From: neil.armstrong@linaro.org
To: Akhil P Oommen <quic_akhilpo@quicinc.com>
Cc: Viresh Kumar <vireshk@kernel.org>, Nishanth Menon <nm@ti.com>,
Stephen Boyd <sboyd@kernel.org>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Rob Clark <robdclark@gmail.com>, Sean Paul <sean@poorly.run>,
Konrad Dybcio <konradybcio@kernel.org>,
Abhinav Kumar <quic_abhinavk@quicinc.com>,
Dmitry Baryshkov <dmitry.baryshkov@linaro.org>,
Marijn Suijten <marijn.suijten@somainline.org>,
David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
Bjorn Andersson <andersson@kernel.org>,
Rob Herring <robh@kernel.org>,
Krzysztof Kozlowski <krzk+dt@kernel.org>,
Conor Dooley <conor+dt@kernel.org>,
Connor Abbott <cwabbott0@gmail.com>,
linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-arm-msm@vger.kernel.org, dri-devel@lists.freedesktop.org,
freedreno@lists.freedesktop.org, devicetree@vger.kernel.org
Subject: Re: [PATCH v2 08/11] drm/msm: adreno: request for maximum bus bandwidth usage
Date: Wed, 27 Nov 2024 16:55:27 +0100 [thread overview]
Message-ID: <79e76b0d-15df-444e-ab14-24cf32678b96@linaro.org> (raw)
In-Reply-To: <2d3a77da-cf73-4888-bc4d-68482181c908@quicinc.com>
On 27/11/2024 16:46, Akhil P Oommen wrote:
> On 11/25/2024 1:44 PM, Neil Armstrong wrote:
>> On 23/11/2024 23:59, Akhil P Oommen wrote:
>>> On Tue, Nov 19, 2024 at 06:56:43PM +0100, Neil Armstrong wrote:
>>>> When requesting a DDR bandwidth level along a GPU frequency
>>>> level via the GMU, we can also specify the bus bandwidth usage in a
>>>> 16bit
>>>> quantitized value.
>>>>
>>>> For now simply request the maximum bus usage.
>>>
>>> Why? You don't care about power efficiency?
>>> Lets drop this patch. We don't care about AB vote yet.
>>
>> I care about functionality, without this AB vote the spillall use
>> case that fails on SM8650 HDK fails on the SM8650 QRD.
>
> This should have been documented as a comment so that someone doesn't
> remove it in future.
>
>>
>> AB is a quantitized value of the BW voted, so yes I expect we can have
>> 100% of the BW voted, but since we scale the BW it's perfectly fine.
>
> Ah! no. MAX AB vote here is equal to the Max IB vote value in the hfi
> table. This is why I was asking about including all BW levels from the
> DT in the hfi table in the other patch.
>
> So you are always voting for Max DDR Freq which is probably helping (or
> masking?) the spill all issue. We can just add a quirk to vote for MAX
> IB probably.
Oh, indeed I've been re-reading gen7_bus_ab_quantize() and it seems
I should calculate the AB vote when building the bw_table.
Thanks,
Neil
>
> -Akhil
>
>>
>> Neil
>>
>>>
>>> -Akhil
>>>
>>>>
>>>> Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
>>>> ---
>>>> drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 11 +++++++++++
>>>> drivers/gpu/drm/msm/adreno/a6xx_hfi.h | 5 +++++
>>>> 2 files changed, 16 insertions(+)
>>>>
>>>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/
>>>> msm/adreno/a6xx_gmu.c
>>>> index
>>>> dc2d0035544e7848e5c4ea27f1ea9a191f9c4991..36c0f67fd8e109aabf09a0804bacbed3593c39d7 100644
>>>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>>>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>>>> @@ -134,6 +134,17 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu,
>>>> struct dev_pm_opp *opp,
>>>> if (bw == gmu->gpu_bw_table[bw_index])
>>>> break;
>>>> }
>>>> +
>>>> + if (bw_index) {
>>>> + /*
>>>> + * Append AB vote to the maximum bus usage.
>>>> + * AB represents a quantitized 16bit value of the
>>>> + * max ddr bandwidth we could use, let's simply
>>>> + * request the maximum for now.
>>>> + */
>>>> + bw_index |= AB_VOTE(MAX_AB_VOTE);
>>>> + bw_index |= AB_VOTE_ENABLE;
>>>> + }
>>>> }
>>>> gmu->current_perf_index = perf_index;
>>>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/
>>>> msm/adreno/a6xx_hfi.h
>>>> index
>>>> 528110169398f69f16443a29a1594d19c36fb595..52ba4a07d7b9a709289acd244a751ace9bdaab5d 100644
>>>> --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h
>>>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h
>>>> @@ -173,6 +173,11 @@ struct a6xx_hfi_gx_bw_perf_vote_cmd {
>>>> u32 bw;
>>>> };
>>>> +#define AB_VOTE_MASK GENMASK(31, 16)
>>>> +#define MAX_AB_VOTE (FIELD_MAX(AB_VOTE_MASK) - 1)
>>>> +#define AB_VOTE(vote) FIELD_PREP(AB_VOTE_MASK, (vote))
>>>> +#define AB_VOTE_ENABLE BIT(8)
>>>> +
>>>> #define HFI_H2F_MSG_PREPARE_SLUMBER 33
>>>> struct a6xx_hfi_prep_slumber_cmd {
>>>>
>>>> --
>>>> 2.34.1
>>>>
>>
>
next prev parent reply other threads:[~2024-11-27 15:55 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-19 17:56 [PATCH v2 00/11] drm/msm: adreno: add support for DDR bandwidth scaling via GMU Neil Armstrong
2024-11-19 17:56 ` [PATCH v2 01/11] opp: core: implement dev_pm_opp_get_bw Neil Armstrong
2024-11-25 5:18 ` Viresh Kumar
2024-11-19 17:56 ` [PATCH v2 02/11] drm/msm: adreno: rename quirks that are features Neil Armstrong
2024-11-23 19:25 ` Akhil P Oommen
2024-11-25 8:14 ` Neil Armstrong
2024-11-19 17:56 ` [PATCH v2 03/11] drm/msm: adreno: move features bits in a separate variable Neil Armstrong
2024-11-20 11:18 ` Dmitry Baryshkov
2024-11-20 18:54 ` Rob Clark
2024-11-21 18:44 ` Dmitry Baryshkov
2024-11-21 19:48 ` Rob Clark
2024-11-21 22:26 ` Dmitry Baryshkov
2024-11-19 17:56 ` [PATCH v2 04/11] drm/msm: adreno: add GMU_BW_VOTE feature flag Neil Armstrong
2024-11-20 11:19 ` Dmitry Baryshkov
2024-11-20 12:37 ` Neil Armstrong
2024-11-21 18:44 ` Dmitry Baryshkov
2024-11-21 19:50 ` Rob Clark
2024-11-21 19:53 ` Rob Clark
2024-11-23 19:43 ` Akhil P Oommen
2024-11-25 8:16 ` Neil Armstrong
2024-11-27 16:00 ` Akhil P Oommen
2024-11-27 19:01 ` neil.armstrong
2024-11-19 17:56 ` [PATCH v2 05/11] drm/msm: adreno: add plumbing to generate bandwidth vote table for GMU Neil Armstrong
2024-11-20 11:42 ` Dmitry Baryshkov
2024-11-20 12:37 ` Neil Armstrong
2024-11-21 18:45 ` Dmitry Baryshkov
2024-11-23 21:22 ` Akhil P Oommen
2024-11-23 22:46 ` Akhil P Oommen
2024-11-25 8:12 ` Neil Armstrong
2024-11-27 15:29 ` Akhil P Oommen
2024-11-27 15:47 ` neil.armstrong
2024-11-30 20:36 ` Akhil P Oommen
2024-12-11 8:23 ` neil.armstrong
2024-11-19 17:56 ` [PATCH v2 06/11] drm/msm: adreno: dynamically generate GMU bw table Neil Armstrong
2024-11-19 17:56 ` [PATCH v2 07/11] drm/msm: adreno: find bandwidth index of OPP and set it along freq index Neil Armstrong
2024-11-20 11:44 ` Dmitry Baryshkov
2024-11-19 17:56 ` [PATCH v2 08/11] drm/msm: adreno: request for maximum bus bandwidth usage Neil Armstrong
2024-11-23 22:59 ` Akhil P Oommen
2024-11-25 8:14 ` Neil Armstrong
2024-11-27 15:46 ` Akhil P Oommen
2024-11-27 15:55 ` neil.armstrong [this message]
2024-11-19 17:56 ` [PATCH v2 09/11] drm/msm: adreno: enable GMU bandwidth for A740 and A750 Neil Armstrong
2024-11-20 11:45 ` Dmitry Baryshkov
2024-11-19 17:56 ` [PATCH v2 10/11] arm64: qcom: dts: sm8550: add interconnect and opp-peak-kBps for GPU Neil Armstrong
2024-11-20 11:47 ` Dmitry Baryshkov
2024-11-20 12:38 ` Neil Armstrong
2024-11-19 17:56 ` [PATCH v2 11/11] arm64: qcom: dts: sm8650: " Neil Armstrong
2024-11-20 11:47 ` Dmitry Baryshkov
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=79e76b0d-15df-444e-ab14-24cf32678b96@linaro.org \
--to=neil.armstrong@linaro.org \
--cc=airlied@gmail.com \
--cc=andersson@kernel.org \
--cc=conor+dt@kernel.org \
--cc=cwabbott0@gmail.com \
--cc=devicetree@vger.kernel.org \
--cc=dmitry.baryshkov@linaro.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=freedreno@lists.freedesktop.org \
--cc=konradybcio@kernel.org \
--cc=krzk+dt@kernel.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=marijn.suijten@somainline.org \
--cc=nm@ti.com \
--cc=quic_abhinavk@quicinc.com \
--cc=quic_akhilpo@quicinc.com \
--cc=rafael@kernel.org \
--cc=robdclark@gmail.com \
--cc=robh@kernel.org \
--cc=sboyd@kernel.org \
--cc=sean@poorly.run \
--cc=simona@ffwll.ch \
--cc=vireshk@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