Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6:
  quota: Improve checking of quota file header
  jbd: jbd-debug and jbd2-debug should be writable
  ext4: fix sleep inside spinlock issue with quota and dealloc (#14739)
  ext4: Fix potential quota deadlock
  quota: Fix 64-bit limits setting on 32-bit archs
  ext3: Replace lock/unlock_super() with an explicit lock for resizing
  ext3: Replace lock/unlock_super() with an explicit lock for the orphan list
  ext3: ext3_mark_recovery_complete() doesn't need to use lock_super
  ext3: Remove outdated comment about lock_super()
  quota: Move duplicated code to separate functions
  ext4: Convert to generic reserved quota's space management.
  quota: decouple fs reserved space from quota reservation
  Add unlocked version of inode_add_bytes() function
  ext3: quota macros cleanup [V2]

fs/ext3/inode.c

@@ -970,7 +970,7 @@ static int ext3_get_block(struct inode *inode, sector_t iblock,
 		if (max_blocks > DIO_MAX_BLOCKS)
 			max_blocks = DIO_MAX_BLOCKS;
 		handle = ext3_journal_start(inode, DIO_CREDITS +
-				2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb));
+				EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
 			goto out;
@@ -3146,8 +3146,8 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr)
 
 		/* (user+group)*(old+new) structure, inode write (sb,
 		 * inode block, ? - but truncate inode update has it) */
-		handle = ext3_journal_start(inode, 2*(EXT3_QUOTA_INIT_BLOCKS(inode->i_sb)+
-					EXT3_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+		handle = ext3_journal_start(inode, EXT3_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+					EXT3_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)+3);
 		if (IS_ERR(handle)) {
 			error = PTR_ERR(handle);
 			goto err_out;
@@ -3239,7 +3239,7 @@ static int ext3_writepage_trans_blocks(struct inode *inode)
 #ifdef CONFIG_QUOTA
 	/* We know that structure was already allocated during vfs_dq_init so
 	 * we will be updating only the data blocks + inodes */
-	ret += 2*EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb);
+	ret += EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
 #endif
 
 	return ret;

fs/ext3/namei.c

@@ -1699,7 +1699,7 @@ static int ext3_create (struct inode * dir, struct dentry * dentry, int mode,
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -1733,7 +1733,7 @@ static int ext3_mknod (struct inode * dir, struct dentry *dentry,
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -1769,7 +1769,7 @@ static int ext3_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -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:
@@ -2175,7 +2177,7 @@ static int ext3_symlink (struct inode * dir,
 retry:
 	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 5 +
-					2*EXT3_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 

fs/ext3/resize.c

@@ -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 @@ static int setup_new_group_blocks(struct super_block *sb,
 	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 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
  * 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);

fs/ext3/super.c

@@ -1928,6 +1928,8 @@ 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);
+	mutex_init(&sbi->s_resize_lock);
 
 	sb->s_root = NULL;
 
@@ -2014,14 +2016,7 @@ 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;
@@ -2403,13 +2398,11 @@ 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);
@@ -2601,13 +2594,7 @@ 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,

fs/ext4/ext4.h

@@ -704,6 +704,10 @@ struct ext4_inode_info {
 	__u16 i_extra_isize;
 
 	spinlock_t i_block_reservation_lock;
+#ifdef CONFIG_QUOTA
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
 
 	/* completed async DIOs that might need unwritten extents handling */
 	struct list_head i_aio_dio_complete_list;
@@ -1435,7 +1439,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
-extern qsize_t ext4_get_reserved_space(struct inode *inode);
+extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int flush_aio_dio_completed_IO(struct inode *inode);
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);

fs/ext4/inode.c

@@ -1003,17 +1003,12 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	return err;
 }
 
