Adding upstream version 6.7.12.upstream/6.7.12

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 189 insertions, 49 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index aca24186d6..52bab8cf78 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1562,7 +1562,8 @@ 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/block-rsv.c b/fs/btrfs/block-rsv.c
index ceb5f586a2..1043a81423 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -494,7 +494,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 
 	block_rsv = get_block_rsv(trans, root);
 
-	if (unlikely(block_rsv->size == 0))
+	if (unlikely(btrfs_block_rsv_size(block_rsv) == 0))
 		goto try_reserve;
 again:
 	ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize);
diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h
index b0bd12b865..43a9a6b5a7 100644
--- a/fs/btrfs/block-rsv.h
+++ b/fs/btrfs/block-rsv.h
@@ -101,4 +101,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv)
 	return data_race(rsv->full);
 }
 
+/*
+ * Get the reserved mount of a block reserve in a context where getting a stale
+ * value is acceptable, instead of accessing it directly and trigger data race
+ * warning from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->reserved;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
+/*
+ * Get the size of a block reserve in a context where getting a stale value is
+ * acceptable, instead of accessing it directly and trigger data race warning
+ * from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->size;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
 #endif /* BTRFS_BLOCK_RSV_H */
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index eade0432bd..87082f9732 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2734,16 +2734,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode,
 	 * it beyond i_size.
 	 */
 	while (cur_offset < end && cur_offset < i_size) {
+		struct extent_state *cached_state = NULL;
 		u64 delalloc_start;
 		u64 delalloc_end;
 		u64 prealloc_start;
+		u64 lockstart;
+		u64 lockend;
 		u64 prealloc_len = 0;
 		bool delalloc;
 
+		lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize);
+		lockend = round_up(end, inode->root->fs_info->sectorsize);
+
+		/*
+		 * We are only locking for the delalloc range because that's the
+		 * only thing that can change here.  With fiemap we have a lock
+		 * on the inode, so no buffered or direct writes can happen.
+		 *
+		 * However mmaps and normal page writeback will cause this to
+		 * change arbitrarily.  We have to lock the extent lock here to
+		 * make sure that nobody messes with the tree while we're doing
+		 * btrfs_find_delalloc_in_range.
+		 */
+		lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 		delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end,
 							delalloc_cached_state,
 							&delalloc_start,
 							&delalloc_end);
+		unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 		if (!delalloc)
 			break;
 
@@ -2911,15 +2929,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		  u64 start, u64 len)
 {
 	const u64 ino = btrfs_ino(inode);
-	struct extent_state *cached_state = NULL;
 	struct extent_state *delalloc_cached_state = NULL;
 	struct btrfs_path *path;
 	struct fiemap_cache cache = { 0 };
 	struct btrfs_backref_share_check_ctx *backref_ctx;
 	u64 last_extent_end;
 	u64 prev_extent_end;
-	u64 lockstart;
-	u64 lockend;
+	u64 range_start;
+	u64 range_end;
+	const u64 sectorsize = inode->root->fs_info->sectorsize;
 	bool stopped = false;
 	int ret;
 
@@ -2930,12 +2948,11 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		goto out;
 	}
 
-	lockstart = round_down(start, inode->root->fs_info->sectorsize);
-	lockend = round_up(start + len, inode->root->fs_info->sectorsize);
-	prev_extent_end = lockstart;
+	range_start = round_down(start, sectorsize);
+	range_end = round_up(start + len, sectorsize);
+	prev_extent_end = range_start;
 
 	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 
 	ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
 	if (ret < 0)
@@ -2943,7 +2960,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 	btrfs_release_path(path);
 
 	path->reada = READA_FORWARD;
-	ret = fiemap_search_slot(inode, path, lockstart);
+	ret = fiemap_search_slot(inode, path, range_start);
 	if (ret < 0) {
 		goto out_unlock;
 	} else if (ret > 0) {
@@ -2955,7 +2972,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		goto check_eof_delalloc;
 	}
 
-	while (prev_extent_end < lockend) {
+	while (prev_extent_end < range_end) {
 		struct extent_buffer *leaf = path->nodes[0];
 		struct btrfs_file_extent_item *ei;
 		struct btrfs_key key;
@@ -2978,19 +2995,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		 * The first iteration can leave us at an extent item that ends
 		 * before our range's start. Move to the next item.
 		 */
-		if (extent_end <= lockstart)
+		if (extent_end <= range_start)
 			goto next_item;
 
 		backref_ctx->curr_leaf_bytenr = leaf->start;
 
 		/* We have in implicit hole (NO_HOLES feature enabled). */
 		if (prev_extent_end < key.offset) {
-			const u64 range_end = min(key.offset, lockend) - 1;
+			const u64 hole_end = min(key.offset, range_end) - 1;
 
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
 						  &delalloc_cached_state,
 						  backref_ctx, 0, 0, 0,
-						  prev_extent_end, range_end);
+						  prev_extent_end, hole_end);
 			if (ret < 0) {
 				goto out_unlock;
 			} else if (ret > 0) {
@@ -3000,7 +3017,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 			}
 
 			/* We've reached the end of the fiemap range, stop. */
-			if (key.offset >= lockend) {
+			if (key.offset >= range_end) {
 				stopped = true;
 				break;
 			}
@@ -3094,29 +3111,41 @@ check_eof_delalloc:
 	btrfs_free_path(path);
 	path = NULL;
 
-	if (!stopped && prev_extent_end < lockend) {
+	if (!stopped && prev_extent_end < range_end) {
 		ret = fiemap_process_hole(inode, fieinfo, &cache,
 					  &delalloc_cached_state, backref_ctx,
-					  0, 0, 0, prev_extent_end, lockend - 1);
+					  0, 0, 0, prev_extent_end, range_end - 1);
 		if (ret < 0)
 			goto out_unlock;
-		prev_extent_end = lockend;
+		prev_extent_end = range_end;
 	}
 
 	if (cache.cached && cache.offset + cache.len >= last_extent_end) {
 		const u64 i_size = i_size_read(&inode->vfs_inode);
 
 		if (prev_extent_end < i_size) {
+			struct extent_state *cached_state = NULL;
 			u64 delalloc_start;
 			u64 delalloc_end;
+			u64 lockstart;
+			u64 lockend;
 			bool delalloc;
 
+			lockstart = round_down(prev_extent_end, sectorsize);
+			lockend = round_up(i_size, sectorsize);
+
+			/*
+			 * See the comment in fiemap_process_hole as to why
+			 * we're doing the locking here.
+			 */
+			lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 			delalloc = btrfs_find_delalloc_in_range(inode,
 								prev_extent_end,
 								i_size - 1,
 								&delalloc_cached_state,
 								&delalloc_start,
 								&delalloc_end);
+			unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 			if (!delalloc)
 				cache.flags |= FIEMAP_EXTENT_LAST;
 		} else {
@@ -3127,7 +3156,6 @@ check_eof_delalloc:
 	ret = emit_last_fiemap_cache(fieinfo, &cache);
 
 out_unlock:
-	unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 out:
 	free_extent_state(delalloc_cached_state);
@@ -4024,6 +4052,19 @@ 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/qgroup.c b/fs/btrfs/qgroup.c
index bbfa44b89b..1dcf5bb8df 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2959,11 +2959,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 				ctx.roots = NULL;
 			}
 
-			/* Free the reserved data space */
-			btrfs_qgroup_free_refroot(fs_info,
-					record->data_rsv_refroot,
-					record->data_rsv,
-					BTRFS_QGROUP_RSV_DATA);
 			/*
 			 * Use BTRFS_SEQ_LAST as time_seq to do special search,
 			 * which doesn't lock tree or delayed_refs and search
@@ -2987,6 +2982,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 			record->old_roots = NULL;
 			new_roots = NULL;
 		}
+		/* Free the reserved data space */
+		btrfs_qgroup_free_refroot(fs_info,
+				record->data_rsv_refroot,
+				record->data_rsv,
+				BTRFS_QGROUP_RSV_DATA);
 cleanup:
 		ulist_free(record->old_roots);
 		ulist_free(new_roots);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 443d2519f0..258b3e5585 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2809,7 +2809,17 @@ 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/space-info.c b/fs/btrfs/space-info.c
index 571bb13587..3b54eb5834 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -856,7 +856,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info)
 {
-	u64 global_rsv_size = fs_info->global_block_rsv.reserved;
+	const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv);
 	u64 ordered, delalloc;
 	u64 thresh;
 	u64 used;
@@ -956,8 +956,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 	ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1;
 	delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes);
 	if (ordered >= delalloc)
-		used += fs_info->delayed_refs_rsv.reserved +
-			fs_info->delayed_block_rsv.reserved;
+		used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv);
 	else
 		used += space_info->bytes_may_use - global_rsv_size;
 
@@ -1173,7 +1173,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		enum btrfs_flush_state flush;
 		u64 delalloc_size = 0;
 		u64 to_reclaim, block_rsv_size;
-		u64 global_rsv_size = global_rsv->reserved;
+		const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv);
 
 		loops++;
 
@@ -1185,9 +1185,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		 * assume it's tied up in delalloc reservations.
 		 */
 		block_rsv_size = global_rsv_size +
-			delayed_block_rsv->reserved +
-			delayed_refs_rsv->reserved +
-			trans_rsv->reserved;
+			btrfs_block_rsv_reserved(delayed_block_rsv) +
+			btrfs_block_rsv_reserved(delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(trans_rsv);
 		if (block_rsv_size < space_info->bytes_may_use)
 			delalloc_size = space_info->bytes_may_use - block_rsv_size;
 
@@ -1207,16 +1207,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 			to_reclaim = delalloc_size;
 			flush = FLUSH_DELALLOC;
 		} else if (space_info->bytes_pinned >
-			   (delayed_block_rsv->reserved +
-			    delayed_refs_rsv->reserved)) {
+			   (btrfs_block_rsv_reserved(delayed_block_rsv) +
+			    btrfs_block_rsv_reserved(delayed_refs_rsv))) {
 			to_reclaim = space_info->bytes_pinned;
 			flush = COMMIT_TRANS;
-		} else if (delayed_block_rsv->reserved >
-			   delayed_refs_rsv->reserved) {
-			to_reclaim = delayed_block_rsv->reserved;
+		} else if (btrfs_block_rsv_reserved(delayed_block_rsv) >
+			   btrfs_block_rsv_reserved(delayed_refs_rsv)) {
+			to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv);
 			flush = FLUSH_DELAYED_ITEMS_NR;
 		} else {
-			to_reclaim = delayed_refs_rsv->reserved;
+			to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv);
 			flush = FLUSH_DELAYED_REFS_NR;
 		}
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f627674b37..fd30dc3d59 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -683,6 +683,16 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	device->bdev = bdev_handle->bdev;
 	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) {
@@ -1290,6 +1300,47 @@ int btrfs_forget_devices(dev_t devt)
 	return ret;
 }
 
+static bool btrfs_skip_registration(struct btrfs_super_block *disk_super,
+				    const char *path, dev_t devt,
+				    bool mount_arg_dev)
+{
+	struct btrfs_fs_devices *fs_devices;
+
+	/*
+	 * Do not skip device registration for mounted devices with matching
+	 * maj:min but different paths. Booting without initrd relies on
+	 * /dev/root initially, later replaced with the actual root device.
+	 * A successful scan ensures grub2-probe selects the correct device.
+	 */
+	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		struct btrfs_device *device;
+
+		mutex_lock(&fs_devices->device_list_mutex);
+
+		if (!fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
+			continue;
+		}
+
+		list_for_each_entry(device, &fs_devices->devices, dev_list) {
+			if (device->bdev && (device->bdev->bd_dev == devt) &&
+			    strcmp(device->name->str, path) != 0) {
+				mutex_unlock(&fs_devices->device_list_mutex);
+
+				/* Do not skip registration. */
+				return false;
+			}
+		}
+		mutex_unlock(&fs_devices->device_list_mutex);
+	}
+
+	if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 &&
+	    !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING))
+		return true;
+
+	return false;
+}
+
 /*
  * Look for a btrfs signature on a device. This may be called out of the mount path
  * and we are not allowed to call set_blocksize during the scan. The superblock
@@ -1346,18 +1397,14 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 		goto error_bdev_put;
 	}
 
-	if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 &&
-	    !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) {
-		dev_t devt;
+	if (btrfs_skip_registration(disk_super, path, bdev_handle->bdev->bd_dev,
+				    mount_arg_dev)) {
+		pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n",
+			  path, MAJOR(bdev_handle->bdev->bd_dev),
+			  MINOR(bdev_handle->bdev->bd_dev));
 
-		ret = lookup_bdev(path, &devt);
-		if (ret)
-			btrfs_warn(NULL, "lookup bdev failed for path %s: %d",
-				   path, ret);
-		else
-			btrfs_free_stale_devices(devt, NULL);
+		btrfs_free_stale_devices(bdev_handle->bdev->bd_dev, NULL);
 
-		pr_debug("BTRFS: skip registering single non-seed device %s\n", path);
 		device = NULL;
 		goto free_disk_super;
 	}
@@ -1392,7 +1439,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start,
 
 		if (in_range(physical_start, *start, len) ||
 		    in_range(*start, physical_start,
-			     physical_end - physical_start)) {
+			     physical_end + 1 - physical_start)) {
 			*start = physical_end + 1;
 			return true;
 		}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 3779e76a15..524532f992 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1661,6 +1661,15 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
+	/* Reject non SINGLE data profiles without RST */
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) &&
+	    (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+	    !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",