Merge branch 'foreign/anand/dev-del-by-id-ext' into for-chris-4.7-20160516

fs/btrfs/dev-replace.c

@@ -44,9 +44,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 						struct btrfs_fs_info *fs_info,
 						struct btrfs_device *srcdev,
 						struct btrfs_device *tgtdev);
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
-					 char *srcdev_name,
-					 struct btrfs_device **device);
 static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 static int btrfs_dev_replace_kthread(void *data);
 static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
@@ -305,8 +302,8 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
 		dev_replace->cursor_left_last_write_of_item;
 }
 
-int btrfs_dev_replace_start(struct btrfs_root *root,
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
-			    struct btrfs_ioctl_dev_replace_args *args)
+				u64 srcdevid, char *srcdev_name, int read_src)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -315,29 +312,16 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	struct btrfs_device *tgt_device = NULL;
 	struct btrfs_device *src_device = NULL;
 
-	switch (args->start.cont_reading_from_srcdev_mode) {
-	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
-	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
-	    args->start.tgtdev_name[0] == '\0')
-		return -EINVAL;
-
 	/* the disk copy procedure reuses the scrub code */
 	mutex_lock(&fs_info->volume_mutex);
-	ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
+	ret = btrfs_find_device_by_devspec(root, srcdevid,
-					    args->start.srcdev_name,
+					    srcdev_name, &src_device);
-					    &src_device);
 	if (ret) {
 		mutex_unlock(&fs_info->volume_mutex);
 		return ret;
 	}
 
-	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
+	ret = btrfs_init_dev_replace_tgtdev(root, tgtdev_name,
 					    src_device, &tgt_device);
 	mutex_unlock(&fs_info->volume_mutex);
 	if (ret)
@@ -364,18 +348,17 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
-		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
+		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
 		goto leave;
 	}
 
-	dev_replace->cont_reading_from_srcdev_mode =
+	dev_replace->cont_reading_from_srcdev_mode = read_src;
-		args->start.cont_reading_from_srcdev_mode;
 	WARN_ON(!src_device);
 	dev_replace->srcdev = src_device;
 	WARN_ON(!tgt_device);
 	dev_replace->tgtdev = tgt_device;
 
-	btrfs_info_in_rcu(root->fs_info,
+	btrfs_info_in_rcu(fs_info,
 		      "dev_replace from %s (devid %llu) to %s started",
 		      src_device->missing ? "<missing disk>" :
 		        rcu_str_deref(src_device->name),
@@ -396,14 +379,13 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->item_needs_writeback = 1;
 	atomic64_set(&dev_replace->num_write_errors, 0);
 	atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
-	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
 	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
+		btrfs_err(fs_info, "kobj add dev failed %d\n", ret);
 
-	btrfs_wait_ordered_roots(root->fs_info, -1);
+	btrfs_wait_ordered_roots(fs_info, -1);
 
 	/* force writing the updated state information to disk */
 	trans = btrfs_start_transaction(root, 0);
@@ -421,11 +403,9 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 			      btrfs_device_get_total_bytes(src_device),
 			      &dev_replace->scrub_progress, 0, 1);
 
-	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
+	ret = btrfs_dev_replace_finishing(fs_info, ret);
-	/* don't warn if EINPROGRESS, someone else might be running scrub */
 	if (ret == -EINPROGRESS) {
-		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
+		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
-		ret = 0;
 	} else {
 		WARN_ON(ret);
 	}
@@ -440,6 +420,35 @@ leave:
 	return ret;
 }
 
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
+			    struct btrfs_ioctl_dev_replace_args *args)
+{
+	int ret;
+
+	switch (args->start.cont_reading_from_srcdev_mode) {
+	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
+	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
+	    args->start.tgtdev_name[0] == '\0')
+		return -EINVAL;
+
+	ret = btrfs_dev_replace_start(root, args->start.tgtdev_name,
+					args->start.srcdevid,
+					args->start.srcdev_name,
+					args->start.cont_reading_from_srcdev_mode);
+	args->result = ret;
+	/* don't warn if EINPROGRESS, someone else might be running scrub */
+	if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS)
+		ret = 0;
+
+	return ret;
+}
+
 /*
  * blocked until all flighting bios are finished.
  */
@@ -560,10 +569,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	ASSERT(list_empty(&src_device->resized_list));
 	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
 	tgt_device->commit_bytes_used = src_device->bytes_used;
-	if (fs_info->sb->s_bdev == src_device->bdev)
+
-		fs_info->sb->s_bdev = tgt_device->bdev;
+	btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
-	if (fs_info->fs_devices->latest_bdev == src_device->bdev)
+
-		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
 
