Merge branch 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/kernel/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 @@ retry_root_backup:
 	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 @@ commit_trans:
 		    !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 @@ commit_trans:
 				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 @@ again:
 			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 @@ out:
 	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

fs/btrfs/inode.c

@@ -3134,7 +3134,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	down_read(&fs_info->delayed_iput_sem);
 	spin_lock(&fs_info->delayed_iput_lock);
 	while (!list_empty(&fs_info->delayed_iputs)) {
 		struct btrfs_inode *inode;
@@ -3153,7 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 		spin_lock(&fs_info->delayed_iput_lock);
 	}
 	spin_unlock(&fs_info->delayed_iput_lock);
-	up_read(&root->fs_info->delayed_iput_sem);
 }
 
 /*
@@ -4874,26 +4872,6 @@ next:
 	return err;
 }
 
-static int wait_snapshoting_atomic_t(atomic_t *a)
-{
-	schedule();
-	return 0;
-}
-
-static void 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);
-	}
-}
-
 static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -4925,7 +4903,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * truncation, it must capture all writes that happened before
 		 * this truncation.
 		 */
-		wait_for_snapshot_creation(root);
+		btrfs_wait_for_snapshot_creation(root);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
 		if (ret) {
 			btrfs_end_write_no_snapshoting(root);

fs/btrfs/ioctl.c

@@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
+	mutex_lock(&new_root->objectid_mutex);
+	new_root->highest_objectid = new_dirid;
+	mutex_unlock(&new_root->objectid_mutex);
+
 	/*
 	 * insert the directory item
 	 */

fs/btrfs/raid56.c

@@ -609,13 +609,28 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
 	return 1;
 }
 
+static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe,
+				  int index)
+{
+	return stripe * rbio->stripe_npages + index;
+}
+
+/*
+ * these are just the pages from the rbio array, not from anything
+ * the FS sent down to us
+ */
+static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe,
+				     int index)
+{
+	return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)];
+}
+
 /*
  * helper to index into the pstripe
  */
 static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
 {
-	index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
-	return rbio->stripe_pages[index];
+	return rbio_stripe_page(rbio, rbio->nr_data, index);
 }
 
 /*
@@ -626,10 +641,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
 {
 	if (rbio->nr_data + 1 == rbio->real_stripes)
 		return NULL;
-
-	index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
-		PAGE_CACHE_SHIFT;
-	return rbio->stripe_pages[index];
+	return rbio_stripe_page(rbio, rbio->nr_data + 1, index);
 }
 
 /*
@@ -889,6 +901,7 @@ static void raid_write_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 	int err = bio->bi_error;
+	int max_errors;
 
 	if (err)
 		fail_bio_stripe(rbio, bio);
@@ -901,7 +914,9 @@ static void raid_write_end_io(struct bio *bio)
 	err = 0;
 
 	/* OK, we have read all the stripes we need to. */
-	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+	max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
+		     0 : rbio->bbio->max_errors;
+	if (atomic_read(&rbio->error) > max_errors)
 		err = -EIO;
 
 	rbio_orig_end_io(rbio, err);
@@ -947,8 +962,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
  */
 static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
 {
-	unsigned long nr = stripe_len * nr_stripes;
-	return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE);
+	return DIV_ROUND_UP(stripe_len, PAGE_CACHE_SIZE) * nr_stripes;
 }
 
 /*
@@ -966,8 +980,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
 	void *p;
 
 	rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
-		       DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8),
-			GFP_NOFS);
+		       DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
+		       sizeof(long), GFP_NOFS);
 	if (!rbio)
 		return ERR_PTR(-ENOMEM);
 
@@ -1021,18 +1035,17 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
 		if (!page)
 			return -ENOMEM;
 		rbio->stripe_pages[i] = page;
-		ClearPageUptodate(page);
 	}
 	return 0;
 }
 
-/* allocate pages for just the p/q stripes */
+/* only allocate pages for p/q stripes */
 static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
 {
 	int i;
 	struct page *page;
 
-	i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+	i = rbio_stripe_page_index(rbio, rbio->nr_data, 0);
 
 	for (; i < rbio->nr_pages; i++) {
 		if (rbio->stripe_pages[i])
@@ -1120,18 +1133,6 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
 	}
 }
 
-/*
- * these are just the pages from the rbio array, not from anything
- * the FS sent down to us
- */
-static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page)
-{
-	int index;
-	index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
-	index += page;
-	return rbio->stripe_pages[index];
-}
-
 /*
  * helper function to walk our bio list and populate the bio_pages array with
  * the result.  This seems expensive, but it is faster than constantly
@@ -1175,7 +1176,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 {
 	struct btrfs_bio *bbio = rbio->bbio;
 	void *pointers[rbio->real_stripes];
-	int stripe_len = rbio->stripe_len;
 	int nr_data = rbio->nr_data;
 	int stripe;
 	int pagenr;
@@ -1183,7 +1183,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	int q_stripe = -1;
 	struct bio_list bio_list;
 	struct bio *bio;
-	int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
 	int ret;
 
 	bio_list_init(&bio_list);
@@ -1226,7 +1225,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	else
 		clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
 
-	for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 		struct page *p;
 		/* first collect one page from each data stripe */
 		for (stripe = 0; stripe < nr_data; stripe++) {
@@ -1268,7 +1267,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	 * everything else.
 	 */
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
-		for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1292,7 +1291,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 		if (!bbio->tgtdev_map[stripe])
 			continue;
 
-		for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1506,7 +1505,6 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	int bios_to_read = 0;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
@@ -1525,7 +1523,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	 * stripe
 	 */
 	for (stripe = 0; stripe < rbio->nr_data; stripe++) {
-		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			/*
 			 * we want to find all the pages missing from
@@ -1801,7 +1799,6 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 	int pagenr, stripe;
 	void **pointers;
 	int faila = -1, failb = -1;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	struct page *page;
 	int err;
 	int i;
@@ -1824,7 +1821,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 
 	index_rbio_pages(rbio);
 
-	for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 		/*
 		 * Now we just use bitmap to mark the horizontal stripes in
 		 * which we have data when doing parity scrub.
@@ -1935,7 +1932,7 @@ pstripe:
 		 * other endio functions will fiddle the uptodate bits
 		 */
 		if (rbio->operation == BTRFS_RBIO_WRITE) {
-			for (i = 0;  i < nr_pages; i++) {
+			for (i = 0;  i < rbio->stripe_npages; i++) {
 				if (faila != -1) {
 					page = rbio_stripe_page(rbio, faila, i);
 					SetPageUptodate(page);
@@ -2031,7 +2028,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	int bios_to_read = 0;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
@@ -2055,7 +2051,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 			continue;
 		}
 
-		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *p;
 
 			/*
@@ -2279,37 +2275,11 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
 			if (!page)
 				return -ENOMEM;
 			rbio->stripe_pages[index] = page;
-			ClearPageUptodate(page);
 		}
 	}
 	return 0;
 }
 
-/*
- * end io function used by finish_rmw.  When we finally
- * get here, we've written a full stripe
- */
-static void raid_write_parity_end_io(struct bio *bio)
-{
-	struct btrfs_raid_bio *rbio = bio->bi_private;
-	int err = bio->bi_error;
-
-	if (bio->bi_error)
-		fail_bio_stripe(rbio, bio);
-
-	bio_put(bio);
-
-	if (!atomic_dec_and_test(&rbio->stripes_pending))
-		return;
-
-	err = 0;
-
-	if (atomic_read(&rbio->error))
-		err = -EIO;
-
-	rbio_orig_end_io(rbio, err);
-}
-
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check)
 {
@@ -2462,7 +2432,7 @@ submit_write:
 			break;
 
 		bio->bi_private = rbio;
-		bio->bi_end_io = raid_write_parity_end_io;
+		bio->bi_end_io = raid_write_end_io;
 		submit_bio(WRITE, bio);
 	}
 	return;

fs/btrfs/scrub.c

@@ -2813,7 +2813,7 @@ out:
 
 static inline int scrub_calc_parity_bitmap_len(int nsectors)
 {
-	return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8);
+	return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * sizeof(long);
 }
 
 static void scrub_parity_get(struct scrub_parity *sparity)
@@ -3458,7 +3458,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 		return ret;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (em->start != chunk_offset)
 		goto out;
 

fs/btrfs/super.c

@@ -383,6 +383,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	int ret = 0;
 	char *compress_type;
 	bool compress_force = false;
+	enum btrfs_compression_type saved_compress_type;
+	bool saved_compress_force;
+	int no_compress = 0;
 
 	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
 	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE))
@@ -462,6 +465,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			/* Fallthrough */
 		case Opt_compress:
 		case Opt_compress_type:
+			saved_compress_type = btrfs_test_opt(root, COMPRESS) ?
+				info->compress_type : BTRFS_COMPRESS_NONE;
+			saved_compress_force =
+				btrfs_test_opt(root, FORCE_COMPRESS);
 			if (token == Opt_compress ||
 			    token == Opt_compress_force ||
 			    strcmp(args[0].from, "zlib") == 0) {
@@ -470,6 +477,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
+				no_compress = 0;
 			} else if (strcmp(args[0].from, "lzo") == 0) {
 				compress_type = "lzo";
 				info->compress_type = BTRFS_COMPRESS_LZO;
@@ -477,25 +485,21 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
+				no_compress = 0;
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 				compress_force = false;
+				no_compress++;
 			} else {
 				ret = -EINVAL;
 				goto out;
 			}
 
 			if (compress_force) {
-				btrfs_set_and_info(root, FORCE_COMPRESS,
-						   "force %s compression",
-						   compress_type);
+				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
 			} else {
-				if (!btrfs_test_opt(root, COMPRESS))
-					btrfs_info(root->fs_info,
-						   "btrfs: use %s compression",
-						   compress_type);
 				/*
 				 * If we remount from compress-force=xxx to
 				 * compress=xxx, we need clear FORCE_COMPRESS
@@ -504,6 +508,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				 */
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			}
+			if ((btrfs_test_opt(root, COMPRESS) &&
+			     (info->compress_type != saved_compress_type ||
+			      compress_force != saved_compress_force)) ||
+			    (!btrfs_test_opt(root, COMPRESS) &&
+			     no_compress == 1)) {
+				btrfs_info(root->fs_info,
+					   "%s %s compression",
+					   (compress_force) ? "force" : "use",
+					   compress_type);
+			}
+			compress_force = false;
 			break;
 		case Opt_ssd:
 			btrfs_set_and_info(root, SSD,

fs/btrfs/volumes.c

@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	},
 };
 
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
 	[BTRFS_RAID_RAID1]  = BTRFS_BLOCK_GROUP_RAID1,
 	[BTRFS_RAID_DUP]    = BTRFS_BLOCK_GROUP_DUP,
@@ -233,6 +233,7 @@ static struct btrfs_device *__alloc_device(void)
 	spin_lock_init(&dev->reada_lock);
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
+	btrfs_device_data_ordered_init(dev);
 	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
@@ -1183,7 +1184,7 @@ again:
 		struct map_lookup *map;
 		int i;
 
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++) {
 			u64 end;
 
@@ -2755,7 +2756,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 			free_extent_map(em);
 		return -EINVAL;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	lock_chunks(root->fs_info->chunk_root);
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
@@ -3751,7 +3752,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 	if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
 		btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
 		btrfs_warn(fs_info,
-	"metatdata profile 0x%llx has lower redundancy than data profile 0x%llx",
+	"metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
 			bctl->meta.target, bctl->data.target);
 	}
 
@@ -4718,7 +4719,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		goto error;
 	}
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = start;
 	em->len = num_bytes;
 	em->block_start = 0;
@@ -4813,7 +4814,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
 	stripe_size = em->orig_block_len;
 
