diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
61 files changed, 694 insertions, 550 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_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index f15ded1ce905..c6a1dfe79e80 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -967,6 +967,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm) release_sg: kfree(ttm->sg); + ttm->sg = NULL; return r; } 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, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 901fe3590165..d3400da6ab64 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -905,7 +905,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x7a5d0000, 0x807c817c, 0x807aff7a, 0x00000080, 0xbf0a717c, 0xbf85fff8, - 0xbf820141, 0xbef4037e, + 0xbf820142, 0xbef4037e, 0x8775ff7f, 0x0000ffff, 0x8875ff75, 0x00040000, 0xbef60380, 0xbef703ff, @@ -967,7 +967,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x725d0000, 0xe0304080, 0x725d0100, 0xe0304100, 0x725d0200, 0xe0304180, - 0x725d0300, 0xbf820031, + 0x725d0300, 0xbf820032, 0xbef603ff, 0x01000000, 0xbef20378, 0x8078ff78, 0x00000400, 0xbefc0384, @@ -992,83 +992,84 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x725d0000, 0xe0304100, 0x725d0100, 0xe0304200, 0x725d0200, 0xe0304300, - 0x725d0300, 0xb9782a05, - 0x80788178, 0x907c9973, - 0x877c817c, 0xbf06817c, - 0xbf850002, 0x8f788978, - 0xbf820001, 0x8f788a78, - 0xb9721e06, 0x8f728a72, - 0x80787278, 0x8078ff78, - 0x00000200, 0x80f8ff78, - 0x00000050, 0xbef603ff, - 0x01000000, 0xbefc03ff, - 0x0000006c, 0x80f89078, - 0xf429003a, 0xf0000000, - 0xbf8cc07f, 0x80fc847c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0x80f8a078, - 0xf42d003a, 0xf0000000, - 0xbf8cc07f, 0x80fc887c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0xbe843104, - 0xbe863106, 0x80f8c078, - 0xf431003a, 0xf0000000, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0xbe843104, - 0xbe863106, 0xbe883108, - 0xbe8a310a, 0xbe8c310c, - 0xbe8e310e, 0xbf06807c, - 0xbf84fff0, 0xb9782a05, - 0x80788178, 0x907c9973, - 0x877c817c, 0xbf06817c, - 0xbf850002, 0x8f788978, - 0xbf820001, 0x8f788a78, - 0xb9721e06, 0x8f728a72, - 0x80787278, 0x8078ff78, - 0x00000200, 0xbef603ff, - 0x01000000, 0xf4211bfa, + 0x725d0300, 0xbf8c3f70, + 0xb9782a05, 0x80788178, + 0x907c9973, 0x877c817c, + 0xbf06817c, 0xbf850002, + 0x8f788978, 0xbf820001, + 0x8f788a78, 0xb9721e06, + 0x8f728a72, 0x80787278, + 0x8078ff78, 0x00000200, + 0x80f8ff78, 0x00000050, + 0xbef603ff, 0x01000000, + 0xbefc03ff, 0x0000006c, + 0x80f89078, 0xf429003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc847c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0x80f8a078, 0xf42d003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc887c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0xbe843104, 0xbe863106, + 0x80f8c078, 0xf431003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0xbe843104, 0xbe863106, + 0xbe883108, 0xbe8a310a, + 0xbe8c310c, 0xbe8e310e, + 0xbf06807c, 0xbf84fff0, + 0xb9782a05, 0x80788178, + 0x907c9973, 0x877c817c, + 0xbf06817c, 0xbf850002, + 0x8f788978, 0xbf820001, + 0x8f788a78, 0xb9721e06, + 0x8f728a72, 0x80787278, + 0x8078ff78, 0x00000200, + 0xbef603ff, 0x01000000, + 0xf4211bfa, 0xf0000000, + 0x80788478, 0xf4211b3a, 0xf0000000, 0x80788478, - 0xf4211b3a, 0xf0000000, - 0x80788478, 0xf4211b7a, + 0xf4211b7a, 0xf0000000, + 0x80788478, 0xf4211eba, 0xf0000000, 0x80788478, - 0xf4211eba, 0xf0000000, - 0x80788478, 0xf4211efa, + 0xf4211efa, 0xf0000000, + 0x80788478, 0xf4211c3a, 0xf0000000, 0x80788478, - 0xf4211c3a, 0xf0000000, - 0x80788478, 0xf4211c7a, + 0xf4211c7a, 0xf0000000, + 0x80788478, 0xf4211e7a, 0xf0000000, 0x80788478, - 0xf4211e7a, 0xf0000000, - 0x80788478, 0xf4211cfa, + 0xf4211cfa, 0xf0000000, + 0x80788478, 0xf4211bba, 0xf0000000, 0x80788478, + 0xbf8cc07f, 0xb9eef814, 0xf4211bba, 0xf0000000, 0x80788478, 0xbf8cc07f, - 0xb9eef814, 0xf4211bba, - 0xf0000000, 0x80788478, - 0xbf8cc07f, 0xb9eef815, - 0xbef2036d, 0x876dff72, - 0x0000ffff, 0xbefc036f, - 0xbefe037a, 0xbeff037b, - 0x876f71ff, 0x000003ff, - 0xb9ef4803, 0xb9f9f816, - 0x876f71ff, 0xfffff800, - 0x906f8b6f, 0xb9efa2c3, - 0xb9f3f801, 0x876fff72, - 0xfc000000, 0x906f9a6f, - 0x8f6f906f, 0xbef30380, + 0xb9eef815, 0xbef2036d, + 0x876dff72, 0x0000ffff, + 0xbefc036f, 0xbefe037a, + 0xbeff037b, 0x876f71ff, + 0x000003ff, 0xb9ef4803, + 0xb9f9f816, 0x876f71ff, + 0xfffff800, 0x906f8b6f, + 0xb9efa2c3, 0xb9f3f801, + 0x876fff72, 0xfc000000, + 0x906f9a6f, 0x8f6f906f, + 0xbef30380, 0x88736f73, + 0x876fff72, 0x02000000, + 0x906f996f, 0x8f6f8f6f, 0x88736f73, 0x876fff72, - 0x02000000, 0x906f996f, - 0x8f6f8f6f, 0x88736f73, - 0x876fff72, 0x01000000, - 0x906f986f, 0x8f6f996f, - 0x88736f73, 0x876fff70, - 0x00800000, 0x906f976f, - 0xb9f3f807, 0x87fe7e7e, - 0x87ea6a6a, 0xb9f0f802, - 0xbf8a0000, 0xbe80226c, - 0xbf810000, 0xbf9f0000, + 0x01000000, 0x906f986f, + 0x8f6f996f, 0x88736f73, + 0x876fff70, 0x00800000, + 0x906f976f, 0xb9f3f807, + 0x87fe7e7e, 0x87ea6a6a, + 0xb9f0f802, 0xbf8a0000, + 0xbe80226c, 0xbf810000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, + 0xbf9f0000, 0x00000000, }; static const uint32_t cwsr_trap_arcturus_hex[] = { 0xbf820001, 0xbf8202c4, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index cdaa523ce6be..4433bda2ce25 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -758,6 +758,7 @@ L_RESTORE_V0: buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256 buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*2 buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*3 + s_waitcnt vmcnt(0) /* restore SGPRs */ //will be 2+8+16*6 