Re: [PATCH v5 2/3] io_uring: add IOURING_REGISTER_RESTRICTIONS opcode

[Jens Axboe <axboe@kernel.dk>]

On 8/27/20 7:40 AM, Stefano Garzarella wrote:
> @@ -6414,6 +6425,19 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
>  	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
>  		return -EINVAL;
>  
> +	if (unlikely(ctx->restricted)) {
> +		if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
> +			return -EACCES;
> +
> +		if ((sqe_flags & ctx->restrictions.sqe_flags_required) !=
> +		    ctx->restrictions.sqe_flags_required)
> +			return -EACCES;
> +
> +		if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed |
> +				  ctx->restrictions.sqe_flags_required))
> +			return -EACCES;
> +	}
> +

This should be a separate function, ala:

if (unlikely(ctx->restricted)) {
	ret = io_check_restriction(ctx, req);
	if (ret)
		return ret;
}

to move it totally out of the (very) hot path.

>  	if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
>  	    !io_op_defs[req->opcode].buffer_select)
>  		return -EOPNOTSUPP;
> @@ -8714,6 +8738,71 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
>  	return -EINVAL;
>  }
>  
> +static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg,
> +				    unsigned int nr_args)
> +{
> +	struct io_uring_restriction *res;
> +	size_t size;
> +	int i, ret;
> +
> +	/* We allow only a single restrictions registration */
> +	if (ctx->restricted)
> +		return -EBUSY;
> +
> +	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
> +		return -EINVAL;
> +
> +	size = array_size(nr_args, sizeof(*res));
> +	if (size == SIZE_MAX)
> +		return -EOVERFLOW;
> +
> +	res = memdup_user(arg, size);
> +	if (IS_ERR(res))
> +		return PTR_ERR(res);
> +
> +	for (i = 0; i < nr_args; i++) {
> +		switch (res[i].opcode) {
> +		case IORING_RESTRICTION_REGISTER_OP:
> +			if (res[i].register_op >= IORING_REGISTER_LAST) {
> +				ret = -EINVAL;
> +				goto out;
> +			}
> +
> +			__set_bit(res[i].register_op,
> +				  ctx->restrictions.register_op);
> +			break;
> +		case IORING_RESTRICTION_SQE_OP:
> +			if (res[i].sqe_op >= IORING_OP_LAST) {
> +				ret = -EINVAL;
> +				goto out;
> +			}
> +
> +			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
> +			break;
> +		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
> +			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
> +			break;
> +		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
> +			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
> +			break;
> +		default:
> +			ret = -EINVAL;
> +			goto out;
> +		}
> +	}
> +
> +	ctx->restricted = 1;
> +
> +	ret = 0;

I'd set ret = 0 above the switch, that's the usual idiom - start at
zero, have someone set it to -ERROR if something fails.

-- 
Jens Axboe