Merge commit 'v2.6.28-rc4' into timers/rtc

Conflicts:
	drivers/rtc/rtc-cmos.c

9 files changed, 155 insertions, 109 deletions

diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
new file mode 100644
index 00000000000..7505482a08f
--- /dev/null
+++ b/fs/ext4/Kconfig
@@ -0,0 +1,79 @@
+config EXT4_FS
+	tristate "The Extended 4 (ext4) filesystem"
+	select JBD2
+	select CRC16
+	help
+	  This is the next generation of the ext3 filesystem.
+
+	  Unlike the change from ext2 filesystem to ext3 filesystem,
+	  the on-disk format of ext4 is not forwards compatible with
+	  ext3; it is based on extent maps and it supports 48-bit
+	  physical block numbers.  The ext4 filesystem also supports delayed
+	  allocation, persistent preallocation, high resolution time stamps,
+	  and a number of other features to improve performance and speed
+	  up fsck time.  For more information, please see the web pages at
+	  http://ext4.wiki.kernel.org.
+
+	  The ext4 filesystem will support mounting an ext3
+	  filesystem; while there will be some performance gains from
+	  the delayed allocation and inode table readahead, the best
+	  performance gains will require enabling ext4 features in the
+	  filesystem, or formating a new filesystem as an ext4
+	  filesystem initially.
+
+	  To compile this file system support as a module, choose M here. The
+	  module will be called ext4.
+
+	  If unsure, say N.
+
+config EXT4DEV_COMPAT
+	bool "Enable ext4dev compatibility"
+	depends on EXT4_FS
+	help
+	  Starting with 2.6.28, the name of the ext4 filesystem was
+	  renamed from ext4dev to ext4.  Unfortunately there are some
+	  legacy userspace programs (such as klibc's fstype) have
+	  "ext4dev" hardcoded.
+
+	  To enable backwards compatibility so that systems that are
+	  still expecting to mount ext4 filesystems using ext4dev,
+	  chose Y here.   This feature will go away by 2.6.31, so
+	  please arrange to get your userspace programs fixed!
+
+config EXT4_FS_XATTR
+	bool "Ext4 extended attributes"
+	depends on EXT4_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 ext4.
+
+config EXT4_FS_POSIX_ACL
+	bool "Ext4 POSIX Access Control Lists"
+	depends on EXT4_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 EXT4_FS_SECURITY
+	bool "Ext4 Security Labels"
+	depends on EXT4_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 ext4 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index b9821be709b..d2003cdc36a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -589,21 +589,23 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	return;
 }
 
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-						s64 nblocks)
+/**
+ * ext4_has_free_blocks()
+ * @sbi:	in-core super block structure.
+ * @nblocks:	number of needed blocks
+ *
+ * Check if filesystem has nblocks free & available for allocation.
+ * On success return 1, return 0 on failure.
+ */
+int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 {
-	s64 free_blocks, dirty_blocks;
-	s64 root_blocks = 0;
+	s64 free_blocks, dirty_blocks, root_blocks;
 	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
 	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
 	free_blocks  = percpu_counter_read_positive(fbc);
 	dirty_blocks = percpu_counter_read_positive(dbc);
-
-	if (!capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
-		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
-		root_blocks = ext4_r_blocks_count(sbi->s_es);
+	root_blocks = ext4_r_blocks_count(sbi->s_es);
 
 	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
 						EXT4_FREEBLOCKS_WATERMARK) {
@@ -616,57 +618,32 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
 		}
 	}
 	/* Check whether we have space after
-	 * accounting for current dirty blocks
+	 * accounting for current dirty blocks & root reserved blocks.
 	 */
-	if (free_blocks < ((root_blocks + nblocks) + dirty_blocks))
-		/* we don't have free space */
-		return -ENOSPC;
+	if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+		return 1;
+
+	/* Hm, nope.  Are (enough) root reserved blocks available? */
+	if (sbi->s_resuid == current->fsuid ||
+	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
+	    capable(CAP_SYS_RESOURCE)) {
+		if (free_blocks >= (nblocks + dirty_blocks))
+			return 1;
+	}
 
-	/* Add the blocks to nblocks */
-	percpu_counter_add(dbc, nblocks);
 	return 0;
 }
 
-/**
- * ext4_has_free_blocks()
- * @sbi:	in-core super block structure.
- * @nblocks:	number of neeed blocks
- *
- * Check if filesystem has free blocks available for allocation.
- * Return the number of blocks avaible for allocation for this request
- * On success, return nblocks
- */
-ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
 						s64 nblocks)
 {
-	s64 free_blocks, dirty_blocks;
-	s64 root_blocks = 0;
-	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
-	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
-
-	free_blocks  = percpu_counter_read_positive(fbc);
-	dirty_blocks = percpu_counter_read_positive(dbc);
-
-	if (!capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
-		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
-		root_blocks = ext4_r_blocks_count(sbi->s_es);
-
-	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
-						EXT4_FREEBLOCKS_WATERMARK) {
-		free_blocks  = percpu_counter_sum(fbc);
-		dirty_blocks = percpu_counter_sum(dbc);
-	}
-	if (free_blocks <= (root_blocks + dirty_blocks))
-		/* we don't have free space */
+	if (ext4_has_free_blocks(sbi, nblocks)) {
+		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
 		return 0;
-
-	if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
-		return free_blocks - (root_blocks + dirty_blocks);
-	return nblocks;
+	} else
+		return -ENOSPC;
 }
 
