diff options
Diffstat (limited to 'drivers/gpu/drm')
347 files changed, 7748 insertions, 5611 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 50dff69a0f6e..b1172d93c99c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -192,30 +192,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev) static bool amdgpu_read_platform_bios(struct amdgpu_device *adev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = adev->pdev->rom; + size_t romlen = adev->pdev->romlen; + void __iomem *bios; adev->bios = NULL; - bios = pci_platform_rom(adev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - } - adev->bios = kzalloc(size, GFP_KERNEL); - if (adev->bios == NULL) + adev->bios = kzalloc(romlen, GFP_KERNEL); + if (!adev->bios) return false; - memcpy_fromio(adev->bios, bios, size); + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; - if (!check_atom_bios(adev->bios, size)) { - kfree(adev->bios); - return false; - } + memcpy_fromio(adev->bios, bios, romlen); + iounmap(bios); - adev->bios_size = size; + if (!check_atom_bios(adev->bios, romlen)) + goto free_bios; + + adev->bios_size = romlen; return true; +free_bios: + kfree(adev->bios); + return false; } #ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6f469facabfb..f84f9e35a73b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2008,8 +2008,24 @@ 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; + } } /** @@ -2742,6 +2758,9 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work) if (adev->asic_reset_res) goto fail; + + if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count) + adev->mmhub.funcs->reset_ras_error_count(adev); } else { task_barrier_full(&hive->tb); @@ -3353,6 +3372,9 @@ 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, !fbcon); amdgpu_ras_suspend(adev); @@ -3910,8 +3932,15 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, } } - if (!r && amdgpu_ras_intr_triggered()) + if (!r && amdgpu_ras_intr_triggered()) { + list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { + if (tmp_adev->mmhub.funcs && + tmp_adev->mmhub.funcs->reset_ras_error_count) + tmp_adev->mmhub.funcs->reset_ras_error_count(tmp_adev); + } + amdgpu_ras_intr_cleared(); + } list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { if (need_full_reset) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index bc3cf04a1a94..abe94a55ecad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -89,9 +89,13 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev) adev->pm.ac_power = true; else adev->pm.ac_power = false; - if (adev->powerplay.pp_funcs->enable_bapm) + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->enable_bapm) amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power); mutex_unlock(&adev->pm.mutex); + + if (is_support_sw_smu(adev)) + smu_set_ac_dc(&adev->smu); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index dc42086a672b..deaa26808841 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -159,10 +159,6 @@ static int psp_sw_fini(void *handle) adev->psp.sos_fw = NULL; release_firmware(adev->psp.asd_fw); adev->psp.asd_fw = NULL; - if (adev->psp.cap_fw) { - release_firmware(adev->psp.cap_fw); - adev->psp.cap_fw = NULL; - } if (adev->psp.ta_fw) { release_firmware(adev->psp.ta_fw); adev->psp.ta_fw = NULL; @@ -250,7 +246,7 @@ psp_cmd_submit_buf(struct psp_context *psp, DRM_WARN("psp command (0x%X) failed and response status is (0x%X)\n", psp->cmd_buf_mem->cmd_id, psp->cmd_buf_mem->resp.status); - if ((ucode->ucode_id == AMDGPU_UCODE_ID_CAP) || !timeout) { + if (!timeout) { mutex_unlock(&psp->mutex); return -EINVAL; } @@ -822,7 +818,7 @@ static int psp_ras_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_ras_ucode_size || !psp->adev->psp.ta_ras_start_addr) { - dev_warn(psp->adev->dev, "RAS: ras ta ucode is not available\n"); + dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n"); return 0; } @@ -906,7 +902,7 @@ static int psp_hdcp_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_hdcp_ucode_size || !psp->adev->psp.ta_hdcp_start_addr) { - dev_warn(psp->adev->dev, "HDCP: hdcp ta ucode is not available\n"); + dev_info(psp->adev->dev, "HDCP: optional hdcp ta ucode is not available\n"); return 0; } @@ -1052,7 +1048,7 @@ static int psp_dtm_initialize(struct psp_context *psp) if (!psp->adev->psp.ta_dtm_ucode_size || !psp->adev->psp.ta_dtm_start_addr) { - dev_warn(psp->adev->dev, "DTM: dtm ta ucode is not available\n"); + dev_info(psp->adev->dev, "DTM: optional dtm ta ucode is not available\n"); return 0; } @@ -1192,9 +1188,6 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type *type) { switch (ucode->ucode_id) { - case AMDGPU_UCODE_ID_CAP: - *type = GFX_FW_TYPE_CAP; - break; case AMDGPU_UCODE_ID_SDMA0: *type = GFX_FW_TYPE_SDMA0; break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 4a4d8f2ccca2..297435c0c7c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -252,9 +252,6 @@ struct psp_context uint32_t asd_ucode_size; uint8_t *asd_start_addr; - /* cap firmware */ - const struct firmware *cap_fw; - /* fence buffer */ struct amdgpu_bo *fence_buf_bo; uint64_t fence_buf_mc_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 43055a01f35e..ab379b44679c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -281,6 +281,11 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user * struct ras_debug_if data; int ret = 0; + if (amdgpu_ras_intr_triggered()) { + DRM_WARN("RAS WARN: error injection currently inaccessible\n"); + return size; + } + ret = amdgpu_ras_debugfs_ctrl_parse_data(f, buf, size, pos, &data); if (ret) return -EINVAL; @@ -394,6 +399,10 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev, .head = obj->head, }; + if (amdgpu_ras_intr_triggered()) + return snprintf(buf, PAGE_SIZE, + "Query currently inaccessible\n"); + if (amdgpu_ras_error_query(obj->adev, &info)) return -EINVAL; @@ -1415,12 +1424,22 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) { struct amdgpu_ras *ras = container_of(work, struct amdgpu_ras, recovery_work); + struct amdgpu_device *remote_adev = NULL; + struct amdgpu_device *adev = ras->adev; + struct list_head device_list, *device_list_handle = NULL; + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, false); + + /* Build list of devices to query RAS related errors */ + if (hive && adev->gmc.xgmi.num_physical_nodes > 1) { + device_list_handle = &hive->device_list; + } else { + list_add_tail(&adev->gmc.xgmi.head, &device_list); + device_list_handle = &device_list; + } - /* - * Query and print non zero error counter per IP block for - * awareness before recovering GPU. - */ - amdgpu_ras_log_on_err_counter(ras->adev); + list_for_each_entry(remote_adev, device_list_handle, gmc.xgmi.head) { + amdgpu_ras_log_on_err_counter(remote_adev); + } if (amdgpu_device_should_recover_gpu(ras->adev)) amdgpu_device_gpu_recover(ras->adev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index c10ae1cdc1b9..6309ff72bd78 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -770,7 +770,6 @@ struct amdgpu_ttm_tt { static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = { (1 << 0), /* HMM_PFN_VALID */ (1 << 1), /* HMM_PFN_WRITE */ - 0 /* HMM_PFN_DEVICE_PRIVATE */ }; static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = { @@ -851,7 +850,7 @@ retry: range->notifier_seq = mmu_interval_read_begin(&bo->notifier); down_read(&mm->mmap_sem); - r = hmm_range_fault(range, 0); + r = hmm_range_fault(range); up_read(&mm->mmap_sem); if (unlikely(r <= 0)) { /* @@ -968,7 +967,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm) /* Map SG to device */ r = -ENOMEM; nents = dma_map_sg(adev->dev, ttm->sg->sgl, ttm->sg->nents, direction); - if (nents != ttm->sg->nents) + if (nents == 0) goto release_sg; /* convert SG to linear array of pages and dma addresses */ @@ -1840,9 +1839,11 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) *The reserved vram for memory training must be pinned to the specified *place on the VRAM, so reserve it early. */ - r = amdgpu_ttm_training_reserve_vram_init(adev); - if (r) - return r; + if (!amdgpu_sriov_vf(adev)) { + r = amdgpu_ttm_training_reserve_vram_init(adev); + if (r) + return r; + } /* allocate memory as required for VGA * This is used for VGA emulation and pre-OS scanout buffers to diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 88f226070229..b0e656409c03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -283,8 +283,7 @@ union amdgpu_firmware_header { * fw loading support */ enum AMDGPU_UCODE_ID { - AMDGPU_UCODE_ID_CAP = 0, /* CAP must be the 1st fw to be loaded */ - AMDGPU_UCODE_ID_SDMA0, + AMDGPU_UCODE_ID_SDMA0 = 0, AMDGPU_UCODE_ID_SDMA1, AMDGPU_UCODE_ID_SDMA2, AMDGPU_UCODE_ID_SDMA3, 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_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 42bbc0070831..f92c158d89a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1113,7 +1113,7 @@ static int gfx_v10_0_mec_init(struct amdgpu_device *adev) return r; } - memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size); + memset(hpd, 0, mec_hpd_size); amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj); amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj); @@ -1940,6 +1940,11 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev) if (!amdgpu_sriov_vf(adev)) /* enable RLC SRM */ gfx_v10_0_rlc_enable_srm(adev); } else { + if (amdgpu_sriov_vf(adev)) { + gfx_v10_0_init_csb(adev); + return 0; + } + adev->gfx.rlc.funcs->stop(adev); /* disable CG */ @@ -4099,6 +4104,12 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { + /* 0 - Disable some blocks' MGCG */ + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, 0xe0000000); + WREG32_SOC15(GC, 0, mmCGTT_WD_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xff000000); + WREG32_SOC15(GC, 0, mmCGTT_IA_CLK_CTRL, 0xff000000); + /* 1 - RLC_CGTT_MGCG_OVERRIDE */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | @@ -4138,19 +4149,20 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); - /* 2 - disable MGLS in RLC */ + /* 2 - disable MGLS in CP */ + data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); + if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { + data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; + WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); + } + + /* 3 - disable MGLS in RLC */ data = RREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL); if (data & RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK) { data &= ~RLC_MEM_SLP_CNTL__RLC_MEM_LS_EN_MASK; WREG32_SOC15(GC, 0, mmRLC_MEM_SLP_CNTL, data); } - /* 3 - disable MGLS in CP */ - data = RREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL); - if (data & CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK) { - data &= ~CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK; - WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); - } } } @@ -4261,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - gfx_v10_0_update_medium_grain_clock_gating(adev, enable); + /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ } if (adev->cg_flags & diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index ba90a14089cf..0c390485bc10 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1217,6 +1217,8 @@ 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; } } @@ -1232,6 +1234,8 @@ 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 }, }; @@ -1946,7 +1950,7 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev) return r; } - memset(hpd, 0, adev->gfx.mec.hpd_eop_obj->tbo.mem.size); + memset(hpd, 0, mec_hpd_size); amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj); amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj); @@ -4306,7 +4310,7 @@ static const struct soc15_reg_entry vgpr_init_regs_arcturus[] = { { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 }, { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 4 }, { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 }, - { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x81 }, + { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0xbf }, { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x400000 }, /* 64KB LDS */ { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0xffffffff }, { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0xffffffff }, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index cceb46faf212..dce945ef21a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -710,14 +710,16 @@ static int gfx_v9_4_query_utc_edc_status(struct amdgpu_device *adev, sec_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, SEC_COUNT); if (sec_count) { - DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, SEC %d\n", i, vml2_mems[i], sec_count); err_data->ce_count += sec_count; } ded_count = REG_GET_FIELD(data, VML2_MEM_ECC_CNTL, DED_COUNT); if (ded_count) { - DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i, + dev_info(adev->dev, + "Instance[%d]: SubBlock %s, DED %d\n", i, vml2_mems[i], ded_count); err_data->ue_count += ded_count; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 0d413fabd015..c0e3efcb09bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -1539,8 +1539,11 @@ static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = { { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA7_EDC_CNT3), 0, 0, 0 }, }; -static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, - uint32_t value, uint32_t *sec_count, uint32_t *ded_count) +static int mmhub_v9_4_get_ras_error_count(struct amdgpu_device *adev, + const struct soc15_reg_entry *reg, + uint32_t value, + uint32_t *sec_count, + uint32_t *ded_count) { uint32_t i; uint32_t sec_cnt, ded_cnt; @@ -1553,7 +1556,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].sec_count_mask) >> mmhub_v9_4_ras_fields[i].sec_count_shift; if (sec_cnt) { - DRM_INFO("MMHUB SubBlock %s, SEC %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, SEC %d\n", mmhub_v9_4_ras_fields[i].name, sec_cnt); *sec_count += sec_cnt; @@ -1563,7 +1566,7 @@ static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg, mmhub_v9_4_ras_fields[i].ded_count_mask) >> mmhub_v9_4_ras_fields[i].ded_count_shift; if (ded_cnt) { - DRM_INFO("MMHUB SubBlock %s, DED %d\n", + dev_info(adev->dev, "MMHUB SubBlock %s, DED %d\n", mmhub_v9_4_ras_fields[i].name, ded_cnt); *ded_count += ded_cnt; @@ -1588,7 +1591,7 @@ static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev, reg_value = RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i])); if (reg_value) - mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i], + mmhub_v9_4_get_ras_error_count(adev, &mmhub_v9_4_edc_cnt_regs[i], reg_value, &sec_count, &ded_count); } diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 033cbbca2072..52318b03c424 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/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index 6ff9a9544110..a44fd6060d5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -246,7 +246,6 @@ enum psp_gfx_fw_type { GFX_FW_TYPE_SDMA6 = 56, /* SDMA6 MI */ GFX_FW_TYPE_SDMA7 = 57, /* SDMA7 MI */ GFX_FW_TYPE_VCN1 = 58, /* VCN1 MI */ - GFX_FW_TYPE_CAP = 62, /* CAP_FW VG */ GFX_FW_TYPE_MAX }; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index 43896f4779b0..735c43c7daab 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -44,7 +44,6 @@ MODULE_FIRMWARE("amdgpu/vega10_sos.bin"); MODULE_FIRMWARE("amdgpu/vega10_asd.bin"); -MODULE_FIRMWARE("amdgpu/vega10_cap.bin"); MODULE_FIRMWARE("amdgpu/vega12_sos.bin"); MODULE_FIRMWARE("amdgpu/vega12_asd.bin"); @@ -64,7 +63,6 @@ static int psp_v3_1_init_microcode(struct psp_context *psp) char fw_name[30]; int err = 0; const struct psp_firmware_header_v1_0 *hdr; - struct amdgpu_firmware_info *info = NULL; DRM_DEBUG("\n"); @@ -114,26 +112,6 @@ static int psp_v3_1_init_microcode(struct psp_context *psp) adev->psp.asd_start_addr = (uint8_t *)hdr + le32_to_cpu(hdr->header.ucode_array_offset_bytes); - if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_VEGA10) { - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_cap.bin", - chip_name); - err = request_firmware(&adev->psp.cap_fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->psp.cap_fw); - if (err) - goto out; - - info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CAP]; - info->ucode_id = AMDGPU_UCODE_ID_CAP; - info->fw = adev->psp.cap_fw; - hdr = (const struct psp_firmware_header_v1_0 *) - adev->psp.cap_fw->data; - adev->firmware.fw_size += ALIGN( - le32_to_cpu(hdr->header.ucode_size_bytes), PAGE_SIZE); - } - return 0; out: if (err) { @@ -144,8 +122,6 @@ out: adev->psp.sos_fw = NULL; release_firmware(adev->psp.asd_fw); adev->psp.asd_fw = NULL; - release_firmware(adev->psp.cap_fw); - adev->psp.cap_fw = NULL; } return err; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 9159bd46482b..5f3a5ee2a3f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -677,7 +677,7 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring) } /** - * sdma_v4_0_ring_set_wptr - commit the write pointer + * sdma_v4_0_page_ring_set_wptr - commit the write pointer * * @ring: amdgpu ring pointer * @@ -977,7 +977,7 @@ static void sdma_v4_0_page_stop(struct amdgpu_device *adev) } /** - * sdma_v_0_ctx_switch_enable - stop the async dma engines context switch + * sdma_v4_0_ctx_switch_enable - stop the async dma engines context switch * * @adev: amdgpu_device pointer * @enable: enable/disable the DMA MEs context switch. diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 4cb4c891120b..0860e85a2d35 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -3439,7 +3439,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, if (adev->asic_type == CHIP_HAINAN) { if ((adev->pdev->revision == 0x81) || - (adev->pdev->revision == 0x83) || (adev->pdev->revision == 0xC3) || (adev->pdev->device == 0x6664) || (adev->pdev->device == 0x6665) || diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index a40499d51c93..d42a8d8a0dea 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 d5386f15c4a5..05bc6d96ec52 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1112,9 +1112,9 @@ 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.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a4256780e70e..f7c5cdc10a70 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -524,8 +524,9 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) acrtc_state = to_dm_crtc_state(acrtc->base.state); - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); + DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id, + amdgpu_dm_vrr_active(acrtc_state), + acrtc_state->active_planes); amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); drm_crtc_handle_vblank(&acrtc->base); @@ -545,7 +546,18 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) &acrtc_state->vrr_params.adjust); } - if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED) { + /* + * If there aren't any active_planes then DCH HUBP may be clock-gated. + * In that case, pageflip completion interrupts won't fire and pageflip + * completion events won't get delivered. Prevent this by sending + * pending pageflip events from here if a flip is still pending. + * + * If any planes are enabled, use dm_pflip_high_irq() instead, to + * avoid race conditions between flip programming and completion, + * which could cause too early flip completion events. + */ + if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + acrtc_state->active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); acrtc->event = NULL; @@ -3627,6 +3639,9 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, case DRM_FORMAT_NV12: plane_info->format = SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb; break; + case DRM_FORMAT_P010: + plane_info->format = SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb; + break; default: DRM_ERROR( "Unsupported screen format %s\n", @@ -4708,10 +4723,10 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector) static int amdgpu_dm_connector_late_register(struct drm_connector *connector) { +#if defined(CONFIG_DEBUG_FS) struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); -#if defined(CONFIG_DEBUG_FS) connector_debugfs_init(amdgpu_dm_connector); #endif @@ -5523,6 +5538,8 @@ static int get_plane_formats(const struct drm_plane *plane, if (plane_cap && plane_cap->pixel_format_support.nv12) formats[num_formats++] = DRM_FORMAT_NV12; + if (plane_cap && plane_cap->pixel_format_support.p010) + formats[num_formats++] = DRM_FORMAT_P010; break; case DRM_PLANE_TYPE_OVERLAY: @@ -5575,12 +5592,15 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, } if (plane->type == DRM_PLANE_TYPE_PRIMARY && - plane_cap && plane_cap->pixel_format_support.nv12) { + plane_cap && + (plane_cap->pixel_format_support.nv12 || + plane_cap->pixel_format_support.p010)) { /* This only affects YUV formats. */ drm_plane_create_color_properties( plane, BIT(DRM_COLOR_YCBCR_BT601) | - BIT(DRM_COLOR_YCBCR_BT709), + BIT(DRM_COLOR_YCBCR_BT709) | + BIT(DRM_COLOR_YCBCR_BT2020), BIT(DRM_COLOR_YCBCR_LIMITED_RANGE) | BIT(DRM_COLOR_YCBCR_FULL_RANGE), DRM_COLOR_YCBCR_BT709, DRM_COLOR_YCBCR_LIMITED_RANGE); @@ -5909,7 +5929,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, adev->mode_info.underscan_vborder_property, 0); - drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); + if (!aconnector->mst_port) + drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16); /* This defaults to the max in the range, but we want 8bpc for non-edp. */ aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8; @@ -5928,8 +5949,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, &aconnector->base.base, dm->ddev->mode_config.hdr_output_metadata_property, 0); - drm_connector_attach_vrr_capable_property( - &aconnector->base); + if (!aconnector->mst_port) + drm_connector_attach_vrr_capable_property(&aconnector->base); + #ifdef CONFIG_DRM_AMD_DC_HDCP if (adev->dm.hdcp_workqueue) drm_connector_attach_content_protection_property(&aconnector->base, true); @@ -6252,12 +6274,6 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y <= -amdgpu_crtc->max_cursor_height) return 0; - if (crtc->primary->state) { - /* avivo cursor are offset into the total surface */ - x += crtc->primary->state->src_x >> 16; - y += crtc->primary->state->src_y >> 16; - } - if (x < 0) { xorigin = min(-x, amdgpu_crtc->max_cursor_width - 1); x = 0; @@ -6267,6 +6283,7 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc, y = 0; } position->enable = true; + position->translate_by_source = true; position->x = x; position->y = y; position->x_hotspot = xorigin; 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 5b70ed3cdb88..78e1c11d4ae5 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 @@ -192,10 +192,13 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, &hdcp_work->srm_version); 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)); @@ -263,7 +266,7 @@ static void event_callback(struct work_struct *work) mutex_lock(&hdcp_work->mutex); - cancel_delayed_work(&hdcp_work->watchdog_timer_dwork); + cancel_delayed_work(&hdcp_work->callback_dwork); mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_CALLBACK, &hdcp_work->output); @@ -344,6 +347,8 @@ static void event_watchdog_timer(struct work_struct *work) mutex_lock(&hdcp_work->mutex); + cancel_delayed_work(&hdcp_work->watchdog_timer_dwork); + mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_WATCHDOG_TIMEOUT, &hdcp_work->output); @@ -414,7 +419,8 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw; link->dp.mst_supported = config->mst_supported; display->adjust.disable = 1; - link->adjust.auth_delay = 2; + link->adjust.auth_delay = 3; + 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/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d56b758bcce5..3db1ec35d2b4 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 @@ -416,6 +416,14 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, drm_connector_attach_encoder(&aconnector->base, &aconnector->mst_encoder->base); + connector->max_bpc_property = master->base.max_bpc_property; + if (connector->max_bpc_property) + drm_connector_attach_max_bpc_property(connector, 8, 16); + + connector->vrr_capable_property = master->base.vrr_capable_property; + if (connector->vrr_capable_property) + drm_connector_attach_vrr_capable_property(connector); + drm_object_attach_property( &connector->base, dev->mode_config.path_property, 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 ab267ddd4abe..24c5765890fa 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 2ffb22177df9..8489f1e56892 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]; @@ -1360,6 +1362,26 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context) return (result == DC_OK); } +static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context) +{ + int i; + struct pipe_ctx *pipe; + + for (i = 0; i < MAX_PIPES; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->plane_state) + continue; + + /* Must set to false to start with, due to OR in update function */ + pipe->plane_state->status.is_flip_pending = false; + dc->hwss.update_pending_status(pipe); + if (pipe->plane_state->status.is_flip_pending) + return true; + } + return false; +} + bool dc_post_update_surfaces_to_stream(struct dc *dc) { int i; @@ -1370,6 +1392,9 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc) post_surface_trace(dc); + if (is_flip_pending_in_pipes(dc, context)) + return true; + for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].stream == NULL || context->res_ctx.pipe_ctx[i].plane_state == NULL) { @@ -1703,6 +1728,9 @@ static enum surface_update_type det_surface_update(const struct dc *dc, if (u->coeff_reduction_factor) update_flags->bits.coeff_reduction_change = 1; + if (u->gamut_remap_matrix) + update_flags->bits.gamut_remap_change = 1; + if (u->gamma) { enum surface_pixel_format format = SURFACE_PIXEL_FORMAT_GRPH_BEGIN; @@ -1728,7 +1756,8 @@ static enum surface_update_type det_surface_update(const struct dc *dc, if (update_flags->bits.input_csc_change || update_flags->bits.coeff_reduction_change - || update_flags->bits.gamma_change) { + || update_flags->bits.gamma_change + || update_flags->bits.gamut_remap_change) { type = UPDATE_TYPE_FULL; elevate_update_type(&overall_type, type); } @@ -1832,8 +1861,9 @@ enum surface_update_type dc_check_update_surfaces_for_stream( // Else we fallback to mem compare. } else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) { dc->optimized_required = true; - } else if (dc->wm_optimized_required) - dc->optimized_required = true; + } + + dc->optimized_required |= dc->wm_optimized_required; } return type; @@ -1973,6 +2003,10 @@ static void copy_surface_update_to_plane( if (srf_update->coeff_reduction_factor) surface->coeff_reduction_factor = *srf_update->coeff_reduction_factor; + + if (srf_update->gamut_remap_matrix) + surface->gamut_remap_matrix = + *srf_update->gamut_remap_matrix; } static void copy_stream_update_to_stream(struct dc *dc, @@ -2431,7 +2465,7 @@ 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; @@ -2469,6 +2503,17 @@ 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/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 7cbb1efb4f68..aa3c45a69b5e 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 @@ -2530,7 +2530,7 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) /* get phy test pattern and pattern parameters from DP receiver */ core_link_read_dpcd( link, - DP_TEST_PHY_PATTERN, + DP_PHY_TEST_PATTERN, &dpcd_test_pattern.raw, sizeof(dpcd_test_pattern)); core_link_read_dpcd( 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 75c7ce4c7581..f4bcc71b2920 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1077,6 +1077,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) * on certain displays, such as the Sharp 4k */ pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP; + pipe_ctx->plane_res.scl_data.lb_params.alpha_en = plane_state->per_pixel_alpha; pipe_ctx->plane_res.scl_data.recout.x += timing->h_border_left; pipe_ctx->plane_res.scl_data.recout.y += timing->v_border_top; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index d3ceb39e428e..1935cf6601eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -726,6 +726,7 @@ union surface_update_flags { uint32_t output_tf_change:1; uint32_t pixel_format_change:1; uint32_t plane_size_change:1; + uint32_t gamut_remap_change:1; /* Full updates */ uint32_t new_plane:1; @@ -760,6 +761,7 @@ struct dc_plane_state { struct dc_csc_transform input_csc_color_matrix; struct fixed31_32 coeff_reduction_factor; struct fixed31_32 hdr_mult; + struct colorspace_transform gamut_remap_matrix; // TODO: No longer used, remove struct dc_hdr_static_metadata hdr_static_ctx; @@ -839,6 +841,7 @@ struct dc_surface_update { const struct dc_transfer_func *func_shaper; const struct dc_3dlut *lut3d_func; const struct dc_transfer_func *blend_tf; + const struct colorspace_transform *gamut_remap_matrix; }; /* diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 25c50bcab9e9..a8dc3082e3e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -385,6 +385,8 @@ struct dc_cursor_position { */ bool enable; + /* Translate cursor x/y by the source rectangle for each plane. */ + bool translate_by_source; }; struct dc_cursor_mi_param { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 0976e378659f..c279982947e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2685,6 +2685,23 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) .mirror = pipe_ctx->plane_state->horizontal_mirror }; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + pos_cpy.x += pipe_ctx->plane_state->src_rect.x; + pos_cpy.y += pipe_ctx->plane_state->src_rect.y; + } + if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) pos_cpy.enable = false; 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 9cc3314966bd..b0357546471b 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 @@ -2004,6 +2004,12 @@ void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx) for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) adjust.temperature_matrix[i] = pipe_ctx->stream->gamut_remap_matrix.matrix[i]; + } else if (pipe_ctx->plane_state && + pipe_ctx->plane_state->gamut_remap_matrix.enable_remap == true) { + adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW; + for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) + adjust.temperature_matrix[i] = + pipe_ctx->plane_state->gamut_remap_matrix.matrix[i]; } pipe_ctx->plane_res.dpp->funcs->dpp_set_gamut_remap(pipe_ctx->plane_res.dpp, &adjust); @@ -3015,12 +3021,50 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) int x_pos = pos_cpy.x; int y_pos = pos_cpy.y; - // translate cursor from stream space to plane space + /** + * DC cursor is stream space, HW cursor is plane space and drawn + * as part of the framebuffer. + * + * Cursor position can't be negative, but hotspot can be used to + * shift cursor out of the plane bounds. Hotspot must be smaller + * than the cursor size. + */ + + /** + * Translate cursor from stream space to plane space. + * + * If the cursor is scaled then we need to scale the position + * to be in the approximately correct place. We can't do anything + * about the actual size being incorrect, that's a limitation of + * the hardware. + */ x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width / pipe_ctx->plane_state->dst_rect.width; y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height / pipe_ctx->plane_state->dst_rect.height; + /** + * If the cursor's source viewport is clipped then we need to + * translate the cursor to appear in the correct position on + * the screen. + * + * This translation isn't affected by scaling so it needs to be + * done *after* we adjust the position for the scale factor. + * + * This is only done by opt-in for now since there are still + * some usecases like tiled display that might enable the + * cursor on both streams while expecting dc to clip it. + */ + if (pos_cpy.translate_by_source) { + x_pos += pipe_ctx->plane_state->src_rect.x; + y_pos += pipe_ctx->plane_state->src_rect.y; + } + + /** + * If the position is negative then we need to add to the hotspot + * to shift the cursor outside the plane. + */ + if (x_pos < 0) { pos_cpy.x_hotspot -= x_pos; x_pos = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 63acb8ff7462..17d96ec6acd8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -343,6 +343,23 @@ void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enab } /** + * optc1_set_timing_double_buffer() - DRR double buffering control + * + * Sets double buffer point for V_TOTAL, H_TOTAL, VTOTAL_MIN, + * VTOTAL_MAX, VTOTAL_MIN_SEL and VTOTAL_MAX_SEL registers. + * + * Options: any time, start of frame, dp start of frame (range timing) + */ +void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + uint32_t mode = enable ? 2 : 0; + + REG_UPDATE(OTG_DOUBLE_BUFFER_CONTROL, + OTG_RANGE_TIMING_DBUF_UPDATE_MODE, mode); +} + +/** * unblank_crtc * Call ASIC Control Object to UnBlank CRTC. */ @@ -1353,6 +1370,7 @@ void optc1_clear_optc_underflow(struct timing_generator *optc) void optc1_tg_init(struct timing_generator *optc) { optc1_set_blank_data_double_buffer(optc, true); + optc1_set_timing_double_buffer(optc, true); optc1_clear_optc_underflow(optc); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index f277656d5464..9a459a8fe8a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -185,6 +185,7 @@ struct dcn_optc_registers { SF(OTG0_OTG_GLOBAL_CONTROL0, OTG_MASTER_UPDATE_LOCK_SEL, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_UPDATE_PENDING, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_BLANK_DATA_DOUBLE_BUFFER_EN, mask_sh),\ + SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_RANGE_TIMING_DBUF_UPDATE_MODE, mask_sh),\ SF(OTG0_OTG_H_TOTAL, OTG_H_TOTAL, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_START, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_END, mask_sh),\ @@ -643,6 +644,8 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc); void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable); +void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable); + bool optc1_get_otg_active_size(struct timing_generator *optc, uint32_t *otg_active_width, uint32_t *otg_active_height); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 261bdc3a8218..07265ca7d28c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -552,7 +552,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -584,7 +585,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_pplib_clock_request = false, .disable_pplib_wm_range = false, .pplib_wm_report_mode = WM_REPORT_DEFAULT, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = true, .disable_dcc = DCC_ENABLE, .voltage_align_fclk = true, 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 233318260da4..22f421e82733 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1373,6 +1373,7 @@ static void dcn20_update_dchubp_dpp( } if (pipe_ctx->update_flags.bits.viewport || + (context == dc->current_state && plane_state->update_flags.bits.position_change) || (context == dc->current_state && plane_state->update_flags.bits.scaling_change) || (context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) { 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 a67395208991..5cdbba0cd873 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1012,7 +1012,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -3342,7 +3343,7 @@ void dcn20_cap_soc_clocks( void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) { - struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES]; + struct _vcs_dpi_voltage_scaling_st calculated_states[DC__VOLTAGE_STATES]; int i; int num_calculated_states = 0; int min_dcfclk = 0; 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 51b5910cd05f..b25484aa8222 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -300,7 +300,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .xfc_bus_transport_time_us = 4, .xfc_xbuf_latency_tolerance_us = 4, .use_urgent_burst_bw = 1, - .num_states = 9 + .num_states = 8 }; #ifndef MAX @@ -838,7 +838,8 @@ static const struct dc_plane_cap plane_cap = { .pixel_format_support = { .argb8888 = true, .nv12 = true, - .fp16 = true + .fp16 = true, + .p010 = true }, .max_upscale_factor = { @@ -1376,21 +1377,8 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param unsigned int i, j, k; int closest_clk_lvl; - // diags does not retrieve proper values from SMU - // cap states to 5 and make state 5 the max state - if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) || IS_DIAG_DC(dc->ctx->dce_environment)) { - dcn2_1_soc.num_states = 5; - - dcn2_1_soc.clock_limits[5].state = 5; - dcn2_1_soc.clock_limits[5].dcfclk_mhz = 810.0; - dcn2_1_soc.clock_limits[5].fabricclk_mhz = 1600.0; - dcn2_1_soc.clock_limits[5].dispclk_mhz = 1395.0; - dcn2_1_soc.clock_limits[5].dppclk_mhz = 1285.0; - dcn2_1_soc.clock_limits[5].phyclk_mhz = 1325.0; - dcn2_1_soc.clock_limits[5].socclk_mhz = 953.0; - dcn2_1_soc.clock_limits[5].dscclk_mhz = 489.0; - dcn2_1_soc.clock_limits[5].dram_speed_mts = 4266.0; - } else { + // Default clock levels are used for diags, which may lead to overclocking. + if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment)) { dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator; dcn2_1_ip.max_num_dpp = pool->base.pipe_count; dcn2_1_soc.num_chans = bw_params->num_channels; @@ -1403,16 +1391,16 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn2_1_soc.clock_limits[0].dram_speed_mts = clk_table->entries[0].memclk_mhz * 2; /* - * Other levels: find cloest DCN clocks that fit the given clock limit using dcfclk - * as indicater + * Other levels: find closest DCN clocks that fit the given clock limit using dcfclk + * as indicator */ closest_clk_lvl = -1; /* index currently being filled */ k = 1; for (i = 1; i < clk_table->num_entries; i++) { - /* loop backwards, skip duplicate state, +1 because SMU has precision issue */ - for (j = dcn2_1_soc.num_states - 2; j >= k; j--) { + /* loop backwards, skip duplicate state*/ + for (j = dcn2_1_soc.num_states - 1; j >= k; j--) { if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { closest_clk_lvl = j; break; @@ -1437,13 +1425,13 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param k++; } } - - /* duplicate last level */ - dcn2_1_soc.clock_limits[k] = dcn2_1_soc.clock_limits[k - 1]; - dcn2_1_soc.clock_limits[k].state = k; - dcn2_1_soc.num_states = k + 1; + dcn2_1_soc.num_states = k; } + /* duplicate last level */ + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; + dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h index ea4cde952f4f..2a1983324629 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h @@ -29,7 +29,7 @@ #define DC__PRESENT 1 #define DC__PRESENT__1 1 #define DC__NUM_DPP 4 -#define DC__VOLTAGE_STATES 7 +#define DC__VOLTAGE_STATES 9 #define DC__NUM_DPP__4 1 #define DC__NUM_DPP__0_PRESENT 1 #define DC__NUM_DPP__1_PRESENT 1 diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index dfd3be452766..687010c17324 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -22,11 +22,12 @@ * Authors: AMD * */ + +#include "dc_features.h" + #ifndef __DISPLAY_MODE_STRUCTS_H__ #define __DISPLAY_MODE_STRUCTS_H__ -#define MAX_CLOCK_LIMIT_STATES 9 - typedef struct _vcs_dpi_voltage_scaling_st voltage_scaling_st; typedef struct _vcs_dpi_soc_bounding_box_st soc_bounding_box_st; typedef struct _vcs_dpi_ip_params_st ip_params_st; @@ -68,7 +69,7 @@ struct _vcs_dpi_voltage_scaling_st { }; struct _vcs_dpi_soc_bounding_box_st { - struct _vcs_dpi_voltage_scaling_st clock_limits[MAX_CLOCK_LIMIT_STATES]; + struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; unsigned int num_states; double sr_exit_time_us; double sr_enter_plus_exit_time_us; diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 8a87d0ed90ae..2359e88d6029 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -136,6 +136,7 @@ #define RAVEN2_A0 0x81 #define RAVEN1_F0 0xF0 #define RAVEN_UNKNOWN 0xFF +#define RENOIR_A0 0x91 #ifndef ASICREV_IS_RAVEN #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN) #endif @@ -171,8 +172,6 @@ enum { #define ASICREV_IS_NAVI10_P(eChipRev) (eChipRev < NV_NAVI12_P_A0) #define ASICREV_IS_NAVI12_P(eChipRev) ((eChipRev >= NV_NAVI12_P_A0) && (eChipRev < NV_NAVI14_M_A0)) #define ASICREV_IS_NAVI14_M(eChipRev) ((eChipRev >= NV_NAVI14_M_A0) && (eChipRev < NV_UNKNOWN)) -#define RENOIR_A0 0x91 -#define DEVICE_ID_RENOIR_1636 0x1636 // Renoir #define ASICREV_IS_RENOIR(eChipRev) ((eChipRev >= RENOIR_A0) && (eChipRev < RAVEN1_F0)) /* @@ -183,6 +182,9 @@ enum { #define DEVICE_ID_TEMASH_9839 0x9839 #define DEVICE_ID_TEMASH_983D 0x983D +/* RENOIR */ +#define DEVICE_ID_RENOIR_1636 0x1636 + /* Asic Family IDs for different asic family. */ #define FAMILY_CI 120 /* Sea Islands: Hawaii (P), Bonaire (M) */ #define FAMILY_KV 125 /* Fusion => Kaveri: Spectre, Spooky; Kabini: Kalindi */ diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 4e542826cd26..c33454a9e0b4 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -734,6 +734,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, { struct core_freesync *core_freesync = NULL; unsigned long long nominal_field_rate_in_uhz = 0; + unsigned long long rounded_nominal_in_uhz = 0; unsigned int refresh_range = 0; unsigned long long min_refresh_in_uhz = 0; unsigned long long max_refresh_in_uhz = 0; @@ -750,17 +751,20 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, min_refresh_in_uhz = in_config->min_refresh_in_uhz; max_refresh_in_uhz = in_config->max_refresh_in_uhz; - // Don't allow min > max - if (min_refresh_in_uhz > max_refresh_in_uhz) - min_refresh_in_uhz = max_refresh_in_uhz; - // Full range may be larger than current video timing, so cap at nominal if (max_refresh_in_uhz > nominal_field_rate_in_uhz) max_refresh_in_uhz = nominal_field_rate_in_uhz; // Full range may be larger than current video timing, so cap at nominal - if (min_refresh_in_uhz > nominal_field_rate_in_uhz) - min_refresh_in_uhz = nominal_field_rate_in_uhz; + if (min_refresh_in_uhz > max_refresh_in_uhz) + min_refresh_in_uhz = max_refresh_in_uhz; + + // If a monitor reports exactly max refresh of 2x of min, enforce it on nominal + rounded_nominal_in_uhz = + div_u64(nominal_field_rate_in_uhz + 50000, 100000) * 100000; + if (in_config->max_refresh_in_uhz == (2 * in_config->min_refresh_in_uhz) && + in_config->max_refresh_in_uhz == rounded_nominal_in_uhz) + min_refresh_in_uhz = div_u64(nominal_field_rate_in_uhz, 2); if (!vrr_settings_require_update(core_freesync, in_config, (unsigned int)min_refresh_in_uhz, (unsigned int)max_refresh_in_uhz, @@ -792,11 +796,6 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, refresh_range = in_out_vrr->max_refresh_in_uhz - in_out_vrr->min_refresh_in_uhz; - in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - - 2 * in_out_vrr->min_duration_in_us; - if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) - in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; - in_out_vrr->supported = true; } @@ -804,9 +803,14 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, in_out_vrr->btr.btr_enabled = in_config->btr; - if (in_out_vrr->max_refresh_in_uhz < - 2 * in_out_vrr->min_refresh_in_uhz) + if (in_out_vrr->max_refresh_in_uhz < (2 * in_out_vrr->min_refresh_in_uhz)) in_out_vrr->btr.btr_enabled = false; + else { + in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us - + 2 * in_out_vrr->min_duration_in_us; + if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN) + in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN; + } in_out_vrr->btr.btr_active = false; in_out_vrr->btr.inserted_duration_in_us = 0; @@ -1008,8 +1012,8 @@ unsigned long long mod_freesync_calc_nominal_field_rate( unsigned int total = stream->timing.h_total * stream->timing.v_total; /* Calculate nominal field rate for stream, rounded up to nearest integer */ - nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz / 10; - nominal_field_rate_in_uhz *= 1000ULL * 1000ULL * 1000ULL; + nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz; + nominal_field_rate_in_uhz *= 100000000ULL; nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz, total); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index e9fbd94f8635..cc1d3f470b99 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -328,8 +328,7 @@ enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp, /* add display to connection */ hdcp->connection.link = *link; *display_container = *display; - status = mod_hdcp_add_display_to_topology(hdcp, display_container); - + status = mod_hdcp_add_display_to_topology(hdcp, display->index); if (status != MOD_HDCP_STATUS_SUCCESS) goto out; @@ -375,7 +374,7 @@ enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp, status = mod_hdcp_remove_display_from_topology(hdcp, index); if (status != MOD_HDCP_STATUS_SUCCESS) goto out; - memset(display, 0, sizeof(struct mod_hdcp_display)); + display->state = MOD_HDCP_DISPLAY_INACTIVE; /* request authentication when connection is not reset */ if (current_state(hdcp) != HDCP_UNINITIALIZED) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h index 60ff1a0028ac..5cb4546be0ef 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h @@ -328,7 +328,7 @@ void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size, /* psp functions */ enum mod_hdcp_status mod_hdcp_add_display_to_topology( - struct mod_hdcp *hdcp, struct mod_hdcp_display *display); + struct mod_hdcp *hdcp, uint8_t index); enum mod_hdcp_status mod_hdcp_remove_display_from_topology( struct mod_hdcp *hdcp, uint8_t index); enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp); @@ -503,6 +503,11 @@ static inline uint8_t is_display_active(struct mod_hdcp_display *display) return display->state >= MOD_HDCP_DISPLAY_ACTIVE; } +static inline uint8_t is_display_added(struct mod_hdcp_display *display) +{ + return display->state >= MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; +} + static inline uint8_t is_display_encryption_enabled(struct mod_hdcp_display *display) { return display->state >= MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED; @@ -510,23 +515,34 @@ static inline uint8_t is_display_encryption_enabled(struct mod_hdcp_display *dis static inline uint8_t get_active_display_count(struct mod_hdcp *hdcp) { - uint8_t active_count = 0; + uint8_t added_count = 0; uint8_t i; for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) if (is_display_active(&hdcp->displays[i])) - active_count++; - return active_count; + added_count++; + return added_count; +} + +static inline uint8_t get_added_display_count(struct mod_hdcp *hdcp) +{ + uint8_t added_count = 0; + uint8_t i; + + for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) + if (is_display_added(&hdcp->displays[i])) + added_count++; + return added_count; } -static inline struct mod_hdcp_display *get_first_active_display( +static inline struct mod_hdcp_display *get_first_added_display( struct mod_hdcp *hdcp) { uint8_t i; struct mod_hdcp_display *display = NULL; for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) - if (is_display_active(&hdcp->displays[i])) { + if (is_display_added(&hdcp->displays[i])) { display = &hdcp->displays[i]; break; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index f244b72e74e0..37c8c05497d6 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -129,7 +129,7 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp) static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp) { /* device count must be greater than or equal to tracked hdcp displays */ - return (get_device_count(hdcp) < get_active_display_count(hdcp)) ? + return (get_device_count(hdcp) < get_added_display_count(hdcp)) ? MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE : MOD_HDCP_STATUS_SUCCESS; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c index 549c113abcf7..491c00f48026 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c @@ -208,7 +208,7 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp) static enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp) { /* device count must be greater than or equal to tracked hdcp displays */ - return (get_device_count(hdcp) < get_active_display_count(hdcp)) ? + return (get_device_count(hdcp) < get_added_display_count(hdcp)) ? MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE : MOD_HDCP_STATUS_SUCCESS; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index 836e47954938..c2929815c3ee 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -54,7 +54,7 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf; - if (!display || !is_display_active(display)) + if (!display || !is_display_added(display)) return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory)); @@ -73,21 +73,25 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index); return MOD_HDCP_STATUS_SUCCESS; - } - -enum mod_hdcp_status mod_hdcp_add_display_to_topology( - struct mod_hdcp *hdcp, struct mod_hdcp_display *display) + +} +enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, + uint8_t index) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_dtm_shared_memory *dtm_cmd; + struct mod_hdcp_display *display = + get_active_display_at_index(hdcp, index); struct mod_hdcp_link *link = &hdcp->connection.link; if (!psp->dtm_context.dtm_initialized) { DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); - display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } + if (!display || is_display_added(display)) + return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE; + dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf; memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory)); @@ -109,11 +113,10 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology( psp_dtm_invoke(psp, dtm_cmd->cmd_id); - if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) { - display->state = MOD_HDCP_DISPLAY_INACTIVE; + if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE; - } + display->state = MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index); return MOD_HDCP_STATUS_SUCCESS; @@ -123,7 +126,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); struct ta_hdcp_shared_memory *hdcp_cmd; if (!psp->hdcp_context.hdcp_initialized) { @@ -176,7 +179,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp) if (is_display_encryption_enabled( &hdcp->displays[i])) { hdcp->displays[i].state = - MOD_HDCP_DISPLAY_ACTIVE; + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_HDCP1_DISABLED_TRACE(hdcp, hdcp->displays[i].index); } @@ -228,7 +231,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -298,7 +301,8 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(struct mod_hdcp for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { - if (hdcp->displays[i].adjust.disable) + if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED || + hdcp->displays[i].adjust.disable) continue; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -360,7 +364,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); if (!psp->hdcp_context.hdcp_initialized) { DRM_ERROR("Failed to create hdcp session, HDCP TA is not initialized"); @@ -419,7 +423,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp) if (is_display_encryption_enabled( &hdcp->displays[i])) { hdcp->displays[i].state = - MOD_HDCP_DISPLAY_ACTIVE; + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED; HDCP_HDCP2_DISABLED_TRACE(hdcp, hdcp->displays[i].index); } @@ -658,7 +662,7 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp) { struct psp_context *psp = hdcp->config.psp.handle; struct ta_hdcp_shared_memory *hdcp_cmd; - struct mod_hdcp_display *display = get_first_active_display(hdcp); + struct mod_hdcp_display *display = get_first_added_display(hdcp); hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); @@ -743,7 +747,8 @@ enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(struct mod_hdcp for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { - if (hdcp->displays[i].adjust.disable) + if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED || + hdcp->displays[i].adjust.disable) continue; hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.display_handle = hdcp->displays[i].index; hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.session_handle = hdcp->auth.id; diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index eae9309cfb24..c088602bc1a0 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -117,6 +117,7 @@ enum mod_hdcp_operation_mode { enum mod_hdcp_display_state { MOD_HDCP_DISPLAY_INACTIVE = 0, MOD_HDCP_DISPLAY_ACTIVE, + MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED, MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED }; diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index c195575366a3..2a12614a12c2 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -1452,7 +1452,8 @@ static int pp_get_asic_baco_state(void *handle, int *state) if (!hwmgr) return -EINVAL; - if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_state) + if (!