Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/include/asm/pda.h
	kernel/fork.c

9 files changed, 205 insertions, 100 deletions

diff --git a/fs/ext3/Kconfig b/fs/ext3/Kconfig
new file mode 100644
index 00000000000..8e0cfe44b0f
--- /dev/null
+++ b/fs/ext3/Kconfig
@@ -0,0 +1,67 @@
+config EXT3_FS
+	tristate "Ext3 journalling file system support"
+	select JBD
+	help
+	  This is the journalling version of the Second extended file system
+	  (often called ext3), the de facto standard Linux file system
+	  (method to organize files on a storage device) for hard disks.
+
+	  The journalling code included in this driver means you do not have
+	  to run e2fsck (file system checker) on your file systems after a
+	  crash.  The journal keeps track of any changes that were being made
+	  at the time the system crashed, and can ensure that your file system
+	  is consistent without the need for a lengthy check.
+
+	  Other than adding the journal to the file system, the on-disk format
+	  of ext3 is identical to ext2.  It is possible to freely switch
+	  between using the ext3 driver and the ext2 driver, as long as the
+	  file system has been cleanly unmounted, or e2fsck is run on the file
+	  system.
+
+	  To add a journal on an existing ext2 file system or change the
+	  behavior of ext3 file systems, you can use the tune2fs utility ("man
+	  tune2fs").  To modify attributes of files and directories on ext3
+	  file systems, use chattr ("man chattr").  You need to be using
+	  e2fsprogs version 1.20 or later in order to create ext3 journals
+	  (available at <http://sourceforge.net/projects/e2fsprogs/>).
+
+	  To compile this file system support as a module, choose M here: the
+	  module will be called ext3.
+
+config EXT3_FS_XATTR
+	bool "Ext3 extended attributes"
+	depends on EXT3_FS
+	default y
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page, or visit
+	  <http://acl.bestbits.at/> for details).
+
+	  If unsure, say N.
+
+	  You need this for POSIX ACL support on ext3.
+
+config EXT3_FS_POSIX_ACL
+	bool "Ext3 POSIX Access Control Lists"
+	depends on EXT3_FS_XATTR
+	select FS_POSIX_ACL
+	help
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the Posix ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N
+
+config EXT3_FS_SECURITY
+	bool "Ext3 Security Labels"
+	depends on EXT3_FS_XATTR
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux.  This option
+	  enables an extended attribute handler for file security
+	  labels in the ext3 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 92fd0338a6e..0dbf1c04847 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1422,7 +1422,7 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
+		sbi->s_resuid != current_fsuid() &&
 		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
@@ -1547,6 +1547,7 @@ retry_alloc:
 	 * turn off reservation for this allocation
 	 */
 	if (my_rsv && (free_blocks < windowsz)
+		&& (free_blocks > 0)
 		&& (rsv_is_empty(&my_rsv->rsv_window)))
 		my_rsv = NULL;
 
@@ -1585,7 +1586,7 @@ retry_alloc:
 		 * free blocks is less than half of the reservation
 		 * window size.
 		 */
-		if (free_blocks <= (windowsz/2))
+		if (my_rsv && (free_blocks <= (windowsz/2)))
 			continue;
 
 		brelse(bitmap_bh);
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 2eea96ec78e..5853f4440af 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -102,6 +102,7 @@ static int ext3_readdir(struct file * filp,
 	int err;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	int ret = 0;
+	int dir_has_error = 0;
 
 	sb = inode->i_sb;
 
