mbox series

[RFC,00/11] Affirm SMMU coherent pagetable walker capability on RPMh SoCs

Message ID 20240919-topic-apps_smmu_coherent-v1-0-5b3a8662403d@quicinc.com
Headers show
Series Affirm SMMU coherent pagetable walker capability on RPMh SoCs | expand

Message

Konrad Dybcio Sept. 18, 2024, 10:57 p.m. UTC 
I only read back the SMMU config on X1E & 7280, but I have it on good
authority that this concerns all RPMh SoCs. Sending as RFC just in case.

Lacking coherency can hurt performance, but claiming coherency where it's
absent would lead to a kaboom.

Signed-off-by: Konrad Dybcio <quic_kdybcio@quicinc.com>
---
Konrad Dybcio (11):
      arm64: dts: qcom: qdu1000: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sc7180: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sc8180x: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sc8280xp: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sdm670: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sdm845: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sm6350: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sm8150: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sm8350: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: sm8450: Affirm IDR0.CCTW on apps_smmu
      arm64: dts: qcom: x1e80100: Affirm IDR0.CCTW on apps_smmu

 arch/arm64/boot/dts/qcom/qdu1000.dtsi  | 1 +
 arch/arm64/boot/dts/qcom/sc7180.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sc8180x.dtsi  | 2 +-
 arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 1 +
 arch/arm64/boot/dts/qcom/sdm670.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sdm845.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sm6350.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sm8150.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sm8350.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/sm8450.dtsi   | 1 +
 arch/arm64/boot/dts/qcom/x1e80100.dtsi | 2 ++
 11 files changed, 12 insertions(+), 1 deletion(-)
---
base-commit: 55bcd2e0d04c1171d382badef1def1fd04ef66c5
change-id: 20240919-topic-apps_smmu_coherent-070f38a2c207

Best regards,

Comments

Luca Weiss Sept. 19, 2024, 7 a.m. UTC | #1 
On Thu Sep 19, 2024 at 12:57 AM CEST, Konrad Dybcio wrote:
> I only read back the SMMU config on X1E & 7280, but I have it on good
> authority that this concerns all RPMh SoCs. Sending as RFC just in case.
>
> Lacking coherency can hurt performance, but claiming coherency where it's
> absent would lead to a kaboom.

Hi Konrad!

You want people with the affected SoCs to test this I imagine?

Just boot it and see if it doesn't implode, or do you have any more
elaborate test plan for this?

Regards
Luca

>
> Signed-off-by: Konrad Dybcio <quic_kdybcio@quicinc.com>
> ---
> Konrad Dybcio (11):
>       arm64: dts: qcom: qdu1000: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sc7180: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sc8180x: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sc8280xp: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sdm670: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sdm845: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sm6350: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sm8150: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sm8350: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: sm8450: Affirm IDR0.CCTW on apps_smmu
>       arm64: dts: qcom: x1e80100: Affirm IDR0.CCTW on apps_smmu
>
>  arch/arm64/boot/dts/qcom/qdu1000.dtsi  | 1 +
>  arch/arm64/boot/dts/qcom/sc7180.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sc8180x.dtsi  | 2 +-
>  arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 1 +
>  arch/arm64/boot/dts/qcom/sdm670.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sdm845.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sm6350.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sm8150.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sm8350.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/sm8450.dtsi   | 1 +
>  arch/arm64/boot/dts/qcom/x1e80100.dtsi | 2 ++
>  11 files changed, 12 insertions(+), 1 deletion(-)
> ---
> base-commit: 55bcd2e0d04c1171d382badef1def1fd04ef66c5
> change-id: 20240919-topic-apps_smmu_coherent-070f38a2c207
>
> Best regards,
Konrad Dybcio Sept. 19, 2024, 10:07 a.m. UTC | #2 
On 19.09.2024 9:00 AM, Luca Weiss wrote:
> On Thu Sep 19, 2024 at 12:57 AM CEST, Konrad Dybcio wrote:
>> I only read back the SMMU config on X1E & 7280, but I have it on good
>> authority that this concerns all RPMh SoCs. Sending as RFC just in case.
>>
>> Lacking coherency can hurt performance, but claiming coherency where it's
>> absent would lead to a kaboom.
> 
> Hi Konrad!
> 
> You want people with the affected SoCs to test this I imagine?

Yeah, would be nice to confirm

> 
> Just boot it and see if it doesn't implode, or do you have any more
> elaborate test plan for this?

No, booting should be enough of a test

Konrad
Steev Klimaszewski Sept. 19, 2024, 6:48 p.m. UTC | #3 
Hi Konrad,

On Thu, Sep 19, 2024 at 5:07 AM Konrad Dybcio <konradybcio@kernel.org> wrote:
>
> On 19.09.2024 9:00 AM, Luca Weiss wrote:
> > On Thu Sep 19, 2024 at 12:57 AM CEST, Konrad Dybcio wrote:
> >> I only read back the SMMU config on X1E & 7280, but I have it on good
> >> authority that this concerns all RPMh SoCs. Sending as RFC just in case.
> >>
> >> Lacking coherency can hurt performance, but claiming coherency where it's
> >> absent would lead to a kaboom.
> >
> > Hi Konrad!
> >
> > You want people with the affected SoCs to test this I imagine?
>
> Yeah, would be nice to confirm
>
> >
> > Just boot it and see if it doesn't implode, or do you have any more
> > elaborate test plan for this?
>
> No, booting should be enough of a test
>
> Konrad

I have tested sc8280xp on the Thinkpad X13s.  It still boots and
nothing seems to be more broken than usual (kidding, it seems to be
running exactly as it was before the patchset was applied.)  I will
try to find the time to test sc8180x on a Flex 5G as well as the
sdm845 on the Lenovo Yoga C630, but I can't promise I'll find the
time.

Tested-by: Steev Klimaszewski <steev@kali.org> # Thinkpad X13s (sc8280xp)
Neil Armstrong Sept. 20, 2024, 7:35 a.m. UTC | #4 
On 19/09/2024 00:57, Konrad Dybcio wrote:
> I only read back the SMMU config on X1E & 7280, but I have it on good
> authority that this concerns all RPMh SoCs. Sending as RFC just in case.
> 
> Lacking coherency can hurt performance, but claiming coherency where it's
> absent would lead to a kaboom.
> 
> Signed-off-by: Konrad Dybcio <quic_kdybcio@quicinc.com>
> ---
> Konrad Dybcio (11):
>        arm64: dts: qcom: qdu1000: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sc7180: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sc8180x: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sc8280xp: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sdm670: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sdm845: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sm6350: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sm8150: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sm8350: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: sm8450: Affirm IDR0.CCTW on apps_smmu
>        arm64: dts: qcom: x1e80100: Affirm IDR0.CCTW on apps_smmu
> 
>   arch/arm64/boot/dts/qcom/qdu1000.dtsi  | 1 +
>   arch/arm64/boot/dts/qcom/sc7180.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sc8180x.dtsi  | 2 +-
>   arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 1 +
>   arch/arm64/boot/dts/qcom/sdm670.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sdm845.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sm6350.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sm8150.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sm8350.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/sm8450.dtsi   | 1 +
>   arch/arm64/boot/dts/qcom/x1e80100.dtsi | 2 ++
>   11 files changed, 12 insertions(+), 1 deletion(-)
> ---
> base-commit: 55bcd2e0d04c1171d382badef1def1fd04ef66c5
> change-id: 20240919-topic-apps_smmu_coherent-070f38a2c207
> 
> Best regards,

Ran this serie in our CI, here's the pipeline: https://git.codelinaro.org/linaro/qcomlt/ci/staging/cdba-tester/-/pipelines/104656
For some lab reasons, x1e80100 & onneplus-enchilada didn't boot, ignore them.

Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sdm845-rb3
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sm8150-hdk
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sm8350-hdk
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sm8450-hdk

Neil
Bjorn Andersson Oct. 7, 2024, 2:25 p.m. UTC | #5 
On Thu, 19 Sep 2024 00:57:13 +0200, Konrad Dybcio wrote:
> I only read back the SMMU config on X1E & 7280, but I have it on good
> authority that this concerns all RPMh SoCs. Sending as RFC just in case.
> 
> Lacking coherency can hurt performance, but claiming coherency where it's
> absent would lead to a kaboom.
> 
> 
> [...]

Applied, thanks!

[01/11] arm64: dts: qcom: qdu1000: Affirm IDR0.CCTW on apps_smmu
        commit: 7a52db70c8c5f4e2f6cf404b6cac10beae43f2bd
[02/11] arm64: dts: qcom: sc7180: Affirm IDR0.CCTW on apps_smmu
        commit: 3d89c1984000171665d8091c7fdf20f9cf814786
[03/11] arm64: dts: qcom: sc8180x: Affirm IDR0.CCTW on apps_smmu
        commit: 57222f077bd05b6ef8c5b2998400122f3c202e51
[04/11] arm64: dts: qcom: sc8280xp: Affirm IDR0.CCTW on apps_smmu
        commit: 2b73b83cb82aefb6c907ea91a9977641bbcae683
[05/11] arm64: dts: qcom: sdm670: Affirm IDR0.CCTW on apps_smmu
        commit: e009473c5f5d62d4e0f093a3126cf98e319d8cd0
[06/11] arm64: dts: qcom: sdm845: Affirm IDR0.CCTW on apps_smmu
        commit: 6b31a9744b8726c69bb0af290f8475a368a4b805
[07/11] arm64: dts: qcom: sm6350: Affirm IDR0.CCTW on apps_smmu
        commit: 7abe72765d9f6a900a1c2b6c12b9dd70010a8b0b
[08/11] arm64: dts: qcom: sm8150: Affirm IDR0.CCTW on apps_smmu
        commit: 05bd9923d15e8508cd0fa4f3d03437df1a9362aa
[09/11] arm64: dts: qcom: sm8350: Affirm IDR0.CCTW on apps_smmu
        commit: 051ff563cb3d87c631c8997d9b3636a7b59a12b9
[10/11] arm64: dts: qcom: sm8450: Affirm IDR0.CCTW on apps_smmu
        commit: c9ab6652769d331e39f7489241e8b3427f7e8608
[11/11] arm64: dts: qcom: x1e80100: Affirm IDR0.CCTW on apps_smmu
        commit: 5207d9c75f18db46ce42074f6585c7ca8e4aca75

Best regards,