1 files changed, 109 insertions, 82 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b0ab41da91d1..8da2f380d3c0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -279,6 +279,12 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 
 	len = buf->len - offset;
 	while (len > 0) {
+		/*
+		 * Note: we don't need to check for the err == 1 case here, as
+		 * with the given combination of 'start = BTRFS_CSUM_SIZE (32)'
+		 * and 'min_len = 32' and the currently implemented mapping
+		 * algorithm we cannot cross a page boundary.
+		 */
 		err = map_private_extent_buffer(buf, offset, 32,
 					&kaddr, &map_start, &map_len);
 		if (err)
@@ -477,9 +483,9 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
 	int mirror_num = 0;
 	int failed_mirror = 0;
 
-	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 	io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	while (1) {
+		clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 		ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
 					       mirror_num);
 		if (!ret) {
@@ -493,15 +499,6 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
 				break;
 		}
 
-		/*
-		 * This buffer's crc is fine, but its contents are corrupted, so
-		 * there is no reason to read the other copies, they won't be
-		 * any less wrong.
-		 */
-		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) ||
-		    ret == -EUCLEAN)
-			break;
-
 		num_copies = btrfs_num_copies(fs_info,
 					      eb->start, eb->len);
 		if (num_copies == 1)
@@ -551,7 +548,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 	if (WARN_ON(!PageUptodate(page)))
 		return -EUCLEAN;
 
-	ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
+	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
 			btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
 
 	return csum_tree_block(fs_info, eb, 0);
@@ -566,7 +563,20 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 
 	read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
 	while (fs_devices) {
-		if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
+		u8 *metadata_uuid;
+
+		/*
+		 * Checking the incompat flag is only valid for the current
+		 * fs. For seed devices it's forbidden to have their uuid
+		 * changed so reading ->fsid in this case is fine
+		 */
+		if (fs_devices == fs_info->fs_devices &&
+		    btrfs_fs_incompat(fs_info, METADATA_UUID))
+			metadata_uuid = fs_devices->metadata_uuid;
+		else
+			metadata_uuid = fs_devices->fsid;
+
+		if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) {
 			ret = 0;
 			break;
 		}
@@ -669,19 +679,6 @@ out:
 	return ret;
 }
 
-static int btree_io_failed_hook(struct page *page, int failed_mirror)
-{
-	struct extent_buffer *eb;
-
-	eb = (struct extent_buffer *)page->private;
-	set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
-	eb->read_mirror = failed_mirror;
-	atomic_dec(&eb->io_pages);
-	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(eb, -EIO);
-	return -EIO;	/* we fixed nothing */
-}
-
 static void end_workqueue_bio(struct bio *bio)
 {
 	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
@@ -760,11 +757,22 @@ static void run_one_async_start(struct btrfs_work *work)
 		async->status = ret;
 }
 
+/*
+ * In order to insert checksums into the metadata in large chunks, we wait
+ * until bio submission time.   All the pages in the bio are checksummed and
+ * sums are attached onto the ordered extent record.
+ *
+ * At IO completion time the csums attached on the ordered extent record are
+ * inserted into the tree.
+ */
 static void run_one_async_done(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
+	struct inode *inode;
+	blk_status_t ret;
 
 	async = container_of(work, struct  async_submit_bio, work);
+	inode = async->private_data;
 
 	/* If an error occurred we just want to clean up the bio and move on */
 	if (async->status) {
@@ -773,7 +781,12 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	btrfs_submit_bio_done(async->private_data, async->bio, async->mirror_num);
+	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio,
+			async->mirror_num, 1);
+	if (ret) {
+		async->bio->bi_status = ret;
+		bio_endio(async->bio);
+	}
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -1187,6 +1200,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	refcount_set(&root->refs, 1);
 	atomic_set(&root->will_be_snapshotted, 0);
 	atomic_set(&root->snapshot_force_cow, 0);
+	atomic_set(&root->nr_swapfiles, 0);
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
 	root->last_log_commit = 0;
@@ -1664,9 +1678,8 @@ static int cleaner_kthread(void *arg)
 	struct btrfs_root *root = arg;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int again;
-	struct btrfs_trans_handle *trans;
 
