drm/amdgpu: remove hardcoded queue_mask in PACKET3_SET_RESOURCES

The assumption that we are only using the first pipe no longer holds.
Instead, calculate the queue_mask from the queue_bitmap.

Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Andres Rodriguez <andresx7@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -4734,8 +4734,24 @@ static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
 	uint32_t scratch, tmp = 0;
+	uint64_t queue_mask = 0;
 	int r, i;
 
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << i);
+	}
+
 	r = amdgpu_gfx_scratch_get(adev, &scratch);
 	if (r) {
 		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
@@ -4752,8 +4768,8 @@ static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev)
 	/* set resources */
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
 	amdgpu_ring_write(kiq_ring, 0);	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(kiq_ring, 0x000000FF);	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
-	amdgpu_ring_write(kiq_ring, 0);	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -2608,8 +2608,24 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
 	uint32_t scratch, tmp = 0;
+	uint64_t queue_mask = 0;
 	int r, i;
 
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << i);
+	}
+
 	r = amdgpu_gfx_scratch_get(adev, &scratch);
 	if (r) {
 		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
@@ -2628,8 +2644,8 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
 	amdgpu_ring_write(kiq_ring, PACKET3_SET_RESOURCES_VMID_MASK(0) |
 			  PACKET3_SET_RESOURCES_QUEUE_TYPE(0));	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(kiq_ring, 0x000000FF);	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
-	amdgpu_ring_write(kiq_ring, 0);	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
 	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
 	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */