drm/panfrost: Expose the selected coherency protocol to the UMD

Will be needed if we want to skip CPU cache maintenance operations when
the GPU can snoop CPU caches.

v2:
- New commit

v3:
- Fix the coherency values (enum instead of bitmask)

v4:
- Fix init/test on coherency_features

v5:
- No changes

v6:
- Collect R-b

v7:
- No changes

v8:
- No changes

Reviewed-by: Steven Price <steven.price@arm.com>
Link: https://patch.msgid.link/20251208100841.730527-10-boris.brezillon@collabora.com
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>

5 files changed, 40 insertions, 5 deletions

diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index e61c4329fd07..0f3992412205 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -79,6 +79,7 @@ struct panfrost_features {
 	u32 thread_max_workgroup_sz;
 	u32 thread_max_barrier_sz;
 	u32 coherency_features;
+	u32 selected_coherency;
 	u32 afbc_features;
 	u32 texture_features[4];
 	u32 js_features[16];
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 199073cc7d3f..b2c3f6c81be0 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -95,6 +95,7 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct
 		PANFROST_FEATURE_ARRAY(JS_FEATURES, js_features, 15);
 		PANFROST_FEATURE(NR_CORE_GROUPS, nr_core_groups);
 		PANFROST_FEATURE(THREAD_TLS_ALLOC, thread_tls_alloc);
+		PANFROST_FEATURE(SELECTED_COHERENCY, selected_coherency);
 
 	case DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP:
 		ret = panfrost_ioctl_query_timestamp(pfdev, &param->value);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 483d278eb154..7d555e63e21a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -159,8 +159,8 @@ static void panfrost_gpu_init_quirks(struct panfrost_device *pfdev)
 	    pfdev->features.revision >= 0x2000)
 		quirks |= JM_MAX_JOB_THROTTLE_LIMIT << JM_JOB_THROTTLE_LIMIT_SHIFT;
 	else if (panfrost_model_eq(pfdev, 0x6000) &&
-		 pfdev->features.coherency_features == COHERENCY_ACE)
-		quirks |= (COHERENCY_ACE_LITE | COHERENCY_ACE) <<
+		 pfdev->features.coherency_features == BIT(COHERENCY_ACE))
+		quirks |= (BIT(COHERENCY_ACE_LITE) | BIT(COHERENCY_ACE)) <<
 			   JM_FORCE_COHERENCY_FEATURES_SHIFT;
 
 	if (panfrost_has_hw_feature(pfdev, HW_FEATURE_IDVS_GROUP_SIZE))
@@ -263,7 +263,27 @@ static int panfrost_gpu_init_features(struct panfrost_device *pfdev)
 	pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
 	pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
 	pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
-	pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
+
+	if (panfrost_has_hw_feature(pfdev, HW_FEATURE_COHERENCY_REG))
+		pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
+	else
+		pfdev->features.coherency_features = BIT(COHERENCY_ACE_LITE);
+
+	BUILD_BUG_ON(COHERENCY_ACE_LITE != DRM_PANFROST_GPU_COHERENCY_ACE_LITE);
+	BUILD_BUG_ON(COHERENCY_ACE != DRM_PANFROST_GPU_COHERENCY_ACE);
+	BUILD_BUG_ON(COHERENCY_NONE != DRM_PANFROST_GPU_COHERENCY_NONE);
+
+	if (!pfdev->coherent) {
+		pfdev->features.selected_coherency = COHERENCY_NONE;
+	} else if (pfdev->features.coherency_features & BIT(COHERENCY_ACE)) {
+		pfdev->features.selected_coherency = COHERENCY_ACE;
+	} else if (pfdev->features.coherency_features & BIT(COHERENCY_ACE_LITE)) {
+		pfdev->features.selected_coherency = COHERENCY_ACE_LITE;
+	} else {
+		drm_WARN(&pfdev->base, true, "No known coherency protocol supported");
+		pfdev->features.selected_coherency = COHERENCY_NONE;
+	}
+
 	pfdev->features.afbc_features = gpu_read(pfdev, GPU_AFBC_FEATURES);
 	for (i = 0; i < 4; i++)
 		pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index 2b8f1617b836..ee15f6bf6e6f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -102,9 +102,15 @@
 #define GPU_L2_PRESENT_LO		0x120	/* (RO) Level 2 cache present bitmap, low word */
 #define GPU_L2_PRESENT_HI		0x124	/* (RO) Level 2 cache present bitmap, high word */
 
+/* GPU_COHERENCY_FEATURES is a bitmask of BIT(COHERENCY_xxx) values encoding the
+ * set of supported coherency protocols. GPU_COHERENCY_ENABLE is passed a
+ * COHERENCY_xxx value.
+ */
 #define GPU_COHERENCY_FEATURES		0x300	/* (RO) Coherency features present */
-#define   COHERENCY_ACE_LITE		BIT(0)
-#define   COHERENCY_ACE			BIT(1)
+#define GPU_COHERENCY_ENABLE		0x304	/* (RW) Coherency protocol selection */
+#define   COHERENCY_ACE_LITE		0
+#define   COHERENCY_ACE			1
+#define   COHERENCY_NONE		31
 
 #define GPU_STACK_PRESENT_LO		0xE00   /* (RO) Core stack present bitmap, low word */
 #define GPU_STACK_PRESENT_HI		0xE04   /* (RO) Core stack present bitmap, high word */
diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h
index 1956431bb391..0c59714ae42b 100644
--- a/include/uapi/drm/panfrost_drm.h
+++ b/include/uapi/drm/panfrost_drm.h
@@ -228,6 +228,13 @@ enum drm_panfrost_param {
 	DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP,
 	DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP_FREQUENCY,
 	DRM_PANFROST_PARAM_ALLOWED_JM_CTX_PRIORITIES,
+	DRM_PANFROST_PARAM_SELECTED_COHERENCY,
+};
+
+enum drm_panfrost_gpu_coherency {
+	DRM_PANFROST_GPU_COHERENCY_ACE_LITE = 0,
+	DRM_PANFROST_GPU_COHERENCY_ACE = 1,
+	DRM_PANFROST_GPU_COHERENCY_NONE = 31,
 };
 
 struct drm_panfrost_get_param {