netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mike Qiu <qiudayu@linux.vnet.ibm.com>
To: Michael Chan <mchan@broadcom.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>,
	eilong@broadcom.com, mcarlson@broadcom.com,
	zambrano@broadcom.com, jeffrey.t.kirsher@intel.com,
	netdev@vger.kernel.org
Subject: Re: BCM5719(tg3) use multiple MSI with RSS
Date: Thu, 16 May 2013 10:30:36 +0800	[thread overview]
Message-ID: <519444CC.6080406@linux.vnet.ibm.com> (raw)
In-Reply-To: <1368633836.6796.1.camel@LTIRV-MCHAN1.corp.ad.broadcom.com>

于 2013/5/16 0:03, Michael Chan 写道:
> On Wed, 2013-05-15 at 16:52 +0100, Ben Hutchings wrote:
>> On Wed, 2013-05-15 at 08:08 -0700, Michael Chan wrote:
>>> On Wed, 2013-05-15 at 15:56 +0800, Mike Qiu wrote:
>>>> Hi all
>>>>
>>>> Currently, I need to enable multiple MSI on BCM5719 network card.
>>>> But I look in to the spec of 5719 from Broadcom, it seems
>>>> that RSS just enable with MSI-X, so I'm not sure if multiple
>>>> MSI can use RSS.
>>>>
>>> MSI can only support one IRQ source and cannot support RSS.
>> It is possible for an MSI capability to have multiple MSIs, but they
>> will use the same address and consecutive data values.
>>
>> On x86, if you can find a large enough block of free IRQs on an IOAPIC,
>> it is possible to implement RSS this way.  Linux supports this on
>> systems with an x2apic.
>>
>> Now, maybe tg3 hardware doesn't support this (and really, why bother
>> when there is MSI-X?) but the option does exist.
> Yes, tg3 hardware (may be all Broadcom hardware) can only use MSI as a
> replacement for INTA.
That you mean, it can't use multiple MSI for RSS ?
>

  reply	other threads:[~2013-05-16  2:30 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-15  7:56 BCM5719(tg3) use multiple MSI with RSS Mike Qiu
2013-05-15 15:08 ` Michael Chan
2013-05-15 15:52   ` Ben Hutchings
2013-05-15 16:03     ` Michael Chan
2013-05-16  2:30       ` Mike Qiu [this message]
2013-05-16  2:25     ` Mike Qiu

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=519444CC.6080406@linux.vnet.ibm.com \
    --to=qiudayu@linux.vnet.ibm.com \
    --cc=bhutchings@solarflare.com \
    --cc=eilong@broadcom.com \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=mcarlson@broadcom.com \
    --cc=mchan@broadcom.com \
    --cc=netdev@vger.kernel.org \
    --cc=zambrano@broadcom.com \
    /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).