-
 /**
  * ext4_should_retry_alloc()
  * @sb:			super block
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 3ca6a2b7632..fed5b610df5 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -459,17 +459,8 @@ static int ext4_dx_readdir(struct file *filp,
 	if (info->extra_fname) {
 		if (call_filldir(filp, dirent, filldir, info->extra_fname))
 			goto finished;
-
 		info->extra_fname = NULL;
-		info->curr_node = rb_next(info->curr_node);
-		if (!info->curr_node) {
-			if (info->next_hash == ~0) {
-				filp->f_pos = EXT4_HTREE_EOF;
-				goto finished;
-			}
-			info->curr_hash = info->next_hash;
-			info->curr_minor_hash = 0;
-		}
+		goto next_node;
 	} else if (!info->curr_node)
 		info->curr_node = rb_first(&info->root);
 
@@ -501,9 +492,14 @@ static int ext4_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 = EXT4_HTREE_EOF;
 				break;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4880cc3e672..b0537c82702 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1003,8 +1003,7 @@ extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 					ext4_lblk_t iblock, ext4_fsblk_t goal,
 					unsigned long *count, int *errp);
 extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-					 s64 nblocks);
+extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
 extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index fe34d74cfb1..2a117e286e5 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -718,6 +718,8 @@ got:
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			free = ext4_free_blocks_after_init(sb, group, gdp);
 			gdp->bg_free_blocks_count = cpu_to_le16(free);
+			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
+								gdp);
 		}
 		spin_unlock(sb_bgl_lock(sbi, group));
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8dbf6953845..be21a5ae33c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2329,6 +2329,8 @@ static int ext4_da_writepage(struct page *page,
 			unlock_page(page);
 			return 0;
 		}
+		/* now mark the buffer_heads as dirty and uptodate */
+		block_commit_write(page, 0, PAGE_CACHE_SIZE);
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -4580,9 +4582,10 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
 static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 {
 	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
-		return ext4_indirect_trans_blocks(inode, nrblocks, 0);
-	return ext4_ext_index_trans_blocks(inode, nrblocks, 0);
+		return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+	return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
 }
+
 /*
  * Account for index blocks, block groups bitmaps and block group
  * descriptor blocks if modify datablocks and index blocks
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index dfe17a13405..444ad998f72 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4441,6 +4441,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		else if (block >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
 		else {
+			ext4_unlock_group(sb, group);
 			ext4_error(sb, __func__,
 			    "Double free of blocks %d (%d %d)\n",
 			    block, entry->start_blk, entry->count);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 92db9e94514..63adcb79298 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1061,7 +1061,6 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
 struct dentry *ext4_get_parent(struct dentry *child)
 {
 	unsigned long ino;
-	struct dentry *parent;
 	struct inode *inode;
 	static const struct qstr dotdot = {
 		.name = "..",
@@ -1083,16 +1082,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
 		return ERR_PTR(-EIO);
 	}
 
-	inode = ext4_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(ext4_iget(child->d_inode->i_sb, ino));
 }
 
 #define S_SHIFT 12
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9b2b2bc4ec1..e4a241c65db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -333,7 +333,8 @@ void ext4_abort(struct super_block *sb, const char *function,
 	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
 	EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
-	jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+	if (EXT4_SB(sb)->s_journal)
+		jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
 
 void ext4_warning(struct super_block *sb, const char *function,
@@ -399,7 +400,7 @@ fail:
 static int ext4_blkdev_put(struct block_device *bdev)
 {
 	bd_release(bdev);
-	return blkdev_put(bdev);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -442,14 +443,16 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	int i;
+	int i, err;
 
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
-	if (jbd2_journal_destroy(sbi->s_journal) < 0)
-		ext4_abort(sb, __func__, "Couldn't clean up the journal");
+	err = jbd2_journal_destroy(sbi->s_journal);
 	sbi->s_journal = NULL;
+	if (err < 0)
+		ext4_abort(sb, __func__, "Couldn't clean up the journal");
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -1455,9 +1458,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
-			    ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
-			      EXT4_DESC_PER_BLOCK_BITS(sb))) /
-			   groups_per_flex;
+			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
+			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
 	sbi->s_flex_groups = kzalloc(flex_group_count *
 				     sizeof(struct flex_groups), GFP_KERNEL);
 	if (sbi->s_flex_groups == NULL) {
@@ -2553,7 +2555,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	if (bd_claim(bdev, sb)) {
 		printk(KERN_ERR
 			"EXT4: failed to claim external journal device.\n");
-		blkdev_put(bdev);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return NULL;
 	}
 
@@ -2882,12 +2884,9 @@ int ext4_force_commit(struct super_block *sb)
 /*
  * Ext4 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/ext4; eventual cleanup...)
  */
-
 static void ext4_write_super(struct super_block *sb)
 {
 	if (mutex_trylock(&sb->s_lock) != 0)
@@ -2897,15 +2896,15 @@ static void ext4_write_super(struct super_block *sb)
 
 static int ext4_sync_fs(struct super_block *sb, int wait)
 {
-	tid_t target;
+	int ret = 0;
 
 	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
 	sb->s_dirt = 0;
-	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
-		if (wait)
-			jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
-	}
-	return 0;
+	if (wait)
+		ret = ext4_force_commit(sb);
+	else
+		jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+	return ret;
 }
 
 /*
@@ -3328,30 +3327,30 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext4_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 (EXT4_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not in 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
 				"EXT4-fs: Quota file not on filesystem root. "
 				"Journaled quota will not work.\n");
@@ -3361,7 +3360,7 @@ static int ext4_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 (ext4_should_journal_data(nd.path.dentry->d_inode)) {
+	if (ext4_should_journal_data(path.dentry->d_inode)) {
 		/*
 		 * We don't need to lock updates but journal_flush() could
 		 * otherwise be livelocked...
@@ -3370,13 +3369,13 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		if (err) {
-			path_put(&nd.path);
+			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;
 }