From: Rob Clark <robdclark@gmail.com>
To: Jordan Crouse <jcrouse@codeaurora.org>
Cc: linux-arm-msm <linux-arm-msm@vger.kernel.org>,
David Airlie <airlied@linux.ie>,
dri-devel <dri-devel@lists.freedesktop.org>,
Bjorn Andersson <bjorn.andersson@linaro.org>,
Eric Anholt <eric@anholt.net>,
AngeloGioacchino Del Regno <kholk11@gmail.com>,
Will Deacon <will@kernel.org>,
Emil Velikov <emil.velikov@collabora.com>,
Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>,
Jonathan Marek <jonathan@marek.ca>,
Sam Ravnborg <sam@ravnborg.org>,
"list@263.net:IOMMU DRIVERS <iommu@lists.linux-foundation.org>,
Joerg Roedel <joro@8bytes.org>,"
<iommu@lists.linux-foundation.org>,
Ben Dooks <ben.dooks@codethink.co.uk>,
Wambui Karuga <wambui.karugax@gmail.com>,
Sharat Masetty <smasetty@codeaurora.org>,
Brian Masney <masneyb@onstation.org>, Sean Paul <sean@poorly.run>,
Robin Murphy <robin.murphy@arm.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Daniel Vetter <daniel@ffwll.ch>, Shawn Guo <shawn.guo@linaro.org>,
freedreno <freedreno@lists.freedesktop.org>
Subject: Re: [Freedreno] [PATCH v12 07/13] drm/msm: Add a context pointer to the submitqueue
Date: Thu, 13 Aug 2020 09:17:21 -0700 [thread overview]
Message-ID: <CAF6AEGsA-jWLvSjZYz=ZkM7cxC5Wv6rDcoVv-9K5QpEZT=Cv7A@mail.gmail.com> (raw)
In-Reply-To: <20200810222657.1841322-8-jcrouse@codeaurora.org>
On Mon, Aug 10, 2020 at 3:27 PM Jordan Crouse <jcrouse@codeaurora.org> wrote:
>
> Each submitqueue is attached to a context. Add a pointer to the
> context to the submitqueue at create time and refcount it so
> that it stays around through the life of the queue.
>
> GPU submissions can access the active context via the submitqueue
> instead of requiring it to be passed around from function to
> function.
>
> Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
> ---
>
> drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 12 +++++-------
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 5 ++---
> drivers/gpu/drm/msm/adreno/adreno_gpu.c | 5 ++---
> drivers/gpu/drm/msm/adreno/adreno_gpu.h | 3 +--
> drivers/gpu/drm/msm/msm_drv.c | 3 ++-
> drivers/gpu/drm/msm/msm_drv.h | 8 ++++++++
> drivers/gpu/drm/msm/msm_gem.h | 1 +
> drivers/gpu/drm/msm/msm_gem_submit.c | 8 ++++----
> drivers/gpu/drm/msm/msm_gpu.c | 9 ++++-----
> drivers/gpu/drm/msm/msm_gpu.h | 7 +++----
> drivers/gpu/drm/msm/msm_submitqueue.c | 8 +++++++-
> 11 files changed, 39 insertions(+), 30 deletions(-)
>
[snip]
> diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
> index 972490b14ba5..9c573c4269cb 100644
> --- a/drivers/gpu/drm/msm/msm_gem.h
> +++ b/drivers/gpu/drm/msm/msm_gem.h
> @@ -142,6 +142,7 @@ struct msm_gem_submit {
> bool valid; /* true if no cmdstream patching needed */
> bool in_rb; /* "sudo" mode, copy cmds into RB */
> struct msm_ringbuffer *ring;
> + struct msm_file_private *ctx;
So, it looks like this is (currently) unused, and everything is
instead using submit->queue->ctx
That said, changing this so the submit also holds a ref to the ctx
seems to fix the intermittent splat I can trigger by repeatedly
hanging the gpu. Which (from the pile of additional tracepoints I've
added on top of this series) seems to be related to re-playing submits
after the userspace process has crashed and/or closed the device.
It seems like the reference the submit holds to the queue should keep
the ctx (and therefore address space) alive, but I need to dig through
that a bit more.
BR,
-R
> unsigned int nr_cmds;
> unsigned int nr_bos;
> u32 ident; /* A "identifier" for the submit for logging */
next prev parent reply other threads:[~2020-08-13 16:16 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-10 22:26 [PATCH v12 00/13] iommu/arm-smmu: Add Adreno SMMU specific implementation Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 01/13] iommu/arm-smmu: Pass io-pgtable config to implementation specific function Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 02/13] iommu/arm-smmu: Add support for split pagetables Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 03/13] iommu/arm-smmu: Prepare for the adreno-smmu implementation Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 04/13] iommu: Add a domain attribute to get/set a pagetable configuration Jordan Crouse
2020-08-13 13:14 ` Will Deacon
2020-08-13 15:11 ` [Freedreno] " Rob Clark
2020-08-13 15:19 ` Will Deacon
2020-08-13 16:28 ` Rob Clark
2020-08-10 22:26 ` [PATCH v12 05/13] iommu/arm-smmu-qcom: Add implementation for the adreno GPU SMMU Jordan Crouse
2020-08-13 13:23 ` Will Deacon
2020-08-10 22:26 ` [PATCH v12 06/13] dt-bindings: arm-smmu: Add compatible string for Adreno " Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 07/13] drm/msm: Add a context pointer to the submitqueue Jordan Crouse
2020-08-13 16:17 ` Rob Clark [this message]
2020-08-13 17:04 ` [Freedreno] " Rob Clark
2020-08-10 22:26 ` [PATCH v12 08/13] drm/msm: Set the global virtual address range from the IOMMU domain Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 09/13] drm/msm: Add support to create a local pagetable Jordan Crouse
2020-08-23 23:05 ` Guenter Roeck
2020-08-10 22:26 ` [PATCH v12 10/13] drm/msm: Add support for private address space instances Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 11/13] drm/msm/a6xx: Add support for per-instance pagetables Jordan Crouse
2020-08-10 22:26 ` [PATCH v12 12/13] arm: dts: qcom: sm845: Set the compatible string for the GPU SMMU Jordan Crouse
2020-08-10 22:26 ` [RFC v12 13/13] iommu/arm-smmu: Add a init_context_bank implementation hook Jordan Crouse
2020-08-13 13:03 ` Will Deacon
2020-08-13 13:19 ` [PATCH v12 00/13] iommu/arm-smmu: Add Adreno SMMU specific implementation Will Deacon
2020-08-14 2:40 ` [PATCH 00/19] iommu/arm-smmu + drm/msm: per-process GPU pgtables Rob Clark
2020-08-17 16:51 ` Jordan Crouse
2020-08-14 2:40 ` [PATCH 01/19] drm/msm: remove dangling submitqueue references Rob Clark
2020-08-17 16:51 ` Jordan Crouse
2020-09-01 2:35 ` Bjorn Andersson
2020-09-01 3:42 ` Rob Clark
2020-09-01 5:42 ` Bjorn Andersson
2020-09-01 5:42 ` Bjorn Andersson
2020-08-14 2:40 ` [PATCH 02/19] iommu/arm-smmu: Pass io-pgtable config to implementation specific function Rob Clark
2020-09-01 3:36 ` Bjorn Andersson
2020-08-14 2:40 ` [PATCH 03/19] iommu/arm-smmu: Add support for split pagetables Rob Clark
2020-09-01 3:41 ` Bjorn Andersson
2020-08-14 2:40 ` [PATCH 04/19] iommu/arm-smmu: Prepare for the adreno-smmu implementation Rob Clark
2020-08-14 2:41 ` [PATCH 05/19] iommu: add private interface for adreno-smmu Rob Clark
2020-08-17 16:52 ` [Freedreno] " Jordan Crouse
2020-09-01 3:52 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 06/19] drm/msm/gpu: add dev_to_gpu() helper Rob Clark
2020-08-17 16:53 ` [Freedreno] " Jordan Crouse
2020-09-01 4:32 ` Bjorn Andersson
2020-09-01 15:53 ` Rob Clark
2020-08-14 2:41 ` [PATCH 07/19] drm/msm: set adreno_smmu as gpu's drvdata Rob Clark
2020-08-17 16:55 ` Jordan Crouse
2020-09-01 4:58 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 08/19] iommu/arm-smmu: constify some helpers Rob Clark
2020-09-01 4:56 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 09/19] iommu/arm-smmu-qcom: Add implementation for the adreno GPU SMMU Rob Clark
2020-09-01 5:00 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 10/19] dt-bindings: arm-smmu: Add compatible string for Adreno " Rob Clark
2020-09-01 5:00 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 11/19] drm/msm: Add a context pointer to the submitqueue Rob Clark
2020-09-01 5:05 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 12/19] drm/msm: Drop context arg to gpu->submit() Rob Clark
2020-09-01 5:06 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 13/19] drm/msm: Set the global virtual address range from the IOMMU domain Rob Clark
2020-09-01 5:23 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 14/19] drm/msm: Add support to create a local pagetable Rob Clark
2020-09-01 5:28 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 15/19] drm/msm: Add support for private address space instances Rob Clark
2020-09-01 5:30 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 16/19] drm/msm/a6xx: Add support for per-instance pagetables Rob Clark
2020-08-17 15:40 ` Akhil P Oommen
2020-08-17 15:51 ` Rob Clark
2020-08-17 16:47 ` Jordan Crouse
2020-08-14 2:41 ` [PATCH 17/19] arm: dts: qcom: sm845: Set the compatible string for the GPU SMMU Rob Clark
2020-08-14 2:41 ` [PATCH 18/19] iommu/arm-smmu: add a way for implementations to influence SCTLR Rob Clark
2020-09-01 5:31 ` Bjorn Andersson
2020-08-14 2:41 ` [PATCH 19/19] drm/msm: show process names in gem_describe Rob Clark
2020-08-17 17:14 ` [Freedreno] " Jordan Crouse
2020-09-01 5:35 ` Bjorn Andersson
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='CAF6AEGsA-jWLvSjZYz=ZkM7cxC5Wv6rDcoVv-9K5QpEZT=Cv7A@mail.gmail.com' \
--to=robdclark@gmail.com \
--cc=airlied@linux.ie \
--cc=ben.dooks@codethink.co.uk \
--cc=bjorn.andersson@linaro.org \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=emil.velikov@collabora.com \
--cc=eric@anholt.net \
--cc=freedreno@lists.freedesktop.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jcrouse@codeaurora.org \
--cc=jonathan@marek.ca \
--cc=kholk11@gmail.com \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=masneyb@onstation.org \
--cc=robin.murphy@arm.com \
--cc=saiprakash.ranjan@codeaurora.org \
--cc=sam@ravnborg.org \
--cc=sean@poorly.run \
--cc=shawn.guo@linaro.org \
--cc=smasetty@codeaurora.org \
--cc=wambui.karugax@gmail.com \
--cc=will@kernel.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).