-qsize_t ext4_get_reserved_space(struct inode *inode)
+#ifdef CONFIG_QUOTA
+qsize_t *ext4_get_reserved_space(struct inode *inode)
 {
-	unsigned long long total;
-
-	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-	total = EXT4_I(inode)->i_reserved_data_blocks +
-		EXT4_I(inode)->i_reserved_meta_blocks;
-	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-
-	return (total << inode->i_blkbits);
+	return &EXT4_I(inode)->i_reserved_quota;
 }
+#endif
 /*
  * Calculate the number of metadata blocks need to reserve
  * to allocate @blocks for non extent file based file
@@ -1051,7 +1046,7 @@ static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
 static void ext4_da_update_reserve_space(struct inode *inode, int used)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	int total, mdb, mdb_free;
+	int total, mdb, mdb_free, mdb_claim = 0;
 
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 	/* recalculate the number of metablocks still need to be reserved */
@@ -1064,7 +1059,9 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 
 	if (mdb_free) {
 		/* Account for allocated meta_blocks */
-		mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+		mdb_claim = EXT4_I(inode)->i_allocated_meta_blocks;
+		BUG_ON(mdb_free < mdb_claim);
+		mdb_free -= mdb_claim;
 
 		/* update fs dirty blocks counter */
 		percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
@@ -1075,8 +1072,11 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 	/* update per-inode reservations */
 	BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
 	EXT4_I(inode)->i_reserved_data_blocks -= used;
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter, used + mdb_claim);
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
+	vfs_dq_claim_block(inode, used + mdb_claim);
+
 	/*
 	 * free those over-booking quota for metadata blocks
 	 */
@@ -1816,19 +1816,17 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 
 	md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
 	total = md_needed + nrblocks;
+	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
 	/*
 	 * Make quota reservation here to prevent quota overflow
 	 * later. Real quota accounting is done at pages writeout
 	 * time.
 	 */
-	if (vfs_dq_reserve_block(inode, total)) {
-		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+	if (vfs_dq_reserve_block(inode, total))
 		return -EDQUOT;
-	}
 
 	if (ext4_claim_free_blocks(sbi, total)) {
-		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 		vfs_dq_release_reservation_block(inode, total);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
@@ -1836,10 +1834,11 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 		}
 		return -ENOSPC;
 	}
+	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 	EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
-	EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
-
+	EXT4_I(inode)->i_reserved_meta_blocks += md_needed;
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+
 	return 0;       /* success */
 }
 
@@ -4794,6 +4793,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 			((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
 	inode->i_size = ext4_isize(raw_inode);
 	ei->i_disksize = inode->i_size;
+#ifdef CONFIG_QUOTA
+	ei->i_reserved_quota = 0;
+#endif
 	inode->i_generation = le32_to_cpu(raw_inode->i_generation);
 	ei->i_block_group = iloc.block_group;
 	ei->i_last_alloc_group = ~0;

fs/ext4/mballoc.c

@@ -2755,12 +2755,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
 		/* release all the reserved blocks if non delalloc */
 		percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
-	else {
-		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
-						ac->ac_b_ex.fe_len);
-		/* convert reserved quota blocks to real quota blocks */
-		vfs_dq_claim_block(ac->ac_inode, ac->ac_b_ex.fe_len);
-	}
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,

fs/ext4/super.c

@@ -704,6 +704,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_allocated_meta_blocks = 0;
 	ei->i_delalloc_reserved_flag = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
+#ifdef CONFIG_QUOTA
+	ei->i_reserved_quota = 0;
+#endif
 	INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
 	ei->cur_aio_dio = NULL;
 	ei->i_sync_tid = 0;
@@ -1014,7 +1017,9 @@ static const struct dquot_operations ext4_quota_operations = {
 	.reserve_space	= dquot_reserve_space,
 	.claim_space	= dquot_claim_space,
 	.release_rsv	= dquot_release_reserved_space,
+#ifdef CONFIG_QUOTA
 	.get_reserved_space = ext4_get_reserved_space,
+#endif
 	.alloc_inode	= dquot_alloc_inode,
 	.free_space	= dquot_free_space,
 	.free_inode	= dquot_free_inode,

fs/jbd/journal.c

@@ -1913,7 +1913,7 @@ static void __init jbd_create_debugfs_entry(void)
 {
 	jbd_debugfs_dir = debugfs_create_dir("jbd", NULL);
 	if (jbd_debugfs_dir)
-		jbd_debug = debugfs_create_u8("jbd-debug", S_IRUGO,
+		jbd_debug = debugfs_create_u8("jbd-debug", S_IRUGO | S_IWUSR,
 					       jbd_debugfs_dir,
 					       &journal_enable_debug);
 }

fs/jbd2/journal.c

@@ -2115,7 +2115,8 @@ static void __init jbd2_create_debugfs_entry(void)
 {
 	jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL);
 	if (jbd2_debugfs_dir)
-		jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME, S_IRUGO,
+		jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME,
+					       S_IRUGO | S_IWUSR,
 					       jbd2_debugfs_dir,
 					       &jbd2_journal_enable_debug);
 }

fs/quota/dquot.c

@@ -323,6 +323,30 @@ int dquot_mark_dquot_dirty(struct dquot *dquot)
 }
 EXPORT_SYMBOL(dquot_mark_dquot_dirty);
 
+/* Dirtify all the dquots - this can block when journalling */
+static inline int mark_all_dquot_dirty(struct dquot * const *dquot)
+{
+	int ret, err, cnt;
+
+	ret = err = 0;
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+		if (dquot[cnt])
+			/* Even in case of error we have to continue */
+			ret = mark_dquot_dirty(dquot[cnt]);
+		if (!err)
+			err = ret;
+	}
+	return err;
+}
+
+static inline void dqput_all(struct dquot **dquot)
+{
+	unsigned int cnt;
+
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
+		dqput(dquot[cnt]);
+}
+
 /* This function needs dq_list_lock */
 static inline int clear_dquot_dirty(struct dquot *dquot)
 {
@@ -1268,8 +1292,7 @@ int dquot_initialize(struct inode *inode, int type)
 out_err:
 	up_write(&sb_dqopt(sb)->dqptr_sem);
 	/* Drop unused references */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		dqput(got[cnt]);
+	dqput_all(got);
 	return ret;
 }
 EXPORT_SYMBOL(dquot_initialize);
@@ -1288,9 +1311,7 @@ int dquot_drop(struct inode *inode)
 		inode->i_dquot[cnt] = NULL;
 	}
 	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
-
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		dqput(put[cnt]);
+	dqput_all(put);
 	return 0;
 }
 EXPORT_SYMBOL(dquot_drop);
@@ -1318,6 +1339,67 @@ void vfs_dq_drop(struct inode *inode)
 }
 EXPORT_SYMBOL(vfs_dq_drop);
 
+/*
+ * inode_reserved_space is managed internally by quota, and protected by
+ * i_lock similar to i_blocks+i_bytes.
+ */
+static qsize_t *inode_reserved_space(struct inode * inode)
+{
+	/* Filesystem must explicitly define it's own method in order to use
+	 * quota reservation interface */
+	BUG_ON(!inode->i_sb->dq_op->get_reserved_space);
+	return inode->i_sb->dq_op->get_reserved_space(inode);
+}
+
+static void inode_add_rsv_space(struct inode *inode, qsize_t number)
+{
+	spin_lock(&inode->i_lock);
+	*inode_reserved_space(inode) += number;
+	spin_unlock(&inode->i_lock);
+}
+
+
+static void inode_claim_rsv_space(struct inode *inode, qsize_t number)
+{
+	spin_lock(&inode->i_lock);
+	*inode_reserved_space(inode) -= number;
+	__inode_add_bytes(inode, number);
+	spin_unlock(&inode->i_lock);
+}
+
+static void inode_sub_rsv_space(struct inode *inode, qsize_t number)
+{
+	spin_lock(&inode->i_lock);
+	*inode_reserved_space(inode) -= number;
+	spin_unlock(&inode->i_lock);
+}
+
+static qsize_t inode_get_rsv_space(struct inode *inode)
+{
+	qsize_t ret;
+	spin_lock(&inode->i_lock);
+	ret = *inode_reserved_space(inode);
+	spin_unlock(&inode->i_lock);
+	return ret;
+}
+
+static void inode_incr_space(struct inode *inode, qsize_t number,
+				int reserve)
+{
+	if (reserve)
+		inode_add_rsv_space(inode, number);
+	else
+		inode_add_bytes(inode, number);
+}
+
+static void inode_decr_space(struct inode *inode, qsize_t number, int reserve)
+{
+	if (reserve)
+		inode_sub_rsv_space(inode, number);
+	else
+		inode_sub_bytes(inode, number);
+}
+
 /*
  * Following four functions update i_blocks+i_bytes fields and
  * quota information (together with appropriate checks)
@@ -1336,6 +1418,21 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number,
 	int cnt, ret = QUOTA_OK;
 	char warntype[MAXQUOTAS];
 
