Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull second try at vfs part d#2 from Al Viro:
 "Miklos' first series (with do_lookup() rewrite split into edible
  chunks) + assorted bits and pieces.

  The 'untangling of do_lookup()' series is is a splitup of what used to
  be a monolithic patch from Miklos, so this series is basically "how do
  I convince myself that his patch is correct (or find a hole in it)".
  No holes found and I like the resulting cleanup, so in it went..."

Changes from try 1: Fix a boot problem with selinux, and commit messages
prettied up a bit.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (24 commits)
  vfs: fix out-of-date dentry_unhash() comment
  vfs: split __lookup_hash
  untangling do_lookup() - take __lookup_hash()-calling case out of line.
  untangling do_lookup() - switch to calling __lookup_hash()
  untangling do_lookup() - merge d_alloc_and_lookup() callers
  untangling do_lookup() - merge failure exits in !dentry case
  untangling do_lookup() - massage !dentry case towards __lookup_hash()
  untangling do_lookup() - get rid of need_reval in !dentry case
  untangling do_lookup() - eliminate a loop.
  untangling do_lookup() - expand the area under ->i_mutex
  untangling do_lookup() - isolate !dentry stuff from the rest of it.
  vfs: move MAY_EXEC check from __lookup_hash()
  vfs: don't revalidate just looked up dentry
  vfs: fix d_need_lookup/d_revalidate order in do_lookup
  ext3: move headers to fs/ext3/
  migrate ext2_fs.h guts to fs/ext2/ext2.h
  new helper: ext2_image_size()
  get rid of pointless includes of ext2_fs.h
  ext2: No longer export ext2_fs.h to user space
  mtdchar: kill persistently held vfsmount
  ...

41 files changed, 1249 insertions, 1640 deletions

diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 2aa01936850..2ad747e909f 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -550,6 +550,7 @@ static __init void memory_setup(void)
 {
 #ifdef CONFIG_MTD_UCLINUX
 	unsigned long mtd_phys = 0;
+	unsigned long n;
 #endif
 	unsigned long max_mem;
 
@@ -593,9 +594,9 @@ static __init void memory_setup(void)
 	mtd_size = PAGE_ALIGN(*((unsigned long *)(mtd_phys + 8)));
 
 # if defined(CONFIG_EXT2_FS) || defined(CONFIG_EXT3_FS)
-	if (*((unsigned short *)(mtd_phys + 0x438)) == EXT2_SUPER_MAGIC)
-		mtd_size =
-		    PAGE_ALIGN(*((unsigned long *)(mtd_phys + 0x404)) << 10);
+	n = ext2_image_size((void *)(mtd_phys + 0x400));
+	if (n)
+		mtd_size = PAGE_ALIGN(n * 1024);
 # endif
 
 # if defined(CONFIG_CRAMFS)
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 55d82321d30..94eb05b1afd 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -39,7 +39,6 @@
 #include <asm/uaccess.h>
 
 static DEFINE_MUTEX(mtd_mutex);
-static struct vfsmount *mtd_inode_mnt __read_mostly;
 
 /*
  * Data structure to hold the pointer to the mtd device as well
@@ -75,7 +74,9 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
 	return -EINVAL;
 }
 
-
+static int count;
+static struct vfsmount *mnt;
+static struct file_system_type mtd_inodefs_type;
 
 static int mtdchar_open(struct inode *inode, struct file *file)
 {
@@ -92,6 +93,10 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
+	ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count);
+	if (ret)
+		return ret;
+
 	mutex_lock(&mtd_mutex);
 	mtd = get_mtd_device(NULL, devnum);
 
@@ -106,7 +111,7 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 		goto out;
 	}
 
-	mtd_ino = iget_locked(mtd_inode_mnt->mnt_sb, devnum);
+	mtd_ino = iget_locked(mnt->mnt_sb, devnum);
 	if (!mtd_ino) {
 		put_mtd_device(mtd);
 		ret = -ENOMEM;
@@ -141,6 +146,7 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 
 out:
 	mutex_unlock(&mtd_mutex);
+	simple_release_fs(&mnt, &count);
 	return ret;
 } /* mtdchar_open */
 
