public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: Ming Lei <[email protected]>
Cc: [email protected], [email protected],
	[email protected],
	Alexander Viro <[email protected]>,
	Stefan Hajnoczi <[email protected]>,
	Miklos Szeredi <[email protected]>,
	Bernd Schubert <[email protected]>,
	Nitesh Shetty <[email protected]>,
	Christoph Hellwig <[email protected]>,
	Ziyang Zhang <[email protected]>
Subject: Re: [PATCH 3/4] io_uring: add IORING_OP_READ[WRITE]_SPLICE_BUF
Date: Sat, 11 Feb 2023 19:42:57 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <Y+hFZaFte9YyfVwR@T590>

On 2/11/23 6:48 PM, Ming Lei wrote:
> On Sat, Feb 11, 2023 at 10:13:37AM -0700, Jens Axboe wrote:
>> On 2/10/23 8:32?AM, Ming Lei wrote:
>>
>> One more comment on this.
>>
>>> +static int __io_prep_rw_splice_buf(struct io_kiocb *req,
>>> +				   struct io_rw_splice_buf_data *data,
>>> +				   struct file *splice_f,
>>> +				   size_t len,
>>> +				   loff_t splice_off)
>>> +{
>>> +	unsigned flags = req->opcode == IORING_OP_READ_SPLICE_BUF ?
>>> +			SPLICE_F_KERN_FOR_READ : SPLICE_F_KERN_FOR_WRITE;
>>> +	struct splice_desc sd = {
>>> +		.total_len = len,
>>> +		.flags = flags | SPLICE_F_NONBLOCK | SPLICE_F_KERN_NEED_CONFIRM,
>>> +		.pos = splice_off,
>>> +		.u.data = data,
>>> +		.ignore_sig = true,
>>> +	};
>>> +
>>> +	return splice_direct_to_actor(splice_f, &sd,
>>> +			io_splice_buf_direct_actor);
>>
>> Is this safe? We end up using current->splice_pipe here, which should be
>> fine as long as things are left in a sane state after every operation.
>> Which they should be, just like a syscall would. Just wanted to make
>> sure you've considered that part.
> 
> Yeah.
> 
> Direct pipe is always left as empty when splice_direct_to_actor()
> returns. Pipe buffers(pages) are produced from ->splice_read()
> called from splice_direct_to_actor(), and consumed by
> io_splice_buf_direct_actor().
> 
> If any error is returned, direct pipe is empty too, and we just
> need to drop reference of sliced pages by io_rw_cleanup_splice_buf().

OK thanks for confirming, then that should be fine as we can
obviously not have two syscalls (or sendfile(2) and task_work from
io_uring) running at the same time.

-- 
Jens Axboe



  reply	other threads:[~2023-02-12  2:43 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-10 15:32 [PATCH 0/4] io_uring: add IORING_OP_READ[WRITE]_SPLICE_BUF Ming Lei
2023-02-10 15:32 ` [PATCH 1/4] fs/splice: enhance direct pipe & splice for moving pages in kernel Ming Lei
2023-02-11 15:42   ` Ming Lei
2023-02-11 18:57     ` Linus Torvalds
2023-02-12  1:39       ` Ming Lei
2023-02-13 20:04         ` Linus Torvalds
2023-02-14  0:52           ` Ming Lei
2023-02-14  2:35             ` Ming Lei
2023-02-14 11:03           ` Miklos Szeredi
2023-02-14 14:35             ` Ming Lei
2023-02-14 15:39               ` Miklos Szeredi
2023-02-15  0:11                 ` Ming Lei
2023-02-15 10:36                   ` Miklos Szeredi
2023-02-10 15:32 ` [PATCH 2/4] fs/splice: allow to ignore signal in __splice_from_pipe Ming Lei
2023-02-10 15:32 ` [PATCH 3/4] io_uring: add IORING_OP_READ[WRITE]_SPLICE_BUF Ming Lei
2023-02-11 15:45   ` Jens Axboe
2023-02-11 16:12     ` Ming Lei
2023-02-11 16:52       ` Jens Axboe
2023-02-12  3:22         ` Ming Lei
2023-02-12  3:55           ` Jens Axboe
2023-02-13  1:06             ` Ming Lei
2023-02-11 17:13   ` Jens Axboe
2023-02-12  1:48     ` Ming Lei
2023-02-12  2:42       ` Jens Axboe [this message]
2023-02-10 15:32 ` [PATCH 4/4] ublk_drv: support splice based read/write zero copy Ming Lei
2023-02-10 21:54 ` [PATCH 0/4] io_uring: add IORING_OP_READ[WRITE]_SPLICE_BUF Jens Axboe
2023-02-10 22:19   ` Jens Axboe
2023-02-11  5:13   ` Ming Lei
2023-02-11 15:45     ` Jens Axboe
2023-02-14 16:36 ` Stefan Hajnoczi

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] \
    [email protected] \
    [email protected] \
    [email protected] \
    [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