public inbox for [email protected]
 help / color / mirror / Atom feed
From: Mina Almasry <[email protected]>
To: Pavel Begunkov <[email protected]>
Cc: David Wei <[email protected]>,
	[email protected], [email protected],
	 Jens Axboe <[email protected]>, Jakub Kicinski <[email protected]>,
	Paolo Abeni <[email protected]>,
	 "David S. Miller" <[email protected]>,
	Eric Dumazet <[email protected]>,
	 Jesper Dangaard Brouer <[email protected]>,
	David Ahern <[email protected]>,
	 Stanislav Fomichev <[email protected]>,
	Joe Damato <[email protected]>,
	 Pedro Tammela <[email protected]>
Subject: Re: [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request
Date: Tue, 5 Nov 2024 15:09:50 -0800	[thread overview]
Message-ID: <CAHS8izNfBEHQea3EHU7BSYKmKL9py2esROySvgpCO48CxijRmw@mail.gmail.com> (raw)
In-Reply-To: <[email protected]>

On Fri, Nov 1, 2024 at 2:16 PM Pavel Begunkov <[email protected]> wrote:
>
> On 11/1/24 20:11, Mina Almasry wrote:
> > On Tue, Oct 29, 2024 at 4:06 PM David Wei <[email protected]> wrote:
> >>
> > ...
> >> +static void io_zcrx_get_buf_uref(struct net_iov *niov)
> >> +{
> >> +       atomic_long_add(IO_ZC_RX_UREF, &niov->pp_ref_count);
> >> +}
> >> +
> >
> > This is not specific to io_rcrx I think. Please rename this and put it
> > somewhere generic, like netmem.h.
> >
> > Then tcp_recvmsg_dmabuf can use the same helper instead of the very
> > ugly call it currently does:
> >
> > - atomic_long_inc(&niov->pp_ref_count);
> > + net_iov_pp_ref_get(niov, 1);
> >
> > Or something.
> >
> > In general I think io_uring code can do whatever it wants with the
> > io_uring specific bits in net_iov (everything under net_area_owner I
> > think), but please lets try to keep any code touching the generic
> > net_iov fields (pp_pagic, pp_ref_count, and others) in generic
> > helpers.
>
> I'm getting confused, io_uring shouldn't be touching these
> fields, but on the other hand should export net/ private
> netmem_priv.h and page_pool_priv.h and directly hard code a bunch
> of low level setup io_uring that is currently in page_pool.c
>

The only thing requested from this patch is to turn
io_zcrx_get_buf_uref into something more generic. I'm guessing your
confusion is following my other comments in "[PATCH v7 06/15] net:
page pool: add helper creating area from pages". Let me take a closer
look at my feedback there.

-- 
Thanks,
Mina

  reply	other threads:[~2024-11-05 23:10 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-29 23:05 [PATCH v7 00/15] io_uring zero copy rx David Wei
2024-10-29 23:05 ` [PATCH v7 01/15] net: prefix devmem specific helpers David Wei
2024-11-01 14:57   ` Mina Almasry
2024-10-29 23:05 ` [PATCH v7 02/15] net: generalise net_iov chunk owners David Wei
2024-10-29 23:05 ` [PATCH v7 03/15] net: page_pool: create hooks for custom page providers David Wei
2024-11-05 16:28   ` Alexander Lobakin
2024-11-06  1:08     ` Pavel Begunkov
2024-10-29 23:05 ` [PATCH v7 04/15] net: prepare for non devmem TCP memory providers David Wei
2024-11-01 17:09   ` Mina Almasry
2024-11-01 17:41     ` Pavel Begunkov
2024-11-04 20:20       ` Mina Almasry
2024-11-04 21:24         ` Pavel Begunkov
2024-11-11 19:01         ` David Wei
2024-11-15  0:43           ` Mina Almasry
2024-10-29 23:05 ` [PATCH v7 05/15] net: page_pool: add ->scrub mem provider callback David Wei
2024-10-29 23:05 ` [PATCH v7 06/15] net: page pool: add helper creating area from pages David Wei
2024-11-01 17:33   ` Mina Almasry
2024-11-01 18:16     ` Pavel Begunkov
2024-11-05 23:34       ` Mina Almasry
2024-11-06  0:50         ` Pavel Begunkov
2024-10-29 23:05 ` [PATCH v7 07/15] net: page_pool: introduce page_pool_mp_return_in_cache David Wei
2024-11-01 20:05   ` Mina Almasry
2024-10-29 23:05 ` [PATCH v7 08/15] net: add helper executing custom callback from napi David Wei
2024-10-29 23:05 ` [PATCH v7 09/15] io_uring/zcrx: add interface queue and refill queue David Wei
2024-10-29 23:05 ` [PATCH v7 10/15] io_uring/zcrx: add io_zcrx_area David Wei
2024-10-29 23:05 ` [PATCH v7 11/15] io_uring/zcrx: implement zerocopy receive pp memory provider David Wei
2024-11-01 20:06   ` Mina Almasry
2024-11-01 21:09     ` Pavel Begunkov
2024-11-03 21:52       ` Pavel Begunkov
2024-11-04 19:54       ` Mina Almasry
2024-11-04 21:14         ` Pavel Begunkov
2024-11-04 21:53           ` Pavel Begunkov
2024-11-11 21:15         ` David Wei
2024-11-14 20:56           ` Mina Almasry
2024-11-15 23:14             ` Jakub Kicinski
2024-10-29 23:05 ` [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request David Wei
2024-11-01 20:11   ` Mina Almasry
2024-11-01 21:17     ` Pavel Begunkov
2024-11-05 23:09       ` Mina Almasry [this message]
2024-11-11 22:02         ` David Wei
2024-10-29 23:05 ` [PATCH v7 13/15] io_uring/zcrx: set pp memory provider for an rx queue David Wei
2024-11-01 20:16   ` Mina Almasry
2024-11-01 20:35     ` Jens Axboe
2024-11-01 21:12       ` Pavel Begunkov
2024-10-29 23:05 ` [PATCH v7 14/15] io_uring/zcrx: add copy fallback David Wei
2024-10-29 23:05 ` [PATCH v7 15/15] io_uring/zcrx: throttle receive requests David Wei

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 \
    --in-reply-to=CAHS8izNfBEHQea3EHU7BSYKmKL9py2esROySvgpCO48CxijRmw@mail.gmail.com \
    [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] \
    [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