Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull the big VFS changes from Al Viro:
 "This one is *big* and changes quite a few things around VFS.  What's in there:

   - the first of two really major architecture changes - death to open
     intents.

     The former is finally there; it was very long in making, but with
     Miklos getting through really hard and messy final push in
     fs/namei.c, we finally have it.  Unlike his variant, this one
     doesn't introduce struct opendata; what we have instead is
     ->atomic_open() taking preallocated struct file * and passing
     everything via its fields.

     Instead of returning struct file *, it returns -E...  on error, 0
     on success and 1 in "deal with it yourself" case (e.g.  symlink
     found on server, etc.).

     See comments before fs/namei.c:atomic_open().  That made a lot of
     goodies finally possible and quite a few are in that pile:
     ->lookup(), ->d_revalidate() and ->create() do not get struct
     nameidata * anymore; ->lookup() and ->d_revalidate() get lookup
     flags instead, ->create() gets "do we want it exclusive" flag.

     With the introduction of new helper (kern_path_locked()) we are rid
     of all struct nameidata instances outside of fs/namei.c; it's still
     visible in namei.h, but not for long.  Come the next cycle,
     declaration will move either to fs/internal.h or to fs/namei.c
     itself.  [me, miklos, hch]

   - The second major change: behaviour of final fput().  Now we have
     __fput() done without any locks held by caller *and* not from deep
     in call stack.

     That obviously lifts a lot of constraints on the locking in there.
     Moreover, it's legal now to call fput() from atomic contexts (which
     has immediately simplified life for aio.c).  We also don't need
     anti-recursion logics in __scm_destroy() anymore.

     There is a price, though - the damn thing has become partially
     asynchronous.  For fput() from normal process we are guaranteed
     that pending __fput() will be done before the caller returns to
     userland, exits or gets stopped for ptrace.

     For kernel threads and atomic contexts it's done via
     schedule_work(), so theoretically we might need a way to make sure
     it's finished; so far only one such place had been found, but there
     might be more.

     There's flush_delayed_fput() (do all pending __fput()) and there's
     __fput_sync() (fput() analog doing __fput() immediately).  I hope
     we won't need them often; see warnings in fs/file_table.c for
     details.  [me, based on task_work series from Oleg merged last
     cycle]

   - sync series from Jan

   - large part of "death to sync_supers()" work from Artem; the only
     bits missing here are exofs and ext4 ones.  As far as I understand,
     those are going via the exofs and ext4 trees resp.; once they are
     in, we can put ->write_super() to the rest, along with the thread
     calling it.

   - preparatory bits from unionmount series (from dhowells).

   - assorted cleanups and fixes all over the place, as usual.

  This is not the last pile for this cycle; there's at least jlayton's
  ESTALE work and fsfreeze series (the latter - in dire need of fixes,
  so I'm not sure it'll make the cut this cycle).  I'll probably throw
  symlink/hardlink restrictions stuff from Kees into the next pile, too.
  Plus there's a lot of misc patches I hadn't thrown into that one -
  it's large enough as it is..."

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits)
  ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file()
  btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file()
  switch dentry_open() to struct path, make it grab references itself
  spufs: shift dget/mntget towards dentry_open()
  zoran: don't bother with struct file * in zoran_map
  ecryptfs: don't reinvent the wheels, please - use struct completion
  don't expose I_NEW inodes via dentry->d_inode
  tidy up namei.c a bit
  unobfuscate follow_up() a bit
  ext3: pass custom EOF to generic_file_llseek_size()
  ext4: use core vfs llseek code for dir seeks
  vfs: allow custom EOF in generic_file_llseek code
  vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes
  vfs: Remove unnecessary flushing of block devices
  vfs: Make sys_sync writeout also block device inodes
  vfs: Create function for iterating over block devices
  vfs: Reorder operations during sys_sync
  quota: Move quota syncing to ->sync_fs method
  quota: Split dquot_quota_sync() to writeback and cache flushing part
  vfs: Move noop_backing_dev_info check from sync into writeback
  ...

7 files changed, 68 insertions, 59 deletions

diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 62fc14ea4b73..422dde2ec0a1 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -18,7 +18,7 @@
  * hfs_lookup()
  */
 static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
-				 struct nameidata *nd)
+				 unsigned int flags)
 {
 	hfs_cat_rec rec;
 	struct hfs_find_data fd;
@@ -187,7 +187,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
  * the directory and the name (and its length) of the new file.
  */
 static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		      struct nameidata *nd)
+		      bool excl)
 {
 	struct inode *inode;
 	int res;
diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index 2c16316d2917..a67955a0c36f 100644
--- a/fs/hfs/extent.c
+++ b/fs/hfs/extent.c
@@ -432,7 +432,7 @@ out:
 		if (inode->i_ino < HFS_FIRSTUSER_CNID)
 			set_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags);
 		set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-		sb->s_dirt = 1;
+		hfs_mark_mdb_dirty(sb);
 	}
 	return res;
 
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 1bf967c6bfdc..8275175acf6e 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
+#include <linux/workqueue.h>
 
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
@@ -137,16 +138,15 @@ struct hfs_sb_info {
 	gid_t s_gid;				/* The gid of all files */
 
 	int session, part;
-
 	struct nls_table *nls_io, *nls_disk;
-
 	struct mutex bitmap_lock;
-
 	unsigned long flags;
-
 	u16 blockoffset;
-
 	int fs_div;
+	struct super_block *sb;
+	int work_queued;		/* non-zero delayed work is queued */
+	struct delayed_work mdb_work;	/* MDB flush delayed work */
+	spinlock_t work_lock;		/* protects mdb_work and work_queued */
 };
 
 #define HFS_FLG_BITMAP_DIRTY	0
@@ -226,6 +226,9 @@ extern int hfs_compare_dentry(const struct dentry *parent,
 extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *);
 extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *);
 
+/* super.c */
+extern void hfs_mark_mdb_dirty(struct super_block *sb);
+
 extern struct timezone sys_tz;
 
 /*
@@ -253,7 +256,7 @@ static inline const char *hfs_mdb_name(struct super_block *sb)
 static inline void hfs_bitmap_dirty(struct super_block *sb)
 {
 	set_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 }
 
 #define sb_bread512(sb, sec, data) ({			\
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 761ec06354b4..ee1bc55677f1 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -220,7 +220,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode)
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
 	set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 
 	return inode;
 }
@@ -235,7 +235,7 @@ void hfs_delete_inode(struct inode *inode)
 		if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID))
 			HFS_SB(sb)->root_dirs--;
 		set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-		sb->s_dirt = 1;
+		hfs_mark_mdb_dirty(sb);
 		return;
 	}
 	HFS_SB(sb)->file_count--;
@@ -248,7 +248,7 @@ void hfs_delete_inode(struct inode *inode)
 		}
 	}
 	set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 }
 
 void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
@@ -489,7 +489,7 @@ out:
 }
 
 static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
-				      struct nameidata *nd)
+				      unsigned int flags)
 {
 	struct inode *inode = NULL;
 	hfs_cat_rec rec;
@@ -644,13 +644,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 
 	/* sync the superblock to buffers */
 	sb = inode->i_sb;
-	if (sb->s_dirt) {
-		lock_super(sb);
-		sb->s_dirt = 0;
-		if (!(sb->s_flags & MS_RDONLY))
-			hfs_mdb_commit(sb);
-		unlock_super(sb);
-	}
+	flush_delayed_work_sync(&HFS_SB(sb)->mdb_work);
 	/* .. finally sync the buffers to disk */
 	err = sync_blockdev(sb->s_bdev);
 	if (!ret)
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 1563d5ce5764..5fd51a5833ff 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -260,6 +260,10 @@ void hfs_mdb_commit(struct super_block *sb)
 {
 	struct hfs_mdb *mdb = HFS_SB(sb)->mdb;
 
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	lock_buffer(HFS_SB(sb)->mdb_bh);
 	if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) {
 		/* These parameters may have been modified, so write them back */
 		mdb->drLsMod = hfs_mtime();
@@ -283,9 +287,13 @@ void hfs_mdb_commit(struct super_block *sb)
 				     &mdb->drXTFlSize, NULL);
 		hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec,
 				     &mdb->drCTFlSize, NULL);
+
+		lock_buffer(HFS_SB(sb)->alt_mdb_bh);
 		memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE);
 		HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT);
 		HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT);
+		unlock_buffer(HFS_SB(sb)->alt_mdb_bh);
+
 		mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh);
 		sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh);
 	}
@@ -308,7 +316,11 @@ void hfs_mdb_commit(struct super_block *sb)
 				break;
 			}
 			len = min((int)sb->s_blocksize - off, size);
+
+			lock_buffer(bh);
 			memcpy(bh->b_data + off, ptr, len);
+			unlock_buffer(bh);
+
 			mark_buffer_dirty(bh);
 			brelse(bh);
 			block++;
@@ -317,6 +329,7 @@ void hfs_mdb_commit(struct super_block *sb)
 			size -= len;
 		}
 	}
+	unlock_buffer(HFS_SB(sb)->mdb_bh);
 }
 