(hwmgr->not_vf && amdgpu_dpm) || + !hwmgr->hwmgr_func->get_asic_baco_state) return 0; mutex_lock(&hwmgr->smu_lock); diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index f6d4b0ef46ad..e8b27fab6aa1 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1154,6 +1154,21 @@ static int smu_smc_table_hw_init(struct smu_context *smu, } } } + + if (smu->ppt_funcs->set_power_source) { + /* + * For Navi1X, manually switch it to AC mode as PMFW + * may boot it with DC mode. + */ + if (adev->pm.ac_power) + ret = smu_set_power_source(smu, SMU_POWER_SOURCE_AC); + else + ret = smu_set_power_source(smu, SMU_POWER_SOURCE_DC); + if (ret) { + pr_err("Failed to switch to %s mode!\n", adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } } if (adev->asic_type != CHIP_ARCTURUS) { ret = smu_notify_display_change(smu); @@ -2072,6 +2087,29 @@ int smu_set_watermarks_for_clock_ranges(struct smu_context *smu, return 0; } +int smu_set_ac_dc(struct smu_context *smu) +{ + int ret = 0; + + /* controlled by firmware */ + if (smu->dc_controlled_by_gpio) + return 0; + + mutex_lock(&smu->mutex); + if (smu->ppt_funcs->set_power_source) { + if (smu->adev->pm.ac_power) + ret = smu_set_power_source(smu, SMU_POWER_SOURCE_AC); + else + ret = smu_set_power_source(smu, SMU_POWER_SOURCE_DC); + if (ret) + pr_err("Failed to switch to %s mode!\n", + smu->adev->pm.ac_power ? "AC" : "DC"); + } + mutex_unlock(&smu->mutex); + + return ret; +} + const struct amd_ip_funcs smu_ip_funcs = { .name = "smu", .early_init = smu_early_init, diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index c6d3bef15320..1ef0923f7190 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -35,6 +35,7 @@ #include "arcturus_ppt.h" #include "smu_v11_0_pptable.h" #include "arcturus_ppsmc.h" +#include "nbio/nbio_7_4_offset.h" #include "nbio/nbio_7_4_sh_mask.h" #include "amdgpu_xgmi.h" #include <linux/i2c.h> @@ -793,8 +794,21 @@ static int arcturus_force_clk_levels(struct smu_context *smu, struct arcturus_dpm_table *dpm_table; struct arcturus_single_dpm_table *single_dpm_table; uint32_t soft_min_level, soft_max_level; + uint32_t smu_version; int ret = 0; + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + soft_min_level = mask ? (ffs(mask) - 1) : 0; soft_max_level = mask ? (fls(mask) - 1) : 0; @@ -1511,6 +1525,38 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu, return 0; } +static int arcturus_set_performance_level(struct smu_context *smu, + enum amd_dpm_forced_level level) +{ + uint32_t smu_version; + int ret; + + ret = smu_get_smc_version(smu, NULL, &smu_version); + if (ret) { + pr_err("Failed to get smu version!\n"); + return ret; + } + + switch (level) { + case AMD_DPM_FORCED_LEVEL_HIGH: + case AMD_DPM_FORCED_LEVEL_LOW: + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + if (smu_version >= 0x361200) { + pr_err("Forcing clock level is not supported with " + "54.18 and onwards SMU firmwares\n"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + + return smu_v11_0_set_performance_level(smu, level); +} + static void arcturus_dump_pptable(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; @@ -2210,6 +2256,18 @@ static void arcturus_i2c_eeprom_control_fini(struct i2c_adapter *control) i2c_del_adapter(control); } +static bool arcturus_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} + static uint32_t arcturus_get_pptable_power_limit(struct smu_context *smu) { PPTable_t *pptable = smu->smu_table.driver_pptable; @@ -2272,7 +2330,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .get_profiling_clk_mask = arcturus_get_profiling_clk_mask, .get_power_profile_mode = arcturus_get_power_profile_mode, .set_power_profile_mode = arcturus_set_power_profile_mode, - .set_performance_level = smu_v11_0_set_performance_level, + .set_performance_level = arcturus_set_performance_level, /* debug (internal used) */ .dump_pptable = arcturus_dump_pptable, .get_power_limit = arcturus_get_power_limit, @@ -2321,7 +2379,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= arcturus_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 7740488999df..4795eb66b2b2 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/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 657a6f17e91f..ae2c318dd6fa 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -408,6 +408,7 @@ struct smu_context uint32_t smc_if_version; bool uploading_custom_pp_table; + bool dc_controlled_by_gpio; }; struct i2c_adapter; @@ -570,6 +571,7 @@ struct pptable_funcs { int (*override_pcie_parameters)(struct smu_context *smu); uint32_t (*get_pptable_power_limit)(struct smu_context *smu); int (*disable_umc_cdr_12gbps_workaround)(struct smu_context *smu); + int (*set_power_source)(struct smu_context *smu, enum smu_power_src_type power_src); }; int smu_load_microcode(struct smu_context *smu); @@ -718,6 +720,7 @@ int smu_get_dpm_level_range(struct smu_context *smu, enum smu_clk_type clk_type, enum amd_dpm_forced_level smu_get_performance_level(struct smu_context *smu); int smu_force_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level); int smu_set_display_count(struct smu_context *smu, uint32_t count); +int smu_set_ac_dc(struct smu_context *smu); bool smu_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type); const char *smu_get_message_name(struct smu_context *smu, enum smu_message_type type); const char *smu_get_feature_name(struct smu_context *smu, enum smu_feature_mask feature); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h index 1c88219fe403..674e426ed59b 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h @@ -267,4 +267,7 @@ uint32_t smu_v11_0_get_max_power_limit(struct smu_context *smu); int smu_v11_0_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level); +int smu_v11_0_set_power_source(struct smu_context *smu, + enum smu_power_src_type power_src); + #endif diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index d66dfa7410b6..15030284b444 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -28,13 +28,15 @@ #include "smu_internal.h" #include "atomfirmware.h" #include "amdgpu_atomfirmware.h" +#include "soc15_common.h" #include "smu_v11_0.h" #include "smu11_driver_if_navi10.h" #include "atom.h" #include "navi10_ppt.h" #include "smu_v11_0_pptable.h" #include "smu_v11_0_ppsmc.h" -#include "nbio/nbio_7_4_sh_mask.h" +#include "nbio/nbio_2_3_offset.h" +#include "nbio/nbio_2_3_sh_mask.h" #include "asic_reg/mp/mp_11_0_sh_mask.h" @@ -347,7 +349,6 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, | FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT) | FEATURE_MASK(FEATURE_FW_DSTATE_BIT) | FEATURE_MASK(FEATURE_BACO_BIT) - | FEATURE_MASK(FEATURE_ACDC_BIT) | FEATURE_MASK(FEATURE_GFX_SS_BIT) | FEATURE_MASK(FEATURE_APCC_DFLL_BIT) | FEATURE_MASK(FEATURE_FW_CTF_BIT) @@ -391,6 +392,9 @@ navi10_get_allowed_feature_mask(struct smu_context *smu, if (smu->adev->pg_flags & AMD_PG_SUPPORT_JPEG) *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_JPEG_PG_BIT); + if (smu->dc_controlled_by_gpio) + *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ACDC_BIT); + /* disable DPM UCLK and DS SOCCLK on navi10 A0 secure board */ if (is_asic_secure(smu)) { /* only for navi10 A0 */ @@ -525,6 +529,9 @@ static int navi10_store_powerplay_table(struct smu_context *smu) table_context->thermal_controller_type = powerplay_table->thermal_controller_type; + if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_HARDWAREDC) + smu->dc_controlled_by_gpio = true; + mutex_lock(&smu_baco->mutex); if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO || powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO) @@ -1980,6 +1987,18 @@ static int navi10_setup_od_limits(struct smu_context *smu) { return 0; } +static bool navi10_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} + static int navi10_set_default_od_settings(struct smu_context *smu, bool initialize) { OverDriveTable_t *od_table, *boot_od_table; int ret = 0; @@ -2356,7 +2375,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= navi10_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, @@ -2369,6 +2388,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_pptable_power_limit = navi10_get_pptable_power_limit, .run_btc = navi10_run_btc, .disable_umc_cdr_12gbps_workaround = navi10_disable_umc_cdr_12gbps_workaround, + .set_power_source = smu_v11_0_set_power_source, }; void navi10_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 7bf52ecba01d..ff73a735b888 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -239,6 +239,7 @@ 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; @@ -297,8 +298,13 @@ 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; } @@ -887,6 +893,17 @@ 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, @@ -927,6 +944,7 @@ 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/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h index 6900877de845..40c35bcc5a0a 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_internal.h +++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h @@ -211,4 +211,7 @@ static inline int smu_send_smc_msg(struct smu_context *smu, enum smu_message_typ #define smu_disable_umc_cdr_12gbps_workaround(smu) \ ((smu)->ppt_funcs->disable_umc_cdr_12gbps_workaround ? (smu)->ppt_funcs->disable_umc_cdr_12gbps_workaround((smu)) : 0) +#define smu_set_power_source(smu, power_src) \ + ((smu)->ppt_funcs->set_power_source ? (smu)->ppt_funcs->set_power_source((smu), (power_src)) : 0) + #endif diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 4fd77c7cfc80..655ba4fb05dc 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -42,8 +42,6 @@ #include "asic_reg/thm/thm_11_0_2_sh_mask.h" #include "asic_reg/mp/mp_11_0_offset.h" #include "asic_reg/mp/mp_11_0_sh_mask.h" -#include "asic_reg/nbio/nbio_7_4_offset.h" -#include "asic_reg/nbio/nbio_7_4_sh_mask.h" #include "asic_reg/smuio/smuio_11_0_0_offset.h" #include "asic_reg/smuio/smuio_11_0_0_sh_mask.h" @@ -1525,6 +1523,13 @@ int smu_v11_0_set_xgmi_pstate(struct smu_context *smu, return ret; } +static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu) +{ + return smu_send_smc_msg(smu, + SMU_MSG_ReenableAcDcInterrupt, + NULL); +} + #define THM_11_0__SRCID__THM_DIG_THERM_L2H 0 /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH */ #define THM_11_0__SRCID__THM_DIG_THERM_H2L 1 /* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL */ @@ -1558,6 +1563,9 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, break; } + } else if (client_id == SOC15_IH_CLIENTID_MP1) { + if (src_id == 0xfe) + smu_v11_0_ack_ac_dc_interrupt(&adev->smu); } return 0; @@ -1597,6 +1605,12 @@ int smu_v11_0_register_irq_handler(struct smu_context *smu) if (ret) return ret; + ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1, + 0xfe, + irq_src); + if (ret) + return ret; + return ret; } @@ -1646,9 +1660,7 @@ static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v bool smu_v11_0_baco_is_support(struct smu_context *smu) { - struct amdgpu_device *adev = smu->adev; struct smu_baco_context *smu_baco = &smu->smu_baco; - uint32_t val; bool baco_support; mutex_lock(&smu_baco->mutex); @@ -1663,11 +1675,7 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu) !smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) return false; - val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); - if (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) - return true; - - return false; + return true; } enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu) @@ -1684,11 +1692,9 @@ enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu) int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) { - struct smu_baco_context *smu_baco = &smu->smu_baco; struct amdgpu_device *adev = smu->adev; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); - uint32_t bif_doorbell_intr_cntl; uint32_t data; int ret = 0; @@ -1697,14 +1703,7 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) mutex_lock(&smu_baco->mutex); - bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL); - if (state == SMU_BACO_STATE_ENTER) { - bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl, - BIF_DOORBELL_INT_CNTL, - DOORBELL_INTERRUPT_DISABLE, 1); - WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - if (!ras || !ras->supported) { data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL); data |= 0x80000000; @@ -1719,10 +1718,11 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) if (ret) goto out; - bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl, - BIF_DOORBELL_INT_CNTL, - DOORBELL_INTERRUPT_DISABLE, 0); - WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); + if (ras && ras->supported) { + ret = smu_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + if (ret) + goto out; + } /* clear vbios scratch 6 and 7 for coming asic reinit */ WREG32(adev->bios_scratch_reg_offset + 6, 0); @@ -1939,3 +1939,18 @@ int smu_v11_0_set_performance_level(struct smu_context *smu, return ret; } +int smu_v11_0_set_power_source(struct smu_context *smu, + enum smu_power_src_type power_src) +{ + int pwr_source; + + pwr_source = smu_power_get_index(smu, (uint32_t)power_src); + if (pwr_source < 0) + return -EINVAL; + + return smu_send_smc_msg_with_param(smu, + SMU_MSG_NotifyPowerSource, + pwr_source, + NULL); +} + diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 49ff3756bd9f..3f1044326dcb 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -35,6 +35,7 @@ #include "vega20_ppt.h" #include "vega20_pptable.h" #include "vega20_ppsmc.h" +#include "nbio/nbio_7_4_offset.h" #include "nbio/nbio_7_4_sh_mask.h" #include "asic_reg/thm/thm_11_0_2_offset.h" #include "asic_reg/thm/thm_11_0_2_sh_mask.h" @@ -3174,6 +3175,17 @@ static int vega20_update_pcie_parameters(struct smu_context *smu, return ret; } +static bool vega20_is_baco_supported(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t val; + + if (!smu_v11_0_baco_is_support(smu)) + return false; + + val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0); + return (val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true : false; +} static const struct pptable_funcs vega20_ppt_funcs = { .tables_init = vega20_tables_init, @@ -3262,7 +3274,7 @@ static const struct pptable_funcs vega20_ppt_funcs = { .register_irq_handler = smu_v11_0_register_irq_handler, .set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme, .get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc, - .baco_is_support= smu_v11_0_baco_is_support, + .baco_is_support= vega20_is_baco_supported, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, .baco_enter = smu_v11_0_baco_enter, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c index ea5cd1e17304..e7933930a657 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c @@ -146,14 +146,14 @@ static const struct of_device_id komeda_of_match[] = { MODULE_DEVICE_TABLE(of, komeda_of_match); -static int komeda_rt_pm_suspend(struct device *dev) +static int __maybe_unused komeda_rt_pm_suspend(struct device *dev) { struct komeda_drv *mdrv = dev_get_drvdata(dev); return komeda_dev_suspend(mdrv->mdev); } -static int komeda_rt_pm_resume(struct device *dev) +static int __maybe_unused komeda_rt_pm_resume(struct device *dev) { struct komeda_drv *mdrv = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c index 952199cc0462..dce4672e3fc8 100644 --- a/drivers/gpu/drm/bochs/bochs_hw.c +++ b/drivers/gpu/drm/bochs/bochs_hw.c @@ -157,10 +157,8 @@ int bochs_hw_init(struct drm_device *dev) size = min(size, mem); } - if (pci_request_region(pdev, 0, "bochs-drm") != 0) { - DRM_ERROR("Cannot request framebuffer\n"); - return -EBUSY; - } + if (pci_request_region(pdev, 0, "bochs-drm") != 0) + DRM_WARN("Cannot request framebuffer, boot fb still active?\n"); bochs->fb_map = ioremap(addr, size); if (bochs->fb_map == NULL) { diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 9ded2cef57dd..76736fb8ed94 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1652,8 +1652,7 @@ static ssize_t analogix_dpaux_transfer(struct drm_dp_aux *aux, } struct analogix_dp_device * -analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, - struct analogix_dp_plat_data *plat_data) +analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data) { struct platform_device *pdev = to_platform_device(dev); struct analogix_dp_device *dp; @@ -1756,22 +1755,30 @@ analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, irq_flags, "analogix-dp", dp); if (ret) { dev_err(&pdev->dev, "failed to request irq\n"); - goto err_disable_pm_runtime; + return ERR_PTR(ret); } disable_irq(dp->irq); + return dp; +} +EXPORT_SYMBOL_GPL(analogix_dp_probe); + +int analogix_dp_bind(struct analogix_dp_device *dp, struct drm_device *drm_dev) +{ + int ret; + dp->drm_dev = drm_dev; dp->encoder = dp->plat_data->encoder; dp->aux.name = "DP-AUX"; dp->aux.transfer = analogix_dpaux_transfer; - dp->aux.dev = &pdev->dev; + dp->aux.dev = dp->dev; ret = drm_dp_aux_register(&dp->aux); if (ret) - return ERR_PTR(ret); + return ret; - pm_runtime_enable(dev); + pm_runtime_enable(dp->dev); ret = analogix_dp_create_bridge(drm_dev, dp); if (ret) { @@ -1779,13 +1786,12 @@ analogix_dp_bind(struct device *dev, struct drm_device *drm_dev, goto err_disable_pm_runtime; } - return dp; + return 0; err_disable_pm_runtime: + pm_runtime_disable(dp->dev); - pm_runtime_disable(dev); - - return ERR_PTR(ret); + return ret; } EXPORT_SYMBOL_GPL(analogix_dp_bind); @@ -1802,10 +1808,15 @@ void analogix_dp_unbind(struct analogix_dp_device *dp) drm_dp_aux_unregister(&dp->aux); pm_runtime_disable(dp->dev); - clk_disable_unprepare(dp->clock); } EXPORT_SYMBOL_GPL(analogix_dp_unbind); +void analogix_dp_remove(struct analogix_dp_device *dp) +{ + clk_disable_unprepare(dp->clock); +} +EXPORT_SYMBOL_GPL(analogix_dp_remove); + #ifdef CONFIG_PM int analogix_dp_suspend(struct analogix_dp_device *dp) { diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index ec3b06433d98..30681398cfb0 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1659,28 +1659,34 @@ static void hdmi_config_AVI(struct dw_hdmi *hdmi, struct drm_display_mode *mode) frame.colorspace = HDMI_COLORSPACE_RGB; /* Set up colorimetry */ - switch (hdmi->hdmi_data.enc_out_encoding) { - case V4L2_YCBCR_ENC_601: - if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601) - frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; - else + if (!hdmi_bus_fmt_is_rgb(hdmi->hdmi_data.enc_out_bus_format)) { + switch (hdmi->hdmi_data.enc_out_encoding) { + case V4L2_YCBCR_ENC_601: + if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601) + frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; + else + frame.colorimetry = HDMI_COLORIMETRY_ITU_601; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; + break; + case V4L2_YCBCR_ENC_709: + if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709) + frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; + else + frame.colorimetry = HDMI_COLORIMETRY_ITU_709; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_709; + break; + default: /* Carries no data */ frame.colorimetry = HDMI_COLORIMETRY_ITU_601; + frame.extended_colorimetry = + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; + break; + } + } else { + frame.colorimetry = HDMI_COLORIMETRY_NONE; frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; - break; - case V4L2_YCBCR_ENC_709: - if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709) - frame.colorimetry = HDMI_COLORIMETRY_EXTENDED; - else - frame.colorimetry = HDMI_COLORIMETRY_ITU_709; - frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_709; - break; - default: /* Carries no data */ - frame.colorimetry = HDMI_COLORIMETRY_ITU_601; - frame.extended_colorimetry = - HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; - break; + HDMI_EXTENDED_COLORIMETRY_XV_YCC_601; } /* diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index c6fbe6e6bc9d..612a59ec8116 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -1238,6 +1238,8 @@ static const struct dpcd_quirk dpcd_quirk_list[] = { { OUI(0x00, 0x00, 0x00), DEVICE_ID('C', 'H', '7', '5', '1', '1'), false, BIT(DP_DPCD_QUIRK_NO_SINK_COUNT) }, /* Synaptics DP1.4 MST hubs can support DSC without virtual DPCD */ { OUI(0x90, 0xCC, 0x24), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) }, + /* Apple MacBookPro 2017 15 inch eDP Retina panel reports too low DP_MAX_LINK_RATE */ + { OUI(0x00, 0x10, 0xfa), DEVICE_ID(101, 68, 21, 101, 98, 97), false, BIT(DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS) }, }; #undef OUI @@ -1533,3 +1535,97 @@ int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_S return num_bpc; } EXPORT_SYMBOL(drm_dp_dsc_sink_supported_input_bpcs); + +/** + * drm_dp_get_phy_test_pattern() - get the requested pattern from the sink. + * @aux: DisplayPort AUX channel + * @data: DP phy compliance test parameters. + * + * Returns 0 on success or a negative error code on failure. + */ +int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data) +{ + int err; + u8 rate, lanes; + + err = drm_dp_dpcd_readb(aux, DP_TEST_LINK_RATE, &rate); + if (err < 0) + return err; + data->link_rate = drm_dp_bw_code_to_link_rate(rate); + + err = drm_dp_dpcd_readb(aux, DP_TEST_LANE_COUNT, &lanes); + if (err < 0) + return err; + data->num_lanes = lanes & DP_MAX_LANE_COUNT_MASK; + + if (lanes & DP_ENHANCED_FRAME_CAP) + data->enhanced_frame_cap = true; + + err = drm_dp_dpcd_readb(aux, DP_PHY_TEST_PATTERN, &data->phy_pattern); + if (err < 0) + return err; + + switch (data->phy_pattern) { + case DP_PHY_TEST_PATTERN_80BIT_CUSTOM: + err = drm_dp_dpcd_read(aux, DP_TEST_80BIT_CUSTOM_PATTERN_7_0, + &data->custom80, sizeof(data->custom80)); + if (err < 0) + return err; + + break; + case DP_PHY_TEST_PATTERN_CP2520: + err = drm_dp_dpcd_read(aux, DP_TEST_HBR2_SCRAMBLER_RESET, + &data->hbr2_reset, + sizeof(data->hbr2_reset)); + if (err < 0) + return err; + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_get_phy_test_pattern); + +/** + * drm_dp_set_phy_test_pattern() - set the pattern to the sink. + * @aux: DisplayPort AUX channel + * @data: DP phy compliance test parameters. + * + * Returns 0 on success or a negative error code on failure. + */ +int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data, u8 dp_rev) +{ + int err, i; + u8 link_config[2]; + u8 test_pattern; + + link_config[0] = drm_dp_link_rate_to_bw_code(data->link_rate); + link_config[1] = data->num_lanes; + if (data->enhanced_frame_cap) + link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; + err = drm_dp_dpcd_write(aux, DP_LINK_BW_SET, link_config, 2); + if (err < 0) + return err; + + test_pattern = data->phy_pattern; + if (dp_rev < 0x12) { + test_pattern = (test_pattern << 2) & + DP_LINK_QUAL_PATTERN_11_MASK; + err = drm_dp_dpcd_writeb(aux, DP_TRAINING_PATTERN_SET, + test_pattern); + if (err < 0) + return err; + } else { + for (i = 0; i < data->num_lanes; i++) { + err = drm_dp_dpcd_writeb(aux, + DP_LINK_QUAL_LANE0_SET + i, + test_pattern); + if (err < 0) + return err; + } + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_set_phy_test_pattern); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 6529b479645c..13213c4b77d1 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1928,7 +1928,7 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, return parent_lct + 1; } -static bool drm_dp_mst_is_dp_mst_end_device(u8 pdt, bool mcs) +static bool drm_dp_mst_is_end_device(u8 pdt, bool mcs) { switch (pdt) { case DP_PEER_DEVICE_DP_LEGACY_CONV: @@ -1958,13 +1958,13 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, /* Teardown the old pdt, if there is one */ if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* * If the new PDT would also have an i2c bus, * don't bother with reregistering it */ if (new_pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(new_pdt, new_mcs)) { + drm_dp_mst_is_end_device(new_pdt, new_mcs)) { port->pdt = new_pdt; port->mcs = new_mcs; return 0; @@ -1984,7 +1984,7 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, port->mcs = new_mcs; if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* add i2c over sideband */ ret = drm_dp_mst_register_i2c_bus(&port->aux); } else { @@ -2163,7 +2163,7 @@ drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb, } if (port->pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + drm_dp_mst_is_end_device(port->pdt, port->mcs)) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); drm_connector_set_tile_property(port->connector); @@ -2293,14 +2293,18 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, mutex_unlock(&mgr->lock); } - if (old_ddps != port->ddps) { - if (port->ddps) { - if (!port->input) { - drm_dp_send_enum_path_resources(mgr, mstb, - port); - } + /* + * Reprobe PBN caps on both hotplug, and when re-probing the link + * for our parent mstb + */ + if (old_ddps != port->ddps || !created) { + if (port->ddps && !port->input) { + ret = drm_dp_send_enum_path_resources(mgr, mstb, + port); + if (ret == 1) + changed = true; } else { - port->available_pbn = 0; + port->full_pbn = 0; } } @@ -2392,11 +2396,10 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, port->ddps = conn_stat->displayport_device_plug_status; if (old_ddps != port->ddps) { - if (port->ddps) { - dowork = true; - } else { - port->available_pbn = 0; - } + if (port->ddps && !port->input) + drm_dp_send_enum_path_resources(mgr, mstb, port); + else + port->full_pbn = 0; } new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type; @@ -2547,13 +2550,6 @@ static int drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mg if (port->input || !port->ddps) continue; - if (!port->available_pbn) { - drm_modeset_lock(&mgr->base.lock, NULL); - drm_dp_send_enum_path_resources(mgr, mstb, port); - drm_modeset_unlock(&mgr->base.lock); - changed = true; - } - if (port->mstb) mstb_child = drm_dp_mst_topology_get_mstb_validated( mgr, port->mstb); @@ -2984,6 +2980,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); if (ret > 0) { + ret = 0; path_res = &txmsg->reply.u.path_resources; if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) { @@ -2996,14 +2993,22 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, path_res->port_number, path_res->full_payload_bw_number, path_res->avail_payload_bw_number); - port->available_pbn = - path_res->avail_payload_bw_number; + + /* + * If something changed, make sure we send a + * hotplug + */ + if (port->full_pbn != path_res->full_payload_bw_number || + port->fec_capable != path_res->fec_capable) + ret = 1; + + port->full_pbn = path_res->full_payload_bw_number; port->fec_capable = path_res->fec_capable; } } kfree(txmsg); - return 0; + return ret; } static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) @@ -3577,13 +3582,9 @@ drm_dp_mst_topology_mgr_invalidate_mstb(struct drm_dp_mst_branch *mstb) /* The link address will need to be re-sent on resume */ mstb->link_address_sent = false; - list_for_each_entry(port, &mstb->ports, next) { - /* The PBN for each port will also need to be re-probed */ - port->available_pbn = 0; - + list_for_each_entry(port, &mstb->ports, next) if (port->mstb) drm_dp_mst_topology_mgr_invalidate_mstb(port->mstb); - } } /** @@ -4861,41 +4862,102 @@ static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port, return false; } -static inline -int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch, - struct drm_dp_mst_topology_state *mst_state) +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state); + +static int +drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb, + struct drm_dp_mst_topology_state *state) { - struct drm_dp_mst_port *port; struct drm_dp_vcpi_allocation *vcpi; - int pbn_limit = 0, pbn_used = 0; + struct drm_dp_mst_port *port; + int pbn_used = 0, ret; + bool found = false; - list_for_each_entry(port, &branch->ports, next) { - if (port->mstb) - if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state)) - return -ENOSPC; + /* Check that we have at least one port in our state that's downstream + * of this branch, otherwise we can skip this branch + */ + list_for_each_entry(vcpi, &state->vcpis, next) { + if (!vcpi->pbn || + !drm_dp_mst_port_downstream_of_branch(vcpi->port, mstb)) + continue; - if (port->available_pbn > 0) - pbn_limit = port->available_pbn; + found = true; + break; } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n", - branch, pbn_limit); + if (!found) + return 0; - list_for_each_entry(vcpi, &mst_state->vcpis, next) { - if (!vcpi->pbn) - continue; + if (mstb->port_parent) + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] Checking bandwidth limits on [MSTB:%p]\n", + mstb->port_parent->parent, mstb->port_parent, + mstb); + else + DRM_DEBUG_ATOMIC("[MSTB:%p] Checking bandwidth limits\n", + mstb); + + list_for_each_entry(port, &mstb->ports, next) { + ret = drm_dp_mst_atomic_check_port_bw_limit(port, state); + if (ret < 0) + return ret; + + pbn_used += ret; + } + + return pbn_used; +} + +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state) +{ + struct drm_dp_vcpi_allocation *vcpi; + int pbn_used = 0; + + if (port->pdt == DP_PEER_DEVICE_NONE) + return 0; + + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { + bool found = false; + + list_for_each_entry(vcpi, &state->vcpis, next) { + if (vcpi->port != port) + continue; + if (!vcpi->pbn) + return 0; + + found = true; + break; + } + if (!found) + return 0; - if (drm_dp_mst_port_downstream_of_branch(vcpi->port, branch)) - pbn_used += vcpi->pbn; + /* This should never happen, as it means we tried to + * set a mode before querying the full_pbn + */ + if (WARN_ON(!port->full_pbn)) + return -EINVAL; + + pbn_used = vcpi->pbn; + } else { + pbn_used = drm_dp_mst_atomic_check_mstb_bw_limit(port->mstb, + state); + if (pbn_used <= 0) + return pbn_used; } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch used %d PBN\n", - branch, pbn_used); - if (pbn_used > pbn_limit) { - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] No available bandwidth\n", - branch); + if (pbn_used > port->full_pbn) { + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] required PBN of %d exceeds port limit of %d\n", + port->parent, port, pbn_used, + port->full_pbn); return -ENOSPC; } - return 0; + + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] uses %d out of %d PBN\n", + port->parent, port, pbn_used, port->full_pbn); + + return pbn_used; } static inline int @@ -5093,9 +5155,15 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state) ret = drm_dp_mst_atomic_check_vcpi_alloc_limit(mgr, mst_state); if (ret) break; - ret = drm_dp_mst_atomic_check_bw_limit(mgr->mst_primary, mst_state); - if (ret) + + mutex_lock(&mgr->lock); + ret = drm_dp_mst_atomic_check_mstb_bw_limit(mgr->mst_primary, + mst_state); + mutex_unlock(&mgr->lock); + if (ret < 0) break; + else + ret = 0; } return ret; diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index c4c704e01961..eb009d3ab48f 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -48,6 +48,11 @@ #include "drm_internal.h" #include "drm_legacy.h" +#if defined(CONFIG_MMU) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +#include <uapi/asm/mman.h> +#include <drm/drm_vma_manager.h> +#endif + /* from BKL pushdown */ DEFINE_MUTEX(drm_global_mutex); @@ -872,3 +877,139 @@ struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags) return file; } EXPORT_SYMBOL_FOR_TESTS_ONLY(mock_drm_getfile); + +#ifdef CONFIG_MMU +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * drm_addr_inflate() attempts to construct an aligned area by inflating + * the area size and skipping the unaligned start of the area. + * adapted from shmem_get_unmapped_area() + */ +static unsigned long drm_addr_inflate(unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags, + unsigned long huge_size) +{ + unsigned long offset, inflated_len; + unsigned long inflated_addr; + unsigned long inflated_offset; + + offset = (pgoff << PAGE_SHIFT) & (huge_size - 1); + if (offset && offset + len < 2 * huge_size) + return addr; + if ((addr & (huge_size - 1)) == offset) + return addr; + + inflated_len = len + huge_size - PAGE_SIZE; + if (inflated_len > TASK_SIZE) + return addr; + if (inflated_len < len) + return addr; + + inflated_addr = current->mm->get_unmapped_area(NULL, 0, inflated_len, + 0, flags); + if (IS_ERR_VALUE(inflated_addr)) + return addr; + if (inflated_addr & ~PAGE_MASK) + return addr; + + inflated_offset = inflated_addr & (huge_size - 1); + inflated_addr += offset - inflated_offset; + if (inflated_offset > offset) + inflated_addr += huge_size; + + if (inflated_addr > TASK_SIZE - len) + return addr; + + return inflated_addr; +} + +/** + * drm_get_unmapped_area() - Get an unused user-space virtual memory area + * suitable for huge page table entries. + * @file: The struct file representing the address space being mmap()'d. + * @uaddr: Start address suggested by user-space. + * @len: Length of the area. + * @pgoff: The page offset into the address space. + * @flags: mmap flags + * @mgr: The address space manager used by the drm driver. This argument can + * probably be removed at some point when all drivers use the same + * address space manager. + * + * This function attempts to find an unused user-space virtual memory area + * that can accommodate the size we want to map, and that is properly + * aligned to facilitate huge page table entries matching actual + * huge pages or huge page aligned memory in buffer objects. Buffer objects + * are assumed to start at huge page boundary pfns (io memory) or be + * populated by huge pages aligned to the start of the buffer object + * (system- or coherent memory). Adapted from shmem_get_unmapped_area. + * + * Return: aligned user-space address. + */ +unsigned long drm_get_unmapped_area(struct file *file, + unsigned long uaddr, unsigned long len, + unsigned long pgoff, unsigned long flags, + struct drm_vma_offset_manager *mgr) +{ + unsigned long addr; + unsigned long inflated_addr; + struct drm_vma_offset_node *node; + + if (len > TASK_SIZE) + return -ENOMEM; + + /* + * @pgoff is the file page-offset the huge page boundaries of + * which typically aligns to physical address huge page boundaries. + * That's not true for DRM, however, where physical address huge + * page boundaries instead are aligned with the offset from + * buffer object start. So adjust @pgoff to be the offset from + * buffer object start. + */ + drm_vma_offset_lock_lookup(mgr); + node = drm_vma_offset_lookup_locked(mgr, pgoff, 1); + if (node) + pgoff -= node->vm_node.start; + drm_vma_offset_unlock_lookup(mgr); + + addr = current->mm->get_unmapped_area(file, uaddr, len, pgoff, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (addr & ~PAGE_MASK) + return addr; + if (addr > TASK_SIZE - len) + return addr; + + if (len < HPAGE_PMD_SIZE) + return addr; + if (flags & MAP_FIXED) + return addr; + /* + * Our priority is to support MAP_SHARED mapped hugely; + * and support MAP_PRIVATE mapped hugely too, until it is COWed. + * But if caller specified an address hint, respect that as before. + */ + if (uaddr) + return addr; + + inflated_addr = drm_addr_inflate(addr, len, pgoff, flags, + HPAGE_PMD_SIZE); + + if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && + len >= HPAGE_PUD_SIZE) + inflated_addr = drm_addr_inflate(inflated_addr, len, pgoff, + flags, HPAGE_PUD_SIZE); + return inflated_addr; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +unsigned long drm_get_unmapped_area(struct file *file, + unsigned long uaddr, unsigned long len, + unsigned long pgoff, unsigned long flags, + struct drm_vma_offset_manager *mgr) +{ + return current->mm->get_unmapped_area(file, uaddr, len, pgoff, flags); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +EXPORT_SYMBOL_GPL(drm_get_unmapped_area); +#endif /* CONFIG_MMU */ diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index b481cafdde28..825abe38201a 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -542,10 +542,12 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, } DRM_DEBUG_LEASE("Creating lease\n"); + /* lessee will take the ownership of leases */ lessee = drm_lease_create(lessor, &leases); if (IS_ERR(lessee)) { ret = PTR_ERR(lessee); + idr_destroy(&leases); goto out_leases; } @@ -580,7 +582,6 @@ out_lessee: out_leases: put_unused_fd(fd); - idr_destroy(&leases); DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret); return ret; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 86d9b0e45c8c..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->length; + 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/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 8428ae12dfa5..1f79bc2a881e 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -55,6 +55,7 @@ static const char * const decon_clks_name[] = { struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -644,7 +645,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data) decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void decon_unbind(struct device *dev, struct device *master, void *data) @@ -654,7 +655,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data) decon_atomic_disable(ctx->crtc); /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static const struct component_ops decon_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index e7b58097ccdc..f2d87a7445c7 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -40,6 +40,7 @@ struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -127,13 +128,13 @@ static int decon_ctx_initialize(struct decon_context *ctx, decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, ctx->dev); + return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv); } static void decon_ctx_remove(struct decon_context *ctx) { /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static u32 decon_calc_clkdiv(struct decon_context *ctx, diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index a61482af2998..9ac51b6ab34b 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -156,15 +156,8 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data) struct drm_device *drm_dev = data; int ret; - dp->dev = dev; dp->drm_dev = drm_dev; - dp->plat_data.dev_type = EXYNOS_DP; - dp->plat_data.power_on_start = exynos_dp_poweron; - dp->plat_data.power_off = exynos_dp_poweroff; - dp->plat_data.attach = exynos_dp_bridge_attach; - dp->plat_data.get_modes = exynos_dp_get_modes; - if (!dp->plat_data.panel && !dp->ptn_bridge) { ret = exynos_dp_dt_parse_panel(dp); if (ret) @@ -181,13 +174,11 @@ static int exynos_dp_bind(struct device *dev, struct device *master, void *data) dp->plat_data.encoder = encoder; - dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data); - if (IS_ERR(dp->adp)) { + ret = analogix_dp_bind(dp->adp, dp->drm_dev); + if (ret) dp->encoder.funcs->destroy(&dp->encoder); - return PTR_ERR(dp->adp); - } - return 0; + return ret; } static void exynos_dp_unbind(struct device *dev, struct device *master, @@ -218,6 +209,7 @@ static int exynos_dp_probe(struct platform_device *pdev) if (!dp) return -ENOMEM; + dp->dev = dev; /* * We just use the drvdata until driver run into component * add function, and then we would set drvdata to null, so @@ -243,16 +235,29 @@ static int exynos_dp_probe(struct platform_device *pdev) /* The remote port can be either a panel or a bridge */ dp->plat_data.panel = panel; + dp->plat_data.dev_type = EXYNOS_DP; + dp->plat_data.power_on_start = exynos_dp_poweron; + dp->plat_data.power_off = exynos_dp_poweroff; + dp->plat_data.attach = exynos_dp_bridge_attach; + dp->plat_data.get_modes = exynos_dp_get_modes; dp->plat_data.skip_connector = !!bridge; + dp->ptn_bridge = bridge; out: + dp->adp = analogix_dp_probe(dev, &dp->plat_data); + if (IS_ERR(dp->adp)) + return PTR_ERR(dp->adp); + return component_add(&pdev->dev, &exynos_dp_ops); } static int exynos_dp_remove(struct platform_device *pdev) { + struct exynos_dp_device *dp = platform_get_drvdata(pdev); + component_del(&pdev->dev, &exynos_dp_ops); + analogix_dp_remove(dp->adp); return 0; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 9ebc02768847..619f81435c1b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -58,7 +58,7 @@ static inline void clear_dma_max_seg_size(struct device *dev) * mapping. */ static int drm_iommu_attach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; int ret; @@ -74,7 +74,14 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, return ret; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { - if (to_dma_iommu_mapping(subdrv_dev)) + /* + * Keep the original DMA mapping of the sub-device and + * restore it on Exynos DRM detach, otherwise the DMA + * framework considers it as IOMMU-less during the next + * probe (in case of deferred probe or modular build) + */ + *dma_priv = to_dma_iommu_mapping(subdrv_dev); + if (*dma_priv) arm_iommu_detach_device(subdrv_dev); ret = arm_iommu_attach_device(subdrv_dev, priv->mapping); @@ -98,19 +105,21 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, * mapping */ static void drm_iommu_detach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; - if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { arm_iommu_detach_device(subdrv_dev); - else if (IS_ENABLED(CONFIG_IOMMU_DMA)) + arm_iommu_attach_device(subdrv_dev, *dma_priv); + } else if (IS_ENABLED(CONFIG_IOMMU_DMA)) iommu_detach_device(priv->mapping, subdrv_dev); clear_dma_max_seg_size(subdrv_dev); } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { struct exynos_drm_private *priv = drm->dev_private; @@ -137,13 +146,14 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) priv->mapping = mapping; } - return drm_iommu_attach_device(drm, dev); + return drm_iommu_attach_device(drm, dev, dma_priv); } -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev) +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { if (IS_ENABLED(CONFIG_EXYNOS_IOMMU)) - drm_iommu_detach_device(drm, dev); + drm_iommu_detach_device(drm, dev, dma_priv); } void exynos_drm_cleanup_dma(struct drm_device *drm) diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index d4d21d8cfb90..6ae9056e7a18 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -223,8 +223,10 @@ static inline bool is_drm_iommu_supported(struct drm_device *drm_dev) return priv->mapping ? true : false; } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev); -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev); +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); void exynos_drm_cleanup_dma(struct drm_device *drm); #ifdef CONFIG_DRM_EXYNOS_DPI diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 8ea2e1d77802..29ab8be8604c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -97,6 +97,7 @@ struct fimc_scaler { struct fimc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1133,7 +1134,7 @@ static int fimc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1153,7 +1154,7 @@ static void fimc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops fimc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 21aec38702fc..bb67cad8371f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -167,6 +167,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { struct fimd_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -1090,7 +1091,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data) if (is_drm_iommu_supported(drm_dev)) fimd_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void fimd_unbind(struct device *dev, struct device *master, @@ -1100,7 +1101,7 @@ static void fimd_unbind(struct device *dev, struct device *master, fimd_atomic_disable(ctx->crtc); - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); if (ctx->encoder) exynos_dpi_remove(ctx->encoder); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 2a3382d43bc9..fcee33a43aca 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -232,6 +232,7 @@ struct g2d_runqueue_node { struct g2d_data { struct device *dev; + void *dma_priv; struct clk *gate_clk; void __iomem *regs; int irq; @@ -1409,7 +1410,7 @@ static int g2d_bind(struct device *dev, struct device *master, void *data) return ret; } - ret = exynos_drm_register_dma(drm_dev, dev); + ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv); if (ret < 0) { dev_err(dev, "failed to enable iommu.