diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
24 files changed, 179 insertions, 230 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index d10f483f5e27..ce30d4e8bf25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -644,6 +644,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, uint32_t temp; struct v10_compute_mqd *m = get_mqd(mqd); + if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset) + return 0; + #if 0 unsigned long flags; int retry; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index e262f2ac07a3..92754cfb9808 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -540,6 +540,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd, uint32_t temp; struct v9_mqd *m = get_mqd(mqd); + if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset) + return 0; + if (adev->in_gpu_reset) return -EIO; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index edb561baf8b9..f3fa271e3394 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1247,15 +1247,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( * be freed anyway */ - /* No more MMU notifiers */ - amdgpu_mn_unregister(mem->bo); - /* Make sure restore workers don't access the BO any more */ bo_list_entry = &mem->validate_list; mutex_lock(&process_info->lock); list_del(&bo_list_entry->head); mutex_unlock(&process_info->lock); + /* No more MMU notifiers */ + amdgpu_mn_unregister(mem->bo); + ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx); if (unlikely(ret)) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index daf687428cdb..663314f807fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -150,6 +150,7 @@ int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev) (mode_info->atom_context->bios + data_offset); switch (crev) { case 11: + case 12: mem_channel_number = igp_info->v11.umachannelnumber; /* channel width is 64 */ return mem_channel_number * 64; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 50dff69a0f6e..b1172d93c99c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -192,30 +192,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev) static bool amdgpu_read_platform_bios(struct amdgpu_device *adev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = adev->pdev->rom; + size_t romlen = adev->pdev->romlen; + void __iomem *bios; adev->bios = NULL; - bios = pci_platform_rom(adev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - } - adev->bios = kzalloc(size, GFP_KERNEL); - if (adev->bios == NULL) + adev->bios = kzalloc(romlen, GFP_KERNEL); + if (!adev->bios) return false; - memcpy_fromio(adev->bios, bios, size); + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; - if (!check_atom_bios(adev->bios, size)) { - kfree(adev->bios); - return false; - } + memcpy_fromio(adev->bios, bios, romlen); + iounmap(bios); - adev->bios_size = size; + if (!check_atom_bios(adev->bios, romlen)) + goto free_bios; + + adev->bios_size = romlen; return true; +free_bios: + kfree(adev->bios); + return false; } #ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index ece55c8fa673..cda0a76a733d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -719,8 +719,10 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force) if (!drm_kms_helper_is_poll_worker()) { r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) + if (r < 0) { + pm_runtime_put_autosuspend(connector->dev->dev); return connector_status_disconnected; + } } if (encoder) { @@ -857,8 +859,10 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force) if (!drm_kms_helper_is_poll_worker()) { r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) + if (r < 0) { + pm_runtime_put_autosuspend(connector->dev->dev); return connector_status_disconnected; + } } encoder = amdgpu_connector_best_single_encoder(connector); @@ -980,8 +984,10 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force) if (!drm_kms_helper_is_poll_worker()) { r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) + if (r < 0) { + pm_runtime_put_autosuspend(connector->dev->dev); return connector_status_disconnected; + } } if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) { @@ -1330,8 +1336,10 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force) if (!drm_kms_helper_is_poll_worker()) { r = pm_runtime_get_sync(connector->dev->dev); - if (r < 0) + if (r < 0) { + pm_runtime_put_autosuspend(connector->dev->dev); return connector_status_disconnected; + } } if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 1e25ca34d876..700e26b69abc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -990,27 +990,37 