@@ -162,6 +168,7 @@ static int mtdchar_close(struct inode *inode, struct file *file)
 	put_mtd_device(mtd);
 	file->private_data = NULL;
 	kfree(mfi);
+	simple_release_fs(&mnt, &count);
 
 	return 0;
 } /* mtdchar_close */
@@ -1175,10 +1182,15 @@ static const struct file_operations mtd_fops = {
 #endif
 };
 
+static const struct super_operations mtd_ops = {
+	.drop_inode = generic_delete_inode,
+	.statfs = simple_statfs,
+};
+
 static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	return mount_pseudo(fs_type, "mtd_inode:", NULL, NULL, MTD_INODE_FS_MAGIC);
+	return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC);
 }
 
 static struct file_system_type mtd_inodefs_type = {
@@ -1187,26 +1199,6 @@ static struct file_system_type mtd_inodefs_type = {
        .kill_sb = kill_anon_super,
 };
 
-static void mtdchar_notify_add(struct mtd_info *mtd)
-{
-}
-
-static void mtdchar_notify_remove(struct mtd_info *mtd)
-{
-	struct inode *mtd_ino = ilookup(mtd_inode_mnt->mnt_sb, mtd->index);
-
-	if (mtd_ino) {
-		/* Destroy the inode if it exists */
-		clear_nlink(mtd_ino);
-		iput(mtd_ino);
-	}
-}
-
-static struct mtd_notifier mtdchar_notifier = {
-	.add = mtdchar_notify_add,
-	.remove = mtdchar_notify_remove,
-};
-
 static int __init init_mtdchar(void)
 {
 	int ret;
@@ -1224,19 +1216,8 @@ static int __init init_mtdchar(void)
 		pr_notice("Can't register mtd_inodefs filesystem: %d\n", ret);
 		goto err_unregister_chdev;
 	}
-
-	mtd_inode_mnt = kern_mount(&mtd_inodefs_type);
-	if (IS_ERR(mtd_inode_mnt)) {
-		ret = PTR_ERR(mtd_inode_mnt);
-		pr_notice("Error mounting mtd_inodefs filesystem: %d\n", ret);
-		goto err_unregister_filesystem;
-	}
-	register_mtd_user(&mtdchar_notifier);
-
 	return ret;
 
-err_unregister_filesystem:
-	unregister_filesystem(&mtd_inodefs_type);
 err_unregister_chdev:
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 	return ret;
@@ -1244,8 +1225,6 @@ err_unregister_chdev:
 
 static void __exit cleanup_mtdchar(void)
 {
-	unregister_mtd_user(&mtdchar_notifier);
-	kern_unmount(mtd_inode_mnt);
 	unregister_filesystem(&mtd_inodefs_type);
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 }
diff --git a/fs/aio.c b/fs/aio.c
index 4f71627264f..da887604dfc 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -305,15 +305,18 @@ out_freectx:
 	return ERR_PTR(err);
 }
 
-/* aio_cancel_all
+/* kill_ctx
  *	Cancels all outstanding aio requests on an aio context.  Used 
  *	when the processes owning a context have all exited to encourage 
  *	the rapid destruction of the kioctx.
  */
-static void aio_cancel_all(struct kioctx *ctx)
+static void kill_ctx(struct kioctx *ctx)
 {
 	int (*cancel)(struct kiocb *, struct io_event *);
+	struct task_struct *tsk = current;
+	DECLARE_WAITQUEUE(wait, tsk);
 	struct io_event res;
+
 	spin_lock_irq(&ctx->ctx_lock);
 	ctx->dead = 1;
 	while (!list_empty(&ctx->active_reqs)) {
@@ -329,15 +332,7 @@ static void aio_cancel_all(struct kioctx *ctx)
 			spin_lock_irq(&ctx->ctx_lock);
 		}
 	}
-	spin_unlock_irq(&ctx->ctx_lock);
-}
-
-static void wait_for_all_aios(struct kioctx *ctx)
-{
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
 
-	spin_lock_irq(&ctx->ctx_lock);
 	if (!ctx->reqs_active)
 		goto out;
 
@@ -387,9 +382,7 @@ void exit_aio(struct mm_struct *mm)
 		ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
 		hlist_del_rcu(&ctx->list);
 
-		aio_cancel_all(ctx);
-
-		wait_for_all_aios(ctx);
+		kill_ctx(ctx);
 
 		if (1 != atomic_read(&ctx->users))
 			printk(KERN_DEBUG
@@ -1269,8 +1262,7 @@ static void io_destroy(struct kioctx *ioctx)
 	if (likely(!was_dead))
 		put_ioctx(ioctx);	/* twice for the list */
 
-	aio_cancel_all(ioctx);
-	wait_for_all_aios(ioctx);
+	kill_ctx(ioctx);
 
 	/*
 	 * Wake up any waiters.  The setting of ctx->dead must be seen
@@ -1278,7 +1270,6 @@ static void io_destroy(struct kioctx *ioctx)
 	 * locking done by the above calls to ensure this consistency.
 	 */
 	wake_up_all(&ioctx->wait);
-	put_ioctx(ioctx);	/* once for the lookup */
 }
 
 /* sys_io_setup:
@@ -1315,11 +1306,9 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	ret = PTR_ERR(ioctx);
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
-		if (!ret) {
-			put_ioctx(ioctx);
-			return 0;
-		}
-		io_destroy(ioctx);
+		if (ret)
+			io_destroy(ioctx);
+		put_ioctx(ioctx);
 	}
 