\n"); g2d_fini_cmdlist(g2d); @@ -1434,7 +1435,7 @@ static void g2d_unbind(struct device *dev, struct device *master, void *data) priv->g2d_dev = NULL; cancel_work_sync(&g2d->runqueue_work); - exynos_drm_unregister_dma(g2d->drm_dev, dev); + exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv); } static const struct component_ops g2d_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 88b6fcaa20be..45e9aee8366a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -97,6 +97,7 @@ struct gsc_scaler { struct gsc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1169,7 +1170,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ctx->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1189,7 +1190,7 @@ static void gsc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops gsc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index b98482990d1a..dafa87b82052 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -56,6 +56,7 @@ struct rot_variant { struct rot_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock; @@ -243,7 +244,7 @@ static int rotator_bind(struct device *dev, struct device *master, void *data) rot->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE, @@ -261,7 +262,7 @@ static void rotator_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &rot->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(rot->drm_dev, rot->dev); + exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv); } static const struct component_ops rotator_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index 497973e9b2c5..93c43c8d914e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -39,6 +39,7 @@ struct scaler_data { struct scaler_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock[SCALER_MAX_CLK]; @@ -450,7 +451,7 @@ static int scaler_bind(struct device *dev, struct device *master, void *data) scaler->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -470,7 +471,8 @@ static void scaler_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &scaler->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev); + exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev, + &scaler->dma_priv); } static const struct component_ops scaler_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 38ae9c32feef..21b726baedea 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -94,6 +94,7 @@ struct mixer_context { struct platform_device *pdev; struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[MIXER_WIN_NR]; unsigned long flags; @@ -894,12 +895,14 @@ static int mixer_initialize(struct mixer_context *mixer_ctx, } } - return exynos_drm_register_dma(drm_dev, mixer_ctx->dev); + return exynos_drm_register_dma(drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static void mixer_ctx_remove(struct mixer_context *mixer_ctx) { - exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev); + exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static int mixer_enable_vblank(struct exynos_drm_crtc *crtc) diff --git a/drivers/gpu/drm/i915/.gitignore b/drivers/gpu/drm/i915/.gitignore index d9a77f3b59b2..81972dce1aff 100644 --- a/drivers/gpu/drm/i915/.gitignore +++ b/drivers/gpu/drm/i915/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only *.hdrtest diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 9f887a86e555..44c506b7e117 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -28,9 +28,6 @@ subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) -subdir-ccflags-y += \ - $(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA) - subdir-ccflags-y += -I$(srctree)/$(src) # Please keep these build lists sorted! @@ -92,6 +89,7 @@ gt-y += \ gt/intel_engine_pool.o \ gt/intel_engine_user.o \ gt/intel_ggtt.o \ + gt/intel_ggtt_fencing.o \ gt/intel_gt.o \ gt/intel_gt_irq.o \ gt/intel_gt_pm.o \ @@ -153,7 +151,6 @@ i915-y += \ i915_buddy.o \ i915_cmd_parser.o \ i915_gem_evict.o \ - i915_gem_fence_reg.o \ i915_gem_gtt.o \ i915_gem.o \ i915_globals.o \ @@ -167,14 +164,18 @@ i915-y += \ # general-purpose microcontroller (GuC) support i915-y += gt/uc/intel_uc.o \ + gt/uc/intel_uc_debugfs.o \ gt/uc/intel_uc_fw.o \ gt/uc/intel_guc.o \ gt/uc/intel_guc_ads.o \ gt/uc/intel_guc_ct.o \ + gt/uc/intel_guc_debugfs.o \ gt/uc/intel_guc_fw.o \ gt/uc/intel_guc_log.o \ + gt/uc/intel_guc_log_debugfs.o \ gt/uc/intel_guc_submission.o \ gt/uc/intel_huc.o \ + gt/uc/intel_huc_debugfs.o \ gt/uc/intel_huc_fw.o # modesetting core code @@ -243,23 +244,6 @@ i915-y += \ display/vlv_dsi.o \ display/vlv_dsi_pll.o -# perf code -i915-y += \ - oa/i915_oa_hsw.o \ - oa/i915_oa_bdw.o \ - oa/i915_oa_chv.o \ - oa/i915_oa_sklgt2.o \ - oa/i915_oa_sklgt3.o \ - oa/i915_oa_sklgt4.o \ - oa/i915_oa_bxt.o \ - oa/i915_oa_kblgt2.o \ - oa/i915_oa_kblgt3.o \ - oa/i915_oa_glk.o \ - oa/i915_oa_cflgt2.o \ - oa/i915_oa_cflgt3.o \ - oa/i915_oa_cnl.o \ - oa/i915_oa_icl.o \ - oa/i915_oa_tgl.o i915-y += i915_perf.o # Post-mortem debug and GPU hang state capture diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 17cee6f80d8b..99a25c0bb08f 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -186,16 +186,19 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host, static int dsi_send_pkt_payld(struct intel_dsi_host *host, struct mipi_dsi_packet pkt) { + struct intel_dsi *intel_dsi = host->intel_dsi; + struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); + /* payload queue can accept *256 bytes*, check limit */ if (pkt.payload_length > MAX_PLOAD_CREDIT * 4) { - DRM_ERROR("payload size exceeds max queue limit\n"); + drm_err(&i915->drm, "payload size exceeds max queue limit\n"); return -1; } /* load data into command payload queue */ if (!add_payld_to_queue(host, pkt.payload, pkt.payload_length)) { - DRM_ERROR("adding payload to queue failed\n"); + drm_err(&i915->drm, "adding payload to queue failed\n"); return -1; } @@ -744,6 +747,18 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, tmp |= VIDEO_MODE_SYNC_PULSE; break; } + } else { + /* + * FIXME: Retrieve this info from VBT. + * As per the spec when dsi transcoder is operating + * in TE GATE mode, TE comes from GPIO + * which is UTIL PIN for DSI 0. + * Also this GPIO would not be used for other + * purposes is an assumption. + */ + tmp &= ~OP_MODE_MASK; + tmp |= CMD_MODE_TE_GATE; + tmp |= TE_SOURCE_GPIO; } intel_de_write(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans), tmp); @@ -837,14 +852,33 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder, } hactive = adjusted_mode->crtc_hdisplay; - htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div); + + if (is_vid_mode(intel_dsi)) + htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div); + else + htotal = DIV_ROUND_UP((hactive + 160) * mul, div); + hsync_start = DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div); hsync_end = DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div); hsync_size = hsync_end - hsync_start; hback_porch = (adjusted_mode->crtc_htotal - adjusted_mode->crtc_hsync_end); vactive = adjusted_mode->crtc_vdisplay; - vtotal = adjusted_mode->crtc_vtotal; + + if (is_vid_mode(intel_dsi)) { + vtotal = adjusted_mode->crtc_vtotal; + } else { + int bpp, line_time_us, byte_clk_period_ns; + + if (crtc_state->dsc.compression_enable) + bpp = crtc_state->dsc.compressed_bpp; + else + bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format); + + byte_clk_period_ns = 1000000 / afe_clk(encoder, crtc_state); + line_time_us = (htotal * (bpp / 8) * byte_clk_period_ns) / (1000 * intel_dsi->lane_count); + vtotal = vactive + DIV_ROUND_UP(400, line_time_us); + } vsync_start = adjusted_mode->crtc_vsync_start; vsync_end = adjusted_mode->crtc_vsync_end; vsync_shift = hsync_start - htotal / 2; @@ -873,7 +907,7 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder, } /* TRANS_HSYNC register to be programmed only for video mode */ - if (intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE) { + if (is_vid_mode(intel_dsi)) { if (intel_dsi->video_mode_format == VIDEO_MODE_NON_BURST_WITH_SYNC_PULSE) { /* BSPEC: hsync size should be atleast 16 pixels */ @@ -916,22 +950,27 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder, if (vsync_start < vactive) drm_err(&dev_priv->drm, "vsync_start less than vactive\n"); - /* program TRANS_VSYNC register */ - for_each_dsi_port(port, intel_dsi->ports) { - dsi_trans = dsi_port_to_transcoder(port); - intel_de_write(dev_priv, VSYNC(dsi_trans), - (vsync_start - 1) | ((vsync_end - 1) << 16)); + /* program TRANS_VSYNC register for video mode only */ + if (is_vid_mode(intel_dsi)) { + for_each_dsi_port(port, intel_dsi->ports) { + dsi_trans = dsi_port_to_transcoder(port); + intel_de_write(dev_priv, VSYNC(dsi_trans), + (vsync_start - 1) | ((vsync_end - 1) << 16)); + } } /* - * FIXME: It has to be programmed only for interlaced + * FIXME: It has to be programmed only for video modes and interlaced * modes. Put the check condition here once interlaced * info available as described above. * program TRANS_VSYNCSHIFT register */ - for_each_dsi_port(port, intel_dsi->ports) { - dsi_trans = dsi_port_to_transcoder(port); - intel_de_write(dev_priv, VSYNCSHIFT(dsi_trans), vsync_shift); + if (is_vid_mode(intel_dsi)) { + for_each_dsi_port(port, intel_dsi->ports) { + dsi_trans = dsi_port_to_transcoder(port); + intel_de_write(dev_priv, VSYNCSHIFT(dsi_trans), + vsync_shift); + } } /* program TRANS_VBLANK register, should be same as vtotal programmed */ @@ -1016,6 +1055,32 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder, } } +static void gen11_dsi_config_util_pin(struct intel_encoder *encoder, + bool enable) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + u32 tmp; + + /* + * used as TE i/p for DSI0, + * for dual link/DSI1 TE is from slave DSI1 + * through GPIO. + */ + if (is_vid_mode(intel_dsi) || (intel_dsi->ports & BIT(PORT_B))) + return; + + tmp = intel_de_read(dev_priv, UTIL_PIN_CTL); + + if (enable) { + tmp |= UTIL_PIN_DIRECTION_INPUT; + tmp |= UTIL_PIN_ENABLE; + } else { + tmp &= ~UTIL_PIN_ENABLE; + } + intel_de_write(dev_priv, UTIL_PIN_CTL, tmp); +} + static void gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) @@ -1037,6 +1102,9 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder, /* setup D-PHY timings */ gen11_dsi_setup_dphy_timings(encoder, crtc_state); + /* Since transcoder is configured to take events from GPIO */ + gen11_dsi_config_util_pin(encoder, true); + /* step 4h: setup DSI protocol timeouts */ gen11_dsi_setup_timeouts(encoder, crtc_state); @@ -1088,7 +1156,8 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) wait_for_cmds_dispatched_to_panel(encoder); } -static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder, +static void gen11_dsi_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -1099,7 +1168,8 @@ static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder, gen11_dsi_program_esc_clk_div(encoder, crtc_state); } -static void gen11_dsi_pre_enable(struct intel_encoder *encoder, +static void gen11_dsi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -1118,7 +1188,8 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder, gen11_dsi_set_transcoder_timings(encoder, pipe_config); } -static void gen11_dsi_enable(struct intel_encoder *encoder, +static void gen11_dsi_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -1180,6 +1251,15 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder) enum transcoder dsi_trans; u32 tmp; + /* disable periodic update mode */ + if (is_cmd_mode(intel_dsi)) { + for_each_dsi_port(port, intel_dsi->ports) { + tmp = intel_de_read(dev_priv, DSI_CMD_FRMCTL(port)); + tmp &= ~DSI_PERIODIC_FRAME_UPDATE_ENABLE; + intel_de_write(dev_priv, DSI_CMD_FRMCTL(port), tmp); + } + } + /* put dsi link in ULPS */ for_each_dsi_port(port, intel_dsi->ports) { dsi_trans = dsi_port_to_transcoder(port); @@ -1264,7 +1344,8 @@ static void gen11_dsi_disable_io_power(struct intel_encoder *encoder) } } -static void gen11_dsi_disable(struct intel_encoder *encoder, +static void gen11_dsi_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -1286,11 +1367,14 @@ static void gen11_dsi_disable(struct intel_encoder *encoder, /* step3: disable port */ gen11_dsi_disable_port(encoder); + gen11_dsi_config_util_pin(encoder, false); + /* step4: disable IO power */ gen11_dsi_disable_io_power(encoder); } -static void gen11_dsi_post_disable(struct intel_encoder *encoder, +static void gen11_dsi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -1347,6 +1431,22 @@ static void gen11_dsi_get_timings(struct intel_encoder *encoder, adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vtotal; } +static bool gen11_dsi_is_periodic_cmd_mode(struct intel_dsi *intel_dsi) +{ + struct drm_device *dev = intel_dsi->base.base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + enum transcoder dsi_trans; + u32 val; + + if (intel_dsi->ports == BIT(PORT_B)) + dsi_trans = TRANSCODER_DSI_1; + else + dsi_trans = TRANSCODER_DSI_0; + + val = intel_de_read(dev_priv, DSI_TRANS_FUNC_CONF(dsi_trans)); + return (val & DSI_PERIODIC_FRAME_UPDATE_ENABLE); +} + static void gen11_dsi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -1367,6 +1467,10 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder, gen11_dsi_get_timings(encoder, pipe_config); pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI); pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc); + + if (gen11_dsi_is_periodic_cmd_mode(intel_dsi)) + pipe_config->hw.adjusted_mode.private_flags |= + I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE; } static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder, @@ -1417,6 +1521,7 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi, base); struct intel_connector *intel_connector = intel_dsi->attached_connector; @@ -1446,10 +1551,32 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder, pipe_config->clock_set = true; if (gen11_dsi_dsc_compute_config(encoder, pipe_config)) - DRM_DEBUG_KMS("Attempting to use DSC failed\n"); + drm_dbg_kms(&i915->drm, "Attempting to use DSC failed\n"); pipe_config->port_clock = afe_clk(encoder, pipe_config) / 5; + /* We would not operate in periodic command mode */ + pipe_config->hw.adjusted_mode.private_flags &= + ~I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE; + + /* + * In case of TE GATE cmd mode, we + * receive TE from the slave if + * dual link is enabled + */ + if (is_cmd_mode(intel_dsi)) { + if (intel_dsi->ports == (BIT(PORT_B) | BIT(PORT_A))) + pipe_config->hw.adjusted_mode.private_flags |= + I915_MODE_FLAG_DSI_USE_TE1 | + I915_MODE_FLAG_DSI_USE_TE0; + else if (intel_dsi->ports == BIT(PORT_B)) + pipe_config->hw.adjusted_mode.private_flags |= + I915_MODE_FLAG_DSI_USE_TE1; + else + pipe_config->hw.adjusted_mode.private_flags |= + I915_MODE_FLAG_DSI_USE_TE0; + } + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 457b258683d3..25dfeb3197aa 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -264,6 +264,20 @@ void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state, plane_state->hw.color_range = from_plane_state->uapi.color_range; } +void intel_plane_set_invisible(struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + + crtc_state->active_planes &= ~BIT(plane->id); + crtc_state->nv12_planes &= ~BIT(plane->id); + crtc_state->c8_planes &= ~BIT(plane->id); + crtc_state->data_rate[plane->id] = 0; + crtc_state->min_cdclk[plane->id] = 0; + + plane_state->uapi.visible = false; +} + int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *new_crtc_state, const struct intel_plane_state *old_plane_state, @@ -273,12 +287,7 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ const struct drm_framebuffer *fb = new_plane_state->hw.fb; int ret; - new_crtc_state->active_planes &= ~BIT(plane->id); - new_crtc_state->nv12_planes &= ~BIT(plane->id); - new_crtc_state->c8_planes &= ~BIT(plane->id); - new_crtc_state->data_rate[plane->id] = 0; - new_crtc_state->min_cdclk[plane->id] = 0; - new_plane_state->uapi.visible = false; + intel_plane_set_invisible(new_crtc_state, new_plane_state); if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc) return 0; diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h index a6bbf42bae1f..59dd1fbb02ea 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h @@ -52,5 +52,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat int intel_plane_calc_min_cdclk(struct intel_atomic_state *state, struct intel_plane *plane, bool *need_cdclk_calc); +void intel_plane_set_invisible(struct intel_crtc_state *crtc_state, + struct intel_plane_state *plane_state); #endif /* __INTEL_ATOMIC_PLANE_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 62f234f641de..57b80971ae78 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -252,14 +252,16 @@ static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_sta i = ARRAY_SIZE(hdmi_audio_clock); if (i == ARRAY_SIZE(hdmi_audio_clock)) { - DRM_DEBUG_KMS("HDMI audio pixel clock setting for %d not found, falling back to defaults\n", - adjusted_mode->crtc_clock); + drm_dbg_kms(&dev_priv->drm, + "HDMI audio pixel clock setting for %d not found, falling back to defaults\n", + adjusted_mode->crtc_clock); i = 1; } - DRM_DEBUG_KMS("Configuring HDMI audio for pixel clock %d (0x%08x)\n", - hdmi_audio_clock[i].clock, - hdmi_audio_clock[i].config); + drm_dbg_kms(&dev_priv->drm, + "Configuring HDMI audio for pixel clock %d (0x%08x)\n", + hdmi_audio_clock[i].clock, + hdmi_audio_clock[i].config); return hdmi_audio_clock[i].config; } @@ -891,7 +893,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev) ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); if (dev_priv->audio_power_refcount++ == 0) { - if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 9) { intel_de_write(dev_priv, AUD_FREQ_CNTRL, dev_priv->audio_freq_cntrl); drm_dbg_kms(&dev_priv->drm, @@ -931,7 +933,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev, unsigned long cookie; u32 tmp; - if (!IS_GEN(dev_priv, 9)) + if (INTEL_GEN(dev_priv) < 9) return; cookie = i915_audio_component_get_power(kdev); @@ -1173,7 +1175,7 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) return; } - if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 9) { dev_priv->audio_freq_cntrl = intel_de_read(dev_priv, AUD_FREQ_CNTRL); drm_dbg_kms(&dev_priv->drm, diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 58b264bc318d..88f367eb28ea 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -338,16 +338,17 @@ void intel_bw_crtc_update(struct intel_bw_state *bw_state, const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); bw_state->data_rate[crtc->pipe] = intel_bw_crtc_data_rate(crtc_state); bw_state->num_active_planes[crtc->pipe] = intel_bw_crtc_num_active_planes(crtc_state); - DRM_DEBUG_KMS("pipe %c data rate %u num active planes %u\n", - pipe_name(crtc->pipe), - bw_state->data_rate[crtc->pipe], - bw_state->num_active_planes[crtc->pipe]); + drm_dbg_kms(&i915->drm, "pipe %c data rate %u num active planes %u\n", + pipe_name(crtc->pipe), + bw_state->data_rate[crtc->pipe], + bw_state->num_active_planes[crtc->pipe]); } static unsigned int intel_bw_num_active_planes(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index c1cce93a1c25..98ece9cd7cdd 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -460,6 +460,16 @@ static void ilk_lut_10_pack(struct drm_color_lut *entry, u32 val) entry->blue = intel_color_lut_pack(REG_FIELD_GET(PREC_PALETTE_BLUE_MASK, val), 10); } +static void icl_lut_multi_seg_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) +{ + entry->red = REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_LDW_MASK, ldw); + entry->green = REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_LDW_MASK, ldw); + entry->blue = REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_UDW_MASK, udw) << 6 | + REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_LDW_MASK, ldw); +} + static void i9xx_color_commit(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -893,7 +903,7 @@ icl_load_gcmax(const struct intel_crtc_state *crtc_state, struct intel_dsb *dsb = intel_dsb_get(crtc); enum pipe pipe = crtc->pipe; - /* Fixme: LUT entries are 16 bit only, so we can prog 0xFFFF max */ + /* FIXME LUT entries are 16 bit only, so we can prog 0xFFFF max */ intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 0), color->red); intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 1), color->green); intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 2), color->blue); @@ -1630,6 +1640,24 @@ static int glk_gamma_precision(const struct intel_crtc_state *crtc_state) } } +static int icl_gamma_precision(const struct intel_crtc_state *crtc_state) +{ + if ((crtc_state->gamma_mode & POST_CSC_GAMMA_ENABLE) == 0) + return 0; + + switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) { + case GAMMA_MODE_MODE_8BIT: + return 8; + case GAMMA_MODE_MODE_10BIT: + return 10; + case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED: + return 16; + default: + MISSING_CASE(crtc_state->gamma_mode); + return 0; + } +} + int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -1641,7 +1669,9 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat else return i9xx_gamma_precision(crtc_state); } else { - if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) + if (INTEL_GEN(dev_priv) >= 11) + return icl_gamma_precision(crtc_state); + else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) return glk_gamma_precision(crtc_state); else if (IS_IRONLAKE(dev_priv)) return ilk_gamma_precision(crtc_state); @@ -1658,9 +1688,9 @@ static bool err_check(struct drm_color_lut *lut1, ((abs((long)lut2->green - lut1->green)) <= err); } -static bool intel_color_lut_entry_equal(struct drm_color_lut *lut1, - struct drm_color_lut *lut2, - int lut_size, u32 err) +static bool intel_color_lut_entries_equal(struct drm_color_lut *lut1, + struct drm_color_lut *lut2, + int lut_size, u32 err) { int i; @@ -1690,16 +1720,8 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1, lut_size2 = drm_color_lut_size(blob2); /* check sw and hw lut size */ - switch (gamma_mode) { - case GAMMA_MODE_MODE_8BIT: - case GAMMA_MODE_MODE_10BIT: - if (lut_size1 != lut_size2) - return false; - break; - default: - MISSING_CASE(gamma_mode); - return false; - } + if (lut_size1 != lut_size2) + return false; lut1 = blob1->data; lut2 = blob2->data; @@ -1707,11 +1729,16 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1, err = 0xffff >> bit_precision; /* check sw and hw lut entry to be equal */ - switch (gamma_mode) { + switch (gamma_mode & GAMMA_MODE_MODE_MASK) { case GAMMA_MODE_MODE_8BIT: case GAMMA_MODE_MODE_10BIT: - if (!intel_color_lut_entry_equal(lut1, lut2, - lut_size2, err)) + if (!intel_color_lut_entries_equal(lut1, lut2, + lut_size2, err)) + return false; + break; + case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED: + if (!intel_color_lut_entries_equal(lut1, lut2, + 9, err)) return false; break; default: @@ -1946,6 +1973,63 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state) crtc_state->hw.gamma_lut = glk_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); } +static struct drm_property_blob * +icl_read_lut_multi_segment(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + int i, lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size; + enum pipe pipe = crtc->pipe; + struct drm_property_blob *blob; + struct drm_color_lut *lut; + + blob = drm_property_create_blob(&dev_priv->drm, + sizeof(struct drm_color_lut) * lut_size, + NULL); + if (IS_ERR(blob)) + return NULL; + + lut = blob->data; + + intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), + PAL_PREC_AUTO_INCREMENT); + + for (i = 0; i < 9; i++) { + u32 ldw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); + u32 udw = intel_de_read(dev_priv, PREC_PAL_MULTI_SEG_DATA(pipe)); + + icl_lut_multi_seg_pack(&lut[i], ldw, udw); + } + + intel_de_write(dev_priv, PREC_PAL_MULTI_SEG_INDEX(pipe), 0); + + /* + * FIXME readouts from PAL_PREC_DATA register aren't giving + * correct values in the case of fine and coarse segments. + * Restricting readouts only for super fine segment as of now. + */ + + return blob; +} + +static void icl_read_luts(struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + + if ((crtc_state->gamma_mode & POST_CSC_GAMMA_ENABLE) == 0) + return; + + switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) { + case GAMMA_MODE_MODE_8BIT: + crtc_state->hw.gamma_lut = ilk_read_lut_8(crtc); + break; + case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED: + crtc_state->hw.gamma_lut = icl_read_lut_multi_segment(crtc); + break; + default: + crtc_state->hw.gamma_lut = glk_read_lut_10(crtc, PAL_PREC_INDEX_VALUE(0)); + } +} + void intel_color_init(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -1989,6 +2073,7 @@ void intel_color_init(struct intel_crtc *crtc) if (INTEL_GEN(dev_priv) >= 11) { dev_priv->display.load_luts = icl_load_luts; + dev_priv->display.read_luts = icl_read_luts; } else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) { dev_priv->display.load_luts = glk_load_luts; dev_priv->display.read_luts = glk_read_luts; diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 903e49659f56..98ec2ea86c7c 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -290,7 +290,7 @@ intel_attach_colorspace_property(struct drm_connector *connector) return; break; default: - DRM_DEBUG_KMS("Colorspace property not supported\n"); + MISSING_CASE(connector->connector_type); return; } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 78f9b6cde810..a59ecbed0004 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -203,27 +203,31 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, intel_de_write(dev_priv, crt->adpa_reg, adpa); } -static void intel_disable_crt(struct intel_encoder *encoder, +static void intel_disable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { intel_crt_set_dpms(encoder, old_crtc_state, DRM_MODE_DPMS_OFF); } -static void pch_disable_crt(struct intel_encoder *encoder, +static void pch_disable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { } -static void pch_post_disable_crt(struct intel_encoder *encoder, +static void pch_post_disable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_crt(encoder, old_crtc_state, old_conn_state); + intel_disable_crt(state, encoder, old_crtc_state, old_conn_state); } -static void hsw_disable_crt(struct intel_encoder *encoder, +static void hsw_disable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -234,7 +238,8 @@ static void hsw_disable_crt(struct intel_encoder *encoder, intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); } -static void hsw_post_disable_crt(struct intel_encoder *encoder, +static void hsw_post_disable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -250,19 +255,20 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder, intel_ddi_disable_pipe_clock(old_crtc_state); - pch_post_disable_crt(encoder, old_crtc_state, old_conn_state); + pch_post_disable_crt(state, encoder, old_crtc_state, old_conn_state); lpt_disable_pch_transcoder(dev_priv); lpt_disable_iclkip(dev_priv); - intel_ddi_fdi_post_disable(encoder, old_crtc_state, old_conn_state); + intel_ddi_fdi_post_disable(state, encoder, old_crtc_state, old_conn_state); drm_WARN_ON(&dev_priv->drm, !old_crtc_state->has_pch_encoder); intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true); } -static void hsw_pre_pll_enable_crt(struct intel_encoder *encoder, +static void hsw_pre_pll_enable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -273,7 +279,8 @@ static void hsw_pre_pll_enable_crt(struct intel_encoder *encoder, intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); } -static void hsw_pre_enable_crt(struct intel_encoder *encoder, +static void hsw_pre_enable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -290,7 +297,8 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder, intel_ddi_enable_pipe_clock(crtc_state); } -static void hsw_enable_crt(struct intel_encoder *encoder, +static void hsw_enable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -314,7 +322,8 @@ static void hsw_enable_crt(struct intel_encoder *encoder, intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true); } -static void intel_enable_crt(struct intel_encoder *encoder, +static void intel_enable_crt(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -594,7 +603,8 @@ static struct edid *intel_crt_get_edid(struct drm_connector *connector, edid = drm_get_edid(connector, i2c); if (!edid && !intel_gmbus_is_forced_bit(i2c)) { - DRM_DEBUG_KMS("CRT GMBUS EDID read failed, retry using GPIO bit-banging\n"); + drm_dbg_kms(connector->dev, + "CRT GMBUS EDID read failed, retry using GPIO bit-banging\n"); intel_gmbus_force_bit(i2c, true); edid = drm_get_edid(connector, i2c); intel_gmbus_force_bit(i2c, false); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 73d0f4648c06..be6c61bcbc9c 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -568,7 +568,7 @@ static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = { { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 850 3.0 */ }; -static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_hbr2_hbr3[] = { +static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_dp[] = { /* NT mV Trans mV db */ { 0xA, 0x33, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ { 0xA, 0x47, 0x36, 0x00, 0x09 }, /* 350 500 3.1 */ @@ -583,23 +583,51 @@ static const struct cnl_ddi_buf_trans ehl_combo_phy_ddi_translations_hbr2_hbr3[] }; struct icl_mg_phy_ddi_buf_trans { - u32 cri_txdeemph_override_5_0; u32 cri_txdeemph_override_11_6; + u32 cri_txdeemph_override_5_0; u32 cri_txdeemph_override_17_12; }; -static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations[] = { +static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_rbr_hbr[] = { + /* Voltage swing pre-emphasis */ + { 0x18, 0x00, 0x00 }, /* 0 0 */ + { 0x1D, 0x00, 0x05 }, /* 0 1 */ + { 0x24, 0x00, 0x0C }, /* 0 2 */ + { 0x2B, 0x00, 0x14 }, /* 0 3 */ + { 0x21, 0x00, 0x00 }, /* 1 0 */ + { 0x2B, 0x00, 0x08 }, /* 1 1 */ + { 0x30, 0x00, 0x0F }, /* 1 2 */ + { 0x31, 0x00, 0x03 }, /* 2 0 */ + { 0x34, 0x00, 0x0B }, /* 2 1 */ + { 0x3F, 0x00, 0x00 }, /* 3 0 */ +}; + +static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hbr2_hbr3[] = { /* Voltage swing pre-emphasis */ - { 0x0, 0x1B, 0x00 }, /* 0 0 */ - { 0x0, 0x23, 0x08 }, /* 0 1 */ - { 0x0, 0x2D, 0x12 }, /* 0 2 */ - { 0x0, 0x00, 0x00 }, /* 0 3 */ - { 0x0, 0x23, 0x00 }, /* 1 0 */ - { 0x0, 0x2B, 0x09 }, /* 1 1 */ - { 0x0, 0x2E, 0x11 }, /* 1 2 */ - { 0x0, 0x2F, 0x00 }, /* 2 0 */ - { 0x0, 0x33, 0x0C }, /* 2 1 */ - { 0x0, 0x00, 0x00 }, /* 3 0 */ + { 0x18, 0x00, 0x00 }, /* 0 0 */ + { 0x1D, 0x00, 0x05 }, /* 0 1 */ + { 0x24, 0x00, 0x0C }, /* 0 2 */ + { 0x2B, 0x00, 0x14 }, /* 0 3 */ + { 0x26, 0x00, 0x00 }, /* 1 0 */ + { 0x2C, 0x00, 0x07 }, /* 1 1 */ + { 0x33, 0x00, 0x0C }, /* 1 2 */ + { 0x2E, 0x00, 0x00 }, /* 2 0 */ + { 0x36, 0x00, 0x09 }, /* 2 1 */ + { 0x3F, 0x00, 0x00 }, /* 3 0 */ +}; + +static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations_hdmi[] = { + /* HDMI Preset VS Pre-emph */ + { 0x1A, 0x0, 0x0 }, /* 1 400mV 0dB */ + { 0x20, 0x0, 0x0 }, /* 2 500mV 0dB */ + { 0x29, 0x0, 0x0 }, /* 3 650mV 0dB */ + { 0x32, 0x0, 0x0 }, /* 4 800mV 0dB */ + { 0x3F, 0x0, 0x0 }, /* 5 1000mV 0dB */ + { 0x3A, 0x0, 0x5 }, /* 6 Full -1.5 dB */ + { 0x39, 0x0, 0x6 }, /* 7 Full -1.8 dB */ + { 0x38, 0x0, 0x7 }, /* 8 Full -2 dB */ + { 0x37, 0x0, 0x8 }, /* 9 Full -2.5 dB */ + { 0x36, 0x0, 0x9 }, /* 10 Full -3 dB */ }; struct tgl_dkl_phy_ddi_buf_trans { @@ -943,13 +971,29 @@ icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, return icl_combo_phy_ddi_translations_dp_hbr2; } +static const struct icl_mg_phy_ddi_buf_trans * +icl_get_mg_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, + int *n_entries) +{ + if (type == INTEL_OUTPUT_HDMI) { + *n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hdmi); + return icl_mg_phy_ddi_translations_hdmi; + } else if (rate > 270000) { + *n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_hbr2_hbr3); + return icl_mg_phy_ddi_translations_hbr2_hbr3; + } + + *n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations_rbr_hbr); + return icl_mg_phy_ddi_translations_rbr_hbr; +} + static const struct cnl_ddi_buf_trans * ehl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, int *n_entries) { - if (type == INTEL_OUTPUT_DP && rate > 270000) { - *n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_hbr2_hbr3); - return ehl_combo_phy_ddi_translations_hbr2_hbr3; + if (type != INTEL_OUTPUT_HDMI && type != INTEL_OUTPUT_EDP) { + *n_entries = ARRAY_SIZE(ehl_combo_phy_ddi_translations_dp); + return ehl_combo_phy_ddi_translations_dp; } return icl_get_combo_buf_trans(dev_priv, type, rate, n_entries); @@ -959,7 +1003,7 @@ static const struct cnl_ddi_buf_trans * tgl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate, int *n_entries) { - if (type != INTEL_OUTPUT_DP) { + if (type == INTEL_OUTPUT_HDMI || type == INTEL_OUTPUT_EDP) { return icl_get_combo_buf_trans(dev_priv, type, rate, n_entries); } else if (rate > 270000) { *n_entries = ARRAY_SIZE(tgl_combo_phy_ddi_translations_dp_hbr2); @@ -988,7 +1032,8 @@ static int intel_ddi_hdmi_level(struct intel_encoder *encoder) icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI, 0, &n_entries); else - n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); + icl_get_mg_buf_trans(dev_priv, INTEL_OUTPUT_HDMI, 0, + &n_entries); default_entry = n_entries - 1; } else if (IS_CANNONLAKE(dev_priv)) { cnl_get_buf_trans_hdmi(dev_priv, &n_entries); @@ -1102,7 +1147,8 @@ static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv, if (intel_de_read(dev_priv, reg) & DDI_BUF_IS_IDLE) return; } - DRM_ERROR("Timeout waiting for DDI BUF %c idle bit\n", port_name(port)); + drm_err(&dev_priv->drm, "Timeout waiting for DDI BUF %c idle bit\n", + port_name(port)); } static u32 hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll) @@ -1249,7 +1295,8 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, temp = intel_de_read(dev_priv, DP_TP_STATUS(PORT_E)); if (temp & DP_TP_STATUS_AUTOTRAIN_DONE) { - DRM_DEBUG_KMS("FDI link training done on step %d\n", i); + drm_dbg_kms(&dev_priv->drm, + "FDI link training done on step %d\n", i); break; } @@ -1258,7 +1305,7 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, * Results in less fireworks from the state checker. */ if (i == ARRAY_SIZE(hsw_ddi_translations_fdi) * 2 - 1) { - DRM_ERROR("FDI link training failed!\n"); + drm_err(&dev_priv->drm, "FDI link training failed!\n"); break; } @@ -1450,6 +1497,14 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state, intel_de_write(dev_priv, TRANS_MSA_MISC(cpu_transcoder), temp); } +static u32 bdw_trans_port_sync_master_select(enum transcoder master_transcoder) +{ + if (master_transcoder == TRANSCODER_EDP) + return 0; + else + return master_transcoder + 1; +} + /* * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state. * @@ -1550,6 +1605,15 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state) temp |= DDI_PORT_WIDTH(crtc_state->lane_count); } + if (IS_GEN_RANGE(dev_priv, 8, 10) && + crtc_state->master_transcoder != INVALID_TRANSCODER) { + u8 master_select = + bdw_trans_port_sync_master_select(crtc_state->master_transcoder); + + temp |= TRANS_DDI_PORT_SYNC_ENABLE | + TRANS_DDI_PORT_SYNC_MASTER_SELECT(master_select); + } + return temp; } @@ -1558,12 +1622,28 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - u32 temp; + u32 ctl; + + if (INTEL_GEN(dev_priv) >= 11) { + enum transcoder master_transcoder = crtc_state->master_transcoder; + u32 ctl2 = 0; + + if (master_transcoder != INVALID_TRANSCODER) { + u8 master_select = + bdw_trans_port_sync_master_select(master_transcoder); - temp = intel_ddi_transcoder_func_reg_val_get(crtc_state); + ctl2 |= PORT_SYNC_MODE_ENABLE | + PORT_SYNC_MODE_MASTER_SELECT(master_select); + } + + intel_de_write(dev_priv, + TRANS_DDI_FUNC_CTL2(cpu_transcoder), ctl2); + } + + ctl = intel_ddi_transcoder_func_reg_val_get(crtc_state); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)) - temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC; - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); + ctl |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC; + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl); } /* @@ -1576,11 +1656,11 @@ intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - u32 temp; + u32 ctl; - temp = intel_ddi_transcoder_func_reg_val_get(crtc_state); - temp &= ~TRANS_DDI_FUNC_ENABLE; - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); + ctl = intel_ddi_transcoder_func_reg_val_get(crtc_state); + ctl &= ~TRANS_DDI_FUNC_ENABLE; + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl); } void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state) @@ -1588,24 +1668,35 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - u32 val; + u32 ctl; + + if (INTEL_GEN(dev_priv) >= 11) + intel_de_write(dev_priv, + TRANS_DDI_FUNC_CTL2(cpu_transcoder), 0); + + ctl = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); - val = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); - val &= ~TRANS_DDI_FUNC_ENABLE; + ctl &= ~TRANS_DDI_FUNC_ENABLE; + + if (IS_GEN_RANGE(dev_priv, 8, 10)) + ctl &= ~(TRANS_DDI_PORT_SYNC_ENABLE | + TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK); if (INTEL_GEN(dev_priv) >= 12) { if (!intel_dp_mst_is_master_trans(crtc_state)) { - val &= ~(TGL_TRANS_DDI_PORT_MASK | + ctl &= ~(TGL_TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK); } } else { - val &= ~(TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK); + ctl &= ~(TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK); } - intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), val); + + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl); if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { - DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n"); + drm_dbg_kms(&dev_priv->drm, + "Quirk Increase DDI disabled time\n"); /* Quirk time at 100ms for reliable operation */ msleep(100); } @@ -1666,7 +1757,7 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) goto out; } - if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A) + if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A) cpu_transcoder = TRANSCODER_EDP; else cpu_transcoder = (enum transcoder) pipe; @@ -1728,7 +1819,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, if (!(tmp & DDI_BUF_CTL_ENABLE)) goto out; - if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A) { + if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A) { tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); @@ -1786,20 +1877,23 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, } if (!