1 files changed, 253 insertions, 111 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d81035b7ea7d..1d49694e6ae3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2492,9 +2492,6 @@ void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	/* Also free its reserved qgroup space */
-	btrfs_qgroup_free_delayed_ref(fs_info, head->qgroup_ref_root,
-				      head->qgroup_reserved);
 	btrfs_delayed_refs_rsv_release(fs_info, nr_items);
 }
 
@@ -3013,8 +3010,7 @@ again:
 	}
 
 	if (run_all) {
-		if (!list_empty(&trans->new_bgs))
-			btrfs_create_pending_block_groups(trans);
+		btrfs_create_pending_block_groups(trans);
 
 		spin_lock(&delayed_refs->lock);
 		node = rb_first_cached(&delayed_refs->href_root);
@@ -4280,10 +4276,14 @@ commit_trans:
 				/*
 				 * The cleaner kthread might still be doing iput
 				 * operations. Wait for it to finish so that
-				 * more space is released.
+				 * more space is released.  We don't need to
+				 * explicitly run the delayed iputs here because
+				 * the commit_transaction would have woken up
+				 * the cleaner.
 				 */
-				mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
-				mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+				ret = btrfs_wait_on_delayed_iputs(fs_info);
+				if (ret)
+					return ret;
 				goto again;
 			} else {
 				btrfs_end_transaction(trans);
@@ -4396,7 +4396,6 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
 static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
 			      struct btrfs_space_info *sinfo, int force)
 {
-	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	u64 bytes_used = btrfs_space_info_used(sinfo, false);
 	u64 thresh;
 
@@ -4404,14 +4403,6 @@ static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
 		return 1;
 
 	/*
-	 * We need to take into account the global rsv because for all intents
-	 * and purposes it's used space.  Don't worry about locking the
-	 * global_rsv, it doesn't change except when the transaction commits.
-	 */
-	if (sinfo->flags & BTRFS_BLOCK_GROUP_METADATA)
-		bytes_used += calc_global_rsv_need_space(global_rsv);
-
-	/*
 	 * in limited mode, we want to have some free space up to
 	 * about 1% of the FS size.
 	 */
@@ -4741,7 +4732,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
 	u64 delalloc_bytes;
-	u64 max_reclaim;
+	u64 async_pages;
 	u64 items;
 	long time_left;
 	unsigned long nr_pages;
@@ -4766,25 +4757,36 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
 
 	loops = 0;
 	while (delalloc_bytes && loops < 3) {
-		max_reclaim = min(delalloc_bytes, to_reclaim);
-		nr_pages = max_reclaim >> PAGE_SHIFT;
+		nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
+
+		/*
+		 * Triggers inode writeback for up to nr_pages. This will invoke
+		 * ->writepages callback and trigger delalloc filling
+		 *  (btrfs_run_delalloc_range()).
+		 */
 		btrfs_writeback_inodes_sb_nr(fs_info, nr_pages, items);
+
 		/*
-		 * We need to wait for the async pages to actually start before
-		 * we do anything.
+		 * We need to wait for the compressed pages to start before
+		 * we continue.
 		 */
-		max_reclaim = atomic_read(&fs_info->async_delalloc_pages);
-		if (!max_reclaim)
+		async_pages = atomic_read(&fs_info->async_delalloc_pages);
+		if (!async_pages)
 			goto skip_async;
 
-		if (max_reclaim <= nr_pages)
-			max_reclaim = 0;
+		/*
+		 * Calculate how many compressed pages we want to be written
+		 * before we continue. I.e if there are more async pages than we
+		 * require wait_event will wait until nr_pages are written.
+		 */
+		if (async_pages <= nr_pages)
+			async_pages = 0;
 		else
-			max_reclaim -= nr_pages;
+			async_pages -= nr_pages;
 
 		wait_event(fs_info->async_submit_wait,
 			   atomic_read(&fs_info->async_delalloc_pages) <=
-			   (int)max_reclaim);
+			   (int)async_pages);
 skip_async:
 		spin_lock(&space_info->lock);
 		if (list_empty(&space_info->tickets) &&
@@ -4808,6 +4810,7 @@ skip_async:
 }
 
 struct reserve_ticket {
+	u64 orig_bytes;
 	u64 bytes;
 	int error;
 	struct list_head list;
@@ -4851,10 +4854,19 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	if (!bytes_needed)
 		return 0;
 
-	/* See if there is enough pinned space to make this reservation */
-	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes_needed,
-				   BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
+	trans = btrfs_join_transaction(fs_info->extent_root);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	/*
+	 * See if there is enough pinned space to make this reservation, or if
+	 * we have block groups that are going to be freed, allowing us to
+	 * possibly do a chunk allocation the next loop through.
+	 */
+	if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags) ||
+	    __percpu_counter_compare(&space_info->total_bytes_pinned,
+				     bytes_needed,
+				     BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
 		goto commit;
 
 	/*
@@ -4862,7 +4874,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	 * this reservation.
 	 */
 	if (space_info != delayed_rsv->space_info)
-		return -ENOSPC;
+		goto enospc;
 
 	spin_lock(&delayed_rsv->lock);
 	reclaim_bytes += delayed_rsv->reserved;
@@ -4877,16 +4889,14 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 
 	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
 				   bytes_needed,
-				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0) {
-		return -ENOSPC;
-	}
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0)
+		goto enospc;
 
 commit:
-	trans = btrfs_join_transaction(fs_info->extent_root);
-	if (IS_ERR(trans))
-		return -ENOSPC;
-
 	return btrfs_commit_transaction(trans);
+enospc:
+	btrfs_end_transaction(trans);
+	return -ENOSPC;
 }
 
 /*
@@ -4939,6 +4949,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		btrfs_end_transaction(trans);
 		break;
 	case ALLOC_CHUNK:
+	case ALLOC_CHUNK_FORCE:
 		trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
 			ret = PTR_ERR(trans);
@@ -4946,7 +4957,8 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		}
 		ret = do_chunk_alloc(trans,
 				     btrfs_metadata_alloc_profile(fs_info),
-				     CHUNK_ALLOC_NO_FORCE);
+				     (state == ALLOC_CHUNK) ?
+				      CHUNK_ALLOC_NO_FORCE : CHUNK_ALLOC_FORCE);
 		btrfs_end_transaction(trans);
 		if (ret > 0 || ret == -ENOSPC)
 			ret = 0;
@@ -4957,9 +4969,8 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 		 * bunch of pinned space, so make sure we run the iputs before
 		 * we do our pinned bytes check below.
 		 */
-		mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
 		btrfs_run_delayed_iputs(fs_info);
-		mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+		btrfs_wait_on_delayed_iputs(fs_info);
 
 		ret = may_commit_transaction(fs_info, space_info);
 		break;
@@ -5030,7 +5041,7 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 		!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
 }
 
-static void wake_all_tickets(struct list_head *head)
+static bool wake_all_tickets(struct list_head *head)
 {
 	struct reserve_ticket *ticket;
 
@@ -5039,7 +5050,10 @@ static void wake_all_tickets(struct list_head *head)
 		list_del_init(&ticket->list);
 		ticket->error = -ENOSPC;
 		wake_up(&ticket->wait);
+		if (ticket->bytes != ticket->orig_bytes)
+			return true;
 	}
+	return false;
 }
 
 /*
@@ -5091,11 +5105,28 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 				commit_cycles--;
 		}
 
+		/*
+		 * We don't want to force a chunk allocation until we've tried
+		 * pretty hard to reclaim space.  Think of the case where we
+		 * freed up a bunch of space and so have a lot of pinned space
+		 * to reclaim.  We would rather use that than possibly create a
+		 * underutilized metadata chunk.  So if this is our first run
+		 * through the flushing state machine skip ALLOC_CHUNK_FORCE and
+		 * commit the transaction.  If nothing has changed the next go
+		 * around then we can force a chunk allocation.
+		 */
+		if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles)
+			flush_state++;
+
 		if (flush_state > COMMIT_TRANS) {
 			commit_cycles++;
 			if (commit_cycles > 2) {
-				wake_all_tickets(&space_info->tickets);
-				space_info->flush = 0;
+				if (wake_all_tickets(&space_info->tickets)) {
+					flush_state = FLUSH_DELAYED_ITEMS_NR;
+					commit_cycles--;
+				} else {
+					space_info->flush = 0;
+				}
 			} else {
 				flush_state = FLUSH_DELAYED_ITEMS_NR;
 			}
@@ -5109,12 +5140,18 @@ void btrfs_init_async_reclaim_work(struct work_struct *work)
 	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
 }
 
