diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
38 files changed, 509 insertions, 550 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9f9774f58ce1..b20a06abb65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -274,6 +274,8 @@ extern int amdgpu_rebar; extern int amdgpu_wbrf; extern int amdgpu_user_queue; +extern uint amdgpu_hdmi_hpd_debounce_delay_ms; + #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 58c3ffe707d1..d2c3885de711 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3445,11 +3445,10 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; - /* skip CG for VCE/UVD/VPE, it's handled specially */ + /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN && - adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VPE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG && adev->ip_blocks[i].version->funcs->set_powergating_state) { /* enable powergating to save power */ @@ -5064,6 +5063,14 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_ttm_set_buffer_funcs_status(adev, false); + /* + * device went through surprise hotplug; we need to destroy topology + * before ip_fini_early to prevent kfd locking refcount issues by calling + * amdgpu_amdkfd_suspend() + */ + if (drm_dev_is_unplugged(adev_to_drm(adev))) + amdgpu_amdkfd_device_fini_sw(adev); + amdgpu_device_ip_fini_early(adev); amdgpu_irq_fini_hw(adev); @@ -5867,6 +5874,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) if (ret) goto mode1_reset_failed; + /* enable mmio access after mode 1 reset completed */ + adev->no_hw_access = false; + amdgpu_device_load_pci_state(adev->pdev); ret = amdgpu_psp_wait_for_bootloader(adev); if (ret) @@ -6613,6 +6623,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, struct amdgpu_hive_info *hive = NULL; int r = 0; bool need_emergency_restart = false; + /* save the pasid here as the job may be freed before the end of the reset */ + int pasid = job ? job->pasid : -EINVAL; /* * If it reaches here because of hang/timeout and a RAS error is @@ -6713,8 +6725,12 @@ end_reset: if (!r) { struct amdgpu_task_info *ti = NULL; - if (job) - ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid); + /* + * The job may already be freed at this point via the sched tdr workqueue so + * use the cached pasid. + */ + if (pasid >= 0) + ti = amdgpu_vm_get_task_info_pasid(adev, pasid); drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, ti ? &ti->task : NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index b5d34797d606..52bc04452812 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1880,7 +1880,12 @@ int amdgpu_display_get_scanout_buffer(struct drm_plane *plane, struct drm_scanout_buffer *sb) { struct amdgpu_bo *abo; - struct drm_framebuffer *fb = plane->state->fb; + struct drm_framebuffer *fb; + + if (drm_drv_uses_atomic_modeset(plane->dev)) + fb = plane->state->fb; + else + fb = plane->fb; if (!fb) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e22cfa7c6d32..c1461317eb29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -95,18 +95,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) attach->peer2peer = false; - /* - * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. - * Such buffers cannot be safely accessed over P2P due to device-local - * compression metadata. Fallback to system-memory path instead. - * Device supports GFX12 (GC 12.x or newer) - * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag - * - */ - if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) && - bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) - attach->peer2peer = false; - if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) && pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 2dfbddcef9ab..6ccb80e2d7c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -33,6 +33,7 @@ #include <drm/drm_vblank.h> #include <linux/cc_platform.h> +#include <linux/console.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mmu_notifier.h> @@ -246,6 +247,7 @@ int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; int amdgpu_rebar = -1; /* auto */ int amdgpu_user_queue = -1; +uint amdgpu_hdmi_hpd_debounce_delay_ms; DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", @@ -1122,6 +1124,16 @@ module_param_named(rebar, amdgpu_rebar, int, 0444); MODULE_PARM_DESC(user_queue, "Enable user queues (-1 = auto (default), 0 = disable, 1 = enable, 2 = enable UQs and disable KQs)"); module_param_named(user_queue, amdgpu_user_queue, int, 0444); +/* + * DOC: hdmi_hpd_debounce_delay_ms (uint) + * HDMI HPD disconnect debounce delay in milliseconds. + * + * Used to filter short disconnect->reconnect HPD toggles some HDMI sinks + * generate while entering/leaving power save. Set to 0 to disable by default. + */ +MODULE_PARM_DESC(hdmi_hpd_debounce_delay_ms, "HDMI HPD disconnect debounce delay in milliseconds (0 to disable (by default), 1500 is common)"); +module_param_named(hdmi_hpd_debounce_delay_ms, amdgpu_hdmi_hpd_debounce_delay_ms, uint, 0644); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ @@ -2704,7 +2716,9 @@ static int amdgpu_pmops_thaw(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); /* do not resume device if it's normal hibernation */ - if (!pm_hibernate_is_recovering() && !pm_hibernation_mode_is_suspend()) + if (console_suspend_enabled && + !pm_hibernate_is_recovering() && + !pm_hibernation_mode_is_suspend()) return 0; return amdgpu_device_resume(drm_dev, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index c7843e336310..06c333b2213b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -89,6 +89,16 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring) return seq; } +static void amdgpu_fence_save_fence_wptr_start(struct amdgpu_fence *af) +{ + af->fence_wptr_start = af->ring->wptr; +} + +static void amdgpu_fence_save_fence_wptr_end(struct amdgpu_fence *af) +{ + af->fence_wptr_end = af->ring->wptr; +} + /** * amdgpu_fence_emit - emit a fence on the requested ring * @@ -116,8 +126,10 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct amdgpu_fence *af, &ring->fence_drv.lock, adev->fence_context + ring->idx, seq); + amdgpu_fence_save_fence_wptr_start(af); amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, seq, flags | AMDGPU_FENCE_FLAG_INT); + amdgpu_fence_save_fence_wptr_end(af); amdgpu_fence_save_wptr(af); pm_runtime_get_noresume(adev_to_drm(adev)->dev); ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask]; @@ -709,6 +721,7 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) struct amdgpu_ring *ring = af->ring; unsigned long flags; u32 seq, last_seq; + bool reemitted = false; last_seq = amdgpu_fence_read(ring) & ring->fence_drv.num_fences_mask; seq = ring->fence_drv.sync_seq & ring->fence_drv.num_fences_mask; @@ -726,7 +739,9 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) if (unprocessed && !dma_fence_is_signaled_locked(unprocessed)) { fence = container_of(unprocessed, struct amdgpu_fence, base); - if (fence == af) + if (fence->reemitted > 1) + reemitted = true; + else if (fence == af) dma_fence_set_error(&fence->base, -ETIME); else if (fence->context == af->context) dma_fence_set_error(&fence->base, -ECANCELED); @@ -734,9 +749,12 @@ void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af) rcu_read_unlock(); } while (last_seq != seq); spin_unlock_irqrestore(&ring->fence_drv.lock, flags); - /* signal the guilty fence */ - amdgpu_fence_write(ring, (u32)af->base.seqno); - amdgpu_fence_process(ring); + + if (reemitted) { + /* if we've already reemitted once then just cancel everything */ + amdgpu_fence_driver_force_completion(af->ring); + af->ring->ring_backup_entries_to_copy = 0; + } } void amdgpu_fence_save_wptr(struct amdgpu_fence *af) @@ -784,10 +802,18 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring, /* save everything if the ring is not guilty, otherwise * just save the content from other contexts. */ - if (!guilty_fence || (fence->context != guilty_fence->context)) + if (!fence->reemitted && + (!guilty_fence || (fence->context != guilty_fence->context))) { amdgpu_ring_backup_unprocessed_command(ring, wptr, fence->wptr); + } else if (!fence->reemitted) { + /* always save the fence */ + amdgpu_ring_backup_unprocessed_command(ring, + fence->fence_wptr_start, + fence->fence_wptr_end); + } wptr = fence->wptr; + fence->reemitted++; } rcu_read_unlock(); } while (last_seq != seq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index d2237ce9da70..1485f4789440 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -375,7 +375,7 @@ void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, * @start_page: first page to map in the GART aperture * @num_pages: number of pages to be mapped * @flags: page table entry flags - * @dst: CPU address of the GART table + * @dst: valid CPU address of GART table, cannot be null * * Binds a BO that is allocated in VRAM to the GART page table * (all ASICs). @@ -396,7 +396,7 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa, return; for (i = 0; i < num_pages; ++i) { - amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr, + amdgpu_gmc_set_pte_pde(adev, dst, start_page + i, pa + AMDGPU_GPU_PAGE_SIZE * i, flags); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 869bceb0fe2c..8924380086c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -732,6 +732,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, return 0; if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { + + if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) + return 0; + if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 37270c4dab8d..532f83d783d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -318,12 +318,36 @@ void isp_kernel_buffer_free(void **buf_obj, u64 *gpu_addr, void **cpu_addr) } EXPORT_SYMBOL(isp_kernel_buffer_free); +static int isp_resume(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_resume) + return isp->funcs->hw_resume(isp); + + return -ENODEV; +} + +static int isp_suspend(struct amdgpu_ip_block *ip_block) +{ + struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_isp *isp = &adev->isp; + + if (isp->funcs->hw_suspend) + return isp->funcs->hw_suspend(isp); + + return -ENODEV; +} + static const struct amd_ip_funcs isp_ip_funcs = { .name = "isp_ip", .early_init = isp_early_init, .hw_init = isp_hw_init, .hw_fini = isp_hw_fini, .is_idle = isp_is_idle, + .suspend = isp_suspend, + .resume = isp_resume, .set_clockgating_state = isp_set_clockgating_state, .set_powergating_state = isp_set_powergating_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h index d6f4ffa4c97c..9a5d2b1dff9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h @@ -38,6 +38,8 @@ struct amdgpu_isp; struct isp_funcs { int (*hw_init)(struct amdgpu_isp *isp); int (*hw_fini)(struct amdgpu_isp *isp); + int (*hw_suspend)(struct amdgpu_isp *isp); + int (*hw_resume)(struct amdgpu_isp *isp); }; struct amdgpu_isp { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 6ee77f431d56..f65edd80cabf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -201,6 +201,9 @@ static enum amd_ip_block_type type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ? AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN; break; + case AMDGPU_HW_IP_VPE: + type = AMD_IP_BLOCK_TYPE_VPE; + break; default: type = AMD_IP_BLOCK_TYPE_NUM; break; @@ -721,6 +724,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case AMD_IP_BLOCK_TYPE_UVD: count = adev->uvd.num_uvd_inst; break; + case AMD_IP_BLOCK_TYPE_VPE: + count = adev->vpe.num_instances; + break; /* For all other IP block types not listed in the switch statement * the ip status is valid here and the instance count is one. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7a27c6c4bb44..055437d4edf9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -144,10 +144,15 @@ struct amdgpu_fence { struct amdgpu_ring *ring; ktime_t start_timestamp; - /* wptr for the fence for resets */ + /* wptr for the total submission for resets */ u64 wptr; /* fence context for resets */ u64 context; + /* has this fence been reemitted */ + unsigned int reemitted; + /* wptr for the fence for the submission */ + u64 fence_wptr_start; + u64 fence_wptr_end; }; extern const struct drm_sched_backend_ops amdgpu_sched_ops; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 9a969175900e..58b26c78b642 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -885,12 +885,28 @@ static int amdgpu_userq_input_args_validate(struct drm_device *dev, return 0; } +bool amdgpu_userq_enabled(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + for (i = 0; i < AMDGPU_HW_IP_NUM; i++) { + if (adev->userq_funcs[i]) + return true; + } + + return false; +} + int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { union drm_amdgpu_userq *args = data; int r; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + if (amdgpu_userq_input_args_validate(dev, args, filp) < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index c37444427a14..b48b3bc293fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -141,6 +141,7 @@ uint64_t amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr, struct drm_file *filp); u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev); +bool amdgpu_userq_enabled(struct drm_device *dev); int amdgpu_userq_suspend(struct amdgpu_device *adev); int amdgpu_userq_resume(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index eba9fb359047..85e9edc1cb6f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -141,6 +141,8 @@ static void amdgpu_userq_walk_and_drop_fence_drv(struct xarray *xa) void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq) { + dma_fence_put(userq->last_fence); + amdgpu_userq_walk_and_drop_fence_drv(&userq->fence_drv_xa); xa_destroy(&userq->fence_drv_xa); /* Drop the fence_drv reference held by user queue */ @@ -471,6 +473,9 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_exec exec; u64 wptr; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_syncobj_handles = args->num_syncobj_handles; syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles), size_mul(sizeof(u32), num_syncobj_handles)); @@ -653,6 +658,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, int r, i, rentry, wentry, cnt; struct