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index a2ed9c257cb0..e9a278440079 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1075,6 +1075,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 40e3fc0c6942..aa0a617b8d44 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -312,6 +312,7 @@ struct kfd_process *kfd_create_process(struct file *filep) (int)process->lead_thread->pid); if (ret) { pr_warn("Creating procfs pid directory failed"); + kobject_put(process->kobj); goto out; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 7551761f2aa9..a49e2ab071d6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -612,8 +612,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, ret = kobject_init_and_add(dev->kobj_node, &node_type, sys_props.kobj_nodes, "%d", id); - if (ret < 0) + if (ret < 0) { + kobject_put(dev->kobj_node); return ret; + } dev->kobj_mem = kobject_create_and_add("mem_banks", dev->kobj_node); if (!dev->kobj_mem) @@ -660,8 +662,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, return -ENOMEM; ret = kobject_init_and_add(mem->kobj, &mem_type, dev->kobj_mem, "%d", i); - if (ret < 0) + if (ret < 0) { + kobject_put(mem->kobj); return ret; + } mem->attr.name = "properties"; mem->attr.mode = KFD_SYSFS_FILE_MODE; @@ -679,8 +683,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, return -ENOMEM; ret = kobject_init_and_add(cache->kobj, &cache_type, dev->kobj_cache, "%d", i); - if (ret < 0) + if (ret < 0) { + kobject_put(cache->kobj); return ret; + } cache->attr.name = "properties"; cache->attr.mode = KFD_SYSFS_FILE_MODE; @@ -698,8 +704,10 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, return -ENOMEM; ret = kobject_init_and_add(iolink->kobj, &iolink_type, dev->kobj_iolink, "%d", i); - if (ret < 0) + if (ret < 0) { + kobject_put(iolink->kobj); return ret; + } iolink->attr.name = "properties"; iolink->attr.mode = KFD_SYSFS_FILE_MODE; @@ -779,8 +787,10 @@ static int kfd_topology_update_sysfs(void) ret = kobject_init_and_add(sys_props.kobj_topology, &sysprops_type, &kfd_device->kobj, "topology"); - if (ret < 0) + if (ret < 0) { + kobject_put(sys_props.kobj_topology); return ret; + } sys_props.kobj_nodes = kobject_create_and_add("nodes", sys_props.kobj_topology); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9fd12e108a70..7c5808503173 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -928,8 +928,13 @@ static int dm_late_init(void *handle) struct dmcu_iram_parameters params; unsigned int linear_lut[16]; int i; - struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu; - bool ret = false; + struct dmcu *dmcu = NULL; + bool ret; + + if (!adev->dm.fw_dmcu) + return detect_mst_link_for_all_connectors(adev->ddev); + + dmcu = adev->dm.dc->res_pool->dmcu; for (i = 0; i < 16; i++) linear_lut[i] = 0xFFFF * i / 15; @@ -945,13 +950,10 @@ static int dm_late_init(void *handle) */ params.min_abm_backlight = 0x28F; - /* todo will enable for navi10 */ - if (adev->asic_type <= CHIP_RAVEN) { - ret = dmcu_load_iram(dmcu, params); + ret = dmcu_load_iram(dmcu, params); - if (!ret) - return -EINVAL; - } + if (!ret) + return -EINVAL; return detect_mst_link_for_all_connectors(adev->ddev); } @@ -1432,6 +1434,7 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector) drm_connector_update_edid_property(connector, aconnector->edid); + drm_add_edid_modes(connector, aconnector->edid); if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, @@ -2040,12 +2043,18 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) &dm_atomic_state_funcs); r = amdgpu_display_modeset_create_props(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } r = amdgpu_dm_audio_init(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } return 0; } @@ -2061,6 +2070,8 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #if defined(CONFIG_ACPI) struct amdgpu_dm_backlight_caps caps; + memset(&caps, 0, sizeof(caps)); + if (dm->backlight_caps.caps_valid) return; @@ -4288,19 +4299,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -4380,19 +4378,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; @@ -6985,8 +6984,7 @@ static int dm_update_plane_state(struct dc *dc, dm_old_plane_state->dc_state, dm_state->context)) { - ret = EINVAL; - return ret; + return -EINVAL; } @@ -7226,6 +7224,30 @@ cleanup: *out_type = update_type; return ret; } +#if defined(CONFIG_DRM_AMD_DC_DCN) +static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc) +{ + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct amdgpu_dm_connector *aconnector = NULL; + int i; + for_each_new_connector_in_state(state, connector, conn_state, i) { + if (conn_state->crtc != crtc) + continue; + + aconnector = to_amdgpu_dm_connector(connector); + if (!aconnector->port || !aconnector->mst_port) + aconnector = NULL; + else + break; + } + + if (!aconnector) + return 0; + + return drm_dp_mst_add_affected_dsc_crtcs(state, &aconnector->mst_port->mst_mgr); +} +#endif /** * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM. @@ -7279,6 +7301,40 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, if (ret) goto fail; + /* Check connector changes */ + for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) { + struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state); + struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state); + + /* Skip connectors that are disabled or part of modeset already. */ + if (!old_con_state->crtc && !new_con_state->crtc) + continue; + + if (!new_con_state->crtc) + continue; + + new_crtc_state = drm_atomic_get_crtc_state(state, new_con_state->crtc); + if (IS_ERR(new_crtc_state)) { + ret = PTR_ERR(new_crtc_state); + goto fail; + } + + if (dm_old_con_state->abm_level != + dm_new_con_state->abm_level) + new_crtc_state->connectors_changed = true; + } + +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (adev->asic_type >= CHIP_NAVI10) { + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + if (drm_atomic_crtc_needs_modeset(new_crtc_state)) { + ret = add_affected_mst_dsc_crtcs(state, crtc); + if (ret) + goto fail; + } + } + } +#endif for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (!drm_atomic_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->color_mgmt_changed && @@ -7462,20 +7518,38 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * the same resource. If we have a new DC context as part of * the DM atomic state from validation we need to free it and * retain the existing one instead. + * + * Furthermore, since the DM atomic state only contains the DC + * context and can safely be annulled, we can free the state + * and clear the associated private object now to free + * some memory and avoid a possible use-after-free later. */ - struct dm_atomic_state *new_dm_state, *old_dm_state; - new_dm_state = dm_atomic_get_new_state(state); - old_dm_state = dm_atomic_get_old_state(state); + for (i = 0; i < state->num_private_objs; i++) { + struct drm_private_obj *obj = state->private_objs[i].ptr; - if (new_dm_state && old_dm_state) { - if (new_dm_state->context) - dc_release_state(new_dm_state->context); + if (obj->funcs == adev->dm.atomic_obj.funcs) { + int j = state->num_private_objs-1; - new_dm_state->context = old_dm_state->context; + dm_atomic_destroy_state(obj, + state->private_objs[i].state); - if (old_dm_state->context) - dc_retain_state(old_dm_state->context); + /* If i is not at the end of the array then the + * last element needs to be moved to where i was + * before the array can safely be truncated. + */ + if (i != j) + state->private_objs[i] = + state->private_objs[j]; + + state->private_objs[j].ptr = NULL; + state->private_objs[j].state = NULL; + state->private_objs[j].old_state = NULL; + state->private_objs[j].new_state = NULL; + + state->num_private_objs = j; + break; + } } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index b43bb7f90e4e..2233d293a707 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -210,6 +210,8 @@ static int __set_legacy_tf(struct dc_transfer_func *func, res = mod_color_calculate_regamma_params(func, gamma, true, has_rom, NULL); + dc_gamma_release(&gamma); + return res ? 0 : -ENOMEM; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 28a6c7b2ef4b..2f858507ca70 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -101,7 +101,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); - if (payload.write) + if (payload.write && result >= 0) result = msg->size; if (result < 0) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index 785322cd4c6c..7241d4c20778 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -530,6 +530,8 @@ bool dm_pp_get_static_clocks( &pp_clk_info); else if (adev->smu.funcs) ret = smu_get_current_clocks(&adev->smu, &pp_clk_info); + else + return false; if (ret) return false; diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index 221e0f56389f..823843cd2613 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -2543,7 +2543,6 @@ static enum bp_result construct_integrated_info( /* Sort voltage table from low to high*/ if (result == BP_RESULT_OK) { - struct clock_voltage_caps temp = {0, 0}; uint32_t i; uint32_t j; @@ -2553,10 +2552,8 @@ static enum bp_result construct_integrated_info( info->disp_clk_voltage[j].max_supported_clk < info->disp_clk_voltage[j-1].max_supported_clk) { /* swap j and j - 1*/ - temp = info->disp_clk_voltage[j-1]; - info->disp_clk_voltage[j-1] = - info->disp_clk_voltage[j]; - info->disp_clk_voltage[j] = temp; + swap(info->disp_clk_voltage[j - 1], + info->disp_clk_voltage[j]); } } } diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index dff65c0fe82f..7873abea4112 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1613,8 +1613,6 @@ static enum bp_result construct_integrated_info( struct atom_common_table_header *header; struct atom_data_revision revision; - - struct clock_voltage_caps temp = {0, 0}; uint32_t i; uint32_t j; @@ -1644,10 +1642,8 @@ static enum bp_result construct_integrated_info( info->disp_clk_voltage[j-1].max_supported_clk ) { /* swap j and j - 1*/ - temp = info->disp_clk_voltage[j-1]; - info->disp_clk_voltage[j-1] = - info->disp_clk_voltage[j]; - info->disp_clk_voltage[j] = temp; + swap(info->disp_clk_voltage[j - 1], + info->disp_clk_voltage[j]); } } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c index 47f529ce280a..2718396083ee 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c @@ -85,12 +85,77 @@ static int rv1_determine_dppclk_threshold(struct clk_mgr_internal *clk_mgr, stru return disp_clk_threshold; } -static void ramp_up_dispclk_with_dpp(struct clk_mgr_internal *clk_mgr, struct dc *dc, struct dc_clocks *new_clocks) +static void ramp_up_dispclk_with_dpp( + struct clk_mgr_internal *clk_mgr, + struct dc *dc, + struct dc_clocks *new_clocks, + bool safe_to_lower) { int i; int dispclk_to_dpp_threshold = rv1_determine_dppclk_threshold(clk_mgr, new_clocks); bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz; + /* this function is to change dispclk, dppclk and dprefclk according to + * bandwidth requirement. Its call stack is rv1_update_clocks --> + * update_clocks --> dcn10_prepare_bandwidth / dcn10_optimize_bandwidth + * --> prepare_bandwidth / optimize_bandwidth. before change dcn