@@ -626,25 +634,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 	write_unlock(&em_tree->lock);
 }
 
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
-					 char *srcdev_name,
-					 struct btrfs_device **device)
-{
-	int ret;
-
-	if (srcdevid) {
-		ret = 0;
-		*device = btrfs_find_device(root->fs_info, srcdevid, NULL,
-					    NULL);
-		if (!*device)
-			ret = -ENOENT;
-	} else {
-		ret = btrfs_find_device_missing_or_by_path(root, srcdev_name,
-							   device);
-	}
-	return ret;
-}
-
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args)
 {

fs/btrfs/dev-replace.h

@@ -25,8 +25,10 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 			  struct btrfs_fs_info *fs_info);
 void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_start(struct btrfs_root *root,
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
 			    struct btrfs_ioctl_dev_replace_args *args);
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+				u64 srcdevid, char *srcdev_name, int read_src);
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args);
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,

fs/btrfs/ioctl.c

@@ -2676,6 +2676,60 @@ out:
 	return ret;
 }
 
+static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
+{
+	struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+	struct btrfs_ioctl_vol_args_v2 *vol_args;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
+	vol_args = memdup_user(arg, sizeof(*vol_args));
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
+		goto err_drop;
+	}
+
+	/* Check for compatibility reject unknown flags */
+	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
+		return -EOPNOTSUPP;
+
+	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
+			1)) {
+		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+		goto out;
+	}
+
+	mutex_lock(&root->fs_info->volume_mutex);
+	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
+		ret = btrfs_rm_device(root, NULL, vol_args->devid);
+	} else {
+		vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+		ret = btrfs_rm_device(root, vol_args->name, 0);
+	}
+	mutex_unlock(&root->fs_info->volume_mutex);
+	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+
+	if (!ret) {
+		if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
+			btrfs_info(root->fs_info, "device deleted: id %llu",
+					vol_args->devid);
+		else
+			btrfs_info(root->fs_info, "device deleted: %s",
+					vol_args->name);
+	}
+out:
+	kfree(vol_args);
+err_drop:
+	mnt_drop_write_file(file);
+	return ret;
+}
+
 static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 {
 	struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
@@ -2703,7 +2757,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 	mutex_lock(&root->fs_info->volume_mutex);
-	ret = btrfs_rm_device(root, vol_args->name);
+	ret = btrfs_rm_device(root, vol_args->name, 0);
 	mutex_unlock(&root->fs_info->volume_mutex);
 
 	if (!ret)
@@ -4387,7 +4441,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg)
 			1)) {
 			ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 		} else {
-			ret = btrfs_dev_replace_start(root, p);
+			ret = btrfs_dev_replace_by_ioctl(root, p);
 			atomic_set(
 			 &root->fs_info->mutually_exclusive_operation_running,
 			 0);
@@ -5480,6 +5534,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_add_dev(root, argp);
 	case BTRFS_IOC_RM_DEV:
 		return btrfs_ioctl_rm_dev(file, argp);
+	case BTRFS_IOC_RM_DEV_V2:
+		return btrfs_ioctl_rm_dev_v2(file, argp);
 	case BTRFS_IOC_FS_INFO:
 		return btrfs_ioctl_fs_info(root, argp);
 	case BTRFS_IOC_DEV_INFO:

fs/btrfs/volumes.c

@@ -118,6 +118,21 @@ const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID6]  = BTRFS_BLOCK_GROUP_RAID6,
 };
 
+/*
+ * Table to convert BTRFS_RAID_* to the error code if minimum number of devices
+ * condition is not met. Zero means there's no corresponding
+ * BTRFS_ERROR_DEV_*_NOT_MET value.
+ */
+const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
+	[BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
+	[BTRFS_RAID_RAID1]  = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
+	[BTRFS_RAID_DUP]    = 0,
+	[BTRFS_RAID_RAID0]  = 0,
+	[BTRFS_RAID_SINGLE] = 0,
+	[BTRFS_RAID_RAID5]  = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
+	[BTRFS_RAID_RAID6]  = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
+};
+
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				struct btrfs_device *device);
@@ -699,7 +714,8 @@ static noinline int device_list_add(const char *path,
 	 * if there is new btrfs on an already registered device,
 	 * then remove the stale device entry.
 	 */
-	btrfs_free_stale_device(device);
+	if (ret > 0)
+		btrfs_free_stale_device(device);
 