drm_exec exec; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_read_bo_handles = wait_info->num_bo_read_handles; bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles), size_mul(sizeof(u32), num_read_bo_handles)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c362d4dfb5bb..a67285118c37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1069,9 +1069,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked && - /* SI doesn't support pasid or KIQ/MES */ - params->adev->family > AMDGPU_FAMILY_SI) { + if (!params->unlocked) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 8ad7519f7b58..f1ee3921d970 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1235,16 +1235,16 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_NC); break; case AMDGPU_VM_MTYPE_WC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); break; case AMDGPU_VM_MTYPE_RW: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); break; case AMDGPU_VM_MTYPE_CC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); break; case AMDGPU_VM_MTYPE_UC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); break; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index 4258d3e0b706..0002bcc6c4ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -26,6 +26,7 @@ */ #include <linux/gpio/machine.h> +#include <linux/pm_runtime.h> #include "amdgpu.h" #include "isp_v4_1_1.h" @@ -145,6 +146,9 @@ static int isp_genpd_add_device(struct device *dev, void *data) return -ENODEV; } + /* The devices will be managed by the pm ops from the parent */ + dev_pm_syscore_device(dev, true); + exit: /* Continue to add */ return 0; @@ -177,12 +181,47 @@ static int isp_genpd_remove_device(struct device *dev, void *data) drm_err(&adev->ddev, "Failed to remove dev from genpd %d\n", ret); return -ENODEV; } + dev_pm_syscore_device(dev, false); exit: /* Continue to remove */ return 0; } +static int isp_suspend_device(struct device *dev, void *data) +{ + return pm_runtime_force_suspend(dev); +} + +static int isp_resume_device(struct device *dev, void *data) +{ + return pm_runtime_force_resume(dev); +} + +static int isp_v4_1_1_hw_suspend(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_suspend_device); + if (r) + dev_err(isp->parent, "failed to suspend hw devices (%d)\n", r); + + return r; +} + +static int isp_v4_1_1_hw_resume(struct amdgpu_isp *isp) +{ + int r; + + r = device_for_each_child(isp->parent, NULL, + isp_resume_device); + if (r) + dev_err(isp->parent, "failed to resume hw device (%d)\n", r); + + return r; +} + static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) { const struct software_node *amd_camera_node, *isp4_node; @@ -369,6 +408,8 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp) static const struct isp_funcs isp_v4_1_1_funcs = { .hw_init = isp_v4_1_1_hw_init, .hw_fini = isp_v4_1_1_hw_fini, + .hw_suspend = isp_v4_1_1_hw_suspend, + .hw_resume = isp_v4_1_1_hw_resume, }; void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp) 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 d7a2e7178ea9..625ea8ab7a74 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1209,14 +1209,8 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, pr_debug_ratelimited("Evicting process pid %d queues\n", pdd->process->lead_thread->pid); - if (dqm->dev->kfd->shared_resources.enable_mes) { + if (dqm->dev->kfd->shared_resources.enable_mes) pdd->last_evict_timestamp = get_jiffies_64(); - retval = suspend_all_queues_mes(dqm); - if (retval) { - dev_err(dev, "Suspending all queues failed"); - goto out; - } - } /* Mark all queues as evicted. Deactivate all active queues on * the qpd. @@ -1246,10 +1240,6 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); - } else { - retval = resume_all_queues_mes(dqm); - if (retval) - dev_err(dev, "Resuming all queues failed"); } out: @@ -2919,6 +2909,14 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm) return retval; } +static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, + struct kfd_mem_obj *mqd) +{ + WARN(!mqd, "No hiq sdma mqd trunk to free"); + + amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); +} + struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) { struct device_queue_manager *dqm; @@ -3042,19 +3040,14 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) return dqm; } + if (!dev->kfd->shared_resources.enable_mes) + deallocate_hiq_sdma_mqd(dev, &dqm->hiq_sdma_mqd); + out_free: kfree(dqm); return NULL; } -static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, - struct kfd_mem_obj *mqd) -{ - WARN(!mqd, "No hiq sdma mqd trunk to free"); - - amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); -} - void device_queue_manager_uninit(struct device_queue_manager *dqm) { dqm->ops.stop(dqm); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index a499449fcb06..d2bc169e84b0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -312,7 +312,7 @@ void kfd_smi_event_queue_restore(struct kfd_node *node, pid_t pid) { kfd_smi_event_add(pid, node, KFD_SMI_EVENT_QUEUE_RESTORE, KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), pid, - node->id, 0)); + node->id, '0')); } void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm) 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 740711ac1037..1ea5a250440f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5266,6 +5266,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) struct amdgpu_dm_backlight_caps *caps; char bl_name[16]; int min, max; + int real_brightness; + int init_brightness; if (aconnector->bl_idx == -1) return; @@ -5290,6 +5292,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; + init_brightness = props.brightness; + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) { drm_info(drm, "Using custom brightness curve\n"); props.scale = BACKLIGHT_SCALE_NON_LINEAR; @@ -5308,8 +5312,20 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) { drm_err(drm, "DM: Backlight registration failed!\n"); dm->backlight_dev[aconnector->bl_idx] = NULL; - } else + } else { + /* + * dm->brightness[x] can be inconsistent just after startup until + * ops.get_brightness is called. + */ + real_brightness = + amdgpu_dm_backlight_ops.get_brightness(dm->backlight_dev[aconnector->bl_idx]); + + if (real_brightness != init_brightness) { + dm->actual_brightness[aconnector->bl_idx] = real_brightness; + dm->brightness[aconnector->bl_idx] = real_brightness; + } drm_dbg_driver(drm, "DM: Registered Backlight device: %s\n", bl_name); + } } static int initialize_plane(struct amdgpu_display_manager *dm, @@ -5626,7 +5642,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (psr_feature_enabled) { amdgpu_dm_set_psr_caps(link); - drm_info(adev_to_drm(adev), "PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + drm_info(adev_to_drm(adev), "%s: PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + aconnector->base.name, link->psr_settings.psr_feature_enabled, link->psr_settings.psr_version, link->dpcd_caps.psr_info.psr_version, @@ -8930,9 +8947,18 