Merge branch 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/mason/linux-btrfs

Pull more btrfs updates from Chris Mason:
 "These are mostly fixes that we've been testing, but also we grabbed
  and tested a few small cleanups that had been on the list for a while.

  Zhao Lei's patchset also fixes some early ENOSPC buglets"

* 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (21 commits)
  btrfs: raid56: Use raid_write_end_io for scrub
  btrfs: Remove unnecessary ClearPageUptodate for raid56
  btrfs: use rbio->nr_pages to reduce calculation
  btrfs: Use unified stripe_page's index calculation
  btrfs: Fix calculation of rbio->dbitmap's size calculation
  btrfs: Fix no_space in write and rm loop
  btrfs: merge functions for wait snapshot creation
  btrfs: delete unused argument in btrfs_copy_from_user
  btrfs: Use direct way to determine raid56 write/recover mode
  btrfs: Small cleanup for get index_srcdev loop
  btrfs: Enhance chunk validation check
  btrfs: Enhance super validation check
  Btrfs: fix deadlock running delayed iputs at transaction commit time
  Btrfs: fix typo in log message when starting a balance
  btrfs: remove duplicate const specifier
  btrfs: initialize the seq counter in struct btrfs_device
  Btrfs: clean up an error code in btrfs_init_space_info()
  btrfs: fix iterator with update error in backref.c
  Btrfs: fix output of compression message in btrfs_parse_options()
  Btrfs: Initialize btrfs_root->highest_objectid when loading tree root and subvolume roots
  ...

fs/btrfs/backref.c

@@ -560,13 +560,13 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info,
  */
 static void __merge_refs(struct list_head *head, int mode)
 {
-	struct __prelim_ref *ref1;
+	struct __prelim_ref *pos1;
 
-	list_for_each_entry(ref1, head, list) {
-		struct __prelim_ref *ref2 = ref1, *tmp;
+	list_for_each_entry(pos1, head, list) {
+		struct __prelim_ref *pos2 = pos1, *tmp;
 
-		list_for_each_entry_safe_continue(ref2, tmp, head, list) {
-			struct __prelim_ref *xchg;
+		list_for_each_entry_safe_continue(pos2, tmp, head, list) {
+			struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
 			struct extent_inode_elem *eie;
 
 			if (!ref_for_same_block(ref1, ref2))

fs/btrfs/ctree.h

@@ -1614,7 +1614,7 @@ struct btrfs_fs_info {
 
 	spinlock_t delayed_iput_lock;
 	struct list_head delayed_iputs;
-	struct rw_semaphore delayed_iput_sem;
+	struct mutex cleaner_delayed_iput_mutex;
 
 	/* this protects tree_mod_seq_list */
 	spinlock_t tree_mod_seq_lock;
@@ -3641,6 +3641,7 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 int __get_raid_index(u64 flags);
 int btrfs_start_write_no_snapshoting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshoting(struct btrfs_root *root);
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			const u64 type);

fs/btrfs/dev-replace.c

@@ -614,7 +614,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 		em = lookup_extent_mapping(em_tree, start, (u64)-1);
 		if (!em)
 			break;
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++)
 			if (srcdev == map->stripes[i].dev)
 				map->stripes[i].dev = tgtdev;

fs/btrfs/disk-io.c

@@ -55,6 +55,12 @@
 #include <asm/cpufeature.h>
 #endif
 
+#define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
+				 BTRFS_HEADER_FLAG_RELOC |\
+				 BTRFS_SUPER_FLAG_ERROR |\
+				 BTRFS_SUPER_FLAG_SEEDING |\
+				 BTRFS_SUPER_FLAG_METADUMP)
+
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
@@ -1583,8 +1589,23 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	ret = get_anon_bdev(&root->anon_dev);
 	if (ret)
 		goto free_writers;
+
+	mutex_lock(&root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(root,
+					&root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&root->objectid_mutex);
+		goto free_root_dev;
+	}
+
+	ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&root->objectid_mutex);
+
 	return 0;
 
