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

Pull btrfs changes from Chris Mason:
 "This is a pretty long stream of bug fixes and performance fixes.

  Qu Wenruo has replaced the btrfs async threads with regular kernel
  workqueues.  We'll keep an eye out for performance differences, but
  it's nice to be using more generic code for this.

  We still have some corruption fixes and other patches coming in for
  the merge window, but this batch is tested and ready to go"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (108 commits)
  Btrfs: fix a crash of clone with inline extents's split
  btrfs: fix uninit variable warning
  Btrfs: take into account total references when doing backref lookup
  Btrfs: part 2, fix incremental send's decision to delay a dir move/rename
  Btrfs: fix incremental send's decision to delay a dir move/rename
  Btrfs: remove unnecessary inode generation lookup in send
  Btrfs: fix race when updating existing ref head
  btrfs: Add trace for btrfs_workqueue alloc/destroy
  Btrfs: less fs tree lock contention when using autodefrag
  Btrfs: return EPERM when deleting a default subvolume
  Btrfs: add missing kfree in btrfs_destroy_workqueue
  Btrfs: cache extent states in defrag code path
  Btrfs: fix deadlock with nested trans handles
  Btrfs: fix possible empty list access when flushing the delalloc inodes
  Btrfs: split the global ordered extents mutex
  Btrfs: don't flush all delalloc inodes when we doesn't get s_umount lock
  Btrfs: reclaim delalloc metadata more aggressively
  Btrfs: remove unnecessary lock in may_commit_transaction()
  Btrfs: remove the unnecessary flush when preparing the pages
  Btrfs: just do dirty page flush for the inode with compression before direct IO
  ...

1 files changed, 98 insertions, 60 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7331a230e30b..e1ffb1e22898 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -591,7 +591,6 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 		clear_bit(EXTENT_FLAG_LOGGING, &flags);
 		modified = !list_empty(&em->list);
-		remove_extent_mapping(em_tree, em);
 		if (no_splits)
 			goto next;
 
@@ -622,8 +621,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->bdev = em->bdev;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
-			ret = add_extent_mapping(em_tree, split, modified);
-			BUG_ON(ret); /* Logic error */
+			replace_extent_mapping(em_tree, em, split, modified);
 			free_extent_map(split);
 			split = split2;
 			split2 = NULL;
@@ -661,12 +659,20 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 				split->orig_block_len = 0;
 			}
 
-			ret = add_extent_mapping(em_tree, split, modified);
-			BUG_ON(ret); /* Logic error */
+			if (extent_map_in_tree(em)) {
+				replace_extent_mapping(em_tree, em, split,
+						       modified);
+			} else {
+				ret = add_extent_mapping(em_tree, split,
+							 modified);
+				ASSERT(ret == 0); /* Logic error */
+			}
 			free_extent_map(split);
 			split = NULL;
 		}
 next:
+		if (extent_map_in_tree(em))
+			remove_extent_mapping(em_tree, em);
 		write_unlock(&em_tree->lock);
 
 		/* once for us */
@@ -720,7 +726,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	if (drop_cache)
 		btrfs_drop_extent_cache(inode, start, end - 1, 0);
 
-	if (start >= BTRFS_I(inode)->disk_i_size)
+	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
 		modify_tree = 0;
 
 	while (1) {
@@ -798,7 +804,10 @@ next_slot:
 		 */
 		if (start > key.offset && end < extent_end) {
 			BUG_ON(del_nr > 0);
-			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+				ret = -EINVAL;
+				break;
+			}
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = start;
@@ -841,7 +850,10 @@ next_slot:
 		 *      | -------- extent -------- |
 		 */
 		if (start <= key.offset && end < extent_end) {
-			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+				ret = -EINVAL;
+				break;
+			}
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = end;
@@ -864,7 +876,10 @@ next_slot:
 		 */
 		if (start > key.offset && end >= extent_end) {
 			BUG_ON(del_nr > 0);
-			BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+				ret = -EINVAL;
+				break;
+			}
 
