Merge tag 'for-6.11-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull more btrfs fixes from David Sterba:
 "A more fixes. We got reports that shrinker added in 6.10 still causes
  latency spikes and the fixes don't handle all corner cases. Due to
  summer holidays we're taking a shortcut to disable it for release
  builds and will fix it in the near future.

   - only enable extent map shrinker for DEBUG builds, temporary quick
     fix to avoid latency spikes for regular builds

   - update target inode's ctime on unlink, mandated by POSIX

   - properly take lock to read/update block group's zoned variables

   - add counted_by() annotations"

* tag 'for-6.11-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: only enable extent map shrinker for DEBUG builds
  btrfs: zoned: properly take lock to read/update block group's zoned variables
  btrfs: tree-checker: add dev extent item checks
  btrfs: update target inode's ctime on unlink
  btrfs: send: annotate struct name_cache_entry with __counted_by()

5 files changed, 86 insertions, 8 deletions

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index f5996a43db24..eaa1dbd31352 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2697,15 +2697,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 	u64 offset = bytenr - block_group->start;
 	u64 to_free, to_unusable;
 	int bg_reclaim_threshold = 0;
-	bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+	bool initial;
 	u64 reclaimable_unusable;
 
-	WARN_ON(!initial && offset + size > block_group->zone_capacity);
+	spin_lock(&block_group->lock);
 
+	initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+	WARN_ON(!initial && offset + size > block_group->zone_capacity);
 	if (!initial)
 		bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);
 
-	spin_lock(&ctl->tree_lock);
 	if (!used)
 		to_free = size;
 	else if (initial)
@@ -2718,7 +2719,9 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 		to_free = offset + size - block_group->alloc_offset;
 	to_unusable = size - to_free;
 
+	spin_lock(&ctl->tree_lock);
 	ctl->free_space += to_free;
+	spin_unlock(&ctl->tree_lock);
 	/*
 	 * If the block group is read-only, we should account freed space into
 	 * bytes_readonly.
@@ -2727,11 +2730,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 		block_group->zone_unusable += to_unusable;
 		WARN_ON(block_group->zone_unusable > block_group->length);
 	}
-	spin_unlock(&ctl->tree_lock);
 	if (!used) {
-		spin_lock(&block_group->lock);
 		block_group->alloc_offset -= size;
-		spin_unlock(&block_group->lock);
 	}
 
 	reclaimable_unusable = block_group->zone_unusable -
@@ -2745,6 +2745,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 		btrfs_mark_bg_to_reclaim(block_group);
 	}
 
+	spin_unlock(&block_group->lock);
+
 	return 0;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 333b0e8587a2..b1b6564ab68f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4195,6 +4195,7 @@ err:
 
 	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2);
 	inode_inc_iversion(&inode->vfs_inode);
+	inode_set_ctime_current(&inode->vfs_inode);
 	inode_inc_iversion(&dir->vfs_inode);
  	inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
 	ret = btrfs_update_inode(trans, dir);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 7fc692fc76e1..619fa0b8b3f6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -347,7 +347,7 @@ struct name_cache_entry {
 	int ret;
 	int need_later_update;
 	int name_len;
-	char name[];
+	char name[] __counted_by(name_len);
 };
 
 /* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 11044e9e2cb1..98fa0f382480 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2402,7 +2402,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro
 
 	trace_btrfs_extent_map_shrinker_count(fs_info, nr);
 
-	return nr;
+	/*
+	 * Only report the real number for DEBUG builds, as there are reports of
+	 * serious performance degradation caused by too frequent shrinks.
+	 */
+	if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
+		return nr;
+	return 0;
 }
 
 static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 6f1e2f2215d9..634d69964fe4 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1764,6 +1764,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf,
 	return 0;
 }
 
+static int check_dev_extent_item(const struct extent_buffer *leaf,
+				 const struct btrfs_key *key,
+				 int slot,
+				 struct btrfs_key *prev_key)
+{
+	struct btrfs_dev_extent *de;
+	const u32 sectorsize = leaf->fs_info->sectorsize;
+
+	de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+	/* Basic fixed member checks. */
+	if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) !=
+		     BTRFS_CHUNK_TREE_OBJECTID)) {
+		generic_err(leaf, slot,
+			    "invalid dev extent chunk tree id, has %llu expect %llu",
+			    btrfs_dev_extent_chunk_tree(leaf, de),
+			    BTRFS_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+	if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) !=
+		     BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
+		generic_err(leaf, slot,
+			    "invalid dev extent chunk objectid, has %llu expect %llu",
+			    btrfs_dev_extent_chunk_objectid(leaf, de),
+			    BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+	/* Alignment check. */
+	if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
+		generic_err(leaf, slot,
+			    "invalid dev extent key.offset, has %llu not aligned to %u",
+			    key->offset, sectorsize);
+		return -EUCLEAN;
+	}
+	if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de),
+				 sectorsize))) {
+		generic_err(leaf, slot,
+			    "invalid dev extent chunk offset, has %llu not aligned to %u",
+			    btrfs_dev_extent_chunk_objectid(leaf, de),
+			    sectorsize);
+		return -EUCLEAN;
+	}
+	if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de),
+				 sectorsize))) {
+		generic_err(leaf, slot,
+			    "invalid dev extent length, has %llu not aligned to %u",
+			    btrfs_dev_extent_length(leaf, de), sectorsize);
+		return -EUCLEAN;
+	}
+	/* Overlap check with previous dev extent. */
+	if (slot && prev_key->objectid == key->objectid &&
+	    prev_key->type == key->type) {
+		struct btrfs_dev_extent *prev_de;
+		u64 prev_len;
+
+		prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent);
+		prev_len = btrfs_dev_extent_length(leaf, prev_de);
+		if (unlikely(prev_key->offset + prev_len > key->offset)) {
+			generic_err(leaf, slot,
+		"dev extent overlap, prev offset %llu len %llu current offset %llu",
+				    prev_key->objectid, prev_len, key->offset);
+			return -EUCLEAN;
+		}
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -1800,6 +1866,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf,
 	case BTRFS_DEV_ITEM_KEY:
 		ret = check_dev_item(leaf, key, slot);
 		break;
+	case BTRFS_DEV_EXTENT_KEY:
+		ret = check_dev_extent_item(leaf, key, slot, prev_key);
+		break;
 	case BTRFS_INODE_ITEM_KEY:
 		ret = check_inode_item(leaf, key, slot);
 		break;