summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c127
1 files changed, 99 insertions, 28 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ff70bc233489..bcc9343353b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -157,6 +157,8 @@ static int hw_id_map[MAX_HWIP] = {
[HDP_HWIP] = HDP_HWID,
[SDMA0_HWIP] = SDMA0_HWID,
[SDMA1_HWIP] = SDMA1_HWID,
+ [SDMA2_HWIP] = SDMA2_HWID,
+ [SDMA3_HWIP] = SDMA3_HWID,
[MMHUB_HWIP] = MMHUB_HWID,
[ATHUB_HWIP] = ATHUB_HWID,
[NBIO_HWIP] = NBIF_HWID,
@@ -248,8 +250,8 @@ get_from_vram:
offset = offsetof(struct binary_header, binary_checksum) +
sizeof(bhdr->binary_checksum);
- size = bhdr->binary_size - offset;
- checksum = bhdr->binary_checksum;
+ size = le16_to_cpu(bhdr->binary_size) - offset;
+ checksum = le16_to_cpu(bhdr->binary_checksum);
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
size, checksum)) {
@@ -270,7 +272,7 @@ get_from_vram:
}
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
- ihdr->size, checksum)) {
+ le16_to_cpu(ihdr->size), checksum)) {
DRM_ERROR("invalid ip discovery data table checksum\n");
r = -EINVAL;
goto out;
@@ -282,7 +284,7 @@ get_from_vram:
ghdr = (struct gpu_info_header *)(adev->mman.discovery_bin + offset);
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
- ghdr->size, checksum)) {
+ le32_to_cpu(ghdr->size), checksum)) {
DRM_ERROR("invalid gc data table checksum\n");
r = -EINVAL;
goto out;
@@ -489,10 +491,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset));
for (i = 0; i < 32; i++) {
- if (le32_to_cpu(harvest_info->list[i].hw_id) == 0)
+ if (le16_to_cpu(harvest_info->list[i].hw_id) == 0)
break;
- switch (le32_to_cpu(harvest_info->list[i].hw_id)) {
+ switch (le16_to_cpu(harvest_info->list[i].hw_id)) {
case VCN_HWID:
vcn_harvest_count++;
if (harvest_info->list[i].number_instance == 0)
@@ -524,10 +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");
@@ -535,28 +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;
}
@@ -587,6 +621,9 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add common ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -619,6 +656,9 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gmc ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -648,6 +688,9 @@ static int amdgpu_discovery_set_ih_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add ih ip block(OSSSYS_HWIP:0x%x)\n",
+ adev->ip_versions[OSSSYS_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -688,6 +731,9 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add psp ip block(MP0_HWIP:0x%x)\n",
+ adev->ip_versions[MP0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -726,6 +772,9 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add smu ip block(MP1_HWIP:0x%x)\n",
+ adev->ip_versions[MP1_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -753,6 +802,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCE_HWIP:0x%x)\n",
+ adev->ip_versions[DCE_HWIP][0]);
return -EINVAL;
}
} else if (adev->ip_versions[DCI_HWIP][0]) {
@@ -763,6 +815,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &dm_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add dm ip block(DCI_HWIP:0x%x)\n",
+ adev->ip_versions[DCI_HWIP][0]);
return -EINVAL;
}
#endif
@@ -796,6 +851,9 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add gfx ip block(GC_HWIP:0x%x)\n",
+ adev->ip_versions[GC_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -829,6 +887,9 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add sdma ip block(SDMA0_HWIP:0x%x)\n",
+ adev->ip_versions[SDMA0_HWIP][0]);
return -EINVAL;
}
return 0;
@@ -845,6 +906,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add uvd v7 ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
switch (adev->ip_versions[VCE_HWIP][0]) {
@@ -855,6 +919,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add VCE v4 ip block(VCE_HWIP:0x%x)\n",
+ adev->ip_versions[VCE_HWIP][0]);
return -EINVAL;
}
} else {
@@ -885,6 +952,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
case IP_VERSION(3, 0, 64):
case IP_VERSION(3, 1, 1):
case IP_VERSION(3, 0, 2):
+ case IP_VERSION(3, 0, 192):
amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
if (!amdgpu_sriov_vf(adev))
amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
@@ -893,6 +961,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
break;
default:
+ dev_err(adev->dev,
+ "Failed to add vcn/jpeg ip block(UVD_HWIP:0x%x)\n",
+ adev->ip_versions[UVD_HWIP][0]);
return -EINVAL;
}
}
generated by cgit (git 2.34.1) at 2024-04-24 23:26:21 +0000