 	*fs_devices_ret = fs_devices;
 
@@ -988,6 +1004,56 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	return ret;
 }
 
+void btrfs_release_disk_super(struct page *page)
+{
+	kunmap(page);
+	put_page(page);
+}
+
+int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
+		struct page **page, struct btrfs_super_block **disk_super)
+{
+	void *p;
+	pgoff_t index;
+
+	/* make sure our super fits in the device */
+	if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
+		return 1;
+
+	/* make sure our super fits in the page */
+	if (sizeof(**disk_super) > PAGE_SIZE)
+		return 1;
+
+	/* make sure our super doesn't straddle pages on disk */
+	index = bytenr >> PAGE_SHIFT;
+	if ((bytenr + sizeof(**disk_super) - 1) >> PAGE_SHIFT != index)
+		return 1;
+
+	/* pull in the page with our super */
+	*page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+				   index, GFP_KERNEL);
+
+	if (IS_ERR_OR_NULL(*page))
+		return 1;
+
+	p = kmap(*page);
+
+	/* align our pointer to the offset of the super block */
+	*disk_super = p + (bytenr & ~PAGE_MASK);
+
+	if (btrfs_super_bytenr(*disk_super) != bytenr ||
+	    btrfs_super_magic(*disk_super) != BTRFS_MAGIC) {
+		btrfs_release_disk_super(*page);
+		return 1;
+	}
+
+	if ((*disk_super)->label[0] &&
+		(*disk_super)->label[BTRFS_LABEL_SIZE - 1])
+		(*disk_super)->label[BTRFS_LABEL_SIZE - 1] = '\0';
+
+	return 0;
+}
+
 /*
  * Look for a btrfs signature on a device. This may be called out of the mount path
  * and we are not allowed to call set_blocksize during the scan. The superblock
@@ -999,13 +1065,11 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	struct btrfs_super_block *disk_super;
 	struct block_device *bdev;
 	struct page *page;
-	void *p;
 	int ret = -EINVAL;
 	u64 devid;
 	u64 transid;
 	u64 total_devices;
 	u64 bytenr;
-	pgoff_t index;
 
 	/*
 	 * we would like to check all the supers, but that would make
@@ -1018,41 +1082,14 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	mutex_lock(&uuid_mutex);
 
 	bdev = blkdev_get_by_path(path, flags, holder);
-
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
 		goto error;
 	}
 
-	/* make sure our super fits in the device */
+	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super))
-	if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
 		goto error_bdev_put;
 
-	/* make sure our super fits in the page */
-	if (sizeof(*disk_super) > PAGE_SIZE)
-		goto error_bdev_put;
-
-	/* make sure our super doesn't straddle pages on disk */
-	index = bytenr >> PAGE_SHIFT;
-	if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
-		goto error_bdev_put;
-
-	/* pull in the page with our super */
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
-				   index, GFP_NOFS);
-
-	if (IS_ERR_OR_NULL(page))
-		goto error_bdev_put;
-
-	p = kmap(page);
-
-	/* align our pointer to the offset of the super block */
-	disk_super = p + (bytenr & ~PAGE_MASK);
-
-	if (btrfs_super_bytenr(disk_super) != bytenr ||
-	    btrfs_super_magic(disk_super) != BTRFS_MAGIC)
-		goto error_unmap;
-
 	devid = btrfs_stack_device_id(&disk_super->dev_item);
 	transid = btrfs_super_generation(disk_super);
 	total_devices = btrfs_super_num_devices(disk_super);
@@ -1060,8 +1097,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	ret = device_list_add(path, disk_super, devid, fs_devices_ret);
 	if (ret > 0) {
 		if (disk_super->label[0]) {
-			if (disk_super->label[BTRFS_LABEL_SIZE - 1])
-				disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
 			printk(KERN_INFO "BTRFS: device label %s ", disk_super->label);
 		} else {
 			printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid);
@@ -1073,9 +1108,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	if (!ret && fs_devices_ret)
 		(*fs_devices_ret)->total_devices = total_devices;
 