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); - aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; - INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); - aconnector->hdmi_prev_sink = NULL; + /* + * If HDMI HPD debounce delay is set, use the minimum between selected + * value and AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS + */ + if (amdgpu_hdmi_hpd_debounce_delay_ms) { + aconnector->hdmi_hpd_debounce_delay_ms = min(amdgpu_hdmi_hpd_debounce_delay_ms, + AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS); + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + } else { + aconnector->hdmi_hpd_debounce_delay_ms = 0; + } /* * configure support HPD hot plug connector_>polled default value is 0 diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index bd0403005f37..beb0d04d3e68 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,7 +59,10 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) -#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 +/* + * Maximum HDMI HPD debounce delay in milliseconds + */ +#define AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS 5000 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" 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 d1471f34e419..9f11e6ca4051 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -763,14 +763,14 @@ static enum bp_result bios_parser_encoder_control( return BP_RESULT_FAILURE; return bp->cmd_tbl.dac1_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } else if (cntl->engine_id == ENGINE_ID_DACB) { if (!bp->cmd_tbl.dac2_encoder_control) return BP_RESULT_FAILURE; return bp->cmd_tbl.dac2_encoder_control( - bp, cntl->action == ENCODER_CONTROL_ENABLE, + bp, cntl->action, cntl->pixel_clock, ATOM_DAC1_PS2); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c index 22457f417e65..76a3559f0ddc 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c @@ -1797,7 +1797,30 @@ static enum bp_result select_crtc_source_v3( ¶ms.ucEncodeMode)) return BP_RESULT_BADINPUT; - params.ucDstBpc = bp_params->bit_depth; + switch (bp_params->color_depth) { + case COLOR_DEPTH_UNDEFINED: + params.ucDstBpc = PANEL_BPC_UNDEFINE; + break; + case COLOR_DEPTH_666: + params.ucDstBpc = PANEL_6BIT_PER_COLOR; + break; + default: + case COLOR_DEPTH_888: + params.ucDstBpc = PANEL_8BIT_PER_COLOR; + break; + case COLOR_DEPTH_101010: + params.ucDstBpc = PANEL_10BIT_PER_COLOR; + break; + case COLOR_DEPTH_121212: + params.ucDstBpc = PANEL_12BIT_PER_COLOR; + break; + case COLOR_DEPTH_141414: + dm_error("14-bit color not supported by SelectCRTC_Source v3\n"); + break; + case COLOR_DEPTH_161616: + params.ucDstBpc = PANEL_16BIT_PER_COLOR; + break; + } if (EXEC_BIOS_CMD_TABLE(SelectCRTC_Source, params)) result = BP_RESULT_OK; @@ -1815,12 +1838,12 @@ static enum bp_result select_crtc_source_v3( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); @@ -1846,12 +1869,15 @@ static void init_dac_encoder_control(struct bios_parser *bp) static void dac_encoder_control_prepare_params( DAC_ENCODER_CONTROL_PS_ALLOCATION *params, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { params->ucDacStandard = dac_standard; - if (enable) + if (action == ENCODER_CONTROL_SETUP || + action == ENCODER_CONTROL_INIT) + params->ucAction = ATOM_ENCODER_INIT; + else if (action == ENCODER_CONTROL_ENABLE) params->ucAction = ATOM_ENABLE; else params->ucAction = ATOM_DISABLE; @@ -1864,7 +1890,7 @@ static void dac_encoder_control_prepare_params( static enum bp_result dac1_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1873,7 +1899,7 @@ static enum bp_result dac1_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); @@ -1885,7 +1911,7 @@ static enum bp_result dac1_encoder_control_v1( static enum bp_result dac2_encoder_control_v1( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard) { @@ -1894,7 +1920,7 @@ static enum bp_result dac2_encoder_control_v1( dac_encoder_control_prepare_params( ¶ms, - enable, + action, pixel_clock, dac_standard); diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.h b/drivers/gpu/drm/amd/display/dc/bios/command_table.h index e89b1ba0048b..78bdbcaa61c8 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.h @@ -57,12 +57,12 @@ struct cmd_tbl { struct bp_crtc_source_select *bp_params); enum bp_result (*dac1_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac2_encoder_control)( struct bios_parser *bp, - bool enable, + enum bp_encoder_control_action action, uint32_t pixel_clock, uint8_t dac_standard); enum bp_result (*dac1_output_control)( diff --git a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h index b015e80672ec..fcd3ab4b0045 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h @@ -41,7 +41,7 @@ /* kHZ*/ #define DP_ADAPTOR_DVI_MAX_TMDS_CLK 165000 /* kHZ*/ -#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 165000 +#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 340000 struct dp_hdmi_dongle_signature_data { int8_t id[15];/* "DP-HDMI ADAPTOR"*/ diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index b357683b4255..268b5fbdb48b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -30,7 +30,11 @@ dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) - frame_warn_limit := 3072 + ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) + frame_warn_limit := 4096 + else + frame_warn_limit := 3072 + endif else frame_warn_limit := 2048 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index 8d24763938ea..1df3412be346 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -77,32 +77,14 @@ static unsigned int dscceComputeDelay( static unsigned int dscComputeDelay( enum output_format_class pixelFormat, enum output_encoder_class Output); -// Super monster function with some 45 argument static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -116,7 +98,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -124,9 +105,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -135,14 +113,7 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix); + bool *NotEnoughTimeForDynamicMetadata); static double RoundToDFSGranularityUp(double Clock, double VCOSpeed); static double RoundToDFSGranularityDown(double Clock, double VCOSpeed); static void CalculateDCCConfiguration( @@ -294,62 +265,23 @@ static void CalculateDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, double DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + enum clock_change_support *DRAMClockChangeSupport); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, unsigned int NumberOfActivePlanes, @@ -810,29 +742,12 @@ static unsigned int dscComputeDelay(enum output_format_class pixelFormat, enum o static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -846,7 +761,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -854,9 +768,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -865,15 +776,10 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix) + bool *NotEnoughTimeForDynamicMetadata) { + struct vba_vars_st *v = &mode_lib->vba; + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles = 0, DISPCLKCycles = 0; double DSTTotalPixelsAfterScaler = 0; @@ -905,26 +811,26 @@ static bool CalculatePrefetchSchedule( double Tdmec = 