1 files changed, 364 insertions, 338 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7dd7552f53a4..39da9db35278 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -18,6 +18,8 @@
 #include "compression.h"
 #include "qgroup.h"
 #include "inode-map.h"
+#include "block-group.h"
+#include "space-info.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -167,6 +169,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 
+		set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
 		clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		root->log_start_pid = current->pid;
 	}
@@ -193,6 +196,9 @@ static int join_running_log_trans(struct btrfs_root *root)
 {
 	int ret = -ENOENT;
 
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state))
+		return ret;
+
 	mutex_lock(&root->log_mutex);
 	if (root->log_root) {
 		ret = 0;
@@ -311,7 +317,7 @@ static int process_one_buffer(struct btrfs_root *log,
 	}
 
 	if (wc->pin)
-		ret = btrfs_pin_extent_for_log_replay(fs_info, eb->start,
+		ret = btrfs_pin_extent_for_log_replay(wc->trans, eb->start,
 						      eb->len);
 
 	if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) {
@@ -503,13 +509,8 @@ insert:
 			 */
 			if (S_ISREG(btrfs_inode_mode(eb, src_item)) &&
 			    S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) &&
-			    ino_size != 0) {
-				struct btrfs_map_token token;
-
-				btrfs_init_map_token(&token, dst_eb);
-				btrfs_set_token_inode_size(dst_eb, dst_item,
-							   ino_size, &token);
-			}
+			    ino_size != 0)
+				btrfs_set_inode_size(dst_eb, dst_item, ino_size);
 			goto no_copy;
 		}
 
@@ -553,13 +554,9 @@ no_copy:
 static noinline struct inode *read_one_inode(struct btrfs_root *root,
 					     u64 objectid)
 {
-	struct btrfs_key key;
 	struct inode *inode;
 
-	key.objectid = objectid;
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.offset = 0;
-	inode = btrfs_iget(root->fs_info->sb, &key, root);
+	inode = btrfs_iget(root->fs_info->sb, objectid, root);
 	if (IS_ERR(inode))
 		inode = NULL;
 	return inode;
@@ -830,6 +827,11 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			goto out;
 	}
 
+	ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start,
+						extent_end - start);
+	if (ret)
+		goto out;
+
 	inode_add_bytes(inode, nbytes);
 update_inode:
 	ret = btrfs_update_inode(trans, root, inode);
@@ -2659,18 +2661,39 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 	return ret;
 }
 
+/*
+ * Correctly adjust the reserved bytes occupied by a log tree extent buffer
+ */
+static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
+{
+	struct btrfs_block_group *cache;
+
+	cache = btrfs_lookup_block_group(fs_info, start);
+	if (!cache) {
+		btrfs_err(fs_info, "unable to find block group for %llu", start);
+		return;
+	}
+
+	spin_lock(&cache->space_info->lock);
+	spin_lock(&cache->lock);
+	cache->reserved -= fs_info->nodesize;
+	cache->space_info->bytes_reserved -= fs_info->nodesize;
+	spin_unlock(&cache->lock);
+	spin_unlock(&cache->space_info->lock);
+
+	btrfs_put_block_group(cache);
+}
+
 static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct btrfs_path *path, int *level,
 				   struct walk_control *wc)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 root_owner;
 	u64 bytenr;
 	u64 ptr_gen;
 	struct extent_buffer *next;
 	struct extent_buffer *cur;
-	struct extent_buffer *parent;
 	u32 blocksize;
 	int ret = 0;
 
@@ -2690,9 +2713,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
 		blocksize = fs_info->nodesize;
 
