ext3: crossport ext3 sb_lock changes

index 427496c..bed624c 100644
@@ -1974,14 +1974,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	}
 
 	ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
-	/*
-	 * akpm: core read_super() calls in here with the superblock locked.
-	 * That deadlocks, because orphan cleanup needs to lock the superblock
-	 * in numerous places.  Here we just pop the lock - it's relatively
-	 * harmless, because we are now ready to accept write_super() requests,
-	 * and aviro says that's the only reason for hanging onto the
-	 * superblock lock.
-	 */
+
 	EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
 	ext3_orphan_cleanup(sb, es);
 	EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS;

index bed624c..602b308 100644
@@ -2352,13 +2352,11 @@ static void ext3_mark_recovery_complete(struct super_block * sb,
 	if (journal_flush(journal) < 0)
 		goto out;
 
-	lock_super(sb);
 	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
 	    sb->s_flags & MS_RDONLY) {
 		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
 		ext3_commit_super(sb, es, 1);
 	}
-	unlock_super(sb);
 
 out:
 	journal_unlock_updates(journal);

@@ -2550,13 +2548,7 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 			    (sbi->s_mount_state & EXT3_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			/*
-			 * We have to unlock super so that we can wait for
-			 * transactions.
-			 */
-			unlock_super(sb);
 			ext3_mark_recovery_complete(sb, es);
-			lock_super(sb);
 		} else {
 			__le32 ret;
 			if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb,

index aad6400..76d4c58 100644
@@ -1920,7 +1920,7 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
 	struct ext3_iloc iloc;
 	int err = 0, rc;
 
-	lock_super(sb);
+	mutex_lock(&EXT3_SB(sb)->s_orphan_lock);
 	if (!list_empty(&EXT3_I(inode)->i_orphan))
 		goto out_unlock;
 

@@ -1929,9 +1929,13 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
 
 	/* @@@ FIXME: Observation from aviro:
 	 * I think I can trigger J_ASSERT in ext3_orphan_add().  We block
-	 * here (on lock_super()), so race with ext3_link() which might bump
+	 * here (on s_orphan_lock), so race with ext3_link() which might bump
 	 * ->i_nlink. For, say it, character device. Not a regular file,
 	 * not a directory, not a symlink and ->i_nlink > 0.
+	 *
+	 * tytso, 4/25/2009: I'm not sure how that could happen;
+	 * shouldn't the fs core protect us from these sort of
+	 * unlink()/link() races?
 	 */
 	J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);

@@ -1968,7 +1972,7 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
 out_unlock:
-	unlock_super(sb);
+	mutex_unlock(&EXT3_SB(sb)->s_orphan_lock);
 	ext3_std_error(inode->i_sb, err);
 	return err;
 }

@@ -1986,11 +1990,9 @@ int ext3_orphan_del(handle_t *handle, struct inode *inode)
 	struct ext3_iloc iloc;
 	int err = 0;
 
-	lock_super(inode->i_sb);
-	if (list_empty(&ei->i_orphan)) {
-		unlock_super(inode->i_sb);
-		return 0;
-	}
+	mutex_lock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
+	if (list_empty(&ei->i_orphan))
+		goto out;
 
 	ino_next = NEXT_ORPHAN(inode);
 	prev = ei->i_orphan.prev;

@@ -2040,7 +2042,7 @@ int ext3_orphan_del(handle_t *handle, struct inode *inode)
 out_err:
 	ext3_std_error(inode->i_sb, err);
 out:
-	unlock_super(inode->i_sb);
+	mutex_unlock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
 	return err;
 
 out_brelse:

index 602b308..534557c 100644
@@ -1890,6 +1890,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	sb->dq_op = &ext3_quota_operations;
 #endif
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+	mutex_init(&sbi->s_orphan_lock);
 
 	sb->s_root = NULL;
 

index f07f34d..dd61d83 100644
@@ -72,6 +72,7 @@ struct ext3_sb_info {
 	struct inode * s_journal_inode;
 	struct journal_s * s_journal;
 	struct list_head s_orphan;
+	struct mutex s_orphan_lock;
 	unsigned long s_commit_interval;
 	struct block_device *journal_bdev;
 #ifdef CONFIG_JBD_DEBUG

index 8359e7b..57a5bc9 100644
@@ -209,7 +209,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		err = -EBUSY;
 		goto exit_journal;

