Commit 5e713c6a authored by Alex Deucher's avatar Alex Deucher
Browse files

drm/amdgpu: add support for IP discovery gc_info table v2

Used on gfx9 based systems. Fixes incorrect CU counts reported
in the kernel log.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1833


Reviewed-by: default avatarHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
parent b7865173
Loading
Loading
Loading
Loading
+54 −22
Original line number Diff line number Diff line
@@ -526,10 +526,15 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
	}
}

union gc_info {
	struct gc_info_v1_0 v1;
	struct gc_info_v2_0 v2;
};

int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
{
	struct binary_header *bhdr;
	struct gc_info_v1_0 *gc_info;
	union gc_info *gc_info;

	if (!adev->mman.discovery_bin) {
		DRM_ERROR("ip discovery uninitialized\n");
@@ -537,28 +542,55 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
	}

	bhdr = (struct binary_header *)adev->mman.discovery_bin;
	gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
	gc_info = (union gc_info *)(adev->mman.discovery_bin +
			le16_to_cpu(bhdr->table_list[GC].offset));

	adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
	adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
					      le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
	adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
	adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
	adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
	adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
	adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
	adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
	adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
	adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
	adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
	adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
	adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
	adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
	adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
					 le32_to_cpu(gc_info->gc_num_sa_per_se);
	adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);

	switch (gc_info->v1.header.version_major) {
	case 1:
		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se);
		adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) +
						      le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa));
		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se);
		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c);
		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs);
		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds);
		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth);
		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth);
		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer);
		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size);
		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd);
		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu);
		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size);
		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) /
			le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc);
		break;
	case 2:
		adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
		adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh);
		adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
		adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se);
		adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs);
		adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs);
		adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds);
		adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth);
		adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth);
		adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer);
		adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size);
		adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd);
		adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu);
		adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size);
		adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
			le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
		adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
		break;
	default:
		dev_err(adev->dev,
			"Unhandled GC info table %d.%d\n",
			gc_info->v1.header.version_major,
			gc_info->v1.header.version_minor);
		return -EINVAL;
	}
	return 0;
}

+49 −0
Original line number Diff line number Diff line
@@ -143,6 +143,55 @@ struct gc_info_v1_0 {
	uint32_t gc_num_gl2a;
};

struct gc_info_v1_1 {
	struct gpu_info_header header;

	uint32_t gc_num_se;
	uint32_t gc_num_wgp0_per_sa;
	uint32_t gc_num_wgp1_per_sa;
	uint32_t gc_num_rb_per_se;
	uint32_t gc_num_gl2c;
	uint32_t gc_num_gprs;
	uint32_t gc_num_max_gs_thds;
	uint32_t gc_gs_table_depth;
	uint32_t gc_gsprim_buff_depth;
	uint32_t gc_parameter_cache_depth;
	uint32_t gc_double_offchip_lds_buffer;
	uint32_t gc_wave_size;
	uint32_t gc_max_waves_per_simd;
	uint32_t gc_max_scratch_slots_per_cu;
	uint32_t gc_lds_size;
	uint32_t gc_num_sc_per_se;
	uint32_t gc_num_sa_per_se;
	uint32_t gc_num_packer_per_sc;
	uint32_t gc_num_gl2a;
	uint32_t gc_num_tcp_per_sa;
	uint32_t gc_num_sdp_interface;
	uint32_t gc_num_tcps;
};

struct gc_info_v2_0 {
	struct gpu_info_header header;

	uint32_t gc_num_se;
	uint32_t gc_num_cu_per_sh;
	uint32_t gc_num_sh_per_se;
	uint32_t gc_num_rb_per_se;
	uint32_t gc_num_tccs;
	uint32_t gc_num_gprs;
	uint32_t gc_num_max_gs_thds;
	uint32_t gc_gs_table_depth;
	uint32_t gc_gsprim_buff_depth;
	uint32_t gc_parameter_cache_depth;
	uint32_t gc_double_offchip_lds_buffer;
	uint32_t gc_wave_size;
	uint32_t gc_max_waves_per_simd;
	uint32_t gc_max_scratch_slots_per_cu;
	uint32_t gc_lds_size;
	uint32_t gc_num_sc_per_se;
	uint32_t gc_num_packer_per_sc;
};

typedef struct harvest_info_header {
	uint32_t signature; /* Table Signature */
	uint32_t version;   /* Table Version */