1 files changed, 26 insertions, 55 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index ba228f613027..3a0b69b09ed6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1964,8 +1964,8 @@ static void gfx_v9_0_enable_gfx_pipeline_powergating(struct amdgpu_device *adev,
 		data = RREG32(SOC15_REG_OFFSET(GC, 0, mmDB_RENDER_CONTROL));
 }
 
-void gfx_v9_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
-						bool enable)
+static void gfx_v9_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
+						       bool enable)
 {
 	uint32_t data, default_data;
 
@@ -1978,7 +1978,7 @@ void gfx_v9_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_PG_CNTL), data);
 }
 
-void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev,
+static void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev,
 						bool enable)
 {
 	uint32_t data, default_data;
@@ -2502,56 +2502,6 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 	return r;
 }
 
-static int gfx_v9_0_kiq_kcq_disable(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
-	uint32_t scratch, tmp = 0;
-	int r, i;
-
-	r = amdgpu_gfx_scratch_get(adev, &scratch);
-	if (r) {
-		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
-		return r;
-	}
-	WREG32(scratch, 0xCAFEDEAD);
-
-	r = amdgpu_ring_alloc(kiq_ring, 6 + 3);
-	if (r) {
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-		amdgpu_gfx_scratch_free(adev, scratch);
-		return r;
-	}
-	/* unmap queues */
-	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
-	amdgpu_ring_write(kiq_ring,
-			  PACKET3_UNMAP_QUEUES_ACTION(1)| /* RESET_QUEUES */
-			  PACKET3_UNMAP_QUEUES_QUEUE_SEL(2)); /* select all queues */
-	amdgpu_ring_write(kiq_ring, 0);
-	amdgpu_ring_write(kiq_ring, 0);
-	amdgpu_ring_write(kiq_ring, 0);
-	amdgpu_ring_write(kiq_ring, 0);
-	/* write to scratch for completion */
-	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
-	amdgpu_ring_write(kiq_ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
-	amdgpu_ring_write(kiq_ring, 0xDEADBEEF);
-	amdgpu_ring_commit(kiq_ring);
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(scratch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i >= adev->usec_timeout) {
-		DRM_ERROR("KCQ disable failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
-		r = -EINVAL;
-	}
-	amdgpu_gfx_scratch_free(adev, scratch);
-
-	return r;
-}
-
 static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -2996,7 +2946,6 @@ static int gfx_v9_0_hw_fini(void *handle)
 		pr_debug("For SRIOV client, shouldn't do anything.\n");
 		return 0;
 	}
-	gfx_v9_0_kiq_kcq_disable(adev);
 	gfx_v9_0_cp_enable(adev, false);
 	gfx_v9_0_rlc_stop(adev);
 
@@ -4416,6 +4365,20 @@ static void gfx_v9_0_set_gds_init(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v9_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
+						 u32 bitmap)
+{
+	u32 data;
+
+	if (!bitmap)
+		return;
+
+	data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
+	data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
+
+	WREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG, data);
+}
+
 static u32 gfx_v9_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 {
 	u32 data, mask;
@@ -4436,10 +4399,13 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 {
 	int i, j, k, counter, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
+	unsigned disable_masks[4 * 2];
 
 	if (!adev || !cu_info)
 		return -EINVAL;
 
+	amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2);
+
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
@@ -4447,6 +4413,9 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 			ao_bitmap = 0;
 			counter = 0;
 			gfx_v9_0_select_se_sh(adev, i, j, 0xffffffff);
+			if (i < 4 && j < 2)
+				gfx_v9_0_set_user_cu_inactive_bitmap(
+					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v9_0_get_cu_active_bitmap(adev);
 			cu_info->bitmap[i][j] = bitmap;
 
@@ -4459,7 +4428,9 @@ static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev,
 				mask <<= 1;
 			}
 			active_cu_number += counter;
-			ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
+			if (i < 2 && j < 2)
+				ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
+			cu_info->ao_cu_bitmap[i][j] = ao_bitmap;
 		}
 	}
 	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);