diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_crat.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 88 |
1 files changed, 85 insertions, 3 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 1eaabd2cb41b0..5e9adbc71bbd3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1056,7 +1056,7 @@ static int kfd_parse_subtype_iolink(struct crat_subtype_iolink *iolink, * table, add corresponded reversed direction link now. */ if (props && (iolink->flags & CRAT_IOLINK_FLAGS_BI_DIRECTIONAL)) { - to_dev = kfd_topology_device_by_proximity_domain(id_to); + to_dev = kfd_topology_device_by_proximity_domain_no_lock(id_to); if (!to_dev) return -ENODEV; /* same everything but the other direction */ @@ -1315,6 +1315,80 @@ static int fill_in_l2_l3_pcache(struct crat_subtype_cache *pcache, return 1; } +#define KFD_MAX_CACHE_TYPES 6 + +static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, + struct kfd_gpu_cache_info *pcache_info) +{ + struct amdgpu_device *adev = kdev->adev; + int i = 0; + + /* TCP L1 Cache per CU */ + if (adev->gfx.config.gc_tcp_l1_size) { + pcache_info[i].cache_size = adev->gfx.config.gc_tcp_l1_size; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[0].num_cu_shared = adev->gfx.config.gc_num_tcp_per_wpg / 2; + i++; + } + /* Scalar L1 Instruction Cache per SQC */ + if (adev->gfx.config.gc_l1_instruction_cache_size_per_sqc) { + pcache_info[i].cache_size = + adev->gfx.config.gc_l1_instruction_cache_size_per_sqc; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_INST_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; + i++; + } + /* Scalar L1 Data Cache per SQC */ + if (adev->gfx.config.gc_l1_data_cache_size_per_sqc) { + pcache_info[i].cache_size = adev->gfx.config.gc_l1_data_cache_size_per_sqc; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; + i++; + } + /* GL1 Data Cache per SA */ + if (adev->gfx.config.gc_gl1c_per_sa && + adev->gfx.config.gc_gl1c_size_per_instance) { + pcache_info[i].cache_size = adev->gfx.config.gc_gl1c_per_sa * + adev->gfx.config.gc_gl1c_size_per_instance; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; + i++; + } + /* L2 Data Cache per GPU (Total Tex Cache) */ + if (adev->gfx.config.gc_gl2c_per_gpu) { + pcache_info[i].cache_size = adev->gfx.config.gc_gl2c_per_gpu; + pcache_info[i].cache_level = 2; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; + i++; + } + /* L3 Data Cache per GPU */ + if (adev->gmc.mall_size) { + pcache_info[i].cache_size = adev->gmc.mall_size / 1024; + pcache_info[i].cache_level = 3; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; + i++; + } + return i; +} + /* kfd_fill_gpu_cache_info - Fill GPU cache info using kfd_gpu_cache_info * tables * @@ -1336,6 +1410,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev, int *num_of_entries) { struct kfd_gpu_cache_info *pcache_info; + struct kfd_gpu_cache_info cache_info[KFD_MAX_CACHE_TYPES]; int num_of_cache_types = 0; int i, j, k; int ct = 0; @@ -1444,6 +1519,13 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev, pcache_info = yellow_carp_cache_info; num_of_cache_types = ARRAY_SIZE(yellow_carp_cache_info); break; + case IP_VERSION(11, 0, 0): + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 2): + pcache_info = cache_info; + num_of_cache_types = + kfd_fill_gpu_cache_info_from_gfx_config(kdev, pcache_info); + break; default: return -EINVAL; } @@ -2152,7 +2234,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image, * report the total FB size (public+private) as a single * private heap. */ - amdgpu_amdkfd_get_local_mem_info(kdev->adev, &local_mem_info); + local_mem_info = kdev->local_mem_info; sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr + sub_type_hdr->length); @@ -2225,7 +2307,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image, */ if (kdev->hive_id) { for (nid = 0; nid < proximity_domain; ++nid) { - peer_dev = kfd_topology_device_by_proximity_domain(nid); + peer_dev = kfd_topology_device_by_proximity_domain_no_lock(nid); if (!peer_dev->gpu) continue; if (peer_dev->gpu->hive_id != kdev->hive_id) |