1 files changed, 58 insertions, 86 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b79781df70..c03091793a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -29,7 +29,6 @@
 #include "tree-log.h"
 #include "free-space-cache.h"
 #include "free-space-tree.h"
-#include "check-integrity.h"
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "raid56.h"
@@ -245,6 +244,7 @@ blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio)
 	struct extent_buffer *eb = bbio->private;
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	u64 found_start = btrfs_header_bytenr(eb);
+	u64 last_trans;
 	u8 result[BTRFS_CSUM_SIZE];
 	int ret;
 
@@ -282,12 +282,12 @@ blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio)
 	 * Also check the generation, the eb reached here must be newer than
 	 * last committed. Or something seriously wrong happened.
 	 */
-	if (unlikely(btrfs_header_generation(eb) <= fs_info->last_trans_committed)) {
+	last_trans = btrfs_get_last_trans_committed(fs_info);
+	if (unlikely(btrfs_header_generation(eb) <= last_trans)) {
 		ret = -EUCLEAN;
 		btrfs_err(fs_info,
 			"block=%llu bad generation, have %llu expect > %llu",
-			  eb->start, btrfs_header_generation(eb),
-			  fs_info->last_trans_committed);
+			  eb->start, btrfs_header_generation(eb), last_trans);
 		goto error;
 	}
 	write_extent_buffer(eb, result, 0, fs_info->csum_size);
@@ -318,9 +318,10 @@ static bool check_tree_block_fsid(struct extent_buffer *eb)
 			   BTRFS_FSID_SIZE);
 
 	/*
-	 * alloc_fs_devices() copies the fsid into metadata_uuid if the
-	 * metadata_uuid is unset in the superblock, including for a seed device.
-	 * So, we can use fs_devices->metadata_uuid.
+	 * alloc_fsid_devices() copies the fsid into fs_devices::metadata_uuid.
+	 * This is then overwritten by metadata_uuid if it is present in the
+	 * device_list_add(). The same true for a seed device as well. So use of
+	 * fs_devices::metadata_uuid is appropriate here.
 	 */
 	if (memcmp(fsid, fs_info->fs_devices->metadata_uuid, BTRFS_FSID_SIZE) == 0)
 		return false;
@@ -675,9 +676,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	refcount_set(&root->refs, 1);
 	atomic_set(&root->snapshot_force_cow, 0);
 	atomic_set(&root->nr_swapfiles, 0);
-	root->log_transid = 0;
+	btrfs_set_root_log_transid(root, 0);
 	root->log_transid_committed = -1;
-	root->last_log_commit = 0;
+	btrfs_set_root_last_log_commit(root, 0);
 	root->anon_dev = 0;
 	if (!dummy) {
 		extent_io_tree_init(fs_info, &root->dirty_log_pages,
@@ -859,7 +860,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	root->root_key.offset = 0;
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
-				      BTRFS_NESTING_NORMAL);
+				      0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		leaf = NULL;
@@ -936,7 +937,7 @@ int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
 	 */
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
-			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
+			NULL, 0, 0, 0, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf))
 		return PTR_ERR(leaf);
 
@@ -1004,9 +1005,9 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 
 	WARN_ON(root->log_root);
 	root->log_root = log_root;
-	root->log_transid = 0;
+	btrfs_set_root_log_transid(root, 0);
 	root->log_transid_committed = -1;
-	root->last_log_commit = 0;
+	btrfs_set_root_last_log_commit(root, 0);
 	return 0;
 }
 