-		parent = path->nodes[*level];
-		root_owner = btrfs_header_owner(parent);
-
 		next = btrfs_find_create_tree_block(fs_info, bytenr);
 		if (IS_ERR(next))
 			return PTR_ERR(next);
@@ -2720,18 +2740,16 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
+					ret = btrfs_pin_reserved_extent(trans,
+							bytenr, blocksize);
+					if (ret) {
+						free_extent_buffer(next);
+						return ret;
+					}
 				} else {
 					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 						clear_extent_buffer_dirty(next);
-				}
-
-				WARN_ON(root_owner !=
-					BTRFS_TREE_LOG_OBJECTID);
-				ret = btrfs_pin_reserved_extent(fs_info,
-							bytenr, blocksize);
-				if (ret) {
-					free_extent_buffer(next);
-					return ret;
+					unaccount_log_buffer(fs_info, bytenr);
 				}
 			}
 			free_extent_buffer(next);
@@ -2762,7 +2780,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 				 struct walk_control *wc)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 root_owner;
 	int i;
 	int slot;
 	int ret;
@@ -2775,13 +2792,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 			WARN_ON(*level == 0);
 			return 0;
 		} else {
-			struct extent_buffer *parent;
-			if (path->nodes[*level] == root->node)
-				parent = path->nodes[*level];
-			else
-				parent = path->nodes[*level + 1];
-
-			root_owner = btrfs_header_owner(parent);
 			ret = wc->process_func(root, path->nodes[*level], wc,
 				 btrfs_header_generation(path->nodes[*level]),
 				 *level);
@@ -2799,17 +2809,18 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
+					ret = btrfs_pin_reserved_extent(trans,
+						     path->nodes[*level]->start,
+						     path->nodes[*level]->len);
+					if (ret)
+						return ret;
 				} else {
 					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 						clear_extent_buffer_dirty(next);
-				}
 
-				WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
-				ret = btrfs_pin_reserved_extent(fs_info,
-						path->nodes[*level]->start,
-						path->nodes[*level]->len);
-				if (ret)
-					return ret;
+					unaccount_log_buffer(fs_info,
+						path->nodes[*level]->start);
+				}
 			}
 			free_extent_buffer(path->nodes[*level]);
 			path->nodes[*level] = NULL;
@@ -2880,15 +2891,15 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 				btrfs_clean_tree_block(next);
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
+				ret = btrfs_pin_reserved_extent(trans,
+						next->start, next->len);
+				if (ret)
+					goto out;
 			} else {
 				if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 					clear_extent_buffer_dirty(next);
+				unaccount_log_buffer(fs_info, next->start);
 			}
-
-			ret = btrfs_pin_reserved_extent(fs_info, next->start,
-							next->len);
-			if (ret)
-				goto out;
 		}
 	}
 
@@ -3105,29 +3116,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	btrfs_init_log_ctx(&root_log_ctx, NULL);
 
 	mutex_lock(&log_root_tree->log_mutex);
-	atomic_inc(&log_root_tree->log_batch);
-	atomic_inc(&log_root_tree->log_writers);
 
 	index2 = log_root_tree->log_transid % 2;
 	list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
 	root_log_ctx.log_transid = log_root_tree->log_transid;
 
-	mutex_unlock(&log_root_tree->log_mutex);
-
-	mutex_lock(&log_root_tree->log_mutex);
-
 	/*
 	 * Now we are safe to update the log_root_tree because we're under the
 	 * log_mutex, and we're a current writer so we're holding the commit
 	 * open until we drop the log_mutex.
 	 */
 	ret = update_log_root(trans, log, &new_root_item);
-
-	if (atomic_dec_and_test(&log_root_tree->log_writers)) {
-		/* atomic_dec_and_test implies a barrier */
-		cond_wake_up_nomb(&log_root_tree->log_writer_wait);
-	}
-
 	if (ret) {
 		if (!list_empty(&root_log_ctx.list))
 			list_del_init(&root_log_ctx.list);
@@ -3173,8 +3172,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 				root_log_ctx.log_transid - 1);
 	}
 
-	wait_for_writer(log_root_tree);
-
 	/*
 	 * now that we've moved on to the tree of log tree roots,
 	 * check the full commit flag again
@@ -3283,8 +3280,8 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 
 	clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
 			  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
-	free_extent_buffer(log->node);
-	kfree(log);
+	extent_io_tree_release(&log->log_csum_range);
+	btrfs_put_root(log);
 }
 
 /*
@@ -3296,6 +3293,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root)
 	if (root->log_root) {
 		free_log_tree(trans, root->log_root);
 		root->log_root = NULL;
+		clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
 	}
 	return 0;
 }
@@ -3451,11 +3449,13 @@ fail:
 	btrfs_free_path(path);
 out_unlock:
 	mutex_unlock(&dir->log_mutex);
-	if (ret == -ENOSPC) {
+	if (err == -ENOSPC) {
 		btrfs_set_log_full_commit(trans);
-		ret = 0;
-	} else if (ret < 0)
-		btrfs_abort_transaction(trans, ret);
+		err = 0;
+	} else if (err < 0 && err != -ENOENT) {
+		/* ENOENT can be returned if the entry hasn't been fsynced yet */
+		btrfs_abort_transaction(trans, err);
+	}
 
 	btrfs_end_log_trans(root);
 
