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  vfs: fix out-of-date dentry_unhash() comment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
  ...

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)

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 @@ static int __init init_mtdchar(void)
 
 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");
 }

fs/aio.c

@@ -305,15 +305,18 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	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");

fs/ext2/xattr_security.c

@@ -3,10 +3,7 @@
  * Handler for storing security labels as extended attributes.
  */
 
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include <linux/security.h>
 #include "xattr.h"
 

fs/ext2/xattr_trusted.c

@@ -5,10 +5,7 @@
  * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext2_fs.h>
+#include "ext2.h"
 #include "xattr.h"
 
 static size_t

fs/ext2/xip.c

@@ -9,8 +9,6 @@
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/buffer_head.h>
-#include <linux/ext2_fs_sb.h>
-#include <linux/ext2_fs.h>
 #include <linux/blkdev.h>
 #include "ext2.h"
 #include "xip.h"

fs/ext3/acl.c

@@ -4,13 +4,7 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 

fs/ext3/balloc.c

@@ -11,17 +11,9 @@
  *        David S. Miller (davem@caip.rutgers.edu), 1995
  */
 
-#include <linux/time.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines

fs/ext3/bitmap.c

@@ -7,9 +7,7 @@
  * Universite Pierre et Marie Curie (Paris VI)
  */
 
-#include <linux/buffer_head.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 
 #ifdef EXT3FS_DEBUG
 

fs/ext3/dir.c

@@ -21,12 +21,7 @@
  *
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/rbtree.h>
+#include "ext3.h"
 
 static unsigned char ext3_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK

fs/ext3/ext3_jbd.c

@@ -2,7 +2,7 @@
  * Interface between ext3 and JBD
  */
 
-#include <linux/ext3_jbd.h>
+#include "ext3.h"
 
 int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)

fs/ext3/file.c

@@ -18,12 +18,8 @@
  *	(jj@sunsite.ms.mff.cuni.cz)
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/jbd.h>
 #include <linux/quotaops.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 

fs/ext3/fsync.c

@@ -22,15 +22,9 @@
  * we can depend on generic_block_fdatasync() to sync the data blocks.
  */
 
-#include <linux/time.h>
 #include <linux/blkdev.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
 #include <linux/writeback.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 
 /*
  * akpm: A new design for ext3_sync_file().

fs/ext3/hash.c

@@ -9,9 +9,7 @@
  * License.
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include <linux/cryptohash.h>
 
 #define DELTA 0x9E3779B9

fs/ext3/ialloc.c

@@ -12,21 +12,10 @@
  *        David S. Miller (davem@caip.rutgers.edu), 1995
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/stat.h>
-#include <linux/string.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
 #include <linux/random.h>
-#include <linux/bitops.h>
-#include <trace/events/ext3.h>
-
-#include <asm/byteorder.h>
 
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 

fs/ext3/inode.c

@@ -22,22 +22,12 @@
  *  Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
  */
 
-#include <linux/fs.h>
-#include <linux/time.h>
-#include <linux/ext3_jbd.h>
-#include <linux/jbd.h>
 #include <linux/highuid.h>
-#include <linux/pagemap.h>
 #include <linux/quotaops.h>
-#include <linux/string.h>
-#include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/mpage.h>
-#include <linux/uio.h>
-#include <linux/bio.h>
-#include <linux/fiemap.h>
 #include <linux/namei.h>
-#include <trace/events/ext3.h>
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 

fs/ext3/ioctl.c

@@ -7,15 +7,10 @@
  * Universite Pierre et Marie Curie (Paris VI)
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/capability.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
 #include <linux/mount.h>
-#include <linux/time.h>
 #include <linux/compat.h>
 #include <asm/uaccess.h>
+#include "ext3.h"
 
 long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {

fs/ext3/namei.c

@@ -24,20 +24,8 @@
  *	Theodore Ts'o, 2002
  */
 
-#include <linux/fs.h>
-#include <linux/pagemap.h>
-#include <linux/jbd.h>
-#include <linux/time.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/fcntl.h>
-#include <linux/stat.h>
-#include <linux/string.h>
 #include <linux/quotaops.h>
-#include <linux/buffer_head.h>
-#include <linux/bio.h>
-#include <trace/events/ext3.h>
-
+#include "ext3.h"
 #include "namei.h"
 #include "xattr.h"
 #include "acl.h"

fs/ext3/resize.c

@@ -11,10 +11,7 @@
 
 #define EXT3FS_DEBUG
 
-#include <linux/ext3_jbd.h>
-
-#include <linux/errno.h>
-#include <linux/slab.h>
+#include "ext3.h"
 
