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: Update documentation to remind users to update mke2fs.conf
  ext4: Fix small file fragmentation
  ext4: Initialize writeback_index to 0 when allocating a new inode
  ext4: make sure ext4_has_free_blocks returns 0 for ENOSPC
  ext4: journal credit fix for the delayed allocation's writepages() function
  ext4: Rework the ext4_da_writepages() function
  ext4: journal credits reservation fixes for DIO, fallocate
  ext4: journal credits reservation fixes for extent file writepage
  ext4: journal credits calulation cleanup and fix for non-extent writepage
  ext4: Fix bug where we return ENOSPC even though we have plenty of inodes
  ext4: don't try to resize if there are no reserved gdt blocks left
  ext4: Use ext4_discard_reservations instead of mballoc-specific call
  ext4: Fix ext4_dx_readdir hash collision handling
  ext4: Fix delalloc release block reservation for truncate
  ext4: Fix potential truncate BUG due to i_prealloc_list being non-empty
  ext4: Handle unwritten extent properly with delayed allocation

Documentation/filesystems/ext4.txt

@@ -26,6 +26,12 @@ Mailing list: linux-ext4@vger.kernel.org
 
     git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
 
+  - Note that it is highly important to install the mke2fs.conf file
+    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
+    you have edited the /etc/mke2fs.conf file installed on your system,
+    you will need to merge your changes with the version from e2fsprogs
+    1.41.x.
+
   - Create a new filesystem using the ext4dev filesystem type:
 
     	# mke2fs -t ext4dev /dev/hda1

fs/ext4/balloc.c

@@ -1626,6 +1626,9 @@ ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
 		free_blocks =
 			percpu_counter_sum_and_set(&sbi->s_freeblocks_counter);
 #endif
+	if (free_blocks <= root_blocks)
+		/* we don't have free space */
+		return 0;
 	if (free_blocks - root_blocks < nblocks)
 		return free_blocks - root_blocks;
 	return nblocks;

fs/ext4/dir.c

@@ -411,7 +411,7 @@ static int call_filldir(struct file * filp, void * dirent,
 				get_dtype(sb, fname->file_type));
 		if (error) {
 			filp->f_pos = curr_pos;
-			info->extra_fname = fname->next;
+			info->extra_fname = fname;
 			return error;
 		}
 		fname = fname->next;
@@ -450,11 +450,21 @@ static int ext4_dx_readdir(struct file * filp,
 	 * If there are any leftover names on the hash collision
 	 * chain, return them first.
 	 */
-	if (info->extra_fname &&
-	    call_filldir(filp, dirent, filldir, info->extra_fname))
-		goto finished;
+	if (info->extra_fname) {
+		if (call_filldir(filp, dirent, filldir, info->extra_fname))
+			goto finished;
 
-	if (!info->curr_node)
+		info->extra_fname = NULL;
+		info->curr_node = rb_next(info->curr_node);
+		if (!info->curr_node) {
+			if (info->next_hash == ~0) {
+				filp->f_pos = EXT4_HTREE_EOF;
+				goto finished;
+			}
+			info->curr_hash = info->next_hash;
+			info->curr_minor_hash = 0;
+		}
+	} else if (!info->curr_node)
 		info->curr_node = rb_first(&info->root);
 
 	while (1) {

fs/ext4/ext4.h

@@ -1072,6 +1072,8 @@ extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
+extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
+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 page *page);
@@ -1227,6 +1229,8 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
 /* extents.c */
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
+extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
+				       int chunk);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
 			unsigned long max_blocks, struct buffer_head *bh_result,

fs/ext4/ext4_extents.h

@@ -216,7 +216,9 @@ extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
 extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
-extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
+						   int num,
+						   struct ext4_ext_path *path);
 extern int ext4_ext_try_to_merge(struct inode *inode,
 				 struct ext4_ext_path *path,
 				 struct ext4_extent *);

fs/ext4/ext4_jbd2.h

@@ -51,6 +51,14 @@
 					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
 					 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
 