@@ -1179,6 +1180,8 @@ static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
 		return btrfs_grab_root(fs_info->block_group_root);
 	case BTRFS_FREE_SPACE_TREE_OBJECTID:
 		return btrfs_grab_root(btrfs_global_root(fs_info, &key));
+	case BTRFS_RAID_STRIPE_TREE_OBJECTID:
+		return btrfs_grab_root(fs_info->stripe_root);
 	default:
 		return NULL;
 	}
@@ -1259,6 +1262,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(fs_info->fs_root);
 	btrfs_put_root(fs_info->data_reloc_root);
 	btrfs_put_root(fs_info->block_group_root);
+	btrfs_put_root(fs_info->stripe_root);
 	btrfs_check_leaked_roots(fs_info);
 	btrfs_extent_buffer_leak_debug_check(fs_info);
 	kfree(fs_info->super_copy);
@@ -1311,8 +1315,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
-		/* Shouldn't get preallocated anon_dev for cached roots */
-		ASSERT(!anon_dev);
+		/*
+		 * Some other caller may have read out the newly inserted
+		 * subvolume already (for things like backref walk etc).  Not
+		 * that common but still possible.  In that case, we just need
+		 * to free the anon_dev.
+		 */
+		if (unlikely(anon_dev)) {
+			free_anon_bdev(anon_dev);
+			anon_dev = 0;
+		}
+
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1402,7 +1415,8 @@ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
 }
 
 /*
- * btrfs_get_fs_root_commit_root - return a root for the given objectid
+ * Return a root for the given objectid.
+ *
  * @fs_info:	the fs_info
  * @objectid:	the objectid we need to lookup
  *
@@ -1699,11 +1713,11 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 }
 
 /*
- * read_backup_root - Reads a backup root based on the passed priority. Prio 0
- * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
+ * Reads a backup root based on the passed priority. Prio 0 is the newest, prio
+ * 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
  *
- * fs_info - filesystem whose backup roots need to be read
- * priority - priority of backup root required
+ * @fs_info:  filesystem whose backup roots need to be read
+ * @priority: priority of backup root required
  *
  * Returns backup root index on success and -EINVAL otherwise.
  */
@@ -1803,6 +1817,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 	free_root_extent_buffers(info->fs_root);
 	free_root_extent_buffers(info->data_reloc_root);
 	free_root_extent_buffers(info->block_group_root);
+	free_root_extent_buffers(info->stripe_root);
 	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 }
@@ -2262,7 +2277,6 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (!IS_ERR(root)) {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
-		set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 		fs_info->quota_root = root;
 	}
 
@@ -2279,6 +2293,20 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 		fs_info->uuid_root = root;
 	}
 
+	if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) {
+		location.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID;
+		root = btrfs_read_tree_root(tree_root, &location);
+		if (IS_ERR(root)) {
+			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+				ret = PTR_ERR(root);
+				goto out;
+			}
+		} else {
+			set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+			fs_info->stripe_root = root;
+		}
+	}
+
 	return 0;
 out:
 	btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d",
@@ -2381,7 +2409,8 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
-	if (memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) {
+	if (!fs_info->fs_devices->temp_fsid &&
+	    memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
 		"superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
 			  sb->fsid, fs_info->fs_devices->fsid);
@@ -2634,7 +2663,7 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 
 		/* All successful */
 		fs_info->generation = btrfs_header_generation(tree_root->node);
-		fs_info->last_trans_committed = fs_info->generation;
+		btrfs_set_last_trans_committed(fs_info, fs_info->generation);
 		fs_info->last_reloc_trans = 0;
 
 		/* Always begin writing backup roots after the one being used */
@@ -2735,9 +2764,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	spin_lock_init(&fs_info->ordered_root_lock);
 
 	btrfs_init_scrub(fs_info);
-#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	fs_info->check_integrity_print_mask = 0;
-#endif
 	btrfs_init_balance(fs_info);
 	btrfs_init_async_reclaim_work(fs_info);
 
@@ -3157,7 +3183,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	u32 nodesize;
 	u32 stripesize;
 	u64 generation;
-	u64 features;
 	u16 csum_type;
 	struct btrfs_super_block *disk_super;
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
@@ -3240,15 +3265,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 
 	disk_super = fs_info->super_copy;
 
-
-	features = btrfs_super_flags(disk_super);
-	if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) {
-		features &= ~BTRFS_SUPER_FLAG_CHANGING_FSID_V2;
-		btrfs_set_super_flags(disk_super, features);
-		btrfs_info(fs_info,
-			"found metadata UUID change in progress flag, clearing");
-	}
-
 	memcpy(fs_info->super_for_commit, fs_info->super_copy,
 	       sizeof(*fs_info->super_for_commit));
 