@@ -324,7 +324,7 @@ exit_bh:
 	brelse(bh);
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext3_journal_stop(handle)) && !err)
 		err = err2;
 

@@ -662,11 +662,12 @@ exit_free:
  * important part is that the new block and inode counts are in the backup
  * superblocks, and the location of the new group metadata in the GDT backups.
  *
- * We do not need lock_super() for this, because these blocks are not
- * otherwise touched by the filesystem code when it is mounted.  We don't
- * need to worry about last changing from sbi->s_groups_count, because the
- * worst that can happen is that we do not copy the full number of backups
- * at this time.  The resize which changed s_groups_count will backup again.
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted.  We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time.  The resize
+ * which changed s_groups_count will backup again.
  */
 static void update_backups(struct super_block *sb,
 			   int blk_off, char *data, int size)

@@ -825,7 +826,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		ext3_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");

@@ -856,7 +857,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 	/*
 	 * OK, now we've set up the new group.  Time to make it active.
 	 *
-	 * Current kernels don't lock all allocations via lock_super(),
+	 * We do not lock all allocations via s_resize_lock
 	 * so we have to be safe wrt. concurrent accesses the group
 	 * data.  So we need to be careful to set all of the relevant
 	 * group descriptor data etc. *before* we enable the group.

@@ -900,12 +901,12 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 	 *
 	 * The precise rules we use are:
 	 *
-	 * * Writers of s_groups_count *must* hold lock_super
+	 * * Writers of s_groups_count *must* hold s_resize_lock
 	 * AND
 	 * * Writers must perform a smp_wmb() after updating all dependent
 	 *   data and before modifying the groups count
 	 *
-	 * * Readers must hold lock_super() over the access
+	 * * Readers must hold s_resize_lock over the access
 	 * OR
 	 * * Readers must perform an smp_rmb() after reading the groups count
 	 *   and before reading any dependent data.

@@ -936,7 +937,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 	ext3_journal_dirty_metadata(handle, sbi->s_sbh);
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext3_journal_stop(handle)) && !err)
 		err = err2;
 	if (!err) {

@@ -973,7 +974,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after
-	 * taking lock_super() below. */
+	 * taking the s_resize_lock below. */
 	o_blocks_count = le32_to_cpu(es->s_blocks_count);
 	o_groups_count = EXT3_SB(sb)->s_groups_count;
 

@@ -1045,11 +1046,11 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&EXT3_SB(sb)->s_resize_lock);
 	if (o_blocks_count != le32_to_cpu(es->s_blocks_count)) {
 		ext3_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
-		unlock_super(sb);
+		mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
 		ext3_journal_stop(handle);
 		err = -EBUSY;
 		goto exit_put;

@@ -1059,13 +1060,13 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 						 EXT3_SB(sb)->s_sbh))) {
 		ext3_warning(sb, __func__,
 			     "error %d on journal write access", err);
-		unlock_super(sb);
+		mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
 		ext3_journal_stop(handle);
 		goto exit_put;
 	}
 	es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
 	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
-	unlock_super(sb);
+	mutex_unlock(&EXT3_SB(sb)->s_resize_lock);
 	ext3_debug("freeing blocks %lu through "E3FSBLK"\n", o_blocks_count,
 		   o_blocks_count + add);
 	ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);

index 534557c..53d3c53 100644
@@ -1891,6 +1891,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 #endif
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
+	mutex_init(&sbi->s_resize_lock);
 
 	sb->s_root = NULL;
 

index dd61d83..258088a 100644
@@ -73,6 +73,7 @@ struct ext3_sb_info {
 	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_JBD_DEBUG