->next_page != mpd->first_page) {
 		if (mpage_da_map_blocks(mpd) == 0)
 			mpage_da_submit_io(mpd);
-	}
 
-	wbc->nr_to_write = to_write - mpd->pages_written;
+		mpd->io_done = 1;
+		ret = MPAGE_DA_EXTENT_TAIL;
+	}
+	wbc->nr_to_write -= mpd->pages_written;
 	return ret;
 }
 
@@ -2567,11 +2569,13 @@ static int ext4_da_writepages_trans_bloc
 static int ext4_da_writepages(struct address_space *mapping,
 			      struct writeback_control *wbc)
 {
+	pgoff_t	index;
+	int range_whole = 0;
 	handle_t *handle = NULL;
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
+	long pages_written = 0, pages_skipped;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
-	long to_write, pages_skipped = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
 	/*
@@ -2605,16 +2609,20 @@ static int ext4_da_writepages(struct add
 		nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
 		wbc->nr_to_write = sbi->s_mb_stream_request;
 	}
+	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+		range_whole = 1;
 
-
-	pages_skipped = wbc->pages_skipped;
+	if (wbc->range_cyclic)
+		index = mapping->writeback_index;
+	else
+		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
 	mpd.inode = mapping->host;
 
-restart_loop:
-	to_write = wbc->nr_to_write;
-	while (!ret && to_write > 0) {
+	pages_skipped = wbc->pages_skipped;
+
+	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
 		 * we  insert one extent at a time. So we need
@@ -2647,46 +2655,51 @@ restart_loop:
 				goto out_writepages;
 			}
 		}
-		to_write -= wbc->nr_to_write;
-
 		mpd.get_block = ext4_da_get_block_write;
 		ret = mpage_da_writepages(mapping, wbc, &mpd);
 
 		ext4_journal_stop(handle);
 
-		if (mpd.retval == -ENOSPC)
+		if (mpd.retval == -ENOSPC) {
+			/* commit the transaction which would
+			 * free blocks released in the transaction
+			 * and try again
+			 */
 			jbd2_journal_force_commit_nested(sbi->s_journal);
-
-		/* reset the retry count */
-		if (ret == MPAGE_DA_EXTENT_TAIL) {
+			wbc->pages_skipped = pages_skipped;
+			ret = 0;
+		} else if (ret == MPAGE_DA_EXTENT_TAIL) {
 			/*
 			 * got one extent now try with
 			 * rest of the pages
 			 */
-			to_write += wbc->nr_to_write;
+			pages_written += mpd.pages_written;
+			wbc->pages_skipped = pages_skipped;
 			ret = 0;
-		} else if (wbc->nr_to_write) {
+		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
 			 * or we requested for a noblocking writeout
 			 * and we found the device congested
 			 */
-			to_write += wbc->nr_to_write;
 			break;
-		}
-		wbc->nr_to_write = to_write;
-	}
-
-	if (!wbc->range_cyclic && (pages_skipped != wbc->pages_skipped)) {
-		/* We skipped pages in this loop */
-		wbc->nr_to_write = to_write +
-				wbc->pages_skipped - pages_skipped;
-		wbc->pages_skipped = pages_skipped;
-		goto restart_loop;
 	}
+	if (pages_skipped != wbc->pages_skipped)
+		printk(KERN_EMERG "This should not happen leaving %s "
+				"with nr_to_write = %ld ret = %d\n",
+				__func__, wbc->nr_to_write, ret);
+
+	/* Update index */
+	index += pages_written;
+	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+		/*
+		 * set the writeback_index so that range_cyclic
+		 * mode will write it back later
+		 */
+		mapping->writeback_index = index;
 
 out_writepages:
-	wbc->nr_to_write = to_write - nr_to_writebump;
+	wbc->nr_to_write -= nr_to_writebump;
 	return ret;
 }
 

[16/23] ext4: Implement range_cyclic in ext4_da_writepages instead of write_cache_pages

[Greg KH]

2.6.27-stable review patch.  If anyone has any objections, please let us know.

------------------


From: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

commit 2acf2c261b823d9d9ed954f348b97620297a36b5 upstream.

With delayed allocation we lock the page in write_cache_pages() and
try to build an in memory extent of contiguous blocks.  This is needed
so that we can get large contiguous blocks request.  If range_cyclic
mode is enabled, write_cache_pages() will loop back to the 0 index if
no I/O has been done yet, and try to start writing from the beginning
of the range.  That causes an attempt to take the page lock of lower
index page while holding the page lock of higher index page, which can
cause a dead lock with another writeback thread.

The solution is to implement the range_cyclic behavior in
ext4_da_writepages() instead.

http://bugzilla.kernel.org/show_bug.cgi?id=12579

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Jayson R. King <dev@jaysonking.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ext4/inode.c |   21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2575,6 +2575,7 @@ static int ext4_da_writepages(struct add
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
 	long pages_written = 0, pages_skipped;
+	int range_cyclic, cycled = 1, io_done = 0;
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
@@ -2612,9 +2613,15 @@ static int ext4_da_writepages(struct add
 	if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 		range_whole = 1;
 
-	if (wbc->range_cyclic)
+	range_cyclic = wbc->range_cyclic;
+	if (wbc->range_cyclic) {
 		index = mapping->writeback_index;
-	else
+		if (index)
+			cycled = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = LLONG_MAX;
+		wbc->range_cyclic = 0;
+	} else
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 
 	mpd.wbc = wbc;
@@ -2622,6 +2629,7 @@ static int ext4_da_writepages(struct add
 
 	pages_skipped = wbc->pages_skipped;
 
+retry:
 	while (!ret && wbc->nr_to_write > 0) {
 
 		/*
@@ -2676,6 +2684,7 @@ static int ext4_da_writepages(struct add
 			pages_written += mpd.pages_written;
 			wbc->pages_skipped = pages_skipped;
 			ret = 0;
+			io_done = 1;
 		} else if (wbc->nr_to_write)
 			/*
 			 * There is no more writeout needed
@@ -2684,6 +2693,13 @@ static int ext4_da_writepages(struct add
 			 */
 			break;
 	}
+	if (!io_done && !cycled) {
+		cycled = 1;
+		index = 0;
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
+		wbc->range_end  = mapping->writeback_index - 1;
+		goto retry;
+	}
 	if (pages_skipped != wbc->pages_skipped)
 		printk(KERN_EMERG "This should not happen leaving %s "
 				"with nr_to_write = %ld ret = %d\n",
@@ -2691,6 +2707,7 @@ static int ext4_da_writepages(struct add
 
 	/* Update index */
 	index += pages_written;
+	wbc->range_cyclic = range_cyclic;
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		/*
 		 * set the writeback_index so that range_cyclic