DPDK patches and discussions
 help / color / mirror / Atom feed
From: Bruce Richardson <bruce.richardson@intel.com>
To: Manoj Viswanath <manoj.viswanath@gmail.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] Ports not detected by IGB_UIO in DPDK 1.7.1 in QEMU_KVM environment
Date: Wed, 5 Nov 2014 10:12:46 +0000	[thread overview]
Message-ID: <20141105101246.GA9856@bricha3-MOBL3> (raw)
In-Reply-To: <CAC1b25pX3R2y_Cjp5UAdL6Bozrf01OkG6U6LGQvJ2aUTDXGvSA@mail.gmail.com>

On Wed, Nov 05, 2014 at 03:28:13PM +0530, Manoj Viswanath wrote:
> Hi,
> 
> I have a DPDK application running on QEMU-KVM environment using DPDK 1.6.0.
> I am trying to port the same to DPDK version 1.7.1.
> 
> I am using Virt-manager GUI to assign e1000 emulated port to the VM. This
> works fine in DPDK 1.6.0. The device is identified by IGB_UIO and
> initialized by my application as expected.
> 
> However in case of DPDK 1.7.1, the emulated e1000 devices do not seem to be
> recognized.
> Following is my analysis:
> 
> 1. The API pci_get_uio_dev() is returning ERROR. This is called from
> pci_uio_map_resource() in the flow of PCI PROBE [rte_eal_pci_probe()].
> 
> 2. Due to this, the PCI device is not getting mapped to the correct driver
> (EM
> ​ Driver​
> ).
> 
> 3. The reason for the error in [1] appears to be that "uio" sub-directory
> doesn't seem to be correctly created for interfaces assigned to this VM.
> 
> 4. Upon further analysis i found that IGB_UIO probe function
> ["igbuio_pci_probe()"] is not getting triggered indicating the port has *not
> been assigned* to the IGB_UIO.
> 
> Kindly refer to the attachments:-
> - "Output of sys-bus-pci-devices" - indicating "uio" subdirectory not
> created for PCI devices in case of DPDK 1.7.1
> - "Output of lspci -v" - indicating device not bound to driver in case of
> DPDK 1.7.1
> - IGB_UIO init log snippet - indicating PCI devices not detected and
> initialized by IGB_UIO in case of DPDK 1.7.1
> - CONFIG file used for DPDK compilation
> 
> Not sure what has changed between 1.6.0 and 1.7.1 which is impacting this.
> 
> Could someone throw light in this regard as to what i may be missing ?
> 
> Thanks in advance.
> 
> Regards,
> Manoj

Hi Manoj,

can you perhaps give some details on how you were binding the device to the uio
module both for 1.6 and for 1.7?

/Bruce

       reply	other threads:[~2014-11-05 10:03 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CAC1b25pX3R2y_Cjp5UAdL6Bozrf01OkG6U6LGQvJ2aUTDXGvSA@mail.gmail.com>
2014-11-05 10:12 ` Bruce Richardson [this message]
2014-11-07 15:01   ` Manoj Viswanath
     [not found]     ` <20141107153053.GA10376@bricha3-MOBL3>
2014-11-07 17:56       ` Manoj Viswanath
2014-11-10 10:58         ` Bruce Richardson
2014-11-11 13:48           ` Manoj Viswanath
2014-11-12 14:12             ` Bruce Richardson

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=20141105101246.GA9856@bricha3-MOBL3 \
    --to=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=manoj.viswanath@gmail.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).