diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_device.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_device.c | 63 |
1 files changed, 61 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0491ab2b4a9b..4bfedaab183f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -46,6 +46,7 @@ extern const struct kfd2kgd_calls gfx_v8_kfd2kgd; extern const struct kfd2kgd_calls gfx_v9_kfd2kgd; extern const struct kfd2kgd_calls arcturus_kfd2kgd; extern const struct kfd2kgd_calls gfx_v10_kfd2kgd; +extern const struct kfd2kgd_calls gfx_v10_3_kfd2kgd; static const struct kfd2kgd_calls *kfd2kgd_funcs[] = { #ifdef KFD_SUPPORT_IOMMU_V2 @@ -72,6 +73,8 @@ static const struct kfd2kgd_calls *kfd2kgd_funcs[] = { [CHIP_NAVI10] = &gfx_v10_kfd2kgd, [CHIP_NAVI12] = &gfx_v10_kfd2kgd, [CHIP_NAVI14] = &gfx_v10_kfd2kgd, + [CHIP_SIENNA_CICHLID] = &gfx_v10_3_kfd2kgd, + [CHIP_NAVY_FLOUNDER] = &gfx_v10_3_kfd2kgd, }; #ifdef KFD_SUPPORT_IOMMU_V2 @@ -458,6 +461,42 @@ static const struct kfd_device_info navi14_device_info = { .num_sdma_queues_per_engine = 8, }; +static const struct kfd_device_info sienna_cichlid_device_info = { + .asic_family = CHIP_SIENNA_CICHLID, + .asic_name = "sienna_cichlid", + .max_pasid_bits = 16, + .max_no_of_hqd = 24, + .doorbell_size = 8, + .ih_ring_entry_size = 8 * sizeof(uint32_t), + .event_interrupt_class = &event_interrupt_class_v9, + .num_of_watch_points = 4, + .mqd_size_aligned = MQD_SIZE_ALIGNED, + .needs_iommu_device = false, + .supports_cwsr = true, + .needs_pci_atomics = false, + .num_sdma_engines = 4, + .num_xgmi_sdma_engines = 0, + .num_sdma_queues_per_engine = 8, +}; + +static const struct kfd_device_info navy_flounder_device_info = { + .asic_family = CHIP_NAVY_FLOUNDER, + .asic_name = "navy_flounder", + .max_pasid_bits = 16, + .max_no_of_hqd = 24, + .doorbell_size = 8, + .ih_ring_entry_size = 8 * sizeof(uint32_t), + .event_interrupt_class = &event_interrupt_class_v9, + .num_of_watch_points = 4, + .mqd_size_aligned = MQD_SIZE_ALIGNED, + .needs_iommu_device = false, + .supports_cwsr = true, + .needs_pci_atomics = false, + .num_sdma_engines = 2, + .num_xgmi_sdma_engines = 0, + .num_sdma_queues_per_engine = 8, +}; + /* For each entry, [0] is regular and [1] is virtualisation device. */ static const struct kfd_device_info *kfd_supported_devices[][2] = { #ifdef KFD_SUPPORT_IOMMU_V2 @@ -480,6 +519,8 @@ static const struct kfd_device_info *kfd_supported_devices[][2] = { [CHIP_NAVI10] = {&navi10_device_info, NULL}, [CHIP_NAVI12] = {&navi12_device_info, &navi12_device_info}, [CHIP_NAVI14] = {&navi14_device_info, NULL}, + [CHIP_SIENNA_CICHLID] = {&sienna_cichlid_device_info, &sienna_cichlid_device_info}, + [CHIP_NAVY_FLOUNDER] = {&navy_flounder_device_info, &navy_flounder_device_info}, }; static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size, @@ -559,6 +600,10 @@ static void kfd_cwsr_init(struct kfd_dev *kfd) BUILD_BUG_ON(sizeof(cwsr_trap_gfx9_hex) > PAGE_SIZE); kfd->cwsr_isa = cwsr_trap_gfx9_hex; kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx9_hex); + } else if (kfd->device_info->asic_family < CHIP_SIENNA_CICHLID) { + BUILD_BUG_ON(sizeof(cwsr_trap_nv1x_hex) > PAGE_SIZE); + kfd->cwsr_isa = cwsr_trap_nv1x_hex; + kfd->cwsr_isa_size = sizeof(cwsr_trap_nv1x_hex); } else { BUILD_BUG_ON(sizeof(cwsr_trap_gfx10_hex) > PAGE_SIZE); kfd->cwsr_isa = cwsr_trap_gfx10_hex; @@ -577,15 +622,24 @@ static int kfd_gws_init(struct kfd_dev *kfd) return 0; if (hws_gws_support - || (kfd->device_info->asic_family >= CHIP_VEGA10 + || (kfd->device_info->asic_family == CHIP_VEGA10 + && kfd->mec2_fw_version >= 0x81b3) + || (kfd->device_info->asic_family >= CHIP_VEGA12 && kfd->device_info->asic_family <= CHIP_RAVEN - && kfd->mec2_fw_version >= 0x1b3)) + && kfd->mec2_fw_version >= 0x1b3) + || (kfd->device_info->asic_family == CHIP_ARCTURUS + && kfd->mec2_fw_version >= 0x30)) ret = amdgpu_amdkfd_alloc_gws(kfd->kgd, amdgpu_amdkfd_get_num_gws(kfd->kgd), &kfd->gws); return ret; } +static void kfd_smi_init(struct kfd_dev *dev) { + INIT_LIST_HEAD(&dev->smi_clients); + spin_lock_init(&dev->smi_lock); +} + bool kgd2kfd_device_init(struct kfd_dev *kfd, struct drm_device *ddev, const struct kgd2kfd_shared_resources *gpu_resources) @@ -700,6 +754,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_topology_add_device_error; } + kfd_smi_init(kfd); + kfd->init_complete = true; dev_info(kfd_device, "added device %x:%x\n", kfd->pdev->vendor, kfd->pdev->device); @@ -910,6 +966,7 @@ int kgd2kfd_quiesce_mm(struct mm_struct *mm) if (!p) return -ESRCH; + WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid); r = kfd_process_evict_queues(p); kfd_unref_process(p); @@ -977,6 +1034,8 @@ int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm, /* During process initialization eviction_work.dwork is initialized * to kfd_evict_bo_worker */ + WARN(debug_evictions, "Scheduling eviction of pid %d in %ld jiffies", + p->lead_thread->pid, delay_jiffies); schedule_delayed_work(&p->eviction_work, delay_jiffies); out: kfd_unref_process(p); |