 
 #define outside(b, first, last)	((b) < (first) || (b) >= (last))

fs/ext3/super.c

@@ -17,22 +17,12 @@
  */
 
 #include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/time.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/slab.h>
-#include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/buffer_head.h>
 #include <linux/exportfs.h>
-#include <linux/vfs.h>
+#include <linux/statfs.h>
 #include <linux/random.h>
 #include <linux/mount.h>
-#include <linux/namei.h>
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
 #include <linux/log2.h>
@@ -40,13 +30,13 @@
 
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+
+#include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
 #include "namei.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/ext3.h>
-
 #ifdef CONFIG_EXT3_DEFAULTS_TO_ORDERED
   #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_ORDERED_DATA
 #else

fs/ext3/symlink.c

@@ -17,10 +17,8 @@
  *  ext3 symlink handling code
  */
 
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
 #include <linux/namei.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd)

fs/ext3/xattr.c

@@ -50,14 +50,9 @@
  * by the buffer lock.
  */
 
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
-#include <linux/rwsem.h>
 #include "xattr.h"
 #include "acl.h"
 

fs/ext3/xattr_security.c

@@ -3,12 +3,8 @@
  * Handler for storing security labels as extended attributes.
  */
 
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
 #include <linux/security.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t

fs/ext3/xattr_trusted.c

@@ -5,11 +5,7 @@
  * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/capability.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t

fs/ext3/xattr_user.c

@@ -5,10 +5,7 @@
  * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
  */
 
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/ext3_jbd.h>
-#include <linux/ext3_fs.h>
+#include "ext3.h"
 #include "xattr.h"
 
 static size_t

fs/gfs2/file.c

@@ -18,7 +18,6 @@
 #include <linux/mount.h>
 #include <linux/fs.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/ext2_fs.h>
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/crc32.h>

fs/namei.c

@@ -1054,53 +1054,65 @@ static void follow_dotdot(struct nameidata *nd)
 }
 
 /*
- * Allocate a dentry with name and parent, and perform a parent
- * directory ->lookup on it. Returns the new dentry, or ERR_PTR
- * on error. parent->d_inode->i_mutex must be held. d_lookup must
- * have verified that no child exists while under i_mutex.
+ * This looks up the name in dcache, possibly revalidates the old dentry and
+ * allocates a new one if not found or not valid.  In the need_lookup argument
+ * returns whether i_op->lookup is necessary.
+ *
+ * dir->d_inode->i_mutex must be held
  */
-static struct dentry *d_alloc_and_lookup(struct dentry *parent,
-				struct qstr *name, struct nameidata *nd)
+static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
+				    struct nameidata *nd, bool *need_lookup)
 {
-	struct inode *inode = parent->d_inode;
 	struct dentry *dentry;
-	struct dentry *old;
+	int error;
 
-	/* Don't create child dentry for a dead directory. */
-	if (unlikely(IS_DEADDIR(inode)))
-		return ERR_PTR(-ENOENT);
+	*need_lookup = false;
+	dentry = d_lookup(dir, name);
+	if (dentry) {
+		if (d_need_lookup(dentry)) {
+			*need_lookup = true;
+		} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
+			error = d_revalidate(dentry, nd);
+			if (unlikely(error <= 0)) {
+				if (error < 0) {
+					dput(dentry);
+					return ERR_PTR(error);
+				} else if (!d_invalidate(dentry)) {
+					dput(dentry);
+					dentry = NULL;
+				}
+			}
+		}
+	}
 
-	dentry = d_alloc(parent, name);
-	if (unlikely(!dentry))
-		return ERR_PTR(-ENOMEM);
+	if (!dentry) {
+		dentry = d_alloc(dir, name);
+		if (unlikely(!dentry))
+			return ERR_PTR(-ENOMEM);
 
-	old = inode->i_op->lookup(inode, dentry, nd);
-	if (unlikely(old)) {
-		dput(dentry);
-		dentry = old;
+		*need_lookup = true;
 	}
 	return dentry;
 }
 
 /*
- * We already have a dentry, but require a lookup to be performed on the parent
- * directory to fill in d_inode. Returns the new dentry, or ERR_PTR on error.
- * parent->d_inode->i_mutex must be held. d_lookup must have verified that no
- * child exists while under i_mutex.
+ * Call i_op->lookup on the dentry.  The dentry must be negative but may be
+ * hashed if it was pouplated with DCACHE_NEED_LOOKUP.
+ *
+ * dir->d_inode->i_mutex must be held
  */
-static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentry,
-				     struct nameidata *nd)
+static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
+				  struct nameidata *nd)
 {
-	struct inode *inode = parent->d_inode;
 	struct dentry *old;
 
 	/* Don't create child dentry for a dead directory. */
-	if (unlikely(IS_DEADDIR(inode))) {
+	if (unlikely(IS_DEADDIR(dir))) {
 		dput(dentry);
 		return ERR_PTR(-ENOENT);
 	}
 
