From: Mikko Perttunen <cyndis@kapsi.fi>
To: Dmitry Osipenko <digetx@gmail.com>,
Thierry Reding <thierry.reding@gmail.com>,
Jon Hunter <jonathanh@nvidia.com>,
David Airlie <airlied@linux.ie>, Daniel Vetter <daniel@ffwll.ch>,
sumit.semwal@linaro.org, gustavo@padovan.org
Cc: "linux-tegra@vger.kernel.org" <linux-tegra@vger.kernel.org>,
talho@nvidia.com, bhuntsman@nvidia.com,
dri-devel <dri-devel@lists.freedesktop.org>
Subject: Re: [RFC] Host1x/TegraDRM UAPI (drm_tegra_submit_relocation)
Date: Fri, 26 Jun 2020 12:01:00 +0300 [thread overview]
Message-ID: <9486b5c7-7588-34fd-bb60-a3b0f252f113@kapsi.fi> (raw)
In-Reply-To: <eb3cac23-cd8c-732b-684c-c2d531de00a2@gmail.com>
On 6/26/20 1:50 AM, Dmitry Osipenko wrote:
> 25.06.2020 12:27, Mikko Perttunen пишет:
>> On 6/25/20 1:33 AM, Dmitry Osipenko wrote:
>>> 23.06.2020 15:09, Mikko Perttunen пишет:
>>>> struct drm_tegra_submit_relocation {
>>>> /* [in] Index of GATHER or GATHER_UPTR command in commands. */
>>>> __u32 gather_command_index;
>>>>
>>>> /*
>>>> * [in] Mapping handle (obtained through CHANNEL_MAP) of the
>>>> memory
>>>> * the address of which will be patched in.
>>>> */
>>>> __u32 mapping_id;
>>>>
>>>> /*
>>>> * [in] Offset in the gather that will be patched.
>>>> */
>>>> __u64 gather_offset;
>>>>
>>>> /*
>>>> * [in] Offset in target buffer whose paddr/IOVA will be
>>>> written
>>>> * to the gather.
>>>> */
>>>> __u64 target_offset;
>>>>
>>>> /*
>>>> * [in] Number of bits the resulting address will be logically
>>>> * shifted right before writing to gather.
>>>> */
>>>> __u32 shift;
>>>>
>>>> __u32 reserved[1];
>>>> };
>>>
>>> We will also need read/write direction flag here for the
>>> DMA-reservations set up, it will be used for the implicit BO fencing by
>>> the job's scheduler.
>>>
>>
>> Ideally on newer chips with context isolation, we no longer know what
>> DMA-BUFs are being used by the job at submit time - they would just be
>> pointers after being MAPped.
>
> The DMA-BUFs themselves shouldn't be needed, but GEMs should.
Yes, I meant to say GEM instead of DMA-BUF.
>
>> Do you know how other GPUs deal with DMA reservations - I expect
>> separate MAP and SUBMIT steps would be pretty common?
>
> I can't instantly recall what other drivers do, could be worthwhile to
> take a closer look.
I'll see if I can find some similar situations in other drivers.
Mikko
>
>> Do you have to
>> pass the DMA-BUF to both steps (i.e. do IOMMU mapping during MAP, and
>> manage reservations at SUBMIT)?
>
> Yes, this sounds good to me if DMA-BUF part is replaced with a GEM.
>
> Please see my other reply regarding the MAP IOCTL where I'm suggesting
> to back mapping IDs with a GEM.
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2020-06-26 9:01 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-23 12:09 [RFC] Host1x/TegraDRM UAPI Mikko Perttunen
2020-06-24 20:55 ` Dmitry Osipenko
2020-06-25 9:17 ` Mikko Perttunen
2020-06-24 22:33 ` Dmitry Osipenko
2020-06-25 9:27 ` Mikko Perttunen
2020-06-25 22:50 ` [RFC] Host1x/TegraDRM UAPI (drm_tegra_submit_relocation) Dmitry Osipenko
2020-06-26 9:01 ` Mikko Perttunen [this message]
2020-06-24 23:11 ` [RFC] Host1x/TegraDRM UAPI Dmitry Osipenko
2020-06-25 9:16 ` Mikko Perttunen
2020-06-25 23:24 ` Dmitry Osipenko
2020-06-26 9:05 ` Mikko Perttunen
2020-06-24 23:18 ` Dmitry Osipenko
2020-06-25 0:59 ` Dmitry Osipenko
2020-06-24 23:23 ` Dmitry Osipenko
2020-06-25 9:19 ` Mikko Perttunen
2020-06-25 0:47 ` Dmitry Osipenko
2020-06-25 9:23 ` Mikko Perttunen
2020-06-25 22:47 ` [RFC] Host1x/TegraDRM UAPI (drm_tegra_channel_map) Dmitry Osipenko
2020-06-26 7:34 ` Thierry Reding
2020-06-26 16:35 ` Dmitry Osipenko
2020-06-28 11:16 ` Mikko Perttunen
2020-06-28 22:59 ` Dmitry Osipenko
2020-06-30 10:55 ` Mikko Perttunen
2020-06-30 19:48 ` Dmitry Osipenko
2020-06-26 11:06 ` [RFC] Host1x/TegraDRM UAPI Karol Herbst
2020-06-26 11:13 ` Mikko Perttunen
2020-06-26 11:16 ` Karol Herbst
2020-06-26 11:40 ` Thierry Reding
2020-06-26 13:38 ` Daniel Vetter
2020-06-26 13:59 ` Dmitry Osipenko
2020-06-30 9:09 ` Daniel Vetter
2020-06-27 21:47 ` [RFC] Host1x/TegraDRM UAPI (drm_tegra_submit_syncpt_incr) Dmitry Osipenko
2020-06-28 11:10 ` Mikko Perttunen
2020-06-27 22:32 ` [RFC] Host1x/TegraDRM UAPI (drm_tegra_submit_command) Dmitry Osipenko
2020-06-28 10:28 ` Mikko Perttunen
2020-06-29 0:00 ` Dmitry Osipenko
2020-06-30 10:40 ` Mikko Perttunen
2020-06-27 23:27 ` [RFC] Host1x/TegraDRM UAPI (sync points) Dmitry Osipenko
2020-06-28 9:44 ` Mikko Perttunen
2020-06-29 2:36 ` Dmitry Osipenko
2020-06-29 10:27 ` Mikko Perttunen
2020-06-29 19:28 ` Dmitry Osipenko
2020-06-29 19:33 ` Dmitry Osipenko
2020-06-29 19:42 ` Dmitry Osipenko
2020-06-30 10:26 ` Mikko Perttunen
2020-07-01 0:22 ` Dmitry Osipenko
2020-07-02 12:10 ` Mikko Perttunen
2020-07-07 11:06 ` Dmitry Osipenko
2020-07-08 10:06 ` Mikko Perttunen
2020-07-09 9:28 ` Dmitry Osipenko
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=9486b5c7-7588-34fd-bb60-a3b0f252f113@kapsi.fi \
--to=cyndis@kapsi.fi \
--cc=airlied@linux.ie \
--cc=bhuntsman@nvidia.com \
--cc=daniel@ffwll.ch \
--cc=digetx@gmail.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=gustavo@padovan.org \
--cc=jonathanh@nvidia.com \
--cc=linux-tegra@vger.kernel.org \
--cc=sumit.semwal@linaro.org \
--cc=talho@nvidia.com \
--cc=thierry.reding@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).