@@ -3801,8 +3801,7 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans,
 
 		found_key.offset = 0;
 		found_key.type = 0;
-		ret = btrfs_bin_search(path->nodes[0], &found_key, 0,
-				       &start_slot);
+		ret = btrfs_bin_search(path->nodes[0], &found_key, &start_slot);
 		if (ret < 0)
 			break;
 
@@ -3838,44 +3837,41 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 		 * just to say 'this inode exists' and a logging
 		 * to say 'update this inode with these values'
 		 */
-		btrfs_set_token_inode_generation(leaf, item, 0, &token);
-		btrfs_set_token_inode_size(leaf, item, logged_isize, &token);
+		btrfs_set_token_inode_generation(&token, item, 0);
+		btrfs_set_token_inode_size(&token, item, logged_isize);
 	} else {
-		btrfs_set_token_inode_generation(leaf, item,
-						 BTRFS_I(inode)->generation,
-						 &token);
-		btrfs_set_token_inode_size(leaf, item, inode->i_size, &token);
-	}
-
-	btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
-	btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
-	btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
-	btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
-
-	btrfs_set_token_timespec_sec(leaf, &item->atime,
-				     inode->i_atime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, &item->atime,
-				      inode->i_atime.tv_nsec, &token);
-
-	btrfs_set_token_timespec_sec(leaf, &item->mtime,
-				     inode->i_mtime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, &item->mtime,
-				      inode->i_mtime.tv_nsec, &token);
-
-	btrfs_set_token_timespec_sec(leaf, &item->ctime,
-				     inode->i_ctime.tv_sec, &token);
-	btrfs_set_token_timespec_nsec(leaf, &item->ctime,
-				      inode->i_ctime.tv_nsec, &token);
-
-	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
-				     &token);
-
-	btrfs_set_token_inode_sequence(leaf, item,
-				       inode_peek_iversion(inode), &token);
-	btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
-	btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
-	btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
-	btrfs_set_token_inode_block_group(leaf, item, 0, &token);
+		btrfs_set_token_inode_generation(&token, item,
+						 BTRFS_I(inode)->generation);
+		btrfs_set_token_inode_size(&token, item, inode->i_size);
+	}
+
+	btrfs_set_token_inode_uid(&token, item, i_uid_read(inode));
+	btrfs_set_token_inode_gid(&token, item, i_gid_read(inode));
+	btrfs_set_token_inode_mode(&token, item, inode->i_mode);
+	btrfs_set_token_inode_nlink(&token, item, inode->i_nlink);
+
+	btrfs_set_token_timespec_sec(&token, &item->atime,
+				     inode->i_atime.tv_sec);
+	btrfs_set_token_timespec_nsec(&token, &item->atime,
+				      inode->i_atime.tv_nsec);
+
+	btrfs_set_token_timespec_sec(&token, &item->mtime,
+				     inode->i_mtime.tv_sec);
+	btrfs_set_token_timespec_nsec(&token, &item->mtime,
+				      inode->i_mtime.tv_nsec);
+
+	btrfs_set_token_timespec_sec(&token, &item->ctime,
+				     inode->i_ctime.tv_sec);
+	btrfs_set_token_timespec_nsec(&token, &item->ctime,
+				      inode->i_ctime.tv_nsec);
+
+	btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode));
+
+	btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode));
+	btrfs_set_token_inode_transid(&token, item, trans->transid);
+	btrfs_set_token_inode_rdev(&token, item, inode->i_rdev);
+	btrfs_set_token_inode_flags(&token, item, BTRFS_I(inode)->flags);
+	btrfs_set_token_inode_block_group(&token, item, 0);
 }
 
 static int log_inode_item(struct btrfs_trans_handle *trans,
@@ -3898,12 +3894,33 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 }
 
 static int log_csums(struct btrfs_trans_handle *trans,
+		     struct btrfs_inode *inode,
 		     struct btrfs_root *log_root,
 		     struct btrfs_ordered_sum *sums)
 {
+	const u64 lock_end = sums->bytenr + sums->len - 1;
+	struct extent_state *cached_state = NULL;
 	int ret;
 