0; double Tdmsks = 0; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMInefficiencyFactor = PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMInefficiencyFactor = v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMInefficiencyFactor = 1; HostVMDynamicLevelsTrips = 0; } CalculateDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->DPPCLK, myPipe->DISPCLK, myPipe->DCFCLKDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, - ProgressiveToInterlaceUnitInOPP, + v->ProgressiveToInterlaceUnitInOPP, &Tsetup, &Tdmbf, &Tdmec, @@ -932,16 +838,16 @@ static bool CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true && GPUVMEnable == true) { - *Tdmdl = TWait + Tvm_trips + trip_to_mem; + if (v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true) { + v->Tdmdl[k] = TWait + Tvm_trips + trip_to_mem; } else { - *Tdmdl = TWait + UrgentExtraLatency; + v->Tdmdl[k] = TWait + UrgentExtraLatency; } - if (DynamicMetadataEnable == true) { - if (VStartup * LineTime < Tsetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { + if (v->DynamicMetadataEnable[k] == true) { + if (VStartup * LineTime < Tsetup + v->Tdmdl[k] + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; } else { *NotEnoughTimeForDynamicMetadata = false; @@ -949,39 +855,39 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); } } else { *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && GPUVMEnable == true ? TWait + Tvm_trips : 0); + v->Tdmdl_vm[k] = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->DPPCLK == 0.0 || myPipe->DISPCLK == 0.0) return true; - *DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + v->DSTXAfterScaler[k] = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + DSCDelay; - *DSTXAfterScaler = *DSTXAfterScaler + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; + v->DSTXAfterScaler[k] = v->DSTXAfterScaler[k] + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && ProgressiveToInterlaceUnitInOPP)) - *DSTYAfterScaler = 1; + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && v->ProgressiveToInterlaceUnitInOPP)) + v->DSTYAfterScaler[k] = 1; else - *DSTYAfterScaler = 0; + v->DSTYAfterScaler[k] = 0; - DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler; - *DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); - *DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal)); + DSTTotalPixelsAfterScaler = v->DSTYAfterScaler[k] * myPipe->HTotal + v->DSTXAfterScaler[k]; + v->DSTYAfterScaler[k] = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); + v->DSTXAfterScaler[k] = DSTTotalPixelsAfterScaler - ((double) (v->DSTYAfterScaler[k] * myPipe->HTotal)); MyError = false; @@ -990,33 +896,33 @@ static bool CalculatePrefetchSchedule( Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1) / 4 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1) / 4 * LineTime; - if (GPUVMEnable) { - if (GPUVMPageTableLevels >= 3) { - *Tno_bw = UrgentExtraLatency + trip_to_mem * ((GPUVMPageTableLevels - 2) - 1); + if (v->GPUVMEnable) { + if (v->GPUVMMaxPageTableLevels >= 3) { + v->Tno_bw[k] = UrgentExtraLatency + trip_to_mem * ((v->GPUVMMaxPageTableLevels - 2) - 1); } else - *Tno_bw = 0; + v->Tno_bw[k] = 0; } else if (!myPipe->DCCEnable) - *Tno_bw = LineTime; + v->Tno_bw[k] = LineTime; else - *Tno_bw = LineTime / 4; + v->Tno_bw[k] = LineTime / 4; - dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime - - (*DSTYAfterScaler + *DSTXAfterScaler / myPipe->HTotal); + dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, v->Tdmdl[k])) / LineTime + - (v->DSTYAfterScaler[k] + v->DSTXAfterScaler[k] / myPipe->HTotal); dst_y_prefetch_equ = dml_min(dst_y_prefetch_equ, 63.75); // limit to the reg limit of U6.2 for DST_Y_PREFETCH Lsw_oto = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC); Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) / Tsw_oto; + prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / Tsw_oto; - if (GPUVMEnable == true) { - Tvm_oto = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, + if (v->GPUVMEnable == true) { + Tvm_oto = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, Tvm_trips, LineTime / 4.0); } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max3( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, LineTime - Tvm_oto, LineTime / 4); @@ -1042,10 +948,10 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", *Tdmdl_vm); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); - dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", *DSTXAfterScaler); - dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)*DSTYAfterScaler); + dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", v->Tdmdl_vm[k]); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); + dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", v->DSTXAfterScaler[k]); + dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)v->DSTYAfterScaler[k]); *PrefetchBandwidth = 0; *DestinationLinesToRequestVMInVBlank = 0; @@ -1059,26 +965,26 @@ static bool CalculatePrefetchSchedule( double PrefetchBandwidth3 = 0; double PrefetchBandwidth4 = 0; - if (Tpre_rounded - *Tno_bw > 0) + if (Tpre_rounded - v->Tno_bw[k] > 0) PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY - + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) - / (Tpre_rounded - *Tno_bw); + + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) + / (Tpre_rounded - v->Tno_bw[k]); else PrefetchBandwidth1 = 0; - if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw) > 0) { - PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw); + if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]) > 0) { + PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]); } - if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0) + if (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded > 0) PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * - BytePerPixelC) / - (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded); + v->BytePerPixelC[k]) / + (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded); else PrefetchBandwidth2 = 0; @@ -1086,7 +992,7 @@ static bool CalculatePrefetchSchedule( PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * - swath_width_chroma_ub * BytePerPixelC) / (Tpre_rounded - + swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded); else PrefetchBandwidth3 = 0; @@ -1096,7 +1002,7 @@ static bool CalculatePrefetchSchedule( } if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) - PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) + PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded); else PrefetchBandwidth4 = 0; @@ -1107,7 +1013,7 @@ static bool CalculatePrefetchSchedule( bool Case3OK; if (PrefetchBandwidth1 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth1 >= Tr0_trips_rounded) { Case1OK = true; } else { @@ -1118,7 +1024,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth2 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth2 < Tr0_trips_rounded) { Case2OK = true; } else { @@ -1129,7 +1035,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth3 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 < Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth3 >= Tr0_trips_rounded) { Case3OK = true; } else { @@ -1152,13 +1058,13 @@ static bool CalculatePrefetchSchedule( dml_print("DML: prefetch_bw_equ: %f\n", prefetch_bw_equ); if (prefetch_bw_equ > 0) { - if (GPUVMEnable) { - Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); + if (v->GPUVMEnable) { + Tvm_equ = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); } else { Tvm_equ = LineTime / 4; } - if ((GPUVMEnable || myPipe->DCCEnable)) { + if ((v->GPUVMEnable || myPipe->DCCEnable)) { Tr0_equ = dml_max4( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, @@ -1227,7 +1133,7 @@ static bool CalculatePrefetchSchedule( } *RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData * BytePerPixelY * swath_width_luma_ub / LineTime; - *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * BytePerPixelC * swath_width_chroma_ub / LineTime; + *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * v->BytePerPixelC[k] * swath_width_chroma_ub / LineTime; } else { MyError = true; dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); @@ -1243,9 +1149,9 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tr0: %fus - time to fetch first row of data pagetables and first row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tr1: %fus - time to fetch second row of data pagetables and second row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tsw: %fus = time to fetch enough pixel data and cursor data to feed the scalers init position and detile\n", (double)LinesToRequestPrefetchPixelData * LineTime); - dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime); + dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime); dml_print("DML: Tvstartup - Tsetup - Tcalc - Twait - Tpre - To > 0\n"); - dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); + dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n", PixelPTEBytesPerRow); } else { @@ -1276,7 +1182,7 @@ static bool CalculatePrefetchSchedule( dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); } - *prefetch_vmrow_bw = dml_max(prefetch_vm_bw, prefetch_row_bw); + v->prefetch_vmrow_bw[k] = dml_max(prefetch_vm_bw, prefetch_row_bw); } if (MyError) { @@ -2437,30 +2343,12 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->ErrorResult[k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelay[k], - v->DPPCLKDelaySubtotal - + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, v->TCalc, @@ -2474,7 +2362,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathY[k], v->PrefetchSourceLinesC[k], v->SwathWidthC[k], - v->BytePerPixelC[k], v->VInitPreFillC[k], v->MaxNumSwathC[k], v->swath_width_luma_ub[k], @@ -2482,9 +2369,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->DestinationLinesForPrefetch[k], &v->PrefetchBandwidth[k], &v->DestinationLinesToRequestVMInVBlank[k], @@ -2493,14 +2377,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman &v->VRatioPrefetchC[k], &v->RequiredPrefetchPixDataBWLuma[k], &v->RequiredPrefetchPixDataBWChroma[k], - &v->NotEnoughTimeForDynamicMetadata[k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NotEnoughTimeForDynamicMetadata[k]); if (v->BlendingAndTiming[k] == k) { double TotalRepeaterDelayTime = v->MaxInterDCNTileRepeaters * (2 / v->DPPCLK[k] + 3 / v->DISPCLK); v->VUpdateWidthPix[k] = (14 / v->DCFCLKDeepSleep + 12 / v->DPPCLK[k] + TotalRepeaterDelayTime) * v->PixelClock[k]; @@ -2730,62 +2607,23 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->DCFCLKDeepSleep, v->DPPPerPlane, - v->DCCEnable, v->DPPCLK, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &DRAMClockChangeSupport); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -4770,29 +4608,12 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->NoTimeForPrefetch[i][j][k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelayPerState[i][k], - v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, v->SwathWidthYThisState[k] / v->HRatio[k], - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), v->MaximumVStartup[i][j][k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgLatency[i], v->ExtraLatency, v->TimeCalc, @@ -4806,7 +4627,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->MaxNumSwY[k], v->PrefetchLinesC[i][j][k], v->SwathWidthCThisState[k], - v->BytePerPixelC[k], v->PrefillC[k], v->MaxNumSwC[k], v->swath_width_luma_ub_this_state[k], @@ -4814,9 +4634,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->LineTimesForPrefetch[k], &v->PrefetchBW[k], &v->LinesForMetaPTE[k], @@ -4825,14 +4642,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &v->VRatioPreC[i][j][k], &v->RequiredPrefetchPixelDataBWLuma[i][j][k], &v->RequiredPrefetchPixelDataBWChroma[i][j][k], - &v->NoTimeForDynamicMetadata[i][j][k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NoTimeForDynamicMetadata[i][j][k]); } for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) { @@ -5007,62 +4817,23 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->DPPOutputBufferPixels, - v->DETBufferSizeInKByte[0], - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->GPUVMEnable, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->FinalDRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, v->ProjectedDCFCLKDeepSleep[i][j], v->NoOfDPPThisState, - v->DCCEnable, v->RequiredDPPCLKThisState, v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, - &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &v->StutterExitWatermark, - &v->StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->DRAMClockChangeSupport[i][j]); } } @@ -5179,63 +4950,25 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int DPPOutputBufferPixels, - unsigned int DETBufferSizeInKByte, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool GPUVMEnable, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, double DCFCLKDeepSleep, unsigned int DPPPerPlane[], - bool DCCEnable[], double DPPCLK[], unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], - enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, - double *StutterExitWatermark, - double *StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + enum clock_change_support *DRAMClockChangeSupport) { + struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY = 0; double EffectiveLBLatencyHidingC = 0; double LinesInDETY[DC__NUM_DPP__MAX] = { 0 }; @@ -5254,101 +4987,101 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double WritebackDRAMClockChangeLatencyHiding = 0; unsigned int k, j; - mode_lib->vba.TotalActiveDPP = 0; - mode_lib->vba.TotalDCCActiveDPP = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - mode_lib->vba.TotalActiveDPP = mode_lib->vba.TotalActiveDPP + DPPPerPlane[k]; - if (DCCEnable[k] == true) { - mode_lib->vba.TotalDCCActiveDPP = mode_lib->vba.TotalDCCActiveDPP + DPPPerPlane[k]; + v->TotalActiveDPP = 0; + v->TotalDCCActiveDPP = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + v->TotalActiveDPP = v->TotalActiveDPP + DPPPerPlane[k]; + if (v->DCCEnable[k] == true) { + v->TotalDCCActiveDPP = v->TotalDCCActiveDPP + DPPPerPlane[k]; } } - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->UrgentWatermark; - mode_lib->vba.TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { - mode_lib->vba.TotalActiveWriteback = mode_lib->vba.TotalActiveWriteback + 1; + v->TotalActiveWriteback = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { + v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } - if (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - if (mode_lib->vba.TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + if (v->TotalActiveWriteback <= 1) { + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->FinalDRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { - mode_lib->vba.LBLatencyHidingSourceLinesY = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + v->LBLatencyHidingSourceLinesY = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); - mode_lib->vba.LBLatencyHidingSourceLinesC = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + v->LBLatencyHidingSourceLinesC = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = mode_lib->vba.LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = mode_lib->vba.LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); LinesInDETY[k] = (double) DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY[k] = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { - LinesInDETC = mode_lib->vba.DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; + LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } - ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY[k] - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY[k] - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { - ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - *UrgentWatermark - (HTotal[k] / PixelClock[k]) * (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) - *DRAMClockChangeWatermark; + ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - v->UrgentWatermark - (v->HTotal[k] / v->PixelClock[k]) * (v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { - ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + if (v->NumberOfActivePlanes > 1) { + ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; + v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { + if (v->WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } - if (mode_lib->vba.WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { + if (v->WritebackConfiguration == dm_whole_buffer_for_single_stream_interleave) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding * 2; } - WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - mode_lib->vba.WritebackDRAMClockChangeWatermark; - mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] = dml_min(mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); + WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; + v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(v->ActiveDRAMClockChangeLatencyMargin[k], WritebackDRAMClockChangeLatencyMargin); } } - mode_lib->vba.MinActiveDRAMClockChangeMargin = 999999; + v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < mode_lib->vba.MinActiveDRAMClockChangeMargin) { - mode_lib->vba.MinActiveDRAMClockChangeMargin = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { + v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5356,40 +5089,40 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = mode_lib->vba.MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->FinalDRAMClockChangeLatency; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { - SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = mode_lib->vba.ActiveDRAMClockChangeLatencyMargin[k]; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { + SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } } - mode_lib->vba.TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { - mode_lib->vba.TotalNumberOfActiveOTG = mode_lib->vba.TotalNumberOfActiveOTG + 1; + v->TotalNumberOfActiveOTG = 0; + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { + v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (v->MinActiveDRAMClockChangeMargin > 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if (((mode_lib->vba.SynchronizedVBlank == true || mode_lib->vba.TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { + } else if (((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0)) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[0]; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (FullDETBufferingTimeY[k] <= FullDETBufferingTimeYStutterCriticalPlane) { FullDETBufferingTimeYStutterCriticalPlane = FullDETBufferingTimeY[k]; - TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (HTotal[k] / PixelClock[k]) / VRatio[k]; + TimeToFinishSwathTransferStutterCriticalPlane = (SwathHeightY[k] - (LinesInDETY[k] - LinesInDETYRoundedDownToSwath[k])) * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; } } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = dml_max(SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); + v->StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + v->StutterEnterPlusExitWatermark = dml_max(v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep, TimeToFinishSwathTransferStutterCriticalPlane); } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 4986f12dc9df..ebd74b43e935 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1118,13 +1118,13 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) if (dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL) num_audio++; } + if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) { + /*wake AZ from D3 first before access az endpoint*/ + clk_mgr->funcs->enable_pme_wa(clk_mgr); + } pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio); - if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) - /*this is the first audio. apply the PME w/a in order to wake AZ from D3*/ - clk_mgr->funcs->enable_pme_wa(clk_mgr); - link_hwss->enable_audio_packet(pipe_ctx); if (pipe_ctx->stream_res.audio) @@ -1610,38 +1610,12 @@ dce110_select_crtc_source(struct pipe_ctx *pipe_ctx) struct dc_bios *bios = link->ctx->dc_bios; struct bp_crtc_source_select crtc_source_select = {0}; enum engine_id engine_id = link->link_enc->preferred_engine; - uint8_t bit_depth; if (dc_is_rgb_signal(pipe_ctx->stream->signal)) engine_id = link->link_enc->analog_engine; - switch (pipe_ctx->stream->timing.display_color_depth) { - case COLOR_DEPTH_UNDEFINED: - bit_depth = 0; - break; - case COLOR_DEPTH_666: - bit_depth = 6; - break; - default: - case COLOR_DEPTH_888: - bit_depth = 8; - break; - case COLOR_DEPTH_101010: - bit_depth = 10; - break; - case COLOR_DEPTH_121212: - bit_depth = 12; - break; - case COLOR_DEPTH_141414: - bit_depth = 14; - break; - case COLOR_DEPTH_161616: - bit_depth = 16; - break; - } - crtc_source_select.controller_id = CONTROLLER_ID_D0 + pipe_ctx->stream_res.tg->inst; - crtc_source_select.bit_depth = bit_depth; + crtc_source_select.color_depth = pipe_ctx->stream->timing.display_color_depth; crtc_source_select.engine_id = engine_id; crtc_source_select.sink_signal = pipe_ctx->stream->signal; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 