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

Pull VFS fixes and cleanups from Al Viro.

Most of this is the series to remove sync_supers() and the
->write_supers VFS callback from Artem Bityutskiy.  One commit to do the
actual removal work, a whole series of commits to fix up stale comments
etc all over the tree.

There's also a regression fix for an incorrect use of mnt_drop_write()
in do_dentry_open().

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  missed mnt_drop_write() in do_dentry_open()
  UBIFS: nuke pdflush from comments
  gfs2: nuke pdflush from comments
  drbd: nuke pdflush from comments
  nilfs2: nuke write_super from comments
  hfs: nuke write_super from comments
  vfs: nuke pdflush from comments
  jbd/jbd2: nuke write_super from comments
  btrfs: nuke pdflush from comments
  btrfs: nuke write_super from comments
  ext4: nuke pdflush from comments
  ext4: nuke write_super from comments
  ext3: nuke write_super from comments
  Documentation: fix the VM knobs descritpion WRT pdflush
  Documentation: get rid of write_super
  vfs: kill write_super and sync_supers

Documentation/DocBook/filesystems.tmpl

@@ -224,8 +224,8 @@ all your transactions.
 </para>
 
 <para>
-Then at umount time , in your put_super() (2.4) or write_super() (2.5)
-you can then call journal_destroy() to clean up your in-core journal object.
+Then at umount time , in your put_super() you can then call journal_destroy()
+to clean up your in-core journal object.
 </para>
 
 <para>

Documentation/filesystems/Locking

@@ -114,7 +114,6 @@ prototypes:
 	int (*drop_inode) (struct inode *);
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
-	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
 	int (*freeze_fs) (struct super_block *);
 	int (*unfreeze_fs) (struct super_block *);
@@ -136,7 +135,6 @@ write_inode:
 drop_inode:				!!!inode->i_lock!!!
 evict_inode:
 put_super:		write
-write_super:		read
 sync_fs:		read
 freeze_fs:		write
 unfreeze_fs:		write

Documentation/filesystems/porting

@@ -94,9 +94,8 @@ protected.
 ---
 [mandatory]
 
-BKL is also moved from around sb operations.  ->write_super() Is now called 
-without BKL held.  BKL should have been shifted into individual fs sb_op
-functions.  If you don't need it, remove it.  
+BKL is also moved from around sb operations. BKL should have been shifted into
+individual fs sb_op functions.  If you don't need it, remove it.
 
 ---
 [informational]

Documentation/filesystems/vfs.txt

@@ -216,7 +216,6 @@ struct super_operations {
         void (*drop_inode) (struct inode *);
         void (*delete_inode) (struct inode *);
         void (*put_super) (struct super_block *);
-        void (*write_super) (struct super_block *);
         int (*sync_fs)(struct super_block *sb, int wait);
         int (*freeze_fs) (struct super_block *);
         int (*unfreeze_fs) (struct super_block *);
@@ -273,9 +272,6 @@ or bottom half).
   put_super: called when the VFS wishes to free the superblock
 	(i.e. unmount). This is called with the superblock lock held
 
-  write_super: called when the VFS superblock needs to be written to
-	disc. This method is optional
-
   sync_fs: called when VFS is writing out all dirty data associated with
   	a superblock. The second parameter indicates whether the method
 	should wait until the write out has been completed. Optional.

Documentation/laptops/laptop-mode.txt

@@ -262,9 +262,9 @@ MINIMUM_BATTERY_MINUTES=10
 
 #
 # Allowed dirty background ratio, in percent.  Once DIRTY_RATIO has been
-# exceeded, the kernel will wake pdflush which will then reduce the amount
-# of dirty memory to dirty_background_ratio.  Set this nice and low, so once
-# some writeout has commenced, we do a lot of it.
+# exceeded, the kernel will wake flusher threads which will then reduce the
+# amount of dirty memory to dirty_background_ratio.  Set this nice and low,
+# so once some writeout has commenced, we do a lot of it.
 #
 #DIRTY_BACKGROUND_RATIO=5
 
@@ -384,9 +384,9 @@ CPU_MAXFREQ=${CPU_MAXFREQ:-'slowest'}
 
 #
 # Allowed dirty background ratio, in percent.  Once DIRTY_RATIO has been
-# exceeded, the kernel will wake pdflush which will then reduce the amount
-# of dirty memory to dirty_background_ratio.  Set this nice and low, so once
-# some writeout has commenced, we do a lot of it.
+# exceeded, the kernel will wake flusher threads which will then reduce the
+# amount of dirty memory to dirty_background_ratio.  Set this nice and low,
+# so once some writeout has commenced, we do a lot of it.
 #
 DIRTY_BACKGROUND_RATIO=${DIRTY_BACKGROUND_RATIO:-'5'}
 

Documentation/sysctl/vm.txt

@@ -76,8 +76,8 @@ huge pages although processes will also directly compact memory as required.
 
 dirty_background_bytes
 
-Contains the amount of dirty memory at which the pdflush background writeback
-daemon will start writeback.
+Contains the amount of dirty memory at which the background kernel
+flusher threads will start writeback.
 