 	/*
+	 * If this inode was not used for reflink operations in the current
+	 * transaction with new extents, then do the fast path, no need to
+	 * worry about logging checksum items with overlapping ranges.
+	 */
+	if (inode->last_reflink_trans < trans->transid)
+		return btrfs_csum_file_blocks(trans, log_root, sums);
+
+	/*
+	 * Serialize logging for checksums. This is to avoid racing with the
+	 * same checksum being logged by another task that is logging another
+	 * file which happens to refer to the same extent as well. Such races
+	 * can leave checksum items in the log with overlapping ranges.
+	 */
+	ret = lock_extent_bits(&log_root->log_csum_range, sums->bytenr,
+			       lock_end, &cached_state);
+	if (ret)
+		return ret;
+	/*
 	 * Due to extent cloning, we might have logged a csum item that covers a
 	 * subrange of a cloned extent, and later we can end up logging a csum
 	 * item for a larger subrange of the same extent or the entire range.
@@ -3913,10 +3930,13 @@ static int log_csums(struct btrfs_trans_handle *trans,
 	 * trim and adjust) any existing csum items in the log for this range.
 	 */
 	ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len);
-	if (ret)
-		return ret;
+	if (!ret)
+		ret = btrfs_csum_file_blocks(trans, log_root, sums);
 
-	return btrfs_csum_file_blocks(trans, log_root, sums);
+	unlock_extent_cached(&log_root->log_csum_range, sums->bytenr, lock_end,
+			     &cached_state);
+
+	return ret;
 }
 
 static noinline int copy_items(struct btrfs_trans_handle *trans,
@@ -4018,11 +4038,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						fs_info->csum_root,
 						ds + cs, ds + cs + cl - 1,
 						&ordered_sums, 0);
-				if (ret) {
-					btrfs_release_path(dst_path);
-					kfree(ins_data);
-					return ret;
-				}
+				if (ret)
+					break;
 			}
 		}
 	}
@@ -4035,13 +4052,12 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	 * we have to do this after the loop above to avoid changing the
 	 * log tree while trying to change the log tree.
 	 */
-	ret = 0;
 	while (!list_empty(&ordered_sums)) {
 		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = log_csums(trans, log, sums);
+			ret = log_csums(trans, inode, log, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4100,7 +4116,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = log_csums(trans, log_root, sums);
+			ret = log_csums(trans, inode, log_root, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4128,7 +4144,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
-	ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
+	ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
 				   em->start + em->len, NULL, 0, 1,
 				   sizeof(*fi), &extent_inserted);
 	if (ret)
@@ -4149,43 +4165,35 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	fi = btrfs_item_ptr(leaf, path->slots[0],
 			    struct btrfs_file_extent_item);
 
-	btrfs_set_token_file_extent_generation(leaf, fi, trans->transid,
-					       &token);
+	btrfs_set_token_file_extent_generation(&token, fi, trans->transid);
 	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
-		btrfs_set_token_file_extent_type(leaf, fi,
-						 BTRFS_FILE_EXTENT_PREALLOC,
-						 &token);
+		btrfs_set_token_file_extent_type(&token, fi,
+						 BTRFS_FILE_EXTENT_PREALLOC);
 	else
-		btrfs_set_token_file_extent_type(leaf, fi,
-						 BTRFS_FILE_EXTENT_REG,
-						 &token);
+		btrfs_set_token_file_extent_type(&token, fi,
+						 BTRFS_FILE_EXTENT_REG);
 
 	block_len = max(em->block_len, em->orig_block_len);
 	if (em->compress_type != BTRFS_COMPRESS_NONE) {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
-							em->block_start,
-							&token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-							   &token);
+		btrfs_set_token_file_extent_disk_bytenr(&token, fi,
+							em->block_start);
+		btrfs_set_token_file_extent_disk_num_bytes(&token, fi, block_len);
 	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+		btrfs_set_token_file_extent_disk_bytenr(&token, fi,
 							em->block_start -
-							extent_offset, &token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-							   &token);
+							extent_offset);
+		btrfs_set_token_file_extent_disk_num_bytes(&token, fi, block_len);
 	} else {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
-							   &token);
-	}
-
-	btrfs_set_token_file_extent_offset(leaf, fi, extent_offset, &token);
-	btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
-	btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
-	btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
-						&token);
-	btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
-	btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
+		btrfs_set_token_file_extent_disk_bytenr(&token, fi, 0);
+		btrfs_set_token_file_extent_disk_num_bytes(&token, fi, 0);
+	}
+
+	btrfs_set_token_file_extent_offset(&token, fi, extent_offset);
+	btrfs_set_token_file_extent_num_bytes(&token, fi, em->len);
+	btrfs_set_token_file_extent_ram_bytes(&token, fi, em->ram_bytes);
+	btrfs_set_token_file_extent_compression(&token, fi, em->compress_type);
+	btrfs_set_token_file_extent_encryption(&token, fi, 0);
+	btrfs_set_token_file_extent_other_encoding(&token, fi, 0);
 	btrfs_mark_buffer_dirty(leaf);
 
 	btrfs_release_path(path);
@@ -4211,6 +4219,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	const u64 ino = btrfs_ino(inode);
 	struct btrfs_path *dst_path = NULL;
 	bool dropped_extents = false;
+	u64 truncate_offset = i_size;
+	struct extent_buffer *leaf;
+	int slot;
 	int ins_nr = 0;
 	int start_slot;
 	int ret;
@@ -4225,9 +4236,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 
+	/*
+	 * We must check if there is a prealloc extent that starts before the
+	 * i_size and crosses the i_size boundary. This is to ensure later we
+	 * truncate down to the end of that extent and not to the i_size, as
+	 * otherwise we end up losing part of the prealloc extent after a log
+	 * replay and with an implicit hole if there is another prealloc extent
+	 * that starts at an offset beyond i_size.
+	 */
+	ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
+	if (ret < 0)
+		goto out;
+
+	if (ret == 0) {
+		struct btrfs_file_extent_item *ei;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, ei) ==
+		    BTRFS_FILE_EXTENT_PREALLOC) {
+			u64 extent_end;
+
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, ei);
+
+			if (extent_end > i_size)
+				truncate_offset = extent_end;
+		}
+	} else {
+		ret = 0;
+	}
+
 	while (true) {
-		struct extent_buffer *leaf = path->nodes[0];
-		int slot = path->slots[0];
+		leaf = path->nodes[0];
+		slot = path->slots[0];
 
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
@@ -4265,7 +4310,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				ret = btrfs_truncate_inode_items(trans,
 							 root->log_root,
 							 &inode->vfs_inode,
-							 i_size,
+							 truncate_offset,
 							 BTRFS_EXTENT_DATA_KEY);
 			} while (ret == -EAGAIN);
 			if (ret)
@@ -4284,12 +4329,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			}
 		}
 	}
-	if (ins_nr > 0) {
+	if (ins_nr > 0)
 		ret = copy_items(trans, inode, dst_path, path,
 				 start_slot, ins_nr, 1, 0);
-		if (ret > 0)
-			ret = 0;
-	}
 out:
 	btrfs_release_path(path);
 	btrfs_free_path(dst_path);
@@ -4539,9 +4581,7 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 		return ret;
 
 	while (true) {
-		struct btrfs_file_extent_item *extent;
 		struct extent_buffer *leaf = path->nodes[0];
-		u64 len;
 
 		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
 			ret = btrfs_next_leaf(root, path);
@@ -4590,18 +4630,7 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 			leaf = path->nodes[0];
 		}
 
-		extent = btrfs_item_ptr(leaf, path->slots[0],
-					struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(leaf, extent);
-			prev_extent_end = ALIGN(key.offset + len,
-						fs_info->sectorsize);
-		} else {
-			len = btrfs_file_extent_num_bytes(leaf, extent);
-			prev_extent_end = key.offset + len;
-		}
-
+		prev_extent_end = btrfs_file_extent_end(path);
 		path->slots[0]++;
 		cond_resched();
 	}
@@ -4796,10 +4825,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 
 		btrfs_release_path(path);
 
