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

Pull ext4 updates from Ted Ts'o:
 "In addition to some ext4 bug fixes and cleanups, this cycle we add the
  orphan_file feature, which eliminates bottlenecks when doing a large
  number of parallel truncates and file deletions, and move the discard
  operation out of the jbd2 commit thread when using the discard mount
  option, to better support devices with slow discard operations"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
  ext4: make the updating inode data procedure atomic
  ext4: remove an unnecessary if statement in __ext4_get_inode_loc()
  ext4: move inode eio simulation behind io completeion
  ext4: Improve scalability of ext4 orphan file handling
  ext4: Orphan file documentation
  ext4: Speedup ext4 orphan inode handling
  ext4: Move orphan inode handling into a separate file
  ext4: Support for checksumming from journal triggers
  ext4: fix race writing to an inline_data file while its xattrs are changing
  jbd2: add sparse annotations for add_transaction_credits()
  ext4: fix sparse warnings
  ext4: Make sure quota files are not grabbed accidentally
  ext4: fix e2fsprogs checksum failure for mounted filesystem
  ext4: if zeroout fails fall back to splitting the extent node
  ext4: reduce arguments of ext4_fc_add_dentry_tlv
  ext4: flush background discard kwork when retry allocation
  ext4: get discard out of jbd2 commit kthread contex
  ext4: remove the repeated comment of ext4_trim_all_free
  ext4: add new helper interface ext4_try_to_trim_range()
  ext4: remove the 'group' parameter of ext4_trim_extent
  ...

1 files changed, 22 insertions, 192 deletions

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f3bbcd4efb56..da7698341d7d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -70,7 +70,8 @@ static struct buffer_head *ext4_append(handle_t *handle,
 	inode->i_size += inode->i_sb->s_blocksize;
 	EXT4_I(inode)->i_disksize = inode->i_size;
 	BUFFER_TRACE(bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh);
+	err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
+					    EXT4_JTR_NONE);
 	if (err) {
 		brelse(bh);
 		ext4_std_error(inode->i_sb, err);
@@ -1927,12 +1928,14 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	}
 
 	BUFFER_TRACE(*bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, *bh);
+	err = ext4_journal_get_write_access(handle, dir->i_sb, *bh,
+					    EXT4_JTR_NONE);
 	if (err)
 		goto journal_error;
 
 	BUFFER_TRACE(frame->bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, frame->bh);
+	err = ext4_journal_get_write_access(handle, dir->i_sb, frame->bh,
+					    EXT4_JTR_NONE);
 	if (err)
 		goto journal_error;
 
@@ -2109,7 +2112,8 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 			return err;
 	}
 	BUFFER_TRACE(bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh);
+	err = ext4_journal_get_write_access(handle, dir->i_sb, bh,
+					    EXT4_JTR_NONE);
 	if (err) {
 		ext4_std_error(dir->i_sb, err);
 		return err;
@@ -2167,7 +2171,8 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 	blocksize =  dir->i_sb->s_blocksize;
 	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
 	BUFFER_TRACE(bh, "get_write_access");
-	retval = ext4_journal_get_write_access(handle, bh);
+	retval = ext4_journal_get_write_access(handle, dir->i_sb, bh,
+					       EXT4_JTR_NONE);
 	if (retval) {
 		ext4_std_error(dir->i_sb, retval);
 		brelse(bh);
@@ -2419,7 +2424,7 @@ again:
 	}
 
 	BUFFER_TRACE(bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh);
+	err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE);
 	if (err)
 		goto journal_error;
 
@@ -2476,7 +2481,8 @@ again:
 		node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize,
 							   sb->s_blocksize);
 		BUFFER_TRACE(frame->bh, "get_write_access");
-		err = ext4_journal_get_write_access(handle, frame->bh);
+		err = ext4_journal_get_write_access(handle, sb, frame->bh,
+						    EXT4_JTR_NONE);
 		if (err)
 			goto journal_error;
 		if (!add_level) {
@@ -2486,8 +2492,9 @@ again:
 				       icount1, icount2));
 
 			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
-			err = ext4_journal_get_write_access(handle,
-							     (frame - 1)->bh);
+			err = ext4_journal_get_write_access(handle, sb,
+							    (frame - 1)->bh,
+							    EXT4_JTR_NONE);
 			if (err)
 				goto journal_error;
 
@@ -2636,7 +2643,8 @@ static int ext4_delete_entry(handle_t *handle,
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	BUFFER_TRACE(bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh);
+	err = ext4_journal_get_write_access(handle, dir->i_sb, bh,
+					    EXT4_JTR_NONE);
 	if (unlikely(err))
 		goto out;
 
@@ -3046,186 +3054,6 @@ bool ext4_empty_dir(struct inode *inode)
 	return true;
 }
 
