Merge tag 'for-6.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "There are no new features, the changes are in the core code, notably
  tree-log error handling and reporting improvements, and initial
  support for block size > page size.

  Performance improvements:

   - search data checksums in the commit root (previous transaction) to
     avoid locking contention, this improves parallelism of read
     heavy/low write workloads, and also reduces transaction commit
     time; on real and reproducer workload the sync time went from
     minutes to tens of seconds (workload and numbers are in the
     changelog)

  Core:

   - tree-log updates:
      - error handling improvements, transaction aborts
      - add new error state 'O' (printed in status messages) when log
        replay fails and is aborted
      - reduced number of btrfs_path allocations when traversing the
        tree

   - 'block size > page size' support
      - basic implementation with limitations, under experimental build
      - limitations: no direct io, raid56, encoded read (standalone and
        in send ioctl), encoded write
      - preparatory work for compression, removing implicit assumptions
        of page and block sizes
      - compression workspaces are now per-filesystem, we cannot assume
        common block size for work memory among different filesystems

   - tree-checker now verifies INODE_EXTREF item (which is implementing
     hardlinks)

   - tree leaf pretty printer updates, there were missing data from
     items, keys/items

   - move config option CONFIG_BTRFS_REF_VERIFY to CONFIG_BTRFS_DEBUG,
     it's a debugging feature and not needed to be enabled separately

   - more struct btrfs_path auto free updates

   - use ref_tracker API for tracking delayed inodes, enabled by mount
     option 'ref_verify', allowing to better pinpoint leaking references

   - in zoned mode, avoid selecting data relocation zoned for ordinary
     data block groups

   - updated and enhanced error messages

   - lots of cleanups and refactoring"

* tag 'for-6.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (113 commits)
  btrfs: use smp_mb__after_atomic() when forcing COW in create_pending_snapshot()
  btrfs: add unlikely annotations to branches leading to transaction abort
  btrfs: add unlikely annotations to branches leading to EIO
  btrfs: add unlikely annotations to branches leading to EUCLEAN
  btrfs: more trivial BTRFS_PATH_AUTO_FREE conversions
  btrfs: zoned: don't fail mount needlessly due to too many active zones
  btrfs: use kmalloc_array() for open-coded arithmetic in kmalloc()
  btrfs: enable experimental bs > ps support
  btrfs: add extra ASSERT()s to catch unaligned bios
  btrfs: fix symbolic link reading when bs > ps
  btrfs: prepare scrub to support bs > ps cases
  btrfs: prepare zlib to support bs > ps cases
  btrfs: prepare lzo to support bs > ps cases
  btrfs: prepare zstd to support bs > ps cases
  btrfs: prepare compression folio alloc/free for bs > ps cases
  btrfs: fix the incorrect max_bytes value for find_lock_delalloc_range()
  btrfs: remove pointless key offset setup in create_pending_snapshot()
  btrfs: annotate btrfs_is_testing() as unlikely and make it return bool
  btrfs: make the rule checking more readable for should_cow_block()
  btrfs: simplify inline extent end calculation at replay_one_extent()
  ...

1 files changed, 38 insertions, 1 deletions

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a997c7cc35a2..ca30b15ea452 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -183,6 +183,7 @@ static bool check_prev_ino(struct extent_buffer *leaf,
 	/* Only these key->types needs to be checked */
 	ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
 	       key->type == BTRFS_INODE_REF_KEY ||
+	       key->type == BTRFS_INODE_EXTREF_KEY ||
 	       key->type == BTRFS_DIR_INDEX_KEY ||
 	       key->type == BTRFS_DIR_ITEM_KEY ||
 	       key->type == BTRFS_EXTENT_DATA_KEY);
@@ -1209,7 +1210,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
 	/*
 	 * For legacy root item, the members starting at generation_v2 will be
 	 * all filled with 0.
-	 * And since we allow geneartion_v2 as 0, it will still pass the check.
+	 * And since we allow generation_v2 as 0, it will still pass the check.
 	 */
 	read_extent_buffer(leaf, &ri, btrfs_item_ptr_offset(leaf, slot),
 			   btrfs_item_size(leaf, slot));
@@ -1782,6 +1783,39 @@ static int check_inode_ref(struct extent_buffer *leaf,
 	return 0;
 }
 
+static int check_inode_extref(struct extent_buffer *leaf,
+			      struct btrfs_key *key, struct btrfs_key *prev_key,
+			      int slot)
+{
+	unsigned long ptr = btrfs_item_ptr_offset(leaf, slot);
+	unsigned long end = ptr + btrfs_item_size(leaf, slot);
+
+	if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
+		return -EUCLEAN;
+
+	while (ptr < end) {
+		struct btrfs_inode_extref *extref = (struct btrfs_inode_extref *)ptr;
+		u16 namelen;
+
+		if (unlikely(ptr + sizeof(*extref)) > end) {
+			inode_ref_err(leaf, slot,
+			"inode extref overflow, ptr %lu end %lu inode_extref size %zu",
+				      ptr, end, sizeof(*extref));
+			return -EUCLEAN;
+		}
+
+		namelen = btrfs_inode_extref_name_len(leaf, extref);
+		if (unlikely(ptr + sizeof(*extref) + namelen > end)) {
+			inode_ref_err(leaf, slot,
+				"inode extref overflow, ptr %lu end %lu namelen %u",
+				ptr, end, namelen);
+			return -EUCLEAN;
+		}
+		ptr += sizeof(*extref) + namelen;
+	}
+	return 0;
+}
+
 static int check_raid_stripe_extent(const struct extent_buffer *leaf,
 				    const struct btrfs_key *key, int slot)
 {
@@ -1893,6 +1927,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf,
 	case BTRFS_INODE_REF_KEY:
 		ret = check_inode_ref(leaf, key, prev_key, slot);
 		break;
+	case BTRFS_INODE_EXTREF_KEY:
+		ret = check_inode_extref(leaf, key, prev_key, slot);
+		break;
 	case BTRFS_BLOCK_GROUP_ITEM_KEY:
 		ret = check_block_group_item(leaf, key, slot);
 		break;