-		key.objectid = ino;
-		key.type = BTRFS_INODE_ITEM_KEY;
-		key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &key, root);
+		inode = btrfs_iget(fs_info->sb, ino, root);
 		/*
 		 * If the other inode that had a conflicting dir entry was
 		 * deleted in the current transaction, we need to log its parent
@@ -4808,8 +4834,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 		if (IS_ERR(inode)) {
 			ret = PTR_ERR(inode);
 			if (ret == -ENOENT) {
-				key.objectid = parent;
-				inode = btrfs_iget(fs_info->sb, &key, root);
+				inode = btrfs_iget(fs_info->sb, parent, root);
 				if (IS_ERR(inode)) {
 					ret = PTR_ERR(inode);
 				} else {
@@ -4938,6 +4963,138 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static int copy_inode_items_to_log(struct btrfs_trans_handle *trans,
+				   struct btrfs_inode *inode,
+				   struct btrfs_key *min_key,
+				   const struct btrfs_key *max_key,
+				   struct btrfs_path *path,
+				   struct btrfs_path *dst_path,
+				   const u64 logged_isize,
+				   const bool recursive_logging,
+				   const int inode_only,
+				   struct btrfs_log_ctx *ctx,
+				   bool *need_log_inode_item)
+{
+	struct btrfs_root *root = inode->root;
+	int ins_start_slot = 0;
+	int ins_nr = 0;
+	int ret;
+
+	while (1) {
+		ret = btrfs_search_forward(root, min_key, path, trans->transid);
+		if (ret < 0)
+			return ret;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+again:
+		/* Note, ins_nr might be > 0 here, cleanup outside the loop */
+		if (min_key->objectid != max_key->objectid)
+			break;
+		if (min_key->type > max_key->type)
+			break;
+
+		if (min_key->type == BTRFS_INODE_ITEM_KEY)
+			*need_log_inode_item = false;
+
+		if ((min_key->type == BTRFS_INODE_REF_KEY ||
+		     min_key->type == BTRFS_INODE_EXTREF_KEY) &&
+		    inode->generation == trans->transid &&
+		    !recursive_logging) {
+			u64 other_ino = 0;
+			u64 other_parent = 0;
+
+			ret = btrfs_check_ref_name_override(path->nodes[0],
+					path->slots[0], min_key, inode,
+					&other_ino, &other_parent);
+			if (ret < 0) {
+				return ret;
+			} else if (ret > 0 && ctx &&
+				   other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
+				if (ins_nr > 0) {
+					ins_nr++;
+				} else {
+					ins_nr = 1;
+					ins_start_slot = path->slots[0];
+				}
+				ret = copy_items(trans, inode, dst_path, path,
+						 ins_start_slot, ins_nr,
+						 inode_only, logged_isize);
+				if (ret < 0)
+					return ret;
+				ins_nr = 0;
+
+				ret = log_conflicting_inodes(trans, root, path,
+						ctx, other_ino, other_parent);
+				if (ret)
+					return ret;
+				btrfs_release_path(path);
+				goto next_key;
+			}
+		}
+
+		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
+		if (min_key->type == BTRFS_XATTR_ITEM_KEY) {
+			if (ins_nr == 0)
+				goto next_slot;
+			ret = copy_items(trans, inode, dst_path, path,
+					 ins_start_slot,
+					 ins_nr, inode_only, logged_isize);
+			if (ret < 0)
+				return ret;
+			ins_nr = 0;
+			goto next_slot;
+		}
+
+		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
+			ins_nr++;
+			goto next_slot;
+		} else if (!ins_nr) {
+			ins_start_slot = path->slots[0];
+			ins_nr = 1;
+			goto next_slot;
+		}
+
+		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
+				 ins_nr, inode_only, logged_isize);
+		if (ret < 0)
+			return ret;
+		ins_nr = 1;
+		ins_start_slot = path->slots[0];
+next_slot:
+		path->slots[0]++;
+		if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
+			btrfs_item_key_to_cpu(path->nodes[0], min_key,
+					      path->slots[0]);
+			goto again;
+		}
+		if (ins_nr) {
+			ret = copy_items(trans, inode, dst_path, path,
+					 ins_start_slot, ins_nr, inode_only,
+					 logged_isize);
+			if (ret < 0)
+				return ret;
+			ins_nr = 0;
+		}
+		btrfs_release_path(path);
+next_key:
+		if (min_key->offset < (u64)-1) {
+			min_key->offset++;
+		} else if (min_key->type < max_key->type) {
+			min_key->type++;
+			min_key->offset = 0;
+		} else {
+			break;
+		}
+	}
+	if (ins_nr)
+		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
+				 ins_nr, inode_only, logged_isize);
+
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4959,17 +5116,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			   const loff_t end,
 			   struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	struct btrfs_path *dst_path;
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
 	int err = 0;
-	int ret;
-	int nritems;
-	int ins_start_slot = 0;
-	int ins_nr;
+	int ret = 0;
 	bool fast_search = false;
 	u64 ino = btrfs_ino(inode);
 	struct extent_map_tree *em_tree = &inode->extent_tree;
@@ -5005,15 +5158,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	max_key.offset = (u64)-1;
 
 	/*
-	 * Only run delayed items if we are a dir or a new file.
-	 * Otherwise commit the delayed inode only, which is needed in
-	 * order for the log replay code to mark inodes for link count
-	 * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items).
+	 * Only run delayed items if we are a directory. We want to make sure
+	 * all directory indexes hit the fs/subvolume tree so we can find them
+	 * and figure out which index ranges have to be logged.
+	 *
+	 * Otherwise commit the delayed inode only if the full sync flag is set,
+	 * as we want to make sure an up to date version is in the subvolume
+	 * tree so copy_inode_items_to_log() / copy_items() can find it and copy
+	 * it to the log tree. For a non full sync, we always log the inode item
+	 * based on the in-memory struct btrfs_inode which is always up to date.
 	 */
-	if (S_ISDIR(inode->vfs_inode.i_mode) ||
-	    inode->generation > fs_info->last_trans_committed)
+	if (S_ISDIR(inode->vfs_inode.i_mode))
 		ret = btrfs_commit_inode_delayed_items(trans, inode);
-	else
+	else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
 		ret = btrfs_commit_inode_delayed_inode(inode);
 
 	if (ret) {
@@ -5100,139 +5257,12 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		goto out_unlock;
 	}
 
-	while (1) {
-		ins_nr = 0;
-		ret = btrfs_search_forward(root, &min_key,
-					   path, trans->transid);
-		if (ret < 0) {
-			err = ret;
-			goto out_unlock;
-		}
-		if (ret != 0)
-			break;
-again:
-		/* note, ins_nr might be > 0 here, cleanup outside the loop */
-		if (min_key.objectid != ino)
-			break;
-		if (min_key.type > max_key.type)
-			break;
-
-		if (min_key.type == BTRFS_INODE_ITEM_KEY)
-			need_log_inode_item = false;
-
-		if ((min_key.type == BTRFS_INODE_REF_KEY ||
-		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
-		    inode->generation == trans->transid &&
-		    !recursive_logging) {
-			u64 other_ino = 0;
-			u64 other_parent = 0;
-
-			ret = btrfs_check_ref_name_override(path->nodes[0],
-					path->slots[0], &min_key, inode,
-					&other_ino, &other_parent);
-			if (ret < 0) {
-				err = ret;
-				goto out_unlock;
-			} else if (ret > 0 && ctx &&
-				   other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
-				if (ins_nr > 0) {
-					ins_nr++;
-				} else {
-					ins_nr = 1;
-					ins_start_slot = path->slots[0];
-				}
-				ret = copy_items(trans, inode, dst_path, path,
-						 ins_start_slot,
-						 ins_nr, inode_only,
-						 logged_isize);
-				if (ret < 0) {
-					err = ret;
-					goto out_unlock;
-				}
-				ins_nr = 0;
-
-				err = log_conflicting_inodes(trans, root, path,
-						ctx, other_ino, other_parent);
-				if (err)
-					goto out_unlock;
-				btrfs_release_path(path);
-				goto next_key;
-			}
-		}
-
-		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
-		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
-			if (ins_nr == 0)
-				goto next_slot;
-			ret = copy_items(trans, inode, dst_path, path,
-					 ins_start_slot,
-					 ins_nr, inode_only, logged_isize);
-			if (ret < 0) {
-				err = ret;
-				goto out_unlock;
-			}
-			ins_nr = 0;
-			goto next_slot;
-		}
-
-		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
-			ins_nr++;
-			goto next_slot;
-		} else if (!ins_nr) {
-			ins_start_slot = path->slots[0];
-			ins_nr = 1;
-			goto next_slot;
-		}
-
-		ret = copy_items(trans, inode, dst_path, path,
-				 ins_start_slot, ins_nr, inode_only,
-				 logged_isize);
-		if (ret < 0) {
-			err = ret;
-			goto out_unlock;
-		}
-		ins_nr = 1;
-		ins_start_slot = path->slots[0];
-next_slot:
-
-		nritems = btrfs_header_nritems(path->nodes[0]);
-		path->slots[0]++;
-		if (path->slots[0] < nritems) {
-			btrfs_item_key_to_cpu(path->nodes[0], &min_key,
-					      path->slots[0]);
-			goto again;
-		}
-		if (ins_nr) {
-			ret = copy_items(trans, inode, dst_path, path,
-					 ins_start_slot,
-					 ins_nr, inode_only, logged_isize);
-			if (ret < 0) {
-				err = ret;
-				goto out_unlock;
-			}
-			ins_nr = 0;
-		}
-		btrfs_release_path(path);
-next_key:
-		if (min_key.offset < (u64)-1) {
-			min_key.offset++;
-		} else if (min_key.type < max_key.type) {
-			min_key.type++;
-			min_key.offset = 0;
-		} else {
-			break;
-		}
-	}
-	if (ins_nr) {
-		ret = copy_items(trans, inode, dst_path, path,
-				 ins_start_slot, ins_nr, inode_only,
-				 logged_isize);
-		if (ret < 0) {
-			err = ret;
-			goto out_unlock;
-		}
-		ins_nr = 0;
-	}
+	err = copy_inode_items_to_log(trans, inode, &min_key, &max_key,
+				      path, dst_path, logged_isize,
+				      recursive_logging, inode_only, ctx,
+				      &need_log_inode_item);
+	if (err)
+		goto out_unlock;
 
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
@@ -5546,7 +5576,7 @@ process_leaf:
 				continue;
 
 			btrfs_release_path(path);
-			di_inode = btrfs_iget(fs_info->sb, &di_key, root);
+			di_inode = btrfs_iget(fs_info->sb, di_key.objectid, root);
 			if (IS_ERR(di_inode)) {
 				ret = PTR_ERR(di_inode);
 				goto next_dir_inode;
@@ -5672,7 +5702,8 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				cur_offset = item_size;
 			}
 
-			dir_inode = btrfs_iget(fs_info->sb, &inode_key, root);
+			dir_inode = btrfs_iget(fs_info->sb, inode_key.objectid,
+					       root);
 			/*
 			 * If the parent inode was deleted, return an error to
 			 * fallback to a transaction commit. This is to prevent
@@ -5739,14 +5770,17 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
 		int slot = path->slots[0];
 		struct btrfs_key search_key;
 		struct inode *inode;
+		u64 ino;
 		int ret = 0;
 
 		btrfs_release_path(path);
 
+		ino = found_key.offset;
+
 		search_key.objectid = found_key.offset;
 		search_key.type = BTRFS_INODE_ITEM_KEY;
 		search_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &search_key, root);
+		inode = btrfs_iget(fs_info->sb, ino, root);
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
@@ -6091,7 +6125,6 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
-	struct btrfs_key tmp_key;
 	struct btrfs_root *log;
 	struct btrfs_fs_info *fs_info = log_root_tree->fs_info;
 	struct walk_control wc = {
@@ -6145,7 +6178,7 @@ again:
 		if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 			break;
 
-		log = btrfs_read_fs_root(log_root_tree, &found_key);
+		log = btrfs_read_tree_root(log_root_tree, &found_key);
 		if (IS_ERR(log)) {
 			ret = PTR_ERR(log);
 			btrfs_handle_fs_error(fs_info, ret,
@@ -6153,11 +6186,8 @@ again:
 			goto error;
 		}
 
-		tmp_key.objectid = found_key.offset;
-		tmp_key.type = BTRFS_ROOT_ITEM_KEY;
-		tmp_key.offset = (u64)-1;
-
-		wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
+		wc.replay_dest = btrfs_get_fs_root(fs_info, found_key.offset,
+						   true);
 		if (IS_ERR(wc.replay_dest)) {
 			ret = PTR_ERR(wc.replay_dest);
 
@@ -6173,12 +6203,10 @@ again:
 			 * each subsequent pass.
 			 */
 			if (ret == -ENOENT)
-				ret = btrfs_pin_extent_for_log_replay(fs_info,
+				ret = btrfs_pin_extent_for_log_replay(trans,
 							log->node->start,
 							log->node->len);
-			free_extent_buffer(log->node);
-			free_extent_buffer(log->commit_root);
-			kfree(log);
+			btrfs_put_root(log);
 
 			if (!ret)
 				goto next;
@@ -6214,9 +6242,8 @@ again:
 		}
 
 		wc.replay_dest->log_root = NULL;
-		free_extent_buffer(log->node);
-		free_extent_buffer(log->commit_root);
-		kfree(log);
+		btrfs_put_root(wc.replay_dest);
+		btrfs_put_root(log);
 
 		if (ret)
 			goto error;
@@ -6247,10 +6274,9 @@ next:
 	if (ret)
 		return ret;
 
-	free_extent_buffer(log_root_tree->node);
 	log_root_tree->log_root = NULL;
 	clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags);
-	kfree(log_root_tree);
+	btrfs_put_root(log_root_tree);
 
 	return 0;
 error: