From: "谢华伟(此时此刻)" <huawei.xhw@alibaba-inc.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: ferruh.yigit@intel.com, maxime.coquelin@redhat.com,
david.marchand@redhat.com, dev@dpdk.org,
anatoly.burakov@intel.com, xuemingl@nvidia.com, grive@u256.net,
chenbo.xia@intel.com
Subject: Re: [dpdk-dev] [PATCH v9 0/2] support both PIO and MMIO BAR for legacy device in virtio PMD
Date: Thu, 04 Mar 2021 21:45:18 +0800 [thread overview]
Message-ID: <8c084916-3de8-360a-eb32-5b4f1a58a209@alibaba-inc.com> (raw)
In-Reply-To: <20210303102424.5df54e30@hermes.local>
On 2021/3/4 2:24, Stephen Hemminger wrote:
> On Thu, 04 Mar 2021 01:46:50 +0800
> "谢华伟(此时此刻)"<huawei.xhw@alibaba-inc.com> wrote:
>
>> virtio PMD assumes legacy device only supports PIO BAR resource. This is wrong.
>> As we need to create lots of devices, as PIO resource on x86 is very limited,
>> we expose MMIO(memory IO) BAR.
>>
>> Kernel supports both PIO and MMIO BAR for legacy virtio-pci device, and for all
>> other pci devices. This patchset handles different type of BAR in the similar way.
>>
>> In previous implementation, under igb_uio driver we get PIO address from igb_uio
>> sysfs entry; with uio_pci_generic, we get PIO address from /proc/ioports for x86,
>> and for other ARCHs, we get PIO address from standard PCI sysfs entry.
>> For PIO/MMIO RW, there is different path for different drivers and arch.
> Just to add some background. At the time virtio for DPDK was developed,
> the kernel only supported legacy mode, and it required I/O ports on x86.
Hi Stephen:
Do you mean QEMU? I think QEMU exports PIO by default.
For kernel, I checked 3.10 code at hand, virtio legacy driver doesn't
assume I/O port. It uses generic API pci_iomap and ioread/write.
>
> One concern is that, you should make sure these patches still work on
> the oldest releases of Linux kernel that DPDK supports. For upstream
> kernel that should be 4.4 kernel (oldest currently maintained LTS).
> The Linux system requirements doc file needs update!
>
> For distributions, the oldest version would be probably be RHEL 7.
PIO is verified on Redhat 7.9 (3.10.0-1160.11.1.el7.x86_64).
As this patch uses the generic kernel exported interface, which all
other PMDs have been using, i think it doesn't break compatibility.
next prev parent reply other threads:[~2021-03-04 13:45 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-29 3:18 [dpdk-dev] [PATCH v6 " 谢华伟(此时此刻)
2021-01-29 3:18 ` [dpdk-dev] [PATCH v6 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-02-03 9:37 ` Maxime Coquelin
2021-02-18 9:33 ` David Marchand
2021-02-21 15:58 ` 谢华伟(此时此刻)
2021-02-24 12:49 ` David Marchand
2021-02-24 15:29 ` 谢华伟(此时此刻)
2021-02-24 17:52 ` David Marchand
2021-03-01 15:47 ` 谢华伟(此时此刻)
2021-03-02 12:31 ` 谢华伟(此时此刻)
2021-01-29 3:18 ` [dpdk-dev] [PATCH v6 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-02-03 9:37 ` Maxime Coquelin
2021-02-09 14:51 ` Ferruh Yigit
2021-02-19 8:52 ` Ferruh Yigit
2021-02-21 15:45 ` 谢华伟(此时此刻)
2021-02-17 9:06 ` David Marchand
2021-02-17 14:15 ` 谢华伟(此时此刻)
2021-02-18 9:33 ` David Marchand
2021-01-29 3:25 ` [dpdk-dev] [PATCH v6 0/2] support both PIO and MMIO BAR for legacy device in virtio PMD 谢华伟(此时此刻)
2021-02-01 7:43 ` 谢华伟(此时此刻)
2021-02-03 9:37 ` Maxime Coquelin
2021-02-04 2:50 ` 谢华伟(此时此刻)
2021-02-22 17:15 ` [dpdk-dev] [PATCH v7 " 谢华伟(此时此刻)
2021-02-22 17:15 ` [dpdk-dev] [PATCH v7 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-02-22 17:15 ` [dpdk-dev] [PATCH v7 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-02-22 17:25 ` Ferruh Yigit
2021-02-23 14:20 ` 谢华伟(此时此刻)
2021-02-24 15:45 ` Ferruh Yigit
2021-02-25 3:59 ` 谢华伟(此时此刻)
2021-02-25 9:52 ` David Marchand
2021-03-01 15:43 ` 谢华伟(此时此刻)
2021-03-02 13:14 ` David Marchand
2021-03-03 7:56 ` 谢华伟(此时此刻)
2021-03-01 16:01 ` [dpdk-dev] [PATCH v8 0/2] support both PIO and MMIO BAR for legacy device in virtio PMD 谢华伟(此时此刻)
2021-03-01 16:01 ` [dpdk-dev] [PATCH v8 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-03-01 16:01 ` [dpdk-dev] [PATCH v8 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-03-02 12:48 ` [dpdk-dev] [PATCH v8 0/2] support both PIO and MMIO BAR for legacy device in virtio PMD 谢华伟(此时此刻)
2021-03-02 13:01 ` Ferruh Yigit
2021-03-02 13:17 ` David Marchand
2021-03-03 17:46 ` [dpdk-dev] [PATCH v9 " 谢华伟(此时此刻)
2021-03-03 17:46 ` [dpdk-dev] [PATCH v9 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-03-03 17:46 ` [dpdk-dev] [PATCH v9 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-03-03 18:24 ` [dpdk-dev] [PATCH v9 0/2] support both PIO and MMIO BAR for legacy device in virtio PMD Stephen Hemminger
2021-03-04 13:45 ` 谢华伟(此时此刻) [this message]
2021-03-03 18:47 ` [dpdk-dev] [PATCH v10 0/2] support both PIO and MMIO BAR for legacy virito device 谢华伟(此时此刻)
2021-03-03 18:47 ` [dpdk-dev] [PATCH v10 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-03-05 16:17 ` 谢华伟(此时此刻)
2021-03-09 6:22 ` 谢华伟(此时此刻)
2021-03-09 7:44 ` David Marchand
2021-03-03 18:47 ` [dpdk-dev] [PATCH v10 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-03-10 17:36 ` [dpdk-dev] [PATCH v11 0/2] support both PIO and MMIO BAR for legacy virito device 谢华伟(此时此刻)
2021-03-10 17:36 ` [dpdk-dev] [PATCH v11 1/2] bus/pci: use PCI standard sysfs entry to get PIO address 谢华伟(此时此刻)
2021-03-10 17:36 ` [dpdk-dev] [PATCH v11 2/2] bus/pci: support MMIO in PCI ioport accessors 谢华伟(此时此刻)
2021-03-11 6:42 ` Wang, Haiyue
2021-03-15 10:19 ` David Marchand
2021-03-15 11:25 ` 谢华伟(此时此刻)
2021-03-15 13:11 ` Wang, Haiyue
2021-03-11 11:54 ` [dpdk-dev] [PATCH v11 0/2] support both PIO and MMIO BAR for legacy virito device Wang, Yinan
2021-03-12 14:32 ` David Marchand
2021-03-15 14:16 ` David Marchand
2021-03-17 8:12 ` 谢华伟(此时此刻)
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=8c084916-3de8-360a-eb32-5b4f1a58a209@alibaba-inc.com \
--to=huawei.xhw@alibaba-inc.com \
--cc=anatoly.burakov@intel.com \
--cc=chenbo.xia@intel.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=grive@u256.net \
--cc=maxime.coquelin@redhat.com \
--cc=stephen@networkplumber.org \
--cc=xuemingl@nvidia.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).