-	old = inode->i_op->lookup(inode, dentry, nd);
+	old = dir->i_op->lookup(dir, dentry, nd);
 	if (unlikely(old)) {
 		dput(dentry);
 		dentry = old;
@@ -1108,6 +1120,19 @@ static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentr
 	return dentry;
 }
 
+static struct dentry *__lookup_hash(struct qstr *name,
+		struct dentry *base, struct nameidata *nd)
+{
+	bool need_lookup;
+	struct dentry *dentry;
+
+	dentry = lookup_dcache(name, base, nd, &need_lookup);
+	if (!need_lookup)
+		return dentry;
+
+	return lookup_real(base->d_inode, dentry, nd);
+}
+
 /*
  *  It's more convoluted than I'd like it to be, but... it's still fairly
  *  small and for now I'd prefer to have fast path as straight as possible.
@@ -1139,6 +1164,8 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 			return -ECHILD;
 		nd->seq = seq;
 
+		if (unlikely(d_need_lookup(dentry)))
+			goto unlazy;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
 			status = d_revalidate(dentry, nd);
 			if (unlikely(status <= 0)) {
@@ -1147,8 +1174,6 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 				goto unlazy;
 			}
 		}
-		if (unlikely(d_need_lookup(dentry)))
-			goto unlazy;
 		path->mnt = mnt;
 		path->dentry = dentry;
 		if (unlikely(!__follow_mount_rcu(nd, path, inode)))
@@ -1163,38 +1188,14 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		dentry = __d_lookup(parent, name);
 	}
 
-	if (dentry && unlikely(d_need_lookup(dentry))) {
+	if (unlikely(!dentry))
+		goto need_lookup;
+
+	if (unlikely(d_need_lookup(dentry))) {
 		dput(dentry);
-		dentry = NULL;
-	}
-retry:
-	if (unlikely(!dentry)) {
-		struct inode *dir = parent->d_inode;
-		BUG_ON(nd->inode != dir);
-
-		mutex_lock(&dir->i_mutex);
-		dentry = d_lookup(parent, name);
-		if (likely(!dentry)) {
-			dentry = d_alloc_and_lookup(parent, name, nd);
-			if (IS_ERR(dentry)) {
-				mutex_unlock(&dir->i_mutex);
-				return PTR_ERR(dentry);
-			}
-			/* known good */
-			need_reval = 0;
-			status = 1;
-		} else if (unlikely(d_need_lookup(dentry))) {
-			dentry = d_inode_lookup(parent, dentry, nd);
-			if (IS_ERR(dentry)) {
-				mutex_unlock(&dir->i_mutex);
-				return PTR_ERR(dentry);
-			}
-			/* known good */
-			need_reval = 0;
-			status = 1;
-		}
-		mutex_unlock(&dir->i_mutex);
+		goto need_lookup;
 	}
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
 		status = d_revalidate(dentry, nd);
 	if (unlikely(status <= 0)) {
@@ -1204,12 +1205,10 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		}
 		if (!d_invalidate(dentry)) {
 			dput(dentry);
-			dentry = NULL;
-			need_reval = 1;
-			goto retry;
+			goto need_lookup;
 		}
 	}
-
+done:
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd->flags);
@@ -1221,6 +1220,16 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
+
+need_lookup:
+	BUG_ON(nd->inode != parent->d_inode);
+
+	mutex_lock(&parent->d_inode->i_mutex);
+	dentry = __lookup_hash(name, parent, nd);
+	mutex_unlock(&parent->d_inode->i_mutex);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	goto done;
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1846,59 +1855,6 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	return err;
 }
 
-static struct dentry *__lookup_hash(struct qstr *name,
-		struct dentry *base, struct nameidata *nd)
-{
-	struct inode *inode = base->d_inode;
-	struct dentry *dentry;
-	int err;
-
-	err = inode_permission(inode, MAY_EXEC);
-	if (err)
-		return ERR_PTR(err);
-
-	/*
-	 * Don't bother with __d_lookup: callers are for creat as
-	 * well as unlink, so a lot of the time it would cost
-	 * a double lookup.
-	 */
-	dentry = d_lookup(base, name);
-
-	if (dentry && d_need_lookup(dentry)) {
-		/*
-		 * __lookup_hash is called with the parent dir's i_mutex already
-		 * held, so we are good to go here.
-		 */
-		dentry = d_inode_lookup(base, dentry, nd);
-		if (IS_ERR(dentry))
-			return dentry;
-	}
-
-	if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE)) {
-		int status = d_revalidate(dentry, nd);
-		if (unlikely(status <= 0)) {
-			/*
-			 * The dentry failed validation.
-			 * If d_revalidate returned 0 attempt to invalidate
-			 * the dentry otherwise d_revalidate is asking us
-			 * to return a fail status.
-			 */
-			if (status < 0) {
-				dput(dentry);
-				return ERR_PTR(status);
-			} else if (!d_invalidate(dentry)) {
-				dput(dentry);
-				dentry = NULL;
-			}
-		}
-	}
-
-	if (!dentry)
-		dentry = d_alloc_and_lookup(base, name, nd);
-
-	return dentry;
-}
-
 /*
  * Restricted form of lookup. Doesn't follow links, single-component only,
  * needs parent already locked. Doesn't follow mounts.
@@ -1924,6 +1880,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
 	struct qstr this;
 	unsigned int c;
+	int err;
 
