aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c237
1 files changed, 173 insertions, 64 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ff70bc233489..028190d42bb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -67,7 +67,8 @@
#include "smuio_v11_0_6.h"
#include "smuio_v13_0.h"
-MODULE_FIRMWARE("amdgpu/ip_discovery.bin");
+#define FIRMWARE_IP_DISCOVERY "amdgpu/ip_discovery.bin"
+MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY);
#define mmRCC_CONFIG_MEMSIZE 0xde3
#define mmMM_INDEX 0x0
@@ -157,6 +158,8 @@ 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,
@@ -177,7 +180,7 @@ static int hw_id_map[MAX_HWIP] = {
[DCI_HWIP] = DCI_HWID,
};
-static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *binary)
+static int amdgpu_discovery_read_binary_from_vram(struct amdgpu_device *adev, uint8_t *binary)
{
uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET;
@@ -187,6 +190,34 @@ static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *bin
return 0;
}
+static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev, uint8_t *binary)
+{
+ const struct firmware *fw;
+ const char *fw_name;
+ int r;
+
+ switch (amdgpu_discovery) {
+ case 2:
+ fw_name = FIRMWARE_IP_DISCOVERY;
+ break;
+ default:
+ dev_warn(adev->dev, "amdgpu_discovery is not set properly\n");
+ return -EINVAL;
+ }
+
+ r = request_firmware(&fw, fw_name, adev->dev);
+ if (r) {
+ dev_err(adev->dev, "can't load firmware \"%s\"\n",
+ fw_name);
+ return r;
+ }
+
+ memcpy((u8 *)binary, (u8 *)fw->data, adev->mman.discovery_tmr_size);
+ release_firmware(fw);
+
+ return 0;
+}
+
static uint16_t amdgpu_discovery_calculate_checksum(uint8_t *data, uint32_t size)
{
uint16_t checksum = 0;
@@ -204,13 +235,20 @@ static inline bool amdgpu_discovery_verify_checksum(uint8_t *data, uint32_t size
return !!(amdgpu_discovery_calculate_checksum(data, size) == expected);
}
+static inline bool amdgpu_discovery_verify_binary_signature(uint8_t *binary)
+{
+ struct binary_header *bhdr;
+ bhdr = (struct binary_header *)binary;
+
+ return (le32_to_cpu(bhdr->binary_signature) == BINARY_SIGNATURE);
+}
+
static int amdgpu_discovery_init(struct amdgpu_device *adev)
{
struct table_info *info;
struct binary_header *bhdr;
struct ip_discovery_header *ihdr;
struct gpu_info_header *ghdr;
- const struct firmware *fw;
uint16_t offset;
uint16_t size;
uint16_t checksum;
@@ -221,39 +259,40 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
if (!adev->mman.discovery_bin)
return -ENOMEM;
- if (amdgpu_discovery == 2) {
- r = request_firmware(&fw, "amdgpu/ip_discovery.bin", adev->dev);
- if (r)
- goto get_from_vram;
- dev_info(adev->dev, "Using IP discovery from file\n");
- memcpy((u8 *)adev->mman.discovery_bin, (u8 *)fw->data,
- adev->mman.discovery_tmr_size);
- release_firmware(fw);
- } else {
-get_from_vram:
- r = amdgpu_discovery_read_binary(adev, adev->mman.discovery_bin);
+ r = amdgpu_discovery_read_binary_from_vram(adev, adev->mman.discovery_bin);
+ if (r) {
+ dev_err(adev->dev, "failed to read ip discovery binary from vram\n");
+ r = -EINVAL;
+ goto out;
+ }
+
+ if(!amdgpu_discovery_verify_binary_signature(adev->mman.discovery_bin)) {
+ dev_warn(adev->dev, "get invalid ip discovery binary signature from vram\n");
+ /* retry read ip discovery binary from file */
+ r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin);
if (r) {
- DRM_ERROR("failed to read ip discovery binary\n");
+ dev_err(adev->dev, "failed to read ip discovery binary from file\n");
+ r = -EINVAL;
+ goto out;
+ }
+ /* check the ip discovery binary signature */
+ if(!amdgpu_discovery_verify_binary_signature(adev->mman.discovery_bin)) {
+ dev_warn(adev->dev, "get invalid ip discovery binary signature from file\n");
+ r = -EINVAL;
goto out;
}
}
bhdr = (struct binary_header *)adev->mman.discovery_bin;
- if (le32_to_cpu(bhdr->binary_signature) != BINARY_SIGNATURE) {
- DRM_ERROR("invalid ip discovery binary signature\n");
- r = -EINVAL;
- goto out;
- }
-
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)) {
- DRM_ERROR("invalid ip discovery binary checksum\n");
+ dev_err(adev->dev, "invalid ip discovery binary checksum\n");
r = -EINVAL;
goto out;
}
@@ -264,14 +303,14 @@ get_from_vram:
ihdr = (struct ip_discovery_header *)(adev->mman.discovery_bin + offset);
if (le32_to_cpu(ihdr->signature) != DISCOVERY_TABLE_SIGNATURE) {
- DRM_ERROR("invalid ip discovery data table signature\n");
+ dev_err(adev->dev, "invalid ip discovery data table signature\n");
r = -EINVAL;
goto out;
}
if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
- ihdr->size, checksum)) {
- DRM_ERROR("invalid ip discovery data table checksum\n");
+ le16_to_cpu(ihdr->size), checksum)) {
+ dev_err(adev->dev, "invalid ip discovery data table checksum\n");
r = -EINVAL;
goto out;
}
@@ -282,8 +321,8 @@ 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)) {
- DRM_ERROR("invalid gc data table checksum\n");
+ le32_to_cpu(ghdr->size), checksum)) {
+ dev_err(adev->dev, "invalid gc data table checksum\n");
r = -EINVAL;
goto out;
}
@@ -377,8 +416,18 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
ip->major, ip->minor,
ip->revision);
- if (le16_to_cpu(ip->hw_id) == VCN_HWID)
+ if (le16_to_cpu(ip->hw_id) == VCN_HWID) {
+ /* Bit [5:0]: original revision value
+ * Bit [7:6]: en/decode capability:
+ * 0b00 : VCN function normally
+ * 0b10 : encode is disabled
+ * 0b01 : decode is disabled
+ */
+ adev->vcn.vcn_config[adev->vcn.num_vcn_inst] =
+ ip->revision & 0xc0;
+ ip->revision &= ~0xc0;
adev->vcn.num_vcn_inst++;
+ }
if (le16_to_cpu(ip->hw_id) == SDMA0_HWID ||
le16_to_cpu(ip->hw_id) == SDMA1_HWID ||
le16_to_cpu(ip->hw_id) == SDMA2_HWID ||
@@ -470,14 +519,6 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int n
return -EINVAL;
}
-
-int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
- int *major, int *minor, int *revision)
-{
- return amdgpu_discovery_get_ip_version(adev, VCN_HWID,
- vcn_instance, major, minor, revision);
-}
-
void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
{
struct binary_header *bhdr;
@@ -489,10 +530,10 @@ 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 +565,15 @@ 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 +581,55 @@ 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 +660,9 @@ 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 +695,9 @@ 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 +727,9 @@ 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 +770,9 @@ 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 +811,9 @@ 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 +841,9 @@ 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 +854,9 @@ 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 +890,9 @@ 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 +926,9 @@ 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 +945,9 @@ 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 +958,9 @@ 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 {
@@ -882,9 +988,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
break;
case IP_VERSION(3, 0, 0):
case IP_VERSION(3, 0, 16):
- 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 +999,9 @@ 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;
}
}
@@ -915,7 +1024,7 @@ static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev)
amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
break;
default:
- break;;
+ break;
}
return 0;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.