[PATCH v8 11/12] drm/msm/a6xx: Enable preemption for tested a7xx targets

[Antonino Maniscalco <antomani103@gmail.com>]

Initialize with 4 rings to enable preemption.

Add the "preemption_enabled" module parameter to override this.

Tested-by: Rob Clark <robdclark@gmail.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8550-QRD
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8450-HDK
Signed-off-by: Antonino Maniscalco <antomani103@gmail.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_catalog.c  | 12 ++++++++----
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c      |  6 +++++-
 drivers/gpu/drm/msm/adreno/adreno_device.c |  4 ++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.h    |  1 +
 drivers/gpu/drm/msm/msm_submitqueue.c      |  6 +++++-
 5 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
index e4d271fa89cc66f188be04206e267fabd83cca83..1c8b31627eb68bff406e70995838e418331449ef 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
@@ -1204,7 +1204,8 @@ static const struct adreno_info a7xx_gpus[] = {
 		.gmem = SZ_2M,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
-			  ADRENO_QUIRK_HAS_HW_APRIV,
+			  ADRENO_QUIRK_HAS_HW_APRIV |
+			  ADRENO_QUIRK_PREEMPTION,
 		.init = a6xx_gpu_init,
 		.zapfw = "a730_zap.mdt",
 		.a6xx = &(const struct a6xx_info) {
@@ -1224,7 +1225,8 @@ static const struct adreno_info a7xx_gpus[] = {
 		.gmem = 3 * SZ_1M,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
-			  ADRENO_QUIRK_HAS_HW_APRIV,
+			  ADRENO_QUIRK_HAS_HW_APRIV |
+			  ADRENO_QUIRK_PREEMPTION,
 		.init = a6xx_gpu_init,
 		.zapfw = "a740_zap.mdt",
 		.a6xx = &(const struct a6xx_info) {
@@ -1245,7 +1247,8 @@ static const struct adreno_info a7xx_gpus[] = {
 		.gmem = 3 * SZ_1M,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
-			  ADRENO_QUIRK_HAS_HW_APRIV,
+			  ADRENO_QUIRK_HAS_HW_APRIV |
+			  ADRENO_QUIRK_PREEMPTION,
 		.init = a6xx_gpu_init,
 		.a6xx = &(const struct a6xx_info) {
 			.hwcg = a740_hwcg,
@@ -1265,7 +1268,8 @@ static const struct adreno_info a7xx_gpus[] = {
 		.gmem = 3 * SZ_1M,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT |
-			  ADRENO_QUIRK_HAS_HW_APRIV,
+			  ADRENO_QUIRK_HAS_HW_APRIV |
+			  ADRENO_QUIRK_PREEMPTION,
 		.init = a6xx_gpu_init,
 		.zapfw = "gen70900_zap.mbn",
 		.a6xx = &(const struct a6xx_info) {
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 2f7c93e74e097a78510700d2c6607d052cbdda66..dca9d011f09e741784ac6dc31b61841149acbae2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -2439,6 +2439,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	struct a6xx_gpu *a6xx_gpu;
 	struct adreno_gpu *adreno_gpu;
 	struct msm_gpu *gpu;
+	extern int enable_preemption;
 	bool is_a7xx;
 	int ret;
 
@@ -2477,7 +2478,10 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 		return ERR_PTR(ret);
 	}
 
-	if (is_a7xx)
+	if ((enable_preemption == 1) || (enable_preemption == -1 &&
+	    (config->info->quirks & ADRENO_QUIRK_PREEMPTION)))
+		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 4);
+	else if (is_a7xx)
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 1);
 	else if (adreno_has_gmu_wrapper(adreno_gpu))
 		ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index cfc74a9e2646d3de76a06bd67457d69afa49e309..9ffe91920fbfb4841b28aabec9fbde94539fdd83 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -20,6 +20,10 @@ bool allow_vram_carveout = false;
 MODULE_PARM_DESC(allow_vram_carveout, "Allow using VRAM Carveout, in place of IOMMU");
 module_param_named(allow_vram_carveout, allow_vram_carveout, bool, 0600);
 
+int enable_preemption = -1;
+MODULE_PARM_DESC(enable_preemption, "Enable preemption (A7xx only) (1=on , 0=disable, -1=auto (default))");
+module_param(enable_preemption, int, 0600);
+
 extern const struct adreno_gpulist a2xx_gpulist;
 extern const struct adreno_gpulist a3xx_gpulist;
 extern const struct adreno_gpulist a4xx_gpulist;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 2d8eef6c668b0da246edceba0c5d92041ea9a35b..30c6b949d0b197fea130c9b2b69c9362c1527737 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -56,6 +56,7 @@ enum adreno_family {
 #define ADRENO_QUIRK_LMLOADKILL_DISABLE		BIT(2)
 #define ADRENO_QUIRK_HAS_HW_APRIV		BIT(3)
 #define ADRENO_QUIRK_HAS_CACHED_COHERENT	BIT(4)
+#define ADRENO_QUIRK_PREEMPTION			BIT(5)
 
 /* Helper for formating the chip_id in the way that userspace tools like
  * crashdec expect.
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 9b3ffca3f3b471f509918edd4a2fdb0f80dfeb06..2fc3eaf81f4461990d48065f67bf5477787708e9 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -161,6 +161,8 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
 	enum drm_sched_priority sched_prio;
+	extern int enable_preemption;
+	bool preemption_supported;
 	unsigned ring_nr;
 	int ret;
 
@@ -170,7 +172,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (!priv->gpu)
 		return -ENODEV;
 
-	if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && priv->gpu->nr_rings == 1)
+	preemption_supported = priv->gpu->nr_rings == 1 && enable_preemption != 0;
+
+	if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && preemption_supported)
 		return -EINVAL;
 
 	ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio);

-- 
2.46.1