-error_unmap:
+	btrfs_release_disk_super(page);
-	kunmap(page);
-	put_page(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
@@ -1688,31 +1721,91 @@ out:
 	return ret;
 }
 
-int btrfs_rm_device(struct btrfs_root *root, char *device_path)
+/*
+ * Verify that @num_devices satisfies the RAID profile constraints in the whole
+ * filesystem. It's up to the caller to adjust that number regarding eg. device
+ * replace.
+ */
+static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info,
+		u64 num_devices)
 {
-	struct btrfs_device *device;
-	struct btrfs_device *next_device;
-	struct block_device *bdev;
-	struct buffer_head *bh = NULL;
-	struct btrfs_super_block *disk_super;
-	struct btrfs_fs_devices *cur_devices;
 	u64 all_avail;
-	u64 devid;
-	u64 num_devices;
-	u8 *dev_uuid;
 	unsigned seq;
-	int ret = 0;
+	int i;
-	bool clear_super = false;
-
-	mutex_lock(&uuid_mutex);
 
 	do {
-		seq = read_seqbegin(&root->fs_info->profiles_lock);
+		seq = read_seqbegin(&fs_info->profiles_lock);
 
-		all_avail = root->fs_info->avail_data_alloc_bits |
+		all_avail = fs_info->avail_data_alloc_bits |
-			    root->fs_info->avail_system_alloc_bits |
+			    fs_info->avail_system_alloc_bits |
-			    root->fs_info->avail_metadata_alloc_bits;
+			    fs_info->avail_metadata_alloc_bits;
-	} while (read_seqretry(&root->fs_info->profiles_lock, seq));
+	} while (read_seqretry(&fs_info->profiles_lock, seq));
+
+	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+		if (!(all_avail & btrfs_raid_group[i]))
+			continue;
+
+		if (num_devices < btrfs_raid_array[i].devs_min) {
+			int ret = btrfs_raid_mindev_error[i];
+
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+struct btrfs_device *btrfs_find_next_active_device(struct btrfs_fs_devices *fs_devs,
+					struct btrfs_device *device)
+{
+	struct btrfs_device *next_device;
+
+	list_for_each_entry(next_device, &fs_devs->devices, dev_list) {
+		if (next_device != device &&
+			!next_device->missing && next_device->bdev)
+			return next_device;
+	}
+
+	return NULL;
+}
+
+/*
+ * Helper function to check if the given device is part of s_bdev / latest_bdev
+ * and replace it with the provided or the next active device, in the context
+ * where this function called, there should be always be another device (or
+ * this_dev) which is active.
+ */
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *device, struct btrfs_device *this_dev)
+{
+	struct btrfs_device *next_device;
+
+	if (this_dev)
+		next_device = this_dev;
+	else
+		next_device = btrfs_find_next_active_device(fs_info->fs_devices,
+								device);
+	ASSERT(next_device);
+
+	if (fs_info->sb->s_bdev &&
+			(fs_info->sb->s_bdev == device->bdev))
+		fs_info->sb->s_bdev = next_device->bdev;
+
+	if (fs_info->fs_devices->latest_bdev == device->bdev)
+		fs_info->fs_devices->latest_bdev = next_device->bdev;
+}
+
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid)
+{
+	struct btrfs_device *device;
+	struct btrfs_fs_devices *cur_devices;
+	u64 num_devices;
+	int ret = 0;
+	bool clear_super = false;
+	char *dev_name = NULL;
+
+	mutex_lock(&uuid_mutex);
 
 	num_devices = root->fs_info->fs_devices->num_devices;
 	btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
@@ -1722,78 +1815,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	}
 	btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
+	ret = btrfs_check_raid_min_devices(root->fs_info, num_devices - 1);
-		ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
+	if (ret)
 		goto out;
-	}
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && num_devices <= 2) {
+	ret = btrfs_find_device_by_devspec(root, devid, device_path,
-		ret = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET;
+				&device);
+	if (ret)
 		goto out;
-	}
-
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) &&
-	    root->fs_info->fs_devices->rw_devices <= 2) {
-		ret = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET;
-		goto out;
-	}
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) &&
-	    root->fs_info->fs_devices->rw_devices <= 3) {
-		ret = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET;
-		goto out;
-	}
-
-	if (strcmp(device_path, "missing") == 0) {
-		struct list_head *devices;
-		struct btrfs_device *tmp;
-
-		device = NULL;
-		devices = &root->fs_info->fs_devices->devices;
-		/*
-		 * It is safe to read the devices since the volume_mutex
-		 * is held.
-		 */
-		list_for_each_entry(tmp, devices, dev_list) {
-			if (tmp->in_fs_metadata &&
-			    !tmp->is_tgtdev_for_dev_replace &&
-			    !tmp->bdev) {
-				device = tmp;
-				break;
-			}
-		}
-		bdev = NULL;
-		bh = NULL;
-		disk_super = NULL;
-		if (!device) {
-			ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
-			goto out;
-		}
-	} else {
-		ret = btrfs_get_bdev_and_sb(device_path,
-					    FMODE_WRITE | FMODE_EXCL,
-					    root->fs_info->bdev_holder, 0,
-					    &bdev, &bh);
-		if (ret)
-			goto out;
-		disk_super = (struct btrfs_super_block *)bh->b_data;
-		devid = btrfs_stack_device_id(&disk_super->dev_item);
-		dev_uuid = disk_super->dev_item.uuid;
-		device = btrfs_find_device(root->fs_info, devid, dev_uuid,
-					   disk_super->fsid);
-		if (!device) {
-			ret = -ENOENT;
-			goto error_brelse;
-		}
-	}
 
 	if (device->is_tgtdev_for_dev_replace) {
 		ret = BTRFS_ERROR_DEV_TGT_REPLACE;
-		goto error_brelse;
+		goto out;
 	}
 
 	if (device->writeable && root->fs_info->fs_devices->rw_devices == 1) {
 		ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
-		goto error_brelse;
+		goto out;
 	}
 
 	if (device->writeable) {
@@ -1801,6 +1839,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		list_del_init(&device->dev_alloc_list);
 		device->fs_devices->rw_devices--;
 		unlock_chunks(root);
+		dev_name = kstrdup(device->name->str, GFP_KERNEL);
+		if (!dev_name) {
+			ret = -ENOMEM;
+			goto error_undo;
+		}
 		clear_super = true;
 	}
 
@@ -1842,12 +1885,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->missing)
 		device->fs_devices->missing_devices--;
 
-	next_device = list_entry(root->fs_info->fs_devices->devices.next,
+	btrfs_assign_next_active_device(root->fs_info, device, NULL);
-				 struct btrfs_device, dev_list);
-	if (device->bdev == root->fs_info->sb->s_bdev)
-		root->fs_info->sb->s_bdev = next_device->bdev;
-	if (device->bdev == root->fs_info->fs_devices->latest_bdev)
-		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
 	if (device->bdev) {
 		device->fs_devices->open_devices--;
@@ -1883,63 +1921,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	 * at this point, the device is zero sized.  We want to
 	 * remove it from the devices list and zero out the old super
 	 */
-	if (clear_super && disk_super) {
+	if (clear_super) {
-		u64 bytenr;
+		struct block_device *bdev;
-		int i;
 
-		/* make sure this device isn't detected as part of
+		bdev = blkdev_get_by_path(dev_name, FMODE_READ | FMODE_EXCL,
-		 * the FS anymore
+						root->fs_info->bdev_holder);
-		 */
+		if (!IS_ERR(bdev)) {
-		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+			btrfs_scratch_superblocks(bdev, dev_name);
-		set_buffer_dirty(bh);
+			blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
-		sync_dirty_buffer(bh);
-
-		/* clear the mirror copies of super block on the disk
-		 * being removed, 0th copy is been taken care above and
-		 * the below would take of the rest
-		 */
-		for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) {
-			bytenr = btrfs_sb_offset(i);
-			if (bytenr + BTRFS_SUPER_INFO_SIZE >=
-					i_size_read(bdev->bd_inode))
-				break;
-
-			brelse(bh);
-			bh = __bread(bdev, bytenr / 4096,
-					BTRFS_SUPER_INFO_SIZE);
-			if (!bh)
-				continue;
-
-			disk_super = (struct btrfs_super_block *)bh->b_data;
-
-			if (btrfs_super_bytenr(disk_super) != bytenr ||
-				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
-				continue;
-			}
-			memset(&disk_super->magic, 0,
-						sizeof(disk_super->magic));
-			set_buffer_dirty(bh);
-			sync_dirty_buffer(bh);
 		}
 	}
 
-	ret = 0;
-
-	if (bdev) {
-		/* Notify udev that device has changed */
-		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
-
-		/* Update ctime/mtime for device path for libblkid */
-		update_dev_time(device_path);
-	}
-
-error_brelse:
-	brelse(bh);
-	if (bdev)
-		blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
+	kfree(dev_name);
+
 	mutex_unlock(&uuid_mutex);
 	return ret;
+
 error_undo:
 	if (device->writeable) {
 		lock_chunks(root);
@@ -1948,7 +1946,7 @@ error_undo:
 		device->fs_devices->rw_devices++;
 		unlock_chunks(root);
 	}
-	goto error_brelse;
+	goto out;
 }
 
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
@@ -2017,8 +2015,6 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *tgtdev)
 {
-	struct btrfs_device *next_device;
-
 	mutex_lock(&uuid_mutex);
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
@@ -2030,12 +2026,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	fs_info->fs_devices->num_devices--;
 
-	next_device = list_entry(fs_info->fs_devices->devices.next,
+	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
-				 struct btrfs_device, dev_list);
+
-	if (tgtdev->bdev == fs_info->sb->s_bdev)
-		fs_info->sb->s_bdev = next_device->bdev;
-	if (tgtdev->bdev == fs_info->fs_devices->latest_bdev)
-		fs_info->fs_devices->latest_bdev = next_device->bdev;
 	list_del_rcu(&tgtdev->dev_list);
 
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -2109,6 +2101,31 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
 	}
 }
 
+/*
+ * Lookup a device given by device id, or the path if the id is 0.
+ */
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+					 char *devpath,
+					 struct btrfs_device **device)
+{
+	int ret;
+
+	if (devid) {
+		ret = 0;
+		*device = btrfs_find_device(root->fs_info, devid, NULL,
+					    NULL);
+		if (!*device)
+			ret = -ENOENT;
+	} else {
+		if (!devpath || !devpath[0])
+			return -EINVAL;
+
+		ret = btrfs_find_device_missing_or_by_path(root, devpath,
+							   device);
+	}
+	return ret;
+}
+
 /*
  * does all the dirty work required for changing file system's UUID.
  */

fs/btrfs/volumes.h

@@ -340,7 +340,7 @@ struct btrfs_raid_attr {
 };
 
 extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
-
+extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
 extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
 
 struct map_lookup {
@@ -445,13 +445,18 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 			  struct btrfs_fs_devices **fs_devices_ret);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *device, struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
 					 char *device_path,
 					 struct btrfs_device **device);
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+					 char *devpath,
+					 struct btrfs_device **device);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
-int btrfs_rm_device(struct btrfs_root *root, char *device_path);
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid);
 void btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,

include/uapi/linux/btrfs.h

@@ -36,6 +36,14 @@ struct btrfs_ioctl_vol_args {
 #define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
 #define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
 #define BTRFS_SUBVOL_QGROUP_INHERIT	(1ULL << 2)
+#define BTRFS_DEVICE_SPEC_BY_ID		(1ULL << 3)
+
+#define BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED		\
+			(BTRFS_SUBVOL_CREATE_ASYNC |	\
+			BTRFS_SUBVOL_RDONLY |		\
+			BTRFS_SUBVOL_QGROUP_INHERIT |	\
+			BTRFS_DEVICE_SPEC_BY_ID)
+
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_UUID_SIZE 16
 #define BTRFS_UUID_UNPARSED_SIZE	37
@@ -76,7 +84,10 @@ struct btrfs_ioctl_vol_args_v2 {
 		};
 		__u64 unused[4];
 	};
-	char name[BTRFS_SUBVOL_NAME_MAX + 1];
+	union {
+		char name[BTRFS_SUBVOL_NAME_MAX + 1];
+		u64 devid;
+	};
 };
 
 /*
@@ -659,5 +670,7 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				   struct btrfs_ioctl_feature_flags[2])
 #define BTRFS_IOC_GET_SUPPORTED_FEATURES _IOR(BTRFS_IOCTL_MAGIC, 57, \
 				   struct btrfs_ioctl_feature_flags[3])
+#define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \
+				   struct btrfs_ioctl_vol_args_v2)
 
 #endif /* _UAPI_LINUX_BTRFS_H */