All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: "chensihang \(A\)" <chensihang1@hisilicon.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	Zhangfei Gao <zhangfei.gao@linaro.org>,
	"Liguozhu \(Kenneth\)" <liguozhu@hisilicon.com>,
	"linux-accelerators@lists.ozlabs.org"
	<linux-accelerators@lists.ozlabs.org>
Subject: Re: [RFC PATCH v2] uacce: Add uacce_ctrl misc device
Date: Mon, 1 Feb 2021 19:44:24 -0400	[thread overview]
Message-ID: <20210201234424.GI4718@ziepe.ca> (raw)
In-Reply-To: <MWHPR11MB1886DC78C5FBA3636B94F2578CB99@MWHPR11MB1886.namprd11.prod.outlook.com>

On Fri, Jan 29, 2021 at 10:09:03AM +0000, Tian, Kevin wrote:
> > SVA is not doom to work with IO page fault only. If we have SVA+pin,
> > we would get both sharing address and stable I/O latency.
> 
> Isn't it like a traditional MAP_DMA API (imply pinning) plus specifying 
> cpu_va of the memory pool as the iova? 

I think their issue is the HW can't do the cpu_va trick without also
involving the system IOMMU in a SVA mode

It really is something that belongs under some general /dev/sva as we
talked on the vfio thread

Jason
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: "Song Bao Hua (Barry Song)" <song.bao.hua@hisilicon.com>,
	"chensihang (A)" <chensihang1@hisilicon.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Zhangfei Gao <zhangfei.gao@linaro.org>,
	"Liguozhu (Kenneth)" <liguozhu@hisilicon.com>,
	"linux-accelerators@lists.ozlabs.org"
	<linux-accelerators@lists.ozlabs.org>
Subject: Re: [RFC PATCH v2] uacce: Add uacce_ctrl misc device
Date: Mon, 1 Feb 2021 19:44:24 -0400	[thread overview]
Message-ID: <20210201234424.GI4718@ziepe.ca> (raw)
In-Reply-To: <MWHPR11MB1886DC78C5FBA3636B94F2578CB99@MWHPR11MB1886.namprd11.prod.outlook.com>

On Fri, Jan 29, 2021 at 10:09:03AM +0000, Tian, Kevin wrote:
> > SVA is not doom to work with IO page fault only. If we have SVA+pin,
> > we would get both sharing address and stable I/O latency.
> 
> Isn't it like a traditional MAP_DMA API (imply pinning) plus specifying 
> cpu_va of the memory pool as the iova? 

I think their issue is the HW can't do the cpu_va trick without also
involving the system IOMMU in a SVA mode

It really is something that belongs under some general /dev/sva as we
talked on the vfio thread

Jason


  parent reply	other threads:[~2021-02-01 23:44 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-25  8:34 [RFC PATCH v2] uacce: Add uacce_ctrl misc device Zhou Wang
2021-01-25  8:34 ` Zhou Wang
2021-01-25  9:28 ` Greg Kroah-Hartman
2021-01-25  9:28   ` Greg Kroah-Hartman
2021-01-25 12:47   ` Zhou Wang
2021-01-25 12:47     ` Zhou Wang
2021-01-25 15:47 ` Jason Gunthorpe
2021-01-25 15:47   ` Jason Gunthorpe
2021-01-25 22:21   ` Song Bao Hua (Barry Song)
2021-01-25 22:21     ` Song Bao Hua (Barry Song)
2021-01-25 23:16     ` Jason Gunthorpe
2021-01-25 23:16       ` Jason Gunthorpe
2021-01-25 23:35       ` Song Bao Hua (Barry Song)
2021-01-25 23:35         ` Song Bao Hua (Barry Song)
2021-01-26  1:13         ` Jason Gunthorpe
2021-01-26  1:13           ` Jason Gunthorpe
2021-01-26  1:26           ` Song Bao Hua (Barry Song)
2021-01-26  1:26             ` Song Bao Hua (Barry Song)
2021-01-26 18:20             ` Jason Gunthorpe
2021-01-26 18:20               ` Jason Gunthorpe
2021-01-28  1:28               ` Song Bao Hua (Barry Song)
2021-01-28  1:28                 ` Song Bao Hua (Barry Song)
2021-01-29 10:09             ` Tian, Kevin
2021-01-29 10:09               ` Tian, Kevin
2021-01-29 10:33               ` Song Bao Hua (Barry Song)
2021-01-29 10:33                 ` Song Bao Hua (Barry Song)
2021-02-01 23:44               ` Jason Gunthorpe [this message]
2021-02-01 23:44                 ` Jason Gunthorpe
2021-02-02  0:22                 ` Song Bao Hua (Barry Song)
2021-02-02  0:22                   ` Song Bao Hua (Barry Song)
2021-02-02  2:51                 ` Tian, Kevin
2021-02-02  2:51                   ` Tian, Kevin
2021-02-02  3:47                   ` Song Bao Hua (Barry Song)
2021-02-02  3:47                     ` Song Bao Hua (Barry Song)
2021-01-26  9:00   ` Zhou Wang
2021-01-26  9:00     ` Zhou Wang

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=20210201234424.GI4718@ziepe.ca \
    --to=jgg@ziepe.ca \
    --cc=arnd@arndb.de \
    --cc=chensihang1@hisilicon.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=kevin.tian@intel.com \
    --cc=liguozhu@hisilicon.com \
    --cc=linux-accelerators@lists.ozlabs.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=zhangfei.gao@linaro.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.