[PATCH 0/6] hfs: stop using write_supers and s_dirt

[PATCH 0/6] hfs: stop using write_supers and s_dirt

[Artem Bityutskiy]

This patch-set makes HFS file-system stop using the VFS '->write_supers()'
call-back and the '->s_dirt' superblock field because I plan to remove them
once all users are gone.

Like the other similar patch-sets, we switch to a delayed job for writing out
the superblock instead of using the 's_dirt' flag. Additionally, this patch-set
includes several clean-ups.

Reminder:

The goal is to get rid of the 'sync_supers()' kernel thread. This kernel thread
wakes up every 5 seconds (by default) and calls '->write_super()' for all
mounted file-systems. And the bad thing is that this is done even if all the
superblocks are clean. Moreover, many file-systems do not even need this end
they do not register the '->write_super()' method at all (e.g., btrfs).

So 'sync_supers()' most often just generates useless wake-ups and wastes power.
I am trying to make all file-systems independent of '->write_super()' and plan
to remove 'sync_supers()' and '->write_super()' completely once there are no
more users.

Al, in the past I was trying to upstream patches which optimized 'sync_super()',
but you wanted me to kill it completely instead, which I am trying to do
now, see http://lkml.org/lkml/2010/7/22/96

Tested using the fsstress test from the LTP project.

======
Overall status:

1. ext4: patches submitted, waiting for review from Ted Ts'o:
   https://lkml.org/lkml/2012/4/2/111
2. udf: patch submitted, should be in Jan Kara's tree:
   https://lkml.org/lkml/2012/6/4/233
3  exofs: patch submitted, not sure if it will go to the exofs tree:
   https://lkml.org/lkml/2012/6/4/211
4. affs: patches submitted, should be in Al Viro's tree:
   https://lkml.org/lkml/2012/6/6/400
4. ext2:     done, see commit f72cf5e223a28d3b3ea7dc9e40464fd534e359e8
5. vfat:     done, see commit 78491189ddb6d84d4a4abae992ed891a236d0263
6. jffs2:    done, see commit 208b14e507c00ff7f108e1a388dd3d8cc805a443
7. reiserfs: done, see commit 033369d1af1264abc23bea2e174aa47cdd212f6f

TODO: hfsplus, sysv, ufs
======

 fs/hfs/extent.c |    2 +-
 fs/hfs/hfs_fs.h |   15 +++++++----
 fs/hfs/inode.c  |   14 +++-------
 fs/hfs/mdb.c    |   15 +++++++++++
 fs/hfs/super.c  |   73 +++++++++++++++++++++++++++----------------------------
 5 files changed, 65 insertions(+), 54 deletions(-)

Thanks,
Artem.

[PATCH 1/6] hfs: push lock_super down

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

HFS uses 'lock_super()'/'unlock_super()' around 'hfs_mdb_commit()' in order
to serialize MDB (Master Directory Block) changes. Push it down to
'hfs_mdb_commit()' in order to simplify the code a bit.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/inode.c |    2 --
 fs/hfs/mdb.c   |    2 ++
 fs/hfs/super.c |    4 ----
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 761ec06..daf3d63 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -645,11 +645,9 @@ 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);
 	}
 	/* .. finally sync the buffers to disk */
 	err = sync_blockdev(sb->s_bdev);
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 1563d5c..3f558d58 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -260,6 +260,7 @@ void hfs_mdb_commit(struct super_block *sb)
 {
 	struct hfs_mdb *mdb = HFS_SB(sb)->mdb;
 
+	lock_super(sb);
 	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();
@@ -317,6 +318,7 @@ void hfs_mdb_commit(struct super_block *sb)
 			size -= len;
 		}
 	}
+	unlock_super(sb);
 }
 
 void hfs_mdb_close(struct super_block *sb)
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 7b4c537..f7c06bb 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -50,21 +50,17 @@ MODULE_LICENSE("GPL");
  */
 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;
 }
-- 
1.7.7.6

[PATCH 2/6] hfs: get rid of lock_super

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

Stop using lock_super for serializing the MDB changes - use the buffer-head own
lock instead. Tested with fsstress.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/mdb.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 3f558d58..7a32240 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -260,7 +260,7 @@ void hfs_mdb_commit(struct super_block *sb)
 {
 	struct hfs_mdb *mdb = HFS_SB(sb)->mdb;
 
-	lock_super(sb);
+	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();
@@ -284,9 +284,13 @@ 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);
 	}
@@ -309,7 +313,11 @@ 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++;
@@ -318,7 +326,7 @@ void hfs_mdb_commit(struct super_block *sb)
 			size -= len;
 		}
 	}
-	unlock_super(sb);
+	unlock_buffer(HFS_SB(sb)->mdb_bh);
 }
 
 void hfs_mdb_close(struct super_block *sb)
-- 
1.7.7.6

[PATCH 3/6] hfs: remove extra mdb write on unmount

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

HFS calls 'hfs_write_super()' from 'hfs_put_super()' in order to write the MDB
to the media. However, it is not needed because VFS calls '->sync_fs()' before
calling '->put_super()' - so by the time we are in 'hfs_write_super()', the MDB
is already synchronized.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/super.c |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index f7c06bb..47e4119 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -74,8 +74,6 @@ 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);
 	hfs_mdb_close(sb);
 	/* release the MDB's resources */
 	hfs_mdb_put(sb);
-- 
1.7.7.6

[PATCH 4/6] hfs: simplify a bit checking for R/O

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

We have the following pattern in 2 places in HFS

if (!RDONLY)
	hfs_mdb_commit();

This patch pushes the RDONLY check down to 'hfs_mdb_commit()'. This will
make the following patches a bit simpler.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/inode.c |    3 +--
 fs/hfs/mdb.c   |    3 +++
 fs/hfs/super.c |    3 +--
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index daf3d63..629eba4 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -646,8 +646,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	sb = inode->i_sb;
 	if (sb->s_dirt) {
 		sb->s_dirt = 0;
-		if (!(sb->s_flags & MS_RDONLY))
-			hfs_mdb_commit(sb);
+		hfs_mdb_commit(sb);
 	}
 	/* .. finally sync the buffers to disk */
 	err = sync_blockdev(sb->s_bdev);
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 7a32240..5fd51a5 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -260,6 +260,9 @@ 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 */
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 47e4119..0730135 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -53,8 +53,7 @@ static void hfs_write_super(struct super_block *sb)
 	sb->s_dirt = 0;
 
 	/* sync everything to the buffers */
-	if (!(sb->s_flags & MS_RDONLY))
-		hfs_mdb_commit(sb);
+	hfs_mdb_commit(sb);
 }
 
 static int hfs_sync_fs(struct super_block *sb, int wait)
-- 
1.7.7.6

[PATCH 5/6] hfs: introduce VFS superblock object back-reference

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

Add an 'sb' VFS superblock back-reference to the 'struct hfs_sb_info' data
structure - we will need to find the VFS superblock from a
'struct hfs_sb_info' object in the next patch, so this change is jut a
preparation.

Remove few useless newlines while on it.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/hfs_fs.h |    6 +-----
 fs/hfs/super.c  |    1 +
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 1bf967c..3515612 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -137,16 +137,12 @@ 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;
 };
 
 #define HFS_FLG_BITMAP_DIRTY	0
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 0730135..99c6239 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -380,6 +380,7 @@ 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;
 
 	res = -EINVAL;
-- 
1.7.7.6

[PATCH 6/6] hfs: get rid of hfs_sync_super

[Artem Bityutskiy]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

This patch makes hfs stop using the VFS '->write_super()' method along with
the 's_dirt' superblock flag, because they are on their way out.

The whole "superblock write-out" VFS infrastructure is served by the
'sync_supers()' kernel thread, which wakes up every 5 (by default) seconds and
writes out all dirty superblocks using the '->write_super()' call-back.  But the
problem with this thread is that it wastes power by waking up the system every
5 seconds, even if there are no diry superblocks, or there are no client
file-systems which would need this (e.g., btrfs does not use
'->write_super()'). So we want to kill it completely and thus, we need to make
file-systems to stop using the '->write_super()' VFS service, and then remove
it together with the kernel thread.

