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
  ...

1 files changed, 82 insertions, 66 deletions

diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 302f340d0071..444927e5706b 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -302,7 +302,7 @@ void ufs_error (struct super_block * sb, const char * function,
 	if (!(sb->s_flags & MS_RDONLY)) {
 		usb1->fs_clean = UFS_FSBAD;
 		ubh_mark_buffer_dirty(USPI_UBH(uspi));
-		sb->s_dirt = 1;
+		ufs_mark_sb_dirty(sb);
 		sb->s_flags |= MS_RDONLY;
 	}
 	va_start (args, fmt);
@@ -334,7 +334,7 @@ void ufs_panic (struct super_block * sb, const char * function,
 	if (!(sb->s_flags & MS_RDONLY)) {
 		usb1->fs_clean = UFS_FSBAD;
 		ubh_mark_buffer_dirty(USPI_UBH(uspi));
-		sb->s_dirt = 1;
+		ufs_mark_sb_dirty(sb);
 	}
 	va_start (args, fmt);
 	vsnprintf (error_buf, sizeof(error_buf), fmt, args);
@@ -691,6 +691,83 @@ static void ufs_put_super_internal(struct super_block *sb)
 	UFSD("EXIT\n");
 }
 
+static int ufs_sync_fs(struct super_block *sb, int wait)
+{
+	struct ufs_sb_private_info * uspi;
+	struct ufs_super_block_first * usb1;
+	struct ufs_super_block_third * usb3;
+	unsigned flags;
+
+	lock_ufs(sb);
+	lock_super(sb);
+
+	UFSD("ENTER\n");
+
+	flags = UFS_SB(sb)->s_flags;
+	uspi = UFS_SB(sb)->s_uspi;
+	usb1 = ubh_get_usb_first(uspi);
+	usb3 = ubh_get_usb_third(uspi);
+
+	usb1->fs_time = cpu_to_fs32(sb, get_seconds());
+	if ((flags & UFS_ST_MASK) == UFS_ST_SUN  ||
+	    (flags & UFS_ST_MASK) == UFS_ST_SUNOS ||
+	    (flags & UFS_ST_MASK) == UFS_ST_SUNx86)
+		ufs_set_fs_state(sb, usb1, usb3,
+				UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
+	ufs_put_cstotal(sb);
+
+	UFSD("EXIT\n");
+	unlock_super(sb);
+	unlock_ufs(sb);
+
+	return 0;
+}
+
+static void delayed_sync_fs(struct work_struct *work)
+{
+	struct ufs_sb_info *sbi;
+
+	sbi = container_of(work, struct ufs_sb_info, sync_work.work);
+
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	ufs_sync_fs(sbi->sb, 1);
+}
+
+void ufs_mark_sb_dirty(struct super_block *sb)
+{
+	struct ufs_sb_info *sbi = UFS_SB(sb);
+	unsigned long delay;
+
+	spin_lock(&sbi->work_lock);
+	if (!sbi->work_queued) {
+		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+		queue_delayed_work(system_long_wq, &sbi->sync_work, delay);
+		sbi->work_queued = 1;
+	}
+	spin_unlock(&sbi->work_lock);
+}
+
+static void ufs_put_super(struct super_block *sb)
+{
+	struct ufs_sb_info * sbi = UFS_SB(sb);
+
+	UFSD("ENTER\n");
+
+	if (!(sb->s_flags & MS_RDONLY))
+		ufs_put_super_internal(sb);
+	cancel_delayed_work_sync(&sbi->sync_work);
+
+	ubh_brelse_uspi (sbi->s_uspi);
+	kfree (sbi->s_uspi);
+	kfree (sbi);
+	sb->s_fs_info = NULL;
+	UFSD("EXIT\n");
+	return;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -716,6 +793,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		goto failed_nomem;
 	sb->s_fs_info = sbi;
+	sbi->sb = sb;
 
 	UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
 	
@@ -727,6 +805,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 #endif
 	mutex_init(&sbi->mutex);
+	spin_lock_init(&sbi->work_lock);
+	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	/*
 	 * Set default mount options
 	 * Parse mount options
@@ -1191,68 +1271,6 @@ failed_nomem:
 	return -ENOMEM;
 }
 
-static int ufs_sync_fs(struct super_block *sb, int wait)
-{
-	struct ufs_sb_private_info * uspi;
-	struct ufs_super_block_first * usb1;
-	struct ufs_super_block_third * usb3;
-	unsigned flags;
-
-	lock_ufs(sb);
-	lock_super(sb);
-
-	UFSD("ENTER\n");
-
-	flags = UFS_SB(sb)->s_flags;
-	uspi = UFS_SB(sb)->s_uspi;
-	usb1 = ubh_get_usb_first(uspi);
-	usb3 = ubh_get_usb_third(uspi);
-
-	usb1->fs_time = cpu_to_fs32(sb, get_seconds());
-	if ((flags & UFS_ST_MASK) == UFS_ST_SUN  ||
-	    (flags & UFS_ST_MASK) == UFS_ST_SUNOS ||
-	    (flags & UFS_ST_MASK) == UFS_ST_SUNx86)
-		ufs_set_fs_state(sb, usb1, usb3,
-				UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
-	ufs_put_cstotal(sb);
-	sb->s_dirt = 0;
-
-	UFSD("EXIT\n");
-	unlock_super(sb);
-	unlock_ufs(sb);
-
-	return 0;
-}
-
-static void ufs_write_super(struct super_block *sb)
-{
-	if (!(sb->s_flags & MS_RDONLY))
-		ufs_sync_fs(sb, 1);
-	else
-		sb->s_dirt = 0;
-}
-
-static void ufs_put_super(struct super_block *sb)
-{
-	struct ufs_sb_info * sbi = UFS_SB(sb);
-		
-	UFSD("ENTER\n");
-
-	if (sb->s_dirt)
-		ufs_write_super(sb);
-
-	if (!(sb->s_flags & MS_RDONLY))
-		ufs_put_super_internal(sb);
-	
-	ubh_brelse_uspi (sbi->s_uspi);
-	kfree (sbi->s_uspi);
-	kfree (sbi);
-	sb->s_fs_info = NULL;
-	UFSD("EXIT\n");
-	return;
-}
-
-
 static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 {
 	struct ufs_sb_private_info * uspi;
@@ -1308,7 +1326,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 			ufs_set_fs_state(sb, usb1, usb3,
 				UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
 		ubh_mark_buffer_dirty (USPI_UBH(uspi));
-		sb->s_dirt = 0;
 		sb->s_flags |= MS_RDONLY;
 	} else {
 	/*
@@ -1458,7 +1475,6 @@ static const struct super_operations ufs_super_ops = {
 	.write_inode	= ufs_write_inode,
 	.evict_inode	= ufs_evict_inode,
 	.put_super	= ufs_put_super,
-	.write_super	= ufs_write_super,
 	.sync_fs	= ufs_sync_fs,
 	.statfs		= ufs_statfs,
 	.remount_fs	= ufs_remount,