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							start - key.offset);
@@ -938,34 +953,42 @@ next_slot:
 		 * Set path->slots[0] to first slot, so that after the delete
 		 * if items are move off from our leaf to its immediate left or
 		 * right neighbor leafs, we end up with a correct and adjusted
-		 * path->slots[0] for our insertion.
+		 * path->slots[0] for our insertion (if replace_extent != 0).
 		 */
 		path->slots[0] = del_slot;
 		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
 		if (ret)
 			btrfs_abort_transaction(trans, root, ret);
+	}
 
-		leaf = path->nodes[0];
-		/*
-		 * leaf eb has flag EXTENT_BUFFER_STALE if it was deleted (that
-		 * is, its contents got pushed to its neighbors), in which case
-		 * it means path->locks[0] == 0
-		 */
-		if (!ret && replace_extent && leafs_visited == 1 &&
-		    path->locks[0] &&
-		    btrfs_leaf_free_space(root, leaf) >=
-		    sizeof(struct btrfs_item) + extent_item_size) {
-
-			key.objectid = ino;
-			key.type = BTRFS_EXTENT_DATA_KEY;
-			key.offset = start;
-			setup_items_for_insert(root, path, &key,
-					       &extent_item_size,
-					       extent_item_size,
-					       sizeof(struct btrfs_item) +
-					       extent_item_size, 1);
-			*key_inserted = 1;
+	leaf = path->nodes[0];
+	/*
+	 * If btrfs_del_items() was called, it might have deleted a leaf, in
+	 * which case it unlocked our path, so check path->locks[0] matches a
+	 * write lock.
+	 */
+	if (!ret && replace_extent && leafs_visited == 1 &&
+	    (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING ||
+	     path->locks[0] == BTRFS_WRITE_LOCK) &&
+	    btrfs_leaf_free_space(root, leaf) >=
+	    sizeof(struct btrfs_item) + extent_item_size) {
+
+		key.objectid = ino;
+		key.type = BTRFS_EXTENT_DATA_KEY;
+		key.offset = start;
+		if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) {
+			struct btrfs_key slot_key;
+
+			btrfs_item_key_to_cpu(leaf, &slot_key, path->slots[0]);
+			if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
+				path->slots[0]++;
 		}
+		setup_items_for_insert(root, path, &key,
+				       &extent_item_size,
+				       extent_item_size,
+				       sizeof(struct btrfs_item) +
+				       extent_item_size, 1);
+		*key_inserted = 1;
 	}
 
 	if (!replace_extent || !(*key_inserted))
@@ -1346,11 +1369,11 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
 				 start_pos, last_pos, 0, cached_state);
-		ordered = btrfs_lookup_first_ordered_extent(inode, last_pos);
+		ordered = btrfs_lookup_ordered_range(inode, start_pos,
+						     last_pos - start_pos + 1);
 		if (ordered &&
 		    ordered->file_offset + ordered->len > start_pos &&
 		    ordered->file_offset <= last_pos) {
-			btrfs_put_ordered_extent(ordered);
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     start_pos, last_pos,
 					     cached_state, GFP_NOFS);
@@ -1358,12 +1381,9 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 				unlock_page(pages[i]);
 				page_cache_release(pages[i]);
 			}
-			ret = btrfs_wait_ordered_range(inode, start_pos,
-						last_pos - start_pos + 1);
-			if (ret)
-				return ret;
-			else
-				return -EAGAIN;
+			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_put_ordered_extent(ordered);
+			return -EAGAIN;
 		}
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
@@ -1396,8 +1416,12 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 	u64 num_bytes;
 	int ret;
 