+/*
+ * Define the number of metadata blocks we need to account to modify data.
+ *
+ * This include super block, inode block, quota blocks and xattr blocks
+ */
+#define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
+					2*EXT4_QUOTA_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. */

fs/ext4/extents.c

@@ -1747,54 +1747,61 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 }
 
 /*
- * ext4_ext_calc_credits_for_insert:
- * This routine returns max. credits that the extent tree can consume.
- * It should be OK for low-performance paths like ->writepage()
- * To allow many writing processes to fit into a single transaction,
- * the caller should calculate credits under i_data_sem and
- * pass the actual path.
+ * ext4_ext_calc_credits_for_single_extent:
+ * This routine returns max. credits that needed to insert an extent
+ * to the extent tree.
+ * When pass the actual path, the caller should calculate credits
+ * under i_data_sem.
  */
-int ext4_ext_calc_credits_for_insert(struct inode *inode,
+int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
 						struct ext4_ext_path *path)
 {
-	int depth, needed;
-
 	if (path) {
+		int depth = ext_depth(inode);
+		int ret = 0;
+
 		/* probably there is space in leaf? */
-		depth = ext_depth(inode);
 		if (le16_to_cpu(path[depth].p_hdr->eh_entries)
-				< le16_to_cpu(path[depth].p_hdr->eh_max))
-			return 1;
-	}
+				< le16_to_cpu(path[depth].p_hdr->eh_max)) {
 
-	/*
-	 * given 32-bit logical block (4294967296 blocks), max. tree
-	 * can be 4 levels in depth -- 4 * 340^4 == 53453440000.
-	 * Let's also add one more level for imbalance.
-	 */
-	depth = 5;
-
-	/* allocation of new data block(s) */
-	needed = 2;
+			/*
+			 *  There are some space in the leaf tree, no
+			 *  need to account for leaf block credit
+			 *
+			 *  bitmaps and block group descriptor blocks
+			 *  and other metadat blocks still need to be
+			 *  accounted.
+			 */
+			/* 1 bitmap, 1 block group descriptor */
+			ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
+		}
+	}
 
-	/*
-	 * tree can be full, so it would need to grow in depth:
-	 * we need one credit to modify old root, credits for
-	 * new root will be added in split accounting
-	 */
-	needed += 1;
+	return ext4_chunk_trans_blocks(inode, nrblocks);
+}
 
-	/*
-	 * Index split can happen, we would need:
-	 *    allocate intermediate indexes (bitmap + group)
-	 *  + change two blocks at each level, but root (already included)
-	 */
-	needed += (depth * 2) + (depth * 2);
+/*
+ * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ *
+ * if nrblocks are fit in a single extent (chunk flag is 1), then
+ * in the worse case, each tree level index/leaf need to be changed
+ * if the tree split due to insert a new extent, then the old tree
+ * index/leaf need to be updated too
+ *
+ * If the nrblocks are discontiguous, they could cause
+ * the whole tree split more than once, but this is really rare.
+ */
+int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+	int index;
+	int depth = ext_depth(inode);
 
-	/* any allocation modifies superblock */
-	needed += 1;
+	if (chunk)
+		index = depth * 2;
+	else
+		index = depth * 3;
 
-	return needed;
+	return index;
 }
 
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
@@ -1921,9 +1928,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			correct_index = 1;
 			credits += (ext_depth(inode)) + 1;
 		}
-#ifdef CONFIG_QUOTA
 		credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
 
 		err = ext4_ext_journal_restart(handle, credits);
 		if (err)
@@ -2805,7 +2810,7 @@ void ext4_ext_truncate(struct inode *inode)
 	/*
 	 * probably first extent we're gonna free will be last in block
 	 */
-	err = ext4_writepage_trans_blocks(inode) + 3;
+	err = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, err);
 	if (IS_ERR(handle))
 		return;
@@ -2819,7 +2824,7 @@ void ext4_ext_truncate(struct inode *inode)
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_ext_invalidate_cache(inode);
 
-	ext4_mb_discard_inode_preallocations(inode);
+	ext4_discard_reservation(inode);
 
 	/*
 	 * TODO: optimization is possible here.
@@ -2858,27 +2863,6 @@ out_stop:
 	ext4_journal_stop(handle);
 }
 
-/*
- * ext4_ext_writepage_trans_blocks:
- * calculate max number of blocks we could modify
- * in order to allocate new block for an inode
- */
-int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
-{
-	int needed;
-
-	needed = ext4_ext_calc_credits_for_insert(inode, NULL);
-
-	/* caller wants to allocate num blocks, but note it includes sb */
-	needed = needed * num - (num - 1);
-
-#ifdef CONFIG_QUOTA
-	needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
-
-	return needed;
-}
-
 static void ext4_falloc_update_inode(struct inode *inode,
 				int mode, loff_t new_size, int update_ctime)
 {
@@ -2939,10 +2923,9 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
 							- block;
 	/*
-	 * credits to insert 1 extent into extent tree + buffers to be able to
-	 * modify 1 super block, 1 block bitmap and 1 group descriptor.
+	 * credits to insert 1 extent into extent tree
 	 */
-	credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
+	credits = ext4_chunk_trans_blocks(inode, max_blocks);
 	mutex_lock(&inode->i_mutex);
 retry:
 	while (ret >= 0 && ret < max_blocks) {

fs/ext4/ialloc.c

@@ -351,7 +351,7 @@ find_close_to_parent:
 			goto found_flexbg;
 		}
 
-		if (best_flex < 0 ||
+		if (flex_group[best_flex].free_inodes == 0 ||
 		    (flex_group[i].free_blocks >
 		     flex_group[best_flex].free_blocks &&
 		     flex_group[i].free_inodes))

fs/ext4/mballoc.c

@@ -3281,6 +3281,35 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
 	mb_debug("use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa);
 }
 
+/*
+ * Return the prealloc space that have minimal distance
+ * from the goal block. @cpa is the prealloc
+ * space that is having currently known minimal distance
+ * from the goal block.
+ */
+static struct ext4_prealloc_space *
+ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
+			struct ext4_prealloc_space *pa,
+			struct ext4_prealloc_space *cpa)
+{
+	ext4_fsblk_t cur_distance, new_distance;
+
+	if (cpa == NULL) {
+		atomic_inc(&pa->pa_count);
+		return pa;
+	}
+	cur_distance = abs(goal_block - cpa->pa_pstart);
+	new_distance = abs(goal_block - pa->pa_pstart);
+
+	if (cur_distance < new_distance)
+		return cpa;
+
+	/* drop the previous reference */
+	atomic_dec(&cpa->pa_count);
+	atomic_inc(&pa->pa_count);
+	return pa;
+}
+
 /*
  * search goal blocks in preallocated space
  */
@@ -3290,7 +3319,8 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	int order, i;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
 	struct ext4_locality_group *lg;
-	struct ext4_prealloc_space *pa;
+	struct ext4_prealloc_space *pa, *cpa = NULL;
+	ext4_fsblk_t goal_block;
 
 	/* only data can be preallocated */
 	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
@@ -3333,6 +3363,13 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		/* The max size of hash table is PREALLOC_TB_SIZE */
 		order = PREALLOC_TB_SIZE - 1;
 
+	goal_block = ac->ac_g_ex.fe_group * EXT4_BLOCKS_PER_GROUP(ac->ac_sb) +
+		     ac->ac_g_ex.fe_start +
+		     le32_to_cpu(EXT4_SB(ac->ac_sb)->s_es->s_first_data_block);
+	/*
+	 * search for the prealloc space that is having
+	 * minimal distance from the goal block.
+	 */
 	for (i = order; i < PREALLOC_TB_SIZE; i++) {
 		rcu_read_lock();
 		list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i],
@@ -3340,17 +3377,19 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 			spin_lock(&pa->pa_lock);
 			if (pa->pa_deleted == 0 &&
 					pa->pa_free >= ac->ac_o_ex.fe_len) {
-				atomic_inc(&pa->pa_count);
-				ext4_mb_use_group_pa(ac, pa);
-				spin_unlock(&pa->pa_lock);
-				ac->ac_criteria = 20;
-				rcu_read_unlock();
-				return 1;
+
+				cpa = ext4_mb_check_group_pa(goal_block,
+								pa, cpa);
 			}
 			spin_unlock(&pa->pa_lock);
 		}
 		rcu_read_unlock();
 	}
+	if (cpa) {
+		ext4_mb_use_group_pa(ac, cpa);
+		ac->ac_criteria = 20;
+		return 1;
+	}
 	return 0;
 }
 

fs/ext4/migrate.c

@@ -53,7 +53,8 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	 * credit. But below we try to not accumalate too much
 	 * of them by restarting the journal.
 	 */
-	needed = ext4_ext_calc_credits_for_insert(inode, path);
+	needed = ext4_ext_calc_credits_for_single_extent(inode,
+		    lb->last_block - lb->first_block + 1, path);
 
 	/*
 	 * Make sure the credit we accumalated is not really high

fs/ext4/resize.c

@@ -773,7 +773,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 
 	if (reserved_gdb || gdb_off == 0) {
 		if (!EXT4_HAS_COMPAT_FEATURE(sb,
-					     EXT4_FEATURE_COMPAT_RESIZE_INODE)){
+					     EXT4_FEATURE_COMPAT_RESIZE_INODE)
+		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
 			ext4_warning(sb, __func__,
 				     "No reserved GDT blocks, can't resize");
 			return -EPERM;

fs/ext4/super.c

@@ -568,6 +568,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 #endif
 	ei->i_block_alloc_info = NULL;
 	ei->vfs_inode.i_version = 1;
+	ei->vfs_inode.i_data.writeback_index = 0;
 	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
 	spin_lock_init(&ei->i_prealloc_lock);