drm/amdgpu/gfx8: move eop programming per queue

It's per queue not per pipe.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1371,7 +1371,7 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 
 	if (adev->gfx.mec.hpd_eop_obj == NULL) {
 		r = amdgpu_bo_create(adev,
-				     adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
+				     adev->gfx.mec.num_queue * MEC_HPD_SIZE,
 				     PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &adev->gfx.mec.hpd_eop_obj);
@@ -1400,7 +1400,7 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	memset(hpd, 0, adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2);
+	memset(hpd, 0, adev->gfx.mec.num_queue * MEC_HPD_SIZE);
 
 	amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
 	amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
@@ -4763,34 +4763,7 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
 	u32 *buf;
 	struct vi_mqd *mqd;
 
-	/* init the pipes */
-	mutex_lock(&adev->srbm_mutex);
-	for (i = 0; i < (adev->gfx.mec.num_pipe * adev->gfx.mec.num_mec); i++) {
-		int me = (i < 4) ? 1 : 2;
-		int pipe = (i < 4) ? i : (i - 4);
-
-		eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
-		eop_gpu_addr >>= 8;
-
-		vi_srbm_select(adev, me, pipe, 0, 0);
-
-		/* write the EOP addr */
-		WREG32(mmCP_HQD_EOP_BASE_ADDR, eop_gpu_addr);
-		WREG32(mmCP_HQD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr));
-
-		/* set the VMID assigned */
-		WREG32(mmCP_HQD_VMID, 0);
-
-		/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-		tmp = RREG32(mmCP_HQD_EOP_CONTROL);
-		tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
-				    (order_base_2(MEC_HPD_SIZE / 4) - 1));
-		WREG32(mmCP_HQD_EOP_CONTROL, tmp);
-	}
-	vi_srbm_select(adev, 0, 0, 0, 0);
-	mutex_unlock(&adev->srbm_mutex);
-
-	/* init the queues.  Just two for now. */
+	/* init the queues.  */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
@@ -4842,6 +4815,22 @@ static int gfx_v8_0_cp_compute_resume(struct amdgpu_device *adev)
 			       ring->pipe,
 			       ring->queue, 0);
 
+		eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+		eop_gpu_addr >>= 8;
+
+		/* write the EOP addr */
+		WREG32(mmCP_HQD_EOP_BASE_ADDR, eop_gpu_addr);
+		WREG32(mmCP_HQD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr));
+
+		/* set the VMID assigned */
+		WREG32(mmCP_HQD_VMID, 0);
+
+		/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
+		tmp = RREG32(mmCP_HQD_EOP_CONTROL);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
+				    (order_base_2(MEC_HPD_SIZE / 4) - 1));
+		WREG32(mmCP_HQD_EOP_CONTROL, tmp);
+
 		/* disable wptr polling */
 		tmp = RREG32(mmCP_PQ_WPTR_POLL_CNTL);
 		tmp = REG_SET_FIELD(tmp, CP_PQ_WPTR_POLL_CNTL, EN, 0);