Netdev List
 help / color / mirror / Atom feed
From: Yoann Juet <yoann.juet@univ-nantes.fr>
To: netdev@vger.kernel.org
Subject: bnx2x + SR-IOV, no internal L2 switching
Date: Wed, 12 Feb 2014 14:33:55 +0100	[thread overview]
Message-ID: <52FB7843.6050601@univ-nantes.fr> (raw)


[-- Attachment #1.1: Type: text/plain, Size: 1363 bytes --]

Hi all,

I'm conducting experiments on SR-IOV with Broadcom and Intel cards on 
debian/unstable with KVM hypervisor. On Broadcom cards (bnx2x module, 
BCM57810 devices), Virtual Functions (VFs) get running, Virtual Machines 
attached to such VFs inherit network connectivity with excellent 
performance.

However, VMs attached to VFs on the Broadcom Physical Functions (PFs) 
behave like they were connected to an ancient hub, not a L2 switch. It 
is as if there was no internal L2 switching on the Broadcom card to 
process VF <-> VF or VF <-> PF communications. As a result, a VM sees 
all inbound/outbound traffic from/to others VMs as well as traffic 
destined to the PF (for instance, the physical ethX has an IP address).

On the other hand, everything works like a charm with Intel cards (ixgbe 
module, 82599EB devices). Traffic between VFs or VF/PF is switched 
internally by the card.

I found very little literature about SR-IOV on Broadcom devices. I 
wonder if it's a normal behaviour, a misconfiguration on my side or 
perhaps a firmware/driver bug.

Have you seen this issue before ?

---
Kernel 3.12.9 (same behaviour with kernels 3.10.x)
	driver: bnx2x
	firmware-version: 7.8.17
Debian/unstable
	libvirt 1.2.1
	QEMU 1.7.0
---

Best regards,
-- 
Université de Nantes - Direction des Systèmes d'Information



[-- Attachment #1.2: yoann_juet.vcf --]
[-- Type: text/x-vcard, Size: 377 bytes --]

begin:vcard
fn:Yoann Juet
n:Juet;Yoann
org;quoted-printable;quoted-printable:Direction des Syst=C3=A8mes d'Information;P=C3=B4le R=C3=A9seau
adr;quoted-printable:BP 92208;;2 rue de la Houssini=C3=A8re;Nantes Cedex 3;;44322;France
email;internet:yoann.juet@univ-nantes.fr
tel;work:02.53.48.49.26
tel;fax:02.53.48.49.09
tel;cell:06.73.15.42.19
version:2.1
end:vcard


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 3256 bytes --]

             reply	other threads:[~2014-02-12 13:41 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-12 13:33 Yoann Juet [this message]
2014-02-12 14:38 ` bnx2x + SR-IOV, no internal L2 switching Ariel Elior
2014-02-12 15:54   ` Yoann Juet
2014-02-12 23:10 ` Ben Hutchings
2014-02-13  9:42   ` Yoann Juet

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=52FB7843.6050601@univ-nantes.fr \
    --to=yoann.juet@univ-nantes.fr \
    --cc=netdev@vger.kernel.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