Tested using fsstress from the LTP project.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/extent.c |    2 +-
 fs/hfs/hfs_fs.h |    9 ++++++-
 fs/hfs/inode.c  |   11 +++------
 fs/hfs/mdb.c    |    2 +
 fs/hfs/super.c  |   65 +++++++++++++++++++++++++++++-------------------------
 5 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index 2c16316..a67955a 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 3515612..8275175 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>
@@ -143,6 +144,9 @@ struct hfs_sb_info {
 	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
@@ -222,6 +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;
 
 /*
@@ -249,7 +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 629eba4..cb78138 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,
@@ -644,10 +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) {
-		sb->s_dirt = 0;
-		hfs_mdb_commit(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 5fd51a5..a5cd355 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -263,6 +263,8 @@ void hfs_mdb_commit(struct super_block *sb)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
+	cancel_delayed_work(&HFS_SB(sb)->mdb_work);
+
 	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 */
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 99c6239..14528ee 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -29,38 +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)
-{
-	sb->s_dirt = 0;
-
-	/* sync everything to the buffers */
-	hfs_mdb_commit(sb);
-}
-
 static int hfs_sync_fs(struct super_block *sb, int wait)
 {
 	hfs_mdb_commit(sb);
-	sb->s_dirt = 0;
-
 	return 0;
 }
 
@@ -73,11 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait)
  */
 static void hfs_put_super(struct super_block *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()
  *
@@ -177,7 +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,
@@ -382,6 +385,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	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)) {
-- 
1.7.7.6

Re: [PATCH 6/6] hfs: get rid of hfs_sync_super

[Artem Bityutskiy]

[-- Attachment #1: Type: text/plain, Size: 8165 bytes --]

From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Tue, 12 Jun 2012 10:40:56 +0300
Subject: [PATCH 19/23] hfs: get rid of hfs_sync_super

This patch makes hfs stop using the VFS '->write_super()' method along with
the 's_dirt' superblock flag, because they are on their way out.

The whole "superblock write-out" VFS infrastructure is served by the
'sync_supers()' kernel thread, which wakes up every 5 (by default) seconds and
writes out all dirty superblocks using the '->write_super()' call-back.  But the
problem with this thread is that it wastes power by waking up the system every
5 seconds, even if there are no diry superblocks, or there are no client
file-systems which would need this (e.g., btrfs does not use
'->write_super()'). So we want to kill it completely and thus, we need to make
file-systems to stop using the '->write_super()' VFS service, and then remove
it together with the kernel thread.

Tested using fsstress from the LTP project.

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 fs/hfs/extent.c |    2 +-
 fs/hfs/hfs_fs.h |    9 +++++++-
 fs/hfs/inode.c  |   11 ++++------
 fs/hfs/mdb.c    |    2 ++
 fs/hfs/super.c  |   65 ++++++++++++++++++++++++++++++-------------------------
 5 files changed, 50 insertions(+), 39 deletions(-)

|This is patch is the same except that it fixes several white-space
|issues. If you prefer an incremental patch, please, let me know. The
|issues are:
|
|WARNING:SUSPECT_CODE_INDENT: suspect code indent for conditional statements (8, 15)
|#213: FILE: fs/hfs/super.c:73:
|+       if (sb->s_flags & MS_RDONLY)
|+              return;
|
|WARNING:SUSPECT_CODE_INDENT: suspect code indent for conditional statements (8, 15)
|#217: FILE: fs/hfs/super.c:77:
|+       if (!sbi->work_queued) {
|+              delay = msecs_to_jiffies(dirty_writeback_interval * 10);

diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index 2c16316..a67955a 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 3515612..8275175 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>
@@ -143,6 +144,9 @@ struct hfs_sb_info {
 	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
@@ -222,6 +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;
 
 /*
@@ -249,7 +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 629eba4..cb78138 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,
@@ -644,10 +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) {
-		sb->s_dirt = 0;
-		hfs_mdb_commit(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 5fd51a5..a5cd355 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -263,6 +263,8 @@ void hfs_mdb_commit(struct super_block *sb)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
+	cancel_delayed_work(&HFS_SB(sb)->mdb_work);
+
 	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 */
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 99c6239..14528ee 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -29,38 +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)
-{
-	sb->s_dirt = 0;
-
-	/* sync everything to the buffers */
-	hfs_mdb_commit(sb);
-}
-
 static int hfs_sync_fs(struct super_block *sb, int wait)
 {
 	hfs_mdb_commit(sb);
-	sb->s_dirt = 0;
-
 	return 0;
 }
 
@@ -73,11 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait)
  */
 static void hfs_put_super(struct super_block *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()
  *
@@ -177,7 +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,
@@ -382,6 +385,8 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	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)) {
-- 
1.7.10

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]