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched) static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring) { struct amdgpu_job *job; - struct drm_sched_job *s_job; + struct drm_sched_job *s_job, *tmp; uint32_t preempt_seq; struct dma_fence *fence, **ptr; struct amdgpu_fence_driver *drv = &ring->fence_drv; struct drm_gpu_scheduler *sched = &ring->sched; + bool preempted = true; if (ring->funcs->type != AMDGPU_RING_TYPE_GFX) return; preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2)); - if (preempt_seq <= atomic_read(&drv->last_seq)) - return; + if (preempt_seq <= atomic_read(&drv->last_seq)) { + preempted = false; + goto no_preempt; + } preempt_seq &= drv->num_fences_mask; ptr = &drv->fences[preempt_seq]; fence = rcu_dereference_protected(*ptr, 1); +no_preempt: spin_lock(&sched->job_list_lock); - list_for_each_entry(s_job, &sched->ring_mirror_list, node) { + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { + if (dma_fence_is_signaled(&s_job->s_fence->finished)) { + /* remove job from ring_mirror_list */ + list_del_init(&s_job->node); + sched->ops->free_job(s_job); + continue; + } job = to_amdgpu_job(s_job); - if (job->fence == fence) + if (preempted && job->fence == fence) /* mark the job as preempted */ job->preemption_status |= AMDGPU_IB_PREEMPTED; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5e1dce424154..4105fbf57167 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3466,6 +3466,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; + amdgpu_amdkfd_pre_reset(adev); + /* Resume IP prior to SMC */ r = amdgpu_device_ip_reinit_early_sriov(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 82efc1e22e61..b588e0e409e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -282,7 +282,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, ret = pm_runtime_get_sync(dev->dev); if (ret < 0) - return ret; + goto out; ret = drm_crtc_helper_set_config(set, ctx); @@ -306,6 +306,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, adev->have_disp_power_ref = false; } +out: /* drop the power reference we got coming in here */ pm_runtime_put_autosuspend(dev->dev); return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 05d114a72ca1..fa2c0f29ad4d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1286,11 +1286,12 @@ long amdgpu_drm_ioctl(struct file *filp, dev = file_priv->minor->dev; ret = pm_runtime_get_sync(dev->dev); if (ret < 0) - return ret; + goto out; ret = drm_ioctl(filp, cmd, arg); pm_runtime_mark_last_busy(dev->dev); +out: pm_runtime_put_autosuspend(dev->dev); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 23085b352cf2..c212d5fc665c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -404,7 +404,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, ring->fence_drv.gpu_addr = adev->uvd.inst[ring->me].gpu_addr + index; } amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq)); - amdgpu_irq_get(adev, irq_src, irq_type); + + if (irq_src) + amdgpu_irq_get(adev, irq_src, irq_type); ring->fence_drv.irq_src = irq_src; ring->fence_drv.irq_type = irq_type; @@ -539,8 +541,9 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) /* no need to trigger GPU reset as we are unloading */ amdgpu_fence_driver_force_completion(ring); } - amdgpu_irq_put(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_put(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); drm_sched_fini(&ring->sched); del_timer_sync(&ring->fence_drv.fallback_timer); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) @@ -576,8 +579,9 @@ void amdgpu_fence_driver_suspend(struct amdgpu_device *adev) } /* disable the interrupt */ - amdgpu_irq_put(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_put(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); } } @@ -603,8 +607,9 @@ void amdgpu_fence_driver_resume(struct amdgpu_device *adev) continue; /* enable the interrupt */ - amdgpu_irq_get(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_get(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 8ceb44925947..5fa5158d18ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -161,16 +161,17 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj, struct amdgpu_bo_list_entry vm_pd; struct list_head list, duplicates; + struct dma_fence *fence = NULL; struct ttm_validate_buffer tv; struct ww_acquire_ctx ticket; struct amdgpu_bo_va *bo_va; - int r; + long r; INIT_LIST_HEAD(&list); INIT_LIST_HEAD(&duplicates); tv.bo = &bo->tbo; - tv.num_shared = 1; + tv.num_shared = 2; list_add(&tv.head, &list); amdgpu_vm_get_pd_bo(vm, &list, &vm_pd); @@ -178,28 +179,34 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj, r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates, false); if (r) { dev_err(adev->dev, "leaking bo va because " - "we fail to reserve bo (%d)\n", r); + "we fail to reserve bo (%ld)\n", r); return; } bo_va = amdgpu_vm_bo_find(vm, bo); - if (bo_va && --bo_va->ref_count == 0) { - amdgpu_vm_bo_rmv(adev, bo_va); - - if (amdgpu_vm_ready(vm)) { - struct dma_fence *fence = NULL; + if (!bo_va || --bo_va->ref_count) + goto out_unlock; - r = amdgpu_vm_clear_freed(adev, vm, &fence); - if (unlikely(r)) { - dev_err(adev->dev, "failed to clear page " - "tables on GEM object close (%d)\n", r); - } + amdgpu_vm_bo_rmv(adev, bo_va); + if (!amdgpu_vm_ready(vm)) + goto out_unlock; - if (fence) { - amdgpu_bo_fence(bo, fence, true); - dma_fence_put(fence); - } - } + fence = dma_resv_get_excl(bo->tbo.base.resv); + if (fence) { + amdgpu_bo_fence(bo, fence, true); + fence = NULL; } + + r = amdgpu_vm_clear_freed(adev, vm, &fence); + if (r || !fence) + goto out_unlock; + + amdgpu_bo_fence(bo, fence, true); + dma_fence_put(fence); + +out_unlock: + if (unlikely(r < 0)) + dev_err(adev->dev, "failed to clear page " + "tables on GEM object close (%ld)\n", r); ttm_eu_backoff_reservation(&ticket, &list); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 96b2a31ccfed..f06a5142d66e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -36,7 +36,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) memset(&ti, 0, sizeof(struct amdgpu_task_info)); - if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { + if (amdgpu_gpu_recovery && + amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", s_job->sched->name); return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index a73206784cba..59fd9ebf3a58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -638,8 +638,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * in the bitfields */ if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; if (info->read_mmr_reg.count > 128) return -EINVAL; @@ -667,9 +671,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info = {}; + struct drm_amdgpu_info_device dev_info; uint64_t vm_size; + memset(&dev_info, 0, sizeof(dev_info)); dev_info.device_id = dev->pdev->device; dev_info.chip_rev = adev->rev_id; dev_info.external_rev = adev->external_rev_id; @@ -975,7 +980,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) r = pm_runtime_get_sync(dev->dev); if (r < 0) - return r; + goto pm_put; fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL); if (unlikely(!fpriv)) { @@ -1026,6 +1031,7 @@ error_pasid: out_suspend: pm_runtime_mark_last_busy(dev->dev); +pm_put: pm_runtime_put_autosuspend(dev->dev); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 51263b8d94b1..3f744e72912f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -370,6 +370,15 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, if (current_level == level) return count; + if (adev->asic_type == CHIP_RAVEN) { + if (adev->rev_id < 8) { + if (current_level != AMD_DPM_FORCED_LEVEL_MANUAL && level == AMD_DPM_FORCED_LEVEL_MANUAL) + amdgpu_gfx_off_ctrl(adev, false); + else if (current_level == AMD_DPM_FORCED_LEVEL_MANUAL && level != AMD_DPM_FORCED_LEVEL_MANUAL) + amdgpu_gfx_off_ctrl(adev, true); + } + } + /* profile_exit setting is valid only when current mode is in profile mode */ if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD | AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK | @@ -416,8 +425,11 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev, ret = smu_get_power_num_states(&adev->smu, &data); if (ret) return ret; - } else if (adev->powerplay.pp_funcs->get_pp_num_states) + } else if (adev->powerplay.pp_funcs->get_pp_num_states) { amdgpu_dpm_get_pp_num_states(adev, &data); + } else { + memset(&data, 0, sizeof(data)); + } buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums); for (i = 0; i < data.nums; i++) @@ -2089,7 +2101,7 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev, @@ -2119,7 +2131,7 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index c8793e6cc3c5..6373bfb47d55 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -124,13 +124,12 @@ int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws) */ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev) { - volatile u32 *dst_ptr; u32 dws; int r; /* allocate clear state block */ adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev); - r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE, + r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, &adev->gfx.rlc.clear_state_obj, &adev->gfx.rlc.clear_state_gpu_addr, @@ -141,13 +140,6 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev) return r; } - /* set up the cs buffer */ - dst_ptr = adev->gfx.rlc.cs_ptr; - adev->gfx.rlc.funcs->get_csb_buffer(adev, dst_ptr); - amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c7514f743409..6335bd4ae374 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2867,10 +2867,17 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, uns WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)), "CPU update of VM recommended only for large BAR system\n"); - if (vm->use_cpu_for_update) + if (vm->use_cpu_for_update) { + /* Sync with last SDMA update/clear before switching to CPU */ + r = amdgpu_bo_sync_wait(vm->root.base.bo, + AMDGPU_FENCE_OWNER_UNDEFINED, true); + if (r) + goto free_idr; + vm->update_funcs = &amdgpu_vm_cpu_funcs; - else + } else { vm->update_funcs = &amdgpu_vm_sdma_funcs; + } dma_fence_put(vm->last_update); vm->last_update = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index dd30f4e61a8c..cae426c7c086 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -744,8 +744,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg) cjiffies = jiffies; if (time_after(cjiffies, ctx->last_jump_jiffies)) { cjiffies -= ctx->last_jump_jiffies; - if ((jiffies_to_msecs(cjiffies) > 5000)) { - DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n"); + if ((jiffies_to_msecs(cjiffies) > 10000)) { + DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n"); ctx->abort = true; } } else { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 6f118292e40f..d17edc850427 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -993,39 +993,6 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v10_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v10_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v10_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -1787,25 +1754,7 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static int gfx_v10_0_init_csb(struct amdgpu_device *adev) { - int r; - - if (adev->in_gpu_reset) { - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (r) - return r; - - r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj, - (void **)&adev->gfx.rlc.cs_ptr); - if (!r) { - adev->gfx.rlc.funcs->get_csb_buffer(adev, - adev->gfx.rlc.cs_ptr); - amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj); - } - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - if (r) - return r; - } + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI, @@ -3774,10 +3723,6 @@ static int gfx_v10_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = gfx_v10_0_csb_vram_pin(adev); - if (r) - return r; - if (!amdgpu_emu_mode) gfx_v10_0_init_golden_registers(adev); @@ -3865,7 +3810,6 @@ static int gfx_v10_0_hw_fini(void *handle) } gfx_v10_0_cp_enable(adev, false); gfx_v10_0_enable_gui_idle_interrupt(adev, false); - gfx_v10_0_csb_vram_unpin(adev); return 0; } @@ -4094,10 +4038,8 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | - RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK); - - /* only for Vega10 & Raven1 */ - data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK; + RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); @@ -4683,12 +4625,17 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring) struct amdgpu_device *adev = ring->adev; struct amdgpu_kiq *kiq = &adev->gfx.kiq; struct amdgpu_ring *kiq_ring = &kiq->ring; + unsigned long flags; if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) return -EINVAL; - if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) + spin_lock_irqsave(&kiq->ring_lock, flags); + + if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) { + spin_unlock_irqrestore(&kiq->ring_lock, flags); return -ENOMEM; + } /* assert preemption condition */ amdgpu_ring_set_preempt_cond_exec(ring, false); @@ -4699,6 +4646,8 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring) ++ring->trail_seq); amdgpu_ring_commit(kiq_ring); + spin_unlock_irqrestore(&kiq->ring_lock, flags); + /* poll the trailing fence */ for (i = 0; i < adev->usec_timeout; i++) { if (ring->trail_seq == diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 791ba398f007..d92e92e5d50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4554,6 +4554,8 @@ static int gfx_v7_0_hw_init(void *handle) gfx_v7_0_constants_init(adev); + /* init CSB */ + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* init rlc */ r = adev->gfx.rlc.funcs->resume(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index cc88ba76a8d4..467ed7fca884 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1321,39 +1321,6 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v8_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v8_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v8_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -3917,6 +3884,7 @@ static void gfx_v8_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static void gfx_v8_0_init_csb(struct amdgpu_device *adev) { + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32(mmRLC_CSIB_ADDR_HI, adev->gfx.rlc.clear_state_gpu_addr >> 32); @@ -4837,10 +4805,6 @@ static int gfx_v8_0_hw_init(void *handle) gfx_v8_0_init_golden_registers(adev); gfx_v8_0_constants_init(adev); - r = gfx_v8_0_csb_vram_pin(adev); - if (r) - return r; - r = adev->gfx.rlc.funcs->resume(adev); if (r) return r; @@ -4958,8 +4922,6 @@ static int gfx_v8_0_hw_fini(void *handle) pr_err("rlc is busy, skip halt rlc\n"); amdgpu_gfx_rlc_exit_safe_mode(adev); - gfx_v8_0_csb_vram_unpin(adev); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6004fdacc866..90dcc7afc9c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1675,39 +1675,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v9_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -2596,6 +2563,7 @@ static void gfx_v9_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static void gfx_v9_0_init_csb(struct amdgpu_device *adev) { + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI), adev->gfx.rlc.clear_state_gpu_addr >> 32); @@ -3888,10 +3856,6 @@ static int gfx_v9_0_hw_init(void *handle) gfx_v9_0_constants_init(adev); - r = gfx_v9_0_csb_vram_pin(adev); - if (r) - return r; - r = adev->gfx.rlc.funcs->resume(adev); if (r) return r; @@ -3977,8 +3941,6 @@ static int gfx_v9_0_hw_fini(void *handle) gfx_v9_0_cp_enable(adev, false); adev->gfx.rlc.funcs->stop(adev); - gfx_v9_0_csb_vram_unpin(adev); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index bd715012185c..465351184bc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -286,30 +286,20 @@ static uint64_t sdma_v5_0_ring_get_rptr(struct amdgpu_ring *ring) static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - u64 *wptr = NULL; - uint64_t local_wptr = 0; + u64 wptr; if (ring->use_doorbell) { /* XXX check if swapping is necessary on BE */ - wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]); - DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr); - *wptr = (*wptr) >> 2; - DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr); + wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs])); + DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr); } else { - u32 lowbit, highbit; - - wptr = &local_wptr; - lowbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2; - highbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2; - - DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n", - ring->me, highbit, lowbit); - *wptr = highbit; - *wptr = (*wptr) << 32; - *wptr |= lowbit; + wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)); + wptr = wptr << 32; + wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)); + DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr); } - return *wptr; + return wptr >> 2; } /** @@ -1273,8 +1263,12 @@ static int sdma_v5_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - for (i = 0; i < adev->sdma.num_instances; i++) + for (i = 0; i < adev->sdma.num_instances; i++) { + if (adev->sdma.instance[i].fw != NULL) + release_firmware(adev->sdma.instance[i].fw); + amdgpu_ring_fini(&adev->sdma.instance[i].ring); + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 36ad0c0e8efb..cd2cbe760e88 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -1026,6 +1026,10 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); /* set the write pointer delay */ WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR_CNTL, 0); @@ -1048,6 +1052,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr)); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); return 0; } @@ -1357,8 +1364,13 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); /* Restore */ ring = &adev->vcn.inst->ring_enc[0]; + ring->wptr = 0; WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr); WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4); @@ -1366,6 +1378,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); ring = &adev->vcn.inst->ring_enc[1]; + ring->wptr = 0; WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr); WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4); @@ -1374,6 +1387,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, |