hw, + * prepare_bandwidth will be called first to allow enough clock, + * watermark for change, after end of dcn hw change, optimize_bandwidth + * is executed to lower clock to save power for new dcn hw settings. + * + * below is sequence of commit_planes_for_stream: + * + * step 1: prepare_bandwidth - raise clock to have enough bandwidth + * step 2: lock_doublebuffer_enable + * step 3: pipe_control_lock(true) - make dchubp register change will + * not take effect right way + * step 4: apply_ctx_for_surface - program dchubp + * step 5: pipe_control_lock(false) - dchubp register change take effect + * step 6: optimize_bandwidth --> dc_post_update_surfaces_to_stream + * for full_date, optimize clock to save power + * + * at end of step 1, dcn clocks (dprefclk, dispclk, dppclk) may be + * changed for new dchubp configuration. but real dcn hub dchubps are + * still running with old configuration until end of step 5. this need + * clocks settings at step 1 should not less than that before step 1. + * this is checked by two conditions: 1. if (should_set_clock(safe_to_lower + * , new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) || + * new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz) + * 2. request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz + * + * the second condition is based on new dchubp configuration. dppclk + * for new dchubp may be different from dppclk before step 1. + * for example, before step 1, dchubps are as below: + * pipe 0: recout=(0,40,1920,980) viewport=(0,0,1920,979) + * pipe 1: recout=(0,0,1920,1080) viewport=(0,0,1920,1080) + * for dppclk for pipe0 need dppclk = dispclk + * + * new dchubp pipe split configuration: + * pipe 0: recout=(0,0,960,1080) viewport=(0,0,960,1080) + * pipe 1: recout=(960,0,960,1080) viewport=(960,0,960,1080) + * dppclk only needs dppclk = dispclk /2. + * + * dispclk, dppclk are not lock by otg master lock. they take effect + * after step 1. during this transition, dispclk are the same, but + * dppclk is changed to half of previous clock for old dchubp + * configuration between step 1 and step 6. This may cause p-state + * warning intermittently. + * + * for new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz, we + * need make sure dppclk are not changed to less between step 1 and 6. + * for new_clocks->dispclk_khz > clk_mgr_base->clks.dispclk_khz, + * new display clock is raised, but we do not know ratio of + * new_clocks->dispclk_khz and clk_mgr_base->clks.dispclk_khz, + * new_clocks->dispclk_khz /2 does not guarantee equal or higher than + * old dppclk. we could ignore power saving different between + * dppclk = displck and dppclk = dispclk / 2 between step 1 and step 6. + * as long as safe_to_lower = false, set dpclk = dispclk to simplify + * condition check. + * todo: review this change for other asic. + **/ + if (!safe_to_lower) + request_dpp_div = false; + /* set disp clk to dpp clk threshold */ clk_mgr->funcs->set_dispclk(clk_mgr, dispclk_to_dpp_threshold); @@ -206,7 +271,7 @@ static void rv1_update_clocks(struct clk_mgr *clk_mgr_base, /* program dispclk on = as a w/a for sleep resume clock ramping issues */ if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) || new_clocks->dispclk_khz == clk_mgr_base->clks.dispclk_khz) { - ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks); + ramp_up_dispclk_with_dpp(clk_mgr, dc, new_clocks, safe_to_lower); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; send_request_to_lower = true; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2028dc017f7a..68d56a91d44b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -907,15 +907,11 @@ static void program_timing_sync( /* set first pipe with plane as master */ for (j = 0; j < group_size; j++) { - struct pipe_ctx *temp; - if (pipe_set[j]->plane_state) { if (j == 0) break; - temp = pipe_set[0]; - pipe_set[0] = pipe_set[j]; - pipe_set[j] = temp; + swap(pipe_set[0], pipe_set[j]); break; } } @@ -2230,6 +2226,14 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_stream_update_to_stream(dc, context, stream, stream_update); + if (update_type > UPDATE_TYPE_FAST) { + if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { + DC_ERROR("Mode validation failed for stream update!\n"); + dc_release_state(context); + return; + } + } + commit_planes_for_stream( dc, srf_updates, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 5bf12a446e95..3efee7b3378a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1733,8 +1733,7 @@ static void write_i2c_retimer_setting( slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1752,8 +1751,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } buffer[0] = offset; @@ -1765,8 +1763,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1786,8 +1783,7 @@ static void write_i2c_retimer_setting( slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1805,8 +1801,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } buffer[0] = offset; @@ -1818,8 +1813,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1837,8 +1831,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1849,8 +1842,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1861,10 +1853,14 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set retimer failed"); } static void write_i2c_default_retimer_setting( @@ -1889,8 +1885,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1901,8 +1896,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0B to 0xDA or 0xD8 */ buffer[0] = 0x0B; @@ -1913,8 +1907,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1925,8 +1918,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0C