 Note: dirty_background_bytes is the counterpart of dirty_background_ratio. Only
 one of them may be specified at a time. When one sysctl is written it is
@@ -89,7 +89,7 @@ other appears as 0 when read.
 dirty_background_ratio
 
 Contains, as a percentage of total system memory, the number of pages at which
-the pdflush background writeback daemon will start writing out dirty data.
+the background kernel flusher threads will start writing out dirty data.
 
 ==============================================================
 
@@ -112,9 +112,9 @@ retained.
 dirty_expire_centisecs
 
 This tunable is used to define when dirty data is old enough to be eligible
-for writeout by the pdflush daemons.  It is expressed in 100'ths of a second.
-Data which has been dirty in-memory for longer than this interval will be
-written out next time a pdflush daemon wakes up.
+for writeout by the kernel flusher threads.  It is expressed in 100'ths
+of a second.  Data which has been dirty in-memory for longer than this
+interval will be written out next time a flusher thread wakes up.
 
 ==============================================================
 
@@ -128,7 +128,7 @@ data.
 
 dirty_writeback_centisecs
 
-The pdflush writeback daemons will periodically wake up and write `old' data
+The kernel flusher threads will periodically wake up and write `old' data
 out to disk.  This tunable expresses the interval between those wakeups, in
 100'ths of a second.
 

drivers/block/drbd/drbd_main.c

@@ -3537,9 +3537,9 @@ static void drbd_cleanup(void)
 }
 
 /**
- * drbd_congested() - Callback for pdflush
+ * drbd_congested() - Callback for the flusher thread
  * @congested_data:	User data
- * @bdi_bits:		Bits pdflush is currently interested in
+ * @bdi_bits:		Bits the BDI flusher thread is currently interested in
  *
  * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested.
  */

fs/bio.c

@@ -1312,7 +1312,7 @@ EXPORT_SYMBOL(bio_copy_kern);
  * Note that this code is very hard to test under normal circumstances because
  * direct-io pins the pages with get_user_pages().  This makes
  * is_page_cache_freeable return false, and the VM will not clean the pages.
- * But other code (eg, pdflush) could clean the pages if they are mapped
+ * But other code (eg, flusher threads) could clean the pages if they are mapped
  * pagecache.
  *
  * Simply disabling the call to bio_set_pages_dirty() is a good way to test the

fs/btrfs/inode.c

@@ -324,7 +324,8 @@ static noinline int add_async_extent(struct async_cow *cow,
  * If this code finds it can't get good compression, it puts an
  * entry onto the work queue to write the uncompressed bytes.  This
  * makes sure that both compressed inodes and uncompressed inodes
- * are written in the same order that pdflush sent them down.
+ * are written in the same order that the flusher thread sent them
+ * down.
  */
 static noinline int compress_file_range(struct inode *inode,
 					struct page *locked_page,

fs/btrfs/ordered-data.c

@@ -596,7 +596,7 @@ void btrfs_start_ordered_extent(struct inode *inode,
 	/*
 	 * pages in the range can be dirty, clean or writeback.  We
 	 * start IO on any dirty ones so the wait doesn't stall waiting
-	 * for pdflush to find them
+	 * for the flusher thread to find them
 	 */
 	if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
 		filemap_fdatawrite_range(inode->i_mapping, start, end);

fs/btrfs/super.c

@@ -100,10 +100,6 @@ static void __save_error_info(struct btrfs_fs_info *fs_info)
 	fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
 }
 
-/* NOTE:
- *	We move write_super stuff at umount in order to avoid deadlock
- *	for umount hold all lock.
- */
 static void save_error_info(struct btrfs_fs_info *fs_info)
 {
 	__save_error_info(fs_info);

fs/btrfs/volumes.c

@@ -1744,10 +1744,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 
 	device->fs_devices = root->fs_info->fs_devices;
 
-	/*
-	 * we don't want write_supers to jump in here with our device
-	 * half setup
-	 */
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices);
 	list_add(&device->dev_alloc_list,

fs/ext3/inode.c

@@ -3459,14 +3459,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
  * inode out, but prune_icache isn't a user-visible syncing function.
  * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
  * we start and wait on commits.
- *
- * Is this efficient/effective?  Well, we're being nice to the system
- * by cleaning up our inodes proactively so they can be reaped
- * without I/O.  But we are potentially leaving up to five seconds'
- * worth of inodes floating about which prune_icache wants us to
- * write out.  One way to fix that would be to get prune_icache()
- * to do a write_super() to free up some memory.  It has the desired
- * effect.
  */
 int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode)
 {

fs/ext3/super.c

@@ -64,11 +64,6 @@ static int ext3_freeze(struct super_block *sb);
 
 /*
  * Wrappers for journal_start/end.
- *
- * The only special thing we need to do here is to make sure that all
- * journal_end calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
  */
 handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
 {
@@ -90,12 +85,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
 	return journal_start(journal, nblocks);
 }
 
-/*
- * The only special thing we need to do here is to make sure that all
- * journal_stop calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- */
 int __ext3_journal_stop(const char *where, handle_t *handle)
 {
 	struct super_block *sb;

fs/ext4/inode.c

@@ -1970,7 +1970,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
  * This function can get called via...
  *   - ext4_da_writepages after taking page lock (have journal handle)
  *   - journal_submit_inode_data_buffers (no journal handle)
- *   - shrink_page_list via pdflush (no journal handle)
+ *   - shrink_page_list via the kswapd/direct reclaim (no journal handle)
  *   - grab_page_cache when doing write_begin (have journal handle)
  *
  * We don't do any block allocation in this function. If we have page with
@@ -4589,14 +4589,6 @@ static int ext4_expand_extra_isize(struct inode *inode,
  * inode out, but prune_icache isn't a user-visible syncing function.
  * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
  * we start and wait on commits.
- *
- * Is this efficient/effective?  Well, we're being nice to the system
- * by cleaning up our inodes proactively so they can be reaped
- * without I/O.  But we are potentially leaving up to five seconds'
- * worth of inodes floating about which prune_icache wants us to
- * write out.  One way to fix that would be to get prune_icache()
- * to do a write_super() to free up some memory.  It has the desired
- * effect.
  */
 int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 {

fs/ext4/super.c

@@ -326,11 +326,6 @@ static void ext4_put_nojournal(handle_t *handle)
 
 /*
  * Wrappers for jbd2_journal_start/end.
- *
- * The only special thing we need to do here is to make sure that all
- * journal_end calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
  */
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 {
@@ -356,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 	return jbd2_journal_start(journal, nblocks);
 }
 
-/*
- * The only special thing we need to do here is to make sure that all
- * jbd2_journal_stop calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- */
 int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
 {
 	struct super_block *sb;

fs/gfs2/meta_io.c

@@ -52,7 +52,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 		/*
 		 * If it's a fully non-blocking write attempt and we cannot
 		 * lock the buffer then redirty the page.  Note that this can
-		 * potentially cause a busy-wait loop from pdflush and kswapd
+		 * potentially cause a busy-wait loop from flusher thread and kswapd
 		 * activity, but those code paths have their own higher-level
 		 * throttling.
 		 */

fs/hfs/mdb.c

@@ -236,10 +236,10 @@ out:
  * hfs_mdb_commit()
  *
  * Description:
- *   This updates the MDB on disk (look also at hfs_write_super()).
+ *   This updates the MDB on disk.
  *   It does not check, if the superblock has been modified, or
  *   if the filesystem has been mounted read-only. It is mainly
- *   called by hfs_write_super() and hfs_btree_extend().
+ *   called by hfs_sync_fs() and flush_mdb().
  * Input Variable(s):
  *   struct hfs_mdb *mdb: Pointer to the hfs MDB
  *   int backup;

fs/jbd/journal.c

@@ -534,8 +534,8 @@ int journal_start_commit(journal_t *journal, tid_t *ptid)
 		ret = 1;
 	} else if (journal->j_committing_transaction) {
 		/*
-		 * If ext3_write_super() recently started a commit, then we
-		 * have to wait for completion of that transaction
+		 * If commit has been started, then we have to wait for
+		 * completion of that transaction.
 		 */
 		if (ptid)
 			*ptid = journal->j_committing_transaction->t_tid;

fs/jbd2/journal.c

@@ -612,8 +612,8 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
 		ret = 1;
 	} else if (journal->j_committing_transaction) {
 		/*
-		 * If ext3_write_super() recently started a commit, then we
-		 * have to wait for completion of that transaction
+		 * If commit has been started, then we have to wait for
+		 * completion of that transaction.
 		 */
 		if (ptid)
 			*ptid = journal->j_committing_transaction->t_tid;