+static const enum btrfs_flush_state priority_flush_states[] = {
+	FLUSH_DELAYED_ITEMS_NR,
+	FLUSH_DELAYED_ITEMS,
+	ALLOC_CHUNK,
+};
+
 static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 					    struct btrfs_space_info *space_info,
 					    struct reserve_ticket *ticket)
 {
 	u64 to_reclaim;
-	int flush_state = FLUSH_DELAYED_ITEMS_NR;
+	int flush_state;
 
 	spin_lock(&space_info->lock);
 	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
@@ -5125,8 +5162,10 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	}
 	spin_unlock(&space_info->lock);
 
+	flush_state = 0;
 	do {
-		flush_space(fs_info, space_info, to_reclaim, flush_state);
+		flush_space(fs_info, space_info, to_reclaim,
+			    priority_flush_states[flush_state]);
 		flush_state++;
 		spin_lock(&space_info->lock);
 		if (ticket->bytes == 0) {
@@ -5134,23 +5173,16 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 			return;
 		}
 		spin_unlock(&space_info->lock);
-
-		/*
-		 * Priority flushers can't wait on delalloc without
-		 * deadlocking.
-		 */
-		if (flush_state == FLUSH_DELALLOC ||
-		    flush_state == FLUSH_DELALLOC_WAIT)
-			flush_state = ALLOC_CHUNK;
-	} while (flush_state < COMMIT_TRANS);
+	} while (flush_state < ARRAY_SIZE(priority_flush_states));
 }
 
 static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 			       struct btrfs_space_info *space_info,
-			       struct reserve_ticket *ticket, u64 orig_bytes)
+			       struct reserve_ticket *ticket)
 
 {
 	DEFINE_WAIT(wait);
+	u64 reclaim_bytes = 0;
 	int ret = 0;
 
 	spin_lock(&space_info->lock);
@@ -5171,14 +5203,12 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 		ret = ticket->error;
 	if (!list_empty(&ticket->list))
 		list_del_init(&ticket->list);
-	if (ticket->bytes && ticket->bytes < orig_bytes) {
-		u64 num_bytes = orig_bytes - ticket->bytes;
-		update_bytes_may_use(space_info, -num_bytes);
-		trace_btrfs_space_reservation(fs_info, "space_info",
-					      space_info->flags, num_bytes, 0);
-	}
+	if (ticket->bytes && ticket->bytes < ticket->orig_bytes)
+		reclaim_bytes = ticket->orig_bytes - ticket->bytes;
 	spin_unlock(&space_info->lock);
 
+	if (reclaim_bytes)
+		space_info_add_old_bytes(fs_info, space_info, reclaim_bytes);
 	return ret;
 }
 
@@ -5204,6 +5234,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 {
 	struct reserve_ticket ticket;
 	u64 used;
+	u64 reclaim_bytes = 0;
 	int ret = 0;
 
 	ASSERT(orig_bytes);
@@ -5239,6 +5270,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 * the list and we will do our own flushing further down.
 	 */
 	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
+		ticket.orig_bytes = orig_bytes;
 		ticket.bytes = orig_bytes;
 		ticket.error = 0;
 		init_waitqueue_head(&ticket.wait);
@@ -5279,25 +5311,21 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 		return ret;
 
 	if (flush == BTRFS_RESERVE_FLUSH_ALL)
-		return wait_reserve_ticket(fs_info, space_info, &ticket,
-					   orig_bytes);
+		return wait_reserve_ticket(fs_info, space_info, &ticket);
 
 	ret = 0;
 	priority_reclaim_metadata_space(fs_info, space_info, &ticket);
 	spin_lock(&space_info->lock);
 	if (ticket.bytes) {
-		if (ticket.bytes < orig_bytes) {
-			u64 num_bytes = orig_bytes - ticket.bytes;
-			update_bytes_may_use(space_info, -num_bytes);
-			trace_btrfs_space_reservation(fs_info, "space_info",
-						      space_info->flags,
-						      num_bytes, 0);
-
-		}
+		if (ticket.bytes < orig_bytes)
+			reclaim_bytes = orig_bytes - ticket.bytes;
 		list_del_init(&ticket.list);
 		ret = -ENOSPC;
 	}
 	spin_unlock(&space_info->lock);
+
+	if (reclaim_bytes)
+		space_info_add_old_bytes(fs_info, space_info, reclaim_bytes);
 	ASSERT(list_empty(&ticket.list));
 	return ret;
 }
@@ -5775,6 +5803,21 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	return ret;
 }
 
+static void calc_refill_bytes(struct btrfs_block_rsv *block_rsv,
+				u64 *metadata_bytes, u64 *qgroup_bytes)
+{
+	*metadata_bytes = 0;
+	*qgroup_bytes = 0;
+
+	spin_lock(&block_rsv->lock);
+	if (block_rsv->reserved < block_rsv->size)
+		*metadata_bytes = block_rsv->size - block_rsv->reserved;
+	if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+		*qgroup_bytes = block_rsv->qgroup_rsv_size -
+			block_rsv->qgroup_rsv_reserved;
+	spin_unlock(&block_rsv->lock);
+}
+
 /**
  * btrfs_inode_rsv_refill - refill the inode block rsv.
  * @inode - the inode we are refilling.
@@ -5790,25 +5833,42 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
-	u64 num_bytes = 0;
-	u64 qgroup_num_bytes = 0;
+	u64 num_bytes, last = 0;
+	u64 qgroup_num_bytes;
 	int ret = -ENOSPC;
 
-	spin_lock(&block_rsv->lock);
-	if (block_rsv->reserved < block_rsv->size)
-		num_bytes = block_rsv->size - block_rsv->reserved;
-	if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
-		qgroup_num_bytes = block_rsv->qgroup_rsv_size -
-				   block_rsv->qgroup_rsv_reserved;
-	spin_unlock(&block_rsv->lock);
-
+	calc_refill_bytes(block_rsv, &num_bytes, &qgroup_num_bytes);
 	if (num_bytes == 0)
 		return 0;
 
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
-	if (ret)
-		return ret;
-	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+	do {
+		ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes,
+							 true);
+		if (ret)
+			return ret;
+		ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+		if (ret) {
+			btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+			last = num_bytes;
+			/*
+			 * If we are fragmented we can end up with a lot of
+			 * outstanding extents which will make our size be much
+			 * larger than our reserved amount.
+			 *
+			 * If the reservation happens here, it might be very
+			 * big though not needed in the end, if the delalloc
+			 * flushing happens.
+			 *
+			 * If this is the case try and do the reserve again.
+			 */
+			if (flush == BTRFS_RESERVE_FLUSH_ALL)
+				calc_refill_bytes(block_rsv, &num_bytes,
+						   &qgroup_num_bytes);
+			if (num_bytes == 0)
+				return 0;
+		}
+	} while (ret && last != num_bytes);
+
 	if (!ret) {
 		block_rsv_add_bytes(block_rsv, num_bytes, false);
 		trace_btrfs_space_reservation(root->fs_info, "delalloc",
@@ -5818,8 +5878,7 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
 		spin_lock(&block_rsv->lock);
 		block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
 		spin_unlock(&block_rsv->lock);
-	} else
-		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+	}
 	return ret;
 }
 
@@ -8066,6 +8125,15 @@ loop:
 	return ret;
 }
 
+#define DUMP_BLOCK_RSV(fs_info, rsv_name)				\
+do {									\
+	struct btrfs_block_rsv *__rsv = &(fs_info)->rsv_name;		\
+	spin_lock(&__rsv->lock);					\
+	btrfs_info(fs_info, #rsv_name ": size %llu reserved %llu",	\
+		   __rsv->size, __rsv->reserved);			\
+	spin_unlock(&__rsv->lock);					\
+} while (0)
+
 static void dump_space_info(struct btrfs_fs_info *fs_info,
 			    struct btrfs_space_info *info, u64 bytes,
 			    int dump_block_groups)
@@ -8085,6 +8153,12 @@ static void dump_space_info(struct btrfs_fs_info *fs_info,
 		info->bytes_readonly);
 	spin_unlock(&info->lock);
 
+	DUMP_BLOCK_RSV(fs_info, global_block_rsv);
+	DUMP_BLOCK_RSV(fs_info, trans_block_rsv);
+	DUMP_BLOCK_RSV(fs_info, chunk_block_rsv);
+	DUMP_BLOCK_RSV(fs_info, delayed_block_rsv);
+	DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv);
+
 	if (!dump_block_groups)
 		return;
 
@@ -8492,7 +8566,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	clean_tree_block(fs_info, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
-	btrfs_set_lock_blocking(buf);
+	btrfs_set_lock_blocking_write(buf);
 	set_extent_buffer_uptodate(buf);
 
 	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
@@ -8690,6 +8764,8 @@ struct walk_control {
 	u64 refs[BTRFS_MAX_LEVEL];
 	u64 flags[BTRFS_MAX_LEVEL];
 	struct btrfs_key update_progress;
+	struct btrfs_key drop_progress;
+	int drop_level;
 	int stage;
 	int level;
 	int shared_level;
@@ -8697,6 +8773,7 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
+	int restarted;
 };
 
 #define DROP_REFERENCE	1
@@ -8860,6 +8937,33 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 }
 
 /*
+ * This is used to verify a ref exists for this root to deal with a bug where we
+ * would have a drop_progress key that hadn't been updated properly.
+ */
+static int check_ref_exists(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root, u64 bytenr, u64 parent,
+			    int level)
+{
+	struct btrfs_path *path;
+	struct btrfs_extent_inline_ref *iref;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = lookup_extent_backref(trans, path, &iref, bytenr,
+				    root->fs_info->nodesize, parent,
+				    root->root_key.objectid, level, 0);
+	btrfs_free_path(path);
+	if (ret == -ENOENT)
+		return 0;
+	if (ret < 0)
+		return ret;
+	return 1;
+}
+
+/*
  * helper to process tree block pointer.
  *
  * when wc->stage == DROP_REFERENCE, this function checks
@@ -8917,7 +9021,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 		reada = 1;
 	}
 	btrfs_tree_lock(next);
-	btrfs_set_lock_blocking(next);
+	btrfs_set_lock_blocking_write(next);
 
 	ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
@@ -8977,7 +9081,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 			return -EIO;
 		}
 		btrfs_tree_lock(next);
-		btrfs_set_lock_blocking(next);
+		btrfs_set_lock_blocking_write(next);
 	}
 
 	level--;
@@ -9014,6 +9118,23 @@ skip:
 		}
 
 		/*
+		 * If we had a drop_progress we need to verify the refs are set
+		 * as expected.  If we find our ref then we know that from here
+		 * on out everything should be correct, and we can clear the
+		 * ->restarted flag.
+		 */
+		if (wc->restarted) {
+			ret = check_ref_exists(trans, root, bytenr, parent,
+					       level - 1);
+			if (ret < 0)
+				goto out_unlock;
+			if (ret == 0)
+				goto no_delete;
+			ret = 0;
+			wc->restarted = 0;
+		}
+
+		/*
 		 * Reloc tree doesn't contribute to qgroup numbers, and we have
 		 * already accounted them at merge time (replace_path),
 		 * thus we could skip expensive subtree trace here.
@@ -9028,13 +9149,23 @@ skip:
 					     ret);
 			}
 		}
+
+		/*
+		 * We need to update the next key in our walk control so we can
+		 * update the drop_progress key accordingly.  We don't care if
+		 * find_next_key doesn't find a key because that means we're at
+		 * the end and are going to clean up now.
+		 */
+		wc->drop_level = level;
+		find_next_key(path, level, &wc->drop_progress);
+
 		ret = btrfs_free_extent(trans, root, bytenr, fs_info->nodesize,
 					parent, root->root_key.objectid,
 					level - 1, 0);
 		if (ret)
 			goto out_unlock;
 	}
-
+no_delete:
 	*lookup_info = 1;
 	ret = 1;
 
@@ -9089,7 +9220,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 		if (!path->locks[level]) {
 			BUG_ON(level == 0);
 			btrfs_tree_lock(eb);
-			btrfs_set_lock_blocking(eb);
+			btrfs_set_lock_blocking_write(eb);
 			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 
 			ret = btrfs_lookup_extent_info(trans, fs_info,
@@ -9131,7 +9262,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 		if (!path->locks[level] &&
 		    btrfs_header_generation(eb) == trans->transid) {
 			btrfs_tree_lock(eb);
-			btrfs_set_lock_blocking(eb);
+			btrfs_set_lock_blocking_write(eb);
 			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 		}
 		clean_tree_block(fs_info, eb);
@@ -9298,7 +9429,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
 		level = btrfs_header_level(root->node);
 		path->nodes[level] = btrfs_lock_root_node(root);
-		btrfs_set_lock_blocking(path->nodes[level]);
+		btrfs_set_lock_blocking_write(path->nodes[level]);
 		path->slots[level] = 0;
 		path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 		memset(&wc->update_progress, 0,
@@ -9328,7 +9459,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		level = btrfs_header_level(root->node);
 		while (1) {
 			btrfs_tree_lock(path->nodes[level]);
-			btrfs_set_lock_blocking(path->nodes[level]);
+			btrfs_set_lock_blocking_write(path->nodes[level]);
 			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 
 			ret = btrfs_lookup_extent_info(trans, fs_info,
@@ -9351,6 +9482,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		}
 	}
 
+	wc->restarted = test_bit(BTRFS_ROOT_DEAD_TREE, &root->state);
 	wc->level = level;
 	wc->shared_level = -1;
 	wc->stage = DROP_REFERENCE;
@@ -9378,12 +9510,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		}
 
 		if (wc->stage == DROP_REFERENCE) {
-			level = wc->level;
-			btrfs_node_key(path->nodes[level],
-				       &root_item->drop_progress,
-				       path->slots[level]);
-			root_item->drop_level = level;
+			wc->drop_level = wc->level;
+			btrfs_node_key_to_cpu(path->nodes[wc->drop_level],
+					      &wc->drop_progress,
+					      path->slots[wc->drop_level]);
 		}
+		btrfs_cpu_key_to_disk(&root_item->drop_progress,
+				      &wc->drop_progress);
+		root_item->drop_level = wc->drop_level;
 
 		BUG_ON(wc->level == 0);
 		if (btrfs_should_end_transaction(trans) ||
@@ -9595,6 +9729,7 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
+	u64 sinfo_used;
 	u64 min_allocable_bytes;
 	int ret = -ENOSPC;
 
@@ -9621,9 +9756,10 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 
 	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
 		    cache->bytes_super - btrfs_block_group_used(&cache->item);
+	sinfo_used = btrfs_space_info_used(sinfo, true);
 
-	if (btrfs_space_info_used(sinfo, true) + num_bytes +
-	    min_allocable_bytes <= sinfo->total_bytes) {
+	if (sinfo_used + num_bytes + min_allocable_bytes <=
+	    sinfo->total_bytes) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
@@ -9632,6 +9768,15 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 out:
 	spin_unlock(&cache->lock);
 	spin_unlock(&sinfo->lock);
+	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
+		btrfs_info(cache->fs_info,
+			"unable to make block group %llu ro",
+			cache->key.objectid);
+		btrfs_info(cache->fs_info,
+			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
+			sinfo_used, num_bytes, min_allocable_bytes);
+		dump_space_info(cache->fs_info, cache->space_info, 0, 0);
+	}
 	return ret;
 }
 
@@ -10781,13 +10926,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	}
 
 	spin_lock(&trans->transaction->dirty_bgs_lock);
-	if (!list_empty(&block_group->dirty_list)) {
-		WARN_ON(1);
-	}
-	if (!list_empty(&block_group->io_list)) {
-		WARN_ON(1);
-	}
+	WARN_ON(!list_empty(&block_group->dirty_list));
+	WARN_ON(!list_empty(&block_group->io_list));
 	spin_unlock(&trans->transaction->dirty_bgs_lock);
+
 	btrfs_remove_free_space_cache(block_group);
 
 	spin_lock(&block_group->space_info->lock);