+	/*
+	 * First test before acquiring mutex - solves deadlocks when we
+	 * re-enter the quota code and are already holding the mutex
+	 */
+	if (IS_NOQUOTA(inode)) {
+		inode_incr_space(inode, number, reserve);
+		goto out;
+	}
+
+	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	if (IS_NOQUOTA(inode)) {
+		inode_incr_space(inode, number, reserve);
+		goto out_unlock;
+	}
+
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
 		warntype[cnt] = QUOTA_NL_NOWARN;
 
@@ -1346,7 +1443,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number,
 		if (check_bdq(inode->i_dquot[cnt], number, warn, warntype+cnt)
 		    == NO_QUOTA) {
 			ret = NO_QUOTA;
-			goto out_unlock;
+			spin_unlock(&dq_data_lock);
+			goto out_flush_warn;
 		}
 	}
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
@@ -1357,64 +1455,29 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number,
 		else
 			dquot_incr_space(inode->i_dquot[cnt], number);
 	}
-	if (!reserve)
-		inode_add_bytes(inode, number);
-out_unlock:
+	inode_incr_space(inode, number, reserve);
 	spin_unlock(&dq_data_lock);
+
+	if (reserve)
+		goto out_flush_warn;
+	mark_all_dquot_dirty(inode->i_dquot);
+out_flush_warn:
 	flush_warnings(inode->i_dquot, warntype);
+out_unlock:
+	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+out:
 	return ret;
 }
 
 int dquot_alloc_space(struct inode *inode, qsize_t number, int warn)
 {
-	int cnt, ret = QUOTA_OK;
-
-	/*
-	 * First test before acquiring mutex - solves deadlocks when we
-	 * re-enter the quota code and are already holding the mutex
-	 */
-	if (IS_NOQUOTA(inode)) {
-		inode_add_bytes(inode, number);
-		goto out;
-	}
-
-	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-	if (IS_NOQUOTA(inode)) {
-		inode_add_bytes(inode, number);
-		goto out_unlock;
-	}
-
-	ret = __dquot_alloc_space(inode, number, warn, 0);
-	if (ret == NO_QUOTA)
-		goto out_unlock;
-
-	/* Dirtify all the dquots - this can block when journalling */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if (inode->i_dquot[cnt])
-			mark_dquot_dirty(inode->i_dquot[cnt]);
-out_unlock:
-	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-out:
-	return ret;
+	return __dquot_alloc_space(inode, number, warn, 0);
 }
 EXPORT_SYMBOL(dquot_alloc_space);
 
 int dquot_reserve_space(struct inode *inode, qsize_t number, int warn)
 {
-	int ret = QUOTA_OK;
-
-	if (IS_NOQUOTA(inode))
-		goto out;
-
-	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-	if (IS_NOQUOTA(inode))
-		goto out_unlock;
-
-	ret = __dquot_alloc_space(inode, number, warn, 1);
-out_unlock:
-	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-out:
-	return ret;
+	return __dquot_alloc_space(inode, number, warn, 1);
 }
 EXPORT_SYMBOL(dquot_reserve_space);
 
@@ -1455,10 +1518,7 @@ int dquot_alloc_inode(const struct inode *inode, qsize_t number)
 warn_put_all:
 	spin_unlock(&dq_data_lock);
 	if (ret == QUOTA_OK)
-		/* Dirtify all the dquots - this can block when journalling */
-		for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-			if (inode->i_dquot[cnt])
-				mark_dquot_dirty(inode->i_dquot[cnt]);
+		mark_all_dquot_dirty(inode->i_dquot);
 	flush_warnings(inode->i_dquot, warntype);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	return ret;
@@ -1471,14 +1531,14 @@ int dquot_claim_space(struct inode *inode, qsize_t number)
 	int ret = QUOTA_OK;
 
 	if (IS_NOQUOTA(inode)) {
-		inode_add_bytes(inode, number);
+		inode_claim_rsv_space(inode, number);
 		goto out;
 	}
 
 	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	if (IS_NOQUOTA(inode))	{
 		up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-		inode_add_bytes(inode, number);
+		inode_claim_rsv_space(inode, number);
 		goto out;
 	}
 
@@ -1490,51 +1550,19 @@ int dquot_claim_space(struct inode *inode, qsize_t number)
 							number);
 	}
 	/* Update inode bytes */
-	inode_add_bytes(inode, number);
+	inode_claim_rsv_space(inode, number);
 	spin_unlock(&dq_data_lock);
-	/* Dirtify all the dquots - this can block when journalling */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if (inode->i_dquot[cnt])
-			mark_dquot_dirty(inode->i_dquot[cnt]);
+	mark_all_dquot_dirty(inode->i_dquot);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 out:
 	return ret;
 }
 EXPORT_SYMBOL(dquot_claim_space);
 
-/*
- * Release reserved quota space
- */
-void dquot_release_reserved_space(struct inode *inode, qsize_t number)
-{
-	int cnt;
-
-	if (IS_NOQUOTA(inode))
-		goto out;
-
-	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-	if (IS_NOQUOTA(inode))
-		goto out_unlock;
-
-	spin_lock(&dq_data_lock);
-	/* Release reserved dquots */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (inode->i_dquot[cnt])
-			dquot_free_reserved_space(inode->i_dquot[cnt], number);
-	}
-	spin_unlock(&dq_data_lock);
-
-out_unlock:
-	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
-out:
-	return;
-}
-EXPORT_SYMBOL(dquot_release_reserved_space);
-
 /*
  * This operation can block, but only after everything is updated
  */
-int dquot_free_space(struct inode *inode, qsize_t number)
+int __dquot_free_space(struct inode *inode, qsize_t number, int reserve)
 {
 	unsigned int cnt;
 	char warntype[MAXQUOTAS];
@@ -1543,7 +1571,7 @@ int dquot_free_space(struct inode *inode, qsize_t number)
          * re-enter the quota code and are already holding the mutex */
 	if (IS_NOQUOTA(inode)) {
 out_sub:
-		inode_sub_bytes(inode, number);
+		inode_decr_space(inode, number, reserve);
 		return QUOTA_OK;
 	}
 
@@ -1558,20 +1586,39 @@ int dquot_free_space(struct inode *inode, qsize_t number)
 		if (!inode->i_dquot[cnt])
 			continue;
 		warntype[cnt] = info_bdq_free(inode->i_dquot[cnt], number);
-		dquot_decr_space(inode->i_dquot[cnt], number);
+		if (reserve)
+			dquot_free_reserved_space(inode->i_dquot[cnt], number);
+		else
+			dquot_decr_space(inode->i_dquot[cnt], number);
 	}
-	inode_sub_bytes(inode, number);
+	inode_decr_space(inode, number, reserve);
 	spin_unlock(&dq_data_lock);
-	/* Dirtify all the dquots - this can block when journalling */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if (inode->i_dquot[cnt])
-			mark_dquot_dirty(inode->i_dquot[cnt]);
+
+	if (reserve)
+		goto out_unlock;
+	mark_all_dquot_dirty(inode->i_dquot);
+out_unlock:
 	flush_warnings(inode->i_dquot, warntype);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	return QUOTA_OK;
 }
+
+int dquot_free_space(struct inode *inode, qsize_t number)
+{
+	return  __dquot_free_space(inode, number, 0);
+}
 EXPORT_SYMBOL(dquot_free_space);
 
+/*
+ * Release reserved quota space
+ */
+void dquot_release_reserved_space(struct inode *inode, qsize_t number)
+{
+	__dquot_free_space(inode, number, 1);
+
+}
+EXPORT_SYMBOL(dquot_release_reserved_space);
+
 /*
  * This operation can block, but only after everything is updated
  */
@@ -1599,29 +1646,13 @@ int dquot_free_inode(const struct inode *inode, qsize_t number)
 		dquot_decr_inodes(inode->i_dquot[cnt], number);
 	}
 	spin_unlock(&dq_data_lock);
-	/* Dirtify all the dquots - this can block when journalling */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if (inode->i_dquot[cnt])
-			mark_dquot_dirty(inode->i_dquot[cnt]);
+	mark_all_dquot_dirty(inode->i_dquot);
 	flush_warnings(inode->i_dquot, warntype);
 	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	return QUOTA_OK;
 }
 EXPORT_SYMBOL(dquot_free_inode);
 
-/*
- * call back function, get reserved quota space from underlying fs
- */
-qsize_t dquot_get_reserved_space(struct inode *inode)
-{
-	qsize_t reserved_space = 0;
-
-	if (sb_any_quota_active(inode->i_sb) &&
-	    inode->i_sb->dq_op->get_reserved_space)
-		reserved_space = inode->i_sb->dq_op->get_reserved_space(inode);
-	return reserved_space;
-}
-
 /*
  * Transfer the number of inode and blocks from one diskquota to an other.
  *
@@ -1665,7 +1696,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
 	}
 	spin_lock(&dq_data_lock);
 	cur_space = inode_get_bytes(inode);
-	rsv_space = dquot_get_reserved_space(inode);
+	rsv_space = inode_get_rsv_space(inode);
 	space = cur_space + rsv_space;
 	/* Build the transfer_from list and check the limits */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
@@ -1709,25 +1740,18 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
 	spin_unlock(&dq_data_lock);
 	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
 
-	/* Dirtify all the dquots - this can block when journalling */
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		if (transfer_from[cnt])
-			mark_dquot_dirty(transfer_from[cnt]);
-		if (transfer_to[cnt]) {
-			mark_dquot_dirty(transfer_to[cnt]);
-			/* The reference we got is transferred to the inode */
-			transfer_to[cnt] = NULL;
-		}
-	}
+	mark_all_dquot_dirty(transfer_from);
+	mark_all_dquot_dirty(transfer_to);
+	/* The reference we got is transferred to the inode */
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
+		transfer_to[cnt] = NULL;
 warn_put_all:
 	flush_warnings(transfer_to, warntype_to);
 	flush_warnings(transfer_from, warntype_from_inodes);
 	flush_warnings(transfer_from, warntype_from_space);
 put_all:
-	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
-		dqput(transfer_from[cnt]);
-		dqput(transfer_to[cnt]);
-	}
+	dqput_all(transfer_from);
+	dqput_all(transfer_to);
 	return ret;
 over_quota:
 	spin_unlock(&dq_data_lock);

fs/quota/quota_v2.c

@@ -97,8 +97,11 @@ static int v2_read_file_info(struct super_block *sb, int type)
 	unsigned int version;
 
 	if (!v2_read_header(sb, type, &dqhead))
-		return 0;
+		return -1;
 	version = le32_to_cpu(dqhead.dqh_version);
+	if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) ||
+	    (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1))
+		return -1;
 
 	size = sb->s_op->quota_read(sb, type, (char *)&dinfo,
 	       sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
@@ -120,8 +123,8 @@ static int v2_read_file_info(struct super_block *sb, int type)
 		info->dqi_maxilimit = 0xffffffff;
 	} else {
 		/* used space is stored as unsigned 64-bit value */
-		info->dqi_maxblimit = 0xffffffffffffffff;	/* 2^64-1 */
-		info->dqi_maxilimit = 0xffffffffffffffff;
+		info->dqi_maxblimit = 0xffffffffffffffffULL;	/* 2^64-1 */
+		info->dqi_maxilimit = 0xffffffffffffffffULL;
 	}
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);

fs/stat.c

@@ -401,9 +401,9 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 */
 
-void inode_add_bytes(struct inode *inode, loff_t bytes)
+/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
+void __inode_add_bytes(struct inode *inode, loff_t bytes)
 {
-	spin_lock(&inode->i_lock);
 	inode->i_blocks += bytes >> 9;
 	bytes &= 511;
 	inode->i_bytes += bytes;
@@ -411,6 +411,12 @@ void inode_add_bytes(struct inode *inode, loff_t bytes)
 		inode->i_blocks++;
 		inode->i_bytes -= 512;
 	}
+}
+
+void inode_add_bytes(struct inode *inode, loff_t bytes)
+{
+	spin_lock(&inode->i_lock);
+	__inode_add_bytes(inode, bytes);
 	spin_unlock(&inode->i_lock);
 }
 

include/linux/ext3_fs_sb.h

@@ -72,6 +72,8 @@ struct ext3_sb_info {
 	struct inode * s_journal_inode;
 	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

include/linux/ext3_jbd.h

@@ -44,13 +44,13 @@
 
 #define EXT3_DATA_TRANS_BLOCKS(sb)	(EXT3_SINGLEDATA_TRANS_BLOCKS + \
 					 EXT3_XATTR_TRANS_BLOCKS - 2 + \
-					 2*EXT3_QUOTA_TRANS_BLOCKS(sb))
+					 EXT3_MAXQUOTAS_TRANS_BLOCKS(sb))
 
 /* Delete operations potentially hit one directory's namespace plus an
  * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
  * generous.  We can grow the delete transaction later if necessary. */
 
-#define EXT3_DELETE_TRANS_BLOCKS(sb)	(2 * EXT3_DATA_TRANS_BLOCKS(sb) + 64)
+#define EXT3_DELETE_TRANS_BLOCKS(sb)   (EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) + 64)
 
 /* Define an arbitrary limit for the amount of data we will anticipate
  * writing to any given transaction.  For unbounded transactions such as
@@ -86,6 +86,9 @@
 #define EXT3_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT3_QUOTA_DEL_BLOCKS(sb) 0
 #endif
+#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
 
 int
 ext3_mark_iloc_dirty(handle_t *handle,

include/linux/fs.h

@@ -2297,6 +2297,7 @@ extern const struct inode_operations page_symlink_inode_operations;
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
 extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+void __inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_sub_bytes(struct inode *inode, loff_t bytes);
 loff_t inode_get_bytes(struct inode *inode);

include/linux/quota.h

@@ -315,8 +315,9 @@ struct dquot_operations {
 	int (*claim_space) (struct inode *, qsize_t);
 	/* release rsved quota for delayed alloc */
 	void (*release_rsv) (struct inode *, qsize_t);
-	/* get reserved quota for delayed alloc */
-	qsize_t (*get_reserved_space) (struct inode *);
+	/* get reserved quota for delayed alloc, value returned is managed by
+	 * quota code only */
+	qsize_t *(*get_reserved_space) (struct inode *);
 };
 
 /* Operations handling requests from userspace */