From: Jens Axboe <[email protected]>
To: Pavel Begunkov <[email protected]>, [email protected]
Cc: [email protected]
Subject: Re: [PATCH 4/4] io_uring: test patch for fd passing
Date: Wed, 4 Mar 2020 10:48:09 -0700 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
On 3/4/20 6:13 AM, Pavel Begunkov wrote:
> On 04/03/2020 02:50, Jens Axboe wrote:
>> This allows a chain link to set ->fd to IOSQE_FD_LAST_OPEN, which will
>> then be turned into the results from the last open (or accept) request
>> in the chain. If no open has been done, this isn't valid and the request
>> will be errored with -EBADF.
>>
>> With this, we can define chains of open+read+close, where the read and
>> close part can work on the fd instantiated by the open request.
>>
>> Totally a work in progress, POC so far.
>
> I'm concerned of having and supporting all these IOSQE flavours. Isn't it the
> thing that can be potentially done with eBPF?
It could totally be done with BPF, but honestly I'd love to avoid the
extra dependency.
But in talks with Josh, I really like his suggestion on being able to ask
for a specific fd instead. I've reworked it to sit on top of that instead,
I'll post a new series soon.
--
Jens Axboe
next prev parent reply other threads:[~2020-03-04 17:48 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-03 23:50 [PATCHSET RFC 0/4] Support passing fds between chain links Jens Axboe
2020-03-03 23:50 ` [PATCH 1/4] io_uring: add end-of-bits marker and build time verify it Jens Axboe
2020-03-03 23:50 ` [PATCH 2/4] io_uring: move CLOSE req->file checking into handler Jens Axboe
2020-03-04 13:07 ` Pavel Begunkov
2020-03-04 17:47 ` Jens Axboe
2020-03-03 23:50 ` [PATCH 3/4] io_uring: move read/write side file based prep into op handler Jens Axboe
2020-03-03 23:50 ` [PATCH 4/4] io_uring: test patch for fd passing Jens Axboe
2020-03-04 13:13 ` Pavel Begunkov
2020-03-04 17:48 ` Jens Axboe [this message]
2020-03-04 0:43 ` [PATCHSET RFC 0/4] Support passing fds between chain links Jeff Layton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox