diff options
Diffstat (limited to 'drivers/gpu')
39 files changed, 415 insertions, 192 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index b8975857d60d..f184cdca938d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1953,8 +1953,24 @@ static void amdgpu_device_fill_reset_magic(struct amdgpu_device *adev) */ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev) { - return !!memcmp(adev->gart.ptr, adev->reset_magic, - AMDGPU_RESET_MAGIC_NUM); + if (memcmp(adev->gart.ptr, adev->reset_magic, + AMDGPU_RESET_MAGIC_NUM)) + return true; + + if (!adev->in_gpu_reset) + return false; + + /* + * For all ASICs with baco/mode1 reset, the VRAM is + * always assumed to be lost. + */ + switch (amdgpu_asic_reset_method(adev)) { + case AMD_RESET_METHOD_BACO: + case AMD_RESET_METHOD_MODE1: + return true; + default: + return false; + } } /** @@ -3309,6 +3325,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + amdgpu_amdkfd_suspend(adev); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 006f21ef7ddf..62635e58e45e 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1358,8 +1358,6 @@ static int cik_asic_reset(struct amdgpu_device *adev) int r; if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); r = amdgpu_dpm_baco_reset(adev); } else { r = cik_asic_pci_config_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 889154a78c4a..73337e658aff 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1158,6 +1158,8 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev) adev->gfx.mec_fw_write_wait = true; break; default: + adev->gfx.me_fw_write_wait = true; + adev->gfx.mec_fw_write_wait = true; break; } } @@ -1173,6 +1175,8 @@ struct amdgpu_gfxoff_quirk { static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { /* https://bugzilla.kernel.org/show_bug.cgi?id=204689 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */ + { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 2d1bebdf1603..cc3a79029376 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -351,8 +351,6 @@ static int nv_asic_reset(struct amdgpu_device *adev) struct smu_context *smu = &adev->smu; if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); ret = smu_baco_enter(smu); if (ret) return ret; @@ -360,8 +358,6 @@ static int nv_asic_reset(struct amdgpu_device *adev) if (ret) return ret; } else { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); ret = nv_asic_mode1_reset(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index d8945c31b622..132a67a041a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -569,14 +569,10 @@ static int soc15_asic_reset(struct amdgpu_device *adev) switch (soc15_asic_reset_method(adev)) { case AMD_RESET_METHOD_BACO: - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); return soc15_asic_baco_reset(adev); case AMD_RESET_METHOD_MODE2: return amdgpu_dpm_mode2_reset(adev); default: - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); return soc15_asic_mode1_reset(adev); } } diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 78b35901643b..3ce10e05d0d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -765,8 +765,6 @@ static int vi_asic_reset(struct amdgpu_device *adev) int r; if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); r = amdgpu_dpm_baco_reset(adev); } else { r = vi_asic_pci_config_reset(adev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 2a9e40131735..0d70cb2248fe 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1104,9 +1104,9 @@ kfd_gtt_out: return 0; kfd_gtt_no_free_chunk: - pr_debug("Allocation failed with mem_obj = %p\n", mem_obj); + pr_debug("Allocation failed with mem_obj = %p\n", *mem_obj); mutex_unlock(&kfd->gtt_sa_lock); - kfree(mem_obj); + kfree(*mem_obj); return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 0acd3409dd6c..3abeff7722e3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -113,10 +113,13 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, if (enable_encryption) { display->adjust.disable = 0; - if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) + if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) { + hdcp_w->link.adjust.hdcp1.disable = 0; hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0; - else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1) + } else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1) { + hdcp_w->link.adjust.hdcp1.disable = 1; hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_1; + } schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS)); @@ -334,6 +337,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw; display->adjust.disable = 1; link->adjust.auth_delay = 2; + link->adjust.hdcp1.disable = 0; hdcp_update_display(hdcp_work, link_index, aconnector, DRM_MODE_HDCP_CONTENT_TYPE0, false); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 9ef3f7b91a1d..abdf29afa2f2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -643,7 +643,7 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params /* Find lowest DPM, FCLK is filled in reverse order*/ for (i = PP_SMU_NUM_FCLK_DPM_LEVELS - 1; i >= 0; i--) { - if (clock_table->FClocks[i].Freq != 0) { + if (clock_table->FClocks[i].Freq != 0 && clock_table->FClocks[i].Vol != 0) { j = i; break; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 04441dbcba76..188e51600070 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -283,6 +283,8 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, int i = 0; bool ret = false; + stream->adjust = *adjust; + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -2347,7 +2349,7 @@ void dc_commit_updates_for_stream(struct dc *dc, enum surface_update_type update_type; struct dc_state *context; struct dc_context *dc_ctx = dc->ctx; - int i; + int i, j; stream_status = dc_stream_get_status(stream); context = dc->current_state; @@ -2385,6 +2387,17 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_surface_update_to_plane(surface, &srf_updates[i]); + if (update_type >= UPDATE_TYPE_MED) { + for (j = 0; j < dc->res_pool->pipe_count; j++) { + struct pipe_ctx *pipe_ctx = + &context->res_ctx.pipe_ctx[j]; + + if (pipe_ctx->plane_state != surface) + continue; + + resource_build_scaling_params(pipe_ctx); + } + } } copy_stream_update_to_stream(dc, context, stream, stream_update); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index bf04cfefb283..662af0f2b0cc 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3804,9 +3804,12 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr, { uint32_t i; + /* force the trim if mclk_switching is disabled to prevent flicker */ + bool force_trim = (low_limit == high_limit); for (i = 0; i < dpm_table->count; i++) { /*skip the trim if od is enabled*/ - if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit + if ((!hwmgr->od_enabled || force_trim) + && (dpm_table->dpm_levels[i].value < low_limit || dpm_table->dpm_levels[i].value > high_limit)) dpm_table->dpm_levels[i].enabled = false; else diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 3ad0f4aa3aa3..f7a1ce37227c 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -240,6 +240,7 @@ static int renoir_print_clk_levels(struct smu_context *smu, uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_t metrics; + bool cur_value_match_level = false; if (!clk_table || clk_type >= SMU_CLK_COUNT) return -EINVAL; @@ -298,8 +299,13 @@ static int renoir_print_clk_levels(struct smu_context *smu, GET_DPM_CUR_FREQ(clk_table, clk_type, i, value); size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, cur_value == value ? "*" : ""); + if (cur_value == value) + cur_value_match_level = true; } + if (!cur_value_match_level) + size += sprintf(buf + size, " %uMhz *\n", cur_value); + return size; } @@ -881,6 +887,17 @@ static int renoir_read_sensor(struct smu_context *smu, return ret; } +static bool renoir_is_dpm_running(struct smu_context *smu) +{ + /* + * Util now, the pmfw hasn't exported the interface of SMU + * feature mask to APU SKU so just force on all the feature + * at early initial stage. + */ + return true; + +} + static const struct pptable_funcs renoir_ppt_funcs = { .get_smu_msg_index = renoir_get_smu_msg_index, .get_smu_clk_index = renoir_get_smu_clk_index, @@ -922,6 +939,7 @@ static const struct pptable_funcs renoir_ppt_funcs = { .mode2_reset = smu_v12_0_mode2_reset, .set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range, .set_driver_table_location = smu_v12_0_set_driver_table_location, + .is_dpm_running = renoir_is_dpm_running, }; void renoir_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h index 2a390ddd37dd..89cd6da118a3 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.h @@ -37,7 +37,7 @@ extern void renoir_set_ppt_funcs(struct smu_context *smu); freq = table->SocClocks[dpm_level].Freq; \ break; \ case SMU_MCLK: \ - freq = table->MemClocks[dpm_level].Freq; \ + freq = table->FClocks[dpm_level].Freq; \ break; \ case SMU_DCEFCLK: \ freq = table->DcfClocks[dpm_level].Freq; \ diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c index 2dfa2fd2a23b..526507102c1e 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c @@ -711,14 +711,14 @@ static int anx6345_i2c_probe(struct i2c_client *client, DRM_DEBUG("No panel found\n"); /* 1.2V digital core power regulator */ - anx6345->dvdd12 = devm_regulator_get(dev, "dvdd12-supply"); + anx6345->dvdd12 = devm_regulator_get(dev, "dvdd12"); if (IS_ERR(anx6345->dvdd12)) { DRM_ERROR("dvdd12-supply not found\n"); return PTR_ERR(anx6345->dvdd12); } /* 2.5V digital core power regulator */ - anx6345->dvdd25 = devm_regulator_get(dev, "dvdd25-supply"); + anx6345->dvdd25 = devm_regulator_get(dev, "dvdd25"); if (IS_ERR(anx6345->dvdd25)) { DRM_ERROR("dvdd25-supply not found\n"); return PTR_ERR(anx6345->dvdd25); diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c index 41867be03751..864423f59d66 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c @@ -722,10 +722,9 @@ static int anx78xx_dp_link_training(struct anx78xx *anx78xx) if (err) return err; - dpcd[0] = drm_dp_max_link_rate(anx78xx->dpcd); - dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]); err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], - SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]); + SP_DP_MAIN_LINK_BW_SET_REG, + anx78xx->dpcd[DP_MAX_LINK_RATE]); if (err) return err; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index ed0fea2ac322..22713ef0eac8 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3504,9 +3504,9 @@ static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8 dp_link_count) int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state) { int ret = 0; - int i = 0; struct drm_dp_mst_branch *mstb = NULL; + mutex_lock(&mgr->payload_lock); mutex_lock(&mgr->lock); if (mst_state == mgr->mst_state) goto out_unlock; @@ -3565,27 +3565,19 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms /* this can fail if the device is gone */ drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0); ret = 0; - mutex_lock(&mgr->payload_lock); - memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload)); + memset(mgr->payloads, 0, + mgr->max_payloads * sizeof(mgr->payloads[0])); + memset(mgr->proposed_vcpis, 0, + mgr->max_payloads * sizeof(mgr->proposed_vcpis[0])); mgr->payload_mask = 0; set_bit(0, &mgr->payload_mask); - for (i = 0; i < mgr->max_payloads; i++) { - struct drm_dp_vcpi *vcpi = mgr->proposed_vcpis[i]; - - if (vcpi) { - vcpi->vcpi = 0; - vcpi->num_slots = 0; - } - mgr->proposed_vcpis[i] = NULL; - } mgr->vcpi_mask = 0; - mutex_unlock(&mgr->payload_lock); - mgr->payload_id_table_cleared = false; } out_unlock: mutex_unlock(&mgr->lock); + mutex_unlock(&mgr->payload_lock); if (mstb) drm_dp_mst_topology_put_mstb(mstb); return ret; @@ -4298,6 +4290,7 @@ int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, if (pos->vcpi) { drm_dp_mst_put_port_malloc(port); pos->vcpi = 0; + pos->pbn = 0; } return 0; diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index f2e43d341980..d16dac4325f9 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -51,8 +51,6 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align) { drm_dma_handle_t *dmah; - unsigned long addr; - size_t sz; /* pci_alloc_consistent only guarantees alignment to the smallest * PAGE_SIZE order which is greater than or equal to the requested size. @@ -68,20 +66,13 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali dmah->size = size; dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size, &dmah->busaddr, - GFP_KERNEL | __GFP_COMP); + GFP_KERNEL); if (dmah->vaddr == NULL) { kfree(dmah); return NULL; } - /* XXX - Is virt_to_page() legal for consistent mem? */ - /* Reserve */ - for (addr = (unsigned long)dmah->vaddr, sz = size; - sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) { - SetPageReserved(virt_to_page((void *)addr)); - } - return dmah; } @@ -94,19 +85,9 @@ EXPORT_SYMBOL(drm_pci_alloc); */ void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah) { - unsigned long addr; - size_t sz; - - if (dmah->vaddr) { - /* XXX - Is virt_to_page() legal for consistent mem? */ - /* Unreserve */ - for (addr = (unsigned long)dmah->vaddr, sz = dmah->size; - sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) { - ClearPageReserved(virt_to_page((void *)addr)); - } + if (dmah->vaddr) dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr, dmah->busaddr); - } } /** diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 1de2cde2277c..282774e469ac 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -962,27 +962,40 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, unsigned count; struct scatterlist *sg; struct page *page; - u32 len, index; + u32 page_len, page_index; dma_addr_t addr; + u32 dma_len, dma_index; - index = 0; + /* + * Scatterlist elements contains both pages and DMA addresses, but + * one shoud not assume 1:1 relation between them. The sg->length is + * the size of the physical memory chunk described by the sg->page, + * while sg_dma_len(sg) is the size of the DMA (IO virtual) chunk + * described by the sg_dma_address(sg). + */ + page_index = 0; + dma_index = 0; for_each_sg(sgt->sgl, sg, sgt->nents, count) { - len = sg_dma_len(sg); + page_len = sg->length; page = sg_page(sg); + dma_len = sg_dma_len(sg); addr = sg_dma_address(sg); - while (len > 0) { - if (WARN_ON(index >= max_entries)) + while (pages && page_len > 0) { + if (WARN_ON(page_index >= max_entries)) return -1; - if (pages) - pages[index] = page; - if (addrs) - addrs[index] = addr; - + pages[page_index] = page; page++; + page_len -= PAGE_SIZE; + page_index++; + } + while (addrs && dma_len > 0) { + if (WARN_ON(dma_index >= max_entries)) + return -1; + addrs[dma_index] = addr; addr += PAGE_SIZE; - len -= PAGE_SIZE; - index++; + dma_len -= PAGE_SIZE; + dma_index++; } } return 0; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c index 8adbf2861bff..e6795bafcbb9 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c @@ -32,6 +32,7 @@ struct etnaviv_pm_domain { }; struct etnaviv_pm_domain_meta { + unsigned int feature; const struct etnaviv_pm_domain *domains; u32 nr_domains; }; @@ -410,36 +411,78 @@ static const struct etnaviv_pm_domain doms_vg[] = { static const struct etnaviv_pm_domain_meta doms_meta[] = { { + .feature = chipFeatures_PIPE_3D, .nr_domains = ARRAY_SIZE(doms_3d), .domains = &doms_3d[0] }, { + .feature = chipFeatures_PIPE_2D, .nr_domains = ARRAY_SIZE(doms_2d), .domains = &doms_2d[0] }, { + .feature = chipFeatures_PIPE_VG, .nr_domains = ARRAY_SIZE(doms_vg), .domains = &doms_vg[0] } }; +static unsigned int num_pm_domains(const struct etnaviv_gpu *gpu) +{ + unsigned int num = 0, i; + + for (i = 0; i < ARRAY_SIZE(doms_meta); i++) { + const struct etnaviv_pm_domain_meta *meta = &doms_meta[i]; + + if (gpu->identity.features & meta->feature) + num += meta->nr_domains; + } + + return num; +} + +static const struct etnaviv_pm_domain *pm_domain(const struct etnaviv_gpu *gpu, + unsigned int index) +{ + const struct etnaviv_pm_domain *domain = NULL; + unsigned int offset = 0, i; + + for (i = 0; i < ARRAY_SIZE(doms_meta); i++) { + const struct etnaviv_pm_domain_meta *meta = &doms_meta[i]; + + if (!(gpu->identity.features & meta->feature)) + continue; + + if (meta->nr_domains < (index - offset)) { + offset += meta->nr_domains; + continue; + } + + domain = meta->domains + (index - offset); + } + + return domain; +} + int etnaviv_pm_query_dom(struct etnaviv_gpu *gpu, struct drm_etnaviv_pm_domain *domain) { - const struct etnaviv_pm_domain_meta *meta = &doms_meta[domain->pipe]; + const unsigned int nr_domains = num_pm_domains(gpu); const struct etnaviv_pm_domain *dom; - if (domain->iter >= meta->nr_domains) + if (domain->iter >= nr_domains) return -EINVAL; - dom = meta->domains + domain->iter; + dom = pm_domain(gpu, domain->iter); + if (!dom) + return -EINVAL; domain->id = domain->iter; domain->nr_signals = dom->nr_signals; strncpy(domain->name, dom->name, sizeof(domain->name)); domain->iter++; - if (domain->iter == meta->nr_domains) + if (domain->iter == nr_domains) domain->iter = 0xff; return 0; @@ -448,14 +491,16 @@ int etnaviv_pm_query_dom(struct etnaviv_gpu *gpu, int etnaviv_pm_query_sig(struct etnaviv_gpu *gpu, struct drm_etnaviv_pm_signal *signal) { - const struct etnaviv_pm_domain_meta *meta = &doms_meta[signal->pipe]; + const unsigned int nr_domains = num_pm_domains(gpu); const struct etnaviv_pm_domain *dom; const struct etnaviv_pm_signal *sig; - if (signal->domain >= meta->nr_domains) + if (signal->domain >= nr_domains) return -EINVAL; - dom = meta->domains + signal->domain; + dom = pm_domain(gpu, signal->domain); + if (!dom) + return -EINVAL; if (signal->iter >= dom->nr_signals) return -EINVAL; diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile index c280b6ae38eb..3b39998b7210 100644 --- a/drivers/gpu/drm/i915/Kconfig.profile +++ b/drivers/gpu/drm/i915/Kconfig.profile @@ -35,6 +35,10 @@ config DRM_I915_PREEMPT_TIMEOUT May be 0 to disable the timeout. + The compiled in default may get overridden at driver probe time on + certain platforms and certain engines which will be reflected in the + sysfs control. + config DRM_I915_SPIN_REQUEST int "Busywait for request completion (us)" default 5 # microseconds diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index d9a61f341070..2fe594952748 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2225,7 +2225,11 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder, return; dig_port = enc_to_dig_port(encoder); - intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); + + if (!intel_phy_is_tc(dev_priv, phy) || + dig_port->tc_mode != TC_PORT_TBT_ALT) + intel_display_power_get(dev_priv, + dig_port->ddi_io_power_domain); /* * AUX power is only needed for (e)DP mode, and for HDMI mode on TC diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index aa453953908b..732db609c897 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -14582,8 +14582,8 @@ static int intel_atomic_check(struct drm_device *dev, /* Catch I915_MODE_FLAG_INHERITED */ for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - if (new_crtc_state->hw.mode.private_flags != - old_crtc_state->hw.mode.private_flags) + if (new_crtc_state->uapi.mode.private_flags != + old_crtc_state->uapi.mode.private_flags) new_crtc_state->uapi.mode_changed = true; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 7643a30ba4cd..2b8681bfecc3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -914,11 +914,13 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) static void reloc_gpu_flush(struct reloc_cache *cache) { - GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32)); + struct drm_i915_gem_object *obj = cache->rq->batch->obj; + + GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32)); cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END; - __i915_gem_object_flush_map(cache->rq->batch->obj, 0, cache->rq_size); - i915_gem_object_unpin_map(cache->rq->batch->obj); + __i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1)); + i915_gem_object_unpin_map(obj); intel_gt_chipset_flush(cache->rq->engine->gt); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 4d1de2d97d5c..9aabc5815d38 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -25,6 +25,30 @@ static u64 gen8_pde_encode(const dma_addr_t addr, return pde; } +static u64 gen8_pte_encode(dma_addr_t addr, + enum i915_cache_level level, + u32 flags) +{ + gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW; + + if (unlikely(flags & PTE_READ_ONLY)) + pte &= ~_PAGE_RW; + + switch (level) { + case I915_CACHE_NONE: + pte |= PPAT_UNCACHED; + break; + case I915_CACHE_WT: + pte |= PPAT_DISPLAY_ELLC; + break; + default: + pte |= PPAT_CACHED; + break; + } + + return pte; +} + static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create) { struct drm_i915_private *i915 = ppgtt->vm.i915; @@ -706,6 +730,8 