drm/amdgpu: fetch cu_info once at init

Fetch this info once at init and just store the results
for future requests.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1148,6 +1148,12 @@ struct amdgpu_gca_config {
 	uint32_t macrotile_mode_array[16];
 };
 
+struct amdgpu_cu_info {
+	uint32_t number; /* total active CU number */
+	uint32_t ao_cu_mask;
+	uint32_t bitmap[4][4];
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gca_config	config;
@@ -1183,6 +1189,7 @@ struct amdgpu_gfx {
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
 	unsigned			ce_ram_size;
+	struct amdgpu_cu_info		cu_info;
 };
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -1794,13 +1801,6 @@ struct amdgpu_allowed_register_entry {
 	bool grbm_indexed;
 };
 
-struct amdgpu_cu_info {
-	uint32_t number; /* total active CU number */
-	uint32_t ao_cu_mask;
-	uint32_t bitmap[4][4];
-};
-
-
 /*
  * ASIC specific functions.
  */
@@ -1818,7 +1818,6 @@ struct amdgpu_asic_funcs {
 	u32 (*get_xclk)(struct amdgpu_device *adev);
 	/* get the gpu clock counter */
 	uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev);
-	int (*get_cu_info)(struct amdgpu_device *adev, struct amdgpu_cu_info *info);
 	/* MM block clocks */
 	int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
 	int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
@@ -2210,7 +2209,6 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
 #define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v)))
-#define amdgpu_asic_get_cu_info(adev, info) (adev)->asic_funcs->get_cu_info((adev), (info))
 #define amdgpu_gart_flush_gpu_tlb(adev, vmid) (adev)->gart.gart_funcs->flush_gpu_tlb((adev), (vmid))
 #define amdgpu_gart_set_pte_pde(adev, pt, idx, addr, flags) (adev)->gart.gart_funcs->set_pte_pde((adev), (pt), (idx), (addr), (flags))
 #define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count)))

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

@@ -793,7 +793,6 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 				struct cgs_system_info *sys_info)
 {
 	CGS_FUNC_ADEV;
-	struct amdgpu_cu_info cu_info;
 
 	if (NULL == sys_info)
 		return -ENODEV;
@@ -818,8 +817,7 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 		sys_info->value = adev->pg_flags;
 		break;
 	case CGS_SYSTEM_INFO_GFX_CU_INFO:
-		amdgpu_asic_get_cu_info(adev, &cu_info);
-		sys_info->value = cu_info.number;
+		sys_info->value = adev->gfx.cu_info.number;
 		break;
 	default:
 		return -ENODEV;

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

@@ -427,7 +427,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	}
 	case AMDGPU_INFO_DEV_INFO: {
 		struct drm_amdgpu_info_device dev_info = {};
-		struct amdgpu_cu_info cu_info;
 
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
@@ -461,11 +460,11 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 					     AMDGPU_GPU_PAGE_SIZE;
 		dev_info.gart_page_size = AMDGPU_GPU_PAGE_SIZE;
 
-		amdgpu_asic_get_cu_info(adev, &cu_info);
-		dev_info.cu_active_number = cu_info.number;
-		dev_info.cu_ao_mask = cu_info.ao_cu_mask;
+		dev_info.cu_active_number = adev->gfx.cu_info.number;
+		dev_info.cu_ao_mask = adev->gfx.cu_info.ao_cu_mask;
 		dev_info.ce_ram_size = adev->gfx.ce_ram_size;
-		memcpy(&dev_info.cu_bitmap[0], &cu_info.bitmap[0], sizeof(cu_info.bitmap));
+		memcpy(&dev_info.cu_bitmap[0], &adev->gfx.cu_info.bitmap[0],
+		       sizeof(adev->gfx.cu_info.bitmap));
 		dev_info.vram_type = adev->mc.vram_type;
 		dev_info.vram_bit_width = adev->mc.vram_width;
 		dev_info.vce_harvest_config = adev->vce.harvest_config;

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

@@ -2007,7 +2007,6 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_xclk = &cik_get_xclk,
 	.set_uvd_clocks = &cik_set_uvd_clocks,
 	.set_vce_clocks = &cik_set_vce_clocks,
-	.get_cu_info = &gfx_v7_0_get_cu_info,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -53,7 +53,6 @@
 static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
-int gfx_v7_0_get_cu_info(struct amdgpu_device *, struct amdgpu_cu_info *);
 
 MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
 MODULE_FIRMWARE("radeon/bonaire_me.bin");
@@ -882,6 +881,7 @@ static u32 gfx_v7_0_get_csb_size(struct amdgpu_device *adev);
 static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer);
 static void gfx_v7_0_init_cp_pg_table(struct amdgpu_device *adev);
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev);
+static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev);
 
 /*
  * Core functions
@@ -1718,6 +1718,7 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
 	gfx_v7_0_tiling_mode_table_init(adev);
 
 	gfx_v7_0_setup_rb(adev);
+	gfx_v7_0_get_cu_info(adev);
 
 	/* set HW defaults for 3D engine */
 	WREG32(mmCP_MEQ_THRESHOLDS,
@@ -3869,18 +3870,13 @@ static u32 gfx_v7_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 
 static void gfx_v7_0_init_ao_cu_mask(struct amdgpu_device *adev)
 {
-	uint32_t tmp, active_cu_number;
-	struct amdgpu_cu_info cu_info;
-
-	gfx_v7_0_get_cu_info(adev, &cu_info);
-	tmp = cu_info.ao_cu_mask;
-	active_cu_number = cu_info.number;
+	u32 tmp;
 
-	WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, tmp);
+	WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
 
 	tmp = RREG32(mmRLC_MAX_PG_CU);
 	tmp &= ~RLC_MAX_PG_CU__MAX_POWERED_UP_CU_MASK;
-	tmp |= (active_cu_number << RLC_MAX_PG_CU__MAX_POWERED_UP_CU__SHIFT);
+	tmp |= (adev->gfx.cu_info.number << RLC_MAX_PG_CU__MAX_POWERED_UP_CU__SHIFT);
 	WREG32(mmRLC_MAX_PG_CU, tmp);
 }
 
@@ -5015,14 +5011,11 @@ static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev)
 }
 
 
-int gfx_v7_0_get_cu_info(struct amdgpu_device *adev,
-			 struct amdgpu_cu_info *cu_info)
+static void gfx_v7_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;
-
-	if (!adev || !cu_info)
-		return -EINVAL;
+	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
@@ -5053,6 +5046,4 @@ int gfx_v7_0_get_cu_info(struct amdgpu_device *adev,
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
-
-	return 0;
 }

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h

@@ -32,6 +32,5 @@ void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev);
 void gfx_v7_0_rlc_stop(struct amdgpu_device *adev);
 uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-int gfx_v7_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info);
 
 #endif

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

@@ -636,6 +636,7 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev);
 static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev);
 static u32 gfx_v8_0_get_csb_size(struct amdgpu_device *adev);
+static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev);
 
 static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 {
@@ -3431,6 +3432,7 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 	gfx_v8_0_tiling_mode_table_init(adev);
 
 	gfx_v8_0_setup_rb(adev);
+	gfx_v8_0_get_cu_info(adev);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
@@ -6212,14 +6214,11 @@ static u32 gfx_v8_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 	return (~data) & mask;
 }
 
-int gfx_v8_0_get_cu_info(struct amdgpu_device *adev,
-			 struct amdgpu_cu_info *cu_info)
+static void gfx_v8_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;
-
-	if (!adev || !cu_info)
-		return -EINVAL;
+	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
@@ -6250,6 +6249,4 @@ int gfx_v8_0_get_cu_info(struct amdgpu_device *adev,
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
-
-	return 0;
 }

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

@@ -28,6 +28,5 @@ extern const struct amd_ip_funcs gfx_v8_0_ip_funcs;
 
 uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-int gfx_v8_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info);
 
 #endif

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

@@ -1118,7 +1118,6 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_xclk = &vi_get_xclk,
 	.set_uvd_clocks = &vi_set_uvd_clocks,
 	.set_vce_clocks = &vi_set_vce_clocks,
-	.get_cu_info = &gfx_v8_0_get_cu_info,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,