btrfs: Fix and enhance merge_extent_mapping() to insert best fitted extent map

The following commit enhanced the merge_extent_mapping() to reduce
fragment in extent map tree, but it can't handle case which existing
lies before map_start:
51f39 btrfs: Use right extent length when inserting overlap extent map.

[BUG]
When existing extent map's start is before map_start,
the em->len will be minus, which will corrupt the extent map and fail to
insert the new extent map.
This will happen when someone get a large extent map, but when it is
going to insert it into extent map tree, some one has already commit
some write and split the huge extent into small parts.

[REPRODUCER]
It is very easy to tiger using filebench with randomrw personality.
It is about 100% to reproduce when using 8G preallocated file in 60s
randonrw test.

[FIX]
This patch can now handle any existing extent position.
Since it does not directly use existing->start, now it will find the
previous and next extent around map_start.
So the old existing->start < map_start bug will never happen again.

[ENHANCE]
This patch will insert the best fitted extent map into extent map tree,
other than the oldest [map_start, map_start + sectorsize) or the
relatively newer but not perfect [map_start, existing->start).

The patch will first search existing extent that does not intersects with
the desired map range [map_start, map_start + len).
The existing extent will be either before or behind map_start, and based
on the existing extent, we can find out the previous and next extent
around map_start.

So the best fitted extent would be [prev->end, next->start).
For prev or next is not found, em->start would be prev->end and em->end
wold be next->start.

With this patch, the fragment in extent map tree should be reduced much
more than the 51f39 commit and reduce an unneeded extent map tree search.
Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

fs/btrfs/inode.c

@@ -6249,21 +6249,60 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	goto out_fail;
 }
 
+/* Find next extent map of a given extent map, caller needs to ensure locks */
+static struct extent_map *next_extent_map(struct extent_map *em)
+{
+	struct rb_node *next;
+
+	next = rb_next(&em->rb_node);
+	if (!next)
+		return NULL;
+	return container_of(next, struct extent_map, rb_node);
+}
+
+static struct extent_map *prev_extent_map(struct extent_map *em)
+{
+	struct rb_node *prev;
+
+	prev = rb_prev(&em->rb_node);
+	if (!prev)
+		return NULL;
+	return container_of(prev, struct extent_map, rb_node);
+}
+
 /* helper for btfs_get_extent.  Given an existing extent in the tree,
+ * the existing extent is the nearest extent to map_start,
  * and an extent that you want to insert, deal with overlap and insert
- * the new extent into the tree.
+ * the best fitted new extent into the tree.
  */
 static int merge_extent_mapping(struct extent_map_tree *em_tree,
 				struct extent_map *existing,
 				struct extent_map *em,
 				u64 map_start)
 {
+	struct extent_map *prev;
+	struct extent_map *next;
+	u64 start;
+	u64 end;
 	u64 start_diff;
 
 	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
-	start_diff = map_start - em->start;
-	em->start = map_start;
-	em->len = existing->start - em->start;
+
+	if (existing->start > map_start) {
+		next = existing;
+		prev = prev_extent_map(next);
+	} else {
+		prev = existing;
+		next = next_extent_map(prev);
+	}
+
+	start = prev ? extent_map_end(prev) : em->start;
+	start = max_t(u64, start, em->start);
+	end = next ? next->start : extent_map_end(em);
+	end = min_t(u64, end, extent_map_end(em));
+	start_diff = start - em->start;
+	em->start = start;
+	em->len = end - start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
 	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 		em->block_start += start_diff;
@@ -6540,16 +6579,17 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 
 		ret = 0;
 
-		existing = lookup_extent_mapping(em_tree, start, len);
-		if (existing && (existing->start > start ||
-		    existing->start + existing->len <= start)) {
-			free_extent_map(existing);
-			existing = NULL;
-		}
-		if (!existing) {
-			existing = lookup_extent_mapping(em_tree, em->start,
-							 em->len);
-			if (existing) {
+		existing = search_extent_mapping(em_tree, start, len);
+		/*
+		 * existing will always be non-NULL, since there must be
+		 * extent causing the -EEXIST.
+		 */
+		if (start >= extent_map_end(existing) ||
+		    start + len <= existing->start) {
+			/*
+			 * The existing extent map is the one nearest to
+			 * the [start, start + len) range which overlaps
+			 */
 			err = merge_extent_mapping(em_tree, existing,
 						   em, start);
 			free_extent_map(existing);
@@ -6557,11 +6597,6 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 				free_extent_map(em);
 				em = NULL;
 			}
-			} else {
-				err = -EIO;
-				free_extent_map(em);
-				em = NULL;
-			}
 		} else {
 			free_extent_map(em);
 			em = existing;