From: Jonathan Cameron <jonathan.cameron@huawei.com>
To: zhangfei <zhangfei.gao@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Arnd Bergmann <arnd@arndb.de>, Zaibo Xu <xuzaibo@huawei.com>,
<linux-kernel@vger.kernel.org>,
Zhou Wang <wangzhou1@hisilicon.com>,
"Kenneth Lee" <liguozhu@hisilicon.com>,
<linux-accelerators@lists.ozlabs.org>
Subject: Re: [PATCH 2/2] uacce: add uacce module
Date: Fri, 23 Aug 2019 17:36:03 +0100 [thread overview]
Message-ID: <20190823173603.00001b3d@huawei.com> (raw)
In-Reply-To: <b5d9fe84-abfd-c8ca-d059-e186e1609e06@linaro.org>
On Fri, 23 Aug 2019 17:21:33 +0800
zhangfei <zhangfei.gao@linaro.org> wrote:
> Hi, Jonathan
Hi zhangfei,
>
> Thanks for your careful review and good suggestion.
> Sorry for late response, I am checking one detail.
I have reviews on patches from years ago that I still haven't replied to ;)
>
> On 2019/8/16 上午12:54, Jonathan Cameron wrote:
> > On Wed, 14 Aug 2019 17:34:25 +0800
> > Zhangfei Gao <zhangfei.gao@linaro.org> wrote:
> >
> >> From: Kenneth Lee <liguozhu@hisilicon.com>
> >>
> >> Uacce is the kernel component to support WarpDrive accelerator
> >> framework. It provides register/unregister interface for device drivers
> >> to expose their hardware resource to the user space. The resource is
> >> taken as "queue" in WarpDrive.
> > It's a bit confusing to have both the term UACCE and WarpDrive in here.
> > I'd just use the uacce name in all comments etc.
> Yes, make sense
> >
> >> Uacce create a chrdev for every registration, the queue is allocated to
> >> the process when the chrdev is opened. Then the process can access the
> >> hardware resource by interact with the queue file. By mmap the queue
> >> file space to user space, the process can directly put requests to the
> >> hardware without syscall to the kernel space.
> >>
> >> Uacce also manages unify addresses between the hardware and user space
> >> of the process. So they can share the same virtual address in the
> >> communication.
> >>
> >> Signed-off-by: Kenneth Lee <liguozhu@hisilicon.com>
> >> Signed-off-by: Zaibo Xu <xuzaibo@huawei.com>
> >> Signed-off-by: Zhou Wang <wangzhou1@hisilicon.com>
> >> Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
> > I would strip this back to which ever case is of most interest (SVA I guess?)
> > and only think about adding support for the others if necessary at a later date.
> > (or in later patches).
> Do you mean split the patch and send sva part first?
Either:
1) SVA only in the first series, second series can do other options.
2) Patch N for SVA only, N+1... for other features.
I don't mind which, but I want to be able to see just one case and
review that before taking into account the affect of the more complex cases.
> >> +
> >> +static int uacce_qfr_alloc_pages(struct uacce_qfile_region *qfr)
> >> +{
> >> + int gfp_mask = GFP_ATOMIC | __GFP_ZERO;
> > More readable to just have this inline.
> Yes, all right.
> >
> >> + int i, j;
> >> +
...
> >> +static int uacce_set_iommu_domain(struct uacce *uacce)
> >> +{
> >> + struct iommu_domain *domain;
> >> + struct iommu_group *group;
> >> + struct device *dev = uacce->pdev;
> >> + bool resv_msi;
> >> + phys_addr_t resv_msi_base = 0;
> >> + int ret;
> >> +
> >> + if ((uacce->flags & UACCE_DEV_NOIOMMU) ||
> >> + (uacce->flags & UACCE_DEV_PASID))
> >> + return 0;
> >> +
> >> + /*
> >> + * We don't support multiple register for the same dev in RFC version ,
> >> + * will add it in formal version
> > So this effectively multiple complete uacce interfaces for one device.
> > Is there a known usecase for that?
> Here is preventing one device with multiple algorithm and register
> multi-times,
> and without sva, they can not be distinguished.
Isn't that a bug in the device driver?
> >> + */
> >> + ret = class_for_each_device(uacce_class, NULL, uacce->pdev,
> >> + uacce_dev_match);
> >> + if (ret)
> >> + return ret;
> >> +
> >> + /* allocate and attach a unmanged domain */
...
next prev parent reply other threads:[~2019-08-23 16:36 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-14 9:34 [PATCH 0/2] A General Accelerator Framework, WarpDrive Zhangfei Gao
2019-08-14 9:34 ` [PATCH 1/2] uacce: Add documents for WarpDrive/uacce Zhangfei Gao
2019-08-14 9:34 ` [PATCH 2/2] uacce: add uacce module Zhangfei Gao
2019-08-15 14:12 ` Greg Kroah-Hartman
[not found] ` <5d5a6757.1c69fb81.e0678.2ab2SMTPIN_ADDED_BROKEN@mx.google.com>
2019-08-19 10:22 ` Greg Kroah-Hartman
2019-08-20 12:38 ` zhangfei
2019-08-20 14:31 ` Greg Kroah-Hartman
2019-08-15 14:13 ` Greg Kroah-Hartman
2019-08-20 13:08 ` zhangfei
2019-08-20 16:59 ` Greg Kroah-Hartman
[not found] ` <5d5cf0fc.1c69fb81.ec57f.b853SMTPIN_ADDED_BROKEN@mx.google.com>
2019-08-21 9:17 ` Greg Kroah-Hartman
2019-08-21 14:30 ` zhangfei
2019-08-21 16:05 ` Greg Kroah-Hartman
2019-08-26 4:10 ` Kenneth Lee
2019-08-26 4:29 ` Greg Kroah-Hartman
2019-08-27 11:42 ` Kenneth Lee
2019-08-27 18:48 ` Greg Kroah-Hartman
2019-08-15 14:20 ` Greg Kroah-Hartman
[not found] ` <5d5a6f5b.1c69fb81.9d35e.5303SMTPIN_ADDED_BROKEN@mx.google.com>
2019-08-19 10:24 ` Greg Kroah-Hartman
2019-08-20 12:36 ` zhangfei
2019-08-20 14:33 ` Greg Kroah-Hartman
2019-08-24 12:53 ` zhangfei
2019-08-24 15:40 ` Greg Kroah-Hartman
2019-08-15 16:54 ` Jonathan Cameron
2019-08-23 9:21 ` zhangfei
2019-08-23 16:36 ` Jonathan Cameron [this message]
2019-08-23 16:42 ` Jonathan Cameron
2019-08-15 17:04 ` [PATCH 0/2] A General Accelerator Framework, WarpDrive Jerome Glisse
2019-08-20 14:26 ` zhangfei
2019-08-26 4:14 ` Kenneth Lee
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=20190823173603.00001b3d@huawei.com \
--to=jonathan.cameron@huawei.com \
--cc=arnd@arndb.de \
--cc=gregkh@linuxfoundation.org \
--cc=liguozhu@hisilicon.com \
--cc=linux-accelerators@lists.ozlabs.org \
--cc=linux-kernel@vger.kernel.org \
--cc=wangzhou1@hisilicon.com \
--cc=xuzaibo@huawei.com \
--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 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).