*pipe_mask) - DRM_DEBUG_KMS("No pipe for [ENCODER:%d:%s] found\n", - encoder->base.base.id, encoder->base.name); + drm_dbg_kms(&dev_priv->drm, + "No pipe for [ENCODER:%d:%s] found\n", + encoder->base.base.id, encoder->base.name); if (!mst_pipe_mask && hweight8(*pipe_mask) > 1) { - DRM_DEBUG_KMS("Multiple pipes for [ENCODER:%d:%s] (pipe_mask %02x)\n", - encoder->base.base.id, encoder->base.name, - *pipe_mask); + drm_dbg_kms(&dev_priv->drm, + "Multiple pipes for [ENCODER:%d:%s] (pipe_mask %02x)\n", + encoder->base.base.id, encoder->base.name, + *pipe_mask); *pipe_mask = BIT(ffs(*pipe_mask) - 1); } if (mst_pipe_mask && mst_pipe_mask != *pipe_mask) - DRM_DEBUG_KMS("Conflicting MST and non-MST state for [ENCODER:%d:%s] (pipe_mask %02x mst_pipe_mask %02x)\n", - encoder->base.base.id, encoder->base.name, - *pipe_mask, mst_pipe_mask); + drm_dbg_kms(&dev_priv->drm, + "Conflicting MST and non-MST state for [ENCODER:%d:%s] (pipe_mask %02x mst_pipe_mask %02x)\n", + encoder->base.base.id, encoder->base.name, + *pipe_mask, mst_pipe_mask); else *is_dp_mst = mst_pipe_mask; @@ -1809,9 +1903,9 @@ out: if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK | BXT_PHY_LANE_POWERDOWN_ACK | BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) - DRM_ERROR("[ENCODER:%d:%s] enabled but PHY powered down? " - "(PHY_CTL %08x)\n", encoder->base.base.id, - encoder->base.name, tmp); + drm_err(&dev_priv->drm, + "[ENCODER:%d:%s] enabled but PHY powered down? (PHY_CTL %08x)\n", + encoder->base.base.id, encoder->base.name, tmp); } intel_display_power_put(dev_priv, encoder->power_domain, wakeref); @@ -1869,7 +1963,11 @@ 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 @@ -1973,7 +2071,7 @@ static void skl_ddi_set_iboost(struct intel_encoder *encoder, /* Make sure that the requested I_boost is valid */ if (iboost && iboost != 0x1 && iboost != 0x3 && iboost != 0x7) { - DRM_ERROR("Invalid I_boost value %u\n", iboost); + drm_err(&dev_priv->drm, "Invalid I_boost value %u\n", iboost); return; } @@ -2032,7 +2130,8 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) icl_get_combo_buf_trans(dev_priv, encoder->type, intel_dp->link_rate, &n_entries); else - n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); + icl_get_mg_buf_trans(dev_priv, encoder->type, + intel_dp->link_rate, &n_entries); } else if (IS_CANNONLAKE(dev_priv)) { if (encoder->type == INTEL_OUTPUT_EDP) cnl_get_buf_trans_edp(dev_priv, &n_entries); @@ -2232,7 +2331,9 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, return; if (level >= n_entries) { - DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.", level, n_entries - 1); + drm_dbg_kms(&dev_priv->drm, + "DDI translation not found for level %d. Using %d instead.", + level, n_entries - 1); level = n_entries - 1; } @@ -2345,21 +2446,28 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, } static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - int link_clock, - u32 level) + int link_clock, u32 level, + enum intel_output_type type) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port); const struct icl_mg_phy_ddi_buf_trans *ddi_translations; u32 n_entries, val; - int ln; + int ln, rate = 0; + + if (type != INTEL_OUTPUT_HDMI) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); - ddi_translations = icl_mg_phy_ddi_translations; + rate = intel_dp->link_rate; + } + + ddi_translations = icl_get_mg_buf_trans(dev_priv, type, rate, + &n_entries); /* The table does not have values for level 3 and level 9. */ if (level >= n_entries || level == 3 || level == 9) { - DRM_DEBUG_KMS("DDI translation not found for level %d. Using %d instead.", - level, n_entries - 2); + drm_dbg_kms(&dev_priv->drm, + "DDI translation not found for level %d. Using %d instead.", + level, n_entries - 2); level = n_entries - 2; } @@ -2478,7 +2586,8 @@ static void icl_ddi_vswing_sequence(struct intel_encoder *encoder, if (intel_phy_is_combo(dev_priv, phy)) icl_combo_phy_ddi_vswing_sequence(encoder, level, type); else - icl_mg_phy_ddi_vswing_sequence(encoder, link_clock, level); + icl_mg_phy_ddi_vswing_sequence(encoder, link_clock, level, + type); } static void @@ -2693,8 +2802,9 @@ static void icl_sanitize_port_clk_off(struct drm_i915_private *dev_priv, if (drm_WARN_ON(&dev_priv->drm, ddi_clk_needed)) continue; - DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n", - phy_name(phy)); + drm_notice(&dev_priv->drm, + "PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n", + phy_name(phy)); val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy); intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val); } @@ -2931,11 +3041,14 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port, static void intel_dp_sink_set_fec_ready(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + if (!crtc_state->fec_enable) return; if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_FEC_CONFIGURATION, DP_FEC_READY) <= 0) - DRM_DEBUG_KMS("Failed to set FEC_READY in the sink\n"); + drm_dbg_kms(&i915->drm, + "Failed to set FEC_READY in the sink\n"); } static void intel_ddi_enable_fec(struct intel_encoder *encoder, @@ -2955,7 +3068,8 @@ static void intel_ddi_enable_fec(struct intel_encoder *encoder, if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status, DP_TP_STATUS_FEC_ENABLE_LIVE, 1)) - DRM_ERROR("Timed out waiting for FEC Enable Status\n"); + drm_err(&dev_priv->drm, + "Timed out waiting for FEC Enable Status\n"); } static void intel_ddi_disable_fec_state(struct intel_encoder *encoder, @@ -2975,7 +3089,8 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder, intel_de_posting_read(dev_priv, intel_dp->regs.dp_tp_ctl); } -static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder, +static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3115,7 +3230,8 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_dsc_enable(encoder, crtc_state); } -static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder, +static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3188,16 +3304,17 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_dsc_enable(encoder, crtc_state); } -static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, +static void intel_ddi_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); if (INTEL_GEN(dev_priv) >= 12) - tgl_ddi_pre_enable_dp(encoder, crtc_state, conn_state); + tgl_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state); else - hsw_ddi_pre_enable_dp(encoder, crtc_state, conn_state); + hsw_ddi_pre_enable_dp(state, encoder, crtc_state, conn_state); /* MST will call a setting of MSA after an allocating of Virtual Channel * from MST encoder pre_enable callback. @@ -3209,7 +3326,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, } } -static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, +static void intel_ddi_pre_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3249,7 +3367,8 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, crtc_state, conn_state); } -static void intel_ddi_pre_enable(struct intel_encoder *encoder, +static void intel_ddi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3278,12 +3397,14 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder, intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { - intel_ddi_pre_enable_hdmi(encoder, crtc_state, conn_state); + intel_ddi_pre_enable_hdmi(state, encoder, crtc_state, + conn_state); } else { struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder); - intel_ddi_pre_enable_dp(encoder, crtc_state, conn_state); + intel_ddi_pre_enable_dp(state, encoder, crtc_state, + conn_state); if (lspcon->active) { struct intel_digital_port *dig_port = enc_to_dig_port(encoder); @@ -3326,7 +3447,8 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder, intel_wait_ddi_buf_idle(dev_priv, port); } -static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, +static void intel_ddi_post_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3382,7 +3504,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, intel_ddi_clk_disable(encoder); } -static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder, +static void intel_ddi_post_disable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3405,22 +3528,8 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder, intel_dp_dual_mode_set_tmds_output(intel_hdmi, false); } -static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - - if (old_crtc_state->master_transcoder == INVALID_TRANSCODER) - return; - - DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n", - transcoder_name(old_crtc_state->cpu_transcoder)); - - intel_de_write(dev_priv, - TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0); -} - -static void intel_ddi_post_disable(struct intel_encoder *encoder, +static void intel_ddi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3434,9 +3543,6 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder, intel_disable_pipe(old_crtc_state); - if (INTEL_GEN(dev_priv) >= 11) - icl_disable_transcoder_port_sync(old_crtc_state); - intel_ddi_disable_transcoder_func(old_crtc_state); intel_dsc_disable(old_crtc_state); @@ -3461,11 +3567,11 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder, */ if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI)) - intel_ddi_post_disable_hdmi(encoder, - old_crtc_state, old_conn_state); + intel_ddi_post_disable_hdmi(state, encoder, old_crtc_state, + old_conn_state); else - intel_ddi_post_disable_dp(encoder, - old_crtc_state, old_conn_state); + intel_ddi_post_disable_dp(state, encoder, old_crtc_state, + old_conn_state); if (INTEL_GEN(dev_priv) >= 11) icl_unmap_plls_to_ports(encoder); @@ -3478,7 +3584,8 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder, intel_tc_port_put_link(dig_port); } -void intel_ddi_fdi_post_disable(struct intel_encoder *encoder, +void intel_ddi_fdi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3512,7 +3619,43 @@ void intel_ddi_fdi_post_disable(struct intel_encoder *encoder, intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), val); } -static void intel_enable_ddi_dp(struct intel_encoder *encoder, +static void trans_port_sync_stop_link_train(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + const struct drm_connector_state *conn_state; + struct drm_connector *conn; + int i; + + if (!crtc_state->sync_mode_slaves_mask) + return; + + for_each_new_connector_in_state(&state->base, conn, conn_state, i) { + struct intel_encoder *slave_encoder = + to_intel_encoder(conn_state->best_encoder); + struct intel_crtc *slave_crtc = to_intel_crtc(conn_state->crtc); + const struct intel_crtc_state *slave_crtc_state; + + if (!slave_crtc) + continue; + + slave_crtc_state = + intel_atomic_get_new_crtc_state(state, slave_crtc); + + if (slave_crtc_state->master_transcoder != + crtc_state->cpu_transcoder) + continue; + + intel_dp_stop_link_train(enc_to_intel_dp(slave_encoder)); + } + + usleep_range(200, 400); + + intel_dp_stop_link_train(enc_to_intel_dp(encoder)); +} + +static void intel_enable_ddi_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3531,6 +3674,8 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder, if (crtc_state->has_audio) intel_audio_codec_enable(encoder, crtc_state, conn_state); + + trans_port_sync_stop_link_train(state, encoder, crtc_state); } static i915_reg_t @@ -3553,7 +3698,8 @@ gen9_chicken_trans_reg_by_port(struct drm_i915_private *dev_priv, return CHICKEN_TRANS(trans[port]); } -static void intel_enable_ddi_hdmi(struct intel_encoder *encoder, +static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3565,9 +3711,9 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder, if (!intel_hdmi_handle_sink_scrambling(encoder, connector, crtc_state->hdmi_high_tmds_clock_ratio, crtc_state->hdmi_scrambling)) - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Failed to configure sink " - "scrambling/TMDS bit clock ratio\n", - connector->base.id, connector->name); + drm_dbg_kms(&dev_priv->drm, + "[CONNECTOR:%d:%s] Failed to configure sink scrambling/TMDS bit clock ratio\n", + connector->base.id, connector->name); /* Display WA #1143: skl,kbl,cfl */ if (IS_GEN9_BC(dev_priv)) { @@ -3615,7 +3761,8 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder, intel_audio_codec_enable(encoder, crtc_state, conn_state); } -static void intel_enable_ddi(struct intel_encoder *encoder, +static void intel_enable_ddi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3626,9 +3773,9 @@ static void intel_enable_ddi(struct intel_encoder *encoder, intel_crtc_vblank_on(crtc_state); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - intel_enable_ddi_hdmi(encoder, crtc_state, conn_state); + intel_enable_ddi_hdmi(state, encoder, crtc_state, conn_state); else - intel_enable_ddi_dp(encoder, crtc_state, conn_state); + intel_enable_ddi_dp(state, encoder, crtc_state, conn_state); /* Enable hdcp if it's desired */ if (conn_state->content_protection == @@ -3638,7 +3785,8 @@ static void intel_enable_ddi(struct intel_encoder *encoder, (u8)conn_state->hdcp_content_type); } -static void intel_disable_ddi_dp(struct intel_encoder *encoder, +static void intel_disable_ddi_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3658,10 +3806,12 @@ static void intel_disable_ddi_dp(struct intel_encoder *encoder, false); } -static void intel_disable_ddi_hdmi(struct intel_encoder *encoder, +static void intel_disable_ddi_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct drm_connector *connector = old_conn_state->connector; if (old_crtc_state->has_audio) @@ -3670,23 +3820,28 @@ static void intel_disable_ddi_hdmi(struct intel_encoder *encoder, if (!intel_hdmi_handle_sink_scrambling(encoder, connector, false, false)) - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Failed to reset sink scrambling/TMDS bit clock ratio\n", - connector->base.id, connector->name); + drm_dbg_kms(&i915->drm, + "[CONNECTOR:%d:%s] Failed to reset sink scrambling/TMDS bit clock ratio\n", + connector->base.id, connector->name); } -static void intel_disable_ddi(struct intel_encoder *encoder, +static void intel_disable_ddi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { intel_hdcp_disable(to_intel_connector(old_conn_state->connector)); if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_HDMI)) - intel_disable_ddi_hdmi(encoder, old_crtc_state, old_conn_state); + intel_disable_ddi_hdmi(state, encoder, old_crtc_state, + old_conn_state); else - intel_disable_ddi_dp(encoder, old_crtc_state, old_conn_state); + intel_disable_ddi_dp(state, encoder, old_crtc_state, + old_conn_state); } -static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder, +static void intel_ddi_update_pipe_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3697,18 +3852,20 @@ static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder, intel_psr_update(intel_dp, crtc_state); intel_edp_drrs_enable(intel_dp, crtc_state); - intel_panel_update_backlight(encoder, crtc_state, conn_state); + intel_panel_update_backlight(state, encoder, crtc_state, conn_state); } -static void intel_ddi_update_pipe(struct intel_encoder *encoder, +static void intel_ddi_update_pipe(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - intel_ddi_update_pipe_dp(encoder, crtc_state, conn_state); + intel_ddi_update_pipe_dp(state, encoder, crtc_state, + conn_state); - intel_hdcp_update_pipe(encoder, crtc_state, conn_state); + intel_hdcp_update_pipe(state, encoder, crtc_state, conn_state); } static void @@ -3737,7 +3894,8 @@ intel_ddi_update_complete(struct intel_atomic_state *state, } static void -intel_ddi_pre_pll_enable(struct intel_encoder *encoder, +intel_ddi_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -3837,6 +3995,66 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, crtc_state->min_voltage_level = 2; } +static enum transcoder bdw_transcoder_master_readout(struct drm_i915_private *dev_priv, + enum transcoder cpu_transcoder) +{ + u32 master_select; + + if (INTEL_GEN(dev_priv) >= 11) { + u32 ctl2 = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL2(cpu_transcoder)); + + if ((ctl2 & PORT_SYNC_MODE_ENABLE) == 0) + return INVALID_TRANSCODER; + + master_select = REG_FIELD_GET(PORT_SYNC_MODE_MASTER_SELECT_MASK, ctl2); + } else { + u32 ctl = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); + + if ((ctl & TRANS_DDI_PORT_SYNC_ENABLE) == 0) + return INVALID_TRANSCODER; + + master_select = REG_FIELD_GET(TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK, ctl); + } + + if (master_select == 0) + return TRANSCODER_EDP; + else + return master_select - 1; +} + +static void bdw_get_trans_port_sync_config(struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + u32 transcoders = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + BIT(TRANSCODER_C) | BIT(TRANSCODER_D); + enum transcoder cpu_transcoder; + + crtc_state->master_transcoder = + bdw_transcoder_master_readout(dev_priv, crtc_state->cpu_transcoder); + + for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) { + enum intel_display_power_domain power_domain; + intel_wakeref_t trans_wakeref; + + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + trans_wakeref = intel_display_power_get_if_enabled(dev_priv, + power_domain); + + if (!trans_wakeref) + continue; + + if (bdw_transcoder_master_readout(dev_priv, cpu_transcoder) == + crtc_state->cpu_transcoder) + crtc_state->sync_mode_slaves_mask |= BIT(cpu_transcoder); + + intel_display_power_put(dev_priv, power_domain, trans_wakeref); + } + + drm_WARN_ON(&dev_priv->drm, + crtc_state->master_transcoder != INVALID_TRANSCODER && + crtc_state->sync_mode_slaves_mask); +} + void intel_ddi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3922,9 +4140,10 @@ void intel_ddi_get_config(struct intel_encoder *encoder, pipe_config->fec_enable = intel_de_read(dev_priv, dp_tp_ctl) & DP_TP_CTL_FEC_ENABLE; - DRM_DEBUG_KMS("[ENCODER:%d:%s] Fec status: %u\n", - encoder->base.base.id, encoder->base.name, - pipe_config->fec_enable); + drm_dbg_kms(&dev_priv->drm, + "[ENCODER:%d:%s] Fec status: %u\n", + encoder->base.base.id, encoder->base.name, + pipe_config->fec_enable); } break; @@ -3961,8 +4180,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder, * up by the BIOS, and thus we can't get the mode at module * load. */ - DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n", - pipe_config->pipe_bpp, dev_priv->vbt.edp.bpp); + drm_dbg_kms(&dev_priv->drm, + "pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n", + pipe_config->pipe_bpp, dev_priv->vbt.edp.bpp); dev_priv->vbt.edp.bpp = pipe_config->pipe_bpp; } @@ -3988,6 +4208,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_read_infoframe(encoder, pipe_config, HDMI_INFOFRAME_TYPE_DRM, &pipe_config->infoframes.drm); + + if (INTEL_GEN(dev_priv) >= 8) + bdw_get_trans_port_sync_config(pipe_config); } static enum intel_output_type @@ -4017,7 +4240,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder, enum port port = encoder->port; int ret; - if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A) + if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP) && port == PORT_A) pipe_config->cpu_transcoder = TRANSCODER_EDP; if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI)) { @@ -4089,7 +4312,11 @@ intel_ddi_port_sync_transcoders(const struct intel_crtc_state *ref_crtc_state, u8 transcoders = 0; int i; - if (INTEL_GEN(dev_priv) < 11) + /* + * We don't enable port sync on BDW due to missing w/as and + * due to not having adjusted the modeset sequence appropriately. + */ + if (INTEL_GEN(dev_priv) < 9) return 0; if (!intel_crtc_has_type(ref_crtc_state, INTEL_OUTPUT_DP)) @@ -4121,12 +4348,13 @@ static int intel_ddi_compute_config_late(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state, struct drm_connector_state *conn_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct drm_connector *connector = conn_state->connector; u8 port_sync_transcoders = 0; - DRM_DEBUG_KMS("[ENCODER:%d:%s] [CRTC:%d:%s]", - encoder->base.base.id, encoder->base.name, - crtc_state->uapi.crtc->base.id, crtc_state->uapi.crtc->name); + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] [CRTC:%d:%s]", + encoder->base.base.id, encoder->base.name, + crtc_state->uapi.crtc->base.id, crtc_state->uapi.crtc->name); if (connector->has_tile) port_sync_transcoders = intel_ddi_port_sync_transcoders(crtc_state, @@ -4265,7 +4493,8 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder, ret = drm_scdc_readb(adapter, SCDC_TMDS_CONFIG, &config); if (ret < 0) { - DRM_ERROR("Failed to read TMDS config: %d\n", ret); + drm_err(&dev_priv->drm, "Failed to read TMDS config: %d\n", + ret); return 0; } @@ -4289,15 +4518,17 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder, static enum intel_hotplug_state intel_ddi_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received) + struct intel_connector *connector) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + enum phy phy = intel_port_to_phy(i915, encoder->port); + bool is_tc = intel_phy_is_tc(i915, phy); struct drm_modeset_acquire_ctx ctx; enum intel_hotplug_state state; int ret; - state = intel_encoder_hotplug(encoder, connector, irq_received); + state = intel_encoder_hotplug(encoder, connector); drm_modeset_acquire_init(&ctx, 0); @@ -4335,8 +4566,15 @@ intel_ddi_hotplug(struct intel_encoder *encoder, * valid EDID. To solve this schedule another detection cycle if this * time around we didn't detect any change in the sink's connection * status. + * + * Type-c connectors which get their HPD signal deasserted then + * reasserted, without unplugging/replugging the sink from the + * connector, introduce a delay until the AUX channel communication + * becomes functional. Retry the detection for 5 seconds on type-c + * connectors to account for this delay. */ - if (state == INTEL_HOTPLUG_UNCHANGED && irq_received && + if (state == INTEL_HOTPLUG_UNCHANGED && + connector->hotplug_retries < (is_tc ? 5 : 1) && !dig_port->dp.is_mst) state = INTEL_HOTPLUG_RETRY; @@ -4411,7 +4649,8 @@ intel_ddi_max_lanes(struct intel_digital_port *intel_dport) * so we use the proper lane count for our calculations. */ if (intel_ddi_a_force_4_lanes(intel_dport)) { - DRM_DEBUG_KMS("Forcing DDI_A_4_LANES for port A\n"); + drm_dbg_kms(&dev_priv->drm, + "Forcing DDI_A_4_LANES for port A\n"); intel_dport->saved_port_bits |= DDI_A_4_LANES; max_lanes = 4; } @@ -4439,12 +4678,14 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) init_dp = true; init_lspcon = true; init_hdmi = false; - DRM_DEBUG_KMS("VBT says port %c has lspcon\n", port_name(port)); + drm_dbg_kms(&dev_priv->drm, "VBT says port %c has lspcon\n", + port_name(port)); } if (!init_dp && !init_hdmi) { - DRM_DEBUG_KMS("VBT says port %c is not DVI/HDMI/DP compatible, respect it\n", - port_name(port)); + drm_dbg_kms(&dev_priv->drm, + "VBT says port %c is not DVI/HDMI/DP compatible, respect it\n", + port_name(port)); return; } @@ -4523,14 +4764,16 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) if (init_lspcon) { if (lspcon_init(intel_dig_port)) /* TODO: handle hdmi info frame part */ - DRM_DEBUG_KMS("LSPCON init success on port %c\n", - port_name(port)); + drm_dbg_kms(&dev_priv->drm, + "LSPCON init success on port %c\n", + port_name(port)); else /* * LSPCON init faied, but DP init was success, so * lets try to drive as DP++ port. */ - DRM_ERROR("LSPCON init failed on port %c\n", + drm_err(&dev_priv->drm, + "LSPCON init failed on port %c\n", port_name(port)); } diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 55fd72b901fe..de4cd877c002 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -17,7 +17,8 @@ struct intel_dp; struct intel_dpll_hw_state; struct intel_encoder; -void intel_ddi_fdi_post_disable(struct intel_encoder *intel_encoder, +void intel_ddi_fdi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *intel_encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state); void hsw_fdi_link_train(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 8f23c4d51c33..af5b4055b38a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -525,7 +525,7 @@ skl_wa_827(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable) intel_de_read(dev_priv, CLKGATE_DIS_PSL(pipe)) & ~(DUPS1_GATING_DIS | DUPS2_GATING_DIS)); } -/* Wa_2006604312:icl */ +/* Wa_2006604312:icl,ehl */ static void icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable) @@ -544,17 +544,23 @@ needs_modeset(const struct intel_crtc_state *state) return drm_atomic_crtc_needs_modeset(&state->uapi); } -bool -is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state) +static bool +is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state) { - return (crtc_state->master_transcoder != INVALID_TRANSCODER || - crtc_state->sync_mode_slaves_mask); + return crtc_state->master_transcoder != INVALID_TRANSCODER; } static bool -is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state) +is_trans_port_sync_master(const struct intel_crtc_state *crtc_state) { - return crtc_state->master_transcoder != INVALID_TRANSCODER; + return crtc_state->sync_mode_slaves_mask != 0; +} + +bool +is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state) +{ + return is_trans_port_sync_master(crtc_state) || + is_trans_port_sync_slave(crtc_state); } /* @@ -620,45 +626,43 @@ int chv_calc_dpll_params(int refclk, struct dpll *clock) return clock->dot / 5; } -#define INTELPllInvalid(s) do { /* DRM_DEBUG(s); */ return false; } while (0) - /* * Returns whether the given set of divisors are valid for a given refclk with * the given connectors. */ -static bool intel_PLL_is_valid(struct drm_i915_private *dev_priv, +static bool intel_pll_is_valid(struct drm_i915_private *dev_priv, const struct intel_limit *limit, const struct dpll *clock) { - if (clock->n < limit->n.min || limit->n.max < clock->n) - INTELPllInvalid("n out of range\n"); - if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1) - INTELPllInvalid("p1 out of range\n"); - if (clock->m2 < limit->m2.min || limit->m2.max < clock->m2) - INTELPllInvalid("m2 out of range\n"); - if (clock->m1 < limit->m1.min || limit->m1.max < clock->m1) - INTELPllInvalid("m1 out of range\n"); + if (clock->n < limit->n.min || limit->n.max < clock->n) + return false; + if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1) + return false; + if (clock->m2 < limit->m2.min || limit->m2.max < clock->m2) + return false; + if (clock->m1 < limit->m1.min || limit->m1.max < clock->m1) + return false; if (!IS_PINEVIEW(dev_priv) && !IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv) && !IS_GEN9_LP(dev_priv)) if (clock->m1 <= clock->m2) - INTELPllInvalid("m1 <= m2\n"); + return false; if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv) && !IS_GEN9_LP(dev_priv)) { if (clock->p < limit->p.min || limit->p.max < clock->p) - INTELPllInvalid("p out of range\n"); + return false; if (clock->m < limit->m.min || limit->m.max < clock->m) - INTELPllInvalid("m out of range\n"); + return false; } if (clock->vco < limit->vco.min || limit->vco.max < clock->vco) - INTELPllInvalid("vco out of range\n"); + return false; /* XXX: We may need to be checking "Dot clock" depending on the multiplier, * connector, etc., rather than just a single range. */ if (clock->dot < limit->dot.min || limit->dot.max < clock->dot) - INTELPllInvalid("dot out of range\n"); + return false; return true; } @@ -725,7 +729,7 @@ i9xx_find_best_dpll(const struct intel_limit *limit, int this_err; i9xx_calc_dpll_params(refclk, &clock); - if (!intel_PLL_is_valid(to_i915(dev), + if (!intel_pll_is_valid(to_i915(dev), limit, &clock)) continue; @@ -781,7 +785,7 @@ pnv_find_best_dpll(const struct intel_limit *limit, int this_err; pnv_calc_dpll_params(refclk, &clock); - if (!intel_PLL_is_valid(to_i915(dev), + if (!intel_pll_is_valid(to_i915(dev), limit, &clock)) continue; @@ -842,7 +846,7 @@ g4x_find_best_dpll(const struct intel_limit *limit, int this_err; i9xx_calc_dpll_params(refclk, &clock); - if (!intel_PLL_is_valid(to_i915(dev), + if (!intel_pll_is_valid(to_i915(dev), limit, &clock)) continue; @@ -939,7 +943,7 @@ vlv_find_best_dpll(const struct intel_limit *limit, vlv_calc_dpll_params(refclk, &clock); - if (!intel_PLL_is_valid(to_i915(dev), + if (!intel_pll_is_valid(to_i915(dev), limit, &clock)) continue; @@ -1008,7 +1012,7 @@ chv_find_best_dpll(const struct intel_limit *limit, chv_calc_dpll_params(refclk, &clock); - if (!intel_PLL_is_valid(to_i915(dev), limit, &clock)) + if (!intel_pll_is_valid(to_i915(dev), limit, &clock)) continue; if (!vlv_PLL_is_optimal(dev, target, &clock, best_clock, @@ -2910,6 +2914,7 @@ intel_fb_plane_get_subsampling(int *hsub, int *vsub, static int intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y) { + struct drm_i915_private *i915 = to_i915(fb->dev); struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); int main_plane; int hsub, vsub; @@ -2938,7 +2943,8 @@ intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y) * x/y offsets must match between CCS and the main surface. */ if (main_x != ccs_x || main_y != ccs_y) { - DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n", + drm_dbg_kms(&i915->drm, + "Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n", main_x, main_y, ccs_x, ccs_y, intel_fb->normal[main_plane].x, @@ -3336,6 +3342,8 @@ int skl_format_to_fourcc(int format, bool rgb_order, bool alpha) return DRM_FORMAT_RGB565; case PLANE_CTL_FORMAT_NV12: return DRM_FORMAT_NV12; + case PLANE_CTL_FORMAT_XYUV: + return DRM_FORMAT_XYUV8888; case PLANE_CTL_FORMAT_P010: return DRM_FORMAT_P010; case PLANE_CTL_FORMAT_P012: @@ -4580,6 +4588,8 @@ static u32 skl_plane_ctl_format(u32 pixel_format) case DRM_FORMAT_XRGB16161616F: case DRM_FORMAT_ARGB16161616F: return PLANE_CTL_FORMAT_XRGB_16161616F; + case DRM_FORMAT_XYUV8888: + return PLANE_CTL_FORMAT_XYUV; case DRM_FORMAT_YUYV: return PLANE_CTL_FORMAT_YUV422 | PLANE_CTL_YUV422_YUYV; case DRM_FORMAT_YVYU: @@ -4998,37 +5008,6 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc) intel_de_write(dev_priv, PIPE_CHICKEN(pipe), tmp); } -static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 trans_ddi_func_ctl2_val; - u8 master_select; - - /* - * Configure the master select and enable Transcoder Port Sync for - * Slave CRTCs transcoder. - */ - if (crtc_state->master_transcoder == INVALID_TRANSCODER) - return; - - if (crtc_state->master_transcoder == TRANSCODER_EDP) - master_select = 0; - else - master_select = crtc_state->master_transcoder + 1; - - /* Set the master select bits for Tranascoder Port Sync */ - trans_ddi_func_ctl2_val = (PORT_SYNC_MODE_MASTER_SELECT(master_select) & - PORT_SYNC_MODE_MASTER_SELECT_MASK) << - PORT_SYNC_MODE_MASTER_SELECT_SHIFT; - /* Enable Transcoder Port Sync */ - trans_ddi_func_ctl2_val |= PORT_SYNC_MODE_ENABLE; - - intel_de_write(dev_priv, - TRANS_DDI_FUNC_CTL2(crtc_state->cpu_transcoder), - trans_ddi_func_ctl2_val); -} - static void intel_fdi_normal_train(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -6200,6 +6179,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state, case DRM_FORMAT_UYVY: case DRM_FORMAT_VYUY: case DRM_FORMAT_NV12: + case DRM_FORMAT_XYUV8888: case DRM_FORMAT_P010: case DRM_FORMAT_P012: case DRM_FORMAT_P016: @@ -6463,8 +6443,8 @@ static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - /* Wa_2006604312:icl */ - if (crtc_state->scaler_state.scaler_users > 0 && IS_ICELAKE(dev_priv)) + /* Wa_2006604312:icl,ehl */ + if (crtc_state->scaler_state.scaler_users > 0 && IS_GEN(dev_priv, 11)) return true; return false; @@ -6534,7 +6514,7 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, needs_nv12_wa(new_crtc_state)) skl_wa_827(dev_priv, pipe, true); - /* Wa_2006604312:icl */ + /* Wa_2006604312:icl,ehl */ if (!needs_scalerclk_wa(old_crtc_state) && needs_scalerclk_wa(new_crtc_state)) icl_wa_scalerclkgating(dev_priv, pipe, true); @@ -6720,7 +6700,8 @@ static void intel_encoders_pre_pll_enable(struct intel_atomic_state *state, continue; if (encoder->pre_pll_enable) - encoder->pre_pll_enable(encoder, crtc_state, conn_state); + encoder->pre_pll_enable(state, encoder, + crtc_state, conn_state); } } @@ -6741,7 +6722,8 @@ static void intel_encoders_pre_enable(struct intel_atomic_state *state, continue; if (encoder->pre_enable) - encoder->pre_enable(encoder, crtc_state, conn_state); + encoder->pre_enable(state, encoder, + crtc_state, conn_state); } } @@ -6762,7 +6744,8 @@ static void intel_encoders_enable(struct intel_atomic_state *state, continue; if (encoder->enable) - encoder->enable(encoder, crtc_state, conn_state); + encoder->enable(state, encoder, + crtc_state, conn_state); intel_opregion_notify_encoder(encoder, true); } } @@ -6785,7 +6768,8 @@ static void intel_encoders_disable(struct intel_atomic_state *state, intel_opregion_notify_encoder(encoder, false); if (encoder->disable) - encoder->disable(encoder, old_crtc_state, old_conn_state); + encoder->disable(state, encoder, + old_crtc_state, old_conn_state); } } @@ -6806,7 +6790,8 @@ static void intel_encoders_post_disable(struct intel_atomic_state *state, continue; if (encoder->post_disable) - encoder->post_disable(encoder, old_crtc_state, old_conn_state); + encoder->post_disable(state, encoder, + old_crtc_state, old_conn_state); } } @@ -6827,7 +6812,8 @@ static void intel_encoders_post_pll_disable(struct intel_atomic_state *state, continue; if (encoder->post_pll_disable) - encoder->post_pll_disable(encoder, old_crtc_state, old_conn_state); + encoder->post_pll_disable(state, encoder, + old_crtc_state, old_conn_state); } } @@ -6848,7 +6834,8 @@ static void intel_encoders_update_pipe(struct intel_atomic_state *state, continue; if (encoder->update_pipe) - encoder->update_pipe(encoder, crtc_state, conn_state); + encoder->update_pipe(state, encoder, + crtc_state, conn_state); } } @@ -7037,9 +7024,6 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, if (!transcoder_is_dsi(cpu_transcoder)) intel_set_pipe_timings(new_crtc_state); - if (INTEL_GEN(dev_priv) >= 11) - icl_enable_trans_port_sync(new_crtc_state); - intel_set_pipe_src_size(new_crtc_state); if (cpu_transcoder != TRANSCODER_EDP && @@ -9398,7 +9382,6 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = NULL; - pipe_config->master_transcoder = INVALID_TRANSCODER; ret = false; @@ -10622,7 +10605,6 @@ static bool ilk_get_pipe_config(struct intel_crtc *crtc, pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = NULL; - pipe_config->master_transcoder = INVALID_TRANSCODER; ret = false; tmp = intel_de_read(dev_priv, PIPECONF(crtc->pipe)); @@ -10891,7 +10873,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, panel_transcoder_mask |= BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1); - if (HAS_TRANSCODER_EDP(dev_priv)) + if (HAS_TRANSCODER(dev_priv, TRANSCODER_EDP)) panel_transcoder_mask |= BIT(TRANSCODER_EDP); /* @@ -11085,61 +11067,6 @@ static void hsw_get_ddi_port_state(struct intel_crtc *crtc, } } -static enum transcoder transcoder_master_readout(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) -{ - u32 trans_port_sync, master_select; - - trans_port_sync = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL2(cpu_transcoder)); - - if ((trans_port_sync & PORT_SYNC_MODE_ENABLE) == 0) - return INVALID_TRANSCODER; - - master_select = trans_port_sync & - PORT_SYNC_MODE_MASTER_SELECT_MASK; - if (master_select == 0) - return TRANSCODER_EDP; - else - return master_select - 1; -} - -static void icl_get_trans_port_sync_config(struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - u32 transcoders; - enum transcoder cpu_transcoder; - - crtc_state->master_transcoder = transcoder_master_readout(dev_priv, - crtc_state->cpu_transcoder); - - transcoders = BIT(TRANSCODER_A) | - BIT(TRANSCODER_B) | - BIT(TRANSCODER_C) | - BIT(TRANSCODER_D); - for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) { - enum intel_display_power_domain power_domain; - intel_wakeref_t trans_wakeref; - - power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); - trans_wakeref = intel_display_power_get_if_enabled(dev_priv, - power_domain); - - if (!trans_wakeref) - continue; - - if (transcoder_master_readout(dev_priv, cpu_transcoder) == - crtc_state->cpu_transcoder) - crtc_state->sync_mode_slaves_mask |= BIT(cpu_transcoder); - - intel_display_power_put(dev_priv, power_domain, trans_wakeref); - } - - drm_WARN_ON(&dev_priv->drm, - crtc_state->master_transcoder != INVALID_TRANSCODER && - crtc_state->sync_mode_slaves_mask); -} - static bool hsw_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config) { @@ -11271,10 +11198,6 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = 1; } - if (INTEL_GEN(dev_priv) >= 11 && - !transcoder_is_dsi(pipe_config->cpu_transcoder)) - icl_get_trans_port_sync_config(pipe_config); - out: for_each_power_domain(power_domain, power_domain_mask) intel_display_power_put(dev_priv, @@ -12377,10 +12300,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat * only combine the results from all planes in the current place? */ if (!is_crtc_enabled) { - plane_state->uapi.visible = visible = false; - crtc_state->active_planes &= ~BIT(plane->id); - crtc_state->data_rate[plane->id] = 0; - crtc_state->min_cdclk[plane->id] = 0; + intel_plane_set_invisible(crtc_state, plane_state); + visible = false; } if (!was_visible && !visible) @@ -12886,16 +12807,17 @@ compute_baseline_pipe_bpp(struct intel_crtc *crtc, return 0; } -static void intel_dump_crtc_timings(const struct drm_display_mode *mode) +static void intel_dump_crtc_timings(struct drm_i915_private *i915, + const struct drm_display_mode *mode) { - DRM_DEBUG_KMS("crtc timings: %d %d %d %d %d %d %d %d %d, " - "type: 0x%x flags: 0x%x\n", - mode->crtc_clock, - mode->crtc_hdisplay, mode->crtc_hsync_start, - mode->crtc_hsync_end, mode->crtc_htotal, - mode->crtc_vdisplay, mode->crtc_vsync_start, - mode->crtc_vsync_end, mode->crtc_vtotal, - mode->type, mode->flags); + drm_dbg_kms(&i915->drm, "crtc timings: %d %d %d %d %d %d %d %d %d, " + "type: 0x%x flags: 0x%x\n", + mode->crtc_clock, + mode->crtc_hdisplay, mode->crtc_hsync_start, + mode->crtc_hsync_end, mode->crtc_htotal, + mode->crtc_vdisplay, mode->crtc_vsync_start, + mode->crtc_vsync_end, mode->crtc_vtotal, + mode->type, mode->flags); } static inline void @@ -13042,6 +12964,11 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config, transcoder_name(pipe_config->cpu_transcoder), pipe_config->pipe_bpp, pipe_config->dither); + drm_dbg_kms(&dev_priv->drm, + "port sync: master transcoder: %s, slave transcoder bitmask = 0x%x\n", + transcoder_name(pipe_config->master_transcoder), + pipe_config->sync_mode_slaves_mask); + if (pipe_config->has_pch_encoder) intel_dump_m_n_config(pipe_config, "fdi", pipe_config->fdi_lanes, @@ -13079,7 +13006,7 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config, drm_mode_debug_printmodeline(&pipe_config->hw.mode); drm_dbg_kms(&dev_priv->drm, "adjusted mode:\n"); drm_mode_debug_printmodeline(&pipe_config->hw.adjusted_mode); - intel_dump_crtc_timings(&pipe_config->hw.adjusted_mode); + intel_dump_crtc_timings(dev_priv, &pipe_config->hw.adjusted_mode); drm_dbg_kms(&dev_priv->drm, "port clock: %d, pipe src size: %dx%d, pixel rate %d\n", pipe_config->port_clock, @@ -14748,8 +14675,8 @@ 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; } @@ -14999,11 +14926,13 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, } static void commit_pipe_config(struct intel_atomic_state *state, - struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) + struct intel_crtc *crtc) { - struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(state->base.dev); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + const struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); bool modeset = needs_modeset(new_crtc_state); /* @@ -15029,22 +14958,35 @@ static void commit_pipe_config(struct intel_atomic_state *state, dev_priv->display.atomic_update_watermarks(state, crtc); } -static void intel_update_crtc(struct intel_crtc *crtc, - struct intel_atomic_state *state, - struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) +static void intel_enable_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - bool modeset = needs_modeset(new_crtc_state); + const struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); - if (modeset) { - intel_crtc_update_active_timings(new_crtc_state); + if (!needs_modeset(new_crtc_state)) + return; - dev_priv->display.crtc_enable(state, crtc); + intel_crtc_update_active_timings(new_crtc_state); - /* vblanks work again, re-enable pipe CRC. */ - intel_crtc_enable_pipe_crc(crtc); - } else { + dev_priv->display.crtc_enable(state, crtc); + + /* vblanks work again, re-enable pipe CRC. */ + intel_crtc_enable_pipe_crc(crtc); +} + +static void intel_update_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + bool modeset = needs_modeset(new_crtc_state); + + if (!modeset) { if (new_crtc_state->preload_luts && (new_crtc_state->uapi.color_mgmt_changed || new_crtc_state->update_pipe)) @@ -15064,7 +15006,7 @@ static void intel_update_crtc(struct intel_crtc *crtc, /* Perform vblank evasion around commit operation */ intel_pipe_update_start(new_crtc_state); - commit_pipe_config(state, old_crtc_state, new_crtc_state); + commit_pipe_config(state, crtc); if (INTEL_GEN(dev_priv) >= 9) skl_update_planes_on_crtc(state, crtc); @@ -15084,18 +15026,6 @@ static void intel_update_crtc(struct intel_crtc *crtc, intel_crtc_arm_fifo_underrun(crtc, new_crtc_state); } -static struct intel_crtc *intel_get_slave_crtc(const struct intel_crtc_state *new_crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(new_crtc_state->uapi.crtc->dev); - enum transcoder slave_transcoder; - - drm_WARN_ON(&dev_priv->drm, - !is_power_of_2(new_crtc_state->sync_mode_slaves_mask)); - - slave_transcoder = ffs(new_crtc_state->sync_mode_slaves_mask) - 1; - return intel_get_crtc_for_pipe(dev_priv, - (enum pipe)slave_transcoder); -} static void intel_old_crtc_state_disables(struct intel_atomic_state *state, struct intel_crtc_state *old_crtc_state, @@ -15171,129 +15101,19 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state) static void intel_commit_modeset_enables(struct intel_atomic_state *state) { + struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; - struct intel_crtc_state *old_crtc_state, *new_crtc_state; int i; - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (!new_crtc_state->hw.active) continue; - intel_update_crtc(crtc, state, old_crtc_state, - new_crtc_state); + intel_enable_crtc(state, crtc); + intel_update_crtc(state, crtc); } } -static void intel_crtc_enable_trans_port_sync(struct intel_crtc *crtc, - struct intel_atomic_state *state, - struct intel_crtc_state *new_crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - - intel_crtc_update_active_timings(new_crtc_state); - dev_priv->display.crtc_enable(state, crtc); - intel_crtc_enable_pipe_crc(crtc); -} - -static void intel_set_dp_tp_ctl_normal(struct intel_crtc *crtc, - struct intel_atomic_state *state) -{ - struct drm_connector *uninitialized_var(conn); - struct drm_connector_state *conn_state; - struct intel_dp *intel_dp; - int i; - - for_each_new_connector_in_state(&state->base, conn, conn_state, i) { - if (conn_state->crtc == &crtc->base) - break; - } - intel_dp = intel_attached_dp(to_intel_connector(conn)); - intel_dp_stop_link_train(intel_dp); -} - -/* - * TODO: This is only called from port sync and it is identical to what will be - * executed again in intel_update_crtc() over port sync pipes - */ -static void intel_post_crtc_enable_updates(struct intel_crtc *crtc, - struct intel_atomic_state *state) -{ - struct intel_crtc_state *new_crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); - bool modeset = needs_modeset(new_crtc_state); - - if (new_crtc_state->update_pipe && !new_crtc_state->enable_fbc) - intel_fbc_disable(crtc); - else - intel_fbc_enable(state, crtc); - - /* Perform vblank evasion around commit operation */ - intel_pipe_update_start(new_crtc_state); - commit_pipe_config(state, old_crtc_state, new_crtc_state); - skl_update_planes_on_crtc(state, crtc); - intel_pipe_update_end(new_crtc_state); - - /* - * We usually enable FIFO underrun interrupts as part of the - * CRTC enable sequence during modesets. But when we inherit a - * valid pipe configuration from the BIOS we need to take care - * of enabling them on the CRTC's first fastset. - */ - if (new_crtc_state->update_pipe && !modeset && - old_crtc_state->hw.mode.private_flags & I915_MODE_FLAG_INHERITED) - intel_crtc_arm_fifo_underrun(crtc, new_crtc_state); -} - -static void intel_update_trans_port_sync_crtcs(struct intel_crtc *crtc, - struct intel_atomic_state *state, - struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) -{ - struct drm_i915_private *i915 = to_i915(crtc->base.dev); - struct intel_crtc *slave_crtc = intel_get_slave_crtc(new_crtc_state); - struct intel_crtc_state *new_slave_crtc_state = - intel_atomic_get_new_crtc_state(state, slave_crtc); - struct intel_crtc_state *old_slave_crtc_state = - intel_atomic_get_old_crtc_state(state, slave_crtc); - - drm_WARN_ON(&i915->drm, !slave_crtc || !new_slave_crtc_state || - !old_slave_crtc_state); - - drm_dbg_kms(&i915->drm, - "Updating Transcoder Port Sync Master CRTC = %d %s and Slave CRTC %d %s\n", - crtc->base.base.id, crtc->base.name, - slave_crtc->base.base.id, slave_crtc->base.name); - - /* Enable seq for slave with with DP_TP_CTL left Idle until the - * master is ready - */ - intel_crtc_enable_trans_port_sync(slave_crtc, - state, - new_slave_crtc_state); - - /* Enable seq for master with with DP_TP_CTL left Idle */ - intel_crtc_enable_trans_port_sync(crtc, - state, - new_crtc_state); - - /* Set Slave's DP_TP_CTL to Normal */ - intel_set_dp_tp_ctl_normal(slave_crtc, - state); - - /* Set Master's DP_TP_CTL To Normal */ - usleep_range(200, 400); - intel_set_dp_tp_ctl_normal(crtc, - state); - - /* Now do the post crtc enable for all master and slaves */ - intel_post_crtc_enable_updates(slave_crtc, - state); - intel_post_crtc_enable_updates(crtc, - state); -} - static void icl_dbuf_slice_pre_update(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); @@ -15365,8 +15185,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state) entries[pipe] = new_crtc_state->wm.skl.ddb; update_pipes &= ~BIT(pipe); - intel_update_crtc(crtc, state, old_crtc_state, - new_crtc_state); + intel_update_crtc(state, crtc); /* * If this is an already active pipe, it's DDB changed, @@ -15381,67 +15200,62 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state) } } + update_pipes = modeset_pipes; + /* * Enable all pipes that needs a modeset and do not depends on other * pipes */ - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { enum pipe pipe = crtc->pipe; if ((modeset_pipes & BIT(pipe)) == 0) continue; if (intel_dp_mst_is_slave_trans(new_crtc_state) || - is_trans_port_sync_slave(new_crtc_state)) + is_trans_port_sync_master(new_crtc_state)) continue; - drm_WARN_ON(&dev_priv->drm, skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb, - entries, I915_MAX_PIPES, pipe)); - - entries[pipe] = new_crtc_state->wm.skl.ddb; modeset_pipes &= ~BIT(pipe); - if (is_trans_port_sync_mode(new_crtc_state)) { - struct intel_crtc *slave_crtc; + intel_enable_crtc(state, crtc); + } - intel_update_trans_port_sync_crtcs(crtc, state, - old_crtc_state, - new_crtc_state); + /* + * Then we enable all remaining pipes that depend on other + * pipes: MST slaves and port sync masters. + */ + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + enum pipe pipe = crtc->pipe; - slave_crtc = intel_get_slave_crtc(new_crtc_state); - /* TODO: update entries[] of slave */ - modeset_pipes &= ~BIT(slave_crtc->pipe); + if ((modeset_pipes & BIT(pipe)) == 0) + continue; - } else { - intel_update_crtc(crtc, state, old_crtc_state, - new_crtc_state); - } + modeset_pipes &= ~BIT(pipe); + + intel_enable_crtc(state, crtc); } /* - * Finally enable all pipes that needs a modeset and depends on - * other pipes, right now it is only MST slaves as both port sync slave - * and master are enabled together + * Finally we do the plane updates/etc. for all pipes that got enabled. */ - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { enum pipe pipe = crtc->pipe; - if ((modeset_pipes & BIT(pipe)) == 0) + if ((update_pipes & BIT(pipe)) == 0) continue; drm_WARN_ON(&dev_priv->drm, skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb, entries, I915_MAX_PIPES, pipe)); entries[pipe] = new_crtc_state->wm.skl.ddb; - modeset_pipes &= ~BIT(pipe); + update_pipes &= ~BIT(pipe); - intel_update_crtc(crtc, state, old_crtc_state, new_crtc_state); + intel_update_crtc(state, crtc); } drm_WARN_ON(&dev_priv->drm, modeset_pipes); - + drm_WARN_ON(&dev_priv->drm, update_pipes); } static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv) @@ -18261,11 +18075,12 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) best_encoder = connector->base.state->best_encoder; connector->base.state->best_encoder = &encoder->base; + /* FIXME NULL atomic state passed! */ if (encoder->disable) - encoder->disable(encoder, crtc_state, + encoder->disable(NULL, encoder, crtc_state, connector->base.state); if (encoder->post_disable) - encoder->post_disable(encoder, crtc_state, + encoder->post_disable(NULL, encoder, crtc_state, connector->base.state); connector->base.state->best_encoder = best_encoder; @@ -18802,15 +18617,6 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) -static bool -has_transcoder(struct drm_i915_private *dev_priv, enum transcoder cpu_transcoder) -{ - if (cpu_transcoder == TRANSCODER_EDP) - return HAS_TRANSCODER_EDP(dev_priv); - else - return INTEL_INFO(dev_priv)->pipe_mask & BIT(cpu_transcoder); -} - struct intel_display_error_state { u32 power_well_driver; @@ -18919,7 +18725,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv) for (i = 0; i < ARRAY_SIZE(error->transcoder); i++) { enum transcoder cpu_transcoder = transcoders[i]; - if (!has_transcoder(dev_priv, cpu_transcoder)) + if (!HAS_TRANSCODER(dev_priv, cpu_transcoder)) continue; error->transcoder[i].available = true; diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index adb1225a3480..cc7f287804d7 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -320,9 +320,13 @@ enum phy_fia { for_each_pipe(__dev_priv, __p) \ for_each_if((__mask) & BIT(__p)) -#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \ +#define for_each_cpu_transcoder(__dev_priv, __t) \ for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++) \ - for_each_if ((__mask) & (1 << (__t))) + for_each_if (INTEL_INFO(__dev_priv)->cpu_transcoder_mask & BIT(__t)) + +#define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \ + for_each_cpu_transcoder(__dev_priv, __t) \ + for_each_if ((__mask) & BIT(__t)) #define for_each_universal_plane(__dev_priv, __pipe, __p) \ for ((__p) = 0; \ diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 9f736420d83f..bdeea2e02642 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -1320,6 +1320,16 @@ static int i915_displayport_test_data_show(struct seq_file *m, void *data) intel_dp->compliance.test_data.vdisplay); seq_printf(m, "bpc: %u\n", intel_dp->compliance.test_data.bpc); + } else if (intel_dp->compliance.test_type == + DP_TEST_LINK_PHY_TEST_PATTERN) { + seq_printf(m, "pattern: %d\n", + intel_dp->compliance.test_data.phytest.phy_pattern); + seq_printf(m, "Number of lanes: %d\n", + intel_dp->compliance.test_data.phytest.num_lanes); + seq_printf(m, "Link Rate: %d\n", + intel_dp->compliance.test_data.phytest.link_rate); + seq_printf(m, "level: %02x\n", + intel_dp->train_set[0]); } } else seq_puts(m, "0"); @@ -1352,7 +1362,7 @@ static int i915_displayport_test_type_show(struct seq_file *m, void *data) if (encoder && connector->status == connector_status_connected) { intel_dp = enc_to_intel_dp(encoder); - seq_printf(m, "%02lx", intel_dp->compliance.test_type); + seq_printf(m, "%02lx\n", intel_dp->compliance.test_type); } else seq_puts(m, "0"); } diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 246e406bb385..03bdde19c8c9 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1873,20 +1873,27 @@ __async_put_domains_state_ok(struct i915_power_domains *power_domains) static void print_power_domains(struct i915_power_domains *power_domains, const char *prefix, u64 mask) { + struct drm_i915_private *i915 = container_of(power_domains, + struct drm_i915_private, + power_domains); enum intel_display_power_domain domain; - DRM_DEBUG_DRIVER("%s (%lu):\n", prefix, hweight64(mask)); + drm_dbg(&i915->drm, "%s (%lu):\n", prefix, hweight64(mask)); for_each_power_domain(domain, mask) - DRM_DEBUG_DRIVER("%s use_count %d\n", - intel_display_power_domain_str(domain), - power_domains->domain_use_count[domain]); + drm_dbg(&i915->drm, "%s use_count %d\n", + intel_display_power_domain_str(domain), + power_domains->domain_use_count[domain]); } static void print_async_put_domains_state(struct i915_power_domains *power_domains) { - DRM_DEBUG_DRIVER("async_put_wakeref %u\n", - power_domains->async_put_wakeref); + struct drm_i915_private *i915 = container_of(power_domains, + struct drm_i915_private, + power_domains); + + drm_dbg(&i915->drm, "async_put_wakeref %u\n", + power_domains->async_put_wakeref); print_power_domains(power_domains, "async_put_domains[0]", power_domains->async_put_domains[0]); @@ -4140,7 +4147,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX D TBT1", .domains = TGL_AUX_D_TBT1_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4151,7 +4158,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX E TBT2", .domains = TGL_AUX_E_TBT2_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4162,7 +4169,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX F TBT3", .domains = TGL_AUX_F_TBT3_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4173,7 +4180,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX G TBT4", .domains = TGL_AUX_G_TBT4_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4184,7 +4191,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX H TBT5", .domains = TGL_AUX_H_TBT5_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4195,7 +4202,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX I TBT6", .domains = TGL_AUX_I_TBT6_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4480,7 +4487,8 @@ void icl_dbuf_slices_update(struct drm_i915_private *dev_priv, drm_WARN(&dev_priv->drm, hweight8(req_slices) > max_slices, "Invalid number of dbuf slices requested\n"); - DRM_DEBUG_KMS("Updating dbuf slices to 0x%x\n", req_slices); + drm_dbg_kms(&dev_priv->drm, "Updating dbuf slices to 0x%x\n", + req_slices); /* * Might be running this in parallel to gen9_dc_off_power_well_enable @@ -5016,7 +5024,7 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) const struct buddy_page_mask *table; int i; - if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B0)) /* Wa_1409767108: tgl */ table = wa_1409767108_buddy_page_masks; else diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index e67474a71761..ba8c08145c88 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -132,8 +132,7 @@ struct intel_encoder { u16 cloneable; u8 pipe_mask; enum intel_hotplug_state (*hotplug)(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received); + struct intel_connector *connector); enum intel_output_type (*compute_output_type)(struct intel_encoder *, struct intel_crtc_state *, struct drm_connector_state *); @@ -146,28 +145,35 @@ struct intel_encoder { void (*update_prepare)(struct intel_atomic_state *, struct intel_encoder *, struct intel_crtc *); - void (*pre_pll_enable)(struct intel_encoder *, + void (*pre_pll_enable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); - void (*pre_enable)(struct intel_encoder *, + void (*pre_enable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); - void (*enable)(struct intel_encoder *, + void (*enable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); void (*update_complete)(struct intel_atomic_state *, struct intel_encoder *, struct intel_crtc *); - void (*disable)(struct intel_encoder *, + void (*disable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); - void (*post_disable)(struct intel_encoder *, + void (*post_disable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); - void (*post_pll_disable)(struct intel_encoder *, + void (*post_pll_disable)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); - void (*update_pipe)(struct intel_encoder *, + void (*update_pipe)(struct intel_atomic_state *, + struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); /* Read out the current hw state of this connector, returning true if @@ -425,6 +431,9 @@ struct intel_connector { struct edid *edid; struct edid *detect_edid; + /* Number of times hotplug detection was tried after an HPD interrupt */ + int hotplug_retries; + /* since POLL and HPD connectors may use the same HPD line keep the native state of connector->polled in case hotplug storm detection changes it */ u8 polled; @@ -640,6 +649,16 @@ struct intel_crtc_scaler_state { #define I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP (1<<1) /* Flag to use the scanline counter instead of the pixel counter */ #define I915_MODE_FLAG_USE_SCANLINE_COUNTER (1<<2) +/* + * TE0 or TE1 flag is set if the crtc has a DSI encoder which + * is operating in command mode. + * Flag to use TE from DSI0 instead of VBI in command mode + */ +#define I915_MODE_FLAG_DSI_USE_TE0 (1<<3) +/* Flag to use TE from DSI1 instead of VBI in command mode */ +#define I915_MODE_FLAG_DSI_USE_TE1 (1<<4) +/* Flag to indicate mipi dsi periodic command mode where we do not get TE */ +#define I915_MODE_FLAG_DSI_PERIODIC_CMD_MODE (1<<5) struct intel_wm_level { bool enable; @@ -1015,6 +1034,7 @@ struct intel_crtc_state { union hdmi_infoframe spd; union hdmi_infoframe hdmi; union hdmi_infoframe drm; + struct drm_dp_vsc_sdp vsc; } infoframes; /* HDMI scrambling status */ @@ -1238,6 +1258,7 @@ struct intel_dp_compliance_data { u8 video_pattern; u16 hdisplay, vdisplay; u8 bpc; + struct drm_dp_phy_test_params phytest; }; struct intel_dp_compliance { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 0a417cd2af2b..d4fcc9583869 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -164,6 +164,17 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) }; int i, max_rate; + if (drm_dp_has_quirk(&intel_dp->desc, 0, + DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS)) { + /* Needed, e.g., for Apple MBP 2017, 15 inch eDP Retina panel */ + static const int quirk_rates[] = { 162000, 270000, 324000 }; + + memcpy(intel_dp->sink_rates, quirk_rates, sizeof(quirk_rates)); + intel_dp->num_sink_rates = ARRAY_SIZE(quirk_rates); + + return; + } + max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]); for (i = 0; i < ARRAY_SIZE(dp_rates); i++) { @@ -452,6 +463,7 @@ static bool intel_dp_can_link_train_fallback_for_edp(struct intel_dp *intel_dp, int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, int link_rate, u8 lane_count) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); int index; index = intel_dp_rate_index(intel_dp->common_rates, @@ -462,7 +474,8 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, !intel_dp_can_link_train_fallback_for_edp(intel_dp, intel_dp->common_rates[index - 1], lane_count)) { - DRM_DEBUG_KMS("Retrying Link training for eDP with same parameters\n"); + drm_dbg_kms(&i915->drm, + "Retrying Link training for eDP with same parameters\n"); return 0; } intel_dp->max_link_rate = intel_dp->common_rates[index - 1]; @@ -472,13 +485,14 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, !intel_dp_can_link_train_fallback_for_edp(intel_dp, intel_dp_max_common_rate(intel_dp), lane_count >> 1)) { - DRM_DEBUG_KMS("Retrying Link training for eDP with same parameters\n"); + drm_dbg_kms(&i915->drm, + "Retrying Link training for eDP with same parameters\n"); return 0; } intel_dp->max_link_rate = intel_dp_max_common_rate(intel_dp); intel_dp->max_link_lane_count = lane_count >> 1; } else { - DRM_ERROR("Link Training Unsuccessful\n"); + drm_err(&i915->drm, "Link Training Unsuccessful\n"); return -1; } @@ -553,6 +567,7 @@ static u16 intel_dp_dsc_get_output_bpp(struct drm_i915_private *i915, static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock, int mode_hdisplay) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 min_slice_count, i; int max_slice_width; @@ -565,8 +580,9 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd); if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) { - DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n", - max_slice_width); + drm_dbg_kms(&i915->drm, + "Unsupported slice width %d by DP DSC Sink device\n", + max_slice_width); return 0; } /* Also take into account max slice width */ @@ -584,7 +600,8 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, return valid_dsc_slicecount[i]; } - DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count); + drm_dbg_kms(&i915->drm, "Unsupported Slice Count %d\n", + min_slice_count); return 0; } @@ -1374,7 +1391,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp, * lowest possible wakeup latency and so prevent the cpu from going into * deep sleep states. */ - pm_qos_update_request(&i915->pm_qos, 0); + cpu_latency_qos_update_request(&i915->pm_qos, 0); intel_dp_check_edp(intel_dp); @@ -1507,7 +1524,7 @@ done: ret = recv_bytes; out: - pm_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE); if (vdd) edp_panel_vdd_off(intel_dp, false); @@ -1832,6 +1849,7 @@ static void snprintf_int_array(char *str, size_t len, static void intel_dp_print_rates(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); char str[128]; /* FIXME: too big for stack? */ if (!drm_debug_enabled(DRM_UT_KMS)) @@ -1839,15 +1857,15 @@ static void intel_dp_print_rates(struct intel_dp *intel_dp) snprintf_int_array(str, sizeof(str), intel_dp->source_rates, intel_dp->num_source_rates); - DRM_DEBUG_KMS("source rates: %s\n", str); + drm_dbg_kms(&i915->drm, "source rates: %s\n", str); snprintf_int_array(str, sizeof(str), intel_dp->sink_rates, intel_dp->num_sink_rates); - DRM_DEBUG_KMS("sink rates: %s\n", str); + drm_dbg_kms(&i915->drm, "sink rates: %s\n", str); snprintf_int_array(str, sizeof(str), intel_dp->common_rates, intel_dp->num_common_rates); - DRM_DEBUG_KMS("common rates: %s\n", str); + drm_dbg_kms(&i915->drm, "common rates: %s\n", str); } int @@ -1954,6 +1972,8 @@ intel_dp_adjust_compliance_config(struct intel_dp *intel_dp, struct intel_crtc_state *pipe_config, struct link_config_limits *limits) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + /* For DP Compliance we override the computed bpp for the pipe */ if (intel_dp->compliance.test_data.bpc != 0) { int bpp = 3 * intel_dp->compliance.test_data.bpc; @@ -1961,7 +1981,7 @@ intel_dp_adjust_compliance_config(struct intel_dp *intel_dp, limits->min_bpp = limits->max_bpp = bpp; pipe_config->dither_force_disable = bpp == 6 * 3; - DRM_DEBUG_KMS("Setting pipe_bpp to %d\n", bpp); + drm_dbg_kms(&i915->drm, "Setting pipe_bpp to %d\n", bpp); } /* Use values requested by Compliance Test Request */ @@ -2055,6 +2075,7 @@ static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc) static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; u8 line_buf_depth; @@ -2089,7 +2110,8 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd); if (!line_buf_depth) { - DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n"); + drm_dbg_kms(&i915->drm, + "DSC Sink Line Buffer Depth invalid\n"); return -EINVAL; } @@ -2114,7 +2136,8 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; + const struct drm_display_mode *adjusted_mode = + &pipe_config->hw.adjusted_mode; u8 dsc_max_bpc; int pipe_bpp; int ret; @@ -2229,7 +2252,9 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { - struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + const struct drm_display_mode *adjusted_mode = + &pipe_config->hw.adjusted_mode; struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct link_config_limits limits; int common_len; @@ -2264,11 +2289,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits); - DRM_DEBUG_KMS("DP link computation with max lane count %i " - "max rate %d max bpp %d pixel clock %iKHz\n", - limits.max_lane_count, - intel_dp->common_rates[limits.max_clock], - limits.max_bpp, adjusted_mode->crtc_clock); + drm_dbg_kms(&i915->drm, "DP link computation with max lane count %i " + "max rate %d max bpp %d pixel clock %iKHz\n", + limits.max_lane_count, + intel_dp->common_rates[limits.max_clock], + limits.max_bpp, adjusted_mode->crtc_clock); /* * Optimize for slow and wide. This is the place to add alternative @@ -2277,7 +2302,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); /* enable compression if the mode doesn't fit available BW */ - DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en); + drm_dbg_kms(&i915->drm, "Force DSC en = %d\n", intel_dp->force_dsc_en); if (ret || intel_dp->force_dsc_en) { ret = intel_dp_dsc_compute_config(intel_dp, pipe_config, conn_state, &limits); @@ -2286,26 +2311,29 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, } if (pipe_config->dsc.compression_enable) { - DRM_DEBUG_KMS("DP lane count %d clock %d Input bpp %d Compressed bpp %d\n", - pipe_config->lane_count, pipe_config->port_clock, - pipe_config->pipe_bpp, - pipe_config->dsc.compressed_bpp); - - DRM_DEBUG_KMS("DP link rate required %i available %i\n", - intel_dp_link_required(adjusted_mode->crtc_clock, - pipe_config->dsc.compressed_bpp), - intel_dp_max_data_rate(pipe_config->port_clock, - pipe_config->lane_count)); + drm_dbg_kms(&i915->drm, + "DP lane count %d clock %d Input bpp %d Compressed bpp %d\n", + pipe_config->lane_count, pipe_config->port_clock, + pipe_config->pipe_bpp, + pipe_config->dsc.compressed_bpp); + + drm_dbg_kms(&i915->drm, + "DP link rate required %i available %i\n", + intel_dp_link_required(adjusted_mode->crtc_clock, + pipe_config->dsc.compressed_bpp), + intel_dp_max_data_rate(pipe_config->port_clock, + pipe_config->lane_count)); } else { - DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n", - pipe_config->lane_count, pipe_config->port_clock, - pipe_config->pipe_bpp); + drm_dbg_kms(&i915->drm, "DP lane count %d clock %d bpp %d\n", + pipe_config->lane_count, pipe_config->port_clock, + pipe_config->pipe_bpp); - DRM_DEBUG_KMS("DP link rate required %i available %i\n", - intel_dp_link_required(adjusted_mode->crtc_clock, - pipe_config->pipe_bpp), - intel_dp_max_data_rate(pipe_config->port_clock, - pipe_config->lane_count)); + drm_dbg_kms(&i915->drm, + "DP link rate required %i available %i\n", + intel_dp_link_required(adjusted_mode->crtc_clock, + pipe_config->pipe_bpp), + intel_dp_max_data_rate(pipe_config->port_clock, + pipe_config->lane_count)); } return 0; } @@ -2315,6 +2343,7 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp, struct drm_connector *connector, struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); const struct drm_display_info *info = &connector->display_info; const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; @@ -2331,7 +2360,8 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp, /* YCBCR 420 output conversion needs a scaler */ ret = skl_update_scaler_crtc(crtc_state); if (ret) { - DRM_DEBUG_KMS("Scaler allocation for output failed\n"); + drm_dbg_kms(&i915->drm, + "Scaler allocation for output failed\n"); return ret; } @@ -2384,6 +2414,128 @@ static bool intel_dp_port_has_audio(struct drm_i915_private *dev_priv, return true; } +static void intel_dp_compute_vsc_colorimetry(const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state, + struct drm_dp_vsc_sdp *vsc) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + + /* + * Prepare VSC Header for SU as per DP 1.4 spec, Table 2-118 + * VSC SDP supporting 3D stereo, PSR2, and Pixel Encoding/ + * Colorimetry Format indication. + */ + vsc->revision = 0x5; + vsc->length = 0x13; + + /* DP 1.4a spec, Table 2-120 */ + switch (crtc_state->output_format) { + case INTEL_OUTPUT_FORMAT_YCBCR444: + vsc->pixelformat = DP_PIXELFORMAT_YUV444; + break; + case INTEL_OUTPUT_FORMAT_YCBCR420: + vsc->pixelformat = DP_PIXELFORMAT_YUV420; + break; + case INTEL_OUTPUT_FORMAT_RGB: + default: + vsc->pixelformat = DP_PIXELFORMAT_RGB; + } + + switch (conn_state->colorspace) { + case DRM_MODE_COLORIMETRY_BT709_YCC: + vsc->colorimetry = DP_COLORIMETRY_BT709_YCC; + break; + case DRM_MODE_COLORIMETRY_XVYCC_601: + vsc->colorimetry = DP_COLORIMETRY_XVYCC_601; + break; + case DRM_MODE_COLORIMETRY_XVYCC_709: + vsc->colorimetry = DP_COLORIMETRY_XVYCC_709; + break; + case DRM_MODE_COLORIMETRY_SYCC_601: + vsc->colorimetry = DP_COLORIMETRY_SYCC_601; + break; + case DRM_MODE_COLORIMETRY_OPYCC_601: + vsc->colorimetry = DP_COLORIMETRY_OPYCC_601; + break; + case DRM_MODE_COLORIMETRY_BT2020_CYCC: + vsc->colorimetry = DP_COLORIMETRY_BT2020_CYCC; + break; + case DRM_MODE_COLORIMETRY_BT2020_RGB: + vsc->colorimetry = DP_COLORIMETRY_BT2020_RGB; + break; + case DRM_MODE_COLORIMETRY_BT2020_YCC: + vsc->colorimetry = DP_COLORIMETRY_BT2020_YCC; + break; + case DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65: + case DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER: + vsc->colorimetry = DP_COLORIMETRY_DCI_P3_RGB; + break; + default: + /* + * RGB->YCBCR color conversion uses the BT.709 + * color space. + */ + if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) + vsc->colorimetry = DP_COLORIMETRY_BT709_YCC; + else + vsc->colorimetry = DP_COLORIMETRY_DEFAULT; + break; + } + + vsc->bpc = crtc_state->pipe_bpp / 3; + + /* only RGB pixelformat supports 6 bpc */ + drm_WARN_ON(&dev_priv->drm, + vsc->bpc == 6 && vsc->pixelformat != DP_PIXELFORMAT_RGB); + + /* all YCbCr are always limited range */ + vsc->dynamic_range = DP_DYNAMIC_RANGE_CTA; + vsc->content_type = DP_CONTENT_TYPE_NOT_DEFINED; +} + +static void intel_dp_compute_vsc_sdp(struct intel_dp *intel_dp, + struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct drm_dp_vsc_sdp *vsc = &crtc_state->infoframes.vsc; + + /* When PSR is enabled, VSC SDP is handled by PSR routine */ + if (intel_psr_enabled(intel_dp)) + return; + + if (!intel_dp_needs_vsc_sdp(crtc_state, conn_state)) + return; + + crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_VSC); + vsc->sdp_type = DP_SDP_VSC; + intel_dp_compute_vsc_colorimetry(crtc_state, conn_state, + &crtc_state->infoframes.vsc); +} + +static void +intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp, + struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + int ret; + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct hdmi_drm_infoframe *drm_infoframe = &crtc_state->infoframes.drm.drm; + + if (!conn_state->hdr_output_metadata) + return; + + ret = drm_hdmi_infoframe_set_hdr_metadata(drm_infoframe, conn_state); + + if (ret) { + drm_dbg_kms(&dev_priv->drm, "couldn't set HDR metadata in infoframe\n"); + return; + } + + crtc_state->infoframes.enable |= + intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA); +} + int intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, @@ -2489,6 +2641,8 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_dp_set_clock(encoder, pipe_config); intel_psr_compute_config(intel_dp, pipe_config); + intel_dp_compute_vsc_sdp(intel_dp, pipe_config, conn_state); + intel_dp_compute_hdr_metadata_infoframe_sdp(intel_dp, pipe_config, conn_state); return 0; } @@ -2633,22 +2787,27 @@ static void wait_panel_status(struct intel_dp *intel_dp, static void wait_panel_on(struct intel_dp *intel_dp) { - DRM_DEBUG_KMS("Wait for panel power on\n"); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + drm_dbg_kms(&i915->drm, "Wait for panel power on\n"); wait_panel_status(intel_dp, IDLE_ON_MASK, IDLE_ON_VALUE); } static void wait_panel_off(struct intel_dp *intel_dp) { - DRM_DEBUG_KMS("Wait for panel power off time\n"); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + drm_dbg_kms(&i915->drm, "Wait for panel power off time\n"); wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE); } static void wait_panel_power_cycle(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); ktime_t panel_power_on_time; s64 panel_power_off_duration; - DRM_DEBUG_KMS("Wait for panel power cycle\n"); + drm_dbg_kms(&i915->drm, "Wait for panel power cycle\n"); /* take the difference of currrent time and panel power off time * and then make panel wait for t11_t12 if needed. */ @@ -3012,11 +3171,12 @@ void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(conn_state->best_encoder)); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); if (!intel_dp_is_edp(intel_dp)) return; - DRM_DEBUG_KMS("\n"); + drm_dbg_kms(&i915->drm, "\n"); intel_panel_enable_backlight(crtc_state, conn_state); _intel_edp_backlight_on(intel_dp); @@ -3050,11 +3210,12 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp) void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state) { struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder)); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); if (!intel_dp_is_edp(intel_dp)) return; - DRM_DEBUG_KMS("\n"); + drm_dbg_kms(&i915->drm, "\n"); _intel_edp_backlight_off(intel_dp); intel_panel_disable_backlight(old_conn_state); @@ -3067,6 +3228,7 @@ void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state) static void intel_edp_backlight_power(struct intel_connector *connector, bool enable) { + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_dp *intel_dp = intel_attached_dp(connector); intel_wakeref_t wakeref; bool is_enabled; @@ -3077,8 +3239,8 @@ static void intel_edp_backlight_power(struct intel_connector *connector, if (is_enabled == enable) return; - DRM_DEBUG_KMS("panel power control backlight %s\n", - enable ? "enable" : "disable"); + drm_dbg_kms(&i915->drm, "panel power control backlight %s\n", + enable ? "enable" : "disable"); if (enable) _intel_edp_backlight_on(intel_dp); @@ -3188,6 +3350,7 @@ void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, bool enable) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); int ret; if (!crtc_state->dsc.compression_enable) @@ -3196,13 +3359,15 @@ void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_DSC_ENABLE, enable ? DP_DECOMPRESSION_EN : 0); if (ret < 0) - DRM_DEBUG_KMS("Failed to %s sink decompression state\n", - enable ? "enable" : "disable"); + drm_dbg_kms(&i915->drm, + "Failed to %s sink decompression state\n", + enable ? "enable" : "disable"); } /* If the sink supports it, try to set the power state appropriately */ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); int ret, i; /* Should have a valid DPCD by this point */ @@ -3235,8 +3400,8 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode) } if (ret != 1) - DRM_DEBUG_KMS("failed to %s sink power state\n", - mode == DRM_MODE_DPMS_ON ? "enable" : "disable"); + drm_dbg_kms(&i915->drm, "failed to %s sink power state\n", + mode == DRM_MODE_DPMS_ON ? "enable" : "disable"); } static bool cpt_dp_port_selected(struct drm_i915_private *dev_priv, @@ -3393,7 +3558,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder, } } -static void intel_disable_dp(struct intel_encoder *encoder, +static void intel_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3413,21 +3579,24 @@ static void intel_disable_dp(struct intel_encoder *encoder, intel_edp_panel_off(intel_dp); } -static void g4x_disable_dp(struct intel_encoder *encoder, +static void g4x_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_dp(encoder, old_crtc_state, old_conn_state); + intel_disable_dp(state, encoder, old_crtc_state, old_conn_state); } -static void vlv_disable_dp(struct intel_encoder *encoder, +static void vlv_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_dp(encoder, old_crtc_state, old_conn_state); + intel_disable_dp(state, encoder, old_crtc_state, old_conn_state); } -static void g4x_post_disable_dp(struct intel_encoder *encoder, +static void g4x_post_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3447,14 +3616,16 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder, ilk_edp_pll_off(intel_dp, old_crtc_state); } -static void vlv_post_disable_dp(struct intel_encoder *encoder, +static void vlv_post_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { intel_dp_link_down(encoder, old_crtc_state); } -static void chv_post_disable_dp(struct intel_encoder *encoder, +static void chv_post_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -3580,7 +3751,8 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp, intel_de_posting_read(dev_priv, intel_dp->output_reg); } -static void intel_enable_dp(struct intel_encoder *encoder, +static void intel_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -3626,22 +3798,25 @@ static void intel_enable_dp(struct intel_encoder *encoder, } } -static void g4x_enable_dp(struct intel_encoder *encoder, +static void g4x_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { - intel_enable_dp(encoder, pipe_config, conn_state); + intel_enable_dp(state, encoder, pipe_config, conn_state); intel_edp_backlight_on(pipe_config, conn_state); } -static void vlv_enable_dp(struct intel_encoder *encoder, +static void vlv_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { intel_edp_backlight_on(pipe_config, conn_state); } -static void g4x_pre_enable_dp(struct intel_encoder *encoder, +static void g4x_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -3761,16 +3936,18 @@ static void vlv_init_panel_power_sequencer(struct intel_encoder *encoder, intel_dp_init_panel_power_sequencer_registers(intel_dp, true); } -static void vlv_pre_enable_dp(struct intel_encoder *encoder, +static void vlv_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { vlv_phy_pre_encoder_enable(encoder, pipe_config); - intel_enable_dp(encoder, pipe_config, conn_state); + intel_enable_dp(state, encoder, pipe_config, conn_state); } -static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder, +static void vlv_dp_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -3779,19 +3956,21 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder, vlv_phy_pre_pll_enable(encoder, pipe_config); } -static void chv_pre_enable_dp(struct intel_encoder *encoder, +static void chv_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { chv_phy_pre_encoder_enable(encoder, pipe_config); - intel_enable_dp(encoder, pipe_config, conn_state); + intel_enable_dp(state, encoder, pipe_config, conn_state); /* Second common lane will stay alive on its own now */ chv_phy_release_cl2_override(encoder); } -static void chv_dp_pre_pll_enable(struct intel_encoder *encoder, +static void chv_dp_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -3800,7 +3979,8 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder, chv_phy_pre_pll_enable(encoder, pipe_config); } -static void chv_dp_post_pll_disable(struct intel_encoder *encoder, +static void chv_dp_post_pll_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -4319,6 +4499,7 @@ intel_dp_link_down(struct intel_encoder *encoder, static void intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 dpcd_ext[6]; /* @@ -4334,20 +4515,22 @@ intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp) if (drm_dp_dpcd_read(&intel_dp->aux, DP_DP13_DPCD_REV, &dpcd_ext, sizeof(dpcd_ext)) != sizeof(dpcd_ext)) { - DRM_ERROR("DPCD failed read at extended capabilities\n"); + drm_err(&i915->drm, + "DPCD failed read at extended capabilities\n"); return; } if (intel_dp->dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { - DRM_DEBUG_KMS("DPCD extended DPCD rev less than base DPCD rev\n"); + drm_dbg_kms(&i915->drm, + "DPCD extended DPCD rev less than base DPCD rev\n"); return; } if (!memcmp(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext))) return; - DRM_DEBUG_KMS("Base DPCD: %*ph\n", - (int)sizeof(intel_dp->dpcd), intel_dp->dpcd); + drm_dbg_kms(&i915->drm, "Base DPCD: %*ph\n", + (int)sizeof(intel_dp->dpcd), intel_dp->dpcd); memcpy(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext)); } @@ -4355,13 +4538,16 @@ intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp) bool intel_dp_read_dpcd(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + if (drm_dp_dpcd_read(&intel_dp->aux, 0x000, intel_dp->dpcd, sizeof(intel_dp->dpcd)) < 0) return false; /* aux transfer failed */ intel_dp_extended_receiver_capabilities(intel_dp); - DRM_DEBUG_KMS("DPCD: %*ph\n", (int) sizeof(intel_dp->dpcd), intel_dp->dpcd); + drm_dbg_kms(&i915->drm, "DPCD: %*ph\n", (int)sizeof(intel_dp->dpcd), + intel_dp->dpcd); return intel_dp->dpcd[DP_DPCD_REV] != 0; } @@ -4378,6 +4564,8 @@ bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) static void intel_dp_get_dsc_sink_cap(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + /* * Clear the cached register set to avoid using stale values * for the sinks that do not support DSC. @@ -4393,20 +4581,23 @@ static void intel_dp_get_dsc_sink_cap(struct intel_dp *intel_dp) if (drm_dp_dpcd_read(&intel_dp->aux, DP_DSC_SUPPORT, intel_dp->dsc_dpcd, sizeof(intel_dp->dsc_dpcd)) < 0) - DRM_ERROR("Failed to read DPCD register 0x%x\n", - DP_DSC_SUPPORT); + drm_err(&i915->drm, + "Failed to read DPCD register 0x%x\n", + DP_DSC_SUPPORT); - DRM_DEBUG_KMS("DSC DPCD: %*ph\n", - (int)sizeof(intel_dp->dsc_dpcd), - intel_dp->dsc_dpcd); + drm_dbg_kms(&i915->drm, "DSC DPCD: %*ph\n", + (int)sizeof(intel_dp->dsc_dpcd), + intel_dp->dsc_dpcd); /* FEC is supported only on DP 1.4 */ if (!intel_dp_is_edp(intel_dp) && drm_dp_dpcd_readb(&intel_dp->aux, DP_FEC_CAPABILITY, &intel_dp->fec_capable) < 0) - DRM_ERROR("Failed to read FEC DPCD register\n"); + drm_err(&i915->drm, + "Failed to read FEC DPCD register\n"); - DRM_DEBUG_KMS("FEC CAPABILITY: %x\n", intel_dp->fec_capable); + drm_dbg_kms(&i915->drm, "FEC CAPABILITY: %x\n", + intel_dp->fec_capable); } } @@ -4580,14 +4771,16 @@ intel_dp_can_mst(struct intel_dp *intel_dp) static void intel_dp_configure_mst(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; bool sink_can_mst = intel_dp_sink_can_mst(intel_dp); - DRM_DEBUG_KMS("[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n", - encoder->base.base.id, encoder->base.name, - yesno(intel_dp->can_mst), yesno(sink_can_mst), - yesno(i915_modparams.enable_dp_mst)); + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n", + encoder->base.base.id, encoder->base.name, + yesno(intel_dp->can_mst), yesno(sink_can_mst), + yesno(i915_modparams.enable_dp_mst)); if (!intel_dp->can_mst) return; @@ -4633,6 +4826,205 @@ intel_dp_needs_vsc_sdp(const struct intel_crtc_state *crtc_state, return false; } +static ssize_t intel_dp_vsc_sdp_pack(const struct drm_dp_vsc_sdp *vsc, + struct dp_sdp *sdp, size_t size) +{ + size_t length = sizeof(struct dp_sdp); + + if (size < length) + return -ENOSPC; + + memset(sdp, 0, size); + + /* + * Prepare VSC Header for SU as per DP 1.4a spec, Table 2-119 + * VSC SDP Header Bytes + */ + sdp->sdp_header.HB0 = 0; /* Secondary-Data Packet ID = 0 */ + sdp->sdp_header.HB1 = vsc->sdp_type; /* Secondary-data Packet Type */ + sdp->sdp_header.HB2 = vsc->revision; /* Revision Number */ + sdp->sdp_header.HB3 = vsc->length; /* Number of Valid Data Bytes */ + + /* VSC SDP Payload for DB16 through DB18 */ + /* Pixel Encoding and Colorimetry Formats */ + sdp->db[16] = (vsc->pixelformat & 0xf) << 4; /* DB16[7:4] */ + sdp->db[16] |= vsc->colorimetry & 0xf; /* DB16[3:0] */ + + switch (vsc->bpc) { + case 6: + /* 6bpc: 0x0 */ + break; + case 8: + sdp->db[17] = 0x1; /* DB17[3:0] */ + break; + case 10: + sdp->db[17] = 0x2; + break; + case 12: + sdp->db[17] = 0x3; + break; + case 16: + sdp->db[17] = 0x4; + break; + default: + MISSING_CASE(vsc->bpc); + break; + } + /* Dynamic Range and Component Bit Depth */ + if (vsc->dynamic_range == DP_DYNAMIC_RANGE_CTA) + sdp->db[17] |= 0x80; /* DB17[7] */ + + /* Content Type */ + sdp->db[18] = vsc->content_type & 0x7; + + return length; +} + +static ssize_t +intel_dp_hdr_metadata_infoframe_sdp_pack(const struct hdmi_drm_infoframe *drm_infoframe, + struct dp_sdp *sdp, + size_t size) +{ + size_t length = sizeof(struct dp_sdp); + const int infoframe_size = HDMI_INFOFRAME_HEADER_SIZE + HDMI_DRM_INFOFRAME_SIZE; + unsigned char buf[HDMI_INFOFRAME_HEADER_SIZE + HDMI_DRM_INFOFRAME_SIZE]; + ssize_t len; + + if (size < length) + return -ENOSPC; + + memset(sdp, 0, size); + + len = hdmi_drm_infoframe_pack_only(drm_infoframe, buf, sizeof(buf)); + if (len < 0) { + DRM_DEBUG_KMS("buffer size is smaller than hdr metadata infoframe\n"); + return -ENOSPC; + } + + if (len != infoframe_size) { + DRM_DEBUG_KMS("wrong static hdr metadata size\n"); + return -ENOSPC; + } + + /* + * Set up the infoframe sdp packet for HDR static metadata. + * Prepare VSC Header for SU as per DP 1.4a spec, + * Table 2-100 and Table 2-101 + */ + + /* Secondary-Data Packet ID, 00h for non-Audio INFOFRAME */ + sdp->sdp_header.HB0 = 0; + /* + * Packet Type 80h + Non-audio INFOFRAME Type value + * HDMI_INFOFRAME_TYPE_DRM: 0x87 + * - 80h + Non-audio INFOFRAME Type value + * - InfoFrame Type: 0x07 + * [CTA-861-G Table-42 Dynamic Range and Mastering InfoFrame] + */ + sdp->sdp_header.HB1 = drm_infoframe->type; + /* + * Least Significant Eight Bits of (Data Byte Count – 1) + * infoframe_size - 1 + */ + sdp->sdp_header.HB2 = 0x1D; + /* INFOFRAME SDP Version Number */ + sdp->sdp_header.HB3 = (0x13 << 2); + /* CTA Header Byte 2 (INFOFRAME Version Number) */ + sdp->db[0] = drm_infoframe->version; + /* CTA Header Byte 3 (Length of INFOFRAME): HDMI_DRM_INFOFRAME_SIZE */ + sdp->db[1] = drm_infoframe->length; + /* + * Copy HDMI_DRM_INFOFRAME_SIZE size from a buffer after + * HDMI_INFOFRAME_HEADER_SIZE + */ + BUILD_BUG_ON(sizeof(sdp->db) < HDMI_DRM_INFOFRAME_SIZE + 2); + memcpy(&sdp->db[2], &buf[HDMI_INFOFRAME_HEADER_SIZE], + HDMI_DRM_INFOFRAME_SIZE); + + /* + * Size of DP infoframe sdp packet for HDR static metadata consists of + * - DP SDP Header(struct dp_sdp_header): 4 bytes + * - Two Data Blocks: 2 bytes + * CTA Header Byte2 (INFOFRAME Version Number) + * CTA Header Byte3 (Length of INFOFRAME) + * - HDMI_DRM_INFOFRAME_SIZE: 26 bytes + * + * Prior to GEN11's GMP register size is identical to DP HDR static metadata + * infoframe size. But GEN11+ has larger than that size, write_infoframe + * will pad rest of the size. + */ + return sizeof(struct dp_sdp_header) + 2 + HDMI_DRM_INFOFRAME_SIZE; +} + +static void intel_write_dp_sdp(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + unsigned int type) +{ + struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct dp_sdp sdp = {}; + ssize_t len; + + if ((crtc_state->infoframes.enable & + intel_hdmi_infoframe_enable(type)) == 0) + return; + + switch (type) { + case DP_SDP_VSC: + len = intel_dp_vsc_sdp_pack(&crtc_state->infoframes.vsc, &sdp, + sizeof(sdp)); + break; + case HDMI_PACKET_TYPE_GAMUT_METADATA: + len = intel_dp_hdr_metadata_infoframe_sdp_pack(&crtc_state->infoframes.drm.drm, + &sdp, sizeof(sdp)); + break; + default: + MISSING_CASE(type); + return; + } + + if (drm_WARN_ON(&dev_priv->drm, len < 0)) + return; + + intel_dig_port->write_infoframe(encoder, crtc_state, type, &sdp, len); +} + +void intel_dp_set_infoframes(struct intel_encoder *encoder, + bool enable, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + i915_reg_t reg = HSW_TVIDEO_DIP_CTL(crtc_state->cpu_transcoder); + u32 dip_enable = VIDEO_DIP_ENABLE_AVI_HSW | VIDEO_DIP_ENABLE_GCP_HSW | + VIDEO_DIP_ENABLE_VS_HSW | VIDEO_DIP_ENABLE_GMP_HSW | + VIDEO_DIP_ENABLE_SPD_HSW | VIDEO_DIP_ENABLE_DRM_GLK; + u32 val = intel_de_read(dev_priv, reg); + + /* TODO: Add DSC case (DIP_ENABLE_PPS) */ + /* When PSR is enabled, this routine doesn't disable VSC DIP */ + if (intel_psr_enabled(intel_dp)) + val &= ~dip_enable; + else + val &= ~(dip_enable | VIDEO_DIP_ENABLE_VSC_HSW); + + if (!enable) { + intel_de_write(dev_priv, reg, val); + intel_de_posting_read(dev_priv, reg); + return; + } + + intel_de_write(dev_priv, reg, val); + intel_de_posting_read(dev_priv, reg); + + /* When PSR is enabled, VSC SDP is handled by PSR routine */ + if (!intel_psr_enabled(intel_dp)) + intel_write_dp_sdp(encoder, crtc_state, DP_SDP_VSC); + + intel_write_dp_sdp(encoder, crtc_state, HDMI_PACKET_TYPE_GAMUT_METADATA); +} + static void intel_dp_setup_vsc_sdp(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, @@ -4762,6 +5154,7 @@ intel_dp_setup_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); struct dp_sdp infoframe_sdp = {}; struct hdmi_drm_infoframe drm_infoframe = {}; @@ -4772,18 +5165,20 @@ intel_dp_setup_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp, ret = drm_hdmi_infoframe_set_hdr_metadata(&drm_infoframe, conn_state); if (ret) { - DRM_DEBUG_KMS("couldn't set HDR metadata in infoframe\n"); + drm_dbg_kms(&i915->drm, + "couldn't set HDR metadata in infoframe\n"); return; } len = hdmi_drm_infoframe_pack_only(&drm_infoframe, buf, sizeof(buf)); if (len < 0) { - DRM_DEBUG_KMS("buffer size is smaller than hdr metadata infoframe\n"); + drm_dbg_kms(&i915->drm, + "buffer size is smaller than hdr metadata infoframe\n"); return; } if (len != infoframe_size) { - DRM_DEBUG_KMS("wrong static hdr metadata size\n"); + drm_dbg_kms(&i915->drm, "wrong static hdr metadata size\n"); return; } @@ -4861,6 +5256,7 @@ void intel_dp_hdr_metadata_enable(struct intel_dp *intel_dp, static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); int status = 0; int test_link_rate; u8 test_lane_count, test_link_bw; @@ -4872,7 +5268,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp) &test_lane_count); if (status <= 0) { - DRM_DEBUG_KMS("Lane count read failed\n"); + drm_dbg_kms(&i915->drm, "Lane count read failed\n"); return DP_TEST_NAK; } test_lane_count &= DP_MAX_LANE_COUNT_MASK; @@ -4880,7 +5276,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp) status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_LINK_RATE, &test_link_bw); if (status <= 0) { - DRM_DEBUG_KMS("Link Rate read failed\n"); + drm_dbg_kms(&i915->drm, "Link Rate read failed\n"); return DP_TEST_NAK; } test_link_rate = drm_dp_bw_code_to_link_rate(test_link_bw); @@ -4898,6 +5294,7 @@ static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp) static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 test_pattern; u8 test_misc; __be16 h_width, v_height; @@ -4907,7 +5304,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_PATTERN, &test_pattern); if (status <= 0) { - DRM_DEBUG_KMS("Test pattern read failed\n"); + drm_dbg_kms(&i915->drm, "Test pattern read failed\n"); return DP_TEST_NAK; } if (test_pattern != DP_COLOR_RAMP) @@ -4916,21 +5313,21 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_H_WIDTH_HI, &h_width, 2); if (status <= 0) { - DRM_DEBUG_KMS("H Width read failed\n"); + drm_dbg_kms(&i915->drm, "H Width read failed\n"); return DP_TEST_NAK; } status = drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_V_HEIGHT_HI, &v_height, 2); if (status <= 0) { - DRM_DEBUG_KMS("V Height read failed\n"); + drm_dbg_kms(&i915->drm, "V Height read failed\n"); return DP_TEST_NAK; } status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_MISC0, &test_misc); if (status <= 0) { - DRM_DEBUG_KMS("TEST MISC read failed\n"); + drm_dbg_kms(&i915->drm, "TEST MISC read failed\n"); return DP_TEST_NAK; } if ((test_misc & DP_TEST_COLOR_FORMAT_MASK) != DP_COLOR_FORMAT_RGB) @@ -4959,6 +5356,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp) static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 test_result = DP_TEST_ACK; struct intel_connector *intel_connector = intel_dp->attached_connector; struct drm_connector *connector = &intel_connector->base; @@ -4975,9 +5373,10 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp) */ if (intel_dp->aux.i2c_nack_count > 0 || intel_dp->aux.i2c_defer_count > 0) - DRM_DEBUG_KMS("EDID read had %d NACKs, %d DEFERs\n", - intel_dp->aux.i2c_nack_count, - intel_dp->aux.i2c_defer_count); + drm_dbg_kms(&i915->drm, + "EDID read had %d NACKs, %d DEFERs\n", + intel_dp->aux.i2c_nack_count, + intel_dp->aux.i2c_defer_count); intel_dp->compliance.test_data.edid = INTEL_DP_RESOLUTION_FAILSAFE; } else { struct edid *block = intel_connector->detect_edid; @@ -4989,7 +5388,8 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp) if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_EDID_CHECKSUM, block->checksum) <= 0) - DRM_DEBUG_KMS("Failed to write EDID checksum\n"); + drm_dbg_kms(&i915->drm, + "Failed to write EDID checksum\n"); test_result = DP_TEST_ACK | DP_TEST_EDID_CHECKSUM_WRITE; intel_dp->compliance.test_data.edid = INTEL_DP_RESOLUTION_PREFERRED; @@ -5001,43 +5401,217 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp) return test_result; } +static u8 intel_dp_prepare_phytest(struct intel_dp *intel_dp) +{ + struct drm_dp_phy_test_params *data = + &intel_dp->compliance.test_data.phytest; + + if (drm_dp_get_phy_test_pattern(&intel_dp->aux, data)) { + DRM_DEBUG_KMS("DP Phy Test pattern AUX read failure\n"); + return DP_TEST_NAK; + } + + /* + * link_mst is set to false to avoid executing mst related code + * during compliance testing. + */ + intel_dp->link_mst = false; + + return DP_TEST_ACK; +} + +static void intel_dp_phy_pattern_update(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = + to_i915(dp_to_dig_port(intel_dp)->base.base.dev); + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_dp_phy_test_params *data = + &intel_dp->compliance.test_data.phytest; + struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc); + enum pipe pipe = crtc->pipe; + u32 pattern_val; + + switch (data->phy_pattern) { + case DP_PHY_TEST_PATTERN_NONE: + DRM_DEBUG_KMS("Disable Phy Test Pattern\n"); + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), 0x0); + break; + case DP_PHY_TEST_PATTERN_D10_2: + DRM_DEBUG_KMS("Set D10.2 Phy Test Pattern\n"); + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), + DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_D10_2); + break; + case DP_PHY_TEST_PATTERN_ERROR_COUNT: + DRM_DEBUG_KMS("Set Error Count Phy Test Pattern\n"); + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), + DDI_DP_COMP_CTL_ENABLE | + DDI_DP_COMP_CTL_SCRAMBLED_0); + break; + case DP_PHY_TEST_PATTERN_PRBS7: + DRM_DEBUG_KMS("Set PRBS7 Phy Test Pattern\n"); + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), + DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_PRBS7); + break; + case DP_PHY_TEST_PATTERN_80BIT_CUSTOM: + /* + * FIXME: Ideally pattern should come from DPCD 0x250. As + * current firmware of DPR-100 could not set it, so hardcoding + * now for complaince test. + */ + DRM_DEBUG_KMS("Set 80Bit Custom Phy Test Pattern 0x3e0f83e0 0x0f83e0f8 0x0000f83e\n"); + pattern_val = 0x3e0f83e0; + intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 0), pattern_val); + pattern_val = 0x0f83e0f8; + intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 1), pattern_val); + pattern_val = 0x0000f83e; + intel_de_write(dev_priv, DDI_DP_COMP_PAT(pipe, 2), pattern_val); + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), + DDI_DP_COMP_CTL_ENABLE | + DDI_DP_COMP_CTL_CUSTOM80); + break; + case DP_PHY_TEST_PATTERN_CP2520: + /* + * FIXME: Ideally pattern should come from DPCD 0x24A. As + * current firmware of DPR-100 could not set it, so hardcoding + * now for complaince test. + */ + DRM_DEBUG_KMS("Set HBR2 compliance Phy Test Pattern\n"); + pattern_val = 0xFB; + intel_de_write(dev_priv, DDI_DP_COMP_CTL(pipe), + DDI_DP_COMP_CTL_ENABLE | DDI_DP_COMP_CTL_HBR2 | + pattern_val); + break; + default: + WARN(1, "Invalid Phy Test Pattern\n"); + } +} + +static void +intel_dp_autotest_phy_ddi_disable(struct intel_dp *intel_dp) +{ + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = intel_dig_port->base.base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc); + enum pipe pipe = crtc->pipe; + u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value; + + trans_ddi_func_ctl_value = intel_de_read(dev_priv, + TRANS_DDI_FUNC_CTL(pipe)); + trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe)); + dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe)); + + trans_ddi_func_ctl_value &= ~(TRANS_DDI_FUNC_ENABLE | + TGL_TRANS_DDI_PORT_MASK); + trans_conf_value &= ~PIPECONF_ENABLE; + dp_tp_ctl_value &= ~DP_TP_CTL_ENABLE; + + intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value); + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe), + trans_ddi_func_ctl_value); + intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value); +} + +static void +intel_dp_autotest_phy_ddi_enable(struct intel_dp *intel_dp, uint8_t lane_cnt) +{ + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_device *dev = intel_dig_port->base.base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + enum port port = intel_dig_port->base.port; + struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc); + enum pipe pipe = crtc->pipe; + u32 trans_ddi_func_ctl_value, trans_conf_value, dp_tp_ctl_value; + + trans_ddi_func_ctl_value = intel_de_read(dev_priv, + TRANS_DDI_FUNC_CTL(pipe)); + trans_conf_value = intel_de_read(dev_priv, PIPECONF(pipe)); + dp_tp_ctl_value = intel_de_read(dev_priv, TGL_DP_TP_CTL(pipe)); + + trans_ddi_func_ctl_value |= TRANS_DDI_FUNC_ENABLE | + TGL_TRANS_DDI_SELECT_PORT(port); + trans_conf_value |= PIPECONF_ENABLE; + dp_tp_ctl_value |= DP_TP_CTL_ENABLE; + + intel_de_write(dev_priv, PIPECONF(pipe), trans_conf_value); + intel_de_write(dev_priv, TGL_DP_TP_CTL(pipe), dp_tp_ctl_value); + intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(pipe), + trans_ddi_func_ctl_value); +} + +void intel_dp_process_phy_request(struct intel_dp *intel_dp) +{ + struct drm_dp_phy_test_params *data = + &intel_dp->compliance.test_data.phytest; + u8 link_status[DP_LINK_STATUS_SIZE]; + + if (!intel_dp_get_link_status(intel_dp, link_status)) { + DRM_DEBUG_KMS("failed to get link status\n"); + return; + } + + /* retrieve vswing & pre-emphasis setting */ + intel_dp_get_adjust_train(intel_dp, link_status); + + intel_dp_autotest_phy_ddi_disable(intel_dp); + + intel_dp_set_signal_levels(intel_dp); + + intel_dp_phy_pattern_update(intel_dp); + + intel_dp_autotest_phy_ddi_enable(intel_dp, data->num_lanes); + + drm_dp_set_phy_test_pattern(&intel_dp->aux, data, + link_status[DP_DPCD_REV]); +} + static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) { u8 test_result = DP_TEST_NAK; + + test_result = intel_dp_prepare_phytest(intel_dp); + if (test_result != DP_TEST_ACK) + DRM_ERROR("Phy test preparation failed\n"); + + intel_dp_process_phy_request(intel_dp); + return test_result; } static void intel_dp_handle_test_request(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 response = DP_TEST_NAK; u8 request = 0; int status; status = drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_REQUEST, &request); if (status <= 0) { - DRM_DEBUG_KMS("Could not read test request from sink\n"); + drm_dbg_kms(&i915->drm, + "Could not read test request from sink\n"); goto update_status; } switch (request) { case DP_TEST_LINK_TRAINING: - DRM_DEBUG_KMS("LINK_TRAINING test requested\n"); + drm_dbg_kms(&i915->drm, "LINK_TRAINING test requested\n"); response = intel_dp_autotest_link_training(intel_dp); break; case DP_TEST_LINK_VIDEO_PATTERN: - DRM_DEBUG_KMS("TEST_PATTERN test requested\n"); + drm_dbg_kms(&i915->drm, "TEST_PATTERN test requested\n"); response = intel_dp_autotest_video_pattern(intel_dp); break; case DP_TEST_LINK_EDID_READ: - DRM_DEBUG_KMS("EDID test requested\n"); + drm_dbg_kms(&i915->drm, "EDID test requested\n"); response = intel_dp_autotest_edid(intel_dp); break; case DP_TEST_LINK_PHY_TEST_PATTERN: - DRM_DEBUG_KMS("PHY_PATTERN test requested\n"); + drm_dbg_kms(&i915->drm, "PHY_PATTERN test requested\n"); response = intel_dp_autotest_phy_pattern(intel_dp); break; default: - DRM_DEBUG_KMS("Invalid test request '%02x'\n", request); + drm_dbg_kms(&i915->drm, "Invalid test request '%02x'\n", + request); break; } @@ -5047,12 +5621,14 @@ static void intel_dp_handle_test_request(struct intel_dp *intel_dp) update_status: status = drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_RESPONSE, response); if (status <= 0) - DRM_DEBUG_KMS("Could not write test response to sink\n"); + drm_dbg_kms(&i915->drm, + "Could not write test response to sink\n"); } static int intel_dp_check_mst_status(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); bool bret; if (intel_dp->is_mst) { @@ -5069,12 +5645,13 @@ go_again: /* check link status - esi[10] = 0x200c */ if (intel_dp->active_mst_links > 0 && !drm_dp_channel_eq_ok(&esi[10], intel_dp->lane_count)) { - DRM_DEBUG_KMS("channel EQ not ok, retraining\n"); + drm_dbg_kms(&i915->drm, + "channel EQ not ok, retraining\n"); intel_dp_start_link_train(intel_dp); intel_dp_stop_link_train(intel_dp); } - DRM_DEBUG_KMS("got esi %3ph\n", esi); + drm_dbg_kms(&i915->drm, "got esi %3ph\n", esi); ret = drm_dp_mst_hpd_irq(&intel_dp->mst_mgr, esi, &handled); if (handled) { @@ -5090,7 +5667,8 @@ go_again: bret = intel_dp_get_sink_irq_esi(intel_dp, esi); if (bret == true) { - DRM_DEBUG_KMS("got esi2 %3ph\n", esi); + drm_dbg_kms(&i915->drm, + "got esi2 %3ph\n", esi); goto go_again; } } else @@ -5098,7 +5676,8 @@ go_again: return ret; } else { - DRM_DEBUG_KMS("failed to get ESI - device may have failed\n"); + drm_dbg_kms(&i915->drm, + "failed to get ESI - device may have failed\n"); intel_dp->is_mst = false; drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst); @@ -5220,14 +5799,13 @@ int intel_dp_retrain_link(struct intel_encoder *encoder, */ static enum intel_hotplug_state intel_dp_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received) + struct intel_connector *connector) { struct drm_modeset_acquire_ctx ctx; enum intel_hotplug_state state; int ret; - state = intel_encoder_hotplug(encoder, connector, irq_received); + state = intel_encoder_hotplug(encoder, connector); drm_modeset_acquire_init(&ctx, 0); @@ -5251,7 +5829,7 @@ intel_dp_hotplug(struct intel_encoder *encoder, * Keeping it consistent with intel_ddi_hotplug() and * intel_hdmi_hotplug(). */ - if (state == INTEL_HOTPLUG_UNCHANGED && irq_received) + if (state == INTEL_HOTPLUG_UNCHANGED && !connector->hotplug_retries) state = INTEL_HOTPLUG_RETRY; return state; @@ -5259,6 +5837,7 @@ intel_dp_hotplug(struct intel_encoder *encoder, static void intel_dp_check_service_irq(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 val; if (intel_dp->dpcd[DP_DPCD_REV] < 0x11) @@ -5277,7 +5856,7 @@ static void intel_dp_check_service_irq(struct intel_dp *intel_dp) intel_hdcp_handle_cp_irq(intel_dp->attached_connector); if (val & DP_SINK_SPECIFIC_IRQ) - DRM_DEBUG_DRIVER("Sink specific irq unhandled\n"); + drm_dbg_kms(&i915->drm, "Sink specific irq unhandled\n"); } /* @@ -5344,6 +5923,7 @@ intel_dp_short_pulse(struct intel_dp *intel_dp) static enum drm_connector_status intel_dp_detect_dpcd(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_lspcon *lspcon = dp_to_lspcon(intel_dp); u8 *dpcd = intel_dp->dpcd; u8 type; @@ -5391,7 +5971,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp) } /* Anything else is out of spec, warn and ignore */ - DRM_DEBUG_KMS("Broken DP branch device, ignoring\n"); + drm_dbg_kms(&i915->drm, "Broken DP branch device, ignoring\n"); return connector_status_disconnected; } @@ -5863,6 +6443,7 @@ static int intel_dp_get_modes(struct drm_connector *connector) static int intel_dp_connector_register(struct drm_connector *connector) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector)); int ret; @@ -5872,8 +6453,8 @@ intel_dp_connector_register(struct drm_connector *connector) intel_connector_debugfs_add(connector); - DRM_DEBUG_KMS("registering %s bus for %s\n", - intel_dp->aux.name, connector->kdev->kobj.name); + drm_dbg_kms(&i915->drm, "registering %s bus for %s\n", + intel_dp->aux.name, connector->kdev->kobj.name); intel_dp->aux.dev = connector->kdev; ret = drm_dp_aux_register(&intel_dp->aux); @@ -5959,6 +6540,7 @@ static int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, u8 *an) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(&intel_dig_port->base.base)); static const struct drm_dp_aux_msg msg = { .request = DP_AUX_NATIVE_WRITE, @@ -5973,8 +6555,9 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, dpcd_ret = drm_dp_dpcd_write(&intel_dig_port->dp.aux, DP_AUX_HDCP_AN, an, DRM_HDCP_AN_LEN); if (dpcd_ret != DRM_HDCP_AN_LEN) { - DRM_DEBUG_KMS("Failed to write An over DP/AUX (%zd)\n", - dpcd_ret); + drm_dbg_kms(&i915->drm, + "Failed to write An over DP/AUX (%zd)\n", + dpcd_ret); return dpcd_ret >= 0 ? -EIO : dpcd_ret; } @@ -5990,17 +6573,19 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, rxbuf, sizeof(rxbuf), DP_AUX_CH_CTL_AUX_AKSV_SELECT); if (ret < 0) { - DRM_DEBUG_KMS("Write Aksv over DP/AUX failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, + "Write Aksv over DP/AUX failed (%d)\n", ret); return ret; } else if (ret == 0) { - DRM_DEBUG_KMS("Aksv write over DP/AUX was empty\n"); + drm_dbg_kms(&i915->drm, "Aksv write over DP/AUX was empty\n"); return -EIO; } reply = (rxbuf[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK; if (reply != DP_AUX_NATIVE_REPLY_ACK) { - DRM_DEBUG_KMS("Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n", - reply); + drm_dbg_kms(&i915->drm, + "Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n", + reply); return -EIO; } return 0; @@ -6009,11 +6594,14 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port, u8 *bksv) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; + ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BKSV, bksv, DRM_HDCP_KSV_LEN); if (ret != DRM_HDCP_KSV_LEN) { - DRM_DEBUG_KMS("Read Bksv from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read Bksv from DP/AUX failed (%zd)\n", ret); return ret >= 0 ? -EIO : ret; } return 0; @@ -6022,7 +6610,9 @@ static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port, static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port, u8 *bstatus) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; + /* * For some reason the HDMI and DP HDCP specs call this register * definition by different names. In the HDMI spec, it's called BSTATUS, @@ -6031,7 +6621,8 @@ static int intel_dp_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port, ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BINFO, bstatus, DRM_HDCP_BSTATUS_LEN); if (ret != DRM_HDCP_BSTATUS_LEN) { - DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); return ret >= 0 ? -EIO : ret; } return 0; @@ -6041,12 +6632,14 @@ static int intel_dp_hdcp_read_bcaps(struct intel_digital_port *intel_dig_port, u8 *bcaps) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BCAPS, bcaps, 1); if (ret != 1) { - DRM_DEBUG_KMS("Read bcaps from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read bcaps from DP/AUX failed (%zd)\n", ret); return ret >= 0 ? -EIO : ret; } @@ -6072,11 +6665,14 @@ static int intel_dp_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port, u8 *ri_prime) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; + ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_RI_PRIME, ri_prime, DRM_HDCP_RI_LEN); if (ret != DRM_HDCP_RI_LEN) { - DRM_DEBUG_KMS("Read Ri' from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, "Read Ri' from DP/AUX failed (%zd)\n", + ret); return ret >= 0 ? -EIO : ret; } return 0; @@ -6086,12 +6682,15 @@ static int intel_dp_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port, bool *ksv_ready) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; u8 bstatus; + ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, &bstatus, 1); if (ret != 1) { - DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); return ret >= 0 ? -EIO : ret; } *ksv_ready = bstatus & DP_BSTATUS_READY; @@ -6102,6 +6701,7 @@ static int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port, int num_downstream, u8 *ksv_fifo) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; int i; @@ -6113,8 +6713,9 @@ int intel_dp_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port, ksv_fifo + i * DRM_HDCP_KSV_LEN, len); if (ret != len) { - DRM_DEBUG_KMS("Read ksv[%d] from DP/AUX failed (%zd)\n", - i, ret); + drm_dbg_kms(&i915->drm, + "Read ksv[%d] from DP/AUX failed (%zd)\n", + i, ret); return ret >= 0 ? -EIO : ret; } } @@ -6125,6 +6726,7 @@ static int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port, int i, u32 *part) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; if (i >= DRM_HDCP_V_PRIME_NUM_PARTS) @@ -6134,7 +6736,8 @@ int intel_dp_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port, DP_AUX_HDCP_V_PRIME(i), part, DRM_HDCP_V_PRIME_PART_LEN); if (ret != DRM_HDCP_V_PRIME_PART_LEN) { - DRM_DEBUG_KMS("Read v'[%d] from DP/AUX failed (%zd)\n", i, ret); + drm_dbg_kms(&i915->drm, + "Read v'[%d] from DP/AUX failed (%zd)\n", i, ret); return ret >= 0 ? -EIO : ret; } return 0; @@ -6151,13 +6754,15 @@ int intel_dp_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port, static bool intel_dp_hdcp_check_link(struct intel_digital_port *intel_dig_port) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; u8 bstatus; ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_AUX_HDCP_BSTATUS, &bstatus, 1); if (ret != 1) { - DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); return false; } @@ -6232,13 +6837,15 @@ static inline int intel_dp_hdcp2_read_rx_status(struct intel_digital_port *intel_dig_port, u8 *rx_status) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); ssize_t ret; ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, DP_HDCP_2_2_REG_RXSTATUS_OFFSET, rx_status, HDCP_2_2_DP_RXSTATUS_LEN); if (ret != HDCP_2_2_DP_RXSTATUS_LEN) { - DRM_DEBUG_KMS("Read bstatus from DP/AUX failed (%zd)\n", ret); + drm_dbg_kms(&i915->drm, + "Read bstatus from DP/AUX failed (%zd)\n", ret); return ret >= 0 ? -EIO : ret; } @@ -6282,6 +6889,7 @@ static ssize_t intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port, const struct hdcp2_dp_msg_data *hdcp2_msg_data) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); struct intel_dp *dp = &intel_dig_port->dp; struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; u8 msg_id = hdcp2_msg_data->msg_id; @@ -6313,8 +6921,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port, } if (ret) - DRM_DEBUG_KMS("msg_id %d, ret %d, timeout(mSec): %d\n", - hdcp2_msg_data->msg_id, ret, timeout); + drm_dbg_kms(&i915->drm, + "msg_id %d, ret %d, timeout(mSec): %d\n", + hdcp2_msg_data->msg_id, ret, timeout); return ret; } @@ -6400,6 +7009,7 @@ static int intel_dp_hdcp2_read_msg(struct intel_digital_port *intel_dig_port, u8 msg_id, void *buf, size_t size) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); unsigned int offset; u8 *byte = buf; ssize_t ret, bytes_to_recv, len; @@ -6433,7 +7043,8 @@ int intel_dp_hdcp2_read_msg(struct intel_digital_port *intel_dig_port, ret = drm_dp_dpcd_read(&intel_dig_port->dp.aux, offset, (void *)byte, len); if (ret < 0) { - DRM_DEBUG_KMS("msg_id %d, ret %zd\n", msg_id, ret); + drm_dbg_kms(&i915->drm, "msg_id %d, ret %zd\n", + msg_id, ret); return ret; } @@ -6724,7 +7335,11 @@ static int intel_dp_connector_atomic_check(struct drm_connector *conn, if (ret) return ret; - if (INTEL_GEN(dev_priv) < 11) + /* + * We don't enable port sync on BDW due to missing w/as and + * due to not having adjusted the modeset sequence appropriately. + */ + if (INTEL_GEN(dev_priv) < 9) return 0; if (!intel_connector_needs_modeset(state, conn)) @@ -6763,28 +7378,45 @@ static const struct drm_encoder_funcs intel_dp_enc_funcs = { .destroy = intel_dp_encoder_destroy, }; +static bool intel_edp_have_power(struct intel_dp *intel_dp) +{ + intel_wakeref_t wakeref; + bool have_power = false; + + with_pps_lock(intel_dp, wakeref) { + have_power = edp_have_panel_power(intel_dp) && + edp_have_panel_vdd(intel_dp); + } + + return have_power; +} + enum irqreturn intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); struct intel_dp *intel_dp = &intel_dig_port->dp; - if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) { + if (intel_dig_port->base.type == INTEL_OUTPUT_EDP && + (long_hpd || !intel_edp_have_power(intel_dp))) { /* - * vdd off can generate a long pulse on eDP which + * vdd off can generate a long/short pulse on eDP which * would require vdd on to handle it, and thus we * would end up in an endless cycle of - * "vdd off -> long hpd -> vdd on -> detect -> vdd off -> ..." + * "vdd off -> long/short hpd -> vdd on -> detect -> vdd off -> ..." */ - DRM_DEBUG_KMS("ignoring long hpd on eDP [ENCODER:%d:%s]\n", - intel_dig_port->base.base.base.id, - intel_dig_port->base.base.name); + drm_dbg_kms(&i915->drm, + "ignoring %s hpd on eDP [ENCODER:%d:%s]\n", + long_hpd ? "long" : "short", + intel_dig_port->base.base.base.id, + intel_dig_port->base.base.name); return IRQ_HANDLED; } - DRM_DEBUG_KMS("got hpd irq on [ENCODER:%d:%s] - %s\n", - intel_dig_port->base.base.base.id, - intel_dig_port->base.base.name, - long_hpd ? "long" : "short"); + drm_dbg_kms(&i915->drm, "got hpd irq on [ENCODER:%d:%s] - %s\n", + intel_dig_port->base.base.base.id, + intel_dig_port->base.base.name, + long_hpd ? "long" : "short"); if (long_hpd) { intel_dp->reset_link_params = true; @@ -6797,8 +7429,10 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) * If we were in MST mode, and device is not * there, get out of MST mode */ - DRM_DEBUG_KMS("MST device may have disappeared %d vs %d\n", - intel_dp->is_mst, intel_dp->mst_mgr.mst_state); + drm_dbg_kms(&i915->drm, + "MST device may have disappeared %d vs %d\n", + intel_dp->is_mst, + intel_dp->mst_mgr.mst_state); intel_dp->is_mst = false; drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst); diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 0c7be8ed1423..6659ce15a693 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -114,7 +114,11 @@ void intel_dp_vsc_enable(struct intel_dp *intel_dp, void intel_dp_hdr_metadata_enable(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); +void intel_dp_set_infoframes(struct intel_encoder *encoder, bool enable, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state); bool intel_digital_port_connected(struct intel_encoder *encoder); +void intel_dp_process_phy_request(struct intel_dp *intel_dp); static inline unsigned int intel_dp_unused_lane_mask(int lane_count) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 3e706bb850a8..4b916468540f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -27,6 +27,7 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 reg_val = 0; /* Early return when display use other mechanism to enable backlight. */ @@ -35,8 +36,8 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER, ®_val) < 0) { - DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n", - DP_EDP_DISPLAY_CONTROL_REGISTER); + drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", + DP_EDP_DISPLAY_CONTROL_REGISTER); return; } if (enable) @@ -46,8 +47,8 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER, reg_val) != 1) { - DRM_DEBUG_KMS("Failed to %s aux backlight\n", - enable ? "enable" : "disable"); + drm_dbg_kms(&i915->drm, "Failed to %s aux backlight\n", + enable ? "enable" : "disable"); } } @@ -58,6 +59,7 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) { struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 read_val[2] = { 0x0 }; u8 mode_reg; u16 level = 0; @@ -65,8 +67,9 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &mode_reg) != 1) { - DRM_DEBUG_KMS("Failed to read the DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_MODE_SET_REGISTER); + drm_dbg_kms(&i915->drm, + "Failed to read the DPCD register 0x%x\n", + DP_EDP_BACKLIGHT_MODE_SET_REGISTER); return 0; } @@ -80,8 +83,8 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, &read_val, sizeof(read_val)) < 0) { - DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_BRIGHTNESS_MSB); + drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", + DP_EDP_BACKLIGHT_BRIGHTNESS_MSB); return 0; } level = read_val[0]; @@ -100,6 +103,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev { struct intel_connector *connector = to_intel_connector(conn_state->connector); struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 vals[2] = { 0x0 }; vals[0] = level; @@ -111,7 +115,8 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev } if (drm_dp_dpcd_write(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, vals, sizeof(vals)) < 0) { - DRM_DEBUG_KMS("Failed to write aux backlight level\n"); + drm_dbg_kms(&i915->drm, + "Failed to write aux backlight level\n"); return; } } @@ -133,7 +138,8 @@ static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector) freq = dev_priv->vbt.backlight.pwm_freq_hz; if (!freq) { - DRM_DEBUG_KMS("Use panel default backlight frequency\n"); + drm_dbg_kms(&dev_priv->drm, + "Use panel default backlight frequency\n"); return false; } @@ -146,13 +152,14 @@ static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector) fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4); if (fxp_min > fxp_actual || fxp_actual > fxp_max) { - DRM_DEBUG_KMS("Actual frequency out of range\n"); + drm_dbg_kms(&dev_priv->drm, "Actual frequency out of range\n"); return false; } if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_BACKLIGHT_FREQ_SET, (u8) f) < 0) { - DRM_DEBUG_KMS("Failed to write aux backlight freq\n"); + drm_dbg_kms(&dev_priv->drm, + "Failed to write aux backlight freq\n"); return false; } return true; @@ -163,13 +170,14 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st { struct intel_connector *connector = to_intel_connector(conn_state->connector); struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_panel *panel = &connector->panel; u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode; if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) { - DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_MODE_SET_REGISTER); + drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", + DP_EDP_BACKLIGHT_MODE_SET_REGISTER); return; } @@ -186,7 +194,8 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT, panel->backlight.pwmgen_bit_count) < 0) - DRM_DEBUG_KMS("Failed to write aux pwmgen bit count\n"); + drm_dbg_kms(&i915->drm, + "Failed to write aux pwmgen bit count\n"); break; @@ -203,7 +212,8 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st if (new_dpcd_buf != dpcd_buf) { if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf) < 0) { - DRM_DEBUG_KMS("Failed to write aux backlight mode\n"); + drm_dbg_kms(&i915->drm, + "Failed to write aux backlight mode\n"); } } @@ -237,9 +247,11 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector) * minimum value will applied automatically. So no need to check that. */ freq = i915->vbt.backlight.pwm_freq_hz; - DRM_DEBUG_KMS("VBT defined backlight frequency %u Hz\n", freq); + drm_dbg_kms(&i915->drm, "VBT defined backlight frequency %u Hz\n", + freq); if (!freq) { - DRM_DEBUG_KMS("Use panel default backlight frequency\n"); + drm_dbg_kms(&i915->drm, + "Use panel default backlight frequency\n"); return max_backlight; } @@ -254,12 +266,14 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector) */ if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min) != 1) { - DRM_DEBUG_KMS("Failed to read pwmgen bit count cap min\n"); + drm_dbg_kms(&i915->drm, + "Failed to read pwmgen bit count cap min\n"); return max_backlight; } if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max) != 1) { - DRM_DEBUG_KMS("Failed to read pwmgen bit count cap max\n"); + drm_dbg_kms(&i915->drm, + "Failed to read pwmgen bit count cap max\n"); return max_backlight; } pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK; @@ -268,7 +282,8 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector) fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4); fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4); if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) { - DRM_DEBUG_KMS("VBT defined backlight frequency out of range\n"); + drm_dbg_kms(&i915->drm, + "VBT defined backlight frequency out of range\n"); return max_backlight; } @@ -279,10 +294,11 @@ static u32 intel_dp_aux_calc_max_backlight(struct intel_connector *connector) break; } - DRM_DEBUG_KMS("Using eDP pwmgen bit count of %d\n", pn); + drm_dbg_kms(&i915->drm, "Using eDP pwmgen bit count of %d\n", pn); if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT, pn) < 0) { - DRM_DEBUG_KMS("Failed to write aux pwmgen bit count\n"); + drm_dbg_kms(&i915->drm, + "Failed to write aux pwmgen bit count\n"); return max_backlight; } panel->backlight.pwmgen_bit_count = pn; @@ -312,6 +328,7 @@ static bool intel_dp_aux_display_control_capable(struct intel_connector *connector) { struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); /* Check the eDP Display control capabilities registers to determine if * the panel can support backlight control over the aux channel @@ -319,7 +336,7 @@ intel_dp_aux_display_control_capable(struct intel_connector *connector) if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP && (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP) && !(intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP)) { - DRM_DEBUG_KMS("AUX Backlight Control Supported!\n"); + drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n"); return true; } return false; @@ -329,8 +346,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector) { struct intel_panel *panel = &intel_connector->panel; struct intel_dp *intel_dp = enc_to_intel_dp(intel_connector->encoder); - struct drm_device *dev = intel_connector->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); if (i915_modparams.enable_dpcd_backlight == 0 || !intel_dp_aux_display_control_capable(intel_connector)) @@ -340,17 +356,17 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector) * There are a lot of machines that don't advertise the backlight * control interface to use properly in their VBIOS, :\ */ - if (dev_priv->vbt.backlight.type != + if (i915->vbt.backlight.type != INTEL_BACKLIGHT_VESA_EDP_AUX_INTERFACE && !drm_dp_has_quirk(&intel_dp->desc, intel_dp->edid_quirks, DP_QUIRK_FORCE_DPCD_BACKLIGHT)) { - DRM_DEV_INFO(dev->dev, - "Panel advertises DPCD backlight support, but " - "VBT disagrees. If your backlight controls " - "don't work try booting with " - "i915.enable_dpcd_backlight=1. If your machine " - "needs this, please file a _new_ bug report on " - "drm/i915, see " FDO_BUG_URL " for details.\n"); + drm_info(&i915->drm, + "Panel advertises DPCD backlight support, but " + "VBT disagrees. If your backlight controls " + "don't work try booting with " + "i915.enable_dpcd_backlight=1. If your machine " + "needs this, please file a _new_ bug report on " + "drm/i915, see " FDO_BUG_URL " for details.\n"); return -ENODEV; } diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index a7defb37ab00..e4f1843170b7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -34,9 +34,8 @@ intel_dp_dump_link_status(const u8 link_status[DP_LINK_STATUS_SIZE]) link_status[3], link_status[4], link_status[5]); } -static void -intel_get_adjust_train(struct intel_dp *intel_dp, - const u8 link_status[DP_LINK_STATUS_SIZE]) +void intel_dp_get_adjust_train(struct intel_dp *intel_dp, + const u8 link_status[DP_LINK_STATUS_SIZE]) { u8 v = 0; u8 p = 0; @@ -219,7 +218,7 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK; /* Update training set as requested by target */ - intel_get_adjust_train(intel_dp, link_status); + intel_dp_get_adjust_train(intel_dp, link_status); if (!intel_dp_update_link_train(intel_dp)) { drm_err(&i915->drm, "failed to update link training\n"); @@ -338,7 +337,7 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) } /* Update training set as requested by target */ - intel_get_adjust_train(intel_dp, link_status); + intel_dp_get_adjust_train(intel_dp, link_status); if (!intel_dp_update_link_train(intel_dp)) { drm_err(&i915->drm, "failed to update link training\n"); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h index 174566adcc92..01f1dabbb060 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h @@ -6,8 +6,12 @@ #ifndef __INTEL_DP_LINK_TRAINING_H__ #define __INTEL_DP_LINK_TRAINING_H__ +#include <drm/drm_dp_helper.h> + struct intel_dp; +void intel_dp_get_adjust_train(struct intel_dp *intel_dp, + const u8 link_status[DP_LINK_STATUS_SIZE]); void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 35debce71366..a83f910d8e15 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -47,9 +47,9 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, struct intel_dp *intel_dp = &intel_mst->primary->dp; struct intel_connector *connector = to_intel_connector(conn_state->connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - void *port = connector->port; bool constant_n = drm_dp_has_quirk(&intel_dp->desc, 0, DP_DPCD_QUIRK_CONSTANT_N); int bpp, slots = -EINVAL; @@ -65,7 +65,8 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, false); slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr, - port, crtc_state->pbn, 0); + connector->port, + crtc_state->pbn, 0); if (slots == -EDEADLK) return slots; if (slots >= 0) @@ -73,7 +74,8 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, } if (slots < 0) { - DRM_DEBUG_KMS("failed finding vcpi slots:%d\n", slots); + drm_dbg_kms(&i915->drm, "failed finding vcpi slots:%d\n", + slots); return slots; } @@ -88,56 +90,10 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, return 0; } -/* - * Iterate over all connectors and return the smallest transcoder in the MST - * stream - */ -static enum transcoder -intel_dp_mst_master_trans_compute(struct intel_atomic_state *state, - struct intel_dp *mst_port) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_digital_connector_state *conn_state; - struct intel_connector *connector; - enum pipe ret = I915_MAX_PIPES; - int i; - - if (INTEL_GEN(dev_priv) < 12) - return INVALID_TRANSCODER; - - for_each_new_intel_connector_in_state(state, connector, conn_state, i) { - struct intel_crtc_state *crtc_state; - struct intel_crtc *crtc; - - if (connector->mst_port != mst_port || !conn_state->base.crtc) - continue; - - crtc = to_intel_crtc(conn_state->base.crtc); - crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - if (!crtc_state->uapi.active) - continue; - - /* - * Using crtc->pipe because crtc_state->cpu_transcoder is - * computed, so others CRTCs could have non-computed - * cpu_transcoder - */ - if (crtc->pipe < ret) - ret = crtc->pipe; - } - - if (ret == I915_MAX_PIPES) - return INVALID_TRANSCODER; - - /* Simple cast works because TGL don't have a eDP transcoder */ - return (enum transcoder)ret; -} - static int intel_dp_mst_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { - struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder); struct intel_dp *intel_dp = &intel_mst->primary->dp; @@ -147,7 +103,6 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder, to_intel_digital_connector_state(conn_state); const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; - void *port = connector->port; struct link_config_limits limits; int ret; @@ -200,7 +155,56 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder, intel_ddi_compute_min_voltage_level(dev_priv, pipe_config); - pipe_config->mst_master_transcoder = intel_dp_mst_master_trans_compute(state, intel_dp); + return 0; +} + +/* + * Iterate over all connectors and return a mask of + * all CPU transcoders streaming over the same DP link. + */ +static unsigned int +intel_dp_mst_transcoder_mask(struct intel_atomic_state *state, + struct intel_dp *mst_port) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + const struct intel_digital_connector_state *conn_state; + struct intel_connector *connector; + u8 transcoders = 0; + int i; + + if (INTEL_GEN(dev_priv) < 12) + return 0; + + for_each_new_intel_connector_in_state(state, connector, conn_state, i) { + const struct intel_crtc_state *crtc_state; + struct intel_crtc *crtc; + + if (connector->mst_port != mst_port || !conn_state->base.crtc) + continue; + + crtc = to_intel_crtc(conn_state->base.crtc); + crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + + if (!crtc_state->hw.active) + continue; + + transcoders |= BIT(crtc_state->cpu_transcoder); + } + + return transcoders; +} + +static int intel_dp_mst_compute_config_late(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state); + struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder); + struct intel_dp *intel_dp = &intel_mst->primary->dp; + + /* lowest numbered transcoder will be designated master */ + crtc_state->mst_master_transcoder = + ffs(intel_dp_mst_transcoder_mask(state, intel_dp)) - 1; return 0; } @@ -312,7 +316,8 @@ intel_dp_mst_atomic_check(struct drm_connector *connector, return ret; } -static void intel_mst_disable_dp(struct intel_encoder *encoder, +static void intel_mst_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -321,22 +326,25 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder, struct intel_dp *intel_dp = &intel_dig_port->dp; struct intel_connector *connector = to_intel_connector(old_conn_state->connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); int ret; - DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links); + drm_dbg_kms(&i915->drm, "active links %d\n", + intel_dp->active_mst_links); drm_dp_mst_reset_vcpi_slots(&intel_dp->mst_mgr, connector->port); ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); if (ret) { - DRM_DEBUG_KMS("failed to update payload %d\n", ret); + drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret); } if (old_crtc_state->has_audio) intel_audio_codec_disable(encoder, old_crtc_state, old_conn_state); } -static void intel_mst_post_disable_dp(struct intel_encoder *encoder, +static void intel_mst_post_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -370,7 +378,8 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder, if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status, DP_TP_STATUS_ACT_SENT, 1)) - DRM_ERROR("Timed out waiting for ACT sent when disabling\n"); + drm_err(&dev_priv->drm, + "Timed out waiting for ACT sent when disabling\n"); drm_dp_check_act_status(&intel_dp->mst_mgr); drm_dp_mst_deallocate_vcpi(&intel_dp->mst_mgr, connector->port); @@ -401,13 +410,15 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder, intel_mst->connector = NULL; if (last_mst_stream) - intel_dig_port->base.post_disable(&intel_dig_port->base, + intel_dig_port->base.post_disable(state, &intel_dig_port->base, old_crtc_state, NULL); - DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links); + drm_dbg_kms(&dev_priv->drm, "active links %d\n", + intel_dp->active_mst_links); } -static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder, +static void intel_mst_pre_pll_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -416,11 +427,12 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder, struct intel_dp *intel_dp = &intel_dig_port->dp; if (intel_dp->active_mst_links == 0) - intel_dig_port->base.pre_pll_enable(&intel_dig_port->base, + intel_dig_port->base.pre_pll_enable(state, &intel_dig_port->base, pipe_config, NULL); } -static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, +static void intel_mst_pre_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -444,7 +456,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, INTEL_GEN(dev_priv) >= 12 && first_mst_stream && !intel_dp_mst_is_master_trans(pipe_config)); - DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links); + drm_dbg_kms(&dev_priv->drm, "active links %d\n", + intel_dp->active_mst_links); if (first_mst_stream) intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); @@ -452,7 +465,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true); if (first_mst_stream) - intel_dig_port->base.pre_enable(&intel_dig_port->base, + intel_dig_port->base.pre_enable(state, &intel_dig_port->base, pipe_config, NULL); ret = drm_dp_mst_allocate_vcpi(&intel_dp->mst_mgr, @@ -460,7 +473,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, pipe_config->pbn, pipe_config->dp_m_n.tu); if (!ret) - DRM_ERROR("failed to allocate vcpi\n"); + drm_err(&dev_priv->drm, "failed to allocate vcpi\n"); intel_dp->active_mst_links++; temp = intel_de_read(dev_priv, intel_dp->regs.dp_tp_status); @@ -483,7 +496,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, intel_dp_set_m_n(pipe_config, M1_N1); } -static void intel_mst_enable_dp(struct intel_encoder *encoder, +static void intel_mst_enable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -498,11 +512,12 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder, intel_crtc_vblank_on(pipe_config); - DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links); + drm_dbg_kms(&dev_priv->drm, "active links %d\n", + intel_dp->active_mst_links); if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status, DP_TP_STATUS_ACT_SENT, 1)) - DRM_ERROR("Timed out waiting for ACT sent\n"); + drm_err(&dev_priv->drm, "Timed out waiting for ACT sent\n"); drm_dp_check_act_status(&intel_dp->mst_mgr); @@ -785,6 +800,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum intel_encoder->pipe_mask = ~0; intel_encoder->compute_config = intel_dp_mst_compute_config; + intel_encoder->compute_config_late = intel_dp_mst_compute_config_late; intel_encoder->disable = intel_mst_disable_dp; intel_encoder->post_disable = intel_mst_post_disable_dp; intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp; diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c index a2a937109a5a..afa4e6817e8c 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.c +++ b/drivers/gpu/drm/i915/display/intel_dsi.c @@ -31,20 +31,21 @@ int intel_dsi_tlpx_ns(const struct intel_dsi *intel_dsi) int intel_dsi_get_modes(struct drm_connector *connector) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_display_mode *mode; - DRM_DEBUG_KMS("\n"); + drm_dbg_kms(&i915->drm, "\n"); if (!intel_connector->panel.fixed_mode) { - DRM_DEBUG_KMS("no fixed mode\n"); + drm_dbg_kms(&i915->drm, "no fixed mode\n"); return 0; } mode = drm_mode_duplicate(connector->dev, intel_connector->panel.fixed_mode); if (!mode) { - DRM_DEBUG_KMS("drm_mode_duplicate failed\n"); + drm_dbg_kms(&i915->drm, "drm_mode_duplicate failed\n"); return 0; } @@ -60,7 +61,7 @@ enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector, const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; - DRM_DEBUG_KMS("\n"); + drm_dbg_kms(&dev_priv->drm, "\n"); if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 574dcfec9577..3c9c05478a03 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -453,8 +453,7 @@ static inline void i2c_acpi_find_adapter(struct intel_dsi *intel_dsi, static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) { - struct drm_device *drm_dev = intel_dsi->base.base.dev; - struct device *dev = &drm_dev->pdev->dev; + struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); struct i2c_adapter *adapter; struct i2c_msg msg; int ret; @@ -471,7 +470,7 @@ static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) adapter = i2c_get_adapter(intel_dsi->i2c_bus_num); if (!adapter) { - DRM_DEV_ERROR(dev, "Cannot find a valid i2c bus for xfer\n"); + drm_err(&i915->drm, "Cannot find a valid i2c bus for xfer\n"); goto err_bus; } @@ -489,9 +488,9 @@ static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) ret = i2c_transfer(adapter, &msg, 1); if (ret < 0) - DRM_DEV_ERROR(dev, - "Failed to xfer payload of size (%u) to reg (%u)\n", - payload_size, reg_offset); + drm_err(&i915->drm, + "Failed to xfer payload of size (%u) to reg (%u)\n", + payload_size, reg_offset); kfree(payload_data); err_alloc: diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index 341d5ce8b062..5cd09034519b 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -183,7 +183,8 @@ static void intel_dvo_get_config(struct intel_encoder *encoder, pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock; } -static void intel_disable_dvo(struct intel_encoder *encoder, +static void intel_disable_dvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -197,7 +198,8 @@ static void intel_disable_dvo(struct intel_encoder *encoder, intel_de_read(dev_priv, dvo_reg); } -static void intel_enable_dvo(struct intel_encoder *encoder, +static void intel_enable_dvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -272,7 +274,8 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder, return 0; } -static void intel_dvo_pre_enable(struct intel_encoder *encoder, +static void intel_dvo_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 2e5d835a9eaa..56bcd6c52a02 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -104,7 +104,7 @@ static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv) /* Wait for compressing bit to clear */ if (intel_de_wait_for_clear(dev_priv, FBC_STATUS, FBC_STAT_COMPRESSING, 10)) { - DRM_DEBUG_KMS("FBC idle timed out\n"); + drm_dbg_kms(&dev_priv->drm, "FBC idle timed out\n"); return; } } @@ -485,7 +485,8 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, if (!ret) goto err_llb; else if (ret > 1) { - DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); + drm_info(&dev_priv->drm, + "Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); } @@ -521,8 +522,9 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, dev_priv->dsm.start + compressed_llb->start); } - DRM_DEBUG_KMS("reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n", - fbc->compressed_fb.size, fbc->threshold); + drm_dbg_kms(&dev_priv->drm, + "reserved %llu bytes of contiguous stolen space for FBC, threshold: %d\n", + fbc->compressed_fb.size, fbc->threshold); return 0; @@ -531,7 +533,7 @@ err_fb: i915_gem_stolen_remove_node(dev_priv, &fbc->compressed_fb); err_llb: if (drm_mm_initialized(&dev_priv->mm.stolen)) - pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size); + drm_info_once(&dev_priv->drm, "not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size); return -ENOSPC; } @@ -606,6 +608,19 @@ static bool pixel_format_is_valid(struct drm_i915_private *dev_priv, } } +static bool rotation_is_valid(struct drm_i915_private *dev_priv, + u32 pixel_format, unsigned int rotation) +{ + if (INTEL_GEN(dev_priv) >= 9 && pixel_format == DRM_FORMAT_RGB565 && + drm_rotation_90_or_270(rotation)) + return false; + else if (INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv) && + rotation != DRM_MODE_ROTATE_0) + return false; + + return true; +} + /* * For some reason, the hardware tracking starts looking at whatever we * programmed as the display plane base address register. It does not look at @@ -640,6 +655,22 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) return effective_w <= max_w && effective_h <= max_h; } +static bool tiling_is_valid(struct drm_i915_private *dev_priv, + uint64_t modifier) +{ + switch (modifier) { + case DRM_FORMAT_MOD_LINEAR: + if (INTEL_GEN(dev_priv) >= 9) + return true; + return false; + case I915_FORMAT_MOD_X_TILED: + case I915_FORMAT_MOD_Y_TILED: + return true; + default: + return false; + } +} + static void intel_fbc_update_state_cache(struct intel_crtc *crtc, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) @@ -673,6 +704,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, cache->fb.format = fb->format; cache->fb.stride = fb->pitches[0]; + cache->fb.modifier = fb->modifier; drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE && !plane_state->vma->fence); @@ -746,29 +778,39 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) return false; } - /* The use of a CPU fence is mandatory in order to detect writes - * by the CPU to the scanout and trigger updates to the FBC. + /* The use of a CPU fence is one of two ways to detect writes by the + * CPU to the scanout and trigger updates to the FBC. + * + * The other method is by software tracking (see + * intel_fbc_invalidate/flush()), it will manually notify FBC and nuke + * the current compressed buffer and recompress it. * * Note that is possible for a tiled surface to be unmappable (and - * so have no fence associated with it) due to aperture constaints + * so have no fence associated with it) due to aperture constraints * at the time of pinning. * * FIXME with 90/270 degree rotation we should use the fence on * the normal GTT view (the rotated view doesn't even have a * fence). Would need changes to the FBC fence Y offset as well. - * For now this will effecively disable FBC with 90/270 degree + * For now this will effectively disable FBC with 90/270 degree * rotation. */ - if (cache->fence_id < 0) { + if (INTEL_GEN(dev_priv) < 9 && cache->fence_id < 0) { fbc->no_fbc_reason = "framebuffer not tiled or fenced"; return false; } - if (INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv) && - cache->plane.rotation != DRM_MODE_ROTATE_0) { + + if (!rotation_is_valid(dev_priv, cache->fb.format->format, + cache->plane.rotation)) { fbc->no_fbc_reason = "rotation unsupported"; return false; } + if (!tiling_is_valid(dev_priv, cache->fb.modifier)) { + fbc->no_fbc_reason = "tiling unsupported"; + return false; + } + if (!stride_is_valid(dev_priv, cache->fb.stride)) { fbc->no_fbc_reason = "framebuffer stride not supported"; return false; @@ -948,7 +990,8 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv) drm_WARN_ON(&dev_priv->drm, !fbc->crtc); drm_WARN_ON(&dev_priv->drm, fbc->active); - DRM_DEBUG_KMS("Disabling FBC on pipe %c\n", pipe_name(crtc->pipe)); + drm_dbg_kms(&dev_priv->drm, "Disabling FBC on pipe %c\n", + pipe_name(crtc->pipe)); __intel_fbc_cleanup_cfb(dev_priv); @@ -1176,7 +1219,8 @@ void intel_fbc_enable(struct intel_atomic_state *state, else cache->gen9_wa_cfb_stride = 0; - DRM_DEBUG_KMS("Enabling FBC on pipe %c\n", pipe_name(crtc->pipe)); + drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n", + pipe_name(crtc->pipe)); fbc->no_fbc_reason = "FBC enabled but not active yet\n"; fbc->crtc = crtc; @@ -1238,7 +1282,7 @@ static void intel_fbc_underrun_work_fn(struct work_struct *work) if (fbc->underrun_detected || !fbc->crtc) goto out; - DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n"); + drm_dbg_kms(&dev_priv->drm, "Disabling FBC due to FIFO underrun.\n"); fbc->underrun_detected = true; intel_fbc_deactivate(dev_priv, "FIFO underrun"); @@ -1264,7 +1308,8 @@ int intel_fbc_reset_underrun(struct drm_i915_private *dev_priv) return ret; if (dev_priv->fbc.underrun_detected) { - DRM_DEBUG_KMS("Re-allowing FBC after fifo underrun\n"); + drm_dbg_kms(&dev_priv->drm, + "Re-allowing FBC after fifo underrun\n"); dev_priv->fbc.no_fbc_reason = "FIFO underrun cleared"; } @@ -1335,7 +1380,8 @@ static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ if (intel_vtd_active() && (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) { - DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); + drm_info(&dev_priv->drm, + "Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); return true; } @@ -1363,8 +1409,8 @@ void intel_fbc_init(struct drm_i915_private *dev_priv) mkwrite_device_info(dev_priv)->display.has_fbc = false; i915_modparams.enable_fbc = intel_sanitize_fbc_option(dev_priv); - DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", - i915_modparams.enable_fbc); + drm_dbg_kms(&dev_priv->drm, "Sanitized enable_fbc value: %d\n", + i915_modparams.enable_fbc); if (!HAS_FBC(dev_priv)) { fbc->no_fbc_reason = "unsupported by this chipset"; diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 3bc804212a99..bd39eb6a21b8 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -146,7 +146,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper, if (IS_ERR(obj)) obj = i915_gem_object_create_shmem(dev_priv, size); if (IS_ERR(obj)) { - DRM_ERROR("failed to allocate framebuffer\n"); + drm_err(&dev_priv->drm, "failed to allocate framebuffer\n"); return PTR_ERR(obj); } @@ -183,21 +183,23 @@ static int intelfb_create(struct drm_fb_helper *helper, if (intel_fb && (sizes->fb_width > intel_fb->base.width || sizes->fb_height > intel_fb->base.height)) { - DRM_DEBUG_KMS("BIOS fb too small (%dx%d), we require (%dx%d)," - " releasing it\n", - intel_fb->base.width, intel_fb->base.height, - sizes->fb_width, sizes->fb_height); + drm_dbg_kms(&dev_priv->drm, + "BIOS fb too small (%dx%d), we require (%dx%d)," + " releasing it\n", + intel_fb->base.width, intel_fb->base.height, + sizes->fb_width, sizes->fb_height); drm_framebuffer_put(&intel_fb->base); intel_fb = ifbdev->fb = NULL; } if (!intel_fb || drm_WARN_ON(dev, !intel_fb_obj(&intel_fb->base))) { - DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n"); + drm_dbg_kms(&dev_priv->drm, + "no BIOS fb, allocating a new one\n"); ret = intelfb_alloc(helper, sizes); if (ret) return ret; intel_fb = ifbdev->fb; } else { - DRM_DEBUG_KMS("re-using BIOS fb\n"); + drm_dbg_kms(&dev_priv->drm, "re-using BIOS fb\n"); prealloc = true; sizes->fb_width = intel_fb->base.width; sizes->fb_height = intel_fb->base.height; @@ -220,7 +222,7 @@ static int intelfb_create(struct drm_fb_helper *helper, info = drm_fb_helper_alloc_fbi(helper); if (IS_ERR(info)) { - DRM_ERROR("Failed to allocate fb_info\n"); + drm_err(&dev_priv->drm, "Failed to allocate fb_info\n"); ret = PTR_ERR(info); goto out_unpin; } @@ -240,7 +242,8 @@ static int intelfb_create(struct drm_fb_helper *helper, vaddr = i915_vma_pin_iomap(vma); if (IS_ERR(vaddr)) { - DRM_ERROR("Failed to remap framebuffer into virtual memory\n"); + drm_err(&dev_priv->drm, + "Failed to remap framebuffer into virtual memory\n"); ret = PTR_ERR(vaddr); goto out_unpin; } @@ -258,9 +261,9 @@ static int intelfb_create(struct drm_fb_helper *helper, /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ - DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x\n", - ifbdev->fb->base.width, ifbdev->fb->base.height, - i915_ggtt_offset(vma)); + drm_dbg_kms(&dev_priv->drm, "allocated %dx%d fb: 0x%08x\n", + ifbdev->fb->base.width, ifbdev->fb->base.height, + i915_ggtt_offset(vma)); ifbdev->vma = vma; ifbdev->vma_flags = flags; @@ -309,6 +312,7 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev) static bool intel_fbdev_init_bios(struct drm_device *dev, struct intel_fbdev *ifbdev) { + struct drm_i915_private *i915 = to_i915(dev); struct intel_framebuffer *fb = NULL; struct drm_crtc *crtc; struct intel_crtc *intel_crtc; @@ -321,21 +325,24 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, intel_crtc = to_intel_crtc(crtc); if (!crtc->state->active || !obj) { - DRM_DEBUG_KMS("pipe %c not active or no fb, skipping\n", - pipe_name(intel_crtc->pipe)); + drm_dbg_kms(&i915->drm, + "pipe %c not active or no fb, skipping\n", + pipe_name(intel_crtc->pipe)); continue; } if (obj->base.size > max_size) { - DRM_DEBUG_KMS("found possible fb from plane %c\n", - pipe_name(intel_crtc->pipe)); + drm_dbg_kms(&i915->drm, + "found possible fb from plane %c\n", + pipe_name(intel_crtc->pipe)); fb = to_intel_framebuffer(crtc->primary->state->fb); max_size = obj->base.size; } } if (!fb) { - DRM_DEBUG_KMS("no active fbs found, not using BIOS config\n"); + drm_dbg_kms(&i915->drm, + "no active fbs found, not using BIOS config\n"); goto out; } @@ -346,13 +353,14 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, intel_crtc = to_intel_crtc(crtc); if (!crtc->state->active) { - DRM_DEBUG_KMS("pipe %c not active, skipping\n", - pipe_name(intel_crtc->pipe)); + drm_dbg_kms(&i915->drm, + "pipe %c not active, skipping\n", + pipe_name(intel_crtc->pipe)); continue; } - DRM_DEBUG_KMS("checking plane %c for BIOS fb\n", - pipe_name(intel_crtc->pipe)); + drm_dbg_kms(&i915->drm, "checking plane %c for BIOS fb\n", + pipe_name(intel_crtc->pipe)); /* * See if the plane fb we found above will fit on this @@ -362,9 +370,10 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, cur_size = crtc->state->adjusted_mode.crtc_hdisplay; cur_size = cur_size * fb->base.format->cpp[0]; if (fb->base.pitches[0] < cur_size) { - DRM_DEBUG_KMS("fb not wide enough for plane %c (%d vs %d)\n", - pipe_name(intel_crtc->pipe), - cur_size, fb->base.pitches[0]); + drm_dbg_kms(&i915->drm, + "fb not wide enough for plane %c (%d vs %d)\n", + pipe_name(intel_crtc->pipe), + cur_size, fb->base.pitches[0]); fb = NULL; break; } @@ -372,28 +381,32 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, cur_size = crtc->state->adjusted_mode.crtc_vdisplay; cur_size = intel_fb_align_height(&fb->base, 0, cur_size); cur_size *= fb->base.pitches[0]; - DRM_DEBUG_KMS("pipe %c area: %dx%d, bpp: %d, size: %d\n", - pipe_name(intel_crtc->pipe), - crtc->state->adjusted_mode.crtc_hdisplay, - crtc->state->adjusted_mode.crtc_vdisplay, - fb->base.format->cpp[0] * 8, - cur_size); + drm_dbg_kms(&i915->drm, + "pipe %c area: %dx%d, bpp: %d, size: %d\n", + pipe_name(intel_crtc->pipe), + crtc->state->adjusted_mode.crtc_hdisplay, + crtc->state->adjusted_mode.crtc_vdisplay, + fb->base.format->cpp[0] * 8, + cur_size); if (cur_size > max_size) { - DRM_DEBUG_KMS("fb not big enough for plane %c (%d vs %d)\n", - pipe_name(intel_crtc->pipe), - cur_size, max_size); + drm_dbg_kms(&i915->drm, + "fb not big enough for plane %c (%d vs %d)\n", + pipe_name(intel_crtc->pipe), + cur_size, max_size); fb = NULL; break; } - DRM_DEBUG_KMS("fb big enough for plane %c (%d >= %d)\n", - pipe_name(intel_crtc->pipe), - max_size, cur_size); + drm_dbg_kms(&i915->drm, + "fb big enough for plane %c (%d >= %d)\n", + pipe_name(intel_crtc->pipe), + max_size, cur_size); } if (!fb) { - DRM_DEBUG_KMS("BIOS fb not suitable for all pipes, not using\n"); + drm_dbg_kms(&i915->drm, + "BIOS fb not suitable for all pipes, not using\n"); goto out; } @@ -415,7 +428,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, } - DRM_DEBUG_KMS("using BIOS fb for initial console\n"); + drm_dbg_kms(&i915->drm, "using BIOS fb for initial console\n"); return true; out: @@ -522,8 +535,9 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv) * processing, fbdev will perform a full connector reprobe if a hotplug event * was received while HPD was suspended. */ -static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state) +static void intel_fbdev_hpd_set_suspend(struct drm_i915_private *i915, int state) { + struct intel_fbdev *ifbdev = i915->fbdev; bool send_hpd = false; mutex_lock(&ifbdev->hpd_lock); @@ -533,7 +547,7 @@ static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state) mutex_unlock(&ifbdev->hpd_lock); if (send_hpd) { - DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n"); + drm_dbg_kms(&i915->drm, "Handling delayed fbcon HPD event\n"); drm_fb_helper_hotplug_event(&ifbdev->helper); } } @@ -588,7 +602,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous drm_fb_helper_set_suspend(&ifbdev->helper, state); console_unlock(); - intel_fbdev_hpd_set_suspend(ifbdev, state); + intel_fbdev_hpd_set_suspend(dev_priv, state); } void intel_fbdev_output_poll_changed(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c index a0cc894c3868..6f72feb14f3e 100644 --- a/drivers/gpu/drm/i915/display/intel_global_state.c +++ b/drivers/gpu/drm/i915/display/intel_global_state.c @@ -71,6 +71,7 @@ struct intel_global_state * intel_atomic_get_global_obj_state(struct intel_atomic_state *state, struct intel_global_obj *obj) { + struct drm_i915_private *i915 = to_i915(state->base.dev); int index, num_objs, i; size_t size; struct __intel_global_objs_state *arr; @@ -106,8 +107,8 @@ intel_atomic_get_global_obj_state(struct intel_atomic_state *state, state->num_global_objs = num_objs; - DRM_DEBUG_ATOMIC("Added new global object %p state %p to %p\n", - obj, obj_state, state); + drm_dbg_atomic(&i915->drm, "Added new global object %p state %p to %p\n", + obj, obj_state, state); return obj_state; } diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index ee0f27ea2810..d3ad10653b2e 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1391,6 +1391,7 @@ static int hdcp2_propagate_stream_management_info(struct intel_connector *connector) { struct intel_digital_port *intel_dig_port = intel_attached_dig_port(connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; union { struct hdcp2_rep_stream_manage stream_manage; @@ -1431,7 +1432,7 @@ int hdcp2_propagate_stream_management_info(struct intel_connector *connector) hdcp->seq_num_m++; if (hdcp->seq_num_m > HDCP_2_2_SEQ_NUM_MAX) { - DRM_DEBUG_KMS("seq_num_m roll over.