-/*
- * ext4_orphan_add() links an unlinked or truncated inode into a list of
- * such inodes, starting at the superblock, in case we crash before the
- * file is closed/deleted, or in case the inode truncate spans multiple
- * transactions and the last transaction is not recovered after a crash.
- *
- * At filesystem recovery time, we walk this list deleting unlinked
- * inodes and truncating linked inodes in ext4_orphan_cleanup().
- *
- * Orphan list manipulation functions must be called under i_mutex unless
- * we are just creating the inode or deleting it.
- */
-int ext4_orphan_add(handle_t *handle, struct inode *inode)
-{
-	struct super_block *sb = inode->i_sb;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_iloc iloc;
-	int err = 0, rc;
-	bool dirty = false;
-
-	if (!sbi->s_journal || is_bad_inode(inode))
-		return 0;
-
-	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
-		     !inode_is_locked(inode));
-	/*
-	 * Exit early if inode already is on orphan list. This is a big speedup
-	 * since we don't have to contend on the global s_orphan_lock.
-	 */
-	if (!list_empty(&EXT4_I(inode)->i_orphan))
-		return 0;
-
-	/*
-	 * Orphan handling is only valid for files with data blocks
-	 * being truncated, or files being unlinked. Note that we either
-	 * hold i_mutex, or the inode can not be referenced from outside,
-	 * so i_nlink should not be bumped due to race
-	 */
-	ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
-
-	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
-	if (err)
-		goto out;
-
-	err = ext4_reserve_inode_write(handle, inode, &iloc);
-	if (err)
-		goto out;
-
-	mutex_lock(&sbi->s_orphan_lock);
-	/*
-	 * Due to previous errors inode may be already a part of on-disk
-	 * orphan list. If so skip on-disk list modification.
-	 */
-	if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
-	    (le32_to_cpu(sbi->s_es->s_inodes_count))) {
-		/* Insert this inode at the head of the on-disk orphan list */
-		NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
-		lock_buffer(sbi->s_sbh);
-		sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
-		ext4_superblock_csum_set(sb);
-		unlock_buffer(sbi->s_sbh);
-		dirty = true;
-	}
-	list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
-	mutex_unlock(&sbi->s_orphan_lock);
-
-	if (dirty) {
-		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
-		rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
-		if (!err)
-			err = rc;
-		if (err) {
-			/*
-			 * We have to remove inode from in-memory list if
-			 * addition to on disk orphan list failed. Stray orphan
-			 * list entries can cause panics at unmount time.
-			 */
-			mutex_lock(&sbi->s_orphan_lock);
-			list_del_init(&EXT4_I(inode)->i_orphan);
-			mutex_unlock(&sbi->s_orphan_lock);
-		}
-	} else
-		brelse(iloc.bh);
-
-	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
-	jbd_debug(4, "orphan inode %lu will point to %d\n",
-			inode->i_ino, NEXT_ORPHAN(inode));
-out:
-	ext4_std_error(sb, err);
-	return err;
-}
-
-/*
- * ext4_orphan_del() removes an unlinked or truncated inode from the list
- * of such inodes stored on disk, because it is finally being cleaned up.
- */
-int ext4_orphan_del(handle_t *handle, struct inode *inode)
-{
-	struct list_head *prev;
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u32 ino_next;
-	struct ext4_iloc iloc;
-	int err = 0;
-
-	if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
-		return 0;
-
-	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
-		     !inode_is_locked(inode));
-	/* Do this quick check before taking global s_orphan_lock. */
-	if (list_empty(&ei->i_orphan))
-		return 0;
-
-	if (handle) {
-		/* Grab inode buffer early before taking global s_orphan_lock */
-		err = ext4_reserve_inode_write(handle, inode, &iloc);
-	}
-
-	mutex_lock(&sbi->s_orphan_lock);
-	jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
-
-	prev = ei->i_orphan.prev;
-	list_del_init(&ei->i_orphan);
-
-	/* If we're on an error path, we may not have a valid
-	 * transaction handle with which to update the orphan list on
-	 * disk, but we still need to remove the inode from the linked
-	 * list in memory. */
-	if (!handle || err) {
-		mutex_unlock(&sbi->s_orphan_lock);
-		goto out_err;
-	}
-
-	ino_next = NEXT_ORPHAN(inode);
-	if (prev == &sbi->s_orphan) {
-		jbd_debug(4, "superblock will point to %u\n", ino_next);
-		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
-		err = ext4_journal_get_write_access(handle, sbi->s_sbh);
-		if (err) {
-			mutex_unlock(&sbi->s_orphan_lock);
-			goto out_brelse;
-		}
-		lock_buffer(sbi->s_sbh);
-		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
-		ext4_superblock_csum_set(inode->i_sb);
-		unlock_buffer(sbi->s_sbh);
-		mutex_unlock(&sbi->s_orphan_lock);
-		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
-	} else {
-		struct ext4_iloc iloc2;
-		struct inode *i_prev =
-			&list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
-
-		jbd_debug(4, "orphan inode %lu will point to %u\n",
-			  i_prev->i_ino, ino_next);
-		err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
-		if (err) {
-			mutex_unlock(&sbi->s_orphan_lock);
-			goto out_brelse;
-		}
-		NEXT_ORPHAN(i_prev) = ino_next;
-		err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
-		mutex_unlock(&sbi->s_orphan_lock);
-	}
-	if (err)
-		goto out_brelse;
-	NEXT_ORPHAN(inode) = 0;
-	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-out_err:
-	ext4_std_error(inode->i_sb, err);
-	return err;
-
-out_brelse:
-	brelse(iloc.bh);
-	goto out_err;
-}
-
 static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int retval;
@@ -3675,7 +3503,8 @@ static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
 	if (le32_to_cpu(ent->parent_de->inode) != ent->dir->i_ino)
 		return -EFSCORRUPTED;
 	BUFFER_TRACE(ent->dir_bh, "get_write_access");
-	return ext4_journal_get_write_access(handle, ent->dir_bh);
+	return ext4_journal_get_write_access(handle, ent->dir->i_sb,
+					     ent->dir_bh, EXT4_JTR_NONE);
 }
 
 static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
@@ -3710,7 +3539,8 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
 	int retval, retval2;
 
 	BUFFER_TRACE(ent->bh, "get write access");
-	retval = ext4_journal_get_write_access(handle, ent->bh);
+	retval = ext4_journal_get_write_access(handle, ent->dir->i_sb, ent->bh,
+					       EXT4_JTR_NONE);
 	if (retval)
 		return retval;
 	ent->de->inode = cpu_to_le32(ino);