 out:
@@ -1337,6 +1326,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
 		io_destroy(ioctx);
+		put_ioctx(ioctx);
 		return 0;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 75ad433c669..0b2b4db5bdc 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -1,5 +1,636 @@
+/*
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/include/linux/minix_fs.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#include <linux/rbtree.h>
+
+/* XXX Here for now... not interested in restructing headers JUST now */
+
+/* data type for block offset of block group */
+typedef int ext2_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long ext2_fsblk_t;
+
+#define E2FSBLK "%lu"
+
+struct ext2_reserve_window {
+	ext2_fsblk_t		_rsv_start;	/* First byte reserved */
+	ext2_fsblk_t		_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext2_reserve_window_node {
+	struct rb_node	 	rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext2_reserve_window	rsv_window;
+};
+
+struct ext2_block_alloc_info {
+	/* information about reservation window */
+	struct ext2_reserve_window_node	rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext2_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32			last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext2_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext2_fsblk_t		last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * second extended-fs super-block data in memory
+ */
+struct ext2_sb_info {
+	unsigned long s_frag_size;	/* Size of a fragment in bytes */
+	unsigned long s_frags_per_block;/* Number of fragments per block */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_frags_per_group;/* Number of fragments in a group */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	unsigned long s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext2_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	unsigned long s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	unsigned long s_dir_count;
+	u8 *s_debts;
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext2_reserve_window_node s_rsv_window_head;
+	/*
+	 * s_lock protects against concurrent modifications of s_mount_state,
+	 * s_blocks_last, s_overhead_last and the content of superblock's
+	 * buffer pointed to by sbi->s_es.
+	 *
+	 * Note: It is used in ext2_show_options() to provide a consistent view
+	 * of the mount options.
+	 */
+	spinlock_t s_lock;
+};
+
+static inline spinlock_t *
+sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
+}
+
+/*
+ * Define EXT2FS_DEBUG to produce debug messages
+ */
+#undef EXT2FS_DEBUG
+
+/*
+ * Define EXT2_RESERVATION to reserve data blocks for expanding files
+ */
+#define EXT2_DEFAULT_RESERVE_BLOCKS     8
+/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
+#define EXT2_MAX_RESERVE_BLOCKS         1027
+#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
+/*
+ * The second extended file system version
+ */
+#define EXT2FS_DATE		"95/08/09"
+#define EXT2FS_VERSION		"0.5b"
+
+/*
+ * Debug code
+ */
+#ifdef EXT2FS_DEBUG
+#	define ext2_debug(f, a...)	{ \
+					printk ("EXT2-fs DEBUG (%s, %d): %s:", \
+						__FILE__, __LINE__, __func__); \
+				  	printk (f, ## a); \
+					}
+#else
+#	define ext2_debug(f, a...)	/**/
+#endif
+
+/*
+ * Special inode numbers
+ */
+#define	EXT2_BAD_INO		 1	/* Bad blocks inode */
+#define EXT2_ROOT_INO		 2	/* Root inode */
+#define EXT2_BOOT_LOADER_INO	 5	/* Boot loader inode */
+#define EXT2_UNDEL_DIR_INO	 6	/* Undelete directory inode */
+
+/* First non-reserved inode for old ext2 filesystems */
+#define EXT2_GOOD_OLD_FIRST_INO	11
+
+static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT2_MIN_BLOCK_SIZE		1024
+#define	EXT2_MAX_BLOCK_SIZE		4096
+#define EXT2_MIN_BLOCK_LOG_SIZE		  10
+#define EXT2_BLOCK_SIZE(s)		((s)->s_blocksize)
+#define	EXT2_ADDR_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT2_BLOCK_SIZE_BITS(s)		((s)->s_blocksize_bits)
+#define	EXT2_ADDR_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_addr_per_block_bits)
+#define EXT2_INODE_SIZE(s)		(EXT2_SB(s)->s_inode_size)
+#define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
+
+/*
+ * Macro-instructions used to manage fragments
+ */
+#define EXT2_MIN_FRAG_SIZE		1024
+#define	EXT2_MAX_FRAG_SIZE		4096
+#define EXT2_MIN_FRAG_LOG_SIZE		  10