-	do {
+	while (1) {
 		again = 0;
 
 		/* Make the cleaner go to sleep early. */
@@ -1715,42 +1728,16 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
+		if (kthread_should_park())
+			kthread_parkme();
+		if (kthread_should_stop())
+			return 0;
 		if (!again) {
 			set_current_state(TASK_INTERRUPTIBLE);
-			if (!kthread_should_stop())
-				schedule();
+			schedule();
 			__set_current_state(TASK_RUNNING);
 		}
-	} while (!kthread_should_stop());
-
-	/*
-	 * Transaction kthread is stopped before us and wakes us up.
-	 * However we might have started a new transaction and COWed some
-	 * tree blocks when deleting unused block groups for example. So
-	 * make sure we commit the transaction we started to have a clean
-	 * shutdown when evicting the btree inode - if it has dirty pages
-	 * when we do the final iput() on it, eviction will trigger a
-	 * writeback for it which will fail with null pointer dereferences
-	 * since work queues and other resources were already released and
-	 * destroyed by the time the iput/eviction/writeback is made.
-	 */
-	trans = btrfs_attach_transaction(root);
-	if (IS_ERR(trans)) {
-		if (PTR_ERR(trans) != -ENOENT)
-			btrfs_err(fs_info,
-				  "cleaner transaction attach returned %ld",
-				  PTR_ERR(trans));
-	} else {
-		int ret;
-
-		ret = btrfs_commit_transaction(trans);
-		if (ret)
-			btrfs_err(fs_info,
-				  "cleaner open transaction commit returned %d",
-				  ret);
 	}
-
-	return 0;
 }
 
 static int transaction_kthread(void *arg)
@@ -2154,10 +2141,8 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 {
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
-	rwlock_init(&fs_info->dev_replace.lock);
-	atomic_set(&fs_info->dev_replace.blocking_readers, 0);
+	init_rwsem(&fs_info->dev_replace.rwsem);
 	init_waitqueue_head(&fs_info->dev_replace.replace_wait);
-	init_waitqueue_head(&fs_info->dev_replace.read_lock_wq);
 }
 
 static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
@@ -2478,10 +2463,11 @@ static int validate_super(struct btrfs_fs_info *fs_info,
 		ret = -EINVAL;
 	}
 
-	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
+	if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
+		   BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
-			   "dev_item UUID does not match fsid: %pU != %pU",
-			   fs_info->fsid, sb->dev_item.fsid);
+			"dev_item UUID does not match metadata fsid: %pU != %pU",
+			fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid);
 		ret = -EINVAL;
 	}
 
@@ -2692,6 +2678,9 @@ int open_ctree(struct super_block *sb,
 	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
 	btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
 			     BTRFS_BLOCK_RSV_DELOPS);
+	btrfs_init_block_rsv(&fs_info->delayed_refs_rsv,
+			     BTRFS_BLOCK_RSV_DELREFS);
+
 	atomic_set(&fs_info->async_delalloc_pages, 0);
 	atomic_set(&fs_info->defrag_running, 0);
 	atomic_set(&fs_info->qgroup_op_seq, 0);
@@ -2781,6 +2770,9 @@ int open_ctree(struct super_block *sb,
 	fs_info->sectorsize = 4096;
 	fs_info->stripesize = 4096;
 
+	spin_lock_init(&fs_info->swapfile_pins_lock);
+	fs_info->swapfile_pins = RB_ROOT;
+
 	ret = btrfs_alloc_stripe_hash_table(fs_info);
 	if (ret) {
 		err = ret;
@@ -2817,11 +2809,29 @@ int open_ctree(struct super_block *sb,
 	 * the whole block of INFO_SIZE
 	 */
 	memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy));
-	memcpy(fs_info->super_for_commit, fs_info->super_copy,
-	       sizeof(*fs_info->super_for_commit));
 	brelse(bh);
 
