Adding upstream version 6.9.7.

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

8 files changed, 107 insertions, 60 deletions

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 477f350a8b..e3a57196b0 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -741,7 +741,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 			ret = btrfs_bio_csum(bbio);
 			if (ret)
 				goto fail_put_bio;
-		} else if (use_append) {
+		} else if (use_append ||
+			   (btrfs_is_zoned(fs_info) && inode &&
+			    inode->flags & BTRFS_INODE_NODATASUM)) {
 			ret = btrfs_alloc_dummy_sum(bbio);
 			if (ret)
 				goto fail_put_bio;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 1e09aeea69..1a66be33bb 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1785,6 +1785,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
 	struct btrfs_block_group *bg;
 	struct btrfs_space_info *space_info;
+	LIST_HEAD(retry_list);
 
 	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
 		return;
@@ -1921,8 +1922,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		}
 
 next:
-		if (ret)
-			btrfs_mark_bg_to_reclaim(bg);
+		if (ret) {
+			/* Refcount held by the reclaim_bgs list after splice. */
+			btrfs_get_block_group(bg);
+			list_add_tail(&bg->bg_list, &retry_list);
+		}
 		btrfs_put_block_group(bg);
 
 		mutex_unlock(&fs_info->reclaim_bgs_lock);
@@ -1942,6 +1946,9 @@ next:
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 end:
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->reclaim_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	btrfs_exclop_finish(fs_info);
 	sb_end_write(fs_info->sb);
 }
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3df5477d48..3a47eec87b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4544,18 +4544,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				       struct btrfs_fs_info *fs_info)
 {
 	struct rb_node *node;
-	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs;
 	struct btrfs_delayed_ref_node *ref;
 
-	delayed_refs = &trans->delayed_refs;
-
 	spin_lock(&delayed_refs->lock);
-	if (atomic_read(&delayed_refs->num_entries) == 0) {
-		spin_unlock(&delayed_refs->lock);
-		btrfs_debug(fs_info, "delayed_refs has NO entry");
-		return;
-	}
-
 	while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) {
 		struct btrfs_delayed_ref_head *head;
 		struct rb_node *n;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2776112dbd..41173701f1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2773,13 +2773,19 @@ static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *p
 		goto out;
 	}
 
-	/* See the comment at fiemap_search_slot() about why we clone. */
-	copy_extent_buffer_full(clone, path->nodes[0]);
 	/*
 	 * Important to preserve the start field, for the optimizations when
 	 * checking if extents are shared (see extent_fiemap()).
+	 *
+	 * We must set ->start before calling copy_extent_buffer_full().  If we
+	 * are on sub-pagesize blocksize, we use ->start to determine the offset
+	 * into the folio where our eb exists, and if we update ->start after
+	 * the fact then any subsequent reads of the eb may read from a
+	 * different offset in the folio than where we originally copied into.
 	 */
 	clone->start = path->nodes[0]->start;
+	/* See the comment at fiemap_search_slot() about why we clone. */
+	copy_extent_buffer_full(clone, path->nodes[0]);
 
 	slot = path->slots[0];
 	btrfs_release_path(path);
@@ -3656,6 +3662,8 @@ static struct extent_buffer *grab_extent_buffer(
 	struct folio *folio = page_folio(page);
 	struct extent_buffer *exists;
 
+	lockdep_assert_held(&page->mapping->i_private_lock);
+
 	/*
 	 * For subpage case, we completely rely on radix tree to ensure we
 	 * don't try to insert two ebs for the same bytenr.  So here we always
@@ -3723,13 +3731,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
  * The caller needs to free the existing folios and retry using the same order.
  */
 static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
+				      struct btrfs_subpage *prealloc,
 				      struct extent_buffer **found_eb_ret)
 {
 
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	const unsigned long index = eb->start >> PAGE_SHIFT;
-	struct folio *existing_folio;
+	struct folio *existing_folio = NULL;
 	int ret;
 
 	ASSERT(found_eb_ret);
@@ -3741,12 +3750,14 @@ retry:
 	ret = filemap_add_folio(mapping, eb->folios[i], index + i,
 				GFP_NOFS | __GFP_NOFAIL);
 	if (!ret)
-		return 0;
+		goto finish;
 
 	existing_folio = filemap_lock_folio(mapping, index + i);
 	/* The page cache only exists for a very short time, just retry. */
-	if (IS_ERR(existing_folio))
+	if (IS_ERR(existing_folio)) {
+		existing_folio = NULL;
 		goto retry;
+	}
 
 	/* For now, we should only have single-page folios for btree inode. */
 	ASSERT(folio_nr_pages(existing_folio) == 1);
@@ -3757,14 +3768,13 @@ retry:
 		return -EAGAIN;
 	}
 
-	if (fs_info->nodesize < PAGE_SIZE) {
-		/*
-		 * We're going to reuse the existing page, can drop our page
-		 * and subpage structure now.
-		 */
+finish:
+	spin_lock(&mapping->i_private_lock);
+	if (existing_folio && fs_info->nodesize < PAGE_SIZE) {
+		/* We're going to reuse the existing page, can drop our folio now. */
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
-	} else {
+	} else if (existing_folio) {
 		struct extent_buffer *existing_eb;
 
 		existing_eb = grab_extent_buffer(fs_info,
@@ -3772,6 +3782,7 @@ retry:
 		if (existing_eb) {
 			/* The extent buffer still exists, we can use it directly. */
 			*found_eb_ret = existing_eb;
+			spin_unlock(&mapping->i_private_lock);
 			folio_unlock(existing_folio);
 			folio_put(existing_folio);
 			return 1;
@@ -3780,6 +3791,22 @@ retry:
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
 	}
+	eb->folio_size = folio_size(eb->folios[i]);
+	eb->folio_shift = folio_shift(eb->folios[i]);
+	/* Should not fail, as we have preallocated the memory. */
+	ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc);
+	ASSERT(!ret);
+	/*
+	 * To inform we have an extra eb under allocation, so that
+	 * detach_extent_buffer_page() won't release the folio private when the
+	 * eb hasn't been inserted into radix tree yet.
+	 *
+	 * The ref will be decreased when the eb releases the page, in
+	 * detach_extent_buffer_page().  Thus needs no special handling in the
+	 * error path.
+	 */
+	btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]);
+	spin_unlock(&mapping->i_private_lock);
 	return 0;
 }
 
@@ -3791,7 +3818,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int attached = 0;
 	struct extent_buffer *eb;
 	struct extent_buffer *existing_eb = NULL;
-	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
 	bool page_contig = true;
@@ -3857,7 +3883,7 @@ reallocate:
 	for (int i = 0; i < num_folios; i++) {
 		struct folio *folio;
 
-		ret = attach_eb_folio_to_filemap(eb, i, &existing_eb);
+		ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb);
 		if (ret > 0) {
 			ASSERT(existing_eb);
 			goto out;
@@ -3894,24 +3920,6 @@ reallocate:
 		 * and free the allocated page.
 		 */
 		folio = eb->folios[i];
-		eb->folio_size = folio_size(folio);
-		eb->folio_shift = folio_shift(folio);
-		spin_lock(&mapping->i_private_lock);
-		/* Should not fail, as we have preallocated the memory */
-		ret = attach_extent_buffer_folio(eb, folio, prealloc);
-		ASSERT(!ret);
-		/*
-		 * To inform we have extra eb under allocation, so that
-		 * detach_extent_buffer_page() won't release the folio private
-		 * when the eb hasn't yet been inserted into radix tree.
-		 *
-		 * The ref will be decreased when the eb released the page, in
-		 * detach_extent_buffer_page().
-		 * Thus needs no special handling in error path.
-		 */
-		btrfs_folio_inc_eb_refs(fs_info, folio);
-		spin_unlock(&mapping->i_private_lock);
-
 		WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
 
 		/*
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 40e5f7f2fc..1167899a16 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -468,6 +468,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 		}
 		if (!qgroup) {
 			struct btrfs_qgroup *prealloc;
+			struct btrfs_root *tree_root = fs_info->tree_root;
 
 			prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 			if (!prealloc) {
@@ -475,6 +476,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				goto out;
 			}
 			qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset);
+			/*
+			 * If a qgroup exists for a subvolume ID, it is possible
+			 * that subvolume has been deleted, in which case
+			 * re-using that ID would lead to incorrect accounting.
+			 *
+			 * Ensure that we skip any such subvol ids.
+			 *
+			 * We don't need to lock because this is only called
+			 * during mount before we start doing things like creating
+			 * subvolumes.
+			 */
+			if (is_fstree(qgroup->qgroupid) &&
+			    qgroup->qgroupid > tree_root->free_objectid)
+				/*
+				 * Don't need to check against BTRFS_LAST_FREE_OBJECTID,
+				 * as it will get checked on the next call to
+				 * btrfs_get_free_objectid.
+				 */
+				tree_root->free_objectid = qgroup->qgroupid + 1;
 		}
 		ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
 		if (ret < 0)
@@ -3129,7 +3149,7 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 	qgids = res->qgroups;
 
 	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
-		qgids[i] = qg_list->group->qgroupid;
+		qgids[i++] = qg_list->group->qgroupid;
 
 	*inherit = res;
 	return 0;
@@ -3826,14 +3846,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		/* we're resuming qgroup rescan at mount time */
 		if (!(fs_info->qgroup_flags &
 		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
 			ret = -EINVAL;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		}
 
 		if (ret)
@@ -3844,14 +3864,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (init_flags) {
 		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
-			btrfs_warn(fs_info,
-				   "qgroup rescan is already in progress");
 			ret = -EINPROGRESS;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		} else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
 			/* Quota disable is in progress */
 			ret = -EBUSY;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7e44ccaf34..fa6964de34 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -119,6 +119,7 @@ enum {
 	Opt_thread_pool,
 	Opt_treelog,
 	Opt_user_subvol_rm_allowed,
+	Opt_norecovery,
 
 	/* Rescue options */
 	Opt_rescue,
@@ -245,6 +246,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = {
 	__fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL),
 	/* Deprecated, with alias rescue=usebackuproot */
 	__fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL),
+	/* For compatibility only, alias for "rescue=nologreplay". */
+	fsparam_flag("norecovery", Opt_norecovery),
 
 	/* Debugging options. */
 	fsparam_flag_no("enospc_debug", Opt_enospc_debug),
@@ -438,6 +441,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		"'nologreplay' is deprecated, use 'rescue=nologreplay' instead");
 		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 		break;
+	case Opt_norecovery:
+		btrfs_info(NULL,
+"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'");
+		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
+		break;
 	case Opt_flushoncommit:
 		if (result.negated)
 			btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 472918a5bc..d4fc5fedd8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4856,18 +4856,23 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			path->slots[0]++;
 			continue;
 		}
-		if (!dropped_extents) {
-			/*
-			 * Avoid logging extent items logged in past fsync calls
-			 * and leading to duplicate keys in the log tree.
-			 */
+		/*
+		 * Avoid overlapping items in the log tree. The first time we
+		 * get here, get rid of everything from a past fsync. After
+		 * that, if the current extent starts before the end of the last
+		 * extent we copied, truncate the last one. This can happen if
+		 * an ordered extent completion modifies the subvolume tree
+		 * while btrfs_next_leaf() has the tree unlocked.
+		 */
+		if (!dropped_extents || key.offset < truncate_offset) {
 			ret = truncate_inode_items(trans, root->log_root, inode,
-						   truncate_offset,
+						   min(key.offset, truncate_offset),
 						   BTRFS_EXTENT_DATA_KEY);
 			if (ret)
 				goto out;
 			dropped_extents = true;
 		}
+		truncate_offset = btrfs_file_extent_end(path);
 		if (ins_nr == 0)
 			start_slot = slot;
 		ins_nr++;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 4cba80b343..459514da16 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1290,7 +1290,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct btrfs_chunk_map *map)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
-	struct btrfs_device *device = map->stripes[zone_idx].dev;
+	struct btrfs_device *device;
 	int dev_replace_is_ongoing = 0;
 	unsigned int nofs_flag;
 	struct blk_zone zone;
@@ -1298,7 +1298,11 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 
 	info->physical = map->stripes[zone_idx].physical;
 
+	down_read(&dev_replace->rwsem);
+	device = map->stripes[zone_idx].dev;
+
 	if (!device->bdev) {
+		up_read(&dev_replace->rwsem);
 		info->alloc_offset = WP_MISSING_DEV;
 		return 0;
 	}
@@ -1308,6 +1312,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		__set_bit(zone_idx, active);
 
 	if (!btrfs_dev_is_sequential(device, info->physical)) {
+		up_read(&dev_replace->rwsem);
 		info->alloc_offset = WP_CONVENTIONAL;
 		return 0;
 	}
@@ -1315,11 +1320,9 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	/* This zone will be used for allocation, so mark this zone non-empty. */
 	btrfs_dev_clear_zone_empty(device, info->physical);
 
-	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
 	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
 		btrfs_dev_clear_zone_empty(dev_replace->tgtdev, info->physical);
-	up_read(&dev_replace->rwsem);
 
 	/*
 	 * The group is mapped to a sequential zone. Get the zone write pointer
@@ -1330,6 +1333,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	ret = btrfs_get_dev_zone(device, info->physical, &zone);
 	memalloc_nofs_restore(nofs_flag);
 	if (ret) {
+		up_read(&dev_replace->rwsem);
 		if (ret != -EIO && ret != -EOPNOTSUPP)
 			return ret;
 		info->alloc_offset = WP_MISSING_DEV;
@@ -1341,6 +1345,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		"zoned: unexpected conventional zone %llu on device %s (devid %llu)",
 			zone.start << SECTOR_SHIFT, rcu_str_deref(device->name),
 			device->devid);
+		up_read(&dev_replace->rwsem);
 		return -EIO;
 	}
 
@@ -1368,6 +1373,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 		break;
 	}
 
+	up_read(&dev_replace->rwsem);
+
 	return 0;
 }