+#define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
+#define EXT2_FRAGS_PER_BLOCK(s)		(EXT2_SB(s)->s_frags_per_block)
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext2_group_desc
+{
+	__le32	bg_block_bitmap;		/* Blocks bitmap block */
+	__le32	bg_inode_bitmap;		/* Inodes bitmap block */
+	__le32	bg_inode_table;		/* Inodes table block */
+	__le16	bg_free_blocks_count;	/* Free blocks count */
+	__le16	bg_free_inodes_count;	/* Free inodes count */
+	__le16	bg_used_dirs_count;	/* Directories count */
+	__le16	bg_pad;
+	__le32	bg_reserved[3];
+};
+
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT2_BLOCKS_PER_GROUP(s)	(EXT2_SB(s)->s_blocks_per_group)
+#define EXT2_DESC_PER_BLOCK(s)		(EXT2_SB(s)->s_desc_per_block)
+#define EXT2_INODES_PER_GROUP(s)	(EXT2_SB(s)->s_inodes_per_group)
+#define EXT2_DESC_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_desc_per_block_bits)
+
+/*
+ * Constants relative to the data blocks
+ */
+#define	EXT2_NDIR_BLOCKS		12
+#define	EXT2_IND_BLOCK			EXT2_NDIR_BLOCKS
+#define	EXT2_DIND_BLOCK			(EXT2_IND_BLOCK + 1)
+#define	EXT2_TIND_BLOCK			(EXT2_DIND_BLOCK + 1)
+#define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
+
+/*
+ * Inode flags (GETFLAGS/SETFLAGS)
+ */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
+/* Reserved for compression usage... */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
+/* End compression flags --- maybe not all used */	
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
+			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
+			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & EXT2_REG_FLMASK;
+	else
+		return flags & EXT2_OTHER_FLMASK;
+}
+
+/*
+ * ioctl commands
+ */
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+#define	EXT2_IOC_GETRSVSZ		_IOR('f', 5, long)
+#define	EXT2_IOC_SETRSVSZ		_IOW('f', 6, long)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext2_inode {
+	__le16	i_mode;		/* File mode */
+	__le16	i_uid;		/* Low 16 bits of Owner Uid */
+	__le32	i_size;		/* Size in bytes */
+	__le32	i_atime;	/* Access time */
+	__le32	i_ctime;	/* Creation time */
+	__le32	i_mtime;	/* Modification time */
+	__le32	i_dtime;	/* Deletion Time */
+	__le16	i_gid;		/* Low 16 bits of Group Id */
+	__le16	i_links_count;	/* Links count */
+	__le32	i_blocks;	/* Blocks count */
+	__le32	i_flags;	/* File flags */
+	union {
+		struct {
+			__le32  l_i_reserved1;
+		} linux1;
+		struct {
+			__le32  h_i_translator;
+		} hurd1;
+		struct {
+			__le32  m_i_reserved1;
+		} masix1;
+	} osd1;				/* OS dependent 1 */
+	__le32	i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
+	__le32	i_generation;	/* File version (for NFS) */
+	__le32	i_file_acl;	/* File ACL */
+	__le32	i_dir_acl;	/* Directory ACL */
+	__le32	i_faddr;	/* Fragment address */
+	union {
+		struct {
+			__u8	l_i_frag;	/* Fragment number */
+			__u8	l_i_fsize;	/* Fragment size */
+			__u16	i_pad1;
+			__le16	l_i_uid_high;	/* these 2 fields    */
+			__le16	l_i_gid_high;	/* were reserved2[0] */
+			__u32	l_i_reserved2;
+		} linux2;
+		struct {
+			__u8	h_i_frag;	/* Fragment number */
+			__u8	h_i_fsize;	/* Fragment size */
+			__le16	h_i_mode_high;
+			__le16	h_i_uid_high;
+			__le16	h_i_gid_high;
+			__le32	h_i_author;
+		} hurd2;
+		struct {
+			__u8	m_i_frag;	/* Fragment number */
+			__u8	m_i_fsize;	/* Fragment size */
+			__u16	m_pad1;
+			__u32	m_i_reserved2[2];
+		} masix2;
+	} osd2;				/* OS dependent 2 */
+};
+
+#define i_size_high	i_dir_acl
+
+#define i_reserved1	osd1.linux1.l_i_reserved1
+#define i_frag		osd2.linux2.l_i_frag
+#define i_fsize		osd2.linux2.l_i_fsize
+#define i_uid_low	i_uid
+#define i_gid_low	i_gid
+#define i_uid_high	osd2.linux2.l_i_uid_high
+#define i_gid_high	osd2.linux2.l_i_gid_high
+#define i_reserved2	osd2.linux2.l_i_reserved2
+
+/*
+ * File system states
+ */
+#define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
+#define	EXT2_ERROR_FS			0x0002	/* Errors detected */
+
+/*
+ * Mount flags
+ */
+#define EXT2_MOUNT_CHECK		0x000001  /* Do mount-time checks */
+#define EXT2_MOUNT_OLDALLOC		0x000002  /* Don't use the new Orlov allocator */
+#define EXT2_MOUNT_GRPID		0x000004  /* Create files with directory's group */
+#define EXT2_MOUNT_DEBUG		0x000008  /* Some debugging messages */
+#define EXT2_MOUNT_ERRORS_CONT		0x000010  /* Continue on errors */