+free_root_dev:
+	free_anon_bdev(root->anon_dev);
 free_writers:
 	btrfs_free_subvolume_writers(root->subv_writers);
 fail:
@@ -1786,7 +1807,10 @@ static int cleaner_kthread(void *arg)
 			goto sleep;
 		}
 
+		mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
 		btrfs_run_delayed_iputs(root);
+		mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -2556,8 +2580,8 @@ int open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
+	mutex_init(&fs_info->cleaner_delayed_iput_mutex);
 	seqlock_init(&fs_info->profiles_lock);
-	init_rwsem(&fs_info->delayed_iput_sem);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
 	INIT_LIST_HEAD(&fs_info->space_info);
@@ -2742,26 +2766,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	/*
-	 * Leafsize and nodesize were always equal, this is only a sanity check.
-	 */
-	if (le32_to_cpu(disk_super->__unused_leafsize) !=
-	    btrfs_super_nodesize(disk_super)) {
-		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
-		       "blocksizes don't match.  node %d leaf %d\n",
-		       btrfs_super_nodesize(disk_super),
-		       le32_to_cpu(disk_super->__unused_leafsize));
-		err = -EINVAL;
-		goto fail_alloc;
-	}
-	if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
-		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
-		       "blocksize (%d) was too large\n",
-		       btrfs_super_nodesize(disk_super));
-		err = -EINVAL;
-		goto fail_alloc;
-	}
-
 	features = btrfs_super_incompat_flags(disk_super);
 	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
 	if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
@@ -2833,17 +2837,6 @@ int open_ctree(struct super_block *sb,
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
 
-	if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
-		printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id);
-		goto fail_sb_buffer;
-	}
-
-	if (sectorsize != PAGE_SIZE) {
-		printk(KERN_ERR "BTRFS: incompatible sector size (%lu) "
-		       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
-		goto fail_sb_buffer;
-	}
-
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);
@@ -2915,6 +2908,18 @@ int open_ctree(struct super_block *sb,
 	tree_root->commit_root = btrfs_root_node(tree_root);
 	btrfs_set_root_refs(&tree_root->root_item, 1);
 
+	mutex_lock(&tree_root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(tree_root,
+					&tree_root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&tree_root->objectid_mutex);
+		goto recovery_tree_root;
+	}
+
+	ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&tree_root->objectid_mutex);
+
 	ret = btrfs_read_roots(fs_info, tree_root);
 	if (ret)
 		goto recovery_tree_root;
@@ -4018,8 +4023,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
 	struct btrfs_super_block *sb = fs_info->super_copy;
+	u64 nodesize = btrfs_super_nodesize(sb);
+	u64 sectorsize = btrfs_super_sectorsize(sb);
 	int ret = 0;
 
+	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+		printk(KERN_ERR "BTRFS: no valid FS found\n");
+		ret = -EINVAL;
+	}
+	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
+		printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
 	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
 		printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
 				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
@@ -4037,31 +4051,46 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	}
 
 	/*
-	 * The common minimum, we don't know if we can trust the nodesize/sectorsize
-	 * items yet, they'll be verified later. Issue just a warning.
+	 * Check sectorsize and nodesize first, other check will need it.
+	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
 	 */
-	if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
+	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+		ret = -EINVAL;
+	}
+	/* Only PAGE SIZE is supported yet */
+	if (sectorsize != PAGE_CACHE_SIZE) {
+		printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
+				sectorsize, PAGE_CACHE_SIZE);
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+		ret = -EINVAL;
+	}
+	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+		printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
+				le32_to_cpu(sb->__unused_leafsize),
+				nodesize);
+		ret = -EINVAL;
+	}
+
+	/* Root alignment check */
+	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
 		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
 				btrfs_super_root(sb));
-	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
+		ret = -EINVAL;
+	}
+	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
 		printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
 				btrfs_super_chunk_root(sb));
-	if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
-		printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
-				btrfs_super_log_root(sb));
-
-	/*
-	 * Check the lower bound, the alignment and other constraints are
-	 * checked later.
-	 */
-	if (btrfs_super_nodesize(sb) < 4096) {
-		printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n",
-				btrfs_super_nodesize(sb));
 		ret = -EINVAL;
 	}
-	if (btrfs_super_sectorsize(sb) < 4096) {
-		printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n",
-				btrfs_super_sectorsize(sb));
+	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+		printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
+				btrfs_super_log_root(sb));
 		ret = -EINVAL;
 	}
 

fs/btrfs/extent-tree.c

@@ -4139,8 +4139,10 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
 		    !atomic_read(&root->fs_info->open_ioctl_trans)) {
 			need_commit--;
 
