diff options
Diffstat (limited to 'drivers/gpu')
24 files changed, 198 insertions, 90 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 087afab67e22..cab1ebaf6d62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -81,7 +81,6 @@ MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/vangogh_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 619d34c041ee..346963e3cf73 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -119,6 +119,8 @@ #define mmVGT_ESGS_RING_SIZE_Vangogh_BASE_IDX 1 #define mmSPI_CONFIG_CNTL_Vangogh 0x2440 #define mmSPI_CONFIG_CNTL_Vangogh_BASE_IDX 1 +#define mmGCR_GENERAL_CNTL_Vangogh 0x1580 +#define mmGCR_GENERAL_CNTL_Vangogh_BASE_IDX 0 #define mmCP_HYP_PFP_UCODE_ADDR 0x5814 #define mmCP_HYP_PFP_UCODE_ADDR_BASE_IDX 1 @@ -3244,7 +3246,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000142), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index 07104a1de308..1961745e89c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -491,12 +491,11 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, { uint32_t def, data, def1, data1; - def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); + def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) { - data |= MM_ATC_L2_MISC_CG__ENABLE_MASK; - + data &= ~MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK; data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | @@ -505,8 +504,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK); } else { - data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK; - + data |= MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK; data1 |= (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | @@ -516,7 +514,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, } if (def != data) - WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data); + WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data); if (def1 != data1) WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2, data1); } @@ -525,17 +523,44 @@ static void mmhub_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev, bool enable) { - uint32_t def, data; - - def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) - data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; - else - data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; + uint32_t def, data, def1, data1, def2, data2; + + def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); + def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL); + def2 = data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL); + + if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) { + data &= ~MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK; + data1 &= !(DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + data2 &= !(DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + } else { + data |= MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK; + data1 |= (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + data2 |= (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + } if (def != data) - WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data); + WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data); + if (def1 != data1) + WREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL, data1); + if (def2 != data2) + WREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL, data2); } static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev, @@ -554,26 +579,39 @@ static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev, static void mmhub_v2_3_get_clockgating(struct amdgpu_device *adev, u32 *flags) { - int data, data1; + int data, data1, data2, data3; if (amdgpu_sriov_vf(adev)) *flags = 0; - data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); - data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); + data = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); + data1 = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); + data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL); + data3 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL); /* AMD_CG_SUPPORT_MC_MGCG */ - if ((data & MM_ATC_L2_MISC_CG__ENABLE_MASK) && - !(data1 & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | + if (!(data & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_TLBWR_CG_MASK | - DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK))) - *flags |= AMD_CG_SUPPORT_MC_MGCG; + DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK)) + && !(data1 & MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK)) { + *flags |= AMD_CG_SUPPORT_MC_MGCG; + } /* AMD_CG_SUPPORT_MC_LS */ - if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK) + if (!(data1 & MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK) + && !(data2 & (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK)) + && !(data3 & (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK))) *flags |= AMD_CG_SUPPORT_MC_LS; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 5b466f440d67..ab98c259ef69 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -251,6 +251,7 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base, struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu; bool force_reset = false; bool update_uclk = false; + bool p_state_change_support; if (dc->work_arounds.skip_clock_update || !clk_mgr->smu_present) return; @@ -291,8 +292,9 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz; clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support; - if (should_update_pstate_support(safe_to_lower, new_clocks->p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { - clk_mgr_base->clks.p_state_change_support = new_clocks->p_state_change_support; + p_state_change_support = new_clocks->p_state_change_support || (display_count == 0); + if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { + clk_mgr_base->clks.p_state_change_support = p_state_change_support; /* to disable P-State switching, set UCLK min = max */ if (!clk_mgr_base->clks.p_state_change_support) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 1bd1a0935290..f95bade59624 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2399,6 +2399,9 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting initial_link_setting; uint32_t link_bw; + if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap)) + return false; + /* search for the minimum link setting that: * 1. is supported according to the link training result * 2. could support the b/w requested by the timing @@ -3045,14 +3048,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link) + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) core_link_disable_stream(pipe_ctx); } for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link) + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) core_link_enable_stream(link->dc->current_state, pipe_ctx); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index cfc130e2d6fd..017b67b830e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -647,8 +647,13 @@ static void power_on_plane( if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - hws->funcs.dpp_pg_control(hws, plane_id, true); - hws->funcs.hubp_pg_control(hws, plane_id, true); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, plane_id, true); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, plane_id, true); + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); DC_LOG_DEBUG( @@ -1082,8 +1087,13 @@ void dcn10_plane_atomic_power_down(struct dc *dc, if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - hws->funcs.dpp_pg_control(hws, dpp->inst, false); - hws->funcs.hubp_pg_control(hws, hubp->inst, false); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, dpp->inst, false); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, hubp->inst, false); + dpp->funcs->dpp_reset(dpp); REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index cb822df21b7c..480d928cb1ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1062,8 +1062,13 @@ static void dcn20_power_on_plane( if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - dcn20_dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true); - dcn20_hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true); + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); DC_LOG_DEBUG( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index e04ecf0fc0db..5ed18cac57e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2517,8 +2517,7 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc, * if this primary pipe has a bottom pipe in prev. state * and if the bottom pipe is still available (which it should be), * pick that pipe as secondary - * Same logic applies for ODM pipes. Since mpo is not allowed with odm - * check in else case. + * Same logic applies for ODM pipes */ if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe) { preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe->pipe_idx; @@ -2526,7 +2525,9 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc, secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx]; secondary_pipe->pipe_idx = preferred_pipe_idx; } - } else if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) { + } + if (secondary_pipe == NULL && + dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) { preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe->pipe_idx; if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) { secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 1c88d2edd381..b000b43a820d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 23.84, + .dram_clock_change_latency_us = 11.72, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index f743685a20e8..9a9697038016 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1121,7 +1121,7 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, static int renoir_gfx_state_change_set(struct smu_context *smu, uint32_t state) { - return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GpuChangeState, state, NULL); + return 0; } static const struct pptable_funcs renoir_ppt_funcs = { diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index ba1507036f26..4a8cbec832bc 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -3021,7 +3021,7 @@ int drm_atomic_helper_set_config(struct drm_mode_set *set, ret = handle_conflicting_encoders(state, true); if (ret) - return ret; + goto fail; ret = drm_atomic_commit(state); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 02ca22e90290..0b232a73c1b7 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -387,9 +387,16 @@ static int drm_gem_vram_kmap_locked(struct drm_gem_vram_object *gbo, if (gbo->vmap_use_count > 0) goto out; - ret = ttm_bo_vmap(&gbo->bo, &gbo->map); - if (ret) - return ret; + /* + * VRAM helpers unmap the BO only on demand. So the previous + * page mapping might still be around. Only vmap if the there's + * no mapping present. + */ + if (dma_buf_map_is_null(&gbo->map)) { + ret = ttm_bo_vmap(&gbo->bo, &gbo->map); + if (ret) + return ret; + } out: ++gbo->vmap_use_count; @@ -577,6 +584,7 @@ static void drm_gem_vram_bo_driver_move_notify(struct drm_gem_vram_object *gbo, return; ttm_bo_vunmap(bo, &gbo->map); + dma_buf_map_clear(&gbo->map); /* explicitly clear mapping for next vmap call */ } static int drm_gem_vram_bo_driver_move(struct drm_gem_vram_object *gbo, diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 6e74e6745eca..349146049849 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -388,19 +388,18 @@ int drm_syncobj_find_fence(struct drm_file *file_private, return -ENOENT; *fence = drm_syncobj_fence_get(syncobj); - drm_syncobj_put(syncobj); if (*fence) { ret = dma_fence_chain_find_seqno(fence, point); if (!ret) - return 0; + goto out; dma_fence_put(*fence); } else { ret = -EINVAL; } if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)) - return ret; + goto out; memset(&wait, 0, sizeof(wait)); wait.task = current; @@ -432,6 +431,9 @@ int drm_syncobj_find_fence(struct drm_file *file_private, if (wait.node.next) drm_syncobj_remove_wait(syncobj, &wait); +out: + drm_syncobj_put(syncobj); + return ret; } EXPORT_SYMBOL(drm_syncobj_find_fence); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 92940a0c5ef8..d5ace48b1ace 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3725,7 +3725,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, intel_ddi_init_dp_buf_reg(encoder, crtc_state); if (!is_mst) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); - intel_dp_configure_protocol_converter(intel_dp); + intel_dp_configure_protocol_converter(intel_dp, crtc_state); intel_dp_sink_set_decompression_state(intel_dp, crtc_state, true); intel_dp_sink_set_fec_ready(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 37f1a10fd021..09123e8625c4 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4014,7 +4014,8 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp, intel_de_posting_read(dev_priv, intel_dp->output_reg); } -void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp) +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 tmp; @@ -4033,8 +4034,8 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp) drm_dbg_kms(&i915->drm, "Failed to set protocol converter HDMI mode to %s\n", enableddisabled(intel_dp->has_hdmi_sink)); - tmp = intel_dp->dfp.ycbcr_444_to_420 ? - DP_CONVERSION_TO_YCBCR420_ENABLE : 0; + tmp = crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444 && + intel_dp->dfp.ycbcr_444_to_420 ? DP_CONVERSION_TO_YCBCR420_ENABLE : 0; if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_PROTOCOL_CONVERTER_CONTROL_1, tmp) != 1) @@ -4088,7 +4089,7 @@ static void intel_enable_dp(struct intel_atomic_state *state, } intel_dp_set_power(intel_dp, DP_SET_POWER_D0); - intel_dp_configure_protocol_converter(intel_dp); + intel_dp_configure_protocol_converter(intel_dp, pipe_config); intel_dp_start_link_train(intel_dp, pipe_config); intel_dp_stop_link_train(intel_dp, pipe_config); diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index b871a09b6901..05f7ddf7a795 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -51,7 +51,8 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx); void intel_dp_set_power(struct intel_dp *intel_dp, u8 mode); -void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp); +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state); void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, bool enable); diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index b2a4bbcfdcd2..b9d8825e2bb1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -2210,6 +2210,7 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, if (content_protection_type_changed) { mutex_lock(&hdcp->mutex); hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; + drm_connector_get(&connector->base); schedule_work(&hdcp->prop_work); mutex_unlock(&hdcp->mutex); } @@ -2221,6 +2222,14 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, desired_and_not_enabled = hdcp->value != DRM_MODE_CONTENT_PROTECTION_ENABLED; mutex_unlock(&hdcp->mutex); + /* + * If HDCP already ENABLED and CP property is DESIRED, schedule + * prop_work to update correct CP property to user space. + */ + if (!desired_and_not_enabled && !content_protection_type_changed) { + drm_connector_get(&connector->base); + schedule_work(&hdcp->prop_work); + } } if (desired_and_not_enabled || content_protection_type_changed) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index a24cc1ff08a0..0625cbb3b431 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -134,11 +134,6 @@ static bool remove_signaling_context(struct intel_breadcrumbs *b, return true; } -static inline bool __request_completed(const struct i915_request *rq) -{ - return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); -} - __maybe_unused static bool check_signal_order(struct intel_context *ce, struct i915_request *rq) { @@ -257,7 +252,7 @@ static void signal_irq_work(struct irq_work *work) list_for_each_entry_rcu(rq, &ce->signals, signal_link) { bool release; - if (!__request_completed(rq)) + if (!__i915_request_is_complete(rq)) break; if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, @@ -379,7 +374,7 @@ static void insert_breadcrumb(struct i915_request *rq) * straight onto a signaled list, and queue the irq worker for * its signal completion. */ - if (__request_completed(rq)) { + if (__i915_request_is_complete(rq)) { if (__signal_request(rq) && llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7614a3d24fca..26c7d0a50585 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -3988,6 +3988,9 @@ err: static void lrc_destroy_wa_ctx(struct intel_engine_cs *engine) { i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0); + + /* Called on error unwind, clear all flags to prevent further use */ + memset(&engine->wa_ctx, 0, sizeof(engine->wa_ctx)); } typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch); diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 7ea94d201fe6..8015964043eb 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -126,6 +126,10 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) struct intel_timeline_cacheline *cl = container_of(rcu, typeof(*cl), rcu); + /* Must wait until after all *rq->hwsp are complete before removing */ + i915_gem_object_unpin_map(cl->hwsp->vma->obj); + __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); + i915_active_fini(&cl->active); kfree(cl); } @@ -133,11 +137,6 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) { GEM_BUG_ON(!i915_active_is_idle(&cl->active)); - - i915_gem_object_unpin_map(cl->hwsp->vma->obj); - i915_vma_put(cl->hwsp->vma); - __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); - call_rcu(&cl->rcu, __rcu_cacheline_free); } @@ -179,7 +178,6 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) return ERR_CAST(vaddr); } - i915_vma_get(hwsp->vma); cl->hwsp = hwsp; cl->vaddr = page_pack_bits(vaddr, cacheline); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d76685ce0399..9856479b56d8 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -184,13 +184,24 @@ static u64 get_rc6(struct intel_gt *gt) return val; } -static void park_rc6(struct drm_i915_private *i915) +static void init_rc6(struct i915_pmu *pmu) { - struct i915_pmu *pmu = &i915->pmu; + struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); + intel_wakeref_t wakeref; - if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY)) + with_intel_runtime_pm(i915->gt.uncore->rpm, wakeref) { pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); + pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = + pmu->sample[__I915_SAMPLE_RC6].cur; + pmu->sleep_last = ktime_get(); + } +} +static void park_rc6(struct drm_i915_private *i915) +{ + struct i915_pmu *pmu = &i915->pmu; + + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); pmu->sleep_last = ktime_get(); } @@ -201,6 +212,7 @@ static u64 get_rc6(struct intel_gt *gt) return __get_rc6(gt); } +static void init_rc6(struct i915_pmu *pmu) { } static void park_rc6(struct drm_i915_private *i915) {} #endif @@ -612,10 +624,8 @@ static void i915_pmu_enable(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); unsigned int bit = event_enabled_bit(event); struct i915_pmu *pmu = &i915->pmu; - intel_wakeref_t wakeref; unsigned long flags; - wakeref = intel_runtime_pm_get(&i915->runtime_pm); spin_lock_irqsave(&pmu->lock, flags); /* @@ -626,13 +636,6 @@ static void i915_pmu_enable(struct perf_event *event) GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count)); GEM_BUG_ON(pmu->enable_count[bit] == ~0); - if (pmu->enable_count[bit] == 0 && - config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) { - pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0; - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); - pmu->sleep_last = ktime_get(); - } - pmu->enable |= BIT_ULL(bit); pmu->enable_count[bit]++; @@ -673,8 +676,6 @@ static void i915_pmu_enable(struct perf_event *event) * an existing non-zero value. */ local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); - - intel_runtime_pm_put(&i915->runtime_pm, wakeref); } static void i915_pmu_disable(struct perf_event *event) @@ -1130,6 +1131,7 @@ void i915_pmu_register(struct drm_i915_private *i915) hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); pmu->timer.function = i915_sample; pmu->cpuhp.cpu = -1; + init_rc6(pmu); if (!is_igp(i915)) { pmu->name = kasprintf(GFP_KERNEL, diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 620b6fab2c5c..92adfee30c7c 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -434,7 +434,7 @@ static inline u32 hwsp_seqno(const struct i915_request *rq) static inline bool __i915_request_has_started(const struct i915_request *rq) { - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno - 1); + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno - 1); } /** @@ -465,11 +465,19 @@ static inline bool __i915_request_has_started(const struct i915_request *rq) */ static inline bool i915_request_started(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - /* Remember: started but may have since been preempted! */ - return __i915_request_has_started(rq); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + /* Remember: started but may have since been preempted! */ + result = __i915_request_has_started(rq); + rcu_read_unlock(); + + return result; } /** @@ -482,10 +490,16 @@ static inline bool i915_request_started(const struct i915_request *rq) */ static inline bool i915_request_is_running(const struct i915_request *rq) { + bool result; + if (!i915_request_is_active(rq)) return false; - return __i915_request_has_started(rq); + rcu_read_lock(); + result = __i915_request_has_started(rq) && i915_request_is_active(rq); + rcu_read_unlock(); + + return result; } /** @@ -509,12 +523,25 @@ static inline bool i915_request_is_ready(const struct i915_request *rq) return !list_empty(&rq->sched.link); } +static inline bool __i915_request_is_complete(const struct i915_request *rq) +{ + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); +} + static inline bool i915_request_completed(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + result = __i915_request_is_complete(rq); + rcu_read_unlock(); + + return result; } static inline void i915_request_mark_complete(struct i915_request *rq) diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 8cd776adc592..11e0313db0ea 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -79,12 +79,13 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, struct page *p; void *vaddr; - if (order) { - gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + /* Don't set the __GFP_COMP flag for higher order allocations. + * Mapping pages directly into an userspace process and calling + * put_page() on a TTM allocated page is illegal. + */ + if (order) + gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM; - gfp_flags &= ~__GFP_MOVABLE; - gfp_flags &= ~__GFP_COMP; - } if (!pool->use_dma_alloc) { p = alloc_pages(gfp_flags, order); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 555106220578..98cab0bbe92d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1267,6 +1267,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) card->dai_link = dai_link; card->num_links = 1; card->name = vc4_hdmi->variant->card_name; + card->driver_name = "vc4-hdmi"; card->dev = dev; card->owner = THIS_MODULE; |