\n"); + drm_dbg_kms(&i915->drm, "seq_num_m roll over.\n"); return -1; } @@ -2075,7 +2076,8 @@ int intel_hdcp_disable(struct intel_connector *connector) return ret; } -void intel_hdcp_update_pipe(struct intel_encoder *encoder, +void intel_hdcp_update_pipe(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h index 7c12ad609b1f..86bbaec120cc 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp.h @@ -11,6 +11,7 @@ struct drm_connector; struct drm_connector_state; struct drm_i915_private; +struct intel_atomic_state; struct intel_connector; struct intel_crtc_state; struct intel_encoder; @@ -26,7 +27,8 @@ int intel_hdcp_init(struct intel_connector *connector, int intel_hdcp_enable(struct intel_connector *connector, enum transcoder cpu_transcoder, u8 content_type); int intel_hdcp_disable(struct intel_connector *connector); -void intel_hdcp_update_pipe(struct intel_encoder *encoder, +void intel_hdcp_update_pipe(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 39930232b253..6b1bc955124c 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -707,13 +707,15 @@ void intel_read_infoframe(struct intel_encoder *encoder, /* see comment above for the reason for this offset */ ret = hdmi_infoframe_unpack(frame, buffer + 1, sizeof(buffer) - 1); if (ret) { - DRM_DEBUG_KMS("Failed to unpack infoframe type 0x%02x\n", type); + drm_dbg_kms(encoder->base.dev, + "Failed to unpack infoframe type 0x%02x\n", type); return; } if (frame->any.type != type) - DRM_DEBUG_KMS("Found the wrong infoframe type 0x%x (expected 0x%02x)\n", - frame->any.type, type); + drm_dbg_kms(encoder->base.dev, + "Found the wrong infoframe type 0x%x (expected 0x%02x)\n", + frame->any.type, type); } static bool @@ -853,7 +855,8 @@ intel_hdmi_compute_drm_infoframe(struct intel_encoder *encoder, ret = drm_hdmi_infoframe_set_hdr_metadata(frame, conn_state); if (ret < 0) { - DRM_DEBUG_KMS("couldn't set HDR metadata in infoframe\n"); + drm_dbg_kms(&dev_priv->drm, + "couldn't set HDR metadata in infoframe\n"); return false; } @@ -893,8 +896,9 @@ static void g4x_set_infoframes(struct intel_encoder *encoder, if (!(val & VIDEO_DIP_ENABLE)) return; if (port != (val & VIDEO_DIP_PORT_MASK)) { - DRM_DEBUG_KMS("video DIP still enabled on port %c\n", - (val & VIDEO_DIP_PORT_MASK) >> 29); + drm_dbg_kms(&dev_priv->drm, + "video DIP still enabled on port %c\n", + (val & VIDEO_DIP_PORT_MASK) >> 29); return; } val &= ~(VIDEO_DIP_ENABLE | VIDEO_DIP_ENABLE_AVI | @@ -906,8 +910,9 @@ static void g4x_set_infoframes(struct intel_encoder *encoder, if (port != (val & VIDEO_DIP_PORT_MASK)) { if (val & VIDEO_DIP_ENABLE) { - DRM_DEBUG_KMS("video DIP already enabled on port %c\n", - (val & VIDEO_DIP_PORT_MASK) >> 29); + drm_dbg_kms(&dev_priv->drm, + "video DIP already enabled on port %c\n", + (val & VIDEO_DIP_PORT_MASK) >> 29); return; } val &= ~VIDEO_DIP_PORT_MASK; @@ -1264,8 +1269,8 @@ void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable) if (hdmi->dp_dual_mode.type < DRM_DP_DUAL_MODE_TYPE2_DVI) return; - DRM_DEBUG_KMS("%s DP dual mode adaptor TMDS output\n", - enable ? "Enabling" : "Disabling"); + drm_dbg_kms(&dev_priv->drm, "%s DP dual mode adaptor TMDS output\n", + enable ? "Enabling" : "Disabling"); drm_dp_dual_mode_set_tmds_output(hdmi->dp_dual_mode.type, adapter, enable); @@ -1346,13 +1351,14 @@ int intel_hdmi_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, ret = intel_hdmi_hdcp_write(intel_dig_port, DRM_HDCP_DDC_AN, an, DRM_HDCP_AN_LEN); if (ret) { - DRM_DEBUG_KMS("Write An over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Write An over DDC failed (%d)\n", + ret); return ret; } ret = intel_gmbus_output_aksv(adapter); if (ret < 0) { - DRM_DEBUG_KMS("Failed to output aksv (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Failed to output aksv (%d)\n", ret); return ret; } return 0; @@ -1361,11 +1367,14 @@ int intel_hdmi_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, static int intel_hdmi_hdcp_read_bksv(struct intel_digital_port *intel_dig_port, u8 *bksv) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); + int ret; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BKSV, bksv, DRM_HDCP_KSV_LEN); if (ret) - DRM_DEBUG_KMS("Read Bksv over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Read Bksv over DDC failed (%d)\n", + ret); return ret; } @@ -1373,11 +1382,14 @@ static int intel_hdmi_hdcp_read_bstatus(struct intel_digital_port *intel_dig_port, u8 *bstatus) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); + int ret; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BSTATUS, bstatus, DRM_HDCP_BSTATUS_LEN); if (ret) - DRM_DEBUG_KMS("Read bstatus over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Read bstatus over DDC failed (%d)\n", + ret); return ret; } @@ -1385,12 +1397,14 @@ static int intel_hdmi_hdcp_repeater_present(struct intel_digital_port *intel_dig_port, bool *repeater_present) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); int ret; u8 val; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1); if (ret) { - DRM_DEBUG_KMS("Read bcaps over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Read bcaps over DDC failed (%d)\n", + ret); return ret; } *repeater_present = val & DRM_HDCP_DDC_BCAPS_REPEATER_PRESENT; @@ -1401,11 +1415,14 @@ static int intel_hdmi_hdcp_read_ri_prime(struct intel_digital_port *intel_dig_port, u8 *ri_prime) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); + int ret; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_RI_PRIME, ri_prime, DRM_HDCP_RI_LEN); if (ret) - DRM_DEBUG_KMS("Read Ri' over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Read Ri' over DDC failed (%d)\n", + ret); return ret; } @@ -1413,12 +1430,14 @@ static int intel_hdmi_hdcp_read_ksv_ready(struct intel_digital_port *intel_dig_port, bool *ksv_ready) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); int ret; u8 val; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_BCAPS, &val, 1); if (ret) { - DRM_DEBUG_KMS("Read bcaps over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, "Read bcaps over DDC failed (%d)\n", + ret); return ret; } *ksv_ready = val & DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY; @@ -1429,11 +1448,13 @@ static int intel_hdmi_hdcp_read_ksv_fifo(struct intel_digital_port *intel_dig_port, int num_downstream, u8 *ksv_fifo) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); int ret; ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_KSV_FIFO, ksv_fifo, num_downstream * DRM_HDCP_KSV_LEN); if (ret) { - DRM_DEBUG_KMS("Read ksv fifo over DDC failed (%d)\n", ret); + drm_dbg_kms(&i915->drm, + "Read ksv fifo over DDC failed (%d)\n", ret); return ret; } return 0; @@ -1443,6 +1464,7 @@ static int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port, int i, u32 *part) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); int ret; if (i >= DRM_HDCP_V_PRIME_NUM_PARTS) @@ -1451,7 +1473,8 @@ int intel_hdmi_hdcp_read_v_prime_part(struct intel_digital_port *intel_dig_port, ret = intel_hdmi_hdcp_read(intel_dig_port, DRM_HDCP_DDC_V_PRIME(i), part, DRM_HDCP_V_PRIME_PART_LEN); if (ret) - DRM_DEBUG_KMS("Read V'[%d] over DDC failed (%d)\n", i, ret); + drm_dbg_kms(&i915->drm, "Read V'[%d] over DDC failed (%d)\n", + i, ret); return ret; } @@ -1474,12 +1497,14 @@ static int kbl_repositioning_enc_en_signal(struct intel_connector *connector) ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, false); if (ret) { - DRM_ERROR("Disable HDCP signalling failed (%d)\n", ret); + drm_err(&dev_priv->drm, + "Disable HDCP signalling failed (%d)\n", ret); return ret; } ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, true); if (ret) { - DRM_ERROR("Enable HDCP signalling failed (%d)\n", ret); + drm_err(&dev_priv->drm, + "Enable HDCP signalling failed (%d)\n", ret); return ret; } @@ -1500,8 +1525,8 @@ int intel_hdmi_hdcp_toggle_signalling(struct intel_digital_port *intel_dig_port, ret = intel_ddi_toggle_hdcp_signalling(&intel_dig_port->base, enable); if (ret) { - DRM_ERROR("%s HDCP signalling failed (%d)\n", - enable ? "Enable" : "Disable", ret); + drm_err(&dev_priv->drm, "%s HDCP signalling failed (%d)\n", + enable ? "Enable" : "Disable", ret); return ret; } @@ -1536,10 +1561,13 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port) intel_de_write(i915, HDCP_RPRIME(i915, cpu_transcoder, port), ri.reg); /* Wait for Ri prime match */ - if (wait_for(intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) & + if (wait_for((intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) & + (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC)) == (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) { - DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n", - intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port))); + drm_err(&i915->drm, + "Ri' mismatch detected, link check failed (%x)\n", + intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, + port))); return false; } return true; @@ -1588,16 +1616,18 @@ static int get_hdcp2_msg_timeout(u8 msg_id, bool is_paired) } static inline -int hdcp2_detect_msg_availability(struct intel_digital_port *intel_digital_port, +int hdcp2_detect_msg_availability(struct intel_digital_port *intel_dig_port, u8 msg_id, bool *msg_ready, ssize_t *msg_sz) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); u8 rx_status[HDCP_2_2_HDMI_RXSTATUS_LEN]; int ret; - ret = intel_hdmi_hdcp2_read_rx_status(intel_digital_port, rx_status); + ret = intel_hdmi_hdcp2_read_rx_status(intel_dig_port, rx_status); if (ret < 0) { - DRM_DEBUG_KMS("rx_status read failed. Err %d\n", ret); + drm_dbg_kms(&i915->drm, "rx_status read failed. Err %d\n", + ret); return ret; } @@ -1617,6 +1647,7 @@ static ssize_t intel_hdmi_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port, u8 msg_id, bool paired) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); bool msg_ready = false; int timeout, ret; ssize_t msg_sz = 0; @@ -1631,8 +1662,8 @@ intel_hdmi_hdcp2_wait_for_msg(struct intel_digital_port *intel_dig_port, !ret && msg_ready && msg_sz, timeout * 1000, 1000, 5 * 1000); if (ret) - DRM_DEBUG_KMS("msg_id: %d, ret: %d, timeout: %d\n", - msg_id, ret, timeout); + drm_dbg_kms(&i915->drm, "msg_id: %d, ret: %d, timeout: %d\n", + msg_id, ret, timeout); return ret ? ret : msg_sz; } @@ -1651,6 +1682,7 @@ static int intel_hdmi_hdcp2_read_msg(struct intel_digital_port *intel_dig_port, u8 msg_id, void *buf, size_t size) { + struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev); struct intel_hdmi *hdmi = &intel_dig_port->hdmi; struct intel_hdcp *hdcp = &hdmi->attached_connector->hdcp; unsigned int offset; @@ -1666,15 +1698,17 @@ int intel_hdmi_hdcp2_read_msg(struct intel_digital_port *intel_dig_port, * available buffer. */ if (ret > size) { - DRM_DEBUG_KMS("msg_sz(%zd) is more than exp size(%zu)\n", - ret, size); + drm_dbg_kms(&i915->drm, + "msg_sz(%zd) is more than exp size(%zu)\n", + ret, size); return -1; } offset = HDCP_2_2_HDMI_REG_RD_MSG_OFFSET; ret = intel_hdmi_hdcp_read(intel_dig_port, offset, buf, ret); if (ret) - DRM_DEBUG_KMS("Failed to read msg_id: %d(%zd)\n", msg_id, ret); + drm_dbg_kms(&i915->drm, "Failed to read msg_id: %d(%zd)\n", + msg_id, ret); return ret; } @@ -1870,15 +1904,17 @@ static void intel_enable_hdmi_audio(struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); - drm_WARN_ON(encoder->base.dev, !pipe_config->has_hdmi_sink); - DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n", - pipe_name(crtc->pipe)); + drm_WARN_ON(&i915->drm, !pipe_config->has_hdmi_sink); + drm_dbg_kms(&i915->drm, "Enabling HDMI audio on pipe %c\n", + pipe_name(crtc->pipe)); intel_audio_codec_enable(encoder, pipe_config, conn_state); } -static void g4x_enable_hdmi(struct intel_encoder *encoder, +static void g4x_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -1900,7 +1936,8 @@ static void g4x_enable_hdmi(struct intel_encoder *encoder, intel_enable_hdmi_audio(encoder, pipe_config, conn_state); } -static void ibx_enable_hdmi(struct intel_encoder *encoder, +static void ibx_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -1951,7 +1988,8 @@ static void ibx_enable_hdmi(struct intel_encoder *encoder, intel_enable_hdmi_audio(encoder, pipe_config, conn_state); } -static void cpt_enable_hdmi(struct intel_encoder *encoder, +static void cpt_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2004,13 +2042,15 @@ static void cpt_enable_hdmi(struct intel_encoder *encoder, intel_enable_hdmi_audio(encoder, pipe_config, conn_state); } -static void vlv_enable_hdmi(struct intel_encoder *encoder, +static void vlv_enable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { } -static void intel_disable_hdmi(struct intel_encoder *encoder, +static void intel_disable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -2068,7 +2108,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder, intel_dp_dual_mode_set_tmds_output(intel_hdmi, false); } -static void g4x_disable_hdmi(struct intel_encoder *encoder, +static void g4x_disable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -2076,10 +2117,11 @@ static void g4x_disable_hdmi(struct intel_encoder *encoder, intel_audio_codec_disable(encoder, old_crtc_state, old_conn_state); - intel_disable_hdmi(encoder, old_crtc_state, old_conn_state); + intel_disable_hdmi(state, encoder, old_crtc_state, old_conn_state); } -static void pch_disable_hdmi(struct intel_encoder *encoder, +static void pch_disable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -2088,11 +2130,12 @@ static void pch_disable_hdmi(struct intel_encoder *encoder, old_crtc_state, old_conn_state); } -static void pch_post_disable_hdmi(struct intel_encoder *encoder, +static void pch_post_disable_hdmi(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_hdmi(encoder, old_crtc_state, old_conn_state); + intel_disable_hdmi(state, encoder, old_crtc_state, old_conn_state); } static int intel_hdmi_source_max_tmds_clock(struct intel_encoder *encoder) @@ -2289,10 +2332,12 @@ static bool intel_hdmi_ycbcr420_config(struct drm_connector *connector, struct intel_crtc_state *config) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_crtc *intel_crtc = to_intel_crtc(config->uapi.crtc); if (!connector->ycbcr_420_allowed) { - DRM_ERROR("Platform doesn't support YCBCR420 output\n"); + drm_err(&i915->drm, + "Platform doesn't support YCBCR420 output\n"); return false; } @@ -2300,7 +2345,8 @@ intel_hdmi_ycbcr420_config(struct drm_connector *connector, /* YCBCR 420 output conversion needs a scaler */ if (skl_update_scaler_crtc(config)) { - DRM_DEBUG_KMS("Scaler allocation for output failed\n"); + drm_dbg_kms(&i915->drm, + "Scaler allocation for output failed\n"); return false; } @@ -2341,6 +2387,7 @@ static int intel_hdmi_compute_bpc(struct intel_encoder *encoder, static int intel_hdmi_compute_clock(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; @@ -2365,13 +2412,15 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder, if (crtc_state->pipe_bpp > bpc * 3) crtc_state->pipe_bpp = bpc * 3; - DRM_DEBUG_KMS("picking %d bpc for HDMI output (pipe bpp: %d)\n", - bpc, crtc_state->pipe_bpp); + drm_dbg_kms(&i915->drm, + "picking %d bpc for HDMI output (pipe bpp: %d)\n", + bpc, crtc_state->pipe_bpp); if (hdmi_port_clock_valid(intel_hdmi, crtc_state->port_clock, false, crtc_state->has_hdmi_sink) != MODE_OK) { - DRM_DEBUG_KMS("unsupported HDMI clock (%d kHz), rejecting mode\n", - crtc_state->port_clock); + drm_dbg_kms(&i915->drm, + "unsupported HDMI clock (%d kHz), rejecting mode\n", + crtc_state->port_clock); return -EINVAL; } @@ -2434,7 +2483,8 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, if (drm_mode_is_420_only(&connector->display_info, adjusted_mode)) { if (!intel_hdmi_ycbcr420_config(connector, pipe_config)) { - DRM_ERROR("Can't support YCBCR420 output\n"); + drm_err(&dev_priv->drm, + "Can't support YCBCR420 output\n"); return -EINVAL; } } @@ -2474,25 +2524,26 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, } } - intel_hdmi_compute_gcp_infoframe(encoder, pipe_config, conn_state); + intel_hdmi_compute_gcp_infoframe(encoder, pipe_config, + conn_state); if (!intel_hdmi_compute_avi_infoframe(encoder, pipe_config, conn_state)) { - DRM_DEBUG_KMS("bad AVI infoframe\n"); + drm_dbg_kms(&dev_priv->drm, "bad AVI infoframe\n"); return -EINVAL; } if (!intel_hdmi_compute_spd_infoframe(encoder, pipe_config, conn_state)) { - DRM_DEBUG_KMS("bad SPD infoframe\n"); + drm_dbg_kms(&dev_priv->drm, "bad SPD infoframe\n"); return -EINVAL; } if (!intel_hdmi_compute_hdmi_infoframe(encoder, pipe_config, conn_state)) { - DRM_DEBUG_KMS("bad HDMI infoframe\n"); + drm_dbg_kms(&dev_priv->drm, "bad HDMI infoframe\n"); return -EINVAL; } if (!intel_hdmi_compute_drm_infoframe(encoder, pipe_config, conn_state)) { - DRM_DEBUG_KMS("bad DRM infoframe\n"); + drm_dbg_kms(&dev_priv->drm, "bad DRM infoframe\n"); return -EINVAL; } @@ -2542,7 +2593,8 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid) */ if (has_edid && !connector->override_edid && intel_bios_is_port_dp_dual_mode(dev_priv, port)) { - DRM_DEBUG_KMS("Assuming DP dual mode adaptor presence based on VBT\n"); + drm_dbg_kms(&dev_priv->drm, + "Assuming DP dual mode adaptor presence based on VBT\n"); type = DRM_DP_DUAL_MODE_TYPE1_DVI; } else { type = DRM_DP_DUAL_MODE_NONE; @@ -2556,9 +2608,10 @@ intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid) hdmi->dp_dual_mode.max_tmds_clock = drm_dp_dual_mode_max_tmds_clock(type, adapter); - DRM_DEBUG_KMS("DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n", - drm_dp_get_dual_mode_type_name(type), - hdmi->dp_dual_mode.max_tmds_clock); + drm_dbg_kms(&dev_priv->drm, + "DP dual mode adaptor (%s) detected (max TMDS clock: %d kHz)\n", + drm_dp_get_dual_mode_type_name(type), + hdmi->dp_dual_mode.max_tmds_clock); } static bool @@ -2578,7 +2631,8 @@ intel_hdmi_set_edid(struct drm_connector *connector) edid = drm_get_edid(connector, i2c); if (!edid && !intel_gmbus_is_forced_bit(i2c)) { - DRM_DEBUG_KMS("HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n"); + drm_dbg_kms(&dev_priv->drm, + "HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n"); intel_gmbus_force_bit(i2c, true); edid = drm_get_edid(connector, i2c); intel_gmbus_force_bit(i2c, false); @@ -2610,8 +2664,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) struct intel_encoder *encoder = &hdmi_to_dig_port(intel_hdmi)->base; intel_wakeref_t wakeref; - DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, connector->name); + drm_dbg_kms(&dev_priv->drm, "[CONNECTOR:%d:%s]\n", + connector->base.id, connector->name); wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); @@ -2642,8 +2696,10 @@ out: static void intel_hdmi_force(struct drm_connector *connector) { - DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", - connector->base.id, connector->name); + struct drm_i915_private *i915 = to_i915(connector->dev); + + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s]\n", + connector->base.id, connector->name); intel_hdmi_unset_edid(connector); @@ -2664,7 +2720,8 @@ static int intel_hdmi_get_modes(struct drm_connector *connector) return intel_connector_update_modes(connector, edid); } -static void intel_hdmi_pre_enable(struct intel_encoder *encoder, +static void intel_hdmi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2678,7 +2735,8 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder, pipe_config, conn_state); } -static void vlv_hdmi_pre_enable(struct intel_encoder *encoder, +static void vlv_hdmi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2695,12 +2753,13 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder, pipe_config->has_infoframe, pipe_config, conn_state); - g4x_enable_hdmi(encoder, pipe_config, conn_state); + g4x_enable_hdmi(state, encoder, pipe_config, conn_state); vlv_wait_port_ready(dev_priv, dport, 0x0); } -static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder, +static void vlv_hdmi_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2709,7 +2768,8 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder, vlv_phy_pre_pll_enable(encoder, pipe_config); } -static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder, +static void chv_hdmi_pre_pll_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2718,14 +2778,16 @@ static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder, chv_phy_pre_pll_enable(encoder, pipe_config); } -static void chv_hdmi_post_pll_disable(struct intel_encoder *encoder, +static void chv_hdmi_post_pll_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { chv_phy_post_pll_disable(encoder, old_crtc_state); } -static void vlv_hdmi_post_disable(struct intel_encoder *encoder, +static void vlv_hdmi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -2733,7 +2795,8 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder, vlv_phy_reset_lanes(encoder, old_crtc_state); } -static void chv_hdmi_post_disable(struct intel_encoder *encoder, +static void chv_hdmi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -2748,7 +2811,8 @@ static void chv_hdmi_post_disable(struct intel_encoder *encoder, vlv_dpio_put(dev_priv); } -static void chv_hdmi_pre_enable(struct intel_encoder *encoder, +static void chv_hdmi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -2766,7 +2830,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder, pipe_config->has_infoframe, pipe_config, conn_state); - g4x_enable_hdmi(encoder, pipe_config, conn_state); + g4x_enable_hdmi(state, encoder, pipe_config, conn_state); vlv_wait_port_ready(dev_priv, dport, 0x0); @@ -2785,6 +2849,7 @@ intel_hdmi_get_i2c_adapter(struct drm_connector *connector) static void intel_hdmi_create_i2c_symlink(struct drm_connector *connector) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct i2c_adapter *adapter = intel_hdmi_get_i2c_adapter(connector); struct kobject *i2c_kobj = &adapter->dev.kobj; struct kobject *connector_kobj = &connector->kdev->kobj; @@ -2792,7 +2857,7 @@ static void intel_hdmi_create_i2c_symlink(struct drm_connector *connector) ret = sysfs_create_link(connector_kobj, i2c_kobj, i2c_kobj->name); if (ret) - DRM_ERROR("Failed to create i2c symlink (%d)\n", ret); + drm_err(&i915->drm, "Failed to create i2c symlink (%d)\n", ret); } static void intel_hdmi_remove_i2c_symlink(struct drm_connector *connector) @@ -2921,9 +2986,10 @@ bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder, if (!sink_scrambling->supported) return true; - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] scrambling=%s, TMDS bit clock ratio=1/%d\n", - connector->base.id, connector->name, - yesno(scrambling), high_tmds_clock_ratio ? 40 : 10); + drm_dbg_kms(&dev_priv->drm, + "[CONNECTOR:%d:%s] scrambling=%s, TMDS bit clock ratio=1/%d\n", + connector->base.id, connector->name, + yesno(scrambling), high_tmds_clock_ratio ? 40 : 10); /* Set TMDS bit clock ratio to 1/40 or 1/10, and enable/disable scrambling */ return drm_scdc_set_high_tmds_clock_ratio(adapter, @@ -3065,8 +3131,9 @@ static u8 intel_hdmi_ddc_pin(struct intel_encoder *encoder) ddc_pin = intel_bios_alternate_ddc_pin(encoder); if (ddc_pin) { - DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (VBT)\n", - ddc_pin, port_name(port)); + drm_dbg_kms(&dev_priv->drm, + "Using DDC pin 0x%x for port %c (VBT)\n", + ddc_pin, port_name(port)); return ddc_pin; } @@ -3083,8 +3150,9 @@ static u8 intel_hdmi_ddc_pin(struct intel_encoder *encoder) else ddc_pin = g4x_port_to_ddc_pin(dev_priv, port); - DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (platform default)\n", - ddc_pin, port_name(port)); + drm_dbg_kms(&dev_priv->drm, + "Using DDC pin 0x%x for port %c (platform default)\n", + ddc_pin, port_name(port)); return ddc_pin; } @@ -3141,8 +3209,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_encoder->port; struct cec_connector_info conn_info; - DRM_DEBUG_KMS("Adding HDMI connector on [ENCODER:%d:%s]\n", - intel_encoder->base.base.id, intel_encoder->base.name); + drm_dbg_kms(&dev_priv->drm, + "Adding HDMI connector on [ENCODER:%d:%s]\n", + intel_encoder->base.base.id, intel_encoder->base.name); if (INTEL_GEN(dev_priv) < 12 && drm_WARN_ON(dev, port == PORT_A)) return; @@ -3186,7 +3255,8 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, int ret = intel_hdcp_init(intel_connector, &intel_hdmi_hdcp_shim); if (ret) - DRM_DEBUG_KMS("HDCP init failed, skipping.\n"); + drm_dbg_kms(&dev_priv->drm, + "HDCP init failed, skipping.\n"); } /* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written @@ -3205,16 +3275,16 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, cec_notifier_conn_register(dev->dev, port_identifier(port), &conn_info); if (!intel_hdmi->cec_notifier) - DRM_DEBUG_KMS("CEC notifier get failed\n"); + drm_dbg_kms(&dev_priv->drm, "CEC notifier get failed\n"); } static enum intel_hotplug_state intel_hdmi_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, bool irq_received) + struct intel_connector *connector) { enum intel_hotplug_state state; - state = intel_encoder_hotplug(encoder, connector, irq_received); + state = intel_encoder_hotplug(encoder, connector); /* * On many platforms the HDMI live state signal is known to be @@ -3228,7 +3298,7 @@ intel_hdmi_hotplug(struct intel_encoder *encoder, * time around we didn't detect any change in the sink's connection * status. */ - if (state == INTEL_HOTPLUG_UNCHANGED && irq_received) + if (state == INTEL_HOTPLUG_UNCHANGED && !connector->hotplug_retries) state = INTEL_HOTPLUG_RETRY; return state; diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c index a091442efba4..4f6f560e093e 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.c +++ b/drivers/gpu/drm/i915/display/intel_hotplug.c @@ -270,8 +270,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) enum intel_hotplug_state intel_encoder_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received) + struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; enum drm_connector_status old_status; @@ -392,12 +391,17 @@ static void i915_hotplug_work_func(struct work_struct *work) struct intel_encoder *encoder = intel_attached_encoder(connector); + if (hpd_event_bits & hpd_bit) + connector->hotplug_retries = 0; + else + connector->hotplug_retries++; + drm_dbg_kms(&dev_priv->drm, - "Connector %s (pin %i) received hotplug event.\n", - connector->base.name, pin); + "Connector %s (pin %i) received hotplug event. (retry %d)\n", + connector->base.name, pin, + connector->hotplug_retries); - switch (encoder->hotplug(encoder, connector, - hpd_event_bits & hpd_bit)) { + switch (encoder->hotplug(encoder, connector)) { case INTEL_HOTPLUG_UNCHANGED: break; case INTEL_HOTPLUG_CHANGED: diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.h b/drivers/gpu/drm/i915/display/intel_hotplug.h index 1e6b4fda2900..777b0743257e 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.h +++ b/drivers/gpu/drm/i915/display/intel_hotplug.h @@ -15,8 +15,7 @@ enum port; void intel_hpd_poll_init(struct drm_i915_private *dev_priv); enum intel_hotplug_state intel_encoder_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received); + struct intel_connector *connector); void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 pin_mask, u32 long_mask); void intel_hpd_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 9a067effcfa0..fe591f82163e 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -220,7 +220,8 @@ static void intel_lvds_pps_init_hw(struct drm_i915_private *dev_priv, REG_FIELD_PREP(PP_REFERENCE_DIVIDER_MASK, pps->divider) | REG_FIELD_PREP(PANEL_POWER_CYCLE_DELAY_MASK, DIV_ROUND_UP(pps->t4, 1000) + 1)); } -static void intel_pre_enable_lvds(struct intel_encoder *encoder, +static void intel_pre_enable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -301,7 +302,8 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder, /* * Sets the power state for the panel. */ -static void intel_enable_lvds(struct intel_encoder *encoder, +static void intel_enable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -323,7 +325,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder, intel_panel_enable_backlight(pipe_config, conn_state); } -static void intel_disable_lvds(struct intel_encoder *encoder, +static void intel_disable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -341,28 +344,31 @@ static void intel_disable_lvds(struct intel_encoder *encoder, intel_de_posting_read(dev_priv, lvds_encoder->reg); } -static void gmch_disable_lvds(struct intel_encoder *encoder, +static void gmch_disable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { intel_panel_disable_backlight(old_conn_state); - intel_disable_lvds(encoder, old_crtc_state, old_conn_state); + intel_disable_lvds(state, encoder, old_crtc_state, old_conn_state); } -static void pch_disable_lvds(struct intel_encoder *encoder, +static void pch_disable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { intel_panel_disable_backlight(old_conn_state); } -static void pch_post_disable_lvds(struct intel_encoder *encoder, +static void pch_post_disable_lvds(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_lvds(encoder, old_crtc_state, old_conn_state); + intel_disable_lvds(state, encoder, old_crtc_state, old_conn_state); } static enum drm_mode_status diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 481187223101..6e1d66323223 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -1342,7 +1342,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv) if (!HAS_OVERLAY(dev_priv)) return; - engine = dev_priv->engine[RCS0]; + engine = dev_priv->gt.engine[RCS0]; if (!engine || !engine->kernel_context) return; diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 276f43870802..08bfecfbe681 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -684,9 +684,10 @@ static void intel_panel_actually_set_backlight(const struct drm_connector_state *conn_state, u32 level) { struct intel_connector *connector = to_intel_connector(conn_state->connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_panel *panel = &connector->panel; - DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level); + drm_dbg_kms(&i915->drm, "set backlight PWM = %d\n", level); level = intel_panel_compute_brightness(connector, level); panel->backlight.set(conn_state, level); @@ -867,8 +868,8 @@ void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_st * another client is not activated. */ if (dev_priv->drm.switch_power_state == DRM_SWITCH_POWER_CHANGING) { - drm_dbg(&dev_priv->drm, - "Skipping backlight disable on vga switch\n"); + drm_dbg_kms(&dev_priv->drm, + "Skipping backlight disable on vga switch\n"); return; } @@ -1244,7 +1245,7 @@ static u32 intel_panel_get_backlight(struct intel_connector *connector) mutex_unlock(&dev_priv->backlight_lock); - drm_dbg(&dev_priv->drm, "get backlight PWM = %d\n", val); + drm_dbg_kms(&dev_priv->drm, "get backlight PWM = %d\n", val); return val; } @@ -1335,6 +1336,7 @@ static const struct backlight_ops intel_backlight_device_ops = { int intel_backlight_device_register(struct intel_connector *connector) { + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_panel *panel = &connector->panel; struct backlight_properties props; @@ -1374,14 +1376,15 @@ int intel_backlight_device_register(struct intel_connector *connector) &intel_backlight_device_ops, &props); if (IS_ERR(panel->backlight.device)) { - DRM_ERROR("Failed to register backlight: %ld\n", - PTR_ERR(panel->backlight.device)); + drm_err(&i915->drm, "Failed to register backlight: %ld\n", + PTR_ERR(panel->backlight.device)); panel->backlight.device = NULL; return -ENODEV; } - DRM_DEBUG_KMS("Connector %s backlight sysfs interface registered\n", - connector->base.name); + drm_dbg_kms(&i915->drm, + "Connector %s backlight sysfs interface registered\n", + connector->base.name); return 0; } @@ -1931,7 +1934,8 @@ static int pwm_setup_backlight(struct intel_connector *connector, return 0; } -void intel_panel_update_backlight(struct intel_encoder *encoder, +void intel_panel_update_backlight(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h index cedeea443336..11f2f6b628d8 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.h +++ b/drivers/gpu/drm/i915/display/intel_panel.h @@ -37,7 +37,8 @@ int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe); void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); -void intel_panel_update_backlight(struct intel_encoder *encoder, +void intel_panel_update_backlight(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state); diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index fd9b146e3aba..a0569fdfeb16 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -137,41 +137,42 @@ static void psr_irq_control(struct drm_i915_private *dev_priv) intel_de_write(dev_priv, imr_reg, val); } -static void psr_event_print(u32 val, bool psr2_enabled) +static void psr_event_print(struct drm_i915_private *i915, + u32 val, bool psr2_enabled) { - DRM_DEBUG_KMS("PSR exit events: 0x%x\n", val); + drm_dbg_kms(&i915->drm, "PSR exit events: 0x%x\n", val); if (val & PSR_EVENT_PSR2_WD_TIMER_EXPIRE) - DRM_DEBUG_KMS("\tPSR2 watchdog timer expired\n"); + drm_dbg_kms(&i915->drm, "\tPSR2 watchdog timer expired\n"); if ((val & PSR_EVENT_PSR2_DISABLED) && psr2_enabled) - DRM_DEBUG_KMS("\tPSR2 disabled\n"); + drm_dbg_kms(&i915->drm, "\tPSR2 disabled\n"); if (val & PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN) - DRM_DEBUG_KMS("\tSU dirty FIFO underrun\n"); + drm_dbg_kms(&i915->drm, "\tSU dirty FIFO underrun\n"); if (val & PSR_EVENT_SU_CRC_FIFO_UNDERRUN) - DRM_DEBUG_KMS("\tSU CRC FIFO underrun\n"); + drm_dbg_kms(&i915->drm, "\tSU CRC FIFO underrun\n"); if (val & PSR_EVENT_GRAPHICS_RESET) - DRM_DEBUG_KMS("\tGraphics reset\n"); + drm_dbg_kms(&i915->drm, "\tGraphics reset\n"); if (val & PSR_EVENT_PCH_INTERRUPT) - DRM_DEBUG_KMS("\tPCH interrupt\n"); + drm_dbg_kms(&i915->drm, "\tPCH interrupt\n"); if (val & PSR_EVENT_MEMORY_UP) - DRM_DEBUG_KMS("\tMemory up\n"); + drm_dbg_kms(&i915->drm, "\tMemory up\n"); if (val & PSR_EVENT_FRONT_BUFFER_MODIFY) - DRM_DEBUG_KMS("\tFront buffer modification\n"); + drm_dbg_kms(&i915->drm, "\tFront buffer modification\n"); if (val & PSR_EVENT_WD_TIMER_EXPIRE) - DRM_DEBUG_KMS("\tPSR watchdog timer expired\n"); + drm_dbg_kms(&i915->drm, "\tPSR watchdog timer expired\n"); if (val & PSR_EVENT_PIPE_REGISTERS_UPDATE) - DRM_DEBUG_KMS("\tPIPE registers updated\n"); + drm_dbg_kms(&i915->drm, "\tPIPE registers updated\n"); if (val & PSR_EVENT_REGISTER_UPDATE) - DRM_DEBUG_KMS("\tRegister updated\n"); + drm_dbg_kms(&i915->drm, "\tRegister updated\n"); if (val & PSR_EVENT_HDCP_ENABLE) - DRM_DEBUG_KMS("\tHDCP enabled\n"); + drm_dbg_kms(&i915->drm, "\tHDCP enabled\n"); if (val & PSR_EVENT_KVMR_SESSION_ENABLE) - DRM_DEBUG_KMS("\tKVMR session enabled\n"); + drm_dbg_kms(&i915->drm, "\tKVMR session enabled\n"); if (val & PSR_EVENT_VBI_ENABLE) - DRM_DEBUG_KMS("\tVBI enabled\n"); + drm_dbg_kms(&i915->drm, "\tVBI enabled\n"); if (val & PSR_EVENT_LPSP_MODE_EXIT) - DRM_DEBUG_KMS("\tLPSP mode exited\n"); + drm_dbg_kms(&i915->drm, "\tLPSP mode exited\n"); if ((val & PSR_EVENT_PSR_DISABLE) && !psr2_enabled) - DRM_DEBUG_KMS("\tPSR disabled\n"); + drm_dbg_kms(&i915->drm, "\tPSR disabled\n"); } void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) @@ -209,7 +210,7 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) intel_de_write(dev_priv, PSR_EVENT(cpu_transcoder), val); - psr_event_print(val, psr2_enabled); + psr_event_print(dev_priv, val, psr2_enabled); } } @@ -249,18 +250,21 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp) static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 val = 8; /* assume the worst if we can't read the value */ if (drm_dp_dpcd_readb(&intel_dp->aux, DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1) val &= DP_MAX_RESYNC_FRAME_COUNT_MASK; else - DRM_DEBUG_KMS("Unable to get sink synchronization latency, assuming 8 frames\n"); + drm_dbg_kms(&i915->drm, + "Unable to get sink synchronization latency, assuming 8 frames\n"); return val; } static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); u16 val; ssize_t r; @@ -273,7 +277,8 @@ static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp) r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_X_GRANULARITY, &val, 2); if (r != 2) - DRM_DEBUG_KMS("Unable to read DP_PSR2_SU_X_GRANULARITY\n"); + drm_dbg_kms(&i915->drm, + "Unable to read DP_PSR2_SU_X_GRANULARITY\n"); /* * Spec says that if the value read is 0 the default granularity should diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 637d8fe2f8c2..bc6c26818e15 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1430,7 +1430,8 @@ static void intel_sdvo_update_props(struct intel_sdvo *intel_sdvo, #undef UPDATE_PROPERTY } -static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, +static void intel_sdvo_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *intel_encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -1727,7 +1728,8 @@ static void intel_sdvo_enable_audio(struct intel_sdvo *intel_sdvo, SDVO_AUDIO_PRESENCE_DETECT); } -static void intel_disable_sdvo(struct intel_encoder *encoder, +static void intel_disable_sdvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *conn_state) { @@ -1775,20 +1777,23 @@ static void intel_disable_sdvo(struct intel_encoder *encoder, } } -static void pch_disable_sdvo(struct intel_encoder *encoder, +static void pch_disable_sdvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { } -static void pch_post_disable_sdvo(struct intel_encoder *encoder, +static void pch_post_disable_sdvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - intel_disable_sdvo(encoder, old_crtc_state, old_conn_state); + intel_disable_sdvo(state, encoder, old_crtc_state, old_conn_state); } -static void intel_enable_sdvo(struct intel_encoder *encoder, +static void intel_enable_sdvo(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -1934,12 +1939,11 @@ static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder) static enum intel_hotplug_state intel_sdvo_hotplug(struct intel_encoder *encoder, - struct intel_connector *connector, - bool irq_received) + struct intel_connector *connector) { intel_sdvo_enable_hotplug(encoder); - return intel_encoder_hotplug(encoder, connector, irq_received); + return intel_encoder_hotplug(encoder, connector); } static bool diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index deda351719db..0000ec7055f7 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -2503,6 +2503,7 @@ static const u32 skl_plane_formats[] = { DRM_FORMAT_YVYU, DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, + DRM_FORMAT_XYUV8888, }; static const u32 skl_planar_formats[] = { @@ -2521,6 +2522,7 @@ static const u32 skl_planar_formats[] = { DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_NV12, + DRM_FORMAT_XYUV8888, }; static const u32 glk_planar_formats[] = { @@ -2539,6 +2541,7 @@ static const u32 glk_planar_formats[] = { DRM_FORMAT_UYVY, DRM_FORMAT_VYUY, DRM_FORMAT_NV12, + DRM_FORMAT_XYUV8888, DRM_FORMAT_P010, DRM_FORMAT_P012, DRM_FORMAT_P016, @@ -2562,6 +2565,7 @@ static const u32 icl_sdr_y_plane_formats[] = { DRM_FORMAT_Y210, DRM_FORMAT_Y212, DRM_FORMAT_Y216, + DRM_FORMAT_XYUV8888, DRM_FORMAT_XVYU2101010, DRM_FORMAT_XVYU12_16161616, DRM_FORMAT_XVYU16161616, @@ -2589,6 +2593,7 @@ static const u32 icl_sdr_uv_plane_formats[] = { DRM_FORMAT_Y210, DRM_FORMAT_Y212, DRM_FORMAT_Y216, + DRM_FORMAT_XYUV8888, DRM_FORMAT_XVYU2101010, DRM_FORMAT_XVYU12_16161616, DRM_FORMAT_XVYU16161616, @@ -2620,6 +2625,7 @@ static const u32 icl_hdr_plane_formats[] = { DRM_FORMAT_Y210, DRM_FORMAT_Y212, DRM_FORMAT_Y216, + DRM_FORMAT_XYUV8888, DRM_FORMAT_XVYU2101010, DRM_FORMAT_XVYU12_16161616, DRM_FORMAT_XVYU16161616, @@ -2790,6 +2796,7 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_UYVY: case DRM_FORMAT_VYUY: case DRM_FORMAT_NV12: + case DRM_FORMAT_XYUV8888: case DRM_FORMAT_P010: case DRM_FORMAT_P012: case DRM_FORMAT_P016: @@ -2817,19 +2824,25 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, } } -static bool gen12_plane_supports_mc_ccs(enum plane_id plane_id) +static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv, + enum plane_id plane_id) { + /* Wa_14010477008:tgl[a0..c0] */ + if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0)) + return false; + return plane_id < PLANE_SPRITE4; } static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { + struct drm_i915_private *dev_priv = to_i915(_plane->dev); struct intel_plane *plane = to_intel_plane(_plane); switch (modifier) { case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: - if (!gen12_plane_supports_mc_ccs(plane->id)) + if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id)) return false; /* fall through */ case DRM_FORMAT_MOD_LINEAR: @@ -2854,6 +2867,7 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, case DRM_FORMAT_UYVY: case DRM_FORMAT_VYUY: case DRM_FORMAT_NV12: + case DRM_FORMAT_XYUV8888: case DRM_FORMAT_P010: case DRM_FORMAT_P012: case DRM_FORMAT_P016: @@ -2998,9 +3012,10 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv, } } -static const u64 *gen12_get_plane_modifiers(enum plane_id plane_id) +static const u64 *gen12_get_plane_modifiers(struct drm_i915_private *dev_priv, + enum plane_id plane_id) { - if (gen12_plane_supports_mc_ccs(plane_id)) + if (gen12_plane_supports_mc_ccs(dev_priv, plane_id)) return gen12_plane_format_modifiers_mc_ccs; else return gen12_plane_format_modifiers_rc_ccs; @@ -3070,7 +3085,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv, plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id); if (INTEL_GEN(dev_priv) >= 12) { - modifiers = gen12_get_plane_modifiers(plane_id); + modifiers = gen12_get_plane_modifiers(dev_priv, plane_id); plane_funcs = &gen12_plane_funcs; } else { if (plane->has_ccs) diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 9b850c11aa78..275618bedf32 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -152,6 +152,7 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port, static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port, u32 live_status_mask) { + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); u32 valid_hpd_mask; if (dig_port->tc_legacy_port) @@ -164,8 +165,9 @@ static void tc_port_fixup_legacy_flag(struct intel_digital_port *dig_port, return; /* If live status mismatches the VBT flag, trust the live status. */ - DRM_ERROR("Port %s: live status %08x mismatches the legacy port flag, fix flag\n", - dig_port->tc_port_name, live_status_mask); + drm_err(&i915->drm, + "Port %s: live status %08x mismatches the legacy port flag, fix flag\n", + dig_port->tc_port_name, live_status_mask); dig_port->tc_legacy_port = !dig_port->tc_legacy_port; } @@ -233,8 +235,7 @@ static bool icl_tc_phy_set_safe_mode(struct intel_digital_port *dig_port, if (val == 0xffffffff) { drm_dbg_kms(&i915->drm, "Port %s: PHY in TCCOLD, can't set safe-mode to %s\n", - dig_port->tc_port_name, - enableddisabled(enable)); + dig_port->tc_port_name, enableddisabled(enable)); return false; } @@ -286,11 +287,12 @@ static bool icl_tc_phy_is_in_safe_mode(struct intel_digital_port *dig_port) static void icl_tc_phy_connect(struct intel_digital_port *dig_port, int required_lanes) { + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); int max_lanes; if (!icl_tc_phy_status_complete(dig_port)) { - DRM_DEBUG_KMS("Port %s: PHY not ready\n", - dig_port->tc_port_name); + drm_dbg_kms(&i915->drm, "Port %s: PHY not ready\n", + dig_port->tc_port_name); goto out_set_tbt_alt_mode; } @@ -311,15 +313,16 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port, * became disconnected. Not necessary for legacy mode. */ if (!