Re: [PATCH 13/16] io_uring: add support for pre-mapped user IO buffers

[Jens Axboe]

On 1/9/19 5:16 AM, Christoph Hellwig wrote:
>> +static int io_setup_rw(int rw, struct io_kiocb *kiocb,
>> +                   const struct io_uring_iocb *iocb, struct iovec **iovec,
>> +                   struct iov_iter *iter, bool kaddr)
>>  {
>>      void __user *buf = (void __user *)(uintptr_t)iocb->addr;
>>      size_t ret;
>>  
>> -    ret = import_single_range(rw, buf, iocb->len, *iovec, iter);
>> +    if (!kaddr) {
>> +            ret = import_single_range(rw, buf, iocb->len, *iovec, iter);
>> +    } else {
>> +            struct io_ring_ctx *ctx = kiocb->ki_ctx;
>> +            struct io_mapped_ubuf *imu;
>> +            size_t len = iocb->len;
>> +            size_t offset;
>> +            int index;
>> +
>> +            /* __io_submit_one() already validated the index */
>> +            index = array_index_nospec(kiocb->ki_index,
>> +                                            ctx->max_reqs);
>> +            imu = &ctx->user_bufs[index];
>> +            if ((unsigned long) iocb->addr < imu->ubuf ||
>> +                (unsigned long) iocb->addr + len > imu->ubuf + imu->len) {
>> +                    ret = -EFAULT;
>> +                    goto err;
>> +            }
>> +
>> +            /*
>> +             * May not be a start of buffer, set size appropriately
>> +             * and advance us to the beginning.
>> +             */
>> +            offset = (unsigned long) iocb->addr - imu->ubuf;
>> +            iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs,
>> +                            offset + len);
>> +            if (offset)
>> +                    iov_iter_advance(iter, offset);
>> +            ret = 0;
>> +
> 
> Please split this code in a separate helper.

Done

>>      if (unlikely(!file->f_op->read_iter))
>>              goto out_fput;
>>  
>> -    ret = io_setup_rw(READ, iocb, &iovec, &iter);
>> +    ret = io_setup_rw(READ, kiocb, iocb, &iovec, &iter, kaddr);
> 
> And I'd personally just call that helper here based on the opcode and
> avoid magic bool arguments.

Then we can also fold the switch cases, cleans it up.

>> +            down_write(&current->mm->mmap_sem);
>> +            pret = get_user_pages(ubuf, nr_pages, 1, pages, NULL);
>> +            up_write(&current->mm->mmap_sem);
> 
> This needs to be get_user_pages_longterm.

Done

>> +     * We don't use the iovecs without fixed buffers being asked for.
>> +     * Error out if they don't match.
>> +     */
>> +    if (!(p->flags & IORING_SETUP_FIXEDBUFS) && iovecs)
>> +            return -EINVAL;
> 
> I don't think we need the IORING_SETUP_FIXEDBUFS flag at all, as a
> non-zero iovecs pointer is enough of an indication.

Good point, no point in that redundancy. Fixed.

-- 
Jens Axboe