+	ret = btrfs_start_nocow_write(root);
+	if (!ret)
+		return -ENOSPC;
+
 	lockstart = round_down(pos, root->sectorsize);
-	lockend = lockstart + round_up(*write_bytes, root->sectorsize) - 1;
+	lockend = round_up(pos + *write_bytes, root->sectorsize) - 1;
 
 	while (1) {
 		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
@@ -1415,12 +1439,10 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 	ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
 	if (ret <= 0) {
 		ret = 0;
+		btrfs_end_nocow_write(root);
 	} else {
-		clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 EXTENT_DIRTY | EXTENT_DELALLOC |
-				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
-				 NULL, GFP_NOFS);
-		*write_bytes = min_t(size_t, *write_bytes, num_bytes);
+		*write_bytes = min_t(size_t, *write_bytes ,
+				     num_bytes - pos + lockstart);
 	}
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
@@ -1510,6 +1532,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			if (!only_release_metadata)
 				btrfs_free_reserved_data_space(inode,
 							       reserve_bytes);
+			else
+				btrfs_end_nocow_write(root);
 			break;
 		}
 
@@ -1598,6 +1622,9 @@ again:
 		}
 
 		release_bytes = 0;
+		if (only_release_metadata)
+			btrfs_end_nocow_write(root);
+
 		if (only_release_metadata && copied > 0) {
 			u64 lockstart = round_down(pos, root->sectorsize);
 			u64 lockend = lockstart +
@@ -1624,10 +1651,12 @@ again:
 	kfree(pages);
 
 	if (release_bytes) {
-		if (only_release_metadata)
+		if (only_release_metadata) {
+			btrfs_end_nocow_write(root);
 			btrfs_delalloc_release_metadata(inode, release_bytes);
-		else
+		} else {
 			btrfs_delalloc_release_space(inode, release_bytes);
+		}
 	}
 
 	return num_written ? num_written : ret;
@@ -1856,8 +1885,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	int ret = 0;
 	struct btrfs_trans_handle *trans;
+	struct btrfs_log_ctx ctx;
+	int ret = 0;
 	bool full_sync = 0;
 
 	trace_btrfs_sync_file(file, datasync);
@@ -1951,7 +1981,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 	trans->sync = true;
 
-	ret = btrfs_log_dentry_safe(trans, root, dentry);
+	btrfs_init_log_ctx(&ctx);
+
+	ret = btrfs_log_dentry_safe(trans, root, dentry, &ctx);
 	if (ret < 0) {
 		/* Fallthrough and commit/free transaction. */
 		ret = 1;
@@ -1971,7 +2003,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	if (ret != BTRFS_NO_LOG_SYNC) {
 		if (!ret) {
-			ret = btrfs_sync_log(trans, root);
+			ret = btrfs_sync_log(trans, root, &ctx);
 			if (!ret) {
 				ret = btrfs_end_transaction(trans, root);
 				goto out;
@@ -2157,6 +2189,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
 			  ((offset + len - 1) >> PAGE_CACHE_SHIFT));
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
+	u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
@@ -2172,14 +2205,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * entire page.
 	 */
 	if (same_page && len < PAGE_CACHE_SIZE) {
-		if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE))
+		if (offset < ino_size)
 			ret = btrfs_truncate_page(inode, offset, len, 0);
 		mutex_unlock(&inode->i_mutex);
 		return ret;
 	}
 
 	/* zero back part of the first page */
-	if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+	if (offset < ino_size) {
 		ret = btrfs_truncate_page(inode, offset, 0, 0);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -2188,7 +2221,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	/* zero the front end of the last page */
-	if (offset + len < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+	if (offset + len < ino_size) {
 		ret = btrfs_truncate_page(inode, offset + len, 0, 1);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -2277,10 +2310,13 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 		trans->block_rsv = &root->fs_info->trans_block_rsv;
 
-		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
-		if (ret) {
-			err = ret;
-			break;
+		if (cur_offset < ino_size) {
+			ret = fill_holes(trans, inode, path, cur_offset,
+					 drop_end);
+			if (ret) {
+				err = ret;
+				break;
+			}
 		}
 
 		cur_offset = drop_end;
@@ -2313,10 +2349,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
-	ret = fill_holes(trans, inode, path, cur_offset, drop_end);
-	if (ret) {
-		err = ret;
-		goto out_trans;
+	if (cur_offset < ino_size) {
+		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
+		if (ret) {
+			err = ret;
+			goto out_trans;
+		}
 	}
 
 out_trans: