netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Roland Dreier <rdreier@cisco.com>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org, shemminger@linux-foundation.org,
	jgarzik@pobox.com, hadi@cyberus.ca, rusty@rustcorp.com.au
Subject: Re: [PATCH RFC]: napi_struct V4
Date: Sat, 28 Jul 2007 08:27:18 -0700	[thread overview]
Message-ID: <ada1wesy2eh.fsf@cisco.com> (raw)
In-Reply-To: <20070725.013154.34764933.davem@davemloft.net> (David Miller's message of "Wed, 25 Jul 2007 01:31:54 -0700 (PDT)")

 > Most drivers are in good shape, although some still have very
 > questionable netif_rx_complete() handling, in that racy area that
 > Rusty and myself were discussing today.
 > 
 > My inclination is to wrap those sequences around with an IRQ
 > safe spinlock to fix the race provably, and then if driver
 > authors want to optimize that away with techniques like those
 > that tg3, bnx2, sky2, skge et al. use, that's fine but can
 > be done later.

Ouch... that extra lock seems pretty expensive.  Also I'm having a
hard time understanding how the techniques you're alluding to apply to
devices that may miss events when enabling interrupts; the drivers you
mention all seem to be for devices that didn't have the race and
didn't use netif_rx_reschedule() in the old NAPI world.  Can you
provide a little more detail on how the lock could be optimized away?

Thanks,
  Roland

  parent reply	other threads:[~2007-07-28 15:27 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-07-25  8:31 [PATCH RFC]: napi_struct V4 David Miller
2007-07-25  8:56 ` Stephen Hemminger
2007-07-26  0:37   ` David Miller
2007-07-26  1:55   ` Jeff Garzik
2007-07-26  1:56     ` David Miller
2007-07-26  2:00       ` Jeff Garzik
2007-07-26  2:02         ` David Miller
2007-07-28 18:08           ` Jeff Garzik
2007-07-29  5:33             ` David Miller
2007-07-25 12:01 ` jamal
2007-07-26  4:09 ` David Miller
2007-07-26  6:33   ` Michael Chan
2007-07-26  6:38     ` David Miller
2007-07-26  7:05       ` Michael Chan
2007-07-26  7:15         ` David Miller
2007-07-26 21:38           ` Michael Chan
2007-07-31  0:25             ` David Miller
2007-07-26  6:39   ` Michael Chan
2007-07-26  6:43     ` David Miller
2007-07-28 15:27 ` Roland Dreier [this message]
2007-07-29  5:32   ` David Miller
2007-07-30 15:04     ` Roland Dreier
2007-07-30 22:48       ` David Miller
2007-07-31  2:01         ` Roland Dreier
2007-07-31  2:03           ` David Miller

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=ada1wesy2eh.fsf@cisco.com \
    --to=rdreier@cisco.com \
    --cc=davem@davemloft.net \
    --cc=hadi@cyberus.ca \
    --cc=jgarzik@pobox.com \
    --cc=netdev@vger.kernel.org \
    --cc=rusty@rustcorp.com.au \
    --cc=shemminger@linux-foundation.org \
    /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;
as well as URLs for NNTP newsgroup(s).