1 files changed, 122 insertions, 72 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 378d9103a207..c0a8f7d92acc 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -23,7 +23,7 @@
 #include "extent-tree.h"
 
 #ifdef CONFIG_BTRFS_DEBUG
-int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group)
+int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 
@@ -40,9 +40,9 @@ int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group)
  *
  * Should be called with balance_lock held
  */
-static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
+static u64 get_restripe_target(const struct btrfs_fs_info *fs_info, u64 flags)
 {
-	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+	const struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 	u64 target = 0;
 
 	if (!bctl)
@@ -173,43 +173,41 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
 	}
 }
 
+static int btrfs_bg_start_cmp(const struct rb_node *new,
+			      const struct rb_node *exist)
+{
+	const struct btrfs_block_group *new_bg =
+		rb_entry(new, struct btrfs_block_group, cache_node);
+	const struct btrfs_block_group *exist_bg =
+		rb_entry(exist, struct btrfs_block_group, cache_node);
+
+	if (new_bg->start < exist_bg->start)
+		return -1;
+	if (new_bg->start > exist_bg->start)
+		return 1;
+	return 0;
+}
+
 /*
  * This adds the block group to the fs_info rb tree for the block group cache
  */
 static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
 				       struct btrfs_block_group *block_group)
 {
-	struct rb_node **p;
-	struct rb_node *parent = NULL;
-	struct btrfs_block_group *cache;
-	bool leftmost = true;
+	struct rb_node *exist;
+	int ret = 0;
 
 	ASSERT(block_group->length != 0);
 
 	write_lock(&info->block_group_cache_lock);
-	p = &info->block_group_cache_tree.rb_root.rb_node;
-
-	while (*p) {
-		parent = *p;
-		cache = rb_entry(parent, struct btrfs_block_group, cache_node);
-		if (block_group->start < cache->start) {
-			p = &(*p)->rb_left;
-		} else if (block_group->start > cache->start) {
-			p = &(*p)->rb_right;
-			leftmost = false;
-		} else {
-			write_unlock(&info->block_group_cache_lock);
-			return -EEXIST;
-		}
-	}
-
-	rb_link_node(&block_group->cache_node, parent, p);
-	rb_insert_color_cached(&block_group->cache_node,
-			       &info->block_group_cache_tree, leftmost);
 
+	exist = rb_find_add_cached(&block_group->cache_node,
+			&info->block_group_cache_tree, btrfs_bg_start_cmp);
+	if (exist)
+		ret = -EEXIST;
 	write_unlock(&info->block_group_cache_lock);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -418,7 +416,7 @@ struct btrfs_caching_control *btrfs_get_caching_control(
 	return ctl;
 }
 
-void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
+static void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
 {
 	if (refcount_dec_and_test(&ctl->count))
 		kfree(ctl);
@@ -1022,6 +1020,13 @@ static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags)
 	}
 }
 
+static struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info)
+{
+	if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))
+		return fs_info->block_group_root;
+	return btrfs_extent_root(fs_info, 0);
+}
+
 static int remove_block_group_item(struct btrfs_trans_handle *trans,
 				   struct btrfs_path *path,
 				   struct btrfs_block_group *block_group)
@@ -1063,7 +1068,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	bool remove_rsv = false;
 
 	block_group = btrfs_lookup_block_group(fs_info, map->start);
-	BUG_ON(!block_group);
+	if (!block_group)
+		return -ENOENT;
+
 	BUG_ON(!block_group->ro);
 
 	trace_btrfs_remove_block_group(block_group);
@@ -1214,8 +1221,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	block_group->space_info->total_bytes -= block_group->length;
 	block_group->space_info->bytes_readonly -=
 		(block_group->length - block_group->zone_unusable);
-	block_group->space_info->bytes_zone_unusable -=
-		block_group->zone_unusable;
+	btrfs_space_info_update_bytes_zone_unusable(block_group->space_info,
+						    -block_group->zone_unusable);
 	block_group->space_info->disk_total -= block_group->length * factor;
 
 	spin_unlock(&block_group->space_info->lock);
@@ -1387,7 +1394,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 		if (btrfs_is_zoned(cache->fs_info)) {
 			/* Migrate zone_unusable bytes to readonly */
 			sinfo->bytes_readonly += cache->zone_unusable;
-			sinfo->bytes_zone_unusable -= cache->zone_unusable;
+			btrfs_space_info_update_bytes_zone_unusable(sinfo, -cache->zone_unusable);
 			cache->zone_unusable = 0;
 		}
 		cache->ro++;
@@ -1405,9 +1412,9 @@ out:
 }
 
 static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group *bg)
+				 const struct btrfs_block_group *bg)
 {
-	struct btrfs_fs_info *fs_info = bg->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_transaction *prev_trans = NULL;
 	const u64 start = bg->start;
 	const u64 end = start + bg->length - 1;
@@ -1429,7 +1436,7 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	 * group in pinned_extents before we were able to clear the whole block
 	 * group range from pinned_extents. This means that task can lookup for
 	 * the block group after we unpinned it from pinned_extents and removed
-	 * it, leading to a BUG_ON() at unpin_extent_range().
+	 * it, leading to an error at unpin_extent_range().
 	 */
 	mutex_lock(&fs_info->unused_bg_unpin_mutex);
 	if (prev_trans) {
@@ -1522,6 +1529,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 * outstanding allocations in this block group.  We do
 			 * the ro check in case balance is currently acting on
 			 * this block group.
+			 *
+			 * Also bail out if this is the only block group for its
+			 * type, because otherwise we would lose profile
+			 * information from fs_info->avail_*_alloc_bits and the
+			 * next block group of this type would be created with a
+			 * "single" profile (even if we're in a raid fs) because
+			 * fs_info->avail_*_alloc_bits would be 0.
 			 */
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
@@ -1550,7 +1564,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * needing to allocate extents from the block group.
 		 */
 		used = btrfs_space_info_used(space_info, true);
-		if (space_info->total_bytes - block_group->length < used) {
+		if (space_info->total_bytes - block_group->length < used &&
+		    block_group->zone_unusable < block_group->length) {
 			/*
 			 * Add a reference for the list, compensate for the ref
 			 * drop under the "next" label for the
@@ -1627,8 +1642,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
 
-		btrfs_space_info_update_bytes_pinned(fs_info, space_info,
-						     -block_group->pinned);
+		btrfs_space_info_update_bytes_pinned(space_info, -block_group->pinned);
 		space_info->bytes_readonly += block_group->pinned;
 		block_group->pinned = 0;
 
@@ -1738,33 +1752,30 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a,
 	return bg1->used > bg2->used;
 }
 
-static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info)
+static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_is_zoned(fs_info))
 		return btrfs_zoned_should_reclaim(fs_info);
 	return true;
 }
 
-static bool should_reclaim_block_group(struct btrfs_block_group *bg, u64 bytes_freed)
+static bool should_reclaim_block_group(const struct btrfs_block_group *bg, u64 bytes_freed)
 {
-	const struct btrfs_space_info *space_info = bg->space_info;
-	const int reclaim_thresh = READ_ONCE(space_info->bg_reclaim_threshold);
+	const int thresh_pct = btrfs_calc_reclaim_threshold(bg->space_info);
+	u64 thresh_bytes = mult_perc(bg->length, thresh_pct);
 	const u64 new_val = bg->used;
 	const u64 old_val = new_val + bytes_freed;
-	u64 thresh;
 
-	if (reclaim_thresh == 0)
+	if (thresh_bytes == 0)
 		return false;
 
-	thresh = mult_perc(bg->length, reclaim_thresh);
-
 	/*
 	 * If we were below the threshold before don't reclaim, we are likely a
 	 * brand new block group and we don't want to relocate new block groups.
 	 */
-	if (old_val < thresh)
+	if (old_val < thresh_bytes)
 		return false;
-	if (new_val >= thresh)
+	if (new_val >= thresh_bytes)
 		return false;
 	return true;
 }
@@ -1775,6 +1786,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
 	struct btrfs_block_group *bg;
 	struct btrfs_space_info *space_info;
+	LIST_HEAD(retry_list);
 
 	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
 		return;
@@ -1811,6 +1823,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 	list_sort(NULL, &fs_info->reclaim_bgs, reclaim_bgs_cmp);
 	while (!list_empty(&fs_info->reclaim_bgs)) {
 		u64 zone_unusable;
+		u64 reclaimed;
 		int ret = 0;
 
 		bg = list_first_entry(&fs_info->reclaim_bgs,
@@ -1824,6 +1837,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		/* Don't race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 
+		spin_lock(&space_info->lock);
 		spin_lock(&bg->lock);
 		if (bg->reserved || bg->pinned || bg->ro) {
 			/*
@@ -1833,6 +1847,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 			 * this block group.
 			 */
 			spin_unlock(&bg->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
@@ -1851,6 +1866,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 			if (!btrfs_test_opt(fs_info, DISCARD_ASYNC))
 				btrfs_mark_bg_unused(bg);
 			spin_unlock(&bg->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 
@@ -1867,10 +1883,12 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		 */
 		if (!should_reclaim_block_group(bg, bg->length)) {
 			spin_unlock(&bg->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
 		spin_unlock(&bg->lock);
+		spin_unlock(&space_info->lock);
 
 		/*
 		 * Get out fast, in case we're read-only or unmounting the
@@ -1903,16 +1921,39 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 				div64_u64(bg->used * 100, bg->length),
 				div64_u64(zone_unusable * 100, bg->length));
 		trace_btrfs_reclaim_block_group(bg);
+		reclaimed = bg->used;
 		ret = btrfs_relocate_chunk(fs_info, bg->start);
 		if (ret) {
 			btrfs_dec_block_group_ro(bg);
 			btrfs_err(fs_info, "error relocating chunk %llu",
 				  bg->start);
+			reclaimed = 0;
+			spin_lock(&space_info->lock);
+			space_info->reclaim_errors++;
+			if (READ_ONCE(space_info->periodic_reclaim))
+				space_info->periodic_reclaim_ready = false;
+			spin_unlock(&space_info->lock);
 		}
+		spin_lock(&space_info->lock);
+		space_info->reclaim_count++;
+		space_info->reclaim_bytes += reclaimed;
+		spin_unlock(&space_info->lock);
 
 next:
-		if (ret)
-			btrfs_mark_bg_to_reclaim(bg);
+		if (ret && !READ_ONCE(space_info->periodic_reclaim)) {
+			/* Refcount held by the reclaim_bgs list after splice. */
+			spin_lock(&fs_info->unused_bgs_lock);
+			/*
+			 * This block group might be added to the unused list
+			 * during the above process. Move it back to the
+			 * reclaim list otherwise.
+			 */
+			if (list_empty(&bg->bg_list)) {
+				btrfs_get_block_group(bg);
+				list_add_tail(&bg->bg_list, &retry_list);
+			}
+			spin_unlock(&fs_info->unused_bgs_lock);
+		}
 		btrfs_put_block_group(bg);
 
 		mutex_unlock(&fs_info->reclaim_bgs_lock);
@@ -1932,12 +1973,16 @@ next:
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 end:
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->reclaim_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	btrfs_exclop_finish(fs_info);
 	sb_end_write(fs_info->sb);
 }
 
 void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info)
 {
+	btrfs_reclaim_sweep(fs_info);
 	spin_lock(&fs_info->unused_bgs_lock);
 	if (!list_empty(&fs_info->reclaim_bgs))
 		queue_work(system_unbound_wq, &fs_info->reclaim_bgs_work);
@@ -1957,8 +2002,8 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
-static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
-			   struct btrfs_path *path)
+static int read_bg_from_eb(struct btrfs_fs_info *fs_info, const struct btrfs_key *key,
+			   const struct btrfs_path *path)
 {
 	struct btrfs_chunk_map *map;
 	struct btrfs_block_group_item bg;
@@ -2006,7 +2051,7 @@ out_free_map:
 
 static int find_first_block_group(struct btrfs_fs_info *fs_info,
 				  struct btrfs_path *path,
-				  struct btrfs_key *key)
+				  const struct btrfs_key *key)
 {
 	struct btrfs_root *root = btrfs_block_group_root(fs_info);
 	int ret;
@@ -2591,8 +2636,8 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans,
 }
 
 static int insert_dev_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_device *device, u64 chunk_offset,
-			    u64 start, u64 num_bytes)
+			     const struct btrfs_device *device, u64 chunk_offset,
+			     u64 start, u64 num_bytes)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_root *root = fs_info->dev_root;
@@ -2623,7 +2668,6 @@ static int insert_dev_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset);
 
 	btrfs_set_dev_extent_length(leaf, extent, num_bytes);
-	btrfs_mark_buffer_dirty(trans, leaf);
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -2748,7 +2792,7 @@ next:
 		 * uncompressed data size, because the compression is only done
 		 * when writeback triggered and we don't know how much space we
 		 * are actually going to need, so we reserve the uncompressed
-		 * size because the data may be uncompressible in the worst case.
+		 * size because the data may be incompressible in the worst case.
 		 */
 		if (ret == 0) {
 			bool used;
@@ -2768,7 +2812,7 @@ next:
  * For extent tree v2 we use the block_group_item->chunk_offset to point at our
  * global root id.  For v1 it's always set to BTRFS_FIRST_CHUNK_TREE_OBJECTID.
  */
-static u64 calculate_global_root_id(struct btrfs_fs_info *fs_info, u64 offset)
+static u64 calculate_global_root_id(const struct btrfs_fs_info *fs_info, u64 offset)
 {
 	u64 div = SZ_1G;
 	u64 index;
@@ -3008,9 +3052,10 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
 		if (btrfs_is_zoned(cache->fs_info)) {
 			/* Migrate zone_unusable bytes back */
 			cache->zone_unusable =
-				(cache->alloc_offset - cache->used) +
+				(cache->alloc_offset - cache->used - cache->pinned -
+				 cache->reserved) +
 				(cache->length - cache->zone_capacity);
-			sinfo->bytes_zone_unusable += cache->zone_unusable;
+			btrfs_space_info_update_bytes_zone_unusable(sinfo, cache->zone_unusable);
 			sinfo->bytes_readonly -= cache->zone_unusable;
 		}
 		num_bytes = cache->length - cache->reserved -
@@ -3072,7 +3117,6 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 						   cache->global_root_id);
 	btrfs_set_stack_block_group_flags(&bgi, cache->flags);
 	write_extent_buffer(leaf, &bgi, bi, sizeof(bgi));
-	btrfs_mark_buffer_dirty(trans, leaf);
 fail:
 	btrfs_release_path(path);
 	/*
@@ -3636,20 +3680,25 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		old_val += num_bytes;
 		cache->used = old_val;
 		cache->reserved -= num_bytes;
+		cache->reclaim_mark = 0;
 		space_info->bytes_reserved -= num_bytes;
 		space_info->bytes_used += num_bytes;
 		space_info->disk_used += num_bytes * factor;
+		if (READ_ONCE(space_info->periodic_reclaim))
+			btrfs_space_info_update_reclaimable(space_info, -num_bytes);
 		spin_unlock(&cache->lock);
 		spin_unlock(&space_info->lock);
 	} else {
 		old_val -= num_bytes;
 		cache->used = old_val;
 		cache->pinned += num_bytes;
-		btrfs_space_info_update_bytes_pinned(info, space_info, num_bytes);
+		btrfs_space_info_update_bytes_pinned(space_info, num_bytes);
 		space_info->bytes_used -= num_bytes;
 		space_info->disk_used -= num_bytes * factor;
-
-		reclaim = should_reclaim_block_group(cache, num_bytes);
+		if (READ_ONCE(space_info->periodic_reclaim))
+			btrfs_space_info_update_reclaimable(space_info, num_bytes);
+		else
+			reclaim = should_reclaim_block_group(cache, num_bytes);
 
 		spin_unlock(&cache->lock);
 		spin_unlock(&space_info->lock);
@@ -3725,8 +3774,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
 	space_info->bytes_reserved += num_bytes;
 	trace_btrfs_space_reservation(cache->fs_info, "space_info",
 				      space_info->flags, num_bytes, 1);
-	btrfs_space_info_update_bytes_may_use(cache->fs_info,
-					      space_info, -ram_bytes);
+	btrfs_space_info_update_bytes_may_use(space_info, -ram_bytes);
 	if (delalloc)
 		cache->delalloc_bytes += num_bytes;
 
@@ -3763,6 +3811,8 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
 	spin_lock(&cache->lock);
 	if (cache->ro)
 		space_info->bytes_readonly += num_bytes;
+	else if (btrfs_is_zoned(cache->fs_info))
+		space_info->bytes_zone_unusable += num_bytes;
 	cache->reserved -= num_bytes;
 	space_info->bytes_reserved -= num_bytes;
 	space_info->max_extent_size = 0;
@@ -3786,8 +3836,8 @@ static void force_metadata_allocation(struct btrfs_fs_info *info)
 	}
 }
 
-static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
-			      struct btrfs_space_info *sinfo, int force)
+static int should_alloc_chunk(const struct btrfs_fs_info *fs_info,
+			      const struct btrfs_space_info *sinfo, int force)
 {
 	u64 bytes_used = btrfs_space_info_used(sinfo, false);
 	u64 thresh;
@@ -4162,7 +4212,7 @@ out:
 	return ret;
 }
 
-static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
+static u64 get_profile_num_devs(const struct btrfs_fs_info *fs_info, u64 type)
 {
 	u64 num_dev;
 
@@ -4303,13 +4353,13 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 		spin_lock(&block_group->lock);
 		if (test_and_clear_bit(BLOCK_GROUP_FLAG_IREF,
 				       &block_group->runtime_flags)) {
-			struct inode *inode = block_group->inode;
+			struct btrfs_inode *inode = block_group->inode;
 
 			block_group->inode = NULL;
 			spin_unlock(&block_group->lock);
 
 			ASSERT(block_group->io_ctl.inode == NULL);
-			iput(inode);
+			iput(&inode->vfs_inode);
 		} else {
 			spin_unlock(&block_group->lock);
 		}
@@ -4566,7 +4616,7 @@ int btrfs_use_block_group_size_class(struct btrfs_block_group *bg,
 	return 0;
 }
 
-bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg)
+bool btrfs_block_group_should_use_size_class(const struct btrfs_block_group *bg)
 {
 	if (btrfs_is_zoned(bg->fs_info))
 		return false;