(tc_port_live_status_mask(dig_port) & BIT(TC_PORT_DP_ALT))) { - DRM_DEBUG_KMS("Port %s: PHY sudden disconnect\n", - dig_port->tc_port_name); + drm_dbg_kms(&i915->drm, "Port %s: PHY sudden disconnect\n", + dig_port->tc_port_name); goto out_set_safe_mode; } if (max_lanes < required_lanes) { - DRM_DEBUG_KMS("Port %s: PHY max lanes %d < required lanes %d\n", - dig_port->tc_port_name, - max_lanes, required_lanes); + drm_dbg_kms(&i915->drm, + "Port %s: PHY max lanes %d < required lanes %d\n", + dig_port->tc_port_name, + max_lanes, required_lanes); goto out_set_safe_mode; } @@ -357,15 +360,17 @@ static void icl_tc_phy_disconnect(struct intel_digital_port *dig_port) static bool icl_tc_phy_is_connected(struct intel_digital_port *dig_port) { + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + if (!icl_tc_phy_status_complete(dig_port)) { - DRM_DEBUG_KMS("Port %s: PHY status not complete\n", - dig_port->tc_port_name); + drm_dbg_kms(&i915->drm, "Port %s: PHY status not complete\n", + dig_port->tc_port_name); return dig_port->tc_mode == TC_PORT_TBT_ALT; } if (icl_tc_phy_is_in_safe_mode(dig_port)) { - DRM_DEBUG_KMS("Port %s: PHY still in safe mode\n", - dig_port->tc_port_name); + drm_dbg_kms(&i915->drm, "Port %s: PHY still in safe mode\n", + dig_port->tc_port_name); return false; } @@ -438,6 +443,7 @@ intel_tc_port_link_init_refcount(struct intel_digital_port *dig_port, void intel_tc_port_sanitize(struct intel_digital_port *dig_port) { + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_encoder *encoder = &dig_port->base; int active_links = 0; @@ -451,8 +457,9 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) if (active_links) { if (!icl_tc_phy_is_connected(dig_port)) - DRM_DEBUG_KMS("Port %s: PHY disconnected with %d active link(s)\n", - dig_port->tc_port_name, active_links); + drm_dbg_kms(&i915->drm, + "Port %s: PHY disconnected with %d active link(s)\n", + dig_port->tc_port_name, active_links); intel_tc_port_link_init_refcount(dig_port, active_links); goto out; @@ -462,9 +469,9 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) icl_tc_phy_connect(dig_port, 1); out: - DRM_DEBUG_KMS("Port %s: sanitize mode (%s)\n", - dig_port->tc_port_name, - tc_port_mode_name(dig_port->tc_mode)); + drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n", + dig_port->tc_port_name, + tc_port_mode_name(dig_port->tc_mode)); mutex_unlock(&dig_port->tc_lock); } diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index d2e3a3a323e9..fbe12aad7d58 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -914,7 +914,8 @@ intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe) } static void -intel_enable_tv(struct intel_encoder *encoder, +intel_enable_tv(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -930,7 +931,8 @@ intel_enable_tv(struct intel_encoder *encoder, } static void -intel_disable_tv(struct intel_encoder *encoder, +intel_disable_tv(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { @@ -1414,7 +1416,8 @@ static void set_color_conversion(struct drm_i915_private *dev_priv, (color_conversion->bv << 16) | color_conversion->av); } -static void intel_tv_pre_enable(struct intel_encoder *encoder, +static void intel_tv_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -1698,13 +1701,13 @@ intel_tv_detect(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx, bool force) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector)); enum drm_connector_status status; int type; - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n", - connector->base.id, connector->name, - force); + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] force=%d\n", + connector->base.id, connector->name, force); if (force) { struct intel_load_detect_pipe tmp; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index f4c362dc6e15..4e18d4627065 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -759,7 +759,8 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder); * DSI port enable has to be done before pipe and plane enable, so we do it in * the pre_enable hook instead of the enable hook. */ -static void intel_dsi_pre_enable(struct intel_encoder *encoder, +static void intel_dsi_pre_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { @@ -858,7 +859,8 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder, intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON); } -static void bxt_dsi_enable(struct intel_encoder *encoder, +static void bxt_dsi_enable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) { @@ -871,14 +873,16 @@ static void bxt_dsi_enable(struct intel_encoder *encoder, * DSI port disable has to be done after pipe and plane disable, so we do it in * the post_disable hook. */ -static void intel_dsi_disable(struct intel_encoder *encoder, +static void intel_dsi_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { + struct drm_i915_private *i915 = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); enum port port; - DRM_DEBUG_KMS("\n"); + drm_dbg_kms(&i915->drm, "\n"); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF); intel_panel_disable_backlight(old_conn_state); @@ -906,7 +910,8 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder) vlv_dsi_clear_device_ready(encoder); } -static void intel_dsi_post_disable(struct intel_encoder *encoder, +static void intel_dsi_post_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 026999b34abd..11d9135cf21a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -570,23 +570,19 @@ static void engines_idle_release(struct i915_gem_context *ctx, engines->ctx = i915_gem_context_get(ctx); for_each_gem_engine(ce, engines, it) { - struct dma_fence *fence; - int err = 0; + int err; /* serialises with execbuf */ - RCU_INIT_POINTER(ce->gem_context, NULL); + set_bit(CONTEXT_CLOSED_BIT, &ce->flags); if (!intel_context_pin_if_active(ce)) continue; - fence = i915_active_fence_get(&ce->timeline->last_request); - if (fence) { - err = i915_sw_fence_await_dma_fence(&engines->fence, - fence, 0, - GFP_KERNEL); - dma_fence_put(fence); - } + /* Wait until context is finally scheduled out and retired */ + err = i915_sw_fence_await_active(&engines->fence, + &ce->active, + I915_ACTIVE_AWAIT_BARRIER); intel_context_unpin(ce); - if (err < 0) + if (err) goto kill; } @@ -757,21 +753,46 @@ err_free: return ERR_PTR(err); } +static inline struct i915_gem_engines * +__context_engines_await(const struct i915_gem_context *ctx) +{ + struct i915_gem_engines *engines; + + rcu_read_lock(); + do { + engines = rcu_dereference(ctx->engines); + GEM_BUG_ON(!engines); + + if (unlikely(!i915_sw_fence_await(&engines->fence))) + continue; + + if (likely(engines == rcu_access_pointer(ctx->engines))) + break; + + i915_sw_fence_complete(&engines->fence); + } while (1); + rcu_read_unlock(); + + return engines; +} + static int context_apply_all(struct i915_gem_context *ctx, int (*fn)(struct intel_context *ce, void *data), void *data) { struct i915_gem_engines_iter it; + struct i915_gem_engines *e; struct intel_context *ce; int err = 0; - for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) { + e = __context_engines_await(ctx); + for_each_gem_engine(ce, e, it) { err = fn(ce, data); if (err) break; } - i915_gem_context_unlock_engines(ctx); + i915_sw_fence_complete(&e->fence); return err; } @@ -786,11 +807,13 @@ static int __apply_ppgtt(struct intel_context *ce, void *vm) static struct i915_address_space * __set_ppgtt(struct i915_gem_context *ctx, struct i915_address_space *vm) { - struct i915_address_space *old = i915_gem_context_vm(ctx); + struct i915_address_space *old; + old = rcu_replace_pointer(ctx->vm, + i915_vm_open(vm), + lockdep_is_held(&ctx->mutex)); GEM_BUG_ON(old && i915_vm_is_4lvl(vm) != i915_vm_is_4lvl(old)); - rcu_assign_pointer(ctx->vm, i915_vm_open(vm)); context_apply_all(ctx, __apply_ppgtt, vm); return old; @@ -1069,30 +1092,6 @@ static void cb_retire(struct i915_active *base) kfree(cb); } -static inline struct i915_gem_engines * -__context_engines_await(const struct i915_gem_context *ctx) -{ - struct i915_gem_engines *engines; - - rcu_read_lock(); - do { - engines = rcu_dereference(ctx->engines); - if (unlikely(!engines)) - break; - - if (unlikely(!i915_sw_fence_await(&engines->fence))) - continue; - - if (likely(engines == rcu_access_pointer(ctx->engines))) - break; - - i915_sw_fence_complete(&engines->fence); - } while (1); - rcu_read_unlock(); - - return engines; -} - I915_SELFTEST_DECLARE(static intel_engine_mask_t context_barrier_inject_fault); static int context_barrier_task(struct i915_gem_context *ctx, intel_engine_mask_t engines, @@ -1401,10 +1400,10 @@ static int get_ringsize(struct i915_gem_context *ctx, return 0; } -static int -user_to_context_sseu(struct drm_i915_private *i915, - const struct drm_i915_gem_context_param_sseu *user, - struct intel_sseu *context) +int +i915_gem_user_to_context_sseu(struct drm_i915_private *i915, + const struct drm_i915_gem_context_param_sseu *user, + struct intel_sseu *context) { const struct sseu_dev_info *device = &RUNTIME_INFO(i915)->sseu; @@ -1539,7 +1538,7 @@ static int set_sseu(struct i915_gem_context *ctx, goto out_ce; } - ret = user_to_context_sseu(i915, &user_sseu, &sseu); + ret = i915_gem_user_to_context_sseu(i915, &user_sseu, &sseu); if (ret) goto out_ce; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index 57b7ae2893e1..3702b2fb27ab 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -192,12 +192,16 @@ i915_gem_context_unlock_engines(struct i915_gem_context *ctx) static inline struct intel_context * i915_gem_context_get_engine(struct i915_gem_context *ctx, unsigned int idx) { - struct intel_context *ce = ERR_PTR(-EINVAL); + struct intel_context *ce; rcu_read_lock(); { struct i915_gem_engines *e = rcu_dereference(ctx->engines); - if (likely(idx < e->num_engines && e->engines[idx])) + if (unlikely(!e)) /* context was closed! */ + ce = ERR_PTR(-ENOENT); + else if (likely(idx < e->num_engines && e->engines[idx])) ce = intel_context_get(e->engines[idx]); + else + ce = ERR_PTR(-EINVAL); } rcu_read_unlock(); return ce; @@ -221,4 +225,8 @@ i915_gem_engines_iter_next(struct i915_gem_engines_iter *it); struct i915_lut_handle *i915_lut_handle_alloc(void); void i915_lut_handle_free(struct i915_lut_handle *lut); +int i915_gem_user_to_context_sseu(struct drm_i915_private *i915, + const struct drm_i915_gem_context_param_sseu *user, + struct intel_sseu *context); + #endif /* !__I915_GEM_CONTEXT_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 0cc40e77bbd2..af43e82f45c7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -369,7 +369,7 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) struct i915_vma *vma; GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); - if (!atomic_read(&obj->bind_count)) + if (list_empty(&obj->vma.list)) return; mutex_lock(&i915->ggtt.vm.mutex); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index d3f4f28e9468..517898aa634c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -40,6 +40,11 @@ struct eb_vma { u32 handle; }; +struct eb_vma_array { + struct kref kref; + struct eb_vma vma[]; +}; + enum { FORCE_CPU_RELOC = 1, FORCE_GTT_RELOC, @@ -52,7 +57,6 @@ enum { #define __EXEC_OBJECT_NEEDS_MAP BIT(29) #define __EXEC_OBJECT_NEEDS_BIAS BIT(28) #define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 28) /* all of the above */ -#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE) #define __EXEC_HAS_RELOC BIT(31) #define __EXEC_INTERNAL_FLAGS (~0u << 31) @@ -283,6 +287,7 @@ struct i915_execbuffer { */ int lut_size; struct hlist_head *buckets; /** ht for relocation handles */ + struct eb_vma_array *array; }; static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) @@ -292,8 +297,62 @@ static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) eb->args->batch_len); } +static struct eb_vma_array *eb_vma_array_create(unsigned int count) +{ + struct eb_vma_array *arr; + + arr = kvmalloc(struct_size(arr, vma, count), GFP_KERNEL | __GFP_NOWARN); + if (!arr) + return NULL; + + kref_init(&arr->kref); + arr->vma[0].vma = NULL; + + return arr; +} + +static inline void eb_unreserve_vma(struct eb_vma *ev) +{ + struct i915_vma *vma = ev->vma; + + if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE)) + __i915_vma_unpin_fence(vma); + + if (ev->flags & __EXEC_OBJECT_HAS_PIN) + __i915_vma_unpin(vma); + + ev->flags &= ~(__EXEC_OBJECT_HAS_PIN | + __EXEC_OBJECT_HAS_FENCE); +} + +static void eb_vma_array_destroy(struct kref *kref) +{ + struct eb_vma_array *arr = container_of(kref, typeof(*arr), kref); + struct eb_vma *ev = arr->vma; + + while (ev->vma) { + eb_unreserve_vma(ev); + i915_vma_put(ev->vma); + ev++; + } + + kvfree(arr); +} + +static void eb_vma_array_put(struct eb_vma_array *arr) +{ + kref_put(&arr->kref, eb_vma_array_destroy); +} + static int eb_create(struct i915_execbuffer *eb) { + /* Allocate an extra slot for use by the command parser + sentinel */ + eb->array = eb_vma_array_create(eb->buffer_count + 2); + if (!eb->array) + return -ENOMEM; + + eb->vma = eb->array->vma; + if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) { unsigned int size = 1 + ilog2(eb->buffer_count); @@ -327,8 +386,10 @@ static int eb_create(struct i915_execbuffer *eb) break; } while (--size); - if (unlikely(!size)) + if (unlikely(!size)) { + eb_vma_array_put(eb->array); return -ENOMEM; + } eb->lut_size = size; } else { @@ -368,6 +429,32 @@ eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry, return false; } +static u64 eb_pin_flags(const struct drm_i915_gem_exec_object2 *entry, + unsigned int exec_flags) +{ + u64 pin_flags = 0; + + if (exec_flags & EXEC_OBJECT_NEEDS_GTT) + pin_flags |= PIN_GLOBAL; + + /* + * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, + * limit address to the first 4GBs for unflagged objects. + */ + if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS)) + pin_flags |= PIN_ZONE_4G; + + if (exec_flags & __EXEC_OBJECT_NEEDS_MAP) + pin_flags |= PIN_MAPPABLE; + + if (exec_flags & EXEC_OBJECT_PINNED) + pin_flags |= entry->offset | PIN_OFFSET_FIXED; + else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS) + pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; + + return pin_flags; +} + static inline bool eb_pin_vma(struct i915_execbuffer *eb, const struct drm_i915_gem_exec_object2 *entry, @@ -385,8 +472,19 @@ eb_pin_vma(struct i915_execbuffer *eb, if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_GTT)) pin_flags |= PIN_GLOBAL; - if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags))) - return false; + /* Attempt to reuse the current location if available */ + if (unlikely(i915_vma_pin(vma, 0, 0, pin_flags))) { + if (entry->flags & EXEC_OBJECT_PINNED) + return false; + + /* Failing that pick any _free_ space if suitable */ + if (unlikely(i915_vma_pin(vma, + entry->pad_to_size, + entry->alignment, + eb_pin_flags(entry, ev->flags) | + PIN_USER | PIN_NOEVICT))) + return false; + } if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) { if (unlikely(i915_vma_pin_fence(vma))) { @@ -402,26 +500,6 @@ eb_pin_vma(struct i915_execbuffer *eb, return !eb_vma_misplaced(entry, vma, ev->flags); } -static inline void __eb_unreserve_vma(struct i915_vma *vma, unsigned int flags) -{ - GEM_BUG_ON(!(flags & __EXEC_OBJECT_HAS_PIN)); - - if (unlikely(flags & __EXEC_OBJECT_HAS_FENCE)) - __i915_vma_unpin_fence(vma); - - __i915_vma_unpin(vma); -} - -static inline void -eb_unreserve_vma(struct eb_vma *ev) -{ - if (!(ev->flags & __EXEC_OBJECT_HAS_PIN)) - return; - - __eb_unreserve_vma(ev->vma, ev->flags); - ev->flags &= ~__EXEC_OBJECT_RESERVED; -} - static int eb_validate_vma(struct i915_execbuffer *eb, struct drm_i915_gem_exec_object2 *entry, @@ -481,7 +559,7 @@ eb_add_vma(struct i915_execbuffer *eb, GEM_BUG_ON(i915_vma_is_closed(vma)); - ev->vma = i915_vma_get(vma); + ev->vma = vma; ev->exec = entry; ev->flags = entry->flags; @@ -547,28 +625,9 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb, u64 pin_flags) { struct drm_i915_gem_exec_object2 *entry = ev->exec; - unsigned int exec_flags = ev->flags; struct i915_vma *vma = ev->vma; int err; - if (exec_flags & EXEC_OBJECT_NEEDS_GTT) - pin_flags |= PIN_GLOBAL; - - /* - * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, - * limit address to the first 4GBs for unflagged objects. - */ - if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS)) - pin_flags |= PIN_ZONE_4G; - - if (exec_flags & __EXEC_OBJECT_NEEDS_MAP) - pin_flags |= PIN_MAPPABLE; - - if (exec_flags & EXEC_OBJECT_PINNED) - pin_flags |= entry->offset | PIN_OFFSET_FIXED; - else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS) - pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; - if (drm_mm_node_allocated(&vma->node) && eb_vma_misplaced(entry, vma, ev->flags)) { err = i915_vma_unbind(vma); @@ -578,7 +637,7 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb, err = i915_vma_pin(vma, entry->pad_to_size, entry->alignment, - pin_flags); + eb_pin_flags(entry, ev->flags) | pin_flags); if (err) return err; @@ -587,7 +646,7 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb, eb->args->flags |= __EXEC_HAS_RELOC; } - if (unlikely(exec_flags & EXEC_OBJECT_NEEDS_FENCE)) { + if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) { err = i915_vma_pin_fence(vma); if (unlikely(err)) { i915_vma_unpin(vma); @@ -595,10 +654,10 @@ static int eb_reserve_vma(const struct i915_execbuffer *eb, } if (vma->fence) - exec_flags |= __EXEC_OBJECT_HAS_FENCE; + ev->flags |= __EXEC_OBJECT_HAS_FENCE; } - ev->flags = exec_flags | __EXEC_OBJECT_HAS_PIN; + ev->flags |= __EXEC_OBJECT_HAS_PIN; GEM_BUG_ON(eb_vma_misplaced(entry, vma, ev->flags)); return 0; @@ -728,77 +787,117 @@ static int eb_select_context(struct i915_execbuffer *eb) return 0; } -static int eb_lookup_vmas(struct i915_execbuffer *eb) +static int __eb_add_lut(struct i915_execbuffer *eb, + u32 handle, struct i915_vma *vma) { - struct radix_tree_root *handles_vma = &eb->gem_context->handles_vma; - struct drm_i915_gem_object *obj; - unsigned int i, batch; + struct i915_gem_context *ctx = eb->gem_context; + struct i915_lut_handle *lut; int err; - if (unlikely(i915_gem_context_is_closed(eb->gem_context))) - return -ENOENT; + lut = i915_lut_handle_alloc(); + if (unlikely(!lut)) + return -ENOMEM; - INIT_LIST_HEAD(&eb->relocs); - INIT_LIST_HEAD(&eb->unbound); + i915_vma_get(vma); + if (!atomic_fetch_inc(&vma->open_count)) + i915_vma_reopen(vma); + lut->handle = handle; + lut->ctx = ctx; + + /* Check that the context hasn't been closed in the meantime */ + err = -EINTR; + if (!mutex_lock_interruptible(&ctx->mutex)) { + err = -ENOENT; + if (likely(!i915_gem_context_is_closed(ctx))) + err = radix_tree_insert(&ctx->handles_vma, handle, vma); + if (err == 0) { /* And nor has this handle */ + struct drm_i915_gem_object *obj = vma->obj; + + i915_gem_object_lock(obj); + if (idr_find(&eb->file->object_idr, handle) == obj) { + list_add(&lut->obj_link, &obj->lut_list); + } else { + radix_tree_delete(&ctx->handles_vma, handle); + err = -ENOENT; + } + i915_gem_object_unlock(obj); + } + mutex_unlock(&ctx->mutex); + } + if (unlikely(err)) + goto err; - batch = eb_batch_index(eb); + return 0; - for (i = 0; i < eb->buffer_count; i++) { - u32 handle = eb->exec[i].handle; - struct i915_lut_handle *lut; +err: + atomic_dec(&vma->open_count); + i915_vma_put(vma); + i915_lut_handle_free(lut); + return err; +} + +static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) +{ + do { + struct drm_i915_gem_object *obj; struct i915_vma *vma; + int err; - vma = radix_tree_lookup(handles_vma, handle); + rcu_read_lock(); + vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle); + if (likely(vma)) + vma = i915_vma_tryget(vma); + rcu_read_unlock(); if (likely(vma)) - goto add_vma; + return vma; obj = i915_gem_object_lookup(eb->file, handle); - if (unlikely(!obj)) { - err = -ENOENT; - goto err_vma; - } + if (unlikely(!obj)) + return ERR_PTR(-ENOENT); vma = i915_vma_instance(obj, eb->context->vm, NULL); if (IS_ERR(vma)) { - err = PTR_ERR(vma); - goto err_obj; + i915_gem_object_put(obj); + return vma; } - lut = i915_lut_handle_alloc(); - if (unlikely(!lut)) { - err = -ENOMEM; - goto err_obj; - } + err = __eb_add_lut(eb, handle, vma); + if (likely(!err)) + return vma; - err = radix_tree_insert(handles_vma, handle, vma); - if (unlikely(err)) { - i915_lut_handle_free(lut); - goto err_obj; - } + i915_gem_object_put(obj); + if (err != -EEXIST) + return ERR_PTR(err); + } while (1); +} + +static int eb_lookup_vmas(struct i915_execbuffer *eb) +{ + unsigned int batch = eb_batch_index(eb); + unsigned int i; + int err = 0; - /* transfer ref to lut */ - if (!atomic_fetch_inc(&vma->open_count)) - i915_vma_reopen(vma); - lut->handle = handle; - lut->ctx = eb->gem_context; + INIT_LIST_HEAD(&eb->relocs); + INIT_LIST_HEAD(&eb->unbound); - i915_gem_object_lock(obj); - list_add(&lut->obj_link, &obj->lut_list); - i915_gem_object_unlock(obj); + for (i = 0; i < eb->buffer_count; i++) { + struct i915_vma *vma; + + vma = eb_lookup_vma(eb, eb->exec[i].handle); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + break; + } -add_vma: err = eb_validate_vma(eb, &eb->exec[i], vma); - if (unlikely(err)) - goto err_vma; + if (unlikely(err)) { + i915_vma_put(vma); + break; + } eb_add_vma(eb, i, batch, vma); } - return 0; - -err_obj: - i915_gem_object_put(obj); -err_vma: eb->vma[i].vma = NULL; return err; } @@ -823,31 +922,13 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle) } } -static void eb_release_vmas(const struct i915_execbuffer *eb) -{ - const unsigned int count = eb->buffer_count; - unsigned int i; - - for (i = 0; i < count; i++) { - struct eb_vma *ev = &eb->vma[i]; - struct i915_vma *vma = ev->vma; - - if (!vma) - break; - - eb->vma[i].vma = NULL; - - if (ev->flags & __EXEC_OBJECT_HAS_PIN) - __eb_unreserve_vma(vma, ev->flags); - - i915_vma_put(vma); - } -} - static void eb_destroy(const struct i915_execbuffer *eb) { GEM_BUG_ON(eb->reloc_cache.rq); + if (eb->array) + eb_vma_array_put(eb->array); + if (eb->lut_size > 0) kfree(eb->buckets); } @@ -896,11 +977,13 @@ 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); @@ -1218,6 +1301,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, return cmd; } +static inline bool use_reloc_gpu(struct i915_vma *vma) +{ + if (DBG_FORCE_RELOC == FORCE_GPU_RELOC) + return true; + + if (DBG_FORCE_RELOC) + return false; + + return !dma_resv_test_signaled_rcu(vma->resv, true); +} + static u64 relocate_entry(struct i915_vma *vma, const struct drm_i915_gem_relocation_entry *reloc, @@ -1229,9 +1323,7 @@ relocate_entry(struct i915_vma *vma, bool wide = eb->reloc_cache.use_64bit_reloc; void *vaddr; - if (!eb->reloc_cache.vaddr && - (DBG_FORCE_RELOC == FORCE_GPU_RELOC || - !dma_resv_test_signaled_rcu(vma->resv, true))) { + if (!eb->reloc_cache.vaddr && use_reloc_gpu(vma)) { const unsigned int gen = eb->reloc_cache.gen; unsigned int len; u32 *batch; @@ -1409,12 +1501,11 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) { #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry)) struct drm_i915_gem_relocation_entry stack[N_RELOC(512)]; - struct drm_i915_gem_relocation_entry __user *urelocs; const struct drm_i915_gem_exec_object2 *entry = ev->exec; - unsigned int remain; + struct drm_i915_gem_relocation_entry __user *urelocs = + u64_to_user_ptr(entry->relocs_ptr); + unsigned long remain = entry->relocation_count; - urelocs = u64_to_user_ptr(entry->relocs_ptr); - remain = entry->relocation_count; if (unlikely(remain > N_RELOC(ULONG_MAX))) return -EINVAL; @@ -1423,13 +1514,13 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * to read. However, if the array is not writable the user loses * the updated relocation values. */ - if (unlikely(!access_ok(urelocs, remain*sizeof(*urelocs)))) + if (unlikely(!access_ok(urelocs, remain * sizeof(*urelocs)))) return -EFAULT; do { struct drm_i915_gem_relocation_entry *r = stack; unsigned int count = - min_t(unsigned int, remain, ARRAY_SIZE(stack)); + min_t(unsigned long, remain, ARRAY_SIZE(stack)); unsigned int copied; /* @@ -1477,10 +1568,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * can read from this userspace address. */ offset = gen8_canonical_addr(offset & ~UPDATE); - if (unlikely(__put_user(offset, &urelocs[r-stack].presumed_offset))) { - remain = -EFAULT; - goto out; - } + __put_user(offset, + &urelocs[r - stack].presumed_offset); } } while (r++, --count); urelocs += ARRAY_SIZE(stack); @@ -1494,9 +1583,7 @@ static int eb_relocate(struct i915_execbuffer *eb) { int err; - mutex_lock(&eb->gem_context->mutex); err = eb_lookup_vmas(eb); - mutex_unlock(&eb->gem_context->mutex); if (err) return err; @@ -1597,19 +1684,15 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) err = i915_vma_move_to_active(vma, eb->request, flags); i915_vma_unlock(vma); - - __eb_unreserve_vma(vma, flags); - i915_vma_put(vma); - - ev->vma = NULL; + eb_unreserve_vma(ev); } ww_acquire_fini(&acquire); + eb_vma_array_put(fetch_and_zero(&eb->array)); + if (unlikely(err)) goto err_skip; - eb->exec = NULL; - /* Unconditionally flush any chipset caches (for streaming writes). */ intel_gt_chipset_flush(eb->engine->gt); return 0; @@ -1784,7 +1867,7 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb, dma_resv_add_excl_fence(shadow->resv, &pw->base.dma); dma_resv_unlock(shadow->resv); - dma_fence_work_commit(&pw->base); + dma_fence_work_commit_imm(&pw->base); return 0; err_batch_unlock: @@ -1861,6 +1944,7 @@ static int eb_parse(struct i915_execbuffer *eb) eb->vma[eb->buffer_count].vma = i915_vma_get(shadow); eb->vma[eb->buffer_count].flags = __EXEC_OBJECT_HAS_PIN; eb->batch = &eb->vma[eb->buffer_count++]; + eb->vma[eb->buffer_count].vma = NULL; eb->trampoline = trampoline; eb->batch_start_offset = 0; @@ -2316,7 +2400,7 @@ static void eb_request_add(struct i915_execbuffer *eb) prev = __i915_request_commit(rq); /* Check that the context wasn't destroyed before submission */ - if (likely(rcu_access_pointer(eb->context->gem_context))) { + if (likely(!intel_context_is_closed(eb->context))) { attr = eb->gem_context->sched; /* @@ -2348,9 +2432,7 @@ static void eb_request_add(struct i915_execbuffer *eb) __i915_request_skip(rq); } - local_bh_disable(); __i915_request_queue(rq, &attr); - local_bh_enable(); /* Kick the execlists tasklet if just scheduled */ /* Try to clean up the client's timeline after submitting the request */ if (prev) @@ -2386,8 +2468,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, args->flags |= __EXEC_HAS_RELOC; eb.exec = exec; - eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1); - eb.vma[0].vma = NULL; eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS; reloc_cache_init(&eb.reloc_cache, eb.i915); @@ -2594,8 +2674,6 @@ err_parse: if (batch->private) intel_engine_pool_put(batch->private); err_vma: - if (eb.exec) - eb_release_vmas(&eb); if (eb.trampoline) i915_vma_unpin(eb.trampoline); eb_unpin_engine(&eb); @@ -2615,7 +2693,7 @@ err_in_fence: static size_t eb_element_size(void) { - return sizeof(struct drm_i915_gem_exec_object2) + sizeof(struct eb_vma); + return sizeof(struct drm_i915_gem_exec_object2); } static bool check_buffer_count(size_t count) @@ -2671,7 +2749,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data, /* Copy in the exec list from userland */ exec_list = kvmalloc_array(count, sizeof(*exec_list), __GFP_NOWARN | GFP_KERNEL); - exec2_list = kvmalloc_array(count + 1, eb_element_size(), + exec2_list = kvmalloc_array(count, eb_element_size(), __GFP_NOWARN | GFP_KERNEL); if (exec_list == NULL || exec2_list == NULL) { drm_dbg(&i915->drm, @@ -2749,8 +2827,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, if (err) return err; - /* Allocate an extra slot for use by the command parser */ - exec2_list = kvmalloc_array(count + 1, eb_element_size(), + exec2_list = kvmalloc_array(count, eb_element_size(), __GFP_NOWARN | GFP_KERNEL); if (exec2_list == NULL) { drm_dbg(&i915->drm, "Failed to allocate exec list for %zd buffers\n", diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 5da9f9e534b9..3f01cdd1a39b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -206,7 +206,6 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, } obj->mmo.offsets = RB_ROOT; - GEM_BUG_ON(atomic_read(&obj->bind_count)); GEM_BUG_ON(obj->userfault_count); GEM_BUG_ON(!list_empty(&obj->lut_list)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index a0b10bcd8d8a..54ee658bb168 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -179,9 +179,6 @@ struct drm_i915_gem_object { #define TILING_MASK (FENCE_MINIMUM_STRIDE - 1) #define STRIDE_MASK (~TILING_MASK) - /** Count of VMA actually bound by this object */ - atomic_t bind_count; - struct { /* * Protects the pages and their use. Do not use directly, but diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 24f4cadea114..5d855fcd5c0f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -199,8 +199,6 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj) if (i915_gem_object_has_pinned_pages(obj)) return -EBUSY; - GEM_BUG_ON(atomic_read(&obj->bind_count)); - /* May be called by shrinker from within get_pages() (on another bo) */ mutex_lock(&obj->mm.lock); if (unlikely(atomic_read(&obj->mm.pages_pin_count))) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 03e5eb4c99d1..5b65ce738b16 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -27,18 +27,6 @@ static bool can_release_pages(struct drm_i915_gem_object *obj) return false; /* - * Only report true if by unbinding the object and putting its pages - * we can actually make forward progress towards freeing physical - * pages. - * - * If the pages are pinned for any other reason than being bound - * to the GPU, simply unbinding from the GPU is not going to succeed - * in releasing our pin count on the pages themselves. - */ - if (atomic_read(&obj->mm.pages_pin_count) > atomic_read(&obj->bind_count)) - return false; - - /* * We can only return physical pages to the system if we can either * discard the contents (because the user has marked them as being * purgeable) or if we can move their contents out to swap. @@ -54,6 +42,8 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj, flags = 0; if (shrink & I915_SHRINK_ACTIVE) flags = I915_GEM_OBJECT_UNBIND_ACTIVE; + if (!(shrink & I915_SHRINK_BOUND)) + flags = I915_GEM_OBJECT_UNBIND_TEST; if (i915_gem_object_unbind(obj, flags) == 0) __i915_gem_object_put_pages(obj); @@ -194,10 +184,6 @@ i915_gem_shrink(struct drm_i915_private *i915, i915_gem_object_is_framebuffer(obj)) continue; - if (!(shrink & I915_SHRINK_BOUND) && - atomic_read(&obj->bind_count)) - continue; - if (!can_release_pages(obj)) continue; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 5557dfa83a7b..dc250278bd2c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -381,14 +381,14 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) mutex_init(&i915->mm.stolen_lock); if (intel_vgpu_active(i915)) { - dev_notice(i915->drm.dev, + drm_notice(&i915->drm, "%s, disabling use of stolen memory\n", "iGVT-g active"); return 0; } if (intel_vtd_active() && INTEL_GEN(i915) < 8) { - dev_notice(i915->drm.dev, + drm_notice(&i915->drm, "%s, disabling use of stolen memory\n", "DMAR active"); return 0; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c index fa16f2c3f3ac..2b46c6530da9 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c @@ -88,8 +88,7 @@ static void huge_put_pages(struct drm_i915_gem_object *obj, } static const struct drm_i915_gem_object_ops huge_ops = { - .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | - I915_GEM_OBJECT_IS_SHRINKABLE, + .flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE, .get_pages = huge_get_pages, .put_pages = huge_put_pages, }; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index 54b86cf7f5d2..f4f933240b39 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -1925,7 +1925,7 @@ static int mock_context_barrier(void *arg) goto out; } - rq = igt_request_alloc(ctx, i915->engine[RCS0]); + rq = igt_request_alloc(ctx, i915->gt.engine[RCS0]); if (IS_ERR(rq)) { pr_err("Request allocation failed!\n"); goto out; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 43912e9b683d..ef7abcb3f4ee 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -1156,9 +1156,6 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915, if (err) goto out_unmap; - GEM_BUG_ON(mmo->mmap_type == I915_MMAP_TYPE_GTT && - !atomic_read(&obj->bind_count)); - err = check_present(addr, obj->base.size); if (err) { pr_err("%s: was not present\n", obj->mm.region->name); @@ -1175,7 +1172,6 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915, pr_err("Failed to unbind object!\n"); goto out_unmap; } - GEM_BUG_ON(atomic_read(&obj->bind_count)); if (type != I915_MMAP_TYPE_GTT) { __i915_gem_object_put_pages(obj); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c index 2b6db6f799de..faa5b6d91795 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c @@ -14,7 +14,7 @@ static int igt_gem_object(void *arg) { struct drm_i915_private *i915 = arg; struct drm_i915_gem_object *obj; - int err = -ENOMEM; + int err; /* Basic test to ensure we can create an object */ diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.c b/drivers/gpu/drm/i915/gt/debugfs_engines.c index 6a5e9ab20b94..5e3725e62241 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_engines.c +++ b/drivers/gpu/drm/i915/gt/debugfs_engines.c @@ -32,5 +32,5 @@ void debugfs_engines_register(struct intel_gt *gt, struct dentry *root) { "engines", &engines_fops }, }; - debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files)); + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt); } diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c index 75255aaacaed..1de5fbaa1cf9 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt.c +++ b/drivers/gpu/drm/i915/gt/debugfs_gt.c @@ -9,6 +9,7 @@ #include "debugfs_engines.h" #include "debugfs_gt.h" #include "debugfs_gt_pm.h" +#include "uc/intel_uc_debugfs.h" #include "i915_drv.h" void debugfs_gt_register(struct intel_gt *gt) @@ -24,17 +25,19 @@ void debugfs_gt_register(struct intel_gt *gt) debugfs_engines_register(gt, root); debugfs_gt_pm_register(gt, root); + + intel_uc_debugfs_register(>->uc, root); } -void debugfs_gt_register_files(struct intel_gt *gt, - struct dentry *root, - const struct debugfs_gt_file *files, - unsigned long count) +void intel_gt_debugfs_register_files(struct dentry *root, + const struct debugfs_gt_file *files, + unsigned long count, void *data) { while (count--) { - if (!files->eval || files->eval(gt)) + umode_t mode = files->fops->write ? 0644 : 0444; + if (!files->eval || files->eval(data)) debugfs_create_file(files->name, - 0444, root, gt, + mode, root, data, files->fops); files++; diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.h b/drivers/gpu/drm/i915/gt/debugfs_gt.h index 4ea0f06cda8f..f77540f727e9 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt.h +++ b/drivers/gpu/drm/i915/gt/debugfs_gt.h @@ -28,12 +28,11 @@ void debugfs_gt_register(struct intel_gt *gt); struct debugfs_gt_file { const char *name; const struct file_operations *fops; - bool (*eval)(const struct intel_gt *gt); + bool (*eval)(void *data); }; -void debugfs_gt_register_files(struct intel_gt *gt, - struct dentry *root, - const struct debugfs_gt_file *files, - unsigned long count); +void intel_gt_debugfs_register_files(struct dentry *root, + const struct debugfs_gt_file *files, + unsigned long count, void *data); #endif /* DEBUGFS_GT_H */ diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c index 059c9e5c002e..aab30d908072 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c @@ -506,8 +506,10 @@ static int llc_show(struct seq_file *m, void *data) return 0; } -static bool llc_eval(const struct intel_gt *gt) +static bool llc_eval(void *data) { + struct intel_gt *gt = data; + return HAS_LLC(gt->i915); } @@ -580,8 +582,10 @@ static int rps_boost_show(struct seq_file *m, void *data) return 0; } -static bool rps_eval(const struct intel_gt *gt) +static bool rps_eval(void *data) { + struct intel_gt *gt = data; + return HAS_RPS(gt->i915); } @@ -597,5 +601,5 @@ void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root) { "rps_boost", &rps_boost_fops, rps_eval }, }; - debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files)); + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt); } diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index cbad7fe722ce..cbedba857d43 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -64,7 +64,7 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) if (!--b->irq_enabled) irq_disable(engine); - b->irq_armed = false; + WRITE_ONCE(b->irq_armed, false); intel_gt_pm_put_async(engine->gt); } @@ -73,7 +73,7 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine) struct intel_breadcrumbs *b = &engine->breadcrumbs; unsigned long flags; - if (!b->irq_armed) + if (!READ_ONCE(b->irq_armed)) return; spin_lock_irqsave(&b->irq_lock, flags); @@ -233,7 +233,7 @@ static bool __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) * which we can add a new waiter and avoid the cost of re-enabling * the irq. */ - b->irq_armed = true; + WRITE_ONCE(b->irq_armed, true); /* * Since we are waiting on a request, the GPU should be busy diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 01474d3a558b..74ddb49b2941 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -97,6 +97,8 @@ int __intel_context_do_pin(struct intel_context *ce) { int err; + GEM_BUG_ON(intel_context_is_closed(ce)); + if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) { err = intel_context_alloc_state(ce); if (err) @@ -112,6 +114,11 @@ int __intel_context_do_pin(struct intel_context *ce) goto out_release; } + if (unlikely(intel_context_is_closed(ce))) { + err = -ENOENT; + goto out_unlock; + } + if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) { err = intel_context_active_acquire(ce); if (unlikely(err)) diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 18efad255124..07be021882cc 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -173,6 +173,11 @@ static inline bool intel_context_is_barrier(const struct intel_context *ce) return test_bit(CONTEXT_BARRIER_BIT, &ce->flags); } +static inline bool intel_context_is_closed(const struct intel_context *ce) +{ + return test_bit(CONTEXT_CLOSED_BIT, &ce->flags); +} + static inline bool intel_context_use_semaphores(const struct intel_context *ce) { return test_bit(CONTEXT_USE_SEMAPHORES, &ce->flags); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 0f3b68b95c56..07cb83a0d017 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -62,10 +62,11 @@ struct intel_context { #define CONTEXT_BARRIER_BIT 0 #define CONTEXT_ALLOC_BIT 1 #define CONTEXT_VALID_BIT 2 -#define CONTEXT_USE_SEMAPHORES 3 -#define CONTEXT_BANNED 4 -#define CONTEXT_FORCE_SINGLE_SUBMISSION 5 -#define CONTEXT_NOPREEMPT 6 +#define CONTEXT_CLOSED_BIT 3 +#define CONTEXT_USE_SEMAPHORES 4 +#define CONTEXT_BANNED 5 +#define CONTEXT_FORCE_SINGLE_SUBMISSION 6 +#define CONTEXT_NOPREEMPT 7 u32 *lrc_reg_state; u64 lrc_desc; diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index b469de0dd9b6..d9ee64e2ef79 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -199,6 +199,8 @@ void intel_engine_cleanup(struct intel_engine_cs *engine); int intel_engines_init_mmio(struct intel_gt *gt); int intel_engines_init(struct intel_gt *gt); +void intel_engine_free_request_pool(struct intel_engine_cs *engine); + void intel_engines_release(struct intel_gt *gt); void intel_engines_free(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 3aa8a652c16d..b1f8527f02c8 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -347,8 +347,6 @@ 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; - i915->engine[id] = engine; - return 0; } @@ -425,17 +423,27 @@ void intel_engines_release(struct intel_gt *gt) engine->release = NULL; memset(&engine->reset, 0, sizeof(engine->reset)); - - gt->i915->engine[id] = NULL; } } +void intel_engine_free_request_pool(struct intel_engine_cs *engine) +{ + if (!engine->request_pool) + return; + + kmem_cache_free(i915_request_slab_cache(), engine->request_pool); +} + void intel_engines_free(struct intel_gt *gt) { struct intel_engine_cs *engine; enum intel_engine_id id; + /* Free the requests! dma-resv keeps fences around for an eternity */ + rcu_barrier(); + for_each_engine(engine, gt, id) { + intel_engine_free_request_pool(engine); kfree(engine); gt->engine[id] = NULL; } @@ -1225,6 +1233,49 @@ static void print_request(struct drm_printer *m, name); } +static struct intel_timeline *get_timeline(struct i915_request *rq) +{ + struct intel_timeline *tl; + + /* + * Even though we are holding the engine->active.lock here, there + * is no control over the submission queue per-se and we are + * inspecting the active state at a random point in time, with an + * unknown queue. Play safe and make sure the timeline remains valid. + * (Only being used for pretty printing, one extra kref shouldn't + * cause a camel stampede!) + */ + rcu_read_lock(); + tl = rcu_dereference(rq->timeline); + if (!kref_get_unless_zero(&tl->kref)) + tl = NULL; + rcu_read_unlock(); + + return tl; +} + +static int print_ring(char *buf, int sz, struct i915_request *rq) +{ + int len = 0; + + if (!i915_request_signaled(rq)) { + struct intel_timeline *tl = get_timeline(rq); + + len = scnprintf(buf, sz, + "ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ", + i915_ggtt_offset(rq->ring->vma), + tl ? tl->hwsp_offset : 0, + hwsp_seqno(rq), + DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context), + 1000 * 1000)); + + if (tl) + intel_timeline_put(tl); + } + + return len; +} + static void hexdump(struct drm_printer *m, const void *buf, size_t len) { const size_t rowsize = 8 * sizeof(u32); @@ -1254,27 +1305,6 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len) } } -static struct intel_timeline *get_timeline(struct i915_request *rq) -{ - struct intel_timeline *tl; - - /* - * Even though we are holding the engine->active.lock here, there - * is no control over the submission queue per-se and we are - * inspecting the active state at a random point in time, with an - * unknown queue. Play safe and make sure the timeline remains valid. - * (Only being used for pretty printing, one extra kref shouldn't - * cause a camel stampede!) - */ - rcu_read_lock(); - tl = rcu_dereference(rq->timeline); - if (!kref_get_unless_zero(&tl->kref)) - tl = NULL; - rcu_read_unlock(); - - return tl; -} - static const char *repr_timer(const struct timer_list *t) { if (!READ_ONCE(t->expires)) @@ -1295,6 +1325,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); + if (HAS_EXECLISTS(dev_priv)) { + drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); + drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_LO)); + } drm_printf(m, "\tRING_START: 0x%08x\n", ENGINE_READ(engine, RING_START)); drm_printf(m, "\tRING_HEAD: 0x%08x\n", @@ -1387,39 +1423,24 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, int len; len = scnprintf(hdr, sizeof(hdr), - "\t\tActive[%d]: ", - (int)(port - execlists->active)); - if (!i915_request_signaled(rq)) { - struct intel_timeline *tl = get_timeline(rq); - - len += scnprintf(hdr + len, sizeof(hdr) - len, - "ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ", - i915_ggtt_offset(rq->ring->vma), - tl ? tl->hwsp_offset : 0, - hwsp_seqno(rq), - DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context), - 1000 * 1000)); - - if (tl) - intel_timeline_put(tl); - } + "\t\tActive[%d]: ccid:%08x, ", + (int)(port - execlists->active), + upper_32_bits(rq->context->lrc_desc)); + len += print_ring(hdr + len, sizeof(hdr) - len, rq); scnprintf(hdr + len, sizeof(hdr) - len, "rq: "); print_request(m, rq, hdr); } for (port = execlists->pending; (rq = *port); port++) { - struct intel_timeline *tl = get_timeline(rq); - char hdr[80]; - - snprintf(hdr, sizeof(hdr), - "\t\tPending[%d] ring:{start:%08x, hwsp:%08x, seqno:%08x}, rq: ", - (int)(port - execlists->pending), - i915_ggtt_offset(rq->ring->vma), - tl ? tl->hwsp_offset : 0, - hwsp_seqno(rq)); - print_request(m, rq, hdr); + char hdr[160]; + int len; - if (tl) - intel_timeline_put(tl); + len = scnprintf(hdr, sizeof(hdr), + "\t\tPending[%d]: ccid:%08x, ", + (int)(port - execlists->pending), + upper_32_bits(rq->context->lrc_desc)); + len += print_ring(hdr + len, sizeof(hdr) - len, rq); + scnprintf(hdr + len, sizeof(hdr) - len, "rq: "); + print_request(m, rq, hdr); } rcu_read_unlock(); execlists_active_unlock_bh(execlists); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index dd825718e4e5..5136c8bf112d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -31,7 +31,7 @@ static bool next_heartbeat(struct intel_engine_cs *engine) delay = msecs_to_jiffies_timeout(delay); if (delay >= HZ) delay = round_jiffies_up_relative(delay); - schedule_delayed_work(&engine->heartbeat.work, delay); + mod_delayed_work(system_wq, &engine->heartbeat.work, delay); return true; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index b6cf284e3a2d..3be679741d22 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -181,7 +181,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine) * Ergo, if we put ourselves on the timelines.active_list * (se intel_timeline_enter()) before we increment the * engine->wakeref.count, we may see the request completion and retire - * it causing an undeflow of the engine->wakeref. + * it causing an underflow of the engine->wakeref. */ flags = __timeline_mark_lock(ce); GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index e52c2b0cb245..418df0a13145 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -37,6 +37,12 @@ static inline void intel_engine_pm_put_async(struct intel_engine_cs *engine) intel_wakeref_put_async(&engine->wakeref); } +static inline void intel_engine_pm_put_delay(struct intel_engine_cs *engine, + unsigned long delay) +{ + intel_wakeref_put_delay(&engine->wakeref, delay); +} + static inline void intel_engine_pm_flush(struct intel_engine_cs *engine) { intel_wakeref_unlock_wait(&engine->wakeref); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 80cdde712842..01d4bd781a2f 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -157,6 +157,15 @@ struct intel_engine_execlists { struct i915_priolