Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:

 - add GETFSMAP support

 - some performance improvements for very large file systems and for
   random write workloads into a preallocated file

 - bug fixes and cleanups.

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  jbd2: cleanup write flags handling from jbd2_write_superblock()
  ext4: mark superblock writes synchronous for nobarrier mounts
  ext4: inherit encryption xattr before other xattrs
  ext4: replace BUG_ON with WARN_ONCE in ext4_end_bio()
  ext4: avoid unnecessary transaction stalls during writeback
  ext4: preload block group descriptors
  ext4: make ext4_shutdown() static
  ext4: support GETFSMAP ioctls
  vfs: add common GETFSMAP ioctl definitions
  ext4: evict inline data when writing to memory map
  ext4: remove ext4_xattr_check_entry()
  ext4: rename ext4_xattr_check_names() to ext4_xattr_check_entries()
  ext4: merge ext4_xattr_list() into ext4_listxattr()
  ext4: constify static data that is never modified
  ext4: trim return value and 'dir' argument from ext4_insert_dentry()
  jbd2: fix dbench4 performance regression for 'nobarrier' mounts
  jbd2: Fix lockdep splat with generic/270 test
  mm: retry writepages() on ENOMEM when doing an data integrity writeback

1 files changed, 40 insertions, 0 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f0729b0705c7..5834c4d76be8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1643,6 +1643,7 @@ struct mpage_da_data {
 	 */
 	struct ext4_map_blocks map;
 	struct ext4_io_submit io_submit;	/* IO submission data */
+	unsigned int do_map:1;
 };
 
 static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -2179,6 +2180,9 @@ static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
 
 	/* First block in the extent? */
 	if (map->m_len == 0) {
+		/* We cannot map unless handle is started... */
+		if (!mpd->do_map)
+			return false;
 		map->m_lblk = lblk;
 		map->m_len = 1;
 		map->m_flags = bh->b_state & BH_FLAGS;
@@ -2231,6 +2235,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 			/* Found extent to map? */
 			if (mpd->map.m_len)
 				return 0;
+			/* Buffer needs mapping and handle is not started? */
+			if (!mpd->do_map)
+				return 0;
 			/* Everything mapped so far and we hit EOF */
 			break;
 		}
@@ -2747,6 +2754,29 @@ retry:
 		tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
 	done = false;
 	blk_start_plug(&plug);
+
+	/*
+	 * First writeback pages that don't need mapping - we can avoid
+	 * starting a transaction unnecessarily and also avoid being blocked
+	 * in the block layer on device congestion while having transaction
+	 * started.
+	 */
+	mpd.do_map = 0;
+	mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
+	if (!mpd.io_submit.io_end) {
+		ret = -ENOMEM;
+		goto unplug;
+	}
+	ret = mpage_prepare_extent_to_map(&mpd);
+	/* Submit prepared bio */
+	ext4_io_submit(&mpd.io_submit);
+	ext4_put_io_end_defer(mpd.io_submit.io_end);
+	mpd.io_submit.io_end = NULL;
+	/* Unlock pages we didn't use */
+	mpage_release_unused_pages(&mpd, false);
+	if (ret < 0)
+		goto unplug;
+
 	while (!done && mpd.first_page <= mpd.last_page) {
 		/* For each extent of pages we use new io_end */
 		mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
@@ -2775,8 +2805,10 @@ retry:
 				wbc->nr_to_write, inode->i_ino, ret);
 			/* Release allocated io_end */
 			ext4_put_io_end(mpd.io_submit.io_end);
+			mpd.io_submit.io_end = NULL;
 			break;
 		}
+		mpd.do_map = 1;
 
 		trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
 		ret = mpage_prepare_extent_to_map(&mpd);
@@ -2807,6 +2839,7 @@ retry:
 		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
 			ext4_journal_stop(handle);
 			handle = NULL;
+			mpd.do_map = 0;
 		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
@@ -2824,6 +2857,7 @@ retry:
 			ext4_journal_stop(handle);
 		} else
 			ext4_put_io_end(mpd.io_submit.io_end);
+		mpd.io_submit.io_end = NULL;
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -2839,6 +2873,7 @@ retry:
 		if (ret)
 			break;
 	}
+unplug:
 	blk_finish_plug(&plug);
 	if (!ret && !cycled && wbc->nr_to_write > 0) {
 		cycled = 1;
@@ -5855,6 +5890,11 @@ int ext4_page_mkwrite(struct vm_fault *vmf)
 	file_update_time(vma->vm_file);
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_convert_inline_data(inode);
+	if (ret)
+		goto out_ret;
+
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&