to 0x1D or 0x91 */ buffer[0] = 0x0C; @@ -1937,8 +1929,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1949,8 +1940,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; if (is_vga_mode) { @@ -1965,8 +1955,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1977,8 +1966,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1989,9 +1977,13 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d end here\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set default retimer failed"); } static void write_i2c_redriver_setting( @@ -2020,8 +2012,7 @@ static void write_i2c_redriver_setting( slave_address, buffer[3], buffer[4], buffer[5], buffer[6], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + DC_LOG_DEBUG("Set redriver failed"); } static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 51991bf26a93..4c90d68db230 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -126,22 +126,16 @@ struct aux_payloads { struct vector payloads; }; -static struct i2c_payloads *dal_ddc_i2c_payloads_create(struct dc_context *ctx, uint32_t count) +static bool dal_ddc_i2c_payloads_create( + struct dc_context *ctx, + struct i2c_payloads *payloads, + uint32_t count) { - struct i2c_payloads *payloads; - - payloads = kzalloc(sizeof(struct i2c_payloads), GFP_KERNEL); - - if (!payloads) - return NULL; - if (dal_vector_construct( &payloads->payloads, ctx, count, sizeof(struct i2c_payload))) - return payloads; - - kfree(payloads); - return NULL; + return true; + return false; } static struct i2c_payload *dal_ddc_i2c_payloads_get(struct i2c_payloads *p) @@ -154,14 +148,12 @@ static uint32_t dal_ddc_i2c_payloads_get_count(struct i2c_payloads *p) return p->payloads.count; } -static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads **p) +static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p) { - if (!p || !*p) + if (!p) return; - dal_vector_destruct(&(*p)->payloads); - kfree(*p); - *p = NULL; + dal_vector_destruct(&p->payloads); } #define DDC_MIN(a, b) (((a) < (b)) ? (a) : (b)) @@ -521,9 +513,13 @@ bool dal_ddc_service_query_ddc_data( uint32_t payloads_num = write_payloads + read_payloads; + if (write_size > EDID_SEGMENT_SIZE || read_size > EDID_SEGMENT_SIZE) return false; + if (!payloads_num) + return false; + /*TODO: len of payload data for i2c and aux is uint8!!!!, * but we want to read 256 over i2c!!!!*/ if (dal_ddc_service_is_in_aux_transaction_mode(ddc)) { @@ -556,23 +552,25 @@ bool dal_ddc_service_query_ddc_data( ret = dc_link_aux_transfer_with_retries(ddc, &read_payload); } else { - struct i2c_payloads *payloads = - dal_ddc_i2c_payloads_create(ddc->ctx, payloads_num); + struct i2c_command command = {0}; + struct i2c_payloads payloads; + + if (!dal_ddc_i2c_payloads_create(ddc->ctx, &payloads, payloads_num)) + return false; - struct i2c_command command = { - .payloads = dal_ddc_i2c_payloads_get(payloads), - .number_of_payloads = 0, - .engine = DDC_I2C_COMMAND_ENGINE, - .speed = ddc->ctx->dc->caps.i2c_speed_in_khz }; + command.payloads = dal_ddc_i2c_payloads_get(&payloads); + command.number_of_payloads = 0; + command.engine = DDC_I2C_COMMAND_ENGINE; + command.speed = ddc->ctx->dc->caps.i2c_speed_in_khz; dal_ddc_i2c_payloads_add( - payloads, address, write_size, write_buf, true); + &payloads, address, write_size, write_buf, true); dal_ddc_i2c_payloads_add( - payloads, address, read_size, read_buf, false); + &payloads, address, read_size, read_buf, false); command.number_of_payloads = - dal_ddc_i2c_payloads_get_count(payloads); + dal_ddc_i2c_payloads_get_count(&payloads); ret = dm_helpers_submit_i2c( ddc->ctx, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index a519dbc5ecb6..5641a9477d29 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -400,6 +400,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; ASSERT(dsc_cfg.dc_dsc_cfg.num_slices_h % opp_cnt == 0); dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt; @@ -496,11 +497,15 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; uint8_t dsc_packed_pps[128]; + memset(&dsc_cfg, 0, sizeof(dsc_cfg)); + memset(dsc_packed_pps, 0, 128); + /* Enable DSC hw block */ dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; DC_LOG_DSC(" "); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 1599bb971111..e860ae05feda 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1151,6 +1151,7 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont bool video_large = false; bool desktop_large = false; bool dcc_disabled = false; + bool mpo_enabled = false; for (i = 0; i < context->stream_count; i++) { if (context->stream_status[i].plane_count == 0) @@ -1159,6 +1160,9 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont if (context->stream_status[i].plane_count > 2) return DC_FAIL_UNSUPPORTED_1; + if (context->stream_status[i].plane_count > 1) + mpo_enabled = true; + for (j = 0; j < context->stream_status[i].plane_count; j++) { struct dc_plane_state *plane = context->stream_status[i].plane_states[j]; @@ -1182,6 +1186,10 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont } } + /* Disable MPO in multi-display configurations. */ + if (context->stream_count > 1 && mpo_enabled) + return DC_FAIL_UNSUPPORTED_1; + /* * Workaround: On DCN10 there is UMC issue that causes underflow when * playing 4k video on 4k desktop with video downscaled and single channel diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index 9aa258f3550b..ddf66046616d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -121,35 +121,35 @@ void enc1_update_generic_info_packet( switch (packet_index) { case 0: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC0_FRAME_UPDATE, 1); + AFMT_GENERIC0_IMMEDIATE_UPDATE, 1); break; case 1: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC1_FRAME_UPDATE, 1); + AFMT_GENERIC1_IMMEDIATE_UPDATE, 1); break; case 2: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC2_FRAME_UPDATE, 1); + AFMT_GENERIC2_IMMEDIATE_UPDATE, 1); break; case 3: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC3_FRAME_UPDATE, 1); + AFMT_GENERIC3_IMMEDIATE_UPDATE, 1); break; case 4: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC4_FRAME_UPDATE, 1); + AFMT_GENERIC4_IMMEDIATE_UPDATE, 1); break; case 5: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC5_FRAME_UPDATE, 1); + AFMT_GENERIC5_IMMEDIATE_UPDATE, 1); break; case 6: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC6_FRAME_UPDATE, 1); + AFMT_GENERIC6_IMMEDIATE_UPDATE, 1); break; case 7: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC7_FRAME_UPDATE, 1); + AFMT_GENERIC7_IMMEDIATE_UPDATE, 1); break; default: break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index a512cbea00d1..b9656614950e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -275,7 +275,14 @@ struct dcn10_stream_enc_registers { SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\ @@ -339,7 +346,14 @@ struct dcn10_stream_enc_registers { type AFMT_GENERIC2_FRAME_UPDATE;\ type AFMT_GENERIC3_FRAME_UPDATE;\ type AFMT_GENERIC4_FRAME_UPDATE;\ + type AFMT_GENERIC0_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC1_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC2_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC3_IMMEDIATE_UPDATE;\ type AFMT_GENERIC4_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC5_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC6_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC7_IMMEDIATE_UPDATE;\ type AFMT_GENERIC5_FRAME_UPDATE;\ type AFMT_GENERIC6_FRAME_UPDATE;\ type AFMT_GENERIC7_FRAME_UPDATE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 16476ed25536..206436632275 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -119,32 +119,6 @@ void dccg2_get_dccg_ref_freq(struct dccg *dccg, void dccg2_init(struct dccg *dccg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - // Fallthrough intentional to program all available dpp_dto's - switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) { - case 6: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1); - /* Fall through */ - case 5: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1); - /* Fall through */ - case 4: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1); - /* Fall through */ - case 3: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1); - /* Fall through */ - case 2: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1); - /* Fall through */ - case 1: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1); - break; - default: - ASSERT(false); - break; - } } static const struct dccg_funcs dccg2_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c index 1b419407af94..5c45c39662fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c @@ -207,6 +207,9 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str struct dsc_reg_values dsc_reg_vals; struct dsc_optc_config dsc_optc_cfg; + memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals)); + memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg)); + DC_LOG_DSC("Getting packed DSC PPS for DSC Config:"); dsc_config_log(dsc, dsc_cfg); DC_LOG_DSC("DSC Picture Parameter Set (PPS):"); @@ -348,6 +351,7 @@ static bool dsc_prepare_config(const struct dsc_config *dsc_cfg, struct dsc_reg_ dsc_reg_vals->pps.block_pred_enable = dsc_cfg->dc_dsc_cfg.block_pred_enable; dsc_reg_vals->pps.line_buf_depth = dsc_cfg->dc_dsc_cfg.linebuf_depth; dsc_reg_vals->alternate_ich_encoding_en = dsc_reg_vals->pps.dsc_version_minor == 1 ? 0 : 1; + dsc_reg_vals->ich_reset_at_eol = (dsc_cfg->is_odm || dsc_reg_vals->num_slices_h > 1) ? 0xF : 0; // TODO: in addition to validating slice height (pic height must be divisible by slice height), // see what happens when the same condition doesn't apply for slice_width/pic_width. @@ -510,7 +514,6 @@ static void dsc_update_from_dsc_parameters(struct dsc_reg_values *reg_vals, cons reg_vals->pps.rc_buf_thresh[i] = reg_vals->pps.rc_buf_thresh[i] >> 6; reg_vals->rc_buffer_model_size = dsc_params->rc_buffer_model_size; - reg_vals->ich_reset_at_eol = reg_vals->num_slices_h == 1 ? 0 : 0xf; } static void dsc_write_to_registers(struct display_stream_compressor *dsc, const struct dsc_reg_values *reg_vals) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index c13dce760098..08062de3fbeb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -340,8 +340,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -2275,6 +2275,7 @@ static bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx) + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt; @@ -2845,7 +2846,7 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); BW_VAL_TRACE_COUNT(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c index a00af513aa2b..c8f77bd0ce8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -73,32 +73,47 @@ void apply_DEDCN21_142_wa_for_hostvm_deadline( struct _vcs_dpi_display_dlg_regs_st *dlg_attr) { struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); - uint32_t cur_value; + uint32_t refcyc_per_vm_group_vblank; + uint32_t refcyc_per_vm_req_vblank; + uint32_t refcyc_per_vm_group_flip; + uint32_t refcyc_per_vm_req_flip; + const uint32_t uninitialized_hw_default = 