+#define EXT2_MOUNT_ERRORS_RO		0x000020  /* Remount fs ro on errors */
+#define EXT2_MOUNT_ERRORS_PANIC		0x000040  /* Panic on errors */
+#define EXT2_MOUNT_MINIX_DF		0x000080  /* Mimics the Minix statfs */
+#define EXT2_MOUNT_NOBH			0x000100  /* No buffer_heads */
+#define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
+#define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
+#define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
+#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
+#define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
+#define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+
+
+#define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
+#define set_opt(o, opt)			o |= EXT2_MOUNT_##opt
+#define test_opt(sb, opt)		(EXT2_SB(sb)->s_mount_opt & \
+					 EXT2_MOUNT_##opt)
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT2_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
+#define EXT2_DFL_CHECKINTERVAL		0	/* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT2_ERRORS_CONTINUE		1	/* Continue execution */
+#define EXT2_ERRORS_RO			2	/* Remount fs read-only */
+#define EXT2_ERRORS_PANIC		3	/* Panic */
+#define EXT2_ERRORS_DEFAULT		EXT2_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext2_super_block {
+	__le32	s_inodes_count;		/* Inodes count */
+	__le32	s_blocks_count;		/* Blocks count */
+	__le32	s_r_blocks_count;	/* Reserved blocks count */
+	__le32	s_free_blocks_count;	/* Free blocks count */
+	__le32	s_free_inodes_count;	/* Free inodes count */
+	__le32	s_first_data_block;	/* First Data Block */
+	__le32	s_log_block_size;	/* Block size */
+	__le32	s_log_frag_size;	/* Fragment size */
+	__le32	s_blocks_per_group;	/* # Blocks per group */
+	__le32	s_frags_per_group;	/* # Fragments per group */
+	__le32	s_inodes_per_group;	/* # Inodes per group */
+	__le32	s_mtime;		/* Mount time */
+	__le32	s_wtime;		/* Write time */
+	__le16	s_mnt_count;		/* Mount count */
+	__le16	s_max_mnt_count;	/* Maximal mount count */
+	__le16	s_magic;		/* Magic signature */
+	__le16	s_state;		/* File system state */
+	__le16	s_errors;		/* Behaviour when detecting errors */
+	__le16	s_minor_rev_level; 	/* minor revision level */
+	__le32	s_lastcheck;		/* time of last check */
+	__le32	s_checkinterval;	/* max. time between checks */
+	__le32	s_creator_os;		/* OS */
+	__le32	s_rev_level;		/* Revision level */
+	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	/*
+	 * These fields are for EXT2_DYNAMIC_REV superblocks only.
+	 *
+	 * Note: the difference between the compatible feature set and
+	 * the incompatible feature set is that if there is a bit set
+	 * in the incompatible feature set that the kernel doesn't
+	 * know about, it should refuse to mount the filesystem.
+	 * 
+	 * e2fsck's requirements are more strict; if it doesn't know
+	 * about a feature in either the compatible or incompatible
+	 * feature set, it must abort and not try to meddle with
+	 * things it doesn't understand...
+	 */
+	__le32	s_first_ino; 		/* First non-reserved inode */
+	__le16   s_inode_size; 		/* size of inode structure */
+	__le16	s_block_group_nr; 	/* block group # of this superblock */
+	__le32	s_feature_compat; 	/* compatible feature set */
+	__le32	s_feature_incompat; 	/* incompatible feature set */
+	__le32	s_feature_ro_compat; 	/* readonly-compatible feature set */
+	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+	char	s_volume_name[16]; 	/* volume name */
+	char	s_last_mounted[64]; 	/* directory where last mounted */
+	__le32	s_algorithm_usage_bitmap; /* For compression */
+	/*
+	 * Performance hints.  Directory preallocation should only
+	 * happen if the EXT2_COMPAT_PREALLOC flag is on.
+	 */
+	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
+	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
+	__u16	s_padding1;
+	/*
+	 * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
+	 */
+	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
+	__u32	s_journal_inum;		/* inode number of journal file */
+	__u32	s_journal_dev;		/* device number of journal file */
+	__u32	s_last_orphan;		/* start of list of inodes to delete */
+	__u32	s_hash_seed[4];		/* HTREE hash seed */
+	__u8	s_def_hash_version;	/* Default hash version to use */
+	__u8	s_reserved_char_pad;
+	__u16	s_reserved_word_pad;
+	__le32	s_default_mo