2020-10-19 13:16:00

by Akhil P Oommen

[permalink] [raw]
Subject: [PATCH v2 1/3] drm/msm: Add support for GPU cooling

Register GPU as a devfreq cooling device so that it can be passively
cooled by the thermal framework.

Signed-off-by: Akhil P Oommen <[email protected]>
---
Changes in v2:
1. Update the dt bindings documentation

drivers/gpu/drm/msm/msm_gpu.c | 12 ++++++++++++
drivers/gpu/drm/msm/msm_gpu.h | 2 ++
2 files changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 55d1648..9f9db46 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -14,6 +14,7 @@
#include <generated/utsrelease.h>
#include <linux/string_helpers.h>
#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
#include <linux/devcoredump.h>
#include <linux/sched/task.h>

@@ -107,9 +108,18 @@ static void msm_devfreq_init(struct msm_gpu *gpu)
if (IS_ERR(gpu->devfreq.devfreq)) {
DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
gpu->devfreq.devfreq = NULL;
+ return;
}

devfreq_suspend_device(gpu->devfreq.devfreq);
+
+ gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node,
+ gpu->devfreq.devfreq);
+ if (IS_ERR(gpu->cooling)) {
+ DRM_DEV_ERROR(&gpu->pdev->dev,
+ "Couldn't register GPU cooling device\n");
+ gpu->cooling = NULL;
+ }
}

static int enable_pwrrail(struct msm_gpu *gpu)
@@ -1005,4 +1015,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
msm_gem_address_space_put(gpu->aspace);
}
+
+ devfreq_cooling_unregister(gpu->cooling);
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 6c9e1fd..9a8f20d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -147,6 +147,8 @@ struct msm_gpu {
struct msm_gpu_state *crashstate;
/* True if the hardware supports expanded apriv (a650 and newer) */
bool hw_apriv;
+
+ struct thermal_cooling_device *cooling;
};

static inline struct msm_gpu *dev_to_gpu(struct device *dev)
--
2.7.4


2020-10-19 13:16:47

by Akhil P Oommen

[permalink] [raw]
Subject: [PATCH v2 2/3] arm64: dts: qcom: sc7180: Add gpu cooling support

Add cooling-cells property and the cooling maps for the gpu tzones
to support GPU cooling.

Signed-off-by: Akhil P Oommen <[email protected]>
---
The thermal policy should be set as 'step_wise' for gpu tzones from
the userspace during boot up.

arch/arm64/boot/dts/qcom/sc7180.dtsi | 30 +++++++++++++++++++++++-------
1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index d46b383..a7ea029 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -2,7 +2,7 @@
/*
* SC7180 SoC device tree source
*
- * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2019-20, The Linux Foundation. All rights reserved.
*/

#include <dt-bindings/clock/qcom,dispcc-sc7180.h>
@@ -1886,6 +1886,8 @@
operating-points-v2 = <&gpu_opp_table>;
qcom,gmu = <&gmu>;

+ #cooling-cells = <2>;
+
interconnects = <&gem_noc MASTER_GFX3D &mc_virt SLAVE_EBI1>;
interconnect-names = "gfx-mem";

@@ -3825,16 +3827,16 @@
};

gpuss0-thermal {
- polling-delay-passive = <0>;
+ polling-delay-passive = <100>;
polling-delay = <0>;

thermal-sensors = <&tsens0 13>;

trips {
gpuss0_alert0: trip-point0 {
- temperature = <90000>;
+ temperature = <95000>;
hysteresis = <2000>;
- type = "hot";
+ type = "passive";
};

gpuss0_crit: gpuss0_crit {
@@ -3843,19 +3845,26 @@
type = "critical";
};
};
+
+ cooling-maps {
+ map0 {
+ trip = <&gpuss0_alert0>;
+ cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
+ };
};

gpuss1-thermal {
- polling-delay-passive = <0>;
+ polling-delay-passive = <100>;
polling-delay = <0>;

thermal-sensors = <&tsens0 14>;

trips {
gpuss1_alert0: trip-point0 {
- temperature = <90000>;
+ temperature = <95000>;
hysteresis = <2000>;
- type = "hot";
+ type = "passive";
};

gpuss1_crit: gpuss1_crit {
@@ -3864,6 +3873,13 @@
type = "critical";
};
};
+
+ cooling-maps {
+ map0 {
+ trip = <&gpuss0_alert0>;
+ cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
+ };
};

aoss1-thermal {
--
2.7.4

2020-10-20 01:01:28

by Akhil P Oommen

[permalink] [raw]
Subject: [PATCH v2 3/3] dt-bindings: drm/msm/gpu: Add cooling device support

Add cooling device support to gpu. A cooling device is bound to a
thermal zone to allow thermal mitigation.

Signed-off-by: Akhil P Oommen <[email protected]>
---
Documentation/devicetree/bindings/display/msm/gpu.txt | 7 +++++++
1 file changed, 7 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt
index 1af0ff1..a496381 100644
--- a/Documentation/devicetree/bindings/display/msm/gpu.txt
+++ b/Documentation/devicetree/bindings/display/msm/gpu.txt
@@ -39,6 +39,10 @@ Required properties:
a4xx Snapdragon SoCs. See
Documentation/devicetree/bindings/sram/qcom,ocmem.yaml.

+Optional properties:
+- #cooling-cells: The value must be 2. Please refer
+ Documentation/devicetree/bindings/thermal/thermal.txt for detail.
+
Example 3xx/4xx:

/ {
@@ -61,6 +65,7 @@ Example 3xx/4xx:
power-domains = <&mmcc OXILICX_GDSC>;
operating-points-v2 = <&gpu_opp_table>;
iommus = <&gpu_iommu 0>;
+ #cooling-cells = <2>;
};

gpu_sram: ocmem@fdd00000 {
@@ -98,6 +103,8 @@ Example a6xx (with GMU):
reg = <0x5000000 0x40000>, <0x509e000 0x10>;
reg-names = "kgsl_3d0_reg_memory", "cx_mem";

+ #cooling-cells = <2>;
+
/*
* Look ma, no clocks! The GPU clocks and power are
* controlled entirely by the GMU
--
2.7.4

2020-10-26 17:33:31

by Rob Herring

[permalink] [raw]
Subject: Re: [PATCH v2 3/3] dt-bindings: drm/msm/gpu: Add cooling device support

On Mon, Oct 19, 2020 at 06:44:28PM +0530, Akhil P Oommen wrote:
> Add cooling device support to gpu. A cooling device is bound to a
> thermal zone to allow thermal mitigation.
>
> Signed-off-by: Akhil P Oommen <[email protected]>
> ---
> Documentation/devicetree/bindings/display/msm/gpu.txt | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt
> index 1af0ff1..a496381 100644
> --- a/Documentation/devicetree/bindings/display/msm/gpu.txt
> +++ b/Documentation/devicetree/bindings/display/msm/gpu.txt
> @@ -39,6 +39,10 @@ Required properties:
> a4xx Snapdragon SoCs. See
> Documentation/devicetree/bindings/sram/qcom,ocmem.yaml.
>
> +Optional properties:
> +- #cooling-cells: The value must be 2. Please refer
> + Documentation/devicetree/bindings/thermal/thermal.txt for detail.

This file doesn't exist anymore.

> +
> Example 3xx/4xx:
>
> / {
> @@ -61,6 +65,7 @@ Example 3xx/4xx:
> power-domains = <&mmcc OXILICX_GDSC>;
> operating-points-v2 = <&gpu_opp_table>;
> iommus = <&gpu_iommu 0>;
> + #cooling-cells = <2>;
> };
>
> gpu_sram: ocmem@fdd00000 {
> @@ -98,6 +103,8 @@ Example a6xx (with GMU):
> reg = <0x5000000 0x40000>, <0x509e000 0x10>;
> reg-names = "kgsl_3d0_reg_memory", "cx_mem";
>
> + #cooling-cells = <2>;
> +
> /*
> * Look ma, no clocks! The GPU clocks and power are
> * controlled entirely by the GMU
> --
> 2.7.4
>