diff options
Diffstat (limited to 'drivers/gpu')
63 files changed, 1027 insertions, 312 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dc3c6b3a00e5..d356e329e6f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -758,7 +758,7 @@ enum amd_hw_ip_block_type { MAX_HWIP }; -#define HWIP_MAX_INSTANCE 8 +#define HWIP_MAX_INSTANCE 10 struct amd_powerplay { void *pp_handle; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 3003ee1c9487..1d41c2c00623 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm) kgd2kfd_suspend(adev->kfd.dev, run_pm); } +int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev) +{ + int r = 0; + + if (adev->kfd.dev) + r = kgd2kfd_resume_iommu(adev->kfd.dev); + + return r; +} + int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm) { int r = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index ec028cf963f5..3bc52b2c604f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void); void amdgpu_amdkfd_fini(void); void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm); +int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev); int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm); void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev, const void *ih_ring_entry); @@ -327,6 +328,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, const struct kgd2kfd_shared_resources *gpu_resources); void kgd2kfd_device_exit(struct kfd_dev *kfd); void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm); +int kgd2kfd_resume_iommu(struct kfd_dev *kfd); int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm); int kgd2kfd_pre_reset(struct kfd_dev *kfd); int kgd2kfd_post_reset(struct kfd_dev *kfd); @@ -365,6 +367,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) { } +static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd) +{ + return 0; +} + static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) { return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 277128846dd1..463b9c0283f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) struct dentry *ent; int r, i; - - ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev, &fops_ib_preempt); - if (!ent) { + if (IS_ERR(ent)) { DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n"); - return -EIO; + return PTR_ERR(ent); } ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev, &fops_sclk_set); - if (!ent) { + if (IS_ERR(ent)) { DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n"); - return -EIO; + return PTR_ERR(ent); } /* Register debugfs entries for amdgpu_ttm */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 41c6b3aacd37..ab3794c42d36 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2394,6 +2394,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (r) goto init_failed; + r = amdgpu_amdkfd_resume_iommu(adev); + if (r) + goto init_failed; + r = amdgpu_device_ip_hw_init_phase1(adev); if (r) goto init_failed; @@ -3148,6 +3152,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev) { int r; + r = amdgpu_amdkfd_resume_iommu(adev); + if (r) + return r; + r = amdgpu_device_ip_resume_phase1(adev); if (r) return r; @@ -4601,6 +4609,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, dev_warn(tmp_adev->dev, "asic atom init failed!"); } else { dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n"); + r = amdgpu_amdkfd_resume_iommu(tmp_adev); + if (r) + goto out; + r = amdgpu_device_ip_resume_phase1(tmp_adev); if (r) goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index c7797eac83c3..9ff600a38559 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) break; default: adev->gmc.tmz_enabled = false; - dev_warn(adev->dev, + dev_info(adev->dev, "Trusted Memory Zone (TMZ) feature not supported\n"); break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index dc44c946a244..98732518543e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -757,7 +757,7 @@ Out: return res; } -inline uint32_t amdgpu_ras_eeprom_max_record_count(void) +uint32_t amdgpu_ras_eeprom_max_record_count(void) { return RAS_MAX_RECORD_COUNT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h index f95fc61b3021..6bb00578bfbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h @@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control, int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, struct eeprom_table_record *records, const u32 num); -inline uint32_t amdgpu_ras_eeprom_max_record_count(void); +uint32_t amdgpu_ras_eeprom_max_record_count(void); void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 7b634a1517f9..0554576d3695 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev, ent = debugfs_create_file(name, S_IFREG | S_IRUGO, root, ring, &amdgpu_debugfs_ring_fops); - if (!ent) - return -ENOMEM; + if (IS_ERR(ent)) + return PTR_ERR(ent); i_size_write(ent->d_inode, ring->ring_size + 12); ring->ent = ent; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 38dade421d46..94126dc39688 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, goto out; } + if (bo->type == ttm_bo_type_device && + new_mem->mem_type == TTM_PL_VRAM && + old_mem->mem_type != TTM_PL_VRAM) { + /* amdgpu_bo_fault_reserve_notify will re-set this if the CPU + * accesses the BO after it's moved. + */ + abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + } + if (adev->mman.buffer_funcs_enabled) { if (((old_mem->mem_type == TTM_PL_SYSTEM && new_mem->mem_type == TTM_PL_VRAM) || @@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } - if (bo->type == ttm_bo_type_device && - new_mem->mem_type == TTM_PL_VRAM && - old_mem->mem_type != TTM_PL_VRAM) { - /* amdgpu_bo_fault_reserve_notify will re-set this if the CPU - * accesses the BO after it's moved. - */ - abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - } - out: /* update statistics */ atomic64_add(bo->base.size, &adev->num_bytes_moved); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 16a57b70cc1a..c2a4d920da40 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -468,6 +468,7 @@ static const struct kfd_device_info navi10_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -487,6 +488,7 @@ static const struct kfd_device_info navi12_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -506,6 +508,7 @@ static const struct kfd_device_info navi14_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -525,6 +528,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 4, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -544,6 +548,7 @@ static const struct kfd_device_info navy_flounder_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -562,7 +567,8 @@ static const struct kfd_device_info vangogh_device_info = { .mqd_size_aligned = MQD_SIZE_ALIGNED, .needs_iommu_device = false, .supports_cwsr = true, - .needs_pci_atomics = false, + .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, @@ -582,6 +588,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -601,6 +608,7 @@ static const struct kfd_device_info beige_goby_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -619,7 +627,8 @@ static const struct kfd_device_info yellow_carp_device_info = { .mqd_size_aligned = MQD_SIZE_ALIGNED, .needs_iommu_device = false, .supports_cwsr = true, - .needs_pci_atomics = false, + .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, @@ -708,20 +717,6 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, if (!kfd) return NULL; - /* Allow BIF to recode atomics to PCIe 3.0 AtomicOps. - * 32 and 64-bit requests are possible and must be - * supported. - */ - kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd); - if (device_info->needs_pci_atomics && - !kfd->pci_atomic_requested) { - dev_info(kfd_device, - "skipped device %x:%x, PCI rejects atomics\n", - pdev->vendor, pdev->device); - kfree(kfd); - return NULL; - } - kfd->kgd = kgd; kfd->device_info = device_info; kfd->pdev = pdev; @@ -821,6 +816,23 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd - kfd->vm_info.first_vmid_kfd + 1; + /* Allow BIF to recode atomics to PCIe 3.0 AtomicOps. + * 32 and 64-bit requests are possible and must be + * supported. + */ + kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kfd->kgd); + if (!kfd->pci_atomic_requested && + kfd->device_info->needs_pci_atomics && + (!kfd->device_info->no_atomic_fw_version || + kfd->mec_fw_version < kfd->device_info->no_atomic_fw_version)) { + dev_info(kfd_device, + "skipped device %x:%x, PCI rejects atomics %d<%d\n", + kfd->pdev->vendor, kfd->pdev->device, + kfd->mec_fw_version, + kfd->device_info->no_atomic_fw_version); + return false; + } + /* Verify module parameters regarding mapped process number*/ if ((hws_max_conc_proc < 0) || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { @@ -959,7 +971,6 @@ out: void kgd2kfd_device_exit(struct kfd_dev *kfd) { if (kfd->init_complete) { - svm_migrate_fini((struct amdgpu_device *)kfd->kgd); device_queue_manager_uninit(kfd->dqm); kfd_interrupt_exit(kfd); kfd_topology_remove_device(kfd); @@ -1057,17 +1068,21 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) return ret; } -static int kfd_resume(struct kfd_dev *kfd) +int kgd2kfd_resume_iommu(struct kfd_dev *kfd) { int err = 0; err = kfd_iommu_resume(kfd); - if (err) { + if (err) dev_err(kfd_device, "Failed to resume IOMMU for device %x:%x\n", kfd->pdev->vendor, kfd->pdev->device); - return err; - } + return err; +} + +static int kfd_resume(struct kfd_dev *kfd) +{ + int err = 0; err = kfd->dqm->ops.start(kfd->dqm); if (err) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index dab290a4d19d..4a16e3c257b9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -891,9 +891,16 @@ int svm_migrate_init(struct amdgpu_device *adev) pgmap->ops = &svm_migrate_pgmap_ops; pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev); pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + + /* Device manager releases device-specific resources, memory region and + * pgmap when driver disconnects from device. + */ r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); + + /* Disable SVM support capability */ + pgmap->type = 0; devm_release_mem_region(adev->dev, res->start, res->end - res->start + 1); return PTR_ERR(r); @@ -908,12 +915,3 @@ int svm_migrate_init(struct amdgpu_device *adev) return 0; } - -void svm_migrate_fini(struct amdgpu_device *adev) -{ - struct dev_pagemap *pgmap = &adev->kfd.dev->pgmap; - - devm_memunmap_pages(adev->dev, pgmap); - devm_release_mem_region(adev->dev, pgmap->range.start, - pgmap->range.end - pgmap->range.start + 1); -} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index 0de76b5d4973..2f5b3394c9ed 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -47,7 +47,6 @@ unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); int svm_migrate_init(struct amdgpu_device *adev); -void svm_migrate_fini(struct amdgpu_device *adev); #else @@ -55,10 +54,6 @@ static inline int svm_migrate_init(struct amdgpu_device *adev) { return 0; } -static inline void svm_migrate_fini(struct amdgpu_device *adev) -{ - /* empty */ -} #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index ab83b0de6b22..6d8f9bb2d905 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -207,6 +207,7 @@ struct kfd_device_info { bool supports_cwsr; bool needs_iommu_device; bool needs_pci_atomics; + uint32_t no_atomic_fw_version; unsigned int num_sdma_engines; unsigned int num_xgmi_sdma_engines; unsigned int num_sdma_queues_per_engine; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9fc8021bb0ab..9d0f65a90002 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c |