From: "Xie, Huawei" <huawei.xie@intel.com>
To: Peter Xu <peterx@redhat.com>
Cc: DPDK Dev <dev@dpdk.org>
Subject: Re: [dpdk-dev] [Question] How pmd virtio works without UIO?
Date: Tue, 22 Dec 2015 14:31:47 +0000 [thread overview]
Message-ID: <C37D651A908B024F974696C65296B57B4C552851@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <20151222113912.GA30780@pxdev.xzpeter.org>
On 12/22/2015 7:39 PM, Peter Xu wrote:
> On Tue, Dec 22, 2015 at 10:47:21AM +0000, Xie, Huawei wrote:
>> On 12/22/2015 5:57 PM, Peter Xu wrote:
>>> On Tue, Dec 22, 2015 at 04:32:46PM +0800, Yuanhan Liu wrote:
>>>> Actually, you are right. I mentioned in the last email that this is
>>>> for configuration part. To answer your question in this email, you
>>>> will not be able to go that further (say initiating virtio pmd) if
>>>> you don't unbind the origin virtio-net driver, and bind it to igb_uio
>>>> (or something similar).
>>>>
>>>> The start point is from rte_eal_pci_scan, where the sub-function
>>>> pci_san_one just initates a DPDK bond driver.
>>> I am not sure whether I do understand your meaning correctly
>>> (regarding "you willl not be able to go that furture"): The problem
>>> is that, we _can_ run testpmd without unbinding the ports and bind
>>> to UIO or something. What we need to do is boot the guest, reserve
>>> huge pages, and run testpmd (keeping its kernel driver as
>>> "virtio-pci"). In pci_scan_one():
>>>
>>> if (!ret) {
>>> if (!strcmp(driver, "vfio-pci"))
>>> dev->kdrv = RTE_KDRV_VFIO;
>>> else if (!strcmp(driver, "igb_uio"))
>>> dev->kdrv = RTE_KDRV_IGB_UIO;
>>> else if (!strcmp(driver, "uio_pci_generic"))
>>> dev->kdrv = RTE_KDRV_UIO_GENERIC;
>>> else
>>> dev->kdrv = RTE_KDRV_UNKNOWN;
>>> } else
>>> dev->kdrv = RTE_KDRV_UNKNOWN;
>>>
>>> I think it should be going to RTE_KDRV_UNKNOWN
>>> (driver=="virtio-pci") here. I tried to run IO and it could work,
>>> but I am not sure whether it is safe, and how.
>> Good catch, peter.
>> Actually recently customers complain that with this feature, DPDK always
>> tries to take over this virtio-pci device, which is unwanted behavior.
>> Using blacklist could workaround this issue.
>> However, the real serious problem is that kernel driver is still
>> managing this device.
>>
>> Changchun, Thomas:
>> I think we should fix this, but firstly i wonder why using port IO to
>> get PCI resource is more secure.
> I am not familiar with this, however, shouldn't port IO from
> userspace the most dangerous way to access PCI resource?
>
>>> Also, I am not sure whether I need to (at least) unbind the
>>> virtio-pci driver, so that there should have no kernel driver
>>> running for the virtio device before DPDK using it.
>> If you unbind, you have no entry under /proc/ioports for virtio IO port.
> I tried to unbind one of the virtio net device, I see the PCI entry
> still there.
>
> Before unbind:
>
> [root@vm proc]# lspci -k -s 00:03.0
> 00:03.0 Ethernet controller: Red Hat, Inc Virtio network device
> Subsystem: Red Hat, Inc Device 0001
> Kernel driver in use: virtio-pci
> [root@vm proc]# cat /proc/ioports | grep c060-c07f
> c060-c07f : 0000:00:03.0
> c060-c07f : virtio-pci
>
> After unbind:
>
> [root@vm proc]# lspci -k -s 00:03.0
> 00:03.0 Ethernet controller: Red Hat, Inc Virtio network device
> Subsystem: Red Hat, Inc Device 0001
> [root@vm proc]# cat /proc/ioports | grep c060-c07f
> c060-c07f : 0000:00:03.0
>
> So... does this means that it is an alternative to black list
> solution?
Users wants to use virtio-net device for normal communication, so they
still want virtio-net driver to manipulate this device. They don't want
DPDK to take over this device blindly.
>
> Peter
>
>>> Thanks
>>> Peter
>>>
>>>> --yliu
next prev parent reply other threads:[~2015-12-22 14:32 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-22 3:50 Peter Xu
2015-12-22 7:00 ` Yuanhan Liu
2015-12-22 8:23 ` Peter Xu
2015-12-22 8:32 ` Yuanhan Liu
2015-12-22 9:56 ` Peter Xu
2015-12-22 10:47 ` Xie, Huawei
2015-12-22 10:53 ` Xie, Huawei
2015-12-22 11:39 ` Peter Xu
2015-12-22 14:31 ` Xie, Huawei [this message]
2015-12-22 16:38 ` Xie, Huawei
2015-12-23 1:55 ` Peter Xu
2015-12-23 2:09 ` Yuanhan Liu
2015-12-23 2:38 ` Peter Xu
2015-12-23 22:26 ` Thomas Monjalon
2015-12-24 3:30 ` Yuanhan Liu
2015-12-24 17:56 ` Stephen Hemminger
2015-12-23 2:01 ` Yuanhan Liu
2015-12-23 2:41 ` Peter Xu
2015-12-23 2:58 ` Yuanhan Liu
2015-12-23 5:13 ` Xie, Huawei
2015-12-23 22:20 ` Thomas Monjalon
2015-12-24 18:38 ` [dpdk-dev] [PATCH 0/4] check if any kernel driver is manipulating the virtio device Huawei Xie
2015-12-24 18:38 ` [dpdk-dev] [PATCH 1/4] eal: make the comment more accurate Huawei Xie
2015-12-24 18:38 ` [dpdk-dev] [PATCH 2/4] eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the device Huawei Xie
2015-12-28 20:24 ` David Marchand
2015-12-24 18:38 ` [dpdk-dev] [PATCH 3/4] virtio: return 1 to tell the upper layer we don't take over this device Huawei Xie
2015-12-28 5:25 ` Yuanhan Liu
2015-12-28 5:38 ` Xie, Huawei
2015-12-24 18:38 ` [dpdk-dev] [PATCH 4/4] virtio: check if any kernel driver is manipulating the device Huawei Xie
2015-12-28 5:26 ` Yuanhan Liu
2015-12-28 5:29 ` Xie, Huawei
2016-01-04 9:02 ` Xie, Huawei
2016-01-04 17:29 ` Stephen Hemminger
2016-01-05 14:44 ` Panu Matilainen
2015-12-28 3:08 ` [dpdk-dev] [PATCH 0/4] check if any kernel driver is manipulating the virtio device Peter Xu
2016-01-03 17:56 ` [dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly Huawei Xie
2016-01-03 17:56 ` [dpdk-dev] [PATCH v2 1/4] eal: make the comment more accurate Huawei Xie
2016-01-03 17:56 ` [dpdk-dev] [PATCH v2 2/4] eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the device Huawei Xie
2016-01-03 17:56 ` [dpdk-dev] [PATCH v2 3/4] virtio: return 1 to tell the upper layer we don't take over this device Huawei Xie
2016-01-03 17:56 ` [dpdk-dev] [PATCH v2 4/4] virtio: check if any kernel driver is manipulating the virtio device Huawei Xie
2016-01-04 17:24 ` Stephen Hemminger
2016-01-04 17:56 ` Xie, Huawei
2016-01-05 1:56 ` Yuanhan Liu
2016-01-07 13:17 ` Ferruh Yigit
2016-01-07 14:17 ` Panu Matilainen
2016-01-27 12:43 ` Thomas Monjalon
2016-01-04 17:25 ` [dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly Stephen Hemminger
2016-01-12 3:02 ` Xie, Huawei
2016-01-12 4:23 ` Santosh Shukla
2016-01-12 5:16 ` Xie, Huawei
2016-01-13 12:17 ` Santosh Shukla
2016-01-27 15:21 ` [dpdk-dev] [PATCH v3 " Huawei Xie
2016-01-27 15:21 ` [dpdk-dev] [PATCH v3 1/4] eal: make the comment more accurate Huawei Xie
2016-01-27 15:21 ` [dpdk-dev] [PATCH v3 2/4] eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the device Huawei Xie
2016-01-27 15:21 ` [dpdk-dev] [PATCH v3 3/4] virtio: return 1 to tell the upper layer we don't take over this device Huawei Xie
2016-01-27 15:21 ` [dpdk-dev] [PATCH v3 4/4] virtio: check if kernel driver is manipulating the virtio device Huawei Xie
2016-01-28 9:55 ` Panu Matilainen
2016-01-29 7:40 ` [dpdk-dev] [PATCH v3 0/4] fix the issue that DPDK takes over virtio device blindly Yuanhan Liu
2016-02-24 12:43 ` Thomas Monjalon
2016-02-26 6:09 ` Xie, Huawei
2016-02-26 8:40 ` David Marchand
2016-02-26 9:00 ` Xie, Huawei
2016-02-26 1:53 ` [dpdk-dev] [PATCH v4 " Huawei Xie
2016-02-26 1:53 ` [dpdk-dev] [PATCH v4 1/4] eal: make the comment more accurate Huawei Xie
2016-02-29 8:48 ` David Marchand
2016-02-26 1:53 ` [dpdk-dev] [PATCH v4 2/4] eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't managing the device Huawei Xie
2016-02-29 2:34 ` Xie, Huawei
2016-02-29 8:46 ` David Marchand
2016-02-29 9:00 ` Xie, Huawei
2016-02-29 9:05 ` David Marchand
2016-02-26 1:53 ` [dpdk-dev] [PATCH v4 3/4] eal: call pci_ioport_map when " Huawei Xie
2016-02-29 9:02 ` David Marchand
2016-02-26 1:53 ` [dpdk-dev] [PATCH v4 4/4] virtio: return 1 to tell the upper layer we don't take over this device Huawei Xie
2016-02-29 13:15 ` Santosh Shukla
2016-03-01 7:16 ` Thomas Monjalon
2016-03-01 7:53 ` Xie, Huawei
2016-03-01 8:20 ` Thomas Monjalon
2016-03-01 8:39 ` Xie, Huawei
2016-03-01 9:55 ` Thomas Monjalon
2016-03-01 10:08 ` Xie, Huawei
2016-03-08 17:00 ` Xie, Huawei
2016-03-08 23:01 ` Thomas Monjalon
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 0/6] fix the issue that DPDK takes over virtio device blindly Huawei Xie
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 1/6] eal: make the comment more accurate Huawei Xie
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 2/6] eal: RTE_KDRV_NONE means kernel driver isn't managing the device Huawei Xie
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 3/6] eal: use new RTE_ARCH_X86 for x86 arch Huawei Xie
2016-03-09 23:04 ` Thomas Monjalon
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 4/6] eal: simple code rework Huawei Xie
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 5/6] eal: map IO port when kernel driver isn't managing the device Huawei Xie
2016-03-08 15:33 ` [dpdk-dev] [PATCH v5 6/6] virtio: return 1 to tell the upper layer we don't take over this device Huawei Xie
2016-03-09 23:23 ` Thomas Monjalon
2016-03-09 23:35 ` [dpdk-dev] [PATCH v5 0/6] fix the issue that DPDK takes over virtio device blindly Thomas Monjalon
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=C37D651A908B024F974696C65296B57B4C552851@SHSMSX101.ccr.corp.intel.com \
--to=huawei.xie@intel.com \
--cc=dev@dpdk.org \
--cc=peterx@redhat.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).