@@ -3510,18 +3526,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 				   "auto enabling async discard");
 	}
 
-#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	if (btrfs_test_opt(fs_info, CHECK_INTEGRITY)) {
-		ret = btrfsic_mount(fs_info, fs_devices,
-				    btrfs_test_opt(fs_info,
-					CHECK_INTEGRITY_DATA) ? 1 : 0,
-				    fs_info->check_integrity_print_mask);
-		if (ret)
-			btrfs_warn(fs_info,
-				"failed to initialize integrity check module: %d",
-				ret);
-	}
-#endif
 	ret = btrfs_read_qgroup_config(fs_info);
 	if (ret)
 		goto fail_trans_kthread;
@@ -3821,8 +3825,6 @@ static int write_dev_supers(struct btrfs_device *device,
 		 */
 		if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER))
 			bio->bi_opf |= REQ_FUA;
-
-		btrfsic_check_bio(bio);
 		submit_bio(bio);
 
 		if (btrfs_advance_sb_log(device, i))
@@ -3918,28 +3920,11 @@ static void write_dev_flush(struct btrfs_device *device)
 
 	device->last_flush_error = BLK_STS_OK;
 
-#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	/*
-	 * When a disk has write caching disabled, we skip submission of a bio
-	 * with flush and sync requests before writing the superblock, since
-	 * it's not needed. However when the integrity checker is enabled, this
-	 * results in reports that there are metadata blocks referred by a
-	 * superblock that were not properly flushed. So don't skip the bio
-	 * submission only when the integrity checker is enabled for the sake
-	 * of simplicity, since this is a debug tool and not meant for use in
-	 * non-debug builds.
-	 */
-	if (!bdev_write_cache(device->bdev))
-		return;
-#endif
-
 	bio_init(bio, device->bdev, NULL, 0,
 		 REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH);
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
-
-	btrfsic_check_bio(bio);
 	submit_bio(bio);
 	set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state);
 }
@@ -4415,11 +4400,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 
 	iput(fs_info->btree_inode);
 
-#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	if (btrfs_test_opt(fs_info, CHECK_INTEGRITY))
-		btrfsic_unmount(fs_info->fs_devices);
-#endif
-
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
 	btrfs_close_devices(fs_info->fs_devices);
 }
@@ -4442,22 +4422,13 @@ void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans,
 	/* This is an active transaction (its state < TRANS_STATE_UNBLOCKED). */
 	ASSERT(trans->transid == fs_info->generation);
 	btrfs_assert_tree_write_locked(buf);
-	if (transid != fs_info->generation) {
-		WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n",
-			buf->start, transid, fs_info->generation);
+	if (unlikely(transid != fs_info->generation)) {
 		btrfs_abort_transaction(trans, -EUCLEAN);
+		btrfs_crit(fs_info,
+"dirty buffer transid mismatch, logical %llu found transid %llu running transid %llu",
+			   buf->start, transid, fs_info->generation);
 	}
 	set_extent_buffer_dirty(buf);
-#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	/*
-	 * btrfs_check_leaf() won't check item data if we don't have WRITTEN
-	 * set, so this will only validate the basic structure of the items.
-	 */
-	if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(buf)) {
-		btrfs_print_leaf(buf);
-		ASSERT(0);
-	}
-#endif
 }
 
 static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info,
@@ -4617,6 +4588,7 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				list_del(&ref->add_list);
 			atomic_dec(&delayed_refs->num_entries);
 			btrfs_put_delayed_ref(ref);
+			btrfs_delayed_refs_rsv_release(fs_info, 1, 0);
 		}
 		if (head->must_insert_reserved)
 			pin_bytes = true;
@@ -4814,7 +4786,7 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 
 		spin_unlock(&cur_trans->dirty_bgs_lock);
 		btrfs_put_block_group(cache);
-		btrfs_delayed_refs_rsv_release(fs_info, 1);
+		btrfs_dec_delayed_refs_rsv_bg_updates(fs_info);
 		spin_lock(&cur_trans->dirty_bgs_lock);
 	}
 	spin_unlock(&cur_trans->dirty_bgs_lock);