Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "These are mostly bug fixes and a two small performance fixes.  The
  most important of the bunch are Josef's fix for a snapshotting
  regression and Mark's update to fix compile problems on arm"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (25 commits)
  Btrfs: create the uuid tree on remount rw
  btrfs: change extent-same to copy entire argument struct
  Btrfs: dir_inode_operations should use btrfs_update_time also
  btrfs: Add btrfs: prefix to kernel log output
  btrfs: refuse to remount read-write after abort
  Btrfs: btrfs_ioctl_default_subvol: Revert back to toplevel subvolume when arg is 0
  Btrfs: don't leak transaction in btrfs_sync_file()
  Btrfs: add the missing mutex unlock in write_all_supers()
  Btrfs: iput inode on allocation failure
  Btrfs: remove space_info->reservation_progress
  Btrfs: kill delay_iput arg to the wait_ordered functions
  Btrfs: fix worst case calculator for space usage
  Revert "Btrfs: rework the overcommit logic to be based on the total size"
  Btrfs: improve replacing nocow extents
  Btrfs: drop dir i_size when adding new names on replay
  Btrfs: replay dir_index items before other items
  Btrfs: check roots last log commit when checking if an inode has been logged
  Btrfs: actually log directory we are fsync()'ing
  Btrfs: actually limit the size of delalloc range
  Btrfs: allocate the free space by the existed max extent size when ENOSPC
  ...

Author: torvalds

fs/btrfs/btrfs_inode.h

@@ -213,7 +213,10 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode)
 static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
 {
 	if (BTRFS_I(inode)->logged_trans == generation &&
-	    BTRFS_I(inode)->last_sub_trans <= BTRFS_I(inode)->last_log_commit)
+	    BTRFS_I(inode)->last_sub_trans <=
+	    BTRFS_I(inode)->last_log_commit &&
+	    BTRFS_I(inode)->last_sub_trans <=
+	    BTRFS_I(inode)->root->last_log_commit)
 		return 1;
 	return 0;
 }

fs/btrfs/ctree.c

@@ -1005,8 +1005,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	if (root->ref_cows)
-		btrfs_reloc_cow_block(trans, root, buf, cow);
+	if (root->ref_cows) {
+		ret = btrfs_reloc_cow_block(trans, root, buf, cow);
+		if (ret)
+			return ret;
+	}
 
 	if (buf == root->node) {
 		WARN_ON(parent && parent != buf);

fs/btrfs/ctree.h

@@ -1118,15 +1118,6 @@ struct btrfs_space_info {
 	 */
 	struct percpu_counter total_bytes_pinned;
 
-	/*
-	 * we bump reservation progress every time we decrement
-	 * bytes_reserved.  This way people waiting for reservations
-	 * know something good has happened and they can check
-	 * for progress.  The number here isn't to be trusted, it
-	 * just shows reclaim activity
-	 */
-	unsigned long reservation_progress;
-
 	unsigned int full:1;	/* indicates that we cannot allocate any more
 				   chunks for this space */
 	unsigned int chunk_alloc:1;	/* set if we are allocating a chunk */
@@ -3135,7 +3126,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
 	return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		3 * num_items;
+		2 * num_items;
 }
 
 /*
@@ -3939,9 +3930,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
 int btrfs_recover_relocation(struct btrfs_root *root);
 int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
-void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, struct extent_buffer *buf,
-			   struct extent_buffer *cow);
+int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root, struct extent_buffer *buf,
+			  struct extent_buffer *cow);
 void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans,
 			      struct btrfs_pending_snapshot *pending,
 			      u64 *bytes_to_reserve);

fs/btrfs/dev-replace.c

@@ -400,7 +400,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
 	btrfs_dev_replace_unlock(dev_replace);
 
-	btrfs_wait_all_ordered_extents(root->fs_info, 0);
+	btrfs_wait_all_ordered_extents(root->fs_info);
 
 	/* force writing the updated state information to disk */
 	trans = btrfs_start_transaction(root, 0);
@@ -475,7 +475,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
 	}
-	btrfs_wait_all_ordered_extents(root->fs_info, 0);
+	btrfs_wait_all_ordered_extents(root->fs_info);
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {

fs/btrfs/disk-io.c

@@ -157,6 +157,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_TREE_LOG_OBJECTID,	.name_stem = "log"	},
 	{ .id = BTRFS_TREE_RELOC_OBJECTID,	.name_stem = "treloc"	},
 	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	.name_stem = "dreloc"	},
+	{ .id = BTRFS_UUID_TREE_OBJECTID,	.name_stem = "uuid"	},
 	{ .id = 0,				.name_stem = "tree"	},
 };
 
@@ -3415,6 +3416,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	if (total_errors > max_errors) {
 		printk(KERN_ERR "btrfs: %d errors while writing supers\n",
 		       total_errors);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 		/* FUA is masked off if unsupported and can't be the reason */
 		btrfs_error(root->fs_info, -EIO,

fs/btrfs/extent-tree.c

@@ -3925,7 +3925,6 @@ static int can_overcommit(struct btrfs_root *root,
 	u64 space_size;
 	u64 avail;
 	u64 used;
-	u64 to_add;
 
 	used = space_info->bytes_used + space_info->bytes_reserved +
 		space_info->bytes_pinned + space_info->bytes_readonly;
@@ -3959,25 +3958,17 @@ static int can_overcommit(struct btrfs_root *root,
 		       BTRFS_BLOCK_GROUP_RAID10))
 		avail >>= 1;
 
-	to_add = space_info->total_bytes;
-
 	/*
 	 * If we aren't flushing all things, let us overcommit up to
 	 * 1/2th of the space. If we can flush, don't let us overcommit
 	 * too much, let it overcommit up to 1/8 of the space.
 	 */
 	if (flush == BTRFS_RESERVE_FLUSH_ALL)
-		to_add >>= 3;
+		avail >>= 3;
 	else
-		to_add >>= 1;
-
-	/*
-	 * Limit the overcommit to the amount of free space we could possibly
-	 * allocate for chunks.
-	 */
-	to_add = min(avail, to_add);
+		avail >>= 1;
 
-	if (used + bytes < space_info->total_bytes + to_add)
+	if (used + bytes < space_info->total_bytes + avail)
 		return 1;
 	return 0;
 }
@@ -4000,7 +3991,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
 		 */
 		btrfs_start_all_delalloc_inodes(root->fs_info, 0);
 		if (!current->journal_info)
-			btrfs_wait_all_ordered_extents(root->fs_info, 0);
+			btrfs_wait_all_ordered_extents(root->fs_info);
 	}
 }
 
@@ -4030,7 +4021,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 	if (delalloc_bytes == 0) {
 		if (trans)
 			return;
-		btrfs_wait_all_ordered_extents(root->fs_info, 0);
+		btrfs_wait_all_ordered_extents(root->fs_info);
 		return;
 	}
 
@@ -4058,7 +4049,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 
 		loops++;
 		if (wait_ordered && !trans) {
-			btrfs_wait_all_ordered_extents(root->fs_info, 0);
+			btrfs_wait_all_ordered_extents(root->fs_info);
 		} else {
 			time_left = schedule_timeout_killable(1);
 			if (time_left)
@@ -4465,7 +4456,6 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			space_info->bytes_may_use -= num_bytes;
 			trace_btrfs_space_reservation(fs_info, "space_info",
 					space_info->flags, num_bytes, 0);
-			space_info->reservation_progress++;
 			spin_unlock(&space_info->lock);
 		}
 	}
@@ -4666,7 +4656,6 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 		sinfo->bytes_may_use -= num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
 				      sinfo->flags, num_bytes, 0);
-		sinfo->reservation_progress++;
 		block_rsv->reserved = block_rsv->size;
 		block_rsv->full = 1;
 	}
@@ -5446,7 +5435,6 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 			space_info->bytes_readonly += num_bytes;
 		cache->reserved -= num_bytes;
 		space_info->bytes_reserved -= num_bytes;
-		space_info->reservation_progress++;
 	}
 	spin_unlock(&cache->lock);
 	spin_unlock(&space_info->lock);
@@ -6117,10 +6105,13 @@ enum btrfs_loop_type {
 /*
  * walks the btree of allocated extents and find a hole of a given size.
  * The key ins is changed to record the hole:
- * ins->objectid == block start
+ * ins->objectid == start position
  * ins->flags = BTRFS_EXTENT_ITEM_KEY
- * ins->offset == number of blocks
+ * ins->offset == the size of the hole.
  * Any available blocks before search_start are skipped.
+ *
+ * If there is no suitable free space, we will record the max size of
+ * the free space extent currently.
  */
 static noinline int find_free_extent(struct btrfs_root *orig_root,
 				     u64 num_bytes, u64 empty_size,
@@ -6133,6 +6124,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 	struct btrfs_block_group_cache *block_group = NULL;
 	struct btrfs_block_group_cache *used_block_group;
 	u64 search_start = 0;
+	u64 max_extent_size = 0;
 	int empty_cluster = 2 * 1024 * 1024;
 	struct btrfs_space_info *space_info;
 	int loop = 0;
@@ -6292,7 +6284,10 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 				btrfs_get_block_group(used_block_group);
 
 			offset = btrfs_alloc_from_cluster(used_block_group,
-			  last_ptr, num_bytes, used_block_group->key.objectid);
+						last_ptr,
+						num_bytes,
+						used_block_group->key.objectid,
+						&max_extent_size);
 			if (offset) {
 				/* we have a block, we're done */
 				spin_unlock(&last_ptr->refill_lock);
@@ -6355,8 +6350,10 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 				 * cluster
 				 */
 				offset = btrfs_alloc_from_cluster(block_group,
-						  last_ptr, num_bytes,
-						  search_start);
+							last_ptr,
+							num_bytes,
+							search_start,
+							&max_extent_size);
 				if (offset) {
 					/* we found one, proceed */
 					spin_unlock(&last_ptr->refill_lock);
@@ -6391,13 +6388,18 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 		if (cached &&
 		    block_group->free_space_ctl->free_space <
 		    num_bytes + empty_cluster + empty_size) {
+			if (block_group->free_space_ctl->free_space >
+			    max_extent_size)
+				max_extent_size =
+					block_group->free_space_ctl->free_space;
 			spin_unlock(&block_group->free_space_ctl->tree_lock);
 			goto loop;
 		}
 		spin_unlock(&block_group->free_space_ctl->tree_lock);
 
 		offset = btrfs_find_space_for_alloc(block_group, search_start,
-						    num_bytes, empty_size);
+						    num_bytes, empty_size,
+						    &max_extent_size);
 		/*
 		 * If we didn't find a chunk, and we haven't failed on this
 		 * block group before, and this block group is in the middle of
@@ -6515,7 +6517,8 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 		ret = 0;
 	}
 out:
-
+	if (ret == -ENOSPC)
+		ins->offset = max_extent_size;
 	return ret;
 }
 
@@ -6573,8 +6576,8 @@ int btrfs_reserve_extent(struct btrfs_root *root,
 			       flags);
 
 	if (ret == -ENOSPC) {
-		if (!final_tried) {
-			num_bytes = num_bytes >> 1;
+		if (!final_tried && ins->offset) {
+			num_bytes = min(num_bytes >> 1, ins->offset);
 			num_bytes = round_down(num_bytes, root->sectorsize);
 			num_bytes = max(num_bytes, min_alloc_size);
 			if (num_bytes == min_alloc_size)

fs/btrfs/extent_io.c

@@ -1481,10 +1481,12 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
 		*end = state->end;
 		cur_start = state->end + 1;
 		node = rb_next(node);
-		if (!node)
-			break;
 		total_bytes += state->end - state->start + 1;
-		if (total_bytes >= max_bytes)
+		if (total_bytes >= max_bytes) {
+			*end = *start + max_bytes - 1;
+			break;
+		}
+		if (!node)
 			break;
 	}
 out:

fs/btrfs/file.c

@@ -1859,8 +1859,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	ret = btrfs_log_dentry_safe(trans, root, dentry);
 	if (ret < 0) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
+		/* Fallthrough and commit/free transaction. */
+		ret = 1;
 	}
 
 	/* we've logged all the items and now have a consistent