8 files changed, 483 insertions, 132 deletions

diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index b3db2264942..045995c8ce5 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -20,6 +20,7 @@
 #include <linux/ext3_jbd.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines
@@ -39,6 +40,21 @@
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
+/*
+ * Calculate the block group number and offset, given a block number
+ */
+static void ext3_get_group_no_and_offset(struct super_block *sb,
+	ext3_fsblk_t blocknr, unsigned long *blockgrpp, ext3_grpblk_t *offsetp)
+{
+	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
+
+	blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
+	if (offsetp)
+		*offsetp = blocknr % EXT3_BLOCKS_PER_GROUP(sb);
+	if (blockgrpp)
+		*blockgrpp = blocknr / EXT3_BLOCKS_PER_GROUP(sb);
+}
+
 /**
  * ext3_get_group_desc() -- load group descriptor from disk
  * @sb:			super block
@@ -1885,3 +1901,253 @@ unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
 	return ext3_bg_num_gdb_meta(sb,group);
 
 }
+
+/**
+ * ext3_trim_all_free -- function to trim all free space in alloc. group
+ * @sb:			super block for file system
+ * @group:		allocation group to trim
+ * @start:		first group block to examine
+ * @max:		last group block to examine
+ * @gdp:		allocation group description structure
+ * @minblocks:		minimum extent block count
+ *
+ * ext3_trim_all_free walks through group's block bitmap searching for free
+ * blocks. When the free block is found, it tries to allocate this block and
+ * consequent free block to get the biggest free extent possible, until it
+ * reaches any used block. Then issue a TRIM command on this extent and free
+ * the extent in the block bitmap. This is done until whole group is scanned.
+ */
+ext3_grpblk_t ext3_trim_all_free(struct super_block *sb, unsigned int group,
+				ext3_grpblk_t start, ext3_grpblk_t max,
+				ext3_grpblk_t minblocks)
+{
+	handle_t *handle;
+	ext3_grpblk_t next, free_blocks, bit, freed, count = 0;
+	ext3_fsblk_t discard_block;
+	struct ext3_sb_info *sbi;
+	struct buffer_head *gdp_bh, *bitmap_bh = NULL;
+	struct ext3_group_desc *gdp;
+	int err = 0, ret = 0;
+
+	/*
+	 * We will update one block bitmap, and one group descriptor
+	 */
+	handle = ext3_journal_start_sb(sb, 2);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	bitmap_bh = read_block_bitmap(sb, group);
+	if (!bitmap_bh) {
+		err = -EIO;
+		goto err_out;
+	}
+
+	BUFFER_TRACE(bitmap_bh, "getting undo access");
+	err = ext3_journal_get_undo_access(handle, bitmap_bh);
+	if (err)
+		goto err_out;
+
+	gdp = ext3_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp) {
+		err = -EIO;
+		goto err_out;
+	}
+
+	BUFFER_TRACE(gdp_bh, "get_write_access");
+	err = ext3_journal_get_write_access(handle, gdp_bh);
+	if (err)
+		goto err_out;
+
+	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+	sbi = EXT3_SB(sb);
+
+	 /* Walk through the whole group */
+	while (start < max) {
+		start = bitmap_search_next_usable_block(start, bitmap_bh, max);
+		if (start < 0)
+			break;
+		next = start;
+
+		/*
+		 * Allocate contiguous free extents by setting bits in the
+		 * block bitmap
+		 */
+		while (next < max
+			&& claim_block(sb_bgl_lock(sbi, group),
+					next, bitmap_bh)) {
+			next++;
+		}
+
+		 /* We did not claim any blocks */
+		if (next == start)
+			continue;
+
+		discard_block = (ext3_fsblk_t)start +
+				ext3_group_first_block_no(sb, group);
+
+		/* Update counters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, start - next);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_sub(&sbi->s_freeblocks_counter, next - start);
+
+		/* Do not issue a TRIM on extents smaller than minblocks */
+		if ((next - start) < minblocks)
+			goto free_extent;
+
+		 /* Send the TRIM command down to the device */
+		err = sb_issue_discard(sb, discard_block, next - start,
+				       GFP_NOFS, 0);
+		count += (next - start);
+free_extent:
+		freed = 0;
+
+		/*
+		 * Clear bits in the bitmap
+		 */
+		for (bit = start; bit < next; bit++) {
+			BUFFER_TRACE(bitmap_bh, "clear bit");