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt) ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc; ppgtt->vm.clear_range = gen8_ppgtt_clear; + ppgtt->vm.pte_encode = gen8_pte_encode; + if (intel_vgpu_active(gt->i915)) gen8_ppgtt_notify_vgt(ppgtt, true); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 06ff7695fa29..4e8ba1dadb02 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -274,6 +274,7 @@ static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine) static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) { const struct engine_info *info = &intel_engines[id]; + struct drm_i915_private *i915 = gt->i915; struct intel_engine_cs *engine; BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH)); @@ -300,11 +301,11 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) engine->id = id; engine->legacy_idx = INVALID_ENGINE; engine->mask = BIT(id); - engine->i915 = gt->i915; + engine->i915 = i915; engine->gt = gt; engine->uncore = gt->uncore; engine->hw_id = engine->guc_id = info->hw_id; - engine->mmio_base = __engine_mmio_base(gt->i915, info->mmio_bases); + engine->mmio_base = __engine_mmio_base(i915, info->mmio_bases); engine->class = info->class; engine->instance = info->instance; @@ -319,11 +320,15 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) engine->props.timeslice_duration_ms = CONFIG_DRM_I915_TIMESLICE_DURATION; + /* Override to uninterruptible for OpenCL workloads. */ + if (INTEL_GEN(i915) == 12 && engine->class == RENDER_CLASS) + engine->props.preempt_timeout_ms = 0; + engine->context_size = intel_engine_context_size(gt, engine->class); if (WARN_ON(engine->context_size > BIT(20))) engine->context_size = 0; if (engine->context_size) - DRIVER_CAPS(gt->i915)->has_logical_contexts = true; + DRIVER_CAPS(i915)->has_logical_contexts = true; /* Nothing to do here, execute in order of dependencies */ engine->schedule = NULL; @@ -339,7 +344,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) gt->engine_class[info->class][info->instance] = engine; gt->engine[id] = engine; - gt->i915->engine[id] = engine; + i915->engine[id] = engine; return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 531d501be01f..d0d35c55170f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -167,6 +167,13 @@ static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt) intel_gtt_chipset_flush(); } +static u64 gen8_ggtt_pte_encode(dma_addr_t addr, + enum i915_cache_level level, + u32 flags) +{ + return addr | _PAGE_PRESENT; +} + static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte) { writeq(pte, addr); @@ -182,7 +189,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, gen8_pte_t __iomem *pte = (gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE; - gen8_set_pte(pte, gen8_pte_encode(addr, level, 0)); + gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, 0)); ggtt->invalidate(ggtt); } @@ -192,10 +199,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level level, u32 flags) { + const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, 0); struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); - struct sgt_iter sgt_iter; - gen8_pte_t __iomem *gtt_entries; - const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0); + gen8_pte_t __iomem *gte; + gen8_pte_t __iomem *end; + struct sgt_iter iter; dma_addr_t addr; /* @@ -203,10 +211,17 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, * not to allow the user to override access to a read only page. */ - gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm; - gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE; - for_each_sgt_daddr(addr, sgt_iter, vma->pages) - gen8_set_pte(gtt_entries++, pte_encode | addr); + gte = (gen8_pte_t __iomem *)ggtt->gsm; + gte += vma->node.start / I915_GTT_PAGE_SIZE; + end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + + for_each_sgt_daddr(addr, iter, vma->pages) + gen8_set_pte(gte++, pte_encode | addr); + GEM_BUG_ON(gte > end); + + /* Fill the allocated but "unused" space beyond the end of the buffer */ + while (gte < end) + gen8_set_pte(gte++, vm->scratch[0].encode); /* * We want to flush the TLBs only after we're certain all the PTE @@ -242,13 +257,22 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, u32 flags) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); - gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm; - unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE; + gen6_pte_t __iomem *gte; + gen6_pte_t __iomem *end; struct sgt_iter iter; dma_addr_t addr; + gte = (gen6_pte_t __iomem *)ggtt->gsm; + gte += vma->node.start / I915_GTT_PAGE_SIZE; + end = gte + vma->node.size / I915_GTT_PAGE_SIZE; + for_each_sgt_daddr(addr, iter, vma->pages) - iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]); + iowrite32(vm->pte_encode(addr, level, flags), gte++); + GEM_BUG_ON(gte > end); + + /* Fill the allocated but "unused" space beyond the end of the buffer */ + while (gte < end) + iowrite32(vm->scratch[0].encode, gte++); /* * We want to flush the TLBs only after we're certain all the PTE @@ -890,7 +914,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.vma_ops.set_pages = ggtt_set_pages; ggtt->vm.vma_ops.clear_pages = clear_pages; - ggtt->vm.pte_encode = gen8_pte_encode; + ggtt->vm.pte_encode = gen8_ggtt_pte_encode; setup_private_pat(ggtt->vm.gt->uncore); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 16acdc5d6734..f6fcf05d54f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -454,30 +454,6 @@ void gtt_write_workarounds(struct intel_gt *gt) } } -u64 gen8_pte_encode(dma_addr_t addr, - enum i915_cache_level level, - u32 flags) -{ - gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW; - - if (unlikely(flags & PTE_READ_ONLY)) - pte &= ~_PAGE_RW; - - switch (level) { - case I915_CACHE_NONE: - pte |= PPAT_UNCACHED; - break; - case I915_CACHE_WT: - pte |= PPAT_DISPLAY_ELLC; - break; - default: - pte |= PPAT_CACHED; - break; - } - - return pte; -} - static void tgl_setup_private_ppat(struct intel_uncore *uncore) { /* TGL doesn't support LLC or AGE settings */ diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 7da7681c20b1..7db9f3ac9aed 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -515,10 +515,6 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt); void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915); void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915); -u64 gen8_pte_encode(dma_addr_t addr, - enum i915_cache_level level, - u32 flags); - int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p); void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index d2a3d935d186..8accea06185b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -83,7 +83,8 @@ static void rps_enable_interrupts(struct intel_rps *rps) gen6_gt_pm_enable_irq(gt, rps->pm_events); spin_unlock_irq(>->irq_lock); - set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq)); + intel_uncore_write(gt->uncore, + GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq)); } static void gen6_rps_reset_interrupts(struct intel_rps *rps) @@ -117,7 +118,8 @@ static void rps_disable_interrupts(struct intel_rps *rps) rps->pm_events = 0; - set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u)); + intel_uncore_write(gt->uncore, + GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u)); spin_lock_irq(>->irq_lock); gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS); @@ -763,6 +765,19 @@ void intel_rps_park(struct intel_rps *rps) intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA); rps_set(rps, rps->idle_freq, false); intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA); + + /* + * Since we will try and restart from the previously requested + * frequency on unparking, treat this idle point as a downclock + * interrupt and reduce the frequency for resume. If we park/unpark + * more frequently than the rps worker can run, we will not respond + * to any EI and never see a change in frequency. + * + * (Note we accommodate Cherryview's limitation of only using an + * even bin by applying it to all.) + */ + rps->cur_freq = + max_t(int, round_down(rps->cur_freq - 1, 2), rps->min_freq); } void intel_rps_boost(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 3b6b913bd27a..a649b6ca6b26 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2910,49 +2910,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce, } /** - * i915_perf_read_locked - &i915_perf_stream_ops->read with error normalisation - * @stream: An i915 perf stream - * @file: An i915 perf stream file - * @buf: destination buffer given by userspace - * @count: the number of bytes userspace wants to read - * @ppos: (inout) file seek position (unused) - * - * Besides wrapping &i915_perf_stream_ops->read this provides a common place to - * ensure that if we've successfully copied any data then reporting that takes - * precedence over any internal error status, so the data isn't lost. - * - * For example ret will be -ENOSPC whenever there is more buffered data than - * can be copied to userspace, but that's only interesting if we weren't able - * to copy some data because it implies the userspace buffer is too small to - * receive a single record (and we never split records). - * - * Another case with ret == -EFAULT is more of a grey area since it would seem - * like bad form for userspace to ask us to overrun its buffer, but the user - * knows best: - * - * http://yarchive.net/comp/linux/partial_reads_writes.html - * - * Returns: The number of bytes copied or a negative error code on failure. - */ -static ssize_t i915_perf_read_locked(struct i915_perf_stream *stream, - struct file *file, - char __user *buf, - size_t count, - loff_t *ppos) -{ - /* Note we keep the offset (aka bytes read) separate from any - * error status so that the final check for whether we return - * the bytes read with a higher precedence than any error (see - * comment below) doesn't need to be handled/duplicated in - * stream->ops->read() implementations. - */ - size_t offset = 0; - int ret = stream->ops->read(stream, buf, count, &offset); - - return offset ?: (ret ?: -EAGAIN); -} - -/** * i915_perf_read - handles read() FOP for i915 perf stream FDs * @file: An i915 perf stream file * @buf: destination buffer given by userspace @@ -2977,7 +2934,8 @@ static ssize_t i915_perf_read(struct file *file, { struct i915_perf_stream *stream = file->private_data; struct i915_perf *perf = stream->perf; - ssize_t ret; + size_t offset = 0; + int ret; /* To ensure it's handled consistently we simply treat all reads of a * disabled stream as an error. In particular it might otherwise lead @@ -3000,13 +2958,12 @@ static ssize_t i915_perf_read(struct file *file, return ret; mutex_lock(&perf->lock); - ret = i915_perf_read_locked(stream, file, - buf, count, ppos); + ret = stream->ops->read(stream, buf, count, &offset); mutex_unlock(&perf->lock); - } while (ret == -EAGAIN); + } while (!offset && !ret); } else { mutex_lock(&perf->lock); - ret = i915_perf_read_locked(stream, file, buf, count, ppos); + ret = stream->ops->read(stream, buf, count, &offset); mutex_unlock(&perf->lock); } @@ -3017,15 +2974,15 @@ static ssize_t i915_perf_read(struct file *file, * and read() returning -EAGAIN. Clearing the oa.pollin state here * effectively ensures we back off until the next hrtimer callback * before reporting another EPOLLIN event. + * The exception to this is if ops->read() returned -ENOSPC which means + * that more OA data is available than could fit in the user provided + * buffer. In this case we want the next poll() call to not block. */ - if (ret >= 0 || ret == -EAGAIN) { - /* Maybe make ->pollin per-stream state if we support multiple - * concurrent streams in the future. - */ + if (ret != -ENOSPC) stream->pollin = false; - } - return ret; + /* Possible values for ret are 0, -EFAULT, -ENOSPC, -EIO, ... */ + return offset ?: (ret ?: -EAGAIN); } static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index b65ae817eabf..2d4c899e1f8b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -618,6 +618,64 @@ nouveau_drm_device_fini(struct drm_device *dev) kfree(drm); } +/* + * On some Intel PCIe bridge controllers doing a + * D0 -> D3hot -> D3cold -> D0 sequence causes Nvidia GPUs to not reappear. + * Skipping the intermediate D3hot step seems to make it work again. This is + * probably caused by not meeting the expectation the involved AML code has + * when the GPU is put into D3hot state before invoking it. + * + * This leads to various manifestations of this issue: + * - AML code execution to power on the GPU hits an infinite loop (as the + * code waits on device memory to change). + * - kernel crashes, as all PCI reads return -1, which most code isn't able + * to handle well enough. + * + * In all cases dmesg will contain at least one line like this: + * 'nouveau 0000:01:00.0: Refused to change power state, currently in D3' + * followed by a lot of nouveau timeouts. + * + * In the \_SB.PCI0.PEG0.PG00._OFF code deeper down writes bit 0x80 to the not + * documented PCI config space register 0x248 of the Intel PCIe bridge + * controller (0x1901) in order to change the state of the PCIe link between + * the PCIe port and the GPU. There are alternative code paths using other + * registers, which seem to work fine (executed pre Windows 8): + * - 0xbc bit 0x20 (publicly available documentation claims 'reserved') + * - 0xb0 bit 0x10 (link disable) + * Changing the conditions inside the firmware by poking into the relevant + * addresses does resolve the issue, but it seemed to be ACPI private memory + * and not any device accessible memory at all, so there is no portable way of + * changing the conditions. + * On a XPS 9560 that means bits [0,3] on \CPEX need to be cleared. + * + * The only systems where this behavior can be seen are hybrid graphics laptops + * with a secondary Nvidia Maxwell, Pascal or Turing GPU. It's unclear whether + * this issue only occurs in combination with listed Intel PCIe bridge + * controllers and the mentioned GPUs or other devices as well. + * + * documentation on the PCIe bridge controller can be found in the + * "7th Generation Intel® Processor Families for H Platforms Datasheet Volume 2" + * Section "12 PCI Express* Controller (x16) Registers" + */ + +static void quirk_broken_nv_runpm(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + struct nouveau_drm *drm = nouveau_drm(dev); + struct pci_dev *bridge = pci_upstream_bridge(pdev); + + if (!bridge || bridge->vendor != PCI_VENDOR_ID_INTEL) + return; + + switch (bridge->device) { + case 0x1901: + drm->old_pm_cap = pdev->pm_cap; + pdev->pm_cap = 0; + NV_INFO(drm, "Disabling PCI power management to avoid bug\n"); + break; + } +} + static int nouveau_drm_probe(struct pci_dev *pdev, const struct pci_device_id *pent) { @@ -699,6 +757,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev, if (ret) goto fail_drm_dev_init; + quirk_broken_nv_runpm(pdev); return 0; fail_drm_dev_init: @@ -734,7 +793,11 @@ static void nouveau_drm_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + struct nouveau_drm *drm = nouveau_drm(dev); + /* revert our workaround */ + if (drm->old_pm_cap) + pdev->pm_cap = drm->old_pm_cap; nouveau_drm_device_remove(dev); pci_disable_device(pdev); } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index c2c332fbde97..2a6519737800 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -140,6 +140,8 @@ struct nouveau_drm { struct list_head clients; + u8 old_pm_cap; + struct { struct agp_bridge_data *bridge; u32 base; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index df9bf1fd1bc0..c567526b75b8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -171,6 +171,11 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, mm = get_task_mm(current); down_read(&mm->mmap_sem); + if (!cli->svm.svmm) { + up_read(&mm->mmap_sem); + return -EINVAL; + } + for (addr = args->va_start, end = args->va_start + size; addr < end;) { struct vm_area_struct *vma; unsigned long next; @@ -179,6 +184,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, if (!vma) break; + addr = max(addr, vma->vm_start); next = min(vma->vm_end, end); /* This is a best effort so we ignore errors */ nouveau_dmem_migrate_vma(cli->drm, vma, addr, next); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index dd8f85b8b3a7..f2f5636efac4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -1981,8 +1981,34 @@ gf100_gr_init_(struct nvkm_gr *base) { struct gf100_gr *gr = gf100_gr(base); struct nvkm_subdev *subdev = &base->engine.subdev; + struct nvkm_device *device = subdev->device; + bool reset = device->chipset == 0x137 || device->chipset == 0x138; u32 ret; + /* On certain GP107/GP108 boards, we trigger a weird issue where + * GR will stop responding to PRI accesses after we've asked the + * SEC2 RTOS to boot the GR falcons. This happens with far more + * frequency when cold-booting a board (ie. returning from D3). + * + * The root cause for this is not known and has proven difficult + * to isolate, with many avenues being dead-ends. + * + * A workaround was discovered by Karol, whereby putting GR into + * reset for an extended period right before initialisation + * prevents the problem from occuring. + * + * XXX: As RM does not require any such workaround, this is more + * of a hack than a true fix. + */ + reset = nvkm_boolopt(device->cfgopt, "NvGrResetWar", reset); + if (reset) { + nvkm_mask(device, 0x000200, 0x00001000, 0x00000000); + nvkm_rd32(device, 0x000200); + msleep(50); + nvkm_mask(device, 0x000200, 0x00001000, 0x00001000); + nvkm_rd32(device, 0x000200); + } + nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false); ret = nvkm_falcon_get(&gr->fecs.falcon, subdev); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c index 232a9d7c51e5..e770c9497871 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c @@ -25,6 +25,9 @@ MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/sig.bin"); static const struct nvkm_sec2_fwif gp108_sec2_fwif[] = { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c index b6ebd95c9ba1..a8295653ceab 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c @@ -56,6 +56,22 @@ tu102_sec2_nofw(struct nvkm_sec2 *sec2, int ver, return 0; } +MODULE_FIRMWARE("nvidia/tu102/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu102/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu102/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/sig.bin"); + static const struct nvkm_sec2_fwif tu102_sec2_fwif[] = { { 0, gp102_sec2_load, &tu102_sec2, &gp102_sec2_acr_1 }, diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 5df596fb0280..fe420ca454e0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -498,8 +498,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo) dma_resv_unlock(bo->base.resv); } - if (bo->base.resv != &bo->base._resv) + if (bo->base.resv != &bo->base._resv) { + ttm_bo_flush_all_fences(bo); dma_resv_unlock(&bo->base._resv); + } error: kref_get(&bo->list_kref); diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index 8512d970a09f..ac8f75db2ecd 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -41,6 +41,10 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!vbox_check_supported(VBE_DISPI_ID_HGSMI)) return -ENODEV; + ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, "vboxvideodrmfb"); + if (ret) + return ret; + vbox = kzalloc(sizeof(*vbox), GFP_KERNEL); if (!vbox) return -ENOMEM; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index cea18dc15f77..340719238753 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -681,11 +681,23 @@ static enum drm_mode_status vc4_hdmi_encoder_mode_valid(struct drm_encoder *crtc, const struct drm_display_mode *mode) { - /* HSM clock must be 108% of the pixel clock. Additionally, - * the AXI clock needs to be at least 25% of pixel clock, but - * HSM ends up being the limiting factor. + /* + * As stated in RPi's vc4 firmware "HDMI state machine (HSM) clock must + * be faster than pixel clock, infinitesimally faster, tested in + * simulation. Otherwise, exact value is unimportant for HDMI + * operation." This conflicts with bcm2835's vc4 documentation, which + * states HSM's clock has to be at least 108% of the pixel clock. + * + * Real life tests reveal that vc4's firmware statement holds up, and + * users are able to use pixel clocks closer to HSM's, namely for + * 1920x1200@60Hz. So it was decided to have leave a 1% margin between + * both clocks. Which, for RPi0-3 implies a maximum pixel clock of + * 162MHz. + * + * Additionally, the AXI clock needs to be at least 25% of + * pixel clock, but HSM ends up being the limiting factor. */ - if (mode->clock > HSM_CLOCK_FREQ / (1000 * 108 / 100)) + if (mode->clock > HSM_CLOCK_FREQ / (1000 * 101 / 100)) return MODE_CLOCK_HIGH; return MODE_OK; |