Merge tag 'for-4.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There are a several user visible changes, the rest is mostly invisible
  and continues to clean up the whole code base.

  User visible changes:
   - new mount option nossd_spread (pair for ssd_spread)

   - mount option subvolid will detect junk after the number and fail
     the mount

   - add message after cancelled device replace

   - direct module dependency on libcrc32, removed own crc wrappers

   - removed user space transaction ioctls

   - use lighter locking when reading /proc/self/mounts, RCU instead of
     mutex to avoid unnecessary contention

  Enhancements:
   - skip writeback of last page when truncating file to same size

   - send: do not issue unnecessary truncate operations

   - mount option token specifiers: use %u for unsigned values, more
     validation

   - selftests: more tree block validations

  qgroups:
   - preparatory work for splitting reservation types for data and
     metadata, this should allow for more accurate tracking and fix some
     issues with underflows or do further enhancements

   - split metadata reservations for started and joined transaction so
     they do not get mixed up and are accounted correctly at commit time

   - with the above, it's possible to revert patch that potentially
     deadlocks when trying to make more space by explicitly committing
     when the quota limit is hit

   - fix root item corruption when multiple same source snapshots are
     created with quota enabled

  RAID56:
   - make sure target is identical to source when raid56 rebuild fails
     after dev-replace

   - faster rebuild during scrub, batch by stripes and not
     block-by-block

   - make more use of cached data when rebuilding from a missing device

  Fixes:
   - null pointer deref when device replace target is missing

   - fix fsync after hole punching when using no-holes feature

   - fix lockdep splat when allocating percpu data with wrong GFP flags

  Cleanups, refactoring, core changes:
   - drop redunant parameters from various functions

   - kill and opencode trivial helpers

   - __cold/__exit function annotations

   - dead code removal

   - continued audit and documentation of memory barriers

   - error handling: handle removal from uuid tree

   - error handling: remove handling of impossible condtitons

   - more debugging or error messages

   - updated tracepoints

   - one VLA use removal (and one still left)"

* tag 'for-4.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (164 commits)
  btrfs: lift errors from add_extent_changeset to the callers
  Btrfs: print error messages when failing to read trees
  btrfs: user proper type for btrfs_mask_flags flags
  btrfs: split dev-replace locking helpers for read and write
  btrfs: remove stale comments about fs_mutex
  btrfs: use RCU in btrfs_show_devname for device list traversal
  btrfs: update barrier in should_cow_block
  btrfs: use lockdep_assert_held for mutexes
  btrfs: use lockdep_assert_held for spinlocks
  btrfs: Validate child tree block's level and first key
  btrfs: tests/qgroup: Fix wrong tree backref level
  Btrfs: fix copy_items() return value when logging an inode
  Btrfs: fix fsync after hole punching when using no-holes feature
  btrfs: use helper to set ulist aux from a qgroup
  Revert "btrfs: qgroups: Retry after commit on getting EDQUOT"
  btrfs: qgroup: Update trace events for metadata reservation
  btrfs: qgroup: Use root::qgroup_meta_rsv_* to record qgroup meta reserved space
  btrfs: delayed-inode: Use new qgroup meta rsv for delayed inode and item
  btrfs: qgroup: Use separate meta reservation type for delalloc
  btrfs: qgroup: Introduce function to convert META_PREALLOC into META_PERTRANS
  ...

1 files changed, 24 insertions, 10 deletions

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cd2298d185dd..4874c09f6d3c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1839,6 +1839,8 @@ again:
 
 	parent = eb;
 	while (1) {
+		struct btrfs_key first_key;
+
 		level = btrfs_header_level(parent);
 		BUG_ON(level < lowest_level);
 
@@ -1852,6 +1854,7 @@ again:
 		old_bytenr = btrfs_node_blockptr(parent, slot);
 		blocksize = fs_info->nodesize;
 		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
+		btrfs_node_key_to_cpu(parent, &key, slot);
 
 		if (level <= max_level) {
 			eb = path->nodes[level];
@@ -1876,7 +1879,8 @@ again:
 				break;
 			}
 
-			eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen);
+			eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen,
+					     level - 1, &first_key);
 			if (IS_ERR(eb)) {
 				ret = PTR_ERR(eb);
 				break;
@@ -2036,6 +2040,8 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 
 	for (i = *level; i > 0; i--) {
+		struct btrfs_key first_key;
+
 		eb = path->nodes[i];
 		nritems = btrfs_header_nritems(eb);
 		while (path->slots[i] < nritems) {
@@ -2056,7 +2062,9 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 		}
 
 		bytenr = btrfs_node_blockptr(eb, path->slots[i]);
-		eb = read_tree_block(fs_info, bytenr, ptr_gen);
+		btrfs_node_key_to_cpu(eb, &first_key, path->slots[i]);
+		eb = read_tree_block(fs_info, bytenr, ptr_gen, i - 1,
+				     &first_key);
 		if (IS_ERR(eb)) {
 			return PTR_ERR(eb);
 		} else if (!extent_buffer_uptodate(eb)) {
@@ -2714,6 +2722,8 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 	path->lowest_level = node->level + 1;
 	rc->backref_cache.path[node->level] = node;
 	list_for_each_entry(edge, &node->upper, list[LOWER]) {
+		struct btrfs_key first_key;
+
 		cond_resched();
 
 		upper = edge->node[UPPER];
@@ -2779,7 +2789,9 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
 		blocksize = root->fs_info->nodesize;
 		generation = btrfs_node_ptr_generation(upper->eb, slot);
-		eb = read_tree_block(fs_info, bytenr, generation);
+		btrfs_node_key_to_cpu(upper->eb, &first_key, slot);
+		eb = read_tree_block(fs_info, bytenr, generation,
+				     upper->level - 1, &first_key);
 		if (IS_ERR(eb)) {
 			err = PTR_ERR(eb);
 			goto next;
@@ -2944,7 +2956,8 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *eb;
 
 	BUG_ON(block->key_ready);
-	eb = read_tree_block(fs_info, block->bytenr, block->key.offset);
+	eb = read_tree_block(fs_info, block->bytenr, block->key.offset,
+			     block->level, NULL);
 	if (IS_ERR(eb)) {
 		return PTR_ERR(eb);
 	} else if (!extent_buffer_uptodate(eb)) {
@@ -3226,7 +3239,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 						   mask);
 			if (!page) {
 				btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							PAGE_SIZE);
+							PAGE_SIZE, true);
 				ret = -ENOMEM;
 				goto out;
 			}
@@ -3245,9 +3258,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
 				unlock_page(page);
 				put_page(page);
 				btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							PAGE_SIZE);
+							PAGE_SIZE, true);
 				btrfs_delalloc_release_extents(BTRFS_I(inode),
-							       PAGE_SIZE);
+							       PAGE_SIZE, true);
 				ret = -EIO;
 				goto out;
 			}
@@ -3274,9 +3287,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			unlock_page(page);
 			put_page(page);
 			btrfs_delalloc_release_metadata(BTRFS_I(inode),
-							 PAGE_SIZE);
+							 PAGE_SIZE, true);
 			btrfs_delalloc_release_extents(BTRFS_I(inode),
-			                               PAGE_SIZE);
+			                               PAGE_SIZE, true);
 
 			clear_extent_bits(&BTRFS_I(inode)->io_tree,
 					  page_start, page_end,
@@ -3292,7 +3305,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		put_page(page);
 
 		index++;
-		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE,
+					       false);
 		balance_dirty_pages_ratelimited(inode->i_mapping);
 		btrfs_throttle(fs_info);
 	}