+			if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, group),
+						bit, bitmap_bh->b_data)) {
+				ext3_error(sb, __func__,
+					"bit already cleared for block "E3FSBLK,
+					 (unsigned long)bit);
+				BUFFER_TRACE(bitmap_bh, "bit already cleared");
+			} else {
+				freed++;
+			}
+		}
+
+		/* Update couters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, freed);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_add(&sbi->s_freeblocks_counter, freed);
+
+		start = next;
+		if (err < 0) {
+			if (err != -EOPNOTSUPP)
+				ext3_warning(sb, __func__, "Discard command "
+					     "returned error %d\n", err);
+			break;
+		}
+
+		if (fatal_signal_pending(current)) {
+			err = -ERESTARTSYS;
+			break;
+		}
+
+		cond_resched();
+
+		/* No more suitable extents */
+		if ((free_blocks - count) < minblocks)
+			break;
+	}
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	ret = ext3_journal_dirty_metadata(handle, bitmap_bh);
+	if (!err)
+		err = ret;
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gdp_bh, "dirtied group descriptor block");
+	ret = ext3_journal_dirty_metadata(handle, gdp_bh);
+	if (!err)
+		err = ret;
+
+	ext3_debug("trimmed %d blocks in the group %d\n",
+		count, group);
+
+err_out:
+	if (err)
+		count = err;
+	ext3_journal_stop(handle);
+	brelse(bitmap_bh);
+
+	return count;
+}
+
+/**
+ * ext3_trim_fs() -- trim ioctl handle function
+ * @sb:			superblock for filesystem
+ * @start:		First Byte to trim
+ * @len:		number of Bytes to trim from start
+ * @minlen:		minimum extent length in Bytes
+ *
+ * ext3_trim_fs goes through all allocation groups containing Bytes from
+ * start to start+len. For each such a group ext3_trim_all_free function
+ * is invoked to trim all free space.
+ */
+int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+	ext3_grpblk_t last_block, first_block, free_blocks;
+	unsigned long first_group, last_group;
+	unsigned long group, ngroups;
+	struct ext3_group_desc *gdp;
+	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
+	uint64_t start, len, minlen, trimmed;
+	ext3_fsblk_t max_blks = le32_to_cpu(es->s_blocks_count);
+	int ret = 0;
+
+	start = range->start >> sb->s_blocksize_bits;
+	len = range->len >> sb->s_blocksize_bits;
+	minlen = range->minlen >> sb->s_blocksize_bits;
+	trimmed = 0;
+
+	if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+	if (start >= max_blks)
+		goto out;
+	if (start < le32_to_cpu(es->s_first_data_block)) {
+		len -= le32_to_cpu(es->s_first_data_block) - start;
+		start = le32_to_cpu(es->s_first_data_block);
+	}
+	if (start + len > max_blks)
+		len = max_blks - start;
+
+	ngroups = EXT3_SB(sb)->s_groups_count;
+	smp_rmb();
+
+	/* Determine first and last group to examine based on start and len */
+	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) start,
+				     &first_group, &first_block);
+	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) (start + len),
+				     &last_group, &last_block);
+	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
+	last_block = EXT3_BLOCKS_PER_GROUP(sb);
+
+	if (first_group > last_group)
+		return -EINVAL;
+
+	for (group = first_group; group <= last_group; group++) {
+		gdp = ext3_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			break;
+
+		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+		if (free_blocks < minlen)
+			continue;
+
+		if (len >= EXT3_BLOCKS_PER_GROUP(sb))
+			len -= (EXT3_BLOCKS_PER_GROUP(sb) - first_block);
+		else
+			last_block = first_block + len;
+
+		ret = ext3_trim_all_free(sb, group, first_block,
+					last_block, minlen);
+		if (ret < 0)
+			break;
+
+		trimmed += ret;
+		first_block = 0;
+	}
+
+	if (ret >= 0)
+		ret = 0;
+
+out:
+	range->len = trimmed * sb->s_blocksize;
+
+	return ret;
+}
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index e2e72c367cf..34f0a072b93 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -69,25 +69,26 @@ int ext3_check_dir_entry (const char * function, struct inode * dir,
 	const char * error_msg = NULL;
 	const int rlen = ext3_rec_len_from_disk(de->rec_len);
 
-	if (rlen < EXT3_DIR_REC_LEN(1))
+	if (unlikely(rlen < EXT3_DIR_REC_LEN(1)))
 		error_msg = "rec_len is smaller than minimal";
-	else if (rlen % 4 != 0)
+	else if (unlikely(rlen % 4 != 0))
 		error_msg = "rec_len % 4 != 0";
-	else if (rlen < EXT3_DIR_REC_LEN(de->name_len))
+	else if (unlikely(rlen < EXT3_DIR_REC_LEN(de->name_len)))
 		error_msg = "rec_len is too small for name_len";
-	else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
+	else if (unlikely((((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)))
 		error_msg = "directory entry across blocks";
-	else if (le32_to_cpu(de->inode) >
-			le32_to_cpu(EXT3_SB(dir->i_sb)->s_es->s_inodes_count))
+	else if (unlikely(le32_to_cpu(de->inode) >
+			le32_to_cpu(EXT3_SB(dir->i_sb)->s_es->s_inodes_count)))
 		error_msg = "inode out of bounds";
 
-	if (error_msg != NULL)
+	if (unlikely(error_msg != NULL))
 		ext3_error (dir->i_sb, function,
 			"bad entry in directory #%lu: %s - "
 			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
 			dir->i_ino, error_msg, offset,
 			(unsigned long) le32_to_cpu(de->inode),
 			rlen, de->name_len);
+
 	return error_msg == NULL ? 1 : 0;
 }
 
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index a9580617edd..ae94f6d949f 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2145,13 +2145,15 @@ static void ext3_clear_blocks(handle_t *handle, struct inode *inode,
 	if (try_to_extend_transaction(handle, inode)) {
 		if (bh) {
 			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
-			ext3_journal_dirty_metadata(handle, bh);
+			if (ext3_journal_dirty_metadata(handle, bh))
+				return;
 		}
 		ext3_mark_inode_dirty(handle, inode);
 		truncate_restart_transaction(handle, inode);
 		if (bh) {
 			BUFFER_TRACE(bh, "retaking write access");
-			ext3_journal_get_write_access(handle, bh);
+			if (ext3_journal_get_write_access(handle, bh))
+				return;
 		}
 	}
 
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 88974814783..fc080dd561f 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -276,7 +276,29 @@ group_add_out:
 		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
+	case FITRIM: {
 
+		struct super_block *sb = inode->i_sb;
+		struct fstrim_range range;
+		int ret = 0;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (copy_from_user(&range, (struct fstrim_range *)arg,
+				   sizeof(range)))
+			return -EFAULT;
+
+		ret = ext3_trim_fs(sb, &range);
+		if (ret < 0)
+			return ret;
+
+		if (copy_to_user((struct fstrim_range *)arg, &range,
+				 sizeof(range)))
+			return -EFAULT;
+
+		return 0;
+	}
 
 	default:
 		return -ENOTTY;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index a900033efcc..9dba3bd69d9 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -858,6 +858,7 @@ static struct buffer_head *ext3_find_entry(struct inode *dir,
 	struct buffer_head * bh_use[NAMEI_RA_SIZE];
 	struct buffer_head * bh, *ret = NULL;
 	unsigned long start, block, b;
+	const u8 *name = entry->name;
 	int ra_max = 0;		/* Number of bh's in the readahead
 				   buffer, bh_use[] */
 	int ra_ptr = 0;		/* Current index into readahead
@@ -871,6 +872,16 @@ static struct buffer_head *ext3_find_entry(struct inode *dir,
 	namelen = entry->len;
 	if (namelen > EXT3_NAME_LEN)
 		return NULL;
+	if ((namelen <= 2) && (name[0] == '.') &&
+	    (name[1] == '.' || name[1] == 0)) {
+		/*
+		 * "." or ".." will only be in the first block
+		 * NFS may look up ".."; "." should be handled by the VFS
+		 */
+		block = start = 0;
+		nblocks = 1;
+		goto restart;
+	}
 	if (is_dx(dir)) {
 		bh = ext3_dx_find_entry(dir, entry, res_dir, &err);
 		/*
@@ -961,55 +972,35 @@ static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
 			struct qstr *entry, struct ext3_dir_entry_2 **res_dir,
 			int *err)
 {
-	struct super_block * sb;
+	struct super_block *sb = dir->i_sb;
 	struct dx_hash_info	hinfo;
-	u32 hash;
 	struct dx_frame frames[2], *frame;
-	struct ext3_dir_entry_2 *de, *top;
 	struct buffer_head *bh;
 	unsigned long block;
 	int retval;
-	int namelen = entry->len;
-	const u8 *name = entry->name;
 
-	sb = dir->i_sb;
-	/* NFS may look up ".." - look at dx_root directory block */
-	if (namelen > 2 || name[0] != '.'|| (namelen == 2 && name[1] != '.')) {
-		if (!(frame = dx_probe(entry, dir, &hinfo, frames, err)))
-			return NULL;
-	} else {
-		frame = frames;
-		frame->bh = NULL;			/* for dx_release() */
-		frame->at = (struct dx_entry *)frames;	/* hack for zero entry*/
-		dx_set_block(frame->at, 0);		/* dx_root block is 0 */
-	}
-	hash = hinfo.hash;
+	if (!(frame = dx_probe(entry, dir, &hinfo, frames, err)))
+		return NULL;
 	do {
 		block = dx_get_block(frame->at);
 		if (!(bh = ext3_bread (NULL,dir, block, 0, err)))
 			goto errout;
-		de = (struct ext3_dir_entry_2 *) bh->b_data;
-		top = (struct ext3_dir_entry_2 *) ((char *) de + sb->s_blocksize -
-				       EXT3_DIR_REC_LEN(0));
-		for (; de < top; de = ext3_next_entry(de)) {
-			int off = (block << EXT3_BLOCK_SIZE_BITS(sb))
-				  + ((char *) de - bh->b_data);
-
-			if (!ext3_check_dir_entry(__func__, dir, de, bh, off)) {
-				brelse(bh);
-				*err = ERR_BAD_DX_DIR;
-				goto errout;
-			}
 
-			if (ext3_match(namelen, name, de)) {
-				*res_dir = de;
-				dx_release(frames);
-				return bh;
-			}
+		retval = search_dirblock(bh, dir, entry,
+					 block << EXT3_BLOCK_SIZE_BITS(sb),
+					 res_dir);
+		if (retval == 1) {
+			dx_release(frames);
+			return bh;
 		}
-		brelse (bh);
+		brelse(bh);
+		if (retval == -1) {
+			*err = ERR_BAD_DX_DIR;
+			goto errout;
+		}
+
 		/* Check to see if we should continue to search */
-		retval = ext3_htree_next_block(dir, hash, frame,
+		retval = ext3_htree_next_block(dir, hinfo.hash, frame,
 					       frames, NULL);
 		if (retval < 0) {
 			ext3_warning(sb, __func__,
@@ -1047,7 +1038,7 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
 			return ERR_PTR(-EIO);
 		}
 		inode = ext3_iget(dir->i_sb, ino);
-		if (unlikely(IS_ERR(inode))) {
+		if (IS_ERR(inode)) {
 			if (PTR_ERR(inode) == -ESTALE) {
 				ext3_error(dir->i_sb, __func__,
 						"deleted inode referenced: %lu",
@@ -1607,7 +1598,9 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		ext3_journal_dirty_metadata(handle, frames[0].bh);
+		err = ext3_journal_dirty_metadata(handle, frames[0].bh);
+		if (err)
+			goto journal_error;
 	}
 	de = do_split(handle, dir, &bh, frame, &hinfo, &err);
 	if (!de)
@@ -1644,8 +1637,13 @@ static int ext3_delete_entry (handle_t *handle,
 		if (!ext3_check_dir_entry("ext3_delete_entry", dir, de, bh, i))
 			return -EIO;
 		if (de == de_del)  {
+			int err;
+
 			BUFFER_TRACE(bh, "get_write_access");
-			ext3_journal_get_write_access(handle, bh);
+			err = ext3_journal_get_write_access(handle, bh);
+			if (err)
+				goto journal_error;
+
 			if (pde)
 				pde->rec_len = ext3_rec_len_to_disk(
 					ext3_rec_len_from_disk(pde->rec_len) +
@@ -1654,7 +1652,12 @@ static int ext3_delete_entry (handle_t *handle,
 				de->inode = 0;
 			dir->i_version++;
 			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
-			ext3_journal_dirty_metadata(handle, bh);
+			err = ext3_journal_dirty_metadata(handle, bh);
+			if (err) {
+journal_error:
+				ext3_std_error(dir->i_sb, err);
+				return err;
+			}
 			return 0;
 		}
 		i += ext3_rec_len_from_disk(de->rec_len);
@@ -1762,7 +1765,7 @@ static int ext3_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 {
 	handle_t *handle;
 	struct inode * inode;
-	struct buffer_head * dir_block;
+	struct buffer_head * dir_block = NULL;
 	struct ext3_dir_entry_2 * de;
 	int err, retries = 0;
 
@@ -1790,15 +1793,14 @@ retry:
 	inode->i_fop = &ext3_dir_operations;
 	inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize;
 	dir_block = ext3_bread (handle, inode, 0, 1, &err);
-	if (!dir_block) {
-		drop_nlink(inode); /* is this nlink == 0? */
-		unlock_new_inode(inode);
-		ext3_mark_inode_dirty(handle, inode);
-		iput (inode);
-		goto out_stop;
-	}
+	if (!dir_block)
+		goto out_clear_inode;
+
 	BUFFER_TRACE(dir_block, "get_write_access");
-	ext3_journal_get_write_access(handle, dir_block);
+	err = ext3_journal_get_write_access(handle, dir_block);
+	if (err)
+		goto out_clear_inode;
+
 	de = (struct ext3_dir_entry_2 *) dir_block->b_data;
 	de->inode = cpu_to_le32(inode->i_ino);
 	de->name_len = 1;
@@ -1814,11 +1816,16 @@ retry:
 	ext3_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext3_journal_dirty_metadata");
-	ext3_journal_dirty_metadata(handle, dir_block);
-	brelse (dir_block);
-	ext3_mark_inode_dirty(handle, inode);
-	err = ext3_add_entry (handle, dentry, inode);
+	err = ext3_journal_dirty_metadata(handle, dir_block);
+	if (err)
+		goto out_clear_inode;
+
+	err = ext3_mark_inode_dirty(handle, inode);
+	if (!err)
+		err = ext3_add_entry (handle, dentry, inode);
+
 	if (err) {
+out_clear_inode:
 		inode->i_nlink = 0;
 		unlock_new_inode(inode);
 		ext3_mark_inode_dirty(handle, inode);
@@ -1827,10 +1834,14 @@ retry:
 	}
 	inc_nlink(dir);
 	ext3_update_dx_flag(dir);
-	ext3_mark_inode_dirty(handle, dir);
+	err = ext3_mark_inode_dirty(handle, dir);
+	if (err)
+		goto out_clear_inode;
+
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
 out_stop:
+	brelse(dir_block);
 	ext3_journal_stop(handle);
 	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
 		goto retry;
@@ -2353,7 +2364,9 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 			goto end_rename;
 	} else {
 		BUFFER_TRACE(new_bh, "get write access");
-		ext3_journal_get_write_access(handle, new_bh);
+		retval = ext3_journal_get_write_access(handle, new_bh);
+		if (retval)
+			goto journal_error;
 		new_de->inode = cpu_to_le32(old_inode->i_ino);
 		if (EXT3_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
 					      EXT3_FEATURE_INCOMPAT_FILETYPE))
@@ -2362,7 +2375,9 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 		new_dir->i_ctime = new_dir->i_mtime = CURRENT_TIME_SEC;
 		ext3_mark_inode_dirty(handle, new_dir);
 		BUFFER_TRACE(new_bh, "call ext3_journal_dirty_metadata");
-		ext3_journal_dirty_metadata(handle, new_bh);
+		retval = ext3_journal_dirty_metadata(handle, new_bh);
+		if (retval)
+			goto journal_error;
 		brelse(new_bh);
 		new_bh = NULL;
 	}
@@ -2411,10 +2426,17 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 	ext3_update_dx_flag(old_dir);
 	if (dir_bh) {
 		BUFFER_TRACE(dir_bh, "get_write_access");
-		ext3_journal_get_write_access(handle, dir_bh);
+		retval = ext3_journal_get_write_access(handle, dir_bh);
+		if (retval)
+			goto journal_error;
 		PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext3_journal_dirty_metadata");
-		ext3_journal_dirty_metadata(handle, dir_bh);
+		retval = ext3_journal_dirty_metadata(handle, dir_bh);
+		if (retval) {
+journal_error:
+			ext3_std_error(new_dir->i_sb, retval);
+			goto end_rename;
+		}
 		drop_nlink(old_dir);
 		if (new_inode) {
 			drop_nlink(new_inode);
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index e746d30b123..108b142e11e 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -249,7 +249,11 @@ static int setup_new_group_blocks(struct super_block *sb,
 		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
 		set_buffer_uptodate(gdb);
 		unlock_buffer(gdb);
-		ext3_journal_dirty_metadata(handle, gdb);
+		err = ext3_journal_dirty_metadata(handle, gdb);
+		if (err) {
+			brelse(gdb);
+			goto exit_bh;
+		}
 		ext3_set_bit(bit, bh->b_data);
 		brelse(gdb);
 	}
@@ -269,7 +273,11 @@ static int setup_new_group_blocks(struct super_block *sb,
 			err = PTR_ERR(gdb);
 			goto exit_bh;
 		}
-		ext3_journal_dirty_metadata(handle, gdb);
+		err = ext3_journal_dirty_metadata(handle, gdb);
+		if (err) {
+			brelse(gdb);
+			goto exit_bh;
+		}
 		ext3_set_bit(bit, bh->b_data);
 		brelse(gdb);
 	}
@@ -295,7 +303,11 @@ static int setup_new_group_blocks(struct super_block *sb,
 			err = PTR_ERR(it);
 			goto exit_bh;
 		}
-		ext3_journal_dirty_metadata(handle, it);
+		err = ext3_journal_dirty_metadata(handle, it);
+		if (err) {
+			brelse(it);
+			goto exit_bh;
+		}
 		brelse(it);
 		ext3_set_bit(bit, bh->b_data);
 	}
@@ -306,7 +318,9 @@ static int setup_new_group_blocks(struct super_block *sb,
 
 	mark_bitmap_end(input->blocks_count, EXT3_BLOCKS_PER_GROUP(sb),
 			bh->b_data);
-	ext3_journal_dirty_metadata(handle, bh);
+	err = ext3_journal_dirty_metadata(handle, bh);
+	if (err)
+		goto exit_bh;
 	brelse(bh);
 
 	/* Mark unused entries in inode bitmap used */
@@ -319,7 +333,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 
 	mark_bitmap_end(EXT3_INODES_PER_GROUP(sb), EXT3_BLOCKS_PER_GROUP(sb),
 			bh->b_data);
-	ext3_journal_dirty_metadata(handle, bh);
+	err = ext3_journal_dirty_metadata(handle, bh);
 exit_bh:
 	brelse(bh);
 
@@ -503,12 +517,19 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	 * reserved inode, and will become GDT blocks (primary and backup).
 	 */
 	data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)] = 0;
-	ext3_journal_dirty_metadata(handle, dind);
+	err = ext3_journal_dirty_metadata(handle, dind);
+	if (err)
+		goto exit_group_desc;
 	brelse(dind);
+	dind = NULL;
 	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
-	ext3_mark_iloc_dirty(handle, inode, &iloc);
+	err = ext3_mark_iloc_dirty(handle, inode, &iloc);
+	if (err)
+		goto exit_group_desc;
 	memset((*primary)->b_data, 0, sb->s_blocksize);
-	ext3_journal_dirty_metadata(handle, *primary);
+	err = ext3_journal_dirty_metadata(handle, *primary);
+	if (err)
+		goto exit_group_desc;
 
 	o_group_desc = EXT3_SB(sb)->s_group_desc;
 	memcpy(n_group_desc, o_group_desc,
@@ -519,10 +540,14 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	kfree(o_group_desc);
 
 	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
-	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+	err = ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+	if (err)
+		goto exit_inode;
 
 	return 0;
 
+exit_group_desc:
+	kfree(n_group_desc);
 exit_inode:
 	//ext3_journal_release_buffer(handle, iloc.bh);
 	brelse(iloc.bh);
@@ -706,16 +731,20 @@ static void update_backups(struct super_block *sb,
 		}
 		ext3_debug("update metadata backup %#04lx\n",
 			  (unsigned long)bh->b_blocknr);
-		if ((err = ext3_journal_get_write_access(handle, bh)))
+		if ((err = ext3_journal_get_write_access(handle, bh))) {
+			brelse(bh);
 			break;
+		}
 		lock_buffer(bh);
 		memcpy(bh->b_data, data, size);
 		if (rest)
 			memset(bh->b_data + size, 0, rest);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
-		ext3_journal_dirty_metadata(handle, bh);
+		err = ext3_journal_dirty_metadata(handle, bh);
 		brelse(bh);
+		if (err)
+			break;
 	}
 	if ((err2 = ext3_journal_stop(handle)) && !err)
 		err = err2;
@@ -922,7 +951,9 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 	/* Update the global fs size fields */
 	sbi->s_groups_count++;
 
-	ext3_journal_dirty_metadata(handle, primary);
+	err = ext3_journal_dirty_metadata(handle, primary);
+	if (err)
+		goto exit_journal;
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
@@ -934,7 +965,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT3_INODES_PER_GROUP(sb));
 
-	ext3_journal_dirty_metadata(handle, sbi->s_sbh);
+	err = ext3_journal_dirty_metadata(handle, sbi->s_sbh);
 
 exit_journal:
 	mutex_unlock(&sbi->s_resize_lock);
@@ -1064,8 +1095,14 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 		goto exit_put;
 	}
 	es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
-	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+	err = ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
 	mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
+	if (err) {
+		ext3_warning(sb, __func__,
+			     "error %d on journal dirty metadata", err);
+		ext3_journal_stop(handle);
+		goto exit_put;
+	}
 	ext3_debug("freeing blocks "E3FSBLK" through "E3FSBLK"\n",
 		   o_blocks_count, o_blocks_count + add);
 	ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 77ce1616f72..85c8cc8f247 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -143,12 +143,16 @@ void ext3_journal_abort_handle(const char *caller, const char *err_fn,
 void ext3_msg(struct super_block *sb, const char *prefix,
 		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	printk("%sEXT3-fs (%s): ", prefix, sb->s_id);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%sEXT3-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
+
 	va_end(args);
 }
 
@@ -195,15 +199,20 @@ static void ext3_handle_error(struct super_block *sb)
 			sb->s_id);
 }
 
-void ext3_error (struct super_block * sb, const char * function,
-		 const char * fmt, ...)
+void ext3_error(struct super_block *sb, const char *function,
+		const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_CRIT "EXT3-fs error (device %s): %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
 	va_end(args);
 
 	ext3_handle_error(sb);
@@ -274,15 +283,20 @@ void __ext3_std_error (struct super_block * sb, const char * function,
  * case we take the easy way out and panic immediately.
  */
 
-void ext3_abort (struct super_block * sb, const char * function,
-		 const char * fmt, ...)
+void ext3_abort(struct super_block *sb, const char *function,
+		 const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	printk(KERN_CRIT "EXT3-fs (%s): error: %s: ", sb->s_id, function);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_CRIT "EXT3-fs (%s): error: %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
 	va_end(args);
 
 	if (test_opt(sb, ERRORS_PANIC))
@@ -300,16 +314,20 @@ void ext3_abort (struct super_block * sb, const char * function,
 		journal_abort(EXT3_SB(sb)->s_journal, -EIO);
 }
 
-void ext3_warning (struct super_block * sb, const char * function,
-		   const char * fmt, ...)
+void ext3_warning(struct super_block *sb, const char *function,
+		  const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	printk(KERN_WARNING "EXT3-fs (%s): warning: %s: ",
-	       sb->s_id, function);
-	vprintk(fmt, args);
-	printk("\n");
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_WARNING "EXT3-fs (%s): warning: %s: %pV\n",
+	       sb->s_id, function, &vaf);
+
 	va_end(args);
 }
 
@@ -346,7 +364,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
 	struct block_device *bdev;
 	char b[BDEVNAME_SIZE];
 
-	bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
 	if (IS_ERR(bdev))
 		goto fail;
 	return bdev;
@@ -363,8 +381,7 @@ fail:
  */
 static int ext3_blkdev_put(struct block_device *bdev)
 {
-	bd_release(bdev);
-	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
@@ -737,7 +754,7 @@ static int ext3_release_dquot(struct dquot *dquot);
 static int ext3_mark_dquot_dirty(struct dquot *dquot);
 static int ext3_write_info(struct super_block *sb, int type);
 static int ext3_quota_on(struct super_block *sb, int type, int format_id,
-				char *path);
+			 struct path *path);
 static int ext3_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -1848,13 +1865,15 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (generic_check_addressable(sb->s_blocksize_bits,
-				      le32_to_cpu(es->s_blocks_count))) {
+	err = generic_check_addressable(sb->s_blocksize_bits,
+					le32_to_cpu(es->s_blocks_count));
+	if (err) {
 		ext3_msg(sb, KERN_ERR,
 			"error: filesystem is too large to mount safely");
 		if (sizeof(sector_t) < 8)
 			ext3_msg(sb, KERN_ERR,
 				"error: CONFIG_LBDAF not enabled");
+		ret = err;
 		goto failed_mount;
 	}
 
@@ -2142,13 +2161,6 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 	if (bdev == NULL)
 		return NULL;
 
-	if (bd_claim(bdev, sb)) {
-		ext3_msg(sb, KERN_ERR,
-			"error: failed to claim external journal device");
-		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
-		return NULL;
-	}
-
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
@@ -2297,7 +2309,7 @@ static int ext3_load_journal(struct super_block *sb,
 	EXT3_SB(sb)->s_journal = journal;
 	ext3_clear_journal_err(sb, es);
 
-	if (journal_devnum &&
+	if (!really_read_only && journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
 		es->s_journal_dev = cpu_to_le32(journal_devnum);
 
@@ -2865,27 +2877,20 @@ static int ext3_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext3_quota_on(struct super_block *sb, int type, int format_id,
-			 char *name)
+			 struct path *path)
 {
 	int err;
-	struct path path;
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
 
-	err = kern_path(name, LOOKUP_FOLLOW, &path);
-	if (err)
-		return err;
-
 	/* Quotafile not on the same filesystem? */
-	if (path.mnt->mnt_sb != sb) {
-		path_put(&path);
+	if (path->mnt->mnt_sb != sb)
 		return -EXDEV;
-	}
 	/* Journaling quota? */
 	if (EXT3_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not of fs root? */
-		if (path.dentry->d_parent != sb->s_root)
+		if (path->dentry->d_parent != sb->s_root)
 			ext3_msg(sb, KERN_WARNING,
 				"warning: Quota file not on filesystem root. "
 				"Journaled quota will not work.");
@@ -2895,7 +2900,7 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 	 * When we journal data on quota file, we have to flush journal to see
 	 * all updates to the file when we bypass pagecache...
 	 */
-	if (ext3_should_journal_data(path.dentry->d_inode)) {
+	if (ext3_should_journal_data(path->dentry->d_inode)) {
 		/*
 		 * We don't need to lock updates but journal_flush() could
 		 * otherwise be livelocked...
@@ -2903,15 +2908,11 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
 		err = journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
-		if (err) {
-			path_put(&path);
+		if (err)
 			return err;
-		}
 	}
 
-	err = dquot_quota_on_path(sb, type, format_id, &path);
-	path_put(&path);
-	return err;
+	return dquot_quota_on(sb, type, format_id, path);
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index e69dc6dfaa8..32e6cc23bd9 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -925,7 +925,7 @@ ext3_xattr_ibody_set(handle_t *handle, struct inode *inode,
 /*
  * ext3_xattr_set_handle()
  *
- * Create, replace or remove an extended attribute for this inode. Buffer
+ * Create, replace or remove an extended attribute for this inode.  Value
  * is NULL to remove an existing extended attribute, and non-NULL to
  * either replace an existing extended attribute, or create a new extended
  * attribute. The flags XATTR_REPLACE and XATTR_CREATE