strace of io_uring events?

[Jens Axboe]

On 7/21/20 1:44 PM, Andy Lutomirski wrote:
> On Tue, Jul 21, 2020 at 11:39 AM Jens Axboe <axboe at kernel.dk> wrote:
>>
>> On 7/21/20 11:44 AM, Andy Lutomirski wrote:
>>> On Tue, Jul 21, 2020 at 10:30 AM Jens Axboe <axboe at kernel.dk> wrote:
>>>>
>>>> On 7/21/20 11:23 AM, Andy Lutomirski wrote:
>>>>> On Tue, Jul 21, 2020 at 8:31 AM Jens Axboe <axboe at kernel.dk> wrote:
>>>>>>
>>>>>> On 7/21/20 9:27 AM, Andy Lutomirski wrote:
>>>>>>> On Fri, Jul 17, 2020 at 1:02 AM Stefano Garzarella <sgarzare at redhat.com> wrote:
>>>>>>>>
>>>>>>>> On Thu, Jul 16, 2020 at 08:12:35AM -0700, Kees Cook wrote:
>>>>>>>>> On Thu, Jul 16, 2020 at 03:14:04PM +0200, Stefano Garzarella wrote:
>>>>>>>
>>>>>>>>> access (IIUC) is possible without actually calling any of the io_uring
>>>>>>>>> syscalls. Is that correct? A process would receive an fd (via SCM_RIGHTS,
>>>>>>>>> pidfd_getfd, or soon seccomp addfd), and then call mmap() on it to gain
>>>>>>>>> access to the SQ and CQ, and off it goes? (The only glitch I see is
>>>>>>>>> waking up the worker thread?)
>>>>>>>>
>>>>>>>> It is true only if the io_uring istance is created with SQPOLL flag (not the
>>>>>>>> default behaviour and it requires CAP_SYS_ADMIN). In this case the
>>>>>>>> kthread is created and you can also set an higher idle time for it, so
>>>>>>>> also the waking up syscall can be avoided.
>>>>>>>
>>>>>>> I stared at the io_uring code for a while, and I'm wondering if we're
>>>>>>> approaching this the wrong way. It seems to me that most of the
>>>>>>> complications here come from the fact that io_uring SQEs don't clearly
>>>>>>> belong to any particular security principle.  (We have struct creds,
>>>>>>> but we don't really have a task or mm.)  But I'm also not convinced
>>>>>>> that io_uring actually supports cross-mm submission except by accident
>>>>>>> -- as it stands, unless a user is very careful to only submit SQEs
>>>>>>> that don't use user pointers, the results will be unpredictable.
>>>>>>
>>>>>> How so?
>>>>>
>>>>> Unless I've missed something, either current->mm or sqo_mm will be
>>>>> used depending on which thread ends up doing the IO.  (And there might
>>>>> be similar issues with threads.)  Having the user memory references
>>>>> end up somewhere that is an implementation detail seems suboptimal.
>>>>
>>>> current->mm is always used from the entering task - obviously if done
>>>> synchronously, but also if it needs to go async. The only exception is a
>>>> setup with SQPOLL, in which case ctx->sqo_mm is the task that set up the
>>>> ring. SQPOLL requires root privileges to setup, and there's no task
>>>> entering the io_uring at all necessarily. It'll just submit sqes with
>>>> the credentials that are registered with the ring.
>>>
>>> Really?  I admit I haven't fully followed how the code works, but it
>>> looks like anything that goes through the io_queue_async_work() path
>>> will use sqo_mm, and can't most requests that end up blocking end up
>>> there?  It looks like, even if SQPOLL is not set, the mm used will
>>> depend on whether the request ends up blocking and thus getting queued
>>> for later completion.
>>>
>>> Or does some magic I missed make this a nonissue.
>>
>> No, you are wrong. The logic works as I described it.
> 
> Can you enlighten me?  I don't see any iov_iter_get_pages() calls or
> equivalents.  If an IO is punted, how does the data end up in the
> io_uring_enter() caller's mm?

If the SQE needs to be punted to an io-wq worker, then
io_prep_async_work() is ultimately called before it's queued with the
io-wq worker. That grabs anything we need to successfully process this
request, user access and all. io-wq then assumes the right "context" to
performn that request. As the async punt is always done on behalf of the
task that is submitting the IO (via io_uring_enter()), that is the
context that we grab and use for that particular request.

You keep looking at ctx->sqo_mm, and I've told you several times that
it's only related to the SQPOLL thread. If you don't use SQPOLL, no
request will ever use it.

-- 
Jens Axboe