-			if (need_commit > 0)
+			if (need_commit > 0) {
+				btrfs_start_delalloc_roots(fs_info, 0, -1);
 				btrfs_wait_ordered_roots(fs_info, -1);
+			}
 
 			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
@@ -4153,11 +4155,12 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
 				if (ret)
 					return ret;
 				/*
-				 * make sure that all running delayed iput are
-				 * done
+				 * The cleaner kthread might still be doing iput
+				 * operations. Wait for it to finish so that
+				 * more space is released.
 				 */
-				down_write(&root->fs_info->delayed_iput_sem);
-				up_write(&root->fs_info->delayed_iput_sem);
+				mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+				mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
 				goto again;
 			} else {
 				btrfs_end_transaction(trans, root);
@@ -10399,7 +10402,7 @@ btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
 	 * more device items and remove one chunk item), but this is done at
 	 * btrfs_remove_chunk() through a call to check_system_chunk().
 	 */
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	num_items = 3 + map->num_stripes;
 	free_extent_map(em);
 
@@ -10586,7 +10589,7 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 
 	disk_super = fs_info->super_copy;
 	if (!btrfs_super_root(disk_super))
-		return 1;
+		return -EINVAL;
 
 	features = btrfs_super_incompat_flags(disk_super);
 	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
@@ -10816,3 +10819,23 @@ int btrfs_start_write_no_snapshoting(struct btrfs_root *root)
 	}
 	return 1;
 }
+
+static int wait_snapshoting_atomic_t(atomic_t *a)
+{
+	schedule();
+	return 0;
+}
+
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
+{
+	while (true) {
+		int ret;
+
+		ret = btrfs_start_write_no_snapshoting(root);
+		if (ret)
+			break;
+		wait_on_atomic_t(&root->will_be_snapshoted,
+				 wait_snapshoting_atomic_t,
+				 TASK_UNINTERRUPTIBLE);
+	}
+}

fs/btrfs/extent_map.c

@@ -76,7 +76,7 @@ void free_extent_map(struct extent_map *em)
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
 		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-			kfree(em->bdev);
+			kfree(em->map_lookup);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }

fs/btrfs/extent_map.h

@@ -32,7 +32,15 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	struct block_device *bdev;
+	union {
+		struct block_device *bdev;
+
+		/*
+		 * used for chunk mappings
+		 * flags & EXTENT_FLAG_FS_MAPPING must be set
+		 */
+		struct map_lookup *map_lookup;
+	};
 	atomic_t refs;
 	unsigned int compress_type;
 	struct list_head list;

fs/btrfs/file.c

@@ -406,8 +406,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
 /* simple helper to fault in pages and copy.  This should go away
  * and be replaced with calls into generic code.
  */
-static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
-					 size_t write_bytes,
+static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes,
 					 struct page **prepared_pages,
 					 struct iov_iter *i)
 {
@@ -1588,8 +1587,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			ret = 0;
 		}
 
-		copied = btrfs_copy_from_user(pos, num_pages,
-					   write_bytes, pages, i);
+		copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
 
 		/*
 		 * if we have trouble faulting in the pages, fall

fs/btrfs/inode-map.c

@@ -515,7 +515,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	return ret;
 }
 
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
-	if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_find_highest_objectid(root,
-						  &root->highest_objectid);
-		if (ret)
-			goto out;
-	}
-
 	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
 		ret = -ENOSPC;
 		goto out;

fs/btrfs/inode-map.h

@@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 			 struct btrfs_trans_handle *trans);
 
 int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 
 #endif