-	memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);
+	disk_super = fs_info->super_copy;
+
+	ASSERT(!memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
+		       BTRFS_FSID_SIZE));
+
+	if (btrfs_fs_incompat(fs_info, METADATA_UUID)) {
+		ASSERT(!memcmp(fs_info->fs_devices->metadata_uuid,
+				fs_info->super_copy->metadata_uuid,
+				BTRFS_FSID_SIZE));
+	}
+
+	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));
 
 	ret = btrfs_validate_mount_super(fs_info);
 	if (ret) {
@@ -2830,7 +2840,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	disk_super = fs_info->super_copy;
 	if (!btrfs_super_root(disk_super))
 		goto fail_alloc;
 
@@ -2942,7 +2951,7 @@ int open_ctree(struct super_block *sb,
 
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
-	memcpy(&sb->s_uuid, fs_info->fsid, BTRFS_FSID_SIZE);
+	memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE);
 
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(fs_info);
@@ -3091,7 +3100,7 @@ retry_root_backup:
 
 	if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) {
 		btrfs_warn(fs_info,
-		"writeable mount is not allowed due to too many missing devices");
+		"writable mount is not allowed due to too many missing devices");
 		goto fail_sysfs;
 	}
 
@@ -3760,7 +3769,8 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
 		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
 		memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE);
-		memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_FSID_SIZE);
+		memcpy(dev_item->fsid, dev->fs_devices->metadata_uuid,
+		       BTRFS_FSID_SIZE);
 
 		flags = btrfs_super_flags(sb);
 		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);
@@ -3931,6 +3941,13 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	int ret;
 
 	set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
+	/*
+	 * We don't want the cleaner to start new transactions, add more delayed
+	 * iputs, etc. while we're closing. We can't use kthread_stop() yet
+	 * because that frees the task_struct, and the transaction kthread might
+	 * still try to wake up the cleaner.
+	 */
+	kthread_park(fs_info->cleaner_kthread);
 
 	/* wait for the qgroup rescan worker to stop */
 	btrfs_qgroup_wait_for_completion(fs_info, false);
@@ -3958,9 +3975,8 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 
 	if (!sb_rdonly(fs_info->sb)) {
 		/*
-		 * If the cleaner thread is stopped and there are
-		 * block groups queued for removal, the deletion will be
-		 * skipped when we quit the cleaner thread.
+		 * The cleaner kthread is stopped, so do one final pass over
+		 * unused block groups.
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
@@ -4061,7 +4077,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	/*
 	 * This is a fast path so only do this check if we have sanity tests
-	 * enabled.  Normal people shouldn't be using umapped buffers as dirty
+	 * enabled.  Normal people shouldn't be using unmapped buffers as dirty
 	 * outside of the sanity tests.
 	 */
 	if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags)))
@@ -4359,13 +4375,26 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
 	unpin = pinned_extents;
 again:
 	while (1) {
+		struct extent_state *cached_state = NULL;
+
+		/*
+		 * The btrfs_finish_extent_commit() may get the same range as
+		 * ours between find_first_extent_bit and clear_extent_dirty.
+		 * Hence, hold the unused_bg_unpin_mutex to avoid double unpin
+		 * the same extent range.
+		 */
+		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
-					    EXTENT_DIRTY, NULL);
-		if (ret)
+					    EXTENT_DIRTY, &cached_state);
+		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			break;
+		}
 
-		clear_extent_dirty(unpin, start, end);
+		clear_extent_dirty(unpin, start, end, &cached_state);
+		free_extent_state(cached_state);
 		btrfs_error_unpin_extent_range(fs_info, start, end);
+		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		cond_resched();
 	}
 
@@ -4420,6 +4449,7 @@ 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);
 		spin_lock(&cur_trans->dirty_bgs_lock);
 	}
 	spin_unlock(&cur_trans->dirty_bgs_lock);
@@ -4525,7 +4555,4 @@ static const struct extent_io_ops btree_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	.readpage_io_failed_hook = btree_io_failed_hook,
-
-	/* optional callbacks */
 };