0; - REG_GET(VBLANK_PARAMETERS_5, REFCYC_PER_VM_GROUP_VBLANK, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_group_vblank) + REG_GET(VBLANK_PARAMETERS_5, + REFCYC_PER_VM_GROUP_VBLANK, &refcyc_per_vm_group_vblank); + + if (refcyc_per_vm_group_vblank == uninitialized_hw_default || + refcyc_per_vm_group_vblank > dlg_attr->refcyc_per_vm_group_vblank) REG_SET(VBLANK_PARAMETERS_5, 0, REFCYC_PER_VM_GROUP_VBLANK, dlg_attr->refcyc_per_vm_group_vblank); REG_GET(VBLANK_PARAMETERS_6, - REFCYC_PER_VM_REQ_VBLANK, - &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_req_vblank) + REFCYC_PER_VM_REQ_VBLANK, &refcyc_per_vm_req_vblank); + + if (refcyc_per_vm_req_vblank == uninitialized_hw_default || + refcyc_per_vm_req_vblank > dlg_attr->refcyc_per_vm_req_vblank) REG_SET(VBLANK_PARAMETERS_6, 0, REFCYC_PER_VM_REQ_VBLANK, dlg_attr->refcyc_per_vm_req_vblank); - REG_GET(FLIP_PARAMETERS_3, REFCYC_PER_VM_GROUP_FLIP, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_group_flip) + REG_GET(FLIP_PARAMETERS_3, + REFCYC_PER_VM_GROUP_FLIP, &refcyc_per_vm_group_flip); + + if (refcyc_per_vm_group_flip == uninitialized_hw_default || + refcyc_per_vm_group_flip > dlg_attr->refcyc_per_vm_group_flip) REG_SET(FLIP_PARAMETERS_3, 0, REFCYC_PER_VM_GROUP_FLIP, dlg_attr->refcyc_per_vm_group_flip); - REG_GET(FLIP_PARAMETERS_4, REFCYC_PER_VM_REQ_FLIP, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_req_flip) + REG_GET(FLIP_PARAMETERS_4, + REFCYC_PER_VM_REQ_FLIP, &refcyc_per_vm_req_flip); + + if (refcyc_per_vm_req_flip == uninitialized_hw_default || + refcyc_per_vm_req_flip > dlg_attr->refcyc_per_vm_req_flip) REG_SET(FLIP_PARAMETERS_4, 0, REFCYC_PER_VM_REQ_FLIP, dlg_attr->refcyc_per_vm_req_flip); REG_SET(FLIP_PARAMETERS_5, 0, REFCYC_PER_PTE_GROUP_FLIP_C, dlg_attr->refcyc_per_pte_group_flip_c); + REG_SET(FLIP_PARAMETERS_6, 0, REFCYC_PER_META_CHUNK_FLIP_C, dlg_attr->refcyc_per_meta_chunk_flip_c); } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h index 1ddb1c6fa149..75ecfdc5d5cd 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h @@ -36,6 +36,7 @@ struct dsc_config { uint32_t pic_height; enum dc_pixel_encoding pixel_encoding; enum dc_color_depth color_depth; /* Bits per component */ + bool is_odm; struct dc_dsc_config dc_dsc_cfg; }; diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h index 89ef9f6860e5..16df2a485dd0 100644 --- a/drivers/gpu/drm/amd/display/include/fixed31_32.h +++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h @@ -431,6 +431,9 @@ struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg); */ static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2) { + if (arg1.value == 0) + return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero; + return dc_fixpt_exp( dc_fixpt_mul( dc_fixpt_log(arg1), diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 2d8f14b69117..51d07a4561ce 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -799,7 +799,7 @@ static bool build_regamma(struct pwl_float_data_ex *rgb_regamma, pow_buffer_ptr = -1; // reset back to no optimize ret = true; release: - kfree(coeff); + kvfree(coeff); return ret; } @@ -1862,7 +1862,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf, kfree(rgb_regamma); rgb_regamma_alloc_fail: - kvfree(rgb_user); + kfree(rgb_user); rgb_user_alloc_fail: return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index fed3fc4bb57a..6322e57893db 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -209,8 +209,7 @@ static int smu10_set_min_deep_sleep_dcefclk(struct pp_hwmgr *hwmgr, uint32_t clo { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->need_min_deep_sleep_dcefclk && - smu10_data->deep_sleep_dcefclk != clock) { + if (clock && smu10_data->deep_sleep_dcefclk != clock) { smu10_data->deep_sleep_dcefclk = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk, @@ -223,8 +222,7 @@ static int smu10_set_hard_min_dcefclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t c { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->dcf_actual_hard_min_freq && - smu10_data->dcf_actual_hard_min_freq != clock) { + if (clock && smu10_data->dcf_actual_hard_min_freq != clock) { smu10_data->dcf_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinDcefclkByFreq, @@ -237,8 +235,7 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->f_actual_hard_min_freq && - smu10_data->f_actual_hard_min_freq != clock) { + if (clock && smu10_data->f_actual_hard_min_freq != clock) { smu10_data->f_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index e6da53e9c3f4..1b55f037ba4a 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3575,7 +3575,8 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_POWER: return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: - if ((data->vr_config & 0xff) == 0x2) + if ((data->vr_config & VRCONF_VDDGFX_MASK) == + (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID); else @@ -3986,6 +3987,13 @@ static int smu7_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input) "Failed to populate and upload SCLK MCLK DPM levels!", result = tmp_result); + /* + * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag. + * That effectively disables AVFS feature. + */ + if (hwmgr->hardcode_pp_table != NULL) + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; + tmp_result = smu7_update_avfs(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to update avfs voltages!", diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index beacfffbdc3e..ecbc9daea57e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -3691,6 +3691,13 @@ static int vega10_set_power_state_tasks(struct pp_hwmgr *hwmgr, PP_ASSERT_WITH_CODE(!result, "Failed to