+ if (ret)
+ bch_err(c, "Error setting device state: %s", bch2_err_str(ret));
+
+ percpu_ref_put(&ca->ref);
+ return ret;
+}
+
+struct bch_data_ctx {
+ struct bch_fs *c;
+ struct bch_ioctl_data arg;
+ struct bch_move_stats stats;
+
+ int ret;
+
+ struct task_struct *thread;
+};
+
+static int bch2_data_thread(void *arg)
+{
+ struct bch_data_ctx *ctx = arg;
+
+ ctx->ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg);
+
+ ctx->stats.data_type = U8_MAX;
+ return 0;
+}
+
+static int bch2_data_job_release(struct inode *inode, struct file *file)
+{
+ struct bch_data_ctx *ctx = file->private_data;
+
+ kthread_stop(ctx->thread);
+ put_task_struct(ctx->thread);
+ kfree(ctx);
+ return 0;
+}
+
+static ssize_t bch2_data_job_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct bch_data_ctx *ctx = file->private_data;
+ struct bch_fs *c = ctx->c;
+ struct bch_ioctl_data_event e = {
+ .type = BCH_DATA_EVENT_PROGRESS,
+ .p.data_type = ctx->stats.data_type,
+ .p.btree_id = ctx->stats.btree_id,
+ .p.pos = ctx->stats.pos,
+ .p.sectors_done = atomic64_read(&ctx->stats.sectors_seen),
+ .p.sectors_total = bch2_fs_usage_read_short(c).used,
+ };
+
+ if (len < sizeof(e))
+ return -EINVAL;
+
+ return copy_to_user(buf, &e, sizeof(e)) ?: sizeof(e);
+}
+
+static const struct file_operations bcachefs_data_ops = {
+ .release = bch2_data_job_release,
+ .read = bch2_data_job_read,
+ .llseek = no_llseek,
+};
+
+static long bch2_ioctl_data(struct bch_fs *c,
+ struct bch_ioctl_data arg)
+{
+ struct bch_data_ctx *ctx = NULL;
+ struct file *file = NULL;
+ unsigned flags = O_RDONLY|O_CLOEXEC|O_NONBLOCK;
+ int ret, fd = -1;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (arg.op >= BCH_DATA_OP_NR || arg.flags)
+ return -EINVAL;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->c = c;
+ ctx->arg = arg;
+
+ ctx->thread = kthread_create(bch2_data_thread, ctx,
+ "bch-data/%s", c->name);
+ if (IS_ERR(ctx->thread)) {
+ ret = PTR_ERR(ctx->thread);
+ goto err;
+ }
+
+ ret = get_unused_fd_flags(flags);
+ if (ret < 0)
+ goto err;
+ fd = ret;
+
+ file = anon_inode_getfile("[bcachefs]", &bcachefs_data_ops, ctx, flags);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err;
+ }
+
+ fd_install(fd, file);
+
+ get_task_struct(ctx->thread);
+ wake_up_process(ctx->thread);
+
+ return fd;
+err:
+ if (fd >= 0)
+ put_unused_fd(fd);
+ if (!IS_ERR_OR_NULL(ctx->thread))
+ kthread_stop(ctx->thread);
+ kfree(ctx);
+ return ret;
+}
+
+static long bch2_ioctl_fs_usage(struct bch_fs *c,
+ struct bch_ioctl_fs_usage __user *user_arg)
+{
+ struct bch_ioctl_fs_usage *arg = NULL;
+ struct bch_replicas_usage *dst_e, *dst_end;
+ struct bch_fs_usage_online *src;
+ u32 replica_entries_bytes;
+ unsigned i;
+ int ret = 0;
+
+ if (!test_bit(BCH_FS_STARTED, &c->flags))
+ return -EINVAL;
+
+ if (get_user(replica_entries_bytes, &user_arg->replica_entries_bytes))
+ return -EFAULT;
+
+ arg = kzalloc(sizeof(*arg) + replica_entries_bytes, GFP_KERNEL);
+ if (!arg)
+ return -ENOMEM;
+
+ src = bch2_fs_usage_read(c);
+ if (!src) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ arg->capacity = c->capacity;
+ arg->used = bch2_fs_sectors_used(c, src);
+ arg->online_reserved = src->online_reserved;
+
+ for (i = 0; i < BCH_REPLICAS_MAX; i++)
+ arg->persistent_reserved[i] = src->u.persistent_reserved[i];
+
+ dst_e = arg->replicas;
+ dst_end = (void *) arg->replicas + replica_entries_bytes;
+
+ for (i = 0; i < c->replicas.nr; i++) {
+ struct bch_replicas_entry *src_e =
+ cpu_replicas_entry(&c->replicas, i);
+
+ /* check that we have enough space for one replicas entry */
+ if (dst_e + 1 > dst_end) {
+ ret = -ERANGE;
+ break;
+ }
+
+ dst_e->sectors = src->u.replicas[i];
+ dst_e->r = *src_e;
+
+ /* recheck after setting nr_devs: */
+ if (replicas_usage_next(dst_e) > dst_end) {
+ ret = -ERANGE;
+ break;
+ }
+
+ memcpy(dst_e->r.devs, src_e->devs, src_e->nr_devs);
+
+ dst_e = replicas_usage_next(dst_e);
+ }
+
+ arg->replica_entries_bytes = (void *) dst_e - (void *) arg->replicas;
+
+ percpu_up_read(&c->mark_lock);
+ kfree(src);
+
+ if (!ret)
+ ret = copy_to_user(user_arg, arg,
+ sizeof(*arg) + arg->replica_entries_bytes);
+err:
+ kfree(arg);
+ return ret;
+}
+
+static long bch2_ioctl_dev_usage(struct bch_fs *c,
+ struct bch_ioctl_dev_usage __user *user_arg)
+{
+ struct bch_ioctl_dev_usage arg;
+ struct bch_dev_usage src;
+ struct bch_dev *ca;
+ unsigned i;
+
+ if (!test_bit(BCH_FS_STARTED, &c->flags))
+ return -EINVAL;
+
+ if (copy_from_user(&arg, user_arg, sizeof(arg)))
+ return -EFAULT;
+
+ if ((arg.flags & ~BCH_BY_INDEX) ||
+ arg.pad[0] ||
+ arg.pad[1] ||
+ arg.pad[2])
+ return -EINVAL;
+
+ ca = bch2_device_lookup(c, arg.dev, arg.flags);
+ if (IS_ERR(ca))
+ return PTR_ERR(ca);
+
+ src = bch2_dev_usage_read(ca);
+
+ arg.state = ca->mi.state;
+ arg.bucket_size = ca->mi.bucket_size;
+ arg.nr_buckets = ca->mi.nbuckets - ca->mi.first_bucket;
+ arg.buckets_ec = src.buckets_ec;
+
+ for (i = 0; i < BCH_DATA_NR; i++) {
+ arg.d[i].buckets = src.d[i].buckets;
+ arg.d[i].sectors = src.d[i].sectors;
+ arg.d[i].fragmented = src.d[i].fragmented;
+ }