@@ -148,9 +149,12 @@ static int ext3_readdir(struct file * filp,
 		 * of recovering data when there's a bad sector
 		 */
 		if (!bh) {
-			ext3_error (sb, "ext3_readdir",
-				"directory #%lu contains a hole at offset %lu",
-				inode->i_ino, (unsigned long)filp->f_pos);
+			if (!dir_has_error) {
+				ext3_error(sb, __func__, "directory #%lu "
+					"contains a hole at offset %lld",
+					inode->i_ino, filp->f_pos);
+				dir_has_error = 1;
+			}
 			/* corrupt size?  Maybe no more blocks to read */
 			if (filp->f_pos > inode->i_blocks << 9)
 				break;
@@ -410,7 +414,7 @@ static int call_filldir(struct file * filp, void * dirent,
 				get_dtype(sb, fname->file_type));
 		if (error) {
 			filp->f_pos = curr_pos;
-			info->extra_fname = fname->next;
+			info->extra_fname = fname;
 			return error;
 		}
 		fname = fname->next;
@@ -449,11 +453,12 @@ static int ext3_dx_readdir(struct file * filp,
 	 * If there are any leftover names on the hash collision
 	 * chain, return them first.
 	 */
-	if (info->extra_fname &&
-	    call_filldir(filp, dirent, filldir, info->extra_fname))
-		goto finished;
-
-	if (!info->curr_node)
+	if (info->extra_fname) {
+		if (call_filldir(filp, dirent, filldir, info->extra_fname))
+			goto finished;
+		info->extra_fname = NULL;
+		goto next_node;
+	} else if (!info->curr_node)
 		info->curr_node = rb_first(&info->root);
 
 	while (1) {
@@ -484,9 +489,14 @@ static int ext3_dx_readdir(struct file * filp,
 		info->curr_minor_hash = fname->minor_hash;
 		if (call_filldir(filp, dirent, filldir, fname))
 			break;
-
+	next_node:
 		info->curr_node = rb_next(info->curr_node);
-		if (!info->curr_node) {
+		if (info->curr_node) {
+			fname = rb_entry(info->curr_node, struct fname,
+					 rb_hash);
+			info->curr_hash = fname->hash;
+			info->curr_minor_hash = fname->minor_hash;
+		} else {
 			if (info->next_hash == ~0) {
 				filp->f_pos = EXT3_HTREE_EOF;
 				break;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 47b678d73e7..490bd0ed789 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -539,7 +539,7 @@ got:
 		percpu_counter_inc(&sbi->s_dirs_counter);
 	sb->s_dirt = 1;
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (test_opt (sb, GRPID))
 		inode->i_gid = dir->i_gid;
 	else if (dir->i_mode & S_ISGID) {
@@ -547,7 +547,7 @@ got:
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
 
 	inode->i_ino = ino;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index ebfec4d0148..f8424ad8997 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1186,6 +1186,13 @@ write_begin_failed:
 		ext3_journal_stop(handle);
 		unlock_page(page);
 		page_cache_release(page);
+		/*
+		 * block_write_begin may have instantiated a few blocks
+		 * outside i_size.  Trim these off again. Don't need
+		 * i_size_read because we hold i_mutex.
+		 */
+		if (pos + len > inode->i_size)
+			vmtruncate(inode, inode->i_size);
 	}
 	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 0d0c7015164..b7394d05ee8 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -239,7 +239,7 @@ setrsvsz_out:
 	case EXT3_IOC_GROUP_EXTEND: {
 		ext3_fsblk_t n_blocks_count;
 		struct super_block *sb = inode->i_sb;
-		int err;
+		int err, err2;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -254,8 +254,10 @@ setrsvsz_out:
 		}
 		err = ext3_group_extend(sb, EXT3_SB(sb)->s_es, n_blocks_count);
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
-		journal_flush(EXT3_SB(sb)->s_journal);
+		err2 = journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
+		if (err == 0)
+			err = err2;
 group_extend_out:
 		mnt_drop_write(filp->f_path.mnt);
 		return err;
@@ -263,7 +265,7 @@ group_extend_out:
 	case EXT3_IOC_GROUP_ADD: {
 		struct ext3_new_group_data input;
 		struct super_block *sb = inode->i_sb;
-		int err;
+		int err, err2;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -280,8 +282,10 @@ group_extend_out:
 
 		err = ext3_group_add(sb, &input);
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
-		journal_flush(EXT3_SB(sb)->s_journal);
+		err2 = journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
+		if (err == 0)
+			err = err2;
 group_add_out:
 		mnt_drop_write(filp->f_path.mnt);
 		return err;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index de13e919cd8..3e5edc92aa0 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -159,7 +159,7 @@ static void dx_set_count (struct dx_entry *entries, unsigned value);
 static void dx_set_limit (struct dx_entry *entries, unsigned value);
 static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
 static unsigned dx_node_limit (struct inode *dir);
-static struct dx_frame *dx_probe(struct dentry *dentry,
+static struct dx_frame *dx_probe(struct qstr *entry,
 				 struct inode *dir,
 				 struct dx_hash_info *hinfo,
 				 struct dx_frame *frame,
@@ -176,8 +176,9 @@ static int ext3_htree_next_block(struct inode *dir, __u32 hash,
 				 struct dx_frame *frame,
 				 struct dx_frame *frames,
 				 __u32 *start_hash);
-static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
-		       struct ext3_dir_entry_2 **res_dir, int *err);
+static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
+			struct qstr *entry, struct ext3_dir_entry_2 **res_dir,
+			int *err);
 static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode);
 
@@ -342,7 +343,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
  * back to userspace.
  */
 static struct dx_frame *
-dx_probe(struct dentry *dentry, struct inode *dir,
+dx_probe(struct qstr *entry, struct inode *dir,
 	 struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
 {
 	unsigned count, indirect;
@@ -353,8 +354,6 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	u32 hash;
 
 	frame->bh = NULL;
-	if (dentry)
-		dir = dentry->d_parent->d_inode;
 	if (!(bh = ext3_bread (NULL,dir, 0, 0, err)))
 		goto fail;
 	root = (struct dx_root *) bh->b_data;
@@ -370,8 +369,8 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	}
 	hinfo->hash_version = root->info.hash_version;
 	hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
-	if (dentry)
-		ext3fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);
+	if (entry)
+		ext3fs_dirhash(entry->name, entry->len, hinfo);
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
@@ -803,15 +802,15 @@ static inline int ext3_match (int len, const char * const name,
  */
 static inline int search_dirblock(struct buffer_head * bh,
 				  struct inode *dir,
-				  struct dentry *dentry,
+				  struct qstr *child,
 				  unsigned long offset,
 				  struct ext3_dir_entry_2 ** res_dir)
 {
 	struct ext3_dir_entry_2 * de;
 	char * dlimit;
 	int de_len;
-	const char *name = dentry->d_name.name;
-	int namelen = dentry->d_name.len;
+	const char *name = child->name;
+	int namelen = child->len;
 
 	de = (struct ext3_dir_entry_2 *) bh->b_data;
 	dlimit = bh->b_data + dir->i_sb->s_blocksize;
@@ -850,8 +849,9 @@ static inline int search_dirblock(struct buffer_head * bh,
  * The returned buffer_head has ->b_count elevated.  The caller is expected
  * to brelse() it when appropriate.
  */
-static struct buffer_head * ext3_find_entry (struct dentry *dentry,
-					struct ext3_dir_entry_2 ** res_dir)
+static struct buffer_head *ext3_find_entry(struct inode *dir,
+					struct qstr *entry,
+					struct ext3_dir_entry_2 **res_dir)
 {
 	struct super_block * sb;
 	struct buffer_head * bh_use[NAMEI_RA_SIZE];
@@ -863,16 +863,15 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry,
 				   buffer */
 	int num = 0;
 	int nblocks, i, err;
-	struct inode *dir = dentry->d_parent->d_inode;
 	int namelen;
 
 	*res_dir = NULL;
 	sb = dir->i_sb;
-	namelen = dentry->d_name.len;
+	namelen = entry->len;
 	if (namelen > EXT3_NAME_LEN)
 		return NULL;
 	if (is_dx(dir)) {
-		bh = ext3_dx_find_entry(dentry, res_dir, &err);
+		bh = ext3_dx_find_entry(dir, entry, res_dir, &err);
 		/*
 		 * On success, or if the error was file not found,
 		 * return.  Otherwise, fall back to doing a search the
@@ -923,7 +922,7 @@ restart:
 			brelse(bh);
 			goto next;
 		}
-		i = search_dirblock(bh, dir, dentry,
+		i = search_dirblock(bh, dir, entry,
 			    block << EXT3_BLOCK_SIZE_BITS(sb), res_dir);
 		if (i == 1) {
 			EXT3_I(dir)->i_dir_start_lookup = block;
@@ -957,8 +956,9 @@ cleanup_and_exit:
 	return ret;
 }
 
-static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
-		       struct ext3_dir_entry_2 **res_dir, int *err)
+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 dx_hash_info	hinfo;
@@ -968,14 +968,13 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
 	struct buffer_head *bh;
 	unsigned long block;
 	int retval;
-	int namelen = dentry->d_name.len;
-	const u8 *name = dentry->d_name.name;
-	struct inode *dir = dentry->d_parent->d_inode;
+	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] != '.'||(name[1] != '.' && name[1] != '\0')){
-		if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err)))
+	if (namelen > 2 || name[0] != '.'|| (namelen == 2 && name[1] != '.')) {
+		if (!(frame = dx_probe(entry, dir, &hinfo, frames, err)))
 			return NULL;
 	} else {
 		frame = frames;
@@ -1036,7 +1035,7 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
 	if (dentry->d_name.len > EXT3_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	bh = ext3_find_entry(dentry, &de);
+	bh = ext3_find_entry(dir, &dentry->d_name, &de);
 	inode = NULL;
 	if (bh) {
 		unsigned long ino = le32_to_cpu(de->inode);
@@ -1057,18 +1056,11 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
 struct dentry *ext3_get_parent(struct dentry *child)
 {
 	unsigned long ino;
-	struct dentry *parent;
-	struct inode *inode;
-	struct dentry dotdot;
+	struct qstr dotdot = {.name = "..", .len = 2};
 	struct ext3_dir_entry_2 * de;
 	struct buffer_head *bh;
 
-	dotdot.d_name.name = "..";
-	dotdot.d_name.len = 2;
-	dotdot.d_parent = child; /* confusing, isn't it! */
-
-	bh = ext3_find_entry(&dotdot, &de);
-	inode = NULL;
+	bh = ext3_find_entry(child->d_inode, &dotdot, &de);
 	if (!bh)
 		return ERR_PTR(-ENOENT);
 	ino = le32_to_cpu(de->inode);
@@ -1080,16 +1072,7 @@ struct dentry *ext3_get_parent(struct dentry *child)
 		return ERR_PTR(-EIO);
 	}
 
-	inode = ext3_iget(child->d_inode->i_sb, ino);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
-
-	parent = d_alloc_anon(inode);
-	if (!parent) {
-		iput(inode);
-		parent = ERR_PTR(-ENOMEM);
-	}
-	return parent;
+	return d_obtain_alias(ext3_iget(child->d_inode->i_sb, ino));
 }
 
 #define S_SHIFT 12
@@ -1503,7 +1486,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	struct ext3_dir_entry_2 *de;
 	int err;
 
-	frame = dx_probe(dentry, NULL, &hinfo, frames, &err);
+	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
 	if (!frame)
 		return err;
 	entries = frame->entries;
@@ -2056,7 +2039,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry)
 		return PTR_ERR(handle);
 
 	retval = -ENOENT;
-	bh = ext3_find_entry (dentry, &de);
+	bh = ext3_find_entry(dir, &dentry->d_name, &de);
 	if (!bh)
 		goto end_rmdir;
 
@@ -2118,7 +2101,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry)
 		handle->h_sync = 1;
 
 	retval = -ENOENT;
-	bh = ext3_find_entry (dentry, &de);
+	bh = ext3_find_entry(dir, &dentry->d_name, &de);
 	if (!bh)
 		goto end_unlink;
 
@@ -2276,7 +2259,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
 		handle->h_sync = 1;
 
-	old_bh = ext3_find_entry (old_dentry, &old_de);
+	old_bh = ext3_find_entry(old_dir, &old_dentry->d_name, &old_de);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -2289,7 +2272,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 		goto end_rename;
 
 	new_inode = new_dentry->d_inode;
-	new_bh = ext3_find_entry (new_dentry, &new_de);
+	new_bh = ext3_find_entry(new_dir, &new_dentry->d_name, &new_de);
 	if (new_bh) {
 		if (!new_inode) {
 			brelse (new_bh);
@@ -2355,7 +2338,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 		struct buffer_head *old_bh2;
 		struct ext3_dir_entry_2 *old_de2;
 
-		old_bh2 = ext3_find_entry(old_dentry, &old_de2);
+		old_bh2 = ext3_find_entry(old_dir, &old_dentry->d_name,
+					  &old_de2);
 		if (old_bh2) {
 			retval = ext3_delete_entry(handle, old_dir,
 						   old_de2, old_bh2);
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 77278e947e9..78fdf383637 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -790,7 +790,8 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 
 	if (reserved_gdb || gdb_off == 0) {
 		if (!EXT3_HAS_COMPAT_FEATURE(sb,
-					     EXT3_FEATURE_COMPAT_RESIZE_INODE)){
+					     EXT3_FEATURE_COMPAT_RESIZE_INODE)
+		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
 			ext3_warning(sb, __func__,
 				     "No reserved GDT blocks, can't resize");
 			return -EPERM;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 399a96a6c55..f6c94f232ec 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -281,7 +281,8 @@ void ext3_abort (struct super_block * sb, const char * function,
 	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
 	EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
-	journal_abort(EXT3_SB(sb)->s_journal, -EIO);
+	if (EXT3_SB(sb)->s_journal)
+		journal_abort(EXT3_SB(sb)->s_journal, -EIO);
 }
 
 void ext3_warning (struct super_block * sb, const char * function,
@@ -347,7 +348,7 @@ fail:
 static int ext3_blkdev_put(struct block_device *bdev)
 {
 	bd_release(bdev);
-	return blkdev_put(bdev);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
@@ -390,10 +391,14 @@ static void ext3_put_super (struct super_block * sb)
 {
 	struct ext3_sb_info *sbi = EXT3_SB(sb);
 	struct ext3_super_block *es = sbi->s_es;
-	int i;
+	int i, err;
 
 	ext3_xattr_put_super(sb);
-	journal_destroy(sbi->s_journal);
+	err = journal_destroy(sbi->s_journal);
+	sbi->s_journal = NULL;
+	if (err < 0)
+		ext3_abort(sb, __func__, "Couldn't clean up the journal");
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -625,6 +630,9 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
 		seq_puts(seq, ",data=writeback");
 
+	if (test_opt(sb, DATA_ERR_ABORT))
+		seq_puts(seq, ",data_err=abort");
+
 	ext3_show_quota_options(seq, sb);
 
 	return 0;
@@ -754,6 +762,7 @@ enum {
 	Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
 	Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+	Opt_data_err_abort, Opt_data_err_ignore,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
@@ -796,6 +805,8 @@ static const match_table_t tokens = {
 	{Opt_data_journal, "data=journal"},
 	{Opt_data_ordered, "data=ordered"},
 	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_err_abort, "data_err=abort"},
+	{Opt_data_err_ignore, "data_err=ignore"},
 	{Opt_offusrjquota, "usrjquota="},
 	{Opt_usrjquota, "usrjquota=%s"},
 	{Opt_offgrpjquota, "grpjquota="},
@@ -1011,6 +1022,12 @@ static int parse_options (char *options, struct super_block *sb,
 				sbi->s_mount_opt |= data_opt;
 			}
 			break;
+		case Opt_data_err_abort:
+			set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
+		case Opt_data_err_ignore:
+			clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
 #ifdef CONFIG_QUOTA
 		case Opt_usrjquota:
 			qtype = USRQUOTA;
@@ -1986,6 +2003,10 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
 		journal->j_flags |= JFS_BARRIER;
 	else
 		journal->j_flags &= ~JFS_BARRIER;
+	if (test_opt(sb, DATA_ERR_ABORT))
+		journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR;
+	else
+		journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR;
 	spin_unlock(&journal->j_state_lock);
 }
 
@@ -2050,7 +2071,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 	if (bd_claim(bdev, sb)) {
 		printk(KERN_ERR
 		        "EXT3: failed to claim external journal device.\n");
-		blkdev_put(bdev);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return NULL;
 	}
 
@@ -2280,7 +2301,9 @@ static void ext3_mark_recovery_complete(struct super_block * sb,
 	journal_t *journal = EXT3_SB(sb)->s_journal;
 
 	journal_lock_updates(journal);
-	journal_flush(journal);
+	if (journal_flush(journal) < 0)
+		goto out;
+
 	lock_super(sb);
 	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
 	    sb->s_flags & MS_RDONLY) {
@@ -2289,6 +2312,8 @@ static void ext3_mark_recovery_complete(struct super_block * sb,
 		ext3_commit_super(sb, es, 1);
 	}
 	unlock_super(sb);
+
+out:
 	journal_unlock_updates(journal);
 }
 
@@ -2350,12 +2375,9 @@ int ext3_force_commit(struct super_block *sb)
 /*
  * Ext3 always journals updates to the superblock itself, so we don't
  * have to propagate any other updates to the superblock on disk at this
- * point.  Just start an async writeback to get the buffers on their way
- * to the disk.
- *
- * This implicitly triggers the writebehind on sync().
+ * point.  (We can probably nuke this function altogether, and remove
+ * any mention to sb->s_dirt in all of fs/ext3; eventual cleanup...)
  */
-
 static void ext3_write_super (struct super_block * sb)
 {
 	if (mutex_trylock(&sb->s_lock) != 0)
@@ -2365,13 +2387,12 @@ static void ext3_write_super (struct super_block * sb)
 
 static int ext3_sync_fs(struct super_block *sb, int wait)
 {
-	tid_t target;
-
 	sb->s_dirt = 0;
-	if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
-		if (wait)
-			log_wait_commit(EXT3_SB(sb)->s_journal, target);
-	}
+	if (wait)
+		ext3_force_commit(sb);
+	else
+		journal_start_commit(EXT3_SB(sb)->s_journal, NULL);
+
 	return 0;
 }
 
@@ -2388,7 +2409,13 @@ static void ext3_write_super_lockfs(struct super_block *sb)
 
 		/* Now we set up the journal barrier. */
 		journal_lock_updates(journal);
-		journal_flush(journal);
+
+		/*
+		 * We don't want to clear needs_recovery flag when we failed
+		 * to flush the journal.
+		 */
+		if (journal_flush(journal) < 0)
+			return;
 
 		/* Journal blocked and flushed, clear needs_recovery flag. */
 		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
@@ -2767,30 +2794,30 @@ 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 *path, int remount)
+			 char *name, int remount)
 {
 	int err;
-	struct nameidata nd;
+	struct path path;
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
-	/* When remounting, no checks are needed and in fact, path is NULL */
+	/* When remounting, no checks are needed and in fact, name is NULL */
 	if (remount)
-		return vfs_quota_on(sb, type, format_id, path, remount);
+		return vfs_quota_on(sb, type, format_id, name, remount);
 
-	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
+	err = kern_path(name, LOOKUP_FOLLOW, &path);
 	if (err)
 		return err;
 
 	/* Quotafile not on the same filesystem? */
-	if (nd.path.mnt->mnt_sb != sb) {
-		path_put(&nd.path);
+	if (path.mnt->mnt_sb != sb) {
+		path_put(&path);
 		return -EXDEV;
 	}
 	/* Journaling quota? */
 	if (EXT3_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not of fs root? */
-		if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+		if (path.dentry->d_parent != sb->s_root)
 			printk(KERN_WARNING
 				"EXT3-fs: Quota file not on filesystem root. "
 				"Journaled quota will not work.\n");
@@ -2800,18 +2827,22 @@ 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(nd.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...
 		 */
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
-		journal_flush(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);
+			return err;
+		}
 	}
 
-	err = vfs_quota_on_path(sb, type, format_id, &nd.path);
-	path_put(&nd.path);
+	err = vfs_quota_on_path(sb, type, format_id, &path);
+	path_put(&path);
 	return err;
 }