1 files changed, 126 insertions, 72 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a23399e8e3ab..366b335946fa 100644
--- a/fs/btrfs/volumes.c
+++ b/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,
@@ -125,6 +125,7 @@ static int btrfs_relocate_sys_chunks(struct btrfs_root *root);
 static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
+static void btrfs_close_one_device(struct btrfs_device *device);
 
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
@@ -232,6 +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);
 
@@ -1102,7 +1104,7 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	key.objectid = device->devid;
 	key.offset = start;
@@ -1182,7 +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;
 
@@ -1257,6 +1259,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
 	int ret;
 	int slot;
 	struct extent_buffer *l;
+	u64 min_search_start;
+
+	/*
+	 * We don't want to overwrite the superblock on the drive nor any area
+	 * used by the boot loader (grub for example), so we make sure to start
+	 * at an offset of at least 1MB.
+	 */
+	min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
+	search_start = max(search_start, min_search_start);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1271,7 +1282,7 @@ again:
 		goto out;
 	}
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -1397,18 +1408,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,
 			 u64 *start, u64 *len)
 {
-	struct btrfs_root *root = device->dev_root;
-	u64 search_start;
-
 	/* FIXME use last free of some kind */
-
-	/*
-	 * we don't want to overwrite the superblock on the drive,
-	 * so we make sure to start at an offset of at least 1MB
-	 */
-	search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
 	return find_free_dev_extent_start(trans->transaction, device,
-					  num_bytes, search_start, start, len);
+					  num_bytes, 0, start, len);
 }
 
 static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -1642,7 +1644,6 @@ static void update_dev_time(char *path_name)
 		return;
 	file_update_time(filp);
 	filp_close(filp, NULL);
-	return;
 }
 
 static int btrfs_rm_dev_item(struct btrfs_root *root,
@@ -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);
@@ -3406,7 +3407,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	list_for_each_entry(device, devices, dev_list) {
 		old_size = btrfs_device_get_total_bytes(device);
 		size_to_free = div_factor(old_size, 1);
-		size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
+		size_to_free = min_t(u64, size_to_free, SZ_1M);
 		if (!device->writeable ||
 		    btrfs_device_get_total_bytes(device) -
 		    btrfs_device_get_bytes_used(device) > size_to_free ||
@@ -3723,14 +3724,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		goto out;
 	}
 
-	/* allow dup'ed data chunks only in mixed mode */
-	if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-	    (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
-		btrfs_err(fs_info, "dup for data is not allowed");
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* allow to reduce meta or sys integrity only if force set */
 	allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
 			BTRFS_BLOCK_GROUP_RAID10 |
@@ -3756,6 +3749,13 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
+	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,
+	"metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
+			bctl->meta.target, bctl->data.target);
+	}
+
 	if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
 		fs_info->num_tolerated_disk_barrier_failures = min(
 			btrfs_calc_num_tolerated_disk_barrier_failures(fs_info),
@@ -4268,7 +4268,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	lock_chunks(root);
 
@@ -4460,7 +4460,7 @@ static int btrfs_cmp_device_info(const void *a, const void *b)
 static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
 {
 	/* TODO allow them to set a preferred stripe size */
-	return 64 * 1024;
+	return SZ_64K;
 }
 
 static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
@@ -4528,21 +4528,21 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	ncopies = btrfs_raid_array[index].ncopies;
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
-		max_stripe_size = 1024 * 1024 * 1024;
+		max_stripe_size = SZ_1G;
 		max_chunk_size = 10 * max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
 		/* for larger filesystems, use larger metadata chunks */
-		if (fs_devices->total_rw_bytes > 50ULL * 1024 * 1024 * 1024)
-			max_stripe_size = 1024 * 1024 * 1024;
+		if (fs_devices->total_rw_bytes > 50ULL * SZ_1G)
+			max_stripe_size = SZ_1G;
 		else
-			max_stripe_size = 256 * 1024 * 1024;
+			max_stripe_size = SZ_256M;
 		max_chunk_size = max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
-		max_stripe_size = 32 * 1024 * 1024;
+		max_stripe_size = SZ_32M;
 		max_chunk_size = 2 * max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS_SYS_CHUNK;
@@ -4719,7 +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;
@@ -4793,7 +4793,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 	u64 dev_offset;
 	u64 stripe_size;
 	int i = 0;
-	int ret;
+	int ret = 0;
 
 	em_tree = &extent_root->fs_info->mapping_tree.map_tree;
 	read_lock(&em_tree->lock);
@@ -4814,7 +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;
 
@@ -4824,20 +4824,32 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
+	/*
+	 * Take the device list mutex to prevent races with the final phase of
+	 * a device replace operation that replaces the device object associated
+	 * with the map's stripes, because the device object's id can change
+	 * at any time during that final phase of the device replace operation
+	 * (dev-replace.c:btrfs_dev_replace_finishing()).
+	 */
+	mutex_lock(&chunk_root->fs_info->fs_devices->device_list_mutex);
 	for (i = 0; i < map->num_stripes; i++) {
 		device = map->stripes[i].dev;
 		dev_offset = map->stripes[i].physical;
 
 		ret = btrfs_update_device(trans, device);
 		if (ret)
-			goto out;
+			break;
 		ret = btrfs_alloc_dev_extent(trans, device,
 					     chunk_root->root_key.objectid,
 					     BTRFS_FIRST_CHUNK_TREE_OBJECTID,
 					     chunk_offset, dev_offset,
 					     stripe_size);
 		if (ret)
-			goto out;
+			break;
+	}
+	if (ret) {
+		mutex_unlock(&chunk_root->fs_info->fs_devices->device_list_mutex);
+		goto out;
 	}
 
 	stripe = &chunk->stripe;
@@ -4850,6 +4862,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE);
 		stripe++;
 	}
+	mutex_unlock(&chunk_root->fs_info->fs_devices->device_list_mutex);
 
 	btrfs_set_stack_chunk_length(chunk, chunk_size);
 	btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
@@ -4956,7 +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++;
@@ -5036,7 +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)
@@ -5072,7 +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);
@@ -5093,7 +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);
@@ -5252,7 +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;
@@ -5366,35 +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;
 	}
@@ -5794,7 +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;
@@ -6057,7 +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) {
@@ -6198,6 +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;
@@ -6206,6 +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);
@@ -6222,7 +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);
@@ -6230,7 +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;
@@ -6465,11 +6508,11 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
 	if (!sb)
 		return -ENOMEM;
-	btrfs_set_buffer_uptodate(sb);
+	set_extent_buffer_uptodate(sb);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
 	/*
 	 * The sb extent buffer is artifical and just used to read the system array.
-	 * btrfs_set_buffer_uptodate() call does not properly mark all it's
+	 * set_extent_buffer_uptodate() call does not properly mark all it's
 	 * pages up-to-date when the page is larger: extent does not cover the
 	 * whole page and consequently check_page_uptodate does not find all
 	 * the page's extents up-to-date (the hole beyond sb),
@@ -6512,6 +6555,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				goto out_short_read;
 
 			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+			if (!num_stripes) {
+				printk(KERN_ERR
+	    "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+					num_stripes, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6520,6 +6571,9 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 			if (ret)
 				break;
 		} else {
+			printk(KERN_ERR
+		"BTRFS: unexpected item type %u in sys_array at offset %u\n",
+				(u32)key.type, cur_offset);
 			ret = -EIO;
 			break;
 		}
@@ -6921,7 +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;
@@ -6949,7 +7003,7 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
 	}
 }
 
-void btrfs_close_one_device(struct btrfs_device *device)
+static void btrfs_close_one_device(struct btrfs_device *device)
 {
 	struct btrfs_fs_devices *fs_devices = device->fs_devices;
 	struct btrfs_device *new_device;