6d31f4967f1a..7fa6bc97a919 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -336,7 +336,7 @@ static void query_dp_dual_mode_adaptor( /* Assume we have no valid DP passive dongle connected */ *dongle = DISPLAY_DONGLE_NONE; - sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; /* Read DP-HDMI dongle I2c (no response interpreted as DP-DVI dongle)*/ if (!i2c_read( @@ -392,6 +392,8 @@ static void query_dp_dual_mode_adaptor( } } + if (is_valid_hdmi_signature) + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; if (is_type2_dongle) { uint32_t max_tmds_clk = @@ -932,7 +934,7 @@ static bool link_detect_dac_load_detect(struct dc_link *link) struct link_encoder *link_enc = link->link_enc; enum engine_id engine_id = link_enc->preferred_engine; enum dal_device_type device_type = DEVICE_TYPE_CRT; - enum bp_result bp_result; + enum bp_result bp_result = BP_RESULT_UNSUPPORTED; uint32_t enum_id; switch (engine_id) { @@ -946,7 +948,9 @@ static bool link_detect_dac_load_detect(struct dc_link *link) break; } - bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + if (bios->funcs->dac_load_detection) + bp_result = bios->funcs->dac_load_detection(bios, engine_id, device_type, enum_id); + return bp_result == BP_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index ef69898d2cc5..d056e5fd5458 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -203,12 +203,12 @@ enum dcn35_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index f3c614c4490c..9fab3169069c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -183,12 +183,12 @@ enum dcn351_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index 973b6bdbac63..f40dc612ec73 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -136,7 +136,7 @@ struct bp_crtc_source_select { enum engine_id engine_id; enum controller_id controller_id; enum signal_type sink_signal; - uint8_t bit_depth; + enum dc_color_depth color_depth; }; struct bp_transmitter_control { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 7c9f77124ab2..c4966dcc6875 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2455,24 +2455,21 @@ static int navi10_update_pcie_parameters(struct smu_context *smu, } for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (pptable->PcieGenSpeed[i] > pcie_gen_cap || - pptable->PcieLaneCount[i] > pcie_width_cap) { - dpm_context->dpm_tables.pcie_table.pcie_gen[i] = - pptable->PcieGenSpeed[i] > pcie_gen_cap ? - pcie_gen_cap : pptable->PcieGenSpeed[i]; - dpm_context->dpm_tables.pcie_table.pcie_lane[i] = - pptable->PcieLaneCount[i] > pcie_width_cap ? - pcie_width_cap : pptable->PcieLaneCount[i]; - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_gen_cap << 8; - smu_pcie_arg |= pcie_width_cap; - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - break; - } + dpm_context->dpm_tables.pcie_table.pcie_gen[i] = + pptable->PcieGenSpeed[i] > pcie_gen_cap ? + pcie_gen_cap : pptable->PcieGenSpeed[i]; + dpm_context->dpm_tables.pcie_table.pcie_lane[i] = + pptable->PcieLaneCount[i] > pcie_width_cap ? + pcie_width_cap : pptable->PcieLaneCount[i]; + smu_pcie_arg = i << 16; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_gen[i] << 8; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_lane[i]; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_OverridePcieParameters, + smu_pcie_arg, + NULL); + if (ret) + return ret; } return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 677781060246..eaeff6a9bc50 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2923,8 +2923,13 @@ static int smu_v13_0_0_mode1_reset(struct smu_context *smu) break; } - if (!ret) + if (!ret) { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index f9b0938c57ea..f2a16dfee599 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -1939,6 +1939,11 @@ int smu_v14_0_od_edit_dpm_table(struct smu_context *smu, dev_err(smu->adev->dev, "Set soft max sclk failed!"); return ret; } + if (smu->gfx_actual_hard_min_freq != smu->gfx_default_hard_min_freq || + smu->gfx_actual_soft_max_freq != smu->gfx_default_soft_max_freq) + smu->user_dpm_profile.user_od = true; + else + smu->user_dpm_profile.user_od = false; break; default: return -ENOSYS; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index b1bd946d8e30..97414bc39764 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -1514,9 +1514,10 @@ static int smu_v14_0_1_set_fine_grain_gfx_freq_parameters(struct smu_context *sm smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; - smu->gfx_actual_hard_min_freq = 0; - smu->gfx_actual_soft_max_freq = 0; - + if (smu->gfx_actual_hard_min_freq == 0) + smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; + if (smu->gfx_actual_soft_max_freq == 0) + smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; return 0; } @@ -1526,8 +1527,10 @@ static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *sm smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; - smu->gfx_actual_hard_min_freq = 0; - smu->gfx_actual_soft_max_freq = 0; + if (smu->gfx_actual_hard_min_freq == 0) + smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; + if (smu->gfx_actual_soft_max_freq == 0) + smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; return 0; } @@ -1665,6 +1668,29 @@ static int smu_v14_0_common_set_mall_enable(struct smu_context *smu) return ret; } +static int smu_v14_0_0_restore_user_od_settings(struct smu_context *smu) +{ + int ret; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk, + smu->gfx_actual_hard_min_freq, + NULL); + if (ret) { + dev_err(smu->adev->dev, "Failed to restore hard min sclk!\n"); + return ret; + } + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk, + smu->gfx_actual_soft_max_freq, + NULL); + if (ret) { + dev_err(smu->adev->dev, "Failed to restore soft max sclk!\n"); + return ret; + } + + return 0; +} + static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .check_fw_version = smu_v14_0_check_fw_version, @@ -1688,6 +1714,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .mode2_reset = smu_v14_0_0_mode2_reset, .get_dpm_ultimate_freq = smu_v14_0_common_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v14_0_0_set_soft_freq_limited_range, + .restore_user_od_settings = smu_v14_0_0_restore_user_od_settings, .od_edit_dpm_table = smu_v14_0_od_edit_dpm_table, .print_clk_levels = smu_v14_0_0_print_clk_levels, .force_clk_levels = smu_v14_0_0_force_clk_levels, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 2cea688c604f..d7642d388bc3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1702,8 +1702,9 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; + int16_t od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; + uint32_t power_limit; if (smu_v14_0_get_current_power_limit(smu, &power_limit)) power_limit = smu->adev->pm.ac_power ? @@ -2143,10 +2144,15 @@ static int smu_v14_0_2_mode1_reset(struct smu_context *smu) ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset); if (!ret) { - if (amdgpu_emu_mode == 1) + if (amdgpu_emu_mode == 1) { msleep(50000); - else + } else { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(1000); + } } return ret; |