upload PPtable!", return result); + /* + * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag. + * That effectively disables AVFS feature. + */ + if(hwmgr->hardcode_pp_table != NULL) + data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; + vega10_update_avfs(hwmgr); /* diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c index ba8763daa380..e8d01abf27fa 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c @@ -364,17 +364,29 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + + /* + * As a common sense, usSoftwareShutdownTemp should be bigger + * than ThotspotLimit. For any invalid usSoftwareShutdownTemp, + * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP + * to avoid false alarms. + */ + if ((tdp_table->usSoftwareShutdownTemp > + range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) { + if (high > tdp_table->usSoftwareShutdownTemp) + high = tdp_table->usSoftwareShutdownTemp; + } if (low > high) return -EINVAL; @@ -383,8 +395,8 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c index 904eb2c9155b..40e7c72eeae0 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c @@ -170,17 +170,18 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -189,8 +190,8 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index f5915308e643..947e4fa3c5e6 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -981,27 +981,15 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint64_t features_enabled; - int i; - bool enabled; - int ret = 0; + int i, ret = 0; PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisableAllSmuFeatures)) == 0, "[DisableAllSMUFeatures] Failed to disable all smu features!", return ret); - ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); - PP_ASSERT_WITH_CODE(!ret, - "[DisableAllSMUFeatures] Failed to get enabled smc features!", - return ret); - - for (i = 0; i < GNLD_FEATURES_MAX; i++) { - enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? - true : false; - data->smu_features[i].enabled = enabled; - data->smu_features[i].supported = enabled; - } + for (i = 0; i < GNLD_FEATURES_MAX; i++) + data->smu_features[i].enabled = 0; return 0; } @@ -1652,12 +1640,6 @@ static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr) data->uvd_power_gated = true; data->vce_power_gated = true; - - if (data->smu_features[GNLD_DPM_UVD].enabled) - data->uvd_power_gated = false; - - if (data->smu_features[GNLD_DPM_VCE].enabled) - data->vce_power_gated = false; } static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) @@ -3211,10 +3193,11 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks) { - uint64_t features_enabled; - uint64_t features_to_enable; - uint64_t features_to_disable; - int ret = 0; + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + uint64_t features_enabled, features_to_enable, features_to_disable; + int i, ret = 0; + bool enabled; if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX)) return -EINVAL; @@ -3243,6 +3226,17 @@ static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return ret; } + /* Update the cached feature enablement state */ + ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); + if (ret) + return ret; + + for (i = 0; i < GNLD_FEATURES_MAX; i++) { + enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? + true : false; + data->smu_features[i].enabled = enabled; + } + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c index ede54e87e287..ce56b93871e8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c @@ -240,17 +240,18 @@ int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -259,8 +260,8 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 0922d9cd858a..c4d8c52c6b9c 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -171,7 +171,8 @@ static int smu_v11_0_init_microcode(struct smu_context *smu) chip_name = "navi12"; break; default: - BUG(); + dev_err(adev->dev, "Unsupported ASIC type %d\n", adev->asic_type); + return -EINVAL; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c index 15590fd86ef4..09a3d8ae4449 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c @@ -239,7 +239,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr) switch (dev_id) { case 0x67BA: - case 0x66B1: + case 0x67B1: smu_data->power_tune_defaults = &defaults_hawaii_pro; break; case 0x67B8: @@ -2725,7 +2725,10 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr) { - return ci_is_smc_ram_running(hwmgr); + return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, + VOLTAGE_CONTROLLER_ON)) + ? true : false; } static int ci_smu_init(struct pp_hwmgr *hwmgr) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c index ae18fbcb26fb..86bdb0194493 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c @@ -642,9 +642,6 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, /* sclk is bigger than max sclk in the dependence table */ *voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), - (dep_table->entries[i - 1].vddc - - (uint16_t)VDDC_VDDCI_DELTA)); if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control) *voltage |= (data->vbios_boot_state.vddci_bootup_value * @@ -652,8 +649,13 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, else if (dep_table->entries[i - 1].vddci) *voltage |= (dep_table->entries[i - 1].vddci * VOLTAGE_SCALE) << VDDC_SHIFT; - else + else { + vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), + (dep_table->entries[i - 1].vddc - + (uint16_t)VDDC_VDDCI_DELTA)); + *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; + } if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) *mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE; |