Merge tag 'for-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fix race when reading extent buffer and 'uptodate' status is missed
   by one thread (introduced in 6.5)

 - do additional validation of devices using major:minor numbers

 - zoned mode fixes:
     - use zone-aware super block access during scrub
     - fix use-after-free during device replace (found by KASAN)
     - also delete zones that are 100% unusable to reclaim space

 - extent unpinning fixes:
     - fix extent map leak after error handling
     - print correct range in error message

 - error code and message updates

* tag 'for-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix race in read_extent_buffer_pages()
  btrfs: return accurate error code on open failure in open_fs_devices()
  btrfs: zoned: don't skip block groups with 100% zone unusable
  btrfs: use btrfs_warn() to log message at btrfs_add_extent_mapping()
  btrfs: fix message not properly printing interval when adding extent map
  btrfs: fix warning messages not printing interval at unpin_extent_range()
  btrfs: fix extent map leak in unexpected scenario at unpin_extent_cache()
  btrfs: validate device maj:min during open
  btrfs: zoned: fix use-after-free in do_zone_finish()
  btrfs: zoned: use zone aware sb location for scrub

6 files changed, 63 insertions, 22 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5f7587ca1ca772..1e09aeea69c22e 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1559,7 +1559,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * needing to allocate extents from the block group.
 		 */
 		used = btrfs_space_info_used(space_info, true);
-		if (space_info->total_bytes - block_group->length < used) {
+		if (space_info->total_bytes - block_group->length < used &&
+		    block_group->zone_unusable < block_group->length) {
 			/*
 			 * Add a reference for the list, compensate for the ref
 			 * drop under the "next" label for the
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7441245b1ceb15..61594eaf1f8969 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4333,6 +4333,19 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags))
 		goto done;
 
+	/*
+	 * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above
+	 * test_and_set_bit(EXTENT_BUFFER_READING), someone else could have
+	 * started and finished reading the same eb.  In this case, UPTODATE
+	 * will now be set, and we shouldn't read it in again.
+	 */
+	if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) {
+		clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
+		smp_mb__after_atomic();
+		wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+		return 0;
+	}
+
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	check_buffer_tree_ref(eb);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 347ca13d15a975..445f7716f1e2f7 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -309,7 +309,7 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 		btrfs_warn(fs_info,
 "no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu",
 			   btrfs_ino(inode), btrfs_root_id(inode->root),
-			   start, len, gen);
+			   start, start + len, gen);
 		ret = -ENOENT;
 		goto out;
 	}
@@ -318,7 +318,7 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 		btrfs_warn(fs_info,
 "found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu",
 			   btrfs_ino(inode), btrfs_root_id(inode->root),
-			   em->start, start, len, gen);
+			   em->start, start, start + len, gen);
 		ret = -EUCLEAN;
 		goto out;
 	}
@@ -340,9 +340,9 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 		em->mod_len = em->len;
 	}
 
-	free_extent_map(em);
 out:
 	write_unlock(&tree->lock);
+	free_extent_map(em);
 	return ret;
 
 }
@@ -629,13 +629,13 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 			 */
 			ret = merge_extent_mapping(em_tree, existing,
 						   em, start);
-			if (ret) {
+			if (WARN_ON(ret)) {
 				free_extent_map(em);
 				*em_in = NULL;
-				WARN_ONCE(ret,
-"extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu\n",
-					  existing->start, existing->len,
-					  orig_start, orig_len, start);
+				btrfs_warn(fs_info,
+"extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu",
+					   existing->start, extent_map_end(existing),
+					   orig_start, orig_start + orig_len, start);
 			}
 			free_extent_map(existing);
 		}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index c4bd0e60db5925..fa25004ab04e7b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2812,7 +2812,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 		gen = btrfs_get_last_trans_committed(fs_info);
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
-		bytenr = btrfs_sb_offset(i);
+		ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr);
+		if (ret == -ENOENT)
+			break;
+
+		if (ret) {
+			spin_lock(&sctx->stat_lock);
+			sctx->stat.super_errors++;
+			spin_unlock(&sctx->stat_lock);
+			continue;
+		}
+
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >
 		    scrub_dev->commit_total_bytes)
 			break;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1dc1f1946ae0eb..f15591f3e54fa4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -692,6 +692,16 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	device->bdev = file_bdev(bdev_file);
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 
+	if (device->devt != device->bdev->bd_dev) {
+		btrfs_warn(NULL,
+			   "device %s maj:min changed from %d:%d to %d:%d",
+			   device->name->str, MAJOR(device->devt),
+			   MINOR(device->devt), MAJOR(device->bdev->bd_dev),
+			   MINOR(device->bdev->bd_dev));
+
+		device->devt = device->bdev->bd_dev;
+	}
+
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
 	    device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -1174,23 +1184,30 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
 	struct btrfs_device *device;
 	struct btrfs_device *latest_dev = NULL;
 	struct btrfs_device *tmp_device;
+	int ret = 0;
 
 	list_for_each_entry_safe(device, tmp_device, &fs_devices->devices,
 				 dev_list) {
-		int ret;
+		int ret2;
 
-		ret = btrfs_open_one_device(fs_devices, device, flags, holder);
-		if (ret == 0 &&
+		ret2 = btrfs_open_one_device(fs_devices, device, flags, holder);
+		if (ret2 == 0 &&
 		    (!latest_dev || device->generation > latest_dev->generation)) {
 			latest_dev = device;
-		} else if (ret == -ENODATA) {
+		} else if (ret2 == -ENODATA) {
 			fs_devices->num_devices--;
 			list_del(&device->dev_list);
 			btrfs_free_device(device);
 		}
+		if (ret == 0 && ret2 != 0)
+			ret = ret2;
 	}
-	if (fs_devices->open_devices == 0)
+
+	if (fs_devices->open_devices == 0) {
+		if (ret)
+			return ret;
 		return -EINVAL;
+	}
 
 	fs_devices->opened = 1;
 	fs_devices->latest_dev = latest_dev;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 5a3d5ec75c5a94..4cba80b34387c1 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1574,11 +1574,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	if (!map)
 		return -EINVAL;
 
-	cache->physical_map = btrfs_clone_chunk_map(map, GFP_NOFS);
-	if (!cache->physical_map) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	cache->physical_map = map;
 
 	zone_info = kcalloc(map->num_stripes, sizeof(*zone_info), GFP_NOFS);
 	if (!zone_info) {
@@ -1690,7 +1686,6 @@ out:
 	}
 	bitmap_free(active);
 	kfree(zone_info);
-	btrfs_free_chunk_map(map);
 
 	return ret;
 }
@@ -2175,6 +2170,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	struct btrfs_chunk_map *map;
 	const bool is_metadata = (block_group->flags &
 			(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM));
+	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	int ret = 0;
 	int i;
 
@@ -2250,6 +2246,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	btrfs_clear_data_reloc_bg(block_group);
 	spin_unlock(&block_group->lock);
 
+	down_read(&dev_replace->rwsem);
 	map = block_group->physical_map;
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *device = map->stripes[i].dev;
@@ -2266,13 +2263,16 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 				       zinfo->zone_size >> SECTOR_SHIFT);
 		memalloc_nofs_restore(nofs_flags);
 
-		if (ret)
+		if (ret) {
+			up_read(&dev_replace->rwsem);
 			return ret;
+		}
 
 		if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
 			zinfo->reserved_active_zones++;
 		btrfs_dev_clear_active_zone(device, physical);
 	}
+	up_read(&dev_replace->rwsem);
 
 	if (!fully_written)
 		btrfs_dec_block_group_ro(block_group);