 	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
 
@@ -1948,6 +1905,10 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 			return ERR_PTR(err);
 	}
 
+	err = inode_permission(base->d_inode, MAY_EXEC);
+	if (err)
+		return ERR_PTR(err);
+
 	return __lookup_hash(&this, base, NULL);
 }
 
@@ -2749,7 +2710,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 
 /*
  * The dentry_unhash() helper will try to drop the dentry early: we
- * should have a usage count of 2 if we're the only user of this
+ * should have a usage count of 1 if we're the only user of this
  * dentry, and if that is true (possibly after pruning the dcache),
  * then we drop the dentry now.
  *

fs/ocfs2/ioctl.c

@@ -28,8 +28,6 @@
 #include "suballoc.h"
 #include "move_extents.h"
 
-#include <linux/ext2_fs.h>
-
 #define o2info_from_user(a, b)	\
 		copy_from_user(&(a), (b), sizeof(a))
 #define o2info_to_user(a, b)	\

fs/pstore/inode.c

@@ -105,26 +105,12 @@ static const struct inode_operations pstore_dir_inode_operations = {
 	.unlink		= pstore_unlink,
 };
 
-static struct inode *pstore_get_inode(struct super_block *sb,
-					const struct inode *dir, int mode, dev_t dev)
+static struct inode *pstore_get_inode(struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
-
 	if (inode) {
 		inode->i_ino = get_next_ino();
-		inode->i_uid = inode->i_gid = 0;
-		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		switch (mode & S_IFMT) {
-		case S_IFREG:
-			inode->i_fop = &pstore_file_operations;
-			break;
-		case S_IFDIR:
-			inode->i_op = &pstore_dir_inode_operations;
-			inode->i_fop = &simple_dir_operations;
-			inc_nlink(inode);
-			break;
-		}
 	}
 	return inode;
 }
@@ -216,9 +202,11 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
 		return rc;
 
 	rc = -ENOMEM;
-	inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0);
+	inode = pstore_get_inode(pstore_sb);
 	if (!inode)
 		goto fail;
+	inode->i_mode = S_IFREG | 0444;
+	inode->i_fop = &pstore_file_operations;
 	private = kmalloc(sizeof *private + size, GFP_KERNEL);
 	if (!private)
 		goto fail_alloc;
@@ -293,10 +281,12 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent)
 
 	parse_options(data);
 
-	inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = pstore_get_inode(sb);
 	if (inode) {
-		/* override ramfs "dir" options so we catch unlink(2) */
+		inode->i_mode = S_IFDIR | 0755;
 		inode->i_op = &pstore_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		inc_nlink(inode);
 	}
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)

include/linux/Kbuild

@@ -120,7 +120,6 @@ header-y += errno.h
 header-y += errqueue.h
 header-y += ethtool.h
 header-y += eventpoll.h
-header-y += ext2_fs.h
 header-y += fadvise.h
 header-y += falloc.h
 header-y += fanotify.h

include/linux/ext2_fs_sb.h

-/*
- *  linux/include/linux/ext2_fs_sb.h
- *
- * 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_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT2_FS_SB
-#define _LINUX_EXT2_FS_SB
-
-#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);
-}
-
-#endif	/* _LINUX_EXT2_FS_SB */

include/linux/ext3_fs_i.h

-/*
- *  linux/include/linux/ext3_fs_i.h
- *
- * 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_i.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT3_FS_I
-#define _LINUX_EXT3_FS_I
-
-#include <linux/rwsem.h>
-#include <linux/rbtree.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-
-/* data type for block offset of block group */
-typedef int ext3_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long ext3_fsblk_t;
-
-#define E3FSBLK "%lu"
-
-struct ext3_reserve_window {
-	ext3_fsblk_t	_rsv_start;	/* First byte reserved */
-	ext3_fsblk_t	_rsv_end;	/* Last byte reserved or 0 */
-};
-
-struct ext3_reserve_window_node {
-	struct rb_node		rsv_node;
-	__u32			rsv_goal_size;
-	__u32			rsv_alloc_hit;
-	struct ext3_reserve_window	rsv_window;
-};
-
-struct ext3_block_alloc_info {
-	/* information about reservation window */
-	struct ext3_reserve_window_node	rsv_window_node;
-	/*
-	 * was i_next_alloc_block in ext3_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 ext3_inode_info
-	 * is the *physical* companion to i_next_alloc_block.
-	 * it 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.
-	 */
-	ext3_fsblk_t		last_alloc_physical_block;
-};
-
-#define rsv_start rsv_window._rsv_start
-#define rsv_end rsv_window._rsv_end
-
-/*
- * third extended file system inode data in memory
- */
-struct ext3_inode_info {
-	__le32	i_data[15];	/* unconverted */
-	__u32	i_flags;
-#ifdef EXT3_FRAGMENTS
-	__u32	i_faddr;
-	__u8	i_frag_no;
-	__u8	i_frag_size;
-#endif
-	ext3_fsblk_t	i_file_acl;
-	__u32	i_dir_acl;
-	__u32	i_dtime;
-
-	/*
-	 * i_block_group is the number of the block group which contains
-	 * this file's inode.  Constant across the lifetime of the inode,
-	 * it is ued for making block allocation decisions - we try to
-	 * place a file's data blocks near its inode block, and new inodes
-	 * near to their parent directory's inode.
-	 */
-	__u32	i_block_group;
-	unsigned long	i_state_flags;	/* Dynamic state flags for ext3 */
-
-	/* block reservation info */
-	struct ext3_block_alloc_info *i_block_alloc_info;
-
-	__u32	i_dir_start_lookup;
-#ifdef CONFIG_EXT3_FS_XATTR
-	/*
-	 * Extended attributes can be read independently of the main file
-	 * data. Taking i_mutex even when reading would cause contention
-	 * between readers of EAs and writers of regular file data, so
-	 * instead we synchronize on xattr_sem when reading or changing
-	 * EAs.
-	 */
-	struct rw_semaphore xattr_sem;
-#endif
-
-	struct list_head i_orphan;	/* unlinked but open inodes */
-
-	/*
-	 * i_disksize keeps track of what the inode size is ON DISK, not
-	 * in memory.  During truncate, i_size is set to the new size by
-	 * the VFS prior to calling ext3_truncate(), but the filesystem won't
-	 * set i_disksize to 0 until the truncate is actually under way.
-	 *
-	 * The intent is that i_disksize always represents the blocks which
-	 * are used by this file.  This allows recovery to restart truncate
-	 * on orphans if we crash during truncate.  We actually write i_disksize
-	 * into the on-disk inode when writing inodes out, instead of i_size.
-	 *
-	 * The only time when i_disksize and i_size may be different is when
-	 * a truncate is in progress.  The only things which change i_disksize
-	 * are ext3_get_block (growth) and ext3_truncate (shrinkth).
-	 */
-	loff_t	i_disksize;
-
-	/* on-disk additional length */
-	__u16 i_extra_isize;
-
-	/*
-	 * truncate_mutex is for serialising ext3_truncate() against
-	 * ext3_getblock().  In the 2.4 ext2 design, great chunks of inode's
-	 * data tree are chopped off during truncate. We can't do that in
-	 * ext3 because whenever we perform intermediate commits during
-	 * truncate, the inode and all the metadata blocks *must* be in a
-	 * consistent state which allows truncation of the orphans to restart
-	 * during recovery.  Hence we must fix the get_block-vs-truncate race
-	 * by other means, so we have truncate_mutex.
-	 */
-	struct mutex truncate_mutex;
-
-	/*
-	 * Transactions that contain inode's metadata needed to complete
-	 * fsync and fdatasync, respectively.
-	 */
-	atomic_t i_sync_tid;
-	atomic_t i_datasync_tid;
-
-	struct inode vfs_inode;
-};
-
-#endif	/* _LINUX_EXT3_FS_I */

include/linux/ext3_fs_sb.h

-/*
- *  linux/include/linux/ext3_fs_sb.h
- *
- * 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_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _LINUX_EXT3_FS_SB
-#define _LINUX_EXT3_FS_SB
-
-#ifdef __KERNEL__
-#include <linux/timer.h>
-#include <linux/wait.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#endif
-#include <linux/rbtree.h>
-
-/*
- * third extended-fs super-block data in memory
- */
-struct ext3_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 ext3_super_block * s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head ** s_group_desc;
-	unsigned long  s_mount_opt;
-	ext3_fsblk_t 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;
-	u32 s_hash_seed[4];
-	int s_def_hash_version;
-	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
-	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 ext3_reserve_window_node s_rsv_window_head;
-
-	/* Journaling */
-	struct inode * s_journal_inode;
-	struct journal_s * s_journal;
-	struct list_head s_orphan;
-	struct mutex s_orphan_lock;
-	struct mutex s_resize_lock;
-	unsigned long s_commit_interval;
-	struct block_device *journal_bdev;
-#ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
-	int s_jquota_fmt;			/* Format of quota to use */
-#endif
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group)
-{
-	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif	/* _LINUX_EXT3_FS_SB */

include/linux/ext3_jbd.h

-/*
- * linux/include/linux/ext3_jbd.h
- *
- * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
- *
- * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
- *
- * This file is part of the Linux kernel and is made available under
- * the terms of the GNU General Public License, version 2, or at your
- * option, any later version, incorporated herein by reference.
- *
- * Ext3-specific journaling extensions.
- */
-
-#ifndef _LINUX_EXT3_JBD_H
-#define _LINUX_EXT3_JBD_H
-
-#include <linux/fs.h>
-#include <linux/jbd.h>
-#include <linux/ext3_fs.h>
-
-#define EXT3_JOURNAL(inode)	(EXT3_SB((inode)->i_sb)->s_journal)
-
-/* Define the number of blocks we need to account to a transaction to
- * modify one block of data.
- *
- * We may have to touch one inode, one bitmap buffer, up to three
- * indirection blocks, the group and superblock summaries, and the data
- * block to complete the transaction.  */
-
-#define EXT3_SINGLEDATA_TRANS_BLOCKS	8U
-
-/* Extended attribute operations touch at most two data buffers,
- * two bitmap buffers, and two group summaries, in addition to the inode
- * and the superblock, which are already accounted for. */
-
-#define EXT3_XATTR_TRANS_BLOCKS		6U
-
-/* Define the minimum size for a transaction which modifies data.  This
- * needs to take into account the fact that we may end up modifying two
- * quota files too (one for the group, one for the user quota).  The
- * superblock only gets updated once, of course, so don't bother
- * counting that again for the quota updates. */
-
-#define EXT3_DATA_TRANS_BLOCKS(sb)	(EXT3_SINGLEDATA_TRANS_BLOCKS + \
-					 EXT3_XATTR_TRANS_BLOCKS - 2 + \
-					 EXT3_MAXQUOTAS_TRANS_BLOCKS(sb))
-
-/* Delete operations potentially hit one directory's namespace plus an
- * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
- * generous.  We can grow the delete transaction later if necessary. */
-
-#define EXT3_DELETE_TRANS_BLOCKS(sb)   (EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) + 64)
-
-/* Define an arbitrary limit for the amount of data we will anticipate
- * writing to any given transaction.  For unbounded transactions such as
- * write(2) and truncate(2) we can write more than this, but we always
- * start off at the maximum transaction size and grow the transaction
- * optimistically as we go. */
-
-#define EXT3_MAX_TRANS_DATA		64U
-
-/* We break up a large truncate or write transaction once the handle's
- * buffer credits gets this low, we need either to extend the
- * transaction or to start a new one.  Reserve enough space here for
- * inode, bitmap, superblock, group and indirection updates for at least
- * one block, plus two quota updates.  Quota allocations are not
- * needed. */
-
-#define EXT3_RESERVE_TRANS_BLOCKS	12U
-
-#define EXT3_INDEX_EXTRA_TRANS_BLOCKS	8
-
-#ifdef CONFIG_QUOTA
-/* Amount of blocks needed for quota update - we know that the structure was
- * allocated so we need to update only inode+data */
-#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
-/* Amount of blocks needed for quota insert/delete - we do some block writes
- * but inode, sb and group updates are done only once */
-#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
-		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0)
-#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
-		(EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0)
-#else
-#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0
-#define EXT3_QUOTA_INIT_BLOCKS(sb) 0
-#define EXT3_QUOTA_DEL_BLOCKS(sb) 0
-#endif
-#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
-
-int
-ext3_mark_iloc_dirty(handle_t *handle,
-		     struct inode *inode,
-		     struct ext3_iloc *iloc);
-
-/*
- * On success, We end up with an outstanding reference count against
- * iloc->bh.  This _must_ be cleaned up later.
- */
-
-int ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
-			struct ext3_iloc *iloc);
-
-int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode);
-
-/*
- * Wrapper functions with which ext3 calls into JBD.  The intent here is
- * to allow these to be turned into appropriate stubs so ext3 can control
- * ext2 filesystems, so ext2+ext3 systems only nee one fs.  This work hasn't
- * been done yet.
- */
-
-static inline void ext3_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	journal_release_buffer(handle, bh);
-}
-
-void ext3_journal_abort_handle(const char *caller, const char *err_fn,
-		struct buffer_head *bh, handle_t *handle, int err);
-
-int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_get_write_access(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_forget(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-int __ext3_journal_revoke(const char *where, handle_t *handle,
-				unsigned long blocknr, struct buffer_head *bh);
-
-int __ext3_journal_get_create_access(const char *where,
-				handle_t *handle, struct buffer_head *bh);
-
-int __ext3_journal_dirty_metadata(const char *where,
-				handle_t *handle, struct buffer_head *bh);
-
-#define ext3_journal_get_undo_access(handle, bh) \
-	__ext3_journal_get_undo_access(__func__, (handle), (bh))
-#define ext3_journal_get_write_access(handle, bh) \
-	__ext3_journal_get_write_access(__func__, (handle), (bh))
-#define ext3_journal_revoke(handle, blocknr, bh) \
-	__ext3_journal_revoke(__func__, (handle), (blocknr), (bh))
-#define ext3_journal_get_create_access(handle, bh) \
-	__ext3_journal_get_create_access(__func__, (handle), (bh))
-#define ext3_journal_dirty_metadata(handle, bh) \
-	__ext3_journal_dirty_metadata(__func__, (handle), (bh))
-#define ext3_journal_forget(handle, bh) \
-	__ext3_journal_forget(__func__, (handle), (bh))
-
-int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
-
-handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks);
-int __ext3_journal_stop(const char *where, handle_t *handle);
-
-static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks)
-{
-	return ext3_journal_start_sb(inode->i_sb, nblocks);
-}
-
-#define ext3_journal_stop(handle) \
-	__ext3_journal_stop(__func__, (handle))
-
-static inline handle_t *ext3_journal_current_handle(void)
-{
-	return journal_current_handle();
-}
-
-static inline int ext3_journal_extend(handle_t *handle, int nblocks)
-{
-	return journal_extend(handle, nblocks);
-}
-
-static inline int ext3_journal_restart(handle_t *handle, int nblocks)
-{
-	return journal_restart(handle, nblocks);
-}
-
-static inline int ext3_journal_blocks_per_page(struct inode *inode)
-{
-	return journal_blocks_per_page(inode);
-}
-
-static inline int ext3_journal_force_commit(journal_t *journal)
-{
-	return journal_force_commit(journal);
-}
-
-/* super.c */
-int ext3_force_commit(struct super_block *sb);
-
-static inline int ext3_should_journal_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 1;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
-		return 1;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 1;
-	return 0;
-}
-
-static inline int ext3_should_order_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
-		return 1;
-	return 0;
-}
-
-static inline int ext3_should_writeback_data(struct inode *inode)
-{
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL)
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
-		return 1;
-	return 0;
-}
-
-#endif	/* _LINUX_EXT3_JBD_H */

init/do_mounts_initrd.c

@@ -2,7 +2,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/minix_fs.h>
-#include <linux/ext2_fs.h>
 #include <linux/romfs_fs.h>
 #include <linux/initrd.h>
 #include <linux/sched.h>

init/do_mounts_rd.c

@@ -54,20 +54,19 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 {
 	const int size = 512;
 	struct minix_super_block *minixsb;
-	struct ext2_super_block *ext2sb;
 	struct romfs_super_block *romfsb;
 	struct cramfs_super *cramfsb;
 	struct squashfs_super_block *squashfsb;
 	int nblocks = -1;
 	unsigned char *buf;
 	const char *compress_name;
+	unsigned long n;
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	minixsb = (struct minix_super_block *) buf;
-	ext2sb = (struct ext2_super_block *) buf;
 	romfsb = (struct romfs_super_block *) buf;
 	cramfsb = (struct cramfs_super *) buf;
 	squashfsb = (struct squashfs_super_block *) buf;
@@ -150,12 +149,12 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	}
 
 	/* Try ext2 */
-	if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
+	n = ext2_image_size(buf);
+	if (n) {
 		printk(KERN_NOTICE
 		       "RAMDISK: ext2 filesystem found at block %d\n",
 		       start_block);
-		nblocks = le32_to_cpu(ext2sb->s_blocks_count) <<
-			le32_to_cpu(ext2sb->s_log_block_size);
+		nblocks = n;
 		goto done;
 	}
 

security/selinux/hooks.c

@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/tracehook.h>
 #include <linux/errno.h>
-#include <linux/ext2_fs.h>
 #include <linux/sched.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
@@ -2971,15 +2970,15 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	/* fall through */
 	case FIGETBSZ:
 	/* fall through */
-	case EXT2_IOC_GETFLAGS:
+	case FS_IOC_GETFLAGS:
 	/* fall through */
-	case EXT2_IOC_GETVERSION:
+	case FS_IOC_GETVERSION:
 		error = file_has_perm(cred, file, FILE__GETATTR);
 		break;
 
-	case EXT2_IOC_SETFLAGS:
+	case FS_IOC_SETFLAGS:
 	/* fall through */
-	case EXT2_IOC_SETVERSION:
+	case FS_IOC_SETVERSION:
 		error = file_has_perm(cred, file, FILE__SETATTR);
 		break;
 

security/selinux/selinuxfs.c

@@ -344,7 +344,7 @@ static int sel_make_classes(void);
 static int sel_make_policycap(void);
 
 /* declaration for sel_make_class_dirs */
-static int sel_make_dir(struct inode *dir, struct dentry *dentry,
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 			unsigned long *ino);
 
 static ssize_t sel_read_mls(struct file *filp, char __user *buf,
@@ -1678,13 +1678,9 @@ static int sel_make_class_dir_entries(char *classname, int index,
 	inode->i_ino = sel_class_to_ino(index);
 	d_add(dentry, inode);
 
-	dentry = d_alloc_name(dir, "perms");
-	if (!dentry)
-		return -ENOMEM;
-
-	rc = sel_make_dir(dir->d_inode, dentry, &last_class_ino);
-	if (rc)
-		return rc;
+	dentry = sel_make_dir(dir, "perms", &last_class_ino);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
 
 	rc = sel_make_perm_files(classname, index, dentry);
 
@@ -1733,15 +1729,12 @@ static int sel_make_classes(void)
 	for (i = 0; i < nclasses; i++) {
 		struct dentry *class_name_dir;
 
-		rc = -ENOMEM;
-		class_name_dir = d_alloc_name(class_dir, classes[i]);
-		if (!class_name_dir)
-			goto out;
-
-		rc = sel_make_dir(class_dir->d_inode, class_name_dir,
+		class_name_dir = sel_make_dir(class_dir, classes[i],
 				&last_class_ino);
-		if (rc)
+		if (IS_ERR(class_name_dir)) {
+			rc = PTR_ERR(class_name_dir);
 			goto out;
+		}
 
 		/* i+1 since class values are 1-indexed */
 		rc = sel_make_class_dir_entries(classes[i], i + 1,
@@ -1787,14 +1780,20 @@ static int sel_make_policycap(void)
 	return 0;
 }
 
-static int sel_make_dir(struct inode *dir, struct dentry *dentry,
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
 			unsigned long *ino)
 {
+	struct dentry *dentry = d_alloc_name(dir, name);
 	struct inode *inode;
 
-	inode = sel_make_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO);
-	if (!inode)
-		return -ENOMEM;
+	if (!dentry)
+		return ERR_PTR(-ENOMEM);
+
+	inode = sel_make_inode(dir->d_sb, S_IFDIR | S_IRUGO | S_IXUGO);
+	if (!inode) {
+		dput(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
@@ -1803,16 +1802,16 @@ static int sel_make_dir(struct inode *dir, struct dentry *dentry,
 	inc_nlink(inode);
 	d_add(dentry, inode);
 	/* bump link count on parent directory, too */
-	inc_nlink(dir);
+	inc_nlink(dir->d_inode);
 
-	return 0;
+	return dentry;
 }
 
 static int sel_fill_super(struct super_block *sb, void *data, int silent)
 {
 	int ret;
 	struct dentry *dentry;
-	struct inode *inode, *root_inode;
+	struct inode *inode;
 	struct inode_security_struct *isec;
 
 	static struct tree_descr selinux_files[] = {
@@ -1839,18 +1838,12 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 	if (ret)
 		goto err;
 
-	root_inode = sb->s_root->d_inode;
-
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, BOOL_DIR_NAME);
-	if (!dentry)
+	bool_dir = sel_make_dir(sb->s_root, BOOL_DIR_NAME, &sel_last_ino);
+	if (IS_ERR(bool_dir)) {
+		ret = PTR_ERR(bool_dir);
+		bool_dir = NULL;
 		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
-		goto err;
-
-	bool_dir = dentry;
+	}
 
 	ret = -ENOMEM;
 	dentry = d_alloc_name(sb->s_root, NULL_FILE_NAME);
@@ -1872,54 +1865,39 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 	d_add(dentry, inode);
 	selinux_null = dentry;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "avc");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	dentry = sel_make_dir(sb->s_root, "avc", &sel_last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
 		goto err;
+	}
 
 	ret = sel_make_avc_files(dentry);
 	if (ret)
 		goto err;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "initial_contexts");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	dentry = sel_make_dir(sb->s_root, "initial_contexts", &sel_last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
 		goto err;
+	}
 
 	ret = sel_make_initcon_files(dentry);
 	if (ret)
 		goto err;
 
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "class");
-	if (!dentry)
-		goto err;
-
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
-		goto err;
-
-	class_dir = dentry;
-
-	ret = -ENOMEM;
-	dentry = d_alloc_name(sb->s_root, "policy_capabilities");
-	if (!dentry)
+	class_dir = sel_make_dir(sb->s_root, "class", &sel_last_ino);
+	if (IS_ERR(class_dir)) {
+		ret = PTR_ERR(class_dir);
+		class_dir = NULL;
 		goto err;
+	}
 
-	ret = sel_make_dir(root_inode, dentry, &sel_last_ino);
-	if (ret)
+	policycap_dir = sel_make_dir(sb->s_root, "policy_capabilities", &sel_last_ino);
+	if (IS_ERR(policycap_dir)) {
+		ret = PTR_ERR(policycap_dir);
+		policycap_dir = NULL;
 		goto err;
-
-	policycap_dir = dentry;
-
+	}
 	return 0;
 err:
 	printk(KERN_ERR "SELinux: %s:  failed while creating inodes\n",