Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: add missing ext4_journal_stop()
ext4: ext4_find_next_zero_bit needs an aligned address on some arch
ext4: set EXT4_EXTENTS_FL only for directory and regular files
ext4: Don't mark filesystem error if fallocate fails
ext4: Fix BUG when writing to an unitialized extent
ext4: Don't use ext4_dec_count() if not needed
ext4: modify block allocation algorithm for the last group
ext4: Don't claim block from group which has corrupt bitmap
ext4: Get journal write access before modifying the extent tree
ext4: Fix memory and buffer head leak in callers to ext4_ext_find_extent()
ext4: Don't leave behind a half-created inode if ext4_mkdir() fails
ext4: Fix kernel BUG at fs/ext4/mballoc.c:910!
ext4: Fix locking hierarchy violation in ext4_fallocate()
Remove incorrect BKL comments in ext4

fs/ext4/dir.c

···
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
-	.fsync		= ext4_sync_file,	/* BKL held */
+	.fsync		= ext4_sync_file,
 	.release	= ext4_release_dir,
 };
 

fs/ext4/extents.c

···
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
 	ext4_grpblk_t colour;
 	int depth;
 
···
 	/* OK. use inode's group */
 	bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
 		le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
-	colour = (current->pid % 16) *
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
 	return bg_start + colour + block;
 }
 
···
 #define ext4_ext_show_leaf(inode,path)
 #endif
 
-static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+void ext4_ext_drop_refs(struct ext4_ext_path *path)
 {
 	int depth = path->p_depth;
 	int i;
···
 	newblock = iblock - ee_block + ext_pblock(ex);
 	ex2 = ex;
 
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+
 	/* ex1: ee_block to iblock - 1 : uninitialized */
 	if (iblock > ee_block) {
 		ex1 = ex;
···
 		newdepth = ext_depth(inode);
 		if (newdepth != depth) {
 			depth = newdepth;
-			path = ext4_ext_find_extent(inode, iblock, NULL);
+			ext4_ext_drop_refs(path);
+			path = ext4_ext_find_extent(inode, iblock, path);
 			if (IS_ERR(path)) {
 				err = PTR_ERR(path);
-				path = NULL;
 				goto out;
 			}
 			eh = path[depth].p_hdr;
 			ex = path[depth].p_ext;
 			if (ex2 != &newex)
 				ex2 = ex;
+
+			err = ext4_ext_get_access(handle, inode, path + depth);
+			if (err)
+				goto out;
 		}
 		allocated = max_blocks;
 	}
···
 	ex2->ee_len = cpu_to_le16(allocated);
 	if (ex2 != ex)
 		goto insert;
-	err = ext4_ext_get_access(handle, inode, path + depth);
-	if (err)
-		goto out;
 	/*
 	 * New (initialized) extent starts from the first block
 	 * in the current extent. i.e., ex2 == ex
···
 }
 
 /*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
  * Need to be called with
  * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
  * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ *          if create == 0 and these are pre-allocated blocks
+ *          	buffer head is unmapped
+ *          otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ *          buffer head is unmapped
+ *
+ * return < 0, error case.
  */
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
···
 	 * modify 1 super block, 1 block bitmap and 1 group descriptor.
 	 */
 	credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
-	down_write((&EXT4_I(inode)->i_data_sem));
+	mutex_lock(&inode->i_mutex);
 retry:
 	while (ret >= 0 && ret < max_blocks) {
 		block = block + ret;
···
 			break;
 		}
 
-		ret = ext4_ext_get_blocks(handle, inode, block,
+		ret = ext4_get_blocks_wrap(handle, inode, block,
 					  max_blocks, &map_bh,
 					  EXT4_CREATE_UNINITIALIZED_EXT, 0);
-		WARN_ON(ret <= 0);
 		if (ret <= 0) {
-			ext4_error(inode->i_sb, "ext4_fallocate",
-				    "ext4_ext_get_blocks returned error: "
-				    "inode#%lu, block=%u, max_blocks=%lu",
+#ifdef EXT4FS_DEBUG
+			WARN_ON(ret <= 0);
+			printk(KERN_ERR "%s: ext4_ext_get_blocks "
+				    "returned error inode#%lu, block=%u, "
+				    "max_blocks=%lu", __func__,
 				    inode->i_ino, block, max_blocks);
-			ret = -EIO;
+#endif
 			ext4_mark_inode_dirty(handle, inode);
 			ret2 = ext4_journal_stop(handle);
 			break;
···
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 
-	up_write((&EXT4_I(inode)->i_data_sem));
 	/*
 	 * Time to update the file size.
 	 * Update only when preallocation was requested beyond the file size.
···
 			 * if no error, we assume preallocation succeeded
 			 * completely
 			 */
-			mutex_lock(&inode->i_mutex);
 			i_size_write(inode, offset + len);
 			EXT4_I(inode)->i_disksize = i_size_read(inode);
-			mutex_unlock(&inode->i_mutex);
 		} else if (ret < 0 && nblocks) {
 			/* Handle partial allocation scenario */
 			loff_t newsize;
 
-			mutex_lock(&inode->i_mutex);
 			newsize  = (nblocks << blkbits) + i_size_read(inode);
 			i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits));
 			EXT4_I(inode)->i_disksize = i_size_read(inode);
-			mutex_unlock(&inode->i_mutex);
 		}
 	}
 
+	mutex_unlock(&inode->i_mutex);
 	return ret > 0 ? ret2 : ret;
 }

fs/ext4/ialloc.c

···
 	ei->i_dir_start_lookup = 0;
 	ei->i_disksize = 0;
 
-	ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
+	/*
+	 * Don't inherit extent flag from directory. We set extent flag on
+	 * newly created directory and file only if -o extent mount option is
+	 * specified
+	 */
+	ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL);
 	if (S_ISLNK(mode))
 		ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
 	/* dirsync only applies to directories */
···
 		goto fail_free_drop;
 	}
 	if (test_opt(sb, EXTENTS)) {
-		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
-		ext4_ext_tree_init(handle, inode);
-		err = ext4_update_incompat_feature(handle, sb,
-						EXT4_FEATURE_INCOMPAT_EXTENTS);
-		if (err)
-			goto fail;
+		/* set extent flag only for directory and file */
+		if (S_ISDIR(mode) || S_ISREG(mode)) {
+			EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+			ext4_ext_tree_init(handle, inode);
+			err = ext4_update_incompat_feature(handle, sb,
+					EXT4_FEATURE_INCOMPAT_EXTENTS);
+			if (err)
+				goto fail;
+		}
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);

fs/ext4/inode.c

···
 	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
 	__le32 *p;
 	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
 	ext4_grpblk_t colour;
 
 	/* Try to find previous block */
···
 	 * into the same cylinder group then.
 	 */
 	bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group);
-	colour = (current->pid % 16) *
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
 	return bg_start + colour;
 }
 
···
  *
  * `handle' can be NULL if create == 0.
  *
- * The BKL may not be held on entry here.  Be sure to take it early.
  * return > 0, # of blocks mapped or allocated.
  * return = 0, if plain lookup failed.
  * return < 0, error case.
···
  */
 #define DIO_CREDITS 25
 
+
+/*
+ *
+ *
+ * ext4_ext4 get_block() wrapper function
+ * It will do a look up first, and returns if the blocks already mapped.
+ * Otherwise it takes the write lock of the i_data_sem and allocate blocks
+ * and store the allocated blocks in the result buffer head and mark it
+ * mapped.
+ *
+ * If file type is extents based, it will call ext4_ext_get_blocks(),
+ * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping
+ * based files
+ *
+ * On success, it returns the number of blocks being mapped or allocate.
+ * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * the result buffer head is unmapped. If the create ==1, it will make sure
+ * the buffer head is mapped.
+ *
+ * It returns 0 if plain look up failed (blocks have not been allocated), in
+ * that casem, buffer head is unmapped
+ *
+ * It returns the error in case of allocation failure.
+ */
 int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 			unsigned long max_blocks, struct buffer_head *bh,
 			int create, int extend_disksize)
 {
 	int retval;
+
+	clear_buffer_mapped(bh);
+
 	/*
 	 * Try to see if we can get  the block without requesting
 	 * for new file system block.
···
 				inode, block, max_blocks, bh, 0, 0);
 	}
 	up_read((&EXT4_I(inode)->i_data_sem));
-	if (!create || (retval > 0))
+
+	/* If it is only a block(s) look up */
+	if (!create)
 		return retval;
 
 	/*
-	 * We need to allocate new blocks which will result
-	 * in i_data update
+	 * Returns if the blocks have already allocated
+	 *
+	 * Note that if blocks have been preallocated
+	 * ext4_ext_get_block() returns th create = 0
+	 * with buffer head unmapped.
+	 */
+	if (retval > 0 && buffer_mapped(bh))
+		return retval;
+
+	/*
+	 * New blocks allocate and/or writing to uninitialized extent
+	 * will possibly result in updating i_data, so we take
+	 * the write lock of i_data_sem, and call get_blocks()
+	 * with create == 1 flag.
 	 */
 	down_write((&EXT4_I(inode)->i_data_sem));
 	/*

fs/ext4/mballoc.c

···
 	return block;
 }
 
+static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
+{
 #if BITS_PER_LONG == 64
-#define mb_correct_addr_and_bit(bit, addr)		\
-{							\
-	bit += ((unsigned long) addr & 7UL) << 3;	\
-	addr = (void *) ((unsigned long) addr & ~7UL);	\
-}
+	*bit += ((unsigned long) addr & 7UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~7UL);
 #elif BITS_PER_LONG == 32
-#define mb_correct_addr_and_bit(bit, addr)		\
-{							\
-	bit += ((unsigned long) addr & 3UL) << 3;	\
-	addr = (void *) ((unsigned long) addr & ~3UL);	\
-}
+	*bit += ((unsigned long) addr & 3UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~3UL);
 #else
 #error "how many bits you are?!"
 #endif
+	return addr;
+}
 
 static inline int mb_test_bit(int bit, void *addr)
 {
···
 	 * ext4_test_bit on architecture like powerpc
 	 * needs unsigned long aligned address
 	 */
-	mb_correct_addr_and_bit(bit, addr);
+	addr = mb_correct_addr_and_bit(&bit, addr);
 	return ext4_test_bit(bit, addr);
 }
 
 static inline void mb_set_bit(int bit, void *addr)
 {
-	mb_correct_addr_and_bit(bit, addr);
+	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_set_bit(bit, addr);
 }
 
 static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr)
 {
-	mb_correct_addr_and_bit(bit, addr);
+	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_set_bit_atomic(lock, bit, addr);
 }
 
 static inline void mb_clear_bit(int bit, void *addr)
 {
-	mb_correct_addr_and_bit(bit, addr);
+	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_clear_bit(bit, addr);
 }
 
 static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr)
 {
-	mb_correct_addr_and_bit(bit, addr);
+	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_clear_bit_atomic(lock, bit, addr);
+}
+
+static inline int mb_find_next_zero_bit(void *addr, int max, int start)
+{
+	int fix = 0;
+	addr = mb_correct_addr_and_bit(&fix, addr);
+	max += fix;
+	start += fix;
+
+	return ext4_find_next_zero_bit(addr, max, start) - fix;
+}
+
+static inline int mb_find_next_bit(void *addr, int max, int start)
+{
+	int fix = 0;
+	addr = mb_correct_addr_and_bit(&fix, addr);
+	max += fix;
+	start += fix;
+
+	return ext4_find_next_bit(addr, max, start) - fix;
 }
 
 static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
···
 	unsigned short chunk;
 	unsigned short border;
 
-	BUG_ON(len >= EXT4_BLOCKS_PER_GROUP(sb));
+	BUG_ON(len > EXT4_BLOCKS_PER_GROUP(sb));
 
 	border = 2 << sb->s_blocksize_bits;
 
···
 
 	/* initialize buddy from bitmap which is aggregation
 	 * of on-disk bitmap and preallocations */
-	i = ext4_find_next_zero_bit(bitmap, max, 0);
+	i = mb_find_next_zero_bit(bitmap, max, 0);
 	grp->bb_first_free = i;
 	while (i < max) {
 		fragments++;
 		first = i;
-		i = ext4_find_next_bit(bitmap, max, i);
+		i = mb_find_next_bit(bitmap, max, i);
 		len = i - first;
 		free += len;
 		if (len > 1)
···
 		else
 			grp->bb_counters[0]++;
 		if (i < max)
-			i = ext4_find_next_zero_bit(bitmap, max, i);
+			i = mb_find_next_zero_bit(bitmap, max, i);
 	}
 	grp->bb_fragments = fragments;
 
···
 		ext4_error(sb, __FUNCTION__,
 			"EXT4-fs: group %lu: %u blocks in bitmap, %u in gd\n",
 			group, free, grp->bb_free);
+		/*
+		 * If we intent to continue, we consider group descritor
+		 * corrupt and update bb_free using bitmap value
+		 */
 		grp->bb_free = free;
 	}
 
···
 		buddy = mb_find_buddy(e4b, i, &max);
 		BUG_ON(buddy == NULL);
 
-		k = ext4_find_next_zero_bit(buddy, max, 0);
+		k = mb_find_next_zero_bit(buddy, max, 0);
 		BUG_ON(k >= max);
 
 		ac->ac_found++;
···
 	i = e4b->bd_info->bb_first_free;
 
 	while (free && ac->ac_status == AC_STATUS_CONTINUE) {
-		i = ext4_find_next_zero_bit(bitmap,
+		i = mb_find_next_zero_bit(bitmap,
 						EXT4_BLOCKS_PER_GROUP(sb), i);
 		if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
 			/*
-			 * IF we corrupt the bitmap  we won't find any
+			 * IF we have corrupt bitmap, we won't find any
 			 * free blocks even though group info says we
 			 * we have free blocks
 			 */
···
 			ext4_error(sb, __FUNCTION__, "%d free blocks as per "
 					"group info. But got %d blocks\n",
 					free, ex.fe_len);
+			/*
+			 * The number of free blocks differs. This mostly
+			 * indicate that the bitmap is corrupt. So exit
+			 * without claiming the space.
+			 */
+			break;
 		}
 
 		ext4_mb_measure_extent(ac, &ex, e4b);
···
 	}
 
 	while (bit < end) {
-		bit = ext4_find_next_zero_bit(bitmap_bh->b_data, end, bit);
+		bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit);
 		if (bit >= end)
 			break;
-		next = ext4_find_next_bit(bitmap_bh->b_data, end, bit);
+		next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
 		if (next > end)
 			next = end;
 		start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit +
···
 			(unsigned long) pa->pa_len);
 		ext4_error(sb, __FUNCTION__, "free %u, pa_free %u\n",
 						free, pa->pa_free);
+		/*
+		 * pa is already deleted so we use the value obtained
+		 * from the bitmap and continue.
+		 */
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
 	if (ac)

fs/ext4/migrate.c

···
 
 	if (IS_ERR(path)) {
 		retval = PTR_ERR(path);
+		path = NULL;
 		goto err_out;
 	}
 
···
 	}
 	retval = ext4_ext_insert_extent(handle, inode, path, &newext);
 err_out:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
 	lb->first_pblock = 0;
 	return retval;
 }

fs/ext4/namei.c

···
 	inode->i_fop = &ext4_dir_operations;
 	inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
 	dir_block = ext4_bread (handle, inode, 0, 1, &err);
-	if (!dir_block) {
-		ext4_dec_count(handle, inode); /* is this nlink == 0? */
-		ext4_mark_inode_dirty(handle, inode);
-		iput (inode);
-		goto out_stop;
-	}
+	if (!dir_block)
+		goto out_clear_inode;
 	BUFFER_TRACE(dir_block, "get_write_access");
 	ext4_journal_get_write_access(handle, dir_block);
 	de = (struct ext4_dir_entry_2 *) dir_block->b_data;
···
 	ext4_mark_inode_dirty(handle, inode);
 	err = ext4_add_entry (handle, dentry, inode);
 	if (err) {
-		inode->i_nlink = 0;
+out_clear_inode:
+		clear_nlink(inode);
 		ext4_mark_inode_dirty(handle, inode);
 		iput (inode);
 		goto out_stop;
···
 	dir->i_ctime = dir->i_mtime = ext4_current_time(dir);
 	ext4_update_dx_flag(dir);
 	ext4_mark_inode_dirty(handle, dir);
-	ext4_dec_count(handle, inode);
+	drop_nlink(inode);
 	if (!inode->i_nlink)
 		ext4_orphan_add(handle, inode);
 	inode->i_ctime = ext4_current_time(inode);
···
 		err = __page_symlink(inode, symname, l,
 				mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
 		if (err) {
-			ext4_dec_count(handle, inode);
+			clear_nlink(inode);
 			ext4_mark_inode_dirty(handle, inode);
 			iput (inode);
 			goto out_stop;
···
 		inode->i_op = &ext4_fast_symlink_inode_operations;
 		memcpy((char*)&EXT4_I(inode)->i_data,symname,l);
 		inode->i_size = l-1;
-		EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
 	}
 	EXT4_I(inode)->i_disksize = inode->i_size;
 	err = ext4_add_nondir(handle, dentry, inode);
···
 		ext4_dec_count(handle, old_dir);
 		if (new_inode) {
 			/* checked empty_dir above, can't have another parent,
-			 * ext3_dec_count() won't work for many-linked dirs */
+			 * ext4_dec_count() won't work for many-linked dirs */
 			new_inode->i_nlink = 0;
 		} else {
 			ext4_inc_count(handle, new_dir);

fs/ext4/resize.c

···
 		ext4_warning(sb, __FUNCTION__,
 			     "multiple resizers run on filesystem!");
 		unlock_super(sb);
+		ext4_journal_stop(handle);
 		err = -EBUSY;
 		goto exit_put;
 	}

include/linux/ext4_fs_extents.h

···
 						ext4_lblk_t *, ext4_fsblk_t *);
 extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
 						ext4_lblk_t *, ext4_fsblk_t *);
+extern void ext4_ext_drop_refs(struct ext4_ext_path *);
 #endif /* _LINUX_EXT4_EXTENTS */