@@ -4968,7 +4969,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (map->stripes[i].dev->missing) {
 			miss_ndevs++;
@@ -5048,7 +5049,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		return 1;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
 		ret = map->num_stripes;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
@@ -5084,7 +5085,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		len = map->stripe_len * nr_data_stripes(map);
 	free_extent_map(em);
@@ -5105,7 +5106,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		ret = 1;
 	free_extent_map(em);
@@ -5264,7 +5265,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	offset = logical - em->start;
 
 	stripe_len = map->stripe_len;
@@ -5378,35 +5379,33 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		 * target drive.
 		 */
 		for (i = 0; i < tmp_num_stripes; i++) {
-			if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) {
-				/*
-				 * In case of DUP, in order to keep it
-				 * simple, only add the mirror with the
-				 * lowest physical address
-				 */
-				if (found &&
-				    physical_of_found <=
-				     tmp_bbio->stripes[i].physical)
-					continue;
-				index_srcdev = i;
-				found = 1;
-				physical_of_found =
-					tmp_bbio->stripes[i].physical;
-			}
+			if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
+				continue;
+
+			/*
+			 * In case of DUP, in order to keep it simple, only add
+			 * the mirror with the lowest physical address
+			 */
+			if (found &&
+			    physical_of_found <= tmp_bbio->stripes[i].physical)
+				continue;
+
+			index_srcdev = i;
+			found = 1;
+			physical_of_found = tmp_bbio->stripes[i].physical;
 		}
 
-		if (found) {
-			mirror_num = index_srcdev + 1;
-			patch_the_first_stripe_for_dev_replace = 1;
-			physical_to_patch_in_first_stripe = physical_of_found;
-		} else {
+		btrfs_put_bbio(tmp_bbio);
+
+		if (!found) {
 			WARN_ON(1);
 			ret = -EIO;
-			btrfs_put_bbio(tmp_bbio);
 			goto out;
 		}
 
-		btrfs_put_bbio(tmp_bbio);
+		mirror_num = index_srcdev + 1;
+		patch_the_first_stripe_for_dev_replace = 1;
+		physical_to_patch_in_first_stripe = physical_of_found;
 	} else if (mirror_num > map->num_stripes) {
 		mirror_num = 0;
 	}
@@ -5806,7 +5805,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		free_extent_map(em);
 		return -EIO;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 
 	length = em->len;
 	rmap_len = map->stripe_len;
@@ -6069,7 +6068,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	bbio->fs_info = root->fs_info;
 	atomic_set(&bbio->stripes_pending, bbio->num_stripes);
 
-	if (bbio->raid_map) {
+	if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+	    ((rw & WRITE) || (mirror_num > 1))) {
 		/* In this case, map_length has been set to the length of
 		   a single stripe; not the whole write */
 		if (rw & WRITE) {
@@ -6210,6 +6210,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	struct extent_map *em;
 	u64 logical;
 	u64 length;
+	u64 stripe_len;
 	u64 devid;
 	u8 uuid[BTRFS_UUID_SIZE];
 	int num_stripes;
@@ -6218,6 +6219,37 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 
 	logical = key->offset;
 	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+	/* Validation check */
+	if (!num_stripes) {
+		btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+			  num_stripes);
+		return -EIO;
+	}
+	if (!IS_ALIGNED(logical, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			  "invalid chunk logical %llu", logical);
+		return -EIO;
+	}
+	if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			"invalid chunk length %llu", length);
+		return -EIO;
+	}
+	if (!is_power_of_2(stripe_len)) {
+		btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+			  stripe_len);
+		return -EIO;
+	}
+	if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+	    btrfs_chunk_type(leaf, chunk)) {
+		btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+			  ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+			    BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+			  btrfs_chunk_type(leaf, chunk));
+		return -EIO;
+	}
 
 	read_lock(&map_tree->map_tree.lock);
 	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6234,7 +6266,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	em = alloc_extent_map();
 	if (!em)
 		return -ENOMEM;
-	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
 	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
 	if (!map) {
 		free_extent_map(em);
@@ -6242,7 +6273,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	}
 
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = logical;
 	em->len = length;
 	em->orig_start = 0;
@@ -6944,7 +6975,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
 	/* In order to kick the device replace finish process */
 	lock_chunks(root);
 	list_for_each_entry(em, &transaction->pending_chunks, list) {
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 
 		for (i = 0; i < map->num_stripes; i++) {
 			dev = map->stripes[i].dev;