diff options
Diffstat (limited to 'drivers/gpu')
47 files changed, 474 insertions, 226 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ee7df1d84e..89cf9ac6da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4048,6 +4048,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->grbm_idx_mutex); mutex_init(&adev->mn_lock); mutex_init(&adev->virt.vf_errors.lock); + mutex_init(&adev->virt.rlcg_reg_lock); hash_init(adev->mn_hash); mutex_init(&adev->psp.mutex); mutex_init(&adev->notifier_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index e4742b6503..4a9cec0026 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -262,9 +262,8 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job, struct dma_fence *fence = NULL; int r; - /* Ignore soft recovered fences here */ r = drm_sched_entity_error(s_entity); - if (r && r != -ENODATA) + if (r) goto error; if (!fence && job->gang_submit) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index ca5c86e5f7..8e8afbd237 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -334,7 +334,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size set_ta_context_funcs(psp, ta_type, &context); - if (!context->initialized) { + if (!context || !context->initialized) { dev_err(adev->dev, "TA is not initialized\n"); ret = -EINVAL; goto err_free_shared_buf; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 1adc81a557..0c4ee06451 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2172,12 +2172,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work) int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev, struct ras_dispatch_if *info) { - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); - struct ras_ih_data *data = &obj->ih_data; + struct ras_manager *obj; + struct ras_ih_data *data; + obj = amdgpu_ras_find_obj(adev, &info->head); if (!obj) return -EINVAL; + data = &obj->ih_data; + if (data->inuse == 0) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 54ab51a4ad..972a58f0f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -980,6 +980,9 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1; scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2; scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3; + + mutex_lock(&adev->virt.rlcg_reg_lock); + if (reg_access_ctrl->spare_int) spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int; @@ -1036,6 +1039,9 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f } ret = readl(scratch_reg0); + + mutex_unlock(&adev->virt.rlcg_reg_lock); + return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 642f1fd287..0ec246c745 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -272,6 +272,8 @@ struct amdgpu_virt { /* the ucode id to signal the autoload */ uint32_t autoload_ucode_id; + + struct mutex rlcg_reg_lock; }; struct amdgpu_video_codec_info; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 66e8a01612..9b748d7058 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -102,6 +102,11 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p, if (!r) r = amdgpu_sync_push_to_job(&sync, p->job); amdgpu_sync_free(&sync); + + if (r) { + p->num_dw_left = 0; + amdgpu_job_free(p->job); + } return r; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 31e500859a..9248525124 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1658,7 +1658,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, start = map_start << PAGE_SHIFT; end = (map_last + 1) << PAGE_SHIFT; for (addr = start; !r && addr < end; ) { - struct hmm_range *hmm_range; + struct hmm_range *hmm_range = NULL; unsigned long map_start_vma; unsigned long map_last_vma; struct vm_area_struct *vma; @@ -1696,7 +1696,12 @@ static int svm_range_validate_and_map(struct mm_struct *mm, } svm_range_lock(prange); - if (!r && amdgpu_hmm_range_get_pages_done(hmm_range)) { + + /* Free backing memory of hmm_range if it was initialized + * Overrride return value to TRY AGAIN only if prior returns + * were successful + */ + if (hmm_range && amdgpu_hmm_range_get_pages_done(hmm_range) && !r) { pr_debug("hmm update the range, need validate again\n"); r = -EAGAIN; } 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 3cdcadd41b..836bf9ba62 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2701,7 +2701,8 @@ static int dm_suspend(void *handle) dm->cached_dc_state = dc_state_create_copy(dm->dc->current_state); - dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); + if (dm->cached_dc_state) + dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); amdgpu_dm_commit_zero_streams(dm->dc); @@ -2943,6 +2944,7 @@ static int dm_resume(void *handle) commit_params.streams = dc_state->streams; commit_params.stream_count = dc_state->stream_count; + dc_exit_ips_for_hw_access(dm->dc); WARN_ON(!dc_commit_streams(dm->dc, &commit_params)); dm_gpureset_commit_state(dm->cached_dc_state, dm); @@ -3015,7 +3017,8 @@ static int dm_resume(void *handle) emulated_link_detect(aconnector->dc_link); } else { mutex_lock(&dm->dc_lock); - dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + dc_exit_ips_for_hw_access(dm->dc); + dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4); mutex_unlock(&dm->dc_lock); } @@ -3351,6 +3354,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) enum dc_connection_type new_connection_type = dc_connection_none; struct amdgpu_device *adev = drm_to_adev(dev); struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state); + struct dc *dc = aconnector->dc_link->ctx->dc; bool ret = false; if (adev->dm.disable_hpd_irq) @@ -3385,6 +3389,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) drm_kms_helper_connector_hotplug_event(connector); } else { mutex_lock(&adev->dm.dc_lock); + dc_exit_ips_for_hw_access(dc); ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); mutex_unlock(&adev->dm.dc_lock); if (ret) { @@ -3444,6 +3449,7 @@ static void handle_hpd_rx_irq(void *param) bool has_left_work = false; int idx = dc_link->link_index; struct hpd_rx_irq_offload_work_queue *offload_wq = &adev->dm.hpd_rx_offload_wq[idx]; + struct dc *dc = aconnector->dc_link->ctx->dc; memset(&hpd_irq_data, 0, sizeof(hpd_irq_data)); @@ -3533,6 +3539,7 @@ out: bool ret = false; mutex_lock(&adev->dm.dc_lock); + dc_exit_ips_for_hw_access(dc); ret = dc_link_detect(dc_link, DETECT_REASON_HPDRX); mutex_unlock(&adev->dm.dc_lock); @@ -4639,6 +4646,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) bool ret = false; mutex_lock(&dm->dc_lock); + dc_exit_ips_for_hw_access(dm->dc); ret = dc_link_detect(link, DETECT_REASON_BOOT); mutex_unlock(&dm->dc_lock); @@ -6788,7 +6796,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector) aconnector->dc_sink = aconnector->dc_link->local_sink ? aconnector->dc_link->local_sink : aconnector->dc_em_sink; - dc_sink_retain(aconnector->dc_sink); + if (aconnector->dc_sink) + dc_sink_retain(aconnector->dc_sink); } } @@ -7615,7 +7624,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 1920, 1080); } else { amdgpu_dm_connector_ddc_get_modes(connector, edid); - amdgpu_dm_connector_add_common_modes(encoder, connector); + if (encoder) + amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, edid); } amdgpu_dm_fbc_init(connector); @@ -8945,7 +8955,8 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, memset(&position, 0, sizeof(position)); mutex_lock(&dm->dc_lock); - dc_stream_set_cursor_position(dm_old_crtc_state->stream, &position); + dc_exit_ips_for_hw_access(dm->dc); + dc_stream_program_cursor_position(dm_old_crtc_state->stream, &position); mutex_unlock(&dm->dc_lock); } @@ -9014,6 +9025,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, dm_enable_per_frame_crtc_master_sync(dc_state); mutex_lock(&dm->dc_lock); + dc_exit_ips_for_hw_access(dm->dc); WARN_ON(!dc_commit_streams(dm->dc, ¶ms)); /* Allow idle optimization when vblank count is 0 for display off */ @@ -9379,6 +9391,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) mutex_lock(&dm->dc_lock); + dc_exit_ips_for_hw_access(dm->dc); dc_update_planes_and_stream(dm->dc, dummy_updates, status->plane_count, 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 a5e1a93dda..b50010ed76 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 @@ -182,6 +182,8 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector) dc_sink_release(dc_sink); aconnector->dc_sink = NULL; aconnector->edid = NULL; + aconnector->dsc_aux = NULL; + port->passthrough_aux = NULL; } aconnector->mst_status = MST_STATUS_DEFAULT; @@ -494,6 +496,8 @@ dm_dp_mst_detect(struct drm_connector *connector, dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; aconnector->edid = NULL; + aconnector->dsc_aux = NULL; + port->passthrough_aux = NULL; amdgpu_dm_set_mst_status(&aconnector->mst_status, MST_REMOTE_EDID | MST_ALLOCATE_NEW_PAYLOAD | MST_CLEAR_ALLOCATED_PAYLOAD, @@ -1233,14 +1237,6 @@ static bool is_dsc_need_re_compute( if (!aconnector || !aconnector->dsc_aux) continue; - /* - * check if cached virtual MST DSC caps are available and DSC is supported - * as per specifications in their Virtual DPCD registers. - */ - if (!(aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported || - aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.fields.dsc_support.DSC_PASSTHROUGH_SUPPORT)) - continue; - stream_on_link[new_stream_on_link_num] = aconnector; new_stream_on_link_num++; @@ -1268,6 +1264,9 @@ static bool is_dsc_need_re_compute( } } + if (new_stream_on_link_num == 0) + return false; + /* check current_state if there stream on link but it is not in * new request state */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 8a4c40b4c2..311c62d2d1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1254,7 +1254,7 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane, /* turn off cursor */ if (crtc_state && crtc_state->stream) { mutex_lock(&adev->dm.dc_lock); - dc_stream_set_cursor_position(crtc_state->stream, + dc_stream_program_cursor_position(crtc_state->stream, &position); mutex_unlock(&adev->dm.dc_lock); } @@ -1284,11 +1284,11 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane, if (crtc_state->stream) { mutex_lock(&adev->dm.dc_lock); - if (!dc_stream_set_cursor_attributes(crtc_state->stream, + if (!dc_stream_program_cursor_attributes(crtc_state->stream, &attributes)) DRM_ERROR("DC failed to set cursor attributes\n"); - if (!dc_stream_set_cursor_position(crtc_state->stream, + if (!dc_stream_program_cursor_position(crtc_state->stream, &position)) DRM_ERROR("DC failed to set cursor position\n"); mutex_unlock(&adev->dm.dc_lock); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 15819416a2..8ed5993246 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -2267,6 +2267,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state) otg_master = resource_get_otg_master_for_stream( &state->res_ctx, state->streams[stream_idx]); + + if (!otg_master) + continue; + resource_log_pipe_for_stream(dc, state, otg_master, stream_idx); } if (state->phantom_stream_count > 0) { @@ -2508,6 +2512,17 @@ static void remove_hpo_dp_link_enc_from_ctx(struct resource_context *res_ctx, } } +static int get_num_of_free_pipes(const struct resource_pool *pool, const struct dc_state *context) +{ + int i; + int count = 0; + + for (i = 0; i < pool->pipe_count; i++) + if (resource_is_pipe_type(&context->res_ctx.pipe_ctx[i], FREE_PIPE)) + count++; + return count; +} + enum dc_status resource_add_otg_master_for_stream_output(struct dc_state *new_ctx, const struct resource_pool *pool, struct dc_stream_state *stream) @@ -2641,37 +2656,33 @@ static bool acquire_secondary_dpp_pipes_and_add_plane( struct dc_state *cur_ctx, struct resource_pool *pool) { - struct pipe_ctx *opp_head_pipe, *sec_pipe, *tail_pipe; + struct pipe_ctx *sec_pipe, *tail_pipe; + struct pipe_ctx *opp_heads[MAX_PIPES]; + int opp_head_count; + int i; if (!pool->funcs->acquire_free_pipe_as_secondary_dpp_pipe) { ASSERT(0); return false; } - opp_head_pipe = otg_master_pipe; - while (opp_head_pipe) { + opp_head_count = resource_get_opp_heads_for_otg_master(otg_master_pipe, + &new_ctx->res_ctx, opp_heads); + if (get_num_of_free_pipes(pool, new_ctx) < opp_head_count) + /* not enough free pipes */ + return false; + + for (i = 0; i < opp_head_count; i++) { sec_pipe = pool->funcs->acquire_free_pipe_as_secondary_dpp_pipe( cur_ctx, new_ctx, pool, - opp_head_pipe); - if (!sec_pipe) { - /* try tearing down MPCC combine */ - int pipe_idx = acquire_first_split_pipe( - &new_ctx->res_ctx, pool, - otg_master_pipe->stream); - - if (pipe_idx >= 0) - sec_pipe = &new_ctx->res_ctx.pipe_ctx[pipe_idx]; - } - - if (!sec_pipe) - return false; - + opp_heads[i]); + ASSERT(sec_pipe); sec_pipe->plane_state = plane_state; /* establish pipe relationship */ - tail_pipe = get_tail_pipe(opp_head_pipe); + tail_pipe = get_tail_pipe(opp_heads[i]); tail_pipe->bottom_pipe = sec_pipe; sec_pipe->top_pipe = tail_pipe; sec_pipe->bottom_pipe = NULL; @@ -2682,8 +2693,6 @@ static bool acquire_secondary_dpp_pipes_and_add_plane( } else { sec_pipe->prev_odm_pipe = NULL; } - - opp_head_pipe = opp_head_pipe->next_odm_pipe; } return true; } @@ -2696,6 +2705,7 @@ bool resource_append_dpp_pipes_for_plane_composition( struct dc_plane_state *plane_state) { bool success; + if (otg_master_pipe->plane_state == NULL) success = add_plane_to_opp_head_pipes(otg_master_pipe, plane_state, new_ctx); @@ -2703,10 +2713,15 @@ bool resource_append_dpp_pipes_for_plane_composition( success = acquire_secondary_dpp_pipes_and_add_plane( otg_master_pipe, plane_state, new_ctx, cur_ctx, pool); - if (success) + if (success) { /* when appending a plane mpc slice count changes from 0 to 1 */ success = update_pipe_params_after_mpc_slice_count_change( plane_state, new_ctx, pool); + if (!success) + resource_remove_dpp_pipes_for_plane_composition(new_ctx, + pool, plane_state); + } + return success; } @@ -2716,6 +2731,7 @@ void resource_remove_dpp_pipes_for_plane_composition( const struct dc_plane_state *plane_state) { int i; + for (i = pool->pipe_count - 1; i >= 0; i--) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 76bb05f4d6..52a1cfc5fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -437,6 +437,19 @@ enum dc_status dc_state_remove_stream( return DC_OK; } +static void remove_mpc_combine_for_stream(const struct dc *dc, + struct dc_state *new_ctx, + const struct dc_state *cur_ctx, + struct dc_stream_status *status) +{ + int i; + + for (i = 0; i < status->plane_count; i++) + resource_update_pipes_for_plane_with_slice_count( + new_ctx, cur_ctx, dc->res_pool, + status->plane_states[i], 1); +} + bool dc_state_add_plane( const struct dc *dc, struct dc_stream_state *stream, @@ -447,8 +460,12 @@ bool dc_state_add_plane( struct pipe_ctx *otg_master_pipe; struct dc_stream_status *stream_status = NULL; bool added = false; + int odm_slice_count; + int i; stream_status = dc_state_get_stream_status(state, stream); + otg_master_pipe = resource_get_otg_master_for_stream( + &state->res_ctx, stream); if (stream_status == NULL) { dm_error("Existing stream not found; failed to attach surface!\n"); goto out; @@ -456,22 +473,39 @@ bool dc_state_add_plane( dm_error("Surface: can not attach plane_state %p! Maximum is: %d\n", plane_state, MAX_SURFACE_NUM); goto out; + } else if (!otg_master_pipe) { + goto out; } - if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm) - /* ODM combine could prevent us from supporting more planes - * we will reset ODM slice count back to 1 when all planes have - * been removed to maximize the amount of planes supported when - * new planes are added. - */ - resource_update_pipes_for_stream_with_slice_count( - state, dc->current_state, dc->res_pool, stream, 1); + added = resource_append_dpp_pipes_for_plane_composition(state, + dc->current_state, pool, otg_master_pipe, plane_state); - otg_master_pipe = resource_get_otg_master_for_stream( - &state->res_ctx, stream); - if (otg_master_pipe) + if (!added) { + /* try to remove MPC combine to free up pipes */ + for (i = 0; i < state->stream_count; i++) + remove_mpc_combine_for_stream(dc, state, + dc->current_state, + &state->stream_status[i]); added = resource_append_dpp_pipes_for_plane_composition(state, - dc->current_state, pool, otg_master_pipe, plane_state); + dc->current_state, pool, + otg_master_pipe, plane_state); + } + + if (!added) { + /* try to decrease ODM slice count gradually to free up pipes */ + odm_slice_count = resource_get_odm_slice_count(otg_master_pipe); + for (i = odm_slice_count - 1; i > 0; i--) { + resource_update_pipes_for_stream_with_slice_count(state, + dc->current_state, dc->res_pool, stream, + i); + added = resource_append_dpp_pipes_for_plane_composition( + state, + dc->current_state, pool, + otg_master_pipe, plane_state); + if (added) + break; + } + } if (added) { stream_status->plane_states[stream_status->plane_count] = @@ -531,15 +565,6 @@ bool dc_state_remove_plane( stream_status->plane_states[stream_status->plane_count] = NULL; - if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm) - /* ODM combine could prevent us from supporting more planes - * we will reset ODM slice count back to 1 when all planes have - * been removed to maximize the amount of planes supported when - * new planes are added. - */ - resource_update_pipes_for_stream_with_slice_count( - state, dc->current_state, dc->res_pool, stream, 1); - return true; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 5c7e4884ca..53bc991b6e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -266,7 +266,6 @@ bool dc_stream_set_cursor_attributes( const struct dc_cursor_attributes *attributes) { struct dc *dc; - bool reset_idle_optimizations = false; if (NULL == stream) { dm_error("DC: dc_stream is NULL!\n"); @@ -297,20 +296,36 @@ bool dc_stream_set_cursor_attributes( stream->cursor_attributes = *attributes; - dc_z10_restore(dc); - /* disable idle optimizations while updating cursor */ - if (dc->idle_optimizations_allowed) { - dc_allow_idle_optimizations(dc, false); - reset_idle_optimizations = true; - } + return true; +} - program_cursor_attributes(dc, stream, attributes); +bool dc_stream_program_cursor_attributes( + struct dc_stream_state *stream, + const struct dc_cursor_attributes *attributes) +{ + struct dc *dc; + bool reset_idle_optimizations = false; - /* re-enable idle optimizations if necessary */ - if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle) - dc_allow_idle_optimizations(dc, true); + dc = stream ? stream->ctx->dc : NULL; - return true; + if (dc_stream_set_cursor_attributes(stream, attributes)) { + dc_z10_restore(dc); + /* disable idle optimizations while updating cursor */ + if (dc->idle_optimizations_allowed) { + dc_allow_idle_optimizations(dc, false); + reset_idle_optimizations = true; + } + + program_cursor_attributes(dc, stream, attributes); + + /* re-enable idle optimizations if necessary */ + if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle) + dc_allow_idle_optimizations(dc, true); + + return true; + } + + return false; } static void program_cursor_position( @@ -355,9 +370,6 @@ bool dc_stream_set_cursor_position( struct dc_stream_state *stream, const struct dc_cursor_position *position) { - struct dc *dc; - bool reset_idle_optimizations = false; - if (NULL == stream) { dm_error("DC: dc_stream is NULL!\n"); return false; @@ -368,24 +380,46 @@ bool dc_stream_set_cursor_position( return false; } + stream->cursor_position = *position; + + + return true; +} + +bool dc_stream_program_cursor_position( + struct dc_stream_state *stream, + const struct dc_cursor_position *position) +{ + struct dc *dc; + bool reset_idle_optimizations = false; + const struct dc_cursor_position *old_position; + + if (!stream) + return false; + + old_position = &stream->cursor_position; dc = stream->ctx->dc; - dc_z10_restore(dc); - /* disable idle optimizations if enabling cursor */ - if (dc->idle_optimizations_allowed && (!stream->cursor_position.enable || dc->debug.exit_idle_opt_for_cursor_updates) - && position->enable) { - dc_allow_idle_optimizations(dc, false); - reset_idle_optimizations = true; - } + if (dc_stream_set_cursor_position(stream, position)) { + dc_z10_restore(dc); - stream->cursor_position = *position; + /* disable idle optimizations if enabling cursor */ + if (dc->idle_optimizations_allowed && + (!old_position->enable || dc->debug.exit_idle_opt_for_cursor_updates) && + position->enable) { + dc_allow_idle_optimizations(dc, false); + reset_idle_optimizations = true; + } - program_cursor_position(dc, stream, position); - /* re-enable idle optimizations if necessary */ - if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle) - dc_allow_idle_optimizations(dc, true); + program_cursor_position(dc, stream, position); + /* re-enable idle optimizations if necessary */ + if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle) + dc_allow_idle_optimizations(dc, true); - return true; + return true; + } + + return false; } bool dc_stream_add_writeback(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index e5dbbc6089..1039dfb0b0 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -470,10 +470,18 @@ bool dc_stream_set_cursor_attributes( struct dc_stream_state *stream, const struct dc_cursor_attributes *attributes); +bool dc_stream_program_cursor_attributes( + struct dc_stream_state *stream, + const struct dc_cursor_attributes *attributes); + bool dc_stream_set_cursor_position( struct dc_stream_state *stream, const struct dc_cursor_position *position); +bool dc_stream_program_cursor_position( + struct dc_stream_state *stream, + const struct dc_cursor_position *position); + bool dc_stream_adjust_vmin_vmax(struct dc *dc, struct dc_stream_state *stream, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c index 4f559a025c..09cf54586f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c @@ -84,7 +84,7 @@ static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, cmd.replay_enable.header.payload_bytes = sizeof(struct dmub_rb_cmd_replay_enable_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); /* Below loops 1000 x 500us = 500 ms. * Exit REPLAY may need to wait 1-2 frames to power up. Timeout after at @@ -127,7 +127,7 @@ static void dmub_replay_set_power_opt(struct dmub_replay *dmub, unsigned int pow cmd.replay_set_power_opt.replay_set_power_opt_data.power_opt = power_opt; cmd.replay_set_power_opt.replay_set_power_opt_data.panel_inst = panel_inst; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* @@ -209,8 +209,7 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub, else copy_settings_data->flags.bitfields.force_wakeup_by_tps3 = 0; - - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -231,7 +230,7 @@ static void dmub_replay_set_coasting_vtotal(struct dmub_replay *dmub, cmd.replay_set_coasting_vtotal.header.payload_bytes = sizeof(struct dmub_cmd_replay_set_coasting_vtotal_data); cmd.replay_set_coasting_vtotal.replay_set_coasting_vtotal_data.coasting_vtotal = coasting_vtotal; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 0c4aef8ffe..3306684e80 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -288,6 +288,7 @@ static void dcn10_log_color_state(struct dc *dc, { struct dc_context *dc_ctx = dc->ctx; struct resource_pool *pool = dc->res_pool; + bool is_gamut_remap_available = false; int i; DTN_INFO("DPP: IGAM format IGAM mode DGAM mode RGAM mode" @@ -300,16 +301,15 @@ static void dcn10_log_color_state(struct dc *dc, struct dcn_dpp_state s = {0}; dpp->funcs->dpp_read_state(dpp, &s); - dpp->funcs->dpp_get_gamut_remap(dpp, &s.gamut_remap); + if (dpp->funcs->dpp_get_gamut_remap) { + dpp->funcs->dpp_get_gamut_remap(dpp, &s.gamut_remap); + is_gamut_remap_available = true; + } if (!s.is_enabled) continue; - DTN_INFO("[%2d]: %11xh %11s %9s %9s" - " %12s " - "%010lld %010lld %010lld %010lld " - "%010lld %010lld %010lld %010lld " - "%010lld %010lld %010lld %010lld", + DTN_INFO("[%2d]: %11xh %11s %9s %9s", dpp->inst, s.igam_input_format, (s.igam_lut_mode == 0) ? "BypassFixed" : @@ -328,22 +328,27 @@ static void dcn10_log_color_state(struct dc *dc, ((s.rgam_lut_mode == 2) ? "Ycc" : ((s.rgam_lut_mode == 3) ? "RAM" : ((s.rgam_lut_mode == 4) ? "RAM" : - "Unknown")))), - (s.gamut_remap.gamut_adjust_type == 0) ? "Bypass" : - ((s.gamut_remap.gamut_adjust_type == 1) ? "HW" : - "SW"), - s.gamut_remap.temperature_matrix[0].value, - s.gamut_remap.temperature_matrix[1].value, - s.gamut_remap.temperature_matrix[2].value, - s.gamut_remap.temperature_matrix[3].value, - s.gamut_remap.temperature_matrix[4].value, - s.gamut_remap.temperature_matrix[5].value, - s.gamut_remap.temperature_matrix[6].value, - s.gamut_remap.temperature_matrix[7].value, - s.gamut_remap.temperature_matrix[8].value, - s.gamut_remap.temperature_matrix[9].value, - s.gamut_remap.temperature_matrix[10].value, - s.gamut_remap.temperature_matrix[11].value); + "Unknown"))))); + if (is_gamut_remap_available) + DTN_INFO(" %12s " + "%010lld %010lld %010lld %010lld " + "%010lld %010lld %010lld %010lld " + "%010lld %010lld %010lld %010lld", + (s.gamut_remap.gamut_adjust_type == 0) ? "Bypass" : + ((s.gamut_remap.gamut_adjust_type == 1) ? "HW" : "SW"), + s.gamut_remap.temperature_matrix[0].value, + s.gamut_remap.temperature_matrix[1].value, + s.gamut_remap.temperature_matrix[2].value, + s.gamut_remap.temperature_matrix[3].value, + s.gamut_remap.temperature_matrix[4].value, + s.gamut_remap.temperature_matrix[5].value, + s.gamut_remap.temperature_matrix[6].value, + s.gamut_remap.temperature_matrix[7].value, + s.gamut_remap.temperature_matrix[8].value, + s.gamut_remap.temperature_matrix[9].value, + s.gamut_remap.temperature_matrix[10].value, + s.gamut_remap.temperature_matrix[11].value); + DTN_INFO("\n"); } DTN_INFO("\n"); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index ed9141a67d..4c47061533 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -919,6 +919,9 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) stream = dc->current_state->streams[0]; plane = (stream ? dc->current_state->stream_status[0].plane_states[0] : NULL); + if (!stream || !plane) + return false; + if (stream && plane) { cursor_cache_enable = stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part; @@ -1038,7 +1041,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) /* Use copied cursor, and it's okay to not switch back */ cursor_attr.address.quad_part = cmd.mall.cursor_copy_dst.quad_part; - dc_stream_set_cursor_attributes(stream, &cursor_attr); + dc_stream_program_cursor_attributes(stream, &cursor_attr); } /* Enable MALL */ diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c index 3e6c7be7e2..5302d2c9c7 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c @@ -165,7 +165,12 @@ static void set_hpo_fixed_vs_pe_retimer_dp_link_test_pattern(struct dc_link *lin link_res->hpo_dp_link_enc->funcs->set_link_test_pattern( link_res->hpo_dp_link_enc, tp_params); } + link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); + + // Give retimer extra time to lock before updating DP_TRAINING_PATTERN_SET to TPS1 + if (tp_params->dp_phy_pattern == DP_TEST_PATTERN_128b_132b_TPS1_TRAINING_MODE) + msleep(30); } static void set_hpo_fixed_vs_pe_retimer_dp_lane_settings(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index b53ad18dbf..ec9ff5f8bd 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -2313,8 +2313,6 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) dc->hwss.disable_audio_stream(pipe_ctx); - edp_set_panel_assr(link, pipe_ctx, &panel_mode_dp, false); - update_psp_stream_config(pipe_ctx, true); dc->hwss.blank_stream(pipe_ctx); @@ -2368,6 +2366,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) dc->hwss.disable_stream(pipe_ctx); disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal); } + edp_set_panel_assr(link, pipe_ctx, &panel_mode_dp, false); if (pipe_ctx->stream->timing.flags.DSC) { if (dc_is_dp_signal(pipe_ctx->stream->signal)) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c index 0fcf0b8530..564246983f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c @@ -454,7 +454,8 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link, * If we got sink count changed it means * Downstream port status changed, * then DM should call DC to do the detection. - * NOTE: Do not handle link loss on eDP since it is internal link*/ + * NOTE: Do not handle link loss on eDP since it is internal link + */ if ((link->connector_signal != SIGNAL_TYPE_EDP) && dp_parse_link_loss_status( link, diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index 0a939437e1..6b380e037e 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -2193,10 +2193,11 @@ bool dcn20_get_dcc_compression_cap(const struct dc *dc, const struct dc_dcc_surface_param *input, struct dc_surface_dcc_cap *output) { - return dc->res_pool->hubbub->funcs->get_dcc_compression_cap( - dc->res_pool->hubbub, - input, - output); + if (dc->res_pool->hubbub->funcs->get_dcc_compression_cap) + return dc->res_pool->hubbub->funcs->get_dcc_compression_cap( + dc->res_pool->hubbub, input, output); + + return false; } static void dcn20_destroy_resource_pool(struct resource_pool **pool) diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 5fb21a0508..f531ce1d2b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -929,7 +929,7 @@ static int pp_dpm_switch_power_profile(void *handle, enum PP_SMC_POWER_PROFILE type, bool en) { struct pp_hwmgr *hwmgr = handle; - long workload; + long workload[1]; uint32_t index; if (!hwmgr || !hwmgr->pm_en) @@ -947,12 +947,12 @@ static int pp_dpm_switch_power_profile(void *handle, hwmgr->workload_mask &= ~(1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } else { hwmgr->workload_mask |= (1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } if (type == PP_SMC_POWER_PROFILE_COMPUTE && @@ -962,7 +962,7 @@ static int pp_dpm_switch_power_profile(void *handle, } if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c index 1d829402cd..f4bd8e9357 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c @@ -269,7 +269,7 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set struct pp_power_state *new_ps) { uint32_t index; - long workload; + long workload[1]; if (hwmgr->not_vf) { if (!skip_display_settings) @@ -294,10 +294,10 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) { index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; - if (hwmgr->power_profile_mode != workload && hwmgr->hwmgr_func->set_power_profile_mode) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + if (hwmgr->power_profile_mode != workload[0] && hwmgr->hwmgr_func->set_power_profile_mode) + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); } return 0; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 1fcd445100..f1c369945a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2957,6 +2957,7 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr) static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { + struct amdgpu_device *adev = hwmgr->adev; struct smu7_hwmgr *data; int result = 0; @@ -2993,40 +2994,37 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) /* Initalize Dynamic State Adjustment Rule Settings */ result = phm_initializa_dynamic_state_adjustment_rule_settings(hwmgr); - if (0 == result) { - struct amdgpu_device *adev = hwmgr->adev; + if (result) + goto fail; - data->is_tlu_enabled = false; + data->is_tlu_enabled = false; - hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = + hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = SMU7_MAX_HARDWARE_POWERLEVELS; - hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; - hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; + hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; + hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; - data->pcie_gen_cap = adev->pm.pcie_gen_mask; - if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) - data->pcie_spc_cap = 20; - else - data->pcie_spc_cap = 16; - data->pcie_lane_cap = adev->pm.pcie_mlw_mask; - - hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ -/* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ - hwmgr->platform_descriptor.clockStep.engineClock = 500; - hwmgr->platform_descriptor.clockStep.memoryClock = 500; - smu7_thermal_parameter_init(hwmgr); - } else { - /* Ignore return value in here, we are cleaning up a mess. */ - smu7_hwmgr_backend_fini(hwmgr); - } + data->pcie_gen_cap = adev->pm.pcie_gen_mask; + if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + data->pcie_spc_cap = 20; + else + data->pcie_spc_cap = 16; + data->pcie_lane_cap = adev->pm.pcie_mlw_mask; + + hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ + /* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ + hwmgr->platform_descriptor.clockStep.engineClock = 500; + hwmgr->platform_descriptor.clockStep.memoryClock = 500; + smu7_thermal_parameter_init(hwmgr); result = smu7_update_edc_leakage_table(hwmgr); - if (result) { - smu7_hwmgr_backend_fini(hwmgr); - return result; - } + if (result) + goto fail; return 0; +fail: + smu7_hwmgr_backend_fini(hwmgr); + return result; } static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr) @@ -3316,8 +3314,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct smu7_power_state *smu7_ps = - cast_phw_smu7_power_state(&request_ps->hardware); + struct smu7_power_state *smu7_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3334,6 +3331,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t latency; bool latency_allowed = false; + smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware); + if (!smu7_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); data->mclk_ignore_signal = false; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index b015a601b3..eb744401e0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1065,16 +1065,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, struct pp_power_state *prequest_ps, const struct pp_power_state *pcurrent_ps) { - struct smu8_power_state *smu8_ps = - cast_smu8_power_state(&prequest_ps->hardware); - - const struct smu8_power_state *smu8_current_ps = - cast_const_smu8_power_state(&pcurrent_ps->hardware); - + struct smu8_power_state *smu8_ps; + const struct smu8_power_state *smu8_current_ps; struct smu8_hwmgr *data = hwmgr->backend; struct PP_Clocks clocks = {0, 0, 0, 0}; bool force_high; + smu8_ps = cast_smu8_power_state(&prequest_ps->hardware); + smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware); + + if (!smu8_ps || !smu8_current_ps) + return -EINVAL; + smu8_ps->need_dfs_bypass = true; data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 9f5bd998c6..f4acdb2267 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3259,8 +3259,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct vega10_power_state *vega10_ps = - cast_phw_vega10_power_state(&request_ps->hardware); + struct vega10_power_state *vega10_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3278,6 +3277,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; uint32_t latency; + vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware); + if (!vega10_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); @@ -3415,13 +3418,17 @@ static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, co const struct vega10_power_state *vega10_ps = cast_const_phw_vega10_power_state(states->pnew_state); struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table); - uint32_t sclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].gfx_clock; struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); - uint32_t mclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].mem_clock; + uint32_t sclk, mclk; uint32_t i; + if (vega10_ps == NULL) + return -EINVAL; + sclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].gfx_clock; + mclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].mem_clock; + for (i = 0; i < sclk_table->count; i++) { if (sclk == sclk_table->dpm_levels[i].value) break; @@ -3728,6 +3735,9 @@ static int vega10_generate_dpm_level_enable_mask( cast_const_phw_vega10_power_state(states->pnew_state); int i; + if (vega10_ps == NULL) + return -EINVAL; + PP_ASSERT_WITH_CODE(!vega10_trim_dpm_states(hwmgr, vega10_ps), "Attempt to Trim DPM States Failed!", return -1); @@ -4995,6 +5005,8 @@ static int vega10_check_states_equal(struct pp_hwmgr *hwmgr, vega10_psa = cast_const_phw_vega10_power_state(pstate1); vega10_psb = cast_const_phw_vega10_power_state(pstate2); + if (vega10_psa == NULL || vega10_psb == NULL) + return -EINVAL; /* If the two states don't even have the same number of performance levels * they cannot be the same state. @@ -5128,6 +5140,8 @@ static int vega10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].gfx_clock = @@ -5179,6 +5193,8 @@ static int vega10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].mem_clock = @@ -5420,6 +5436,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) return; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5442,6 +5461,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) ps = (struct pp_power_state *)((unsigned long)(hwmgr->ps) + hwmgr->ps_size * (hwmgr->num_ps - 1)); vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5632,6 +5654,8 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_ return -EINVAL; vega10_ps = cast_const_phw_vega10_power_state(state); + if (vega10_ps == NULL) + return -EINVAL; i = index > vega10_ps->performance_level_count - 1 ? vega10_ps->performance_level_count - 1 : index; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index e1796ecf9c..06409133b0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2220,7 +2220,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, { int ret = 0; int index = 0; - long workload; + long workload[1]; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); if (!skip_display_settings) { @@ -2260,10 +2260,10 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) { index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; - if (smu->power_profile_mode != workload) - smu_bump_power_profile_mode(smu, &workload, 0); + if (smu->power_profile_mode != workload[0]) + smu_bump_power_profile_mode(smu, workload, 0); } return ret; @@ -2313,7 +2313,7 @@ static int smu_switch_power_profile(void *handle, { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - long workload; + long workload[1]; uint32_t index; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2326,17 +2326,17 @@ static int smu_switch_power_profile(void *handle, smu->workload_mask &= ~(1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } else { smu->workload_mask |= (1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL && smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) - smu_bump_power_profile_mode(smu, &workload, 0); + smu_bump_power_profile_mode(smu, workload, 0); return 0; } diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index 6a4f20fccf..7b0bc9704e 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -1027,7 +1027,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, u32 status_reg; u8 *buffer = msg->buffer; unsigned int i; - int num_transferred = 0; int ret; /* Buffer size of AUX CH is 16 bytes */ @@ -1079,7 +1078,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = buffer[i]; writel(reg, dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); - num_transferred++; } } @@ -1127,7 +1125,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = readl(dp->reg_base + ANALOGIX_DP_BUF_DATA_0 + 4 * i); buffer[i] = (unsigned char)reg; - num_transferred++; } } @@ -1144,7 +1141,7 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, (msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_READ) msg->reply = DP_AUX_NATIVE_REPLY_ACK; - return num_transferred > 0 ? num_transferred : -EBUSY; + return msg->size; aux_error: /* if aux err happen, reset aux */ diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 68831f4e50..fc2ceae61d 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -4069,6 +4069,7 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { const struct drm_dp_connection_status_notify *conn_stat = &up_req->msg.u.conn_stat; + bool handle_csn; drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", conn_stat->port_number, @@ -4077,6 +4078,16 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) conn_stat->message_capability_status, conn_stat->input_port, conn_stat->peer_device_type); + + mutex_lock(&mgr->probe_lock); + handle_csn = mgr->mst_primary->link_address_sent; + mutex_unlock(&mgr->probe_lock); + + if (!handle_csn) { + drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it."); + kfree(up_req); + goto out; + } } else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { const struct drm_dp_resource_status_notify *res_stat = &up_req->msg.u.resource_stat; diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 02b1235c6d..106292d6ed 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1067,23 +1067,16 @@ int drm_atomic_set_property(struct drm_atomic_state *state, } if (async_flip && - prop != config->prop_fb_id && - prop != config->prop_in_fence_fd && - prop != config->prop_fb_damage_clips) { + (plane_state->plane->type != DRM_PLANE_TYPE_PRIMARY || + (prop != config->prop_fb_id && + prop != config->prop_in_fence_fd && + prop != config->prop_fb_damage_clips))) { ret = drm_atomic_plane_get_property(plane, plane_state, prop, &old_val); ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop); break; } - if (async_flip && plane_state->plane->type != DRM_PLANE_TYPE_PRIMARY) { - drm_dbg_atomic(prop->dev, - "[OBJECT:%d] Only primary planes can be changed during async flip\n", - obj->id); - ret = -EINVAL; - break; - } - ret = drm_atomic_plane_set_property(plane, plane_state, file_priv, prop, prop_value); diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 31af5cf37a..cee5eafbfb 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -880,6 +880,11 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, kfree(modeset->mode); modeset->mode = drm_mode_duplicate(dev, mode); + if (!modeset->mode) { + ret = -ENOMEM; + break; + } + drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; modeset->x = offset->x; diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index 071668bfe5..6c33331367 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -1449,6 +1449,9 @@ bxt_setup_backlight(struct intel_connector *connector, enum pipe unused) static int cnp_num_backlight_controllers(struct drm_i915_private *i915) { + if (INTEL_PCH_TYPE(i915) >= PCH_MTL) + return 2; + if (INTEL_PCH_TYPE(i915) >= PCH_DG1) return 1; diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c index 0ccbf9a859..eca07436d1 100644 --- a/drivers/gpu/drm/i915/display/intel_pps.c +++ b/drivers/gpu/drm/i915/display/intel_pps.c @@ -351,6 +351,9 @@ static int intel_num_pps(struct drm_i915_private *i915) if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) return 2; + if (INTEL_PCH_TYPE(i915) >= PCH_MTL) + return 2; + if (INTEL_PCH_TYPE(i915) >= PCH_DG1) return 1; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index a2195e28b6..cac6d41845 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -290,6 +290,41 @@ out: return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->gtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -302,14 +337,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = to_gt(i915)->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -402,12 +441,14 @@ retry: if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->gtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; @@ -1084,6 +1125,8 @@ int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma mmo = mmap_offset_attach(obj, mmap_type, NULL); if (IS_ERR(mmo)) return PTR_ERR(mmo); + + vma->vm_pgoff += drm_vma_node_start(&mmo->vma_node); } /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index e6f177183c..5c72462d1f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -165,7 +165,6 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj, i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] : obj->mm.region, &places[0], obj->bo_offset, obj->base.size, flags); - places[0].flags |= TTM_PL_FLAG_DESIRED; /* Cache this on object? */ for (i = 0; i < num_allowed; ++i) { @@ -779,13 +778,16 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, .interruptible = true, .no_wait_gpu = false, }; - int real_num_busy; + struct ttm_placement initial_placement; + struct ttm_place initial_place; int ret; /* First try only the requested placement. No eviction. */ - real_num_busy = placement->num_placement; - placement->num_placement = 1; - ret = ttm_bo_validate(bo, placement, &ctx); + initial_placement.num_placement = 1; + memcpy(&initial_place, placement->placement, sizeof(struct ttm_place)); + initial_place.flags |= TTM_PL_FLAG_DESIRED; + initial_placement.placement = &initial_place; + ret = ttm_bo_validate(bo, &initial_placement, &ctx); if (ret) { ret = i915_ttm_err_to_gem(ret); /* @@ -800,7 +802,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj, * If the initial attempt fails, allow all accepted placements, * evicting if necessary. */ - placement->num_placement = real_num_busy; ret = ttm_bo_validate(bo, placement, &ctx); if (ret) return i915_ttm_err_to_gem(ret); diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c index 739c865b55..10bce18b7c 100644 --- a/drivers/gpu/drm/lima/lima_drv.c +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -501,3 +501,4 @@ module_platform_driver(lima_platform_driver); MODULE_AUTHOR("Lima Project Developers"); MODULE_DESCRIPTION("Lima DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c index 423eb302be..4caeb68f30 100644 --- a/drivers/gpu/drm/mgag200/mgag200_i2c.c +++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c @@ -31,6 +31,8 @@ #include <linux/i2c.h> #include <linux/pci.h> +#include <drm/drm_managed.h> + #include "mgag200_drv.h" static int mga_i2c_read_gpio(struct mga_device *mdev) @@ -86,7 +88,7 @@ static int mga_gpio_getscl(void *data) return (mga_i2c_read_gpio(mdev) & i2c->clock) ? 1 : 0; } -static void mgag200_i2c_release(void *res) +static void mgag200_i2c_release(struct drm_device *dev, void *res) { struct mga_i2c_chan *i2c = res; @@ -114,7 +116,7 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) i2c->adapter.algo_data = &i2c->bit; i2c->bit.udelay = 10; - i2c->bit.timeout = 2; + i2c->bit.timeout = usecs_to_jiffies(2200); i2c->bit.data = i2c; i2c->bit.setsda = mga_gpio_setsda; i2c->bit.setscl = mga_gpio_setscl; @@ -125,5 +127,5 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) if (ret) return ret; - return devm_add_action_or_reset(dev->dev, mgag200_i2c_release, i2c); + return drmm_add_action_or_reset(dev, mgag200_i2c_release, i2c); } diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index b7f22597ee..969a8fb0ee 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -439,7 +439,7 @@ typedef struct _StateArray{ //how many states we have UCHAR ucNumEntries; - ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries); + ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */; }StateArray; diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index 91202e40cd..60c6527827 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -102,6 +102,17 @@ static void drm_gem_shmem_test_obj_create_private(struct kunit *test) sg_init_one(sgt->sgl, buf, TEST_SIZE); + /* + * Set the DMA mask to 64-bits and map the sgtables + * otherwise drm_gem_shmem_free will cause a warning + * on debug kernels. + */ + ret = dma_set_mask(drm_dev->dev, DMA_BIT_MASK(64)); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = dma_map_sgtable(drm_dev->dev, sgt, DMA_BIDIRECTIONAL, 0); + KUNIT_ASSERT_EQ(test, ret, 0); + /* Init a mock DMA-BUF */ buf_mock.size = TEST_SIZE; attach_mock.dmabuf = &buf_mock; diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index af71b87d80..03c6d4d50a 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -44,9 +44,10 @@ #define GSCCS_RING_BASE 0x11a000 #define RING_TAIL(base) XE_REG((base) + 0x30) +#define TAIL_ADDR REG_GENMASK(20, 3) #define RING_HEAD(base) XE_REG((base) + 0x34) -#define HEAD_ADDR 0x001FFFFC +#define HEAD_ADDR REG_GENMASK(20, 2) #define RING_START(base) XE_REG((base) + 0x38) @@ -135,7 +136,6 @@ #define RING_VALID_MASK 0x00000001 #define RING_VALID 0x00000001 #define STOP_RING REG_BIT(8) -#define TAIL_ADDR 0x001FFFF8 #define RING_CTX_TIMESTAMP(base) XE_REG((base) + 0x3a8) #define CSBE_DEBUG_STATUS(base) XE_REG((base) + 0x3fc) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index e4e3658e6a..0f42971ff0 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1429,8 +1429,8 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q) !xe_sched_job_completed(job)) || xe_sched_invalidate_job(job, 2)) { trace_xe_sched_job_ban(job); - xe_sched_tdr_queue_imm(&q->guc->sched); set_exec_queue_banned(q); + xe_sched_tdr_queue_imm(&q->guc->sched); } } } diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 453e601ddd..d37f1dea9f 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -200,9 +200,10 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, int channel, long va PKG_PWR_LIM_1_EN, 0, channel); if (reg_val & PKG_PWR_LIM_1_EN) { + drm_warn(>_to_xe(hwmon->gt)->drm, "PL1 disable is not supported!\n"); ret = -EOPNOTSUPP; - goto unlock; } + goto unlock; } /* Computation in 64-bits to avoid overflow. Round to nearest. */ diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 615bbc372a..d7bf7bc9dc 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1354,7 +1354,10 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc) if (!snapshot) return NULL; - snapshot->context_desc = lower_32_bits(xe_lrc_ggtt_addr(lrc)); + if (lrc->bo && lrc->bo->vm) + xe_vm_get(lrc->bo->vm); + + snapshot->context_desc = xe_lrc_ggtt_addr(lrc); snapshot->head = xe_lrc_ring_head(lrc); snapshot->tail.internal = lrc->ring.tail; snapshot->tail.memory = xe_lrc_read_ctx_reg(lrc, CTX_RING_TAIL); @@ -1370,12 +1373,14 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc) void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot) { struct xe_bo *bo; + struct xe_vm *vm; struct iosys_map src; if (!snapshot) return; bo = snapshot->lrc_bo; + vm = bo->vm; snapshot->lrc_bo = NULL; snapshot->lrc_snapshot = kvmalloc(snapshot->lrc_size, GFP_KERNEL); @@ -1395,6 +1400,8 @@ void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot) dma_resv_unlock(bo->ttm.base.resv); put_bo: xe_bo_put(bo); + if (vm) + xe_vm_put(vm); } void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer *p) @@ -1440,7 +1447,13 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot) return; kvfree(snapshot->lrc_snapshot); - if (snapshot->lrc_bo) + if (snapshot->lrc_bo) { + struct xe_vm *vm; + + vm = snapshot->lrc_bo->vm; xe_bo_put(snapshot->lrc_bo); + if (vm) + xe_vm_put(vm); + } kfree(snapshot); } diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c index 7d50c6e89d..5b243b7feb 100644 --- a/drivers/gpu/drm/xe/xe_preempt_fence.c +++ b/drivers/gpu/drm/xe/xe_preempt_fence.c @@ -23,11 +23,19 @@ static void preempt_fence_work_func(struct work_struct *w) q->ops->suspend_wait(q); dma_fence_signal(&pfence->base); - dma_fence_end_signalling(cookie); - + /* + * Opt for keep everything in the fence critical section. This looks really strange since we + * have just signalled the fence, however the preempt fences are all signalled via single + * global ordered-wq, therefore anything that happens in this callback can easily block + * progress on the entire wq, which itself may prevent other published preempt fences from + * ever signalling. Therefore try to keep everything here in the callback in the fence + * critical section. For example if something below grabs a scary lock like vm->lock, + * lockdep should complain since we also hold that lock whilst waiting on preempt fences to + * complete. + */ xe_vm_queue_rebind_worker(q->vm); - xe_exec_queue_put(q); + dma_fence_end_signalling(cookie); } static const char * diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c index fb44cc7521..10326bd1bf 100644 --- a/drivers/gpu/drm/xe/xe_rtp.c +++ b/drivers/gpu/drm/xe/xe_rtp.c @@ -200,7 +200,7 @@ static void rtp_mark_active(struct xe_device *xe, if (first == last) bitmap_set(ctx->active_entries, first, 1); else - bitmap_set(ctx->active_entries, first, last - first + 2); + bitmap_set(ctx->active_entries, first, last - first + 1); } /** diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index 65f1f16282..2bfff99845 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -263,7 +263,7 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync) if (sync->fence) dma_fence_put(sync->fence); if (sync->chain_fence) - dma_fence_put(&sync->chain_fence->base); + dma_fence_chain_free(sync->chain_fence); if (sync->ufence) user_fence_put(sync->ufence); } |