 void hfs_mdb_close(struct super_block *sb)
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 7b4c537d6e13..4eb873e0c07b 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -29,43 +29,9 @@ static struct kmem_cache *hfs_inode_cachep;
 
 MODULE_LICENSE("GPL");
 
-/*
- * hfs_write_super()
- *
- * Description:
- *   This function is called by the VFS only. When the filesystem
- *   is mounted r/w it updates the MDB on disk.
- * Input Variable(s):
- *   struct super_block *sb: Pointer to the hfs superblock
- * Output Variable(s):
- *   NONE
- * Returns:
- *   void
- * Preconditions:
- *   'sb' points to a "valid" (struct super_block).
- * Postconditions:
- *   The MDB is marked 'unsuccessfully unmounted' by clearing bit 8 of drAtrb
- *   (hfs_put_super() must set this flag!). Some MDB fields are updated
- *   and the MDB buffer is written to disk by calling hfs_mdb_commit().
- */
-static void hfs_write_super(struct super_block *sb)
-{
-	lock_super(sb);
-	sb->s_dirt = 0;
-
-	/* sync everything to the buffers */
-	if (!(sb->s_flags & MS_RDONLY))
-		hfs_mdb_commit(sb);
-	unlock_super(sb);
-}
-
 static int hfs_sync_fs(struct super_block *sb, int wait)
 {
-	lock_super(sb);
 	hfs_mdb_commit(sb);
-	sb->s_dirt = 0;
-	unlock_super(sb);
-
 	return 0;
 }
 
@@ -78,13 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait)
  */
 static void hfs_put_super(struct super_block *sb)
 {
-	if (sb->s_dirt)
-		hfs_write_super(sb);
+	cancel_delayed_work_sync(&HFS_SB(sb)->mdb_work);
 	hfs_mdb_close(sb);
 	/* release the MDB's resources */
 	hfs_mdb_put(sb);
 }
 
+static void flush_mdb(struct work_struct *work)
+{
+	struct hfs_sb_info *sbi;
+	struct super_block *sb;
+
+	sbi = container_of(work, struct hfs_sb_info, mdb_work.work);
+	sb = sbi->sb;
+
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	hfs_mdb_commit(sb);
+}
+
+void hfs_mark_mdb_dirty(struct super_block *sb)
+{
+	struct hfs_sb_info *sbi = HFS_SB(sb);
+	unsigned long delay;
+
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	spin_lock(&sbi->work_lock);
+	if (!sbi->work_queued) {
+		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+		queue_delayed_work(system_long_wq, &sbi->mdb_work, delay);
+		sbi->work_queued = 1;
+	}
+	spin_unlock(&sbi->work_lock);
+}
+
 /*
  * hfs_statfs()
  *
@@ -184,7 +181,6 @@ static const struct super_operations hfs_super_operations = {
 	.write_inode	= hfs_write_inode,
 	.evict_inode	= hfs_evict_inode,
 	.put_super	= hfs_put_super,
-	.write_super	= hfs_write_super,
 	.sync_fs	= hfs_sync_fs,
 	.statfs		= hfs_statfs,
 	.remount_fs     = hfs_remount,
@@ -387,7 +383,10 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		return -ENOMEM;
 
+	sbi->sb = sb;
 	sb->s_fs_info = sbi;
+	spin_lock_init(&sbi->work_lock);
+	INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb);
 
 	res = -EINVAL;
 	if (!parse_options((char *)data, sbi)) {
diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c
index 19cf291eb91f..91b91fd3a901 100644
--- a/fs/hfs/sysdep.c
+++ b/fs/hfs/sysdep.c
@@ -13,12 +13,12 @@
 
 /* dentry case-handling: just lowercase everything */
 
-static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
+static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	int diff;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = dentry->d_inode;