On 2/6/19 9:05 PM, Al Viro wrote:
> On Wed, Feb 06, 2019 at 10:56:41AM -0700, Jens Axboe wrote:
>> On 2/5/19 6:01 PM, Al Viro wrote:
>>> On Tue, Feb 05, 2019 at 05:27:29PM -0700, Jens Axboe wrote:
>>>
>>>> This should be better, passes some basic testing, too:
>>>>
>>>> http://git.kernel.dk/cgit/linux-block/commit/?h=io_uring&id=01a93aa784319a02ccfa6523371b93401c9e0073
>>>>
>>>> Verified that we're grabbing the right refs, and don't hold any
>>>> ourselves. For the file registration, forbid registration of the
>>>> io_uring fd, as that is pointless and will introduce a loop regardless
>>>> of fd passing.
>>>
>>> *shrug*
>>>
>>> So pass it to AF_UNIX socket and register _that_ - does't change the
>>> underlying problem.
>>
>> Maybe I'm being dense here, but it's an f_op match. Should catch a
>> passed fd as well, correct?
> 
> f_op match on _what_?
> 
>> With that, how can there be a loop?
> 
> 	io_uring_fd = ....
> 	socketpair(PF_UNIX, SOCK_STREAM, 0, sock_fds);
> 	register sock_fds[0] and sock_fds[1] to io_uring_fd
> 	send SCM_RIGHTS datagram with io_uring_fd to sock_fds[0]
> 	close sock_fds[0], sock_fds[1] and io_uring_fd
> 
> And there's your unreachable loop.

I created a small app to do just that, and ran it and verified that
->release() is called and the io_uring is released as expected. This
is run on the current -git branch, which has a socket backing for
the io_uring fd itself, but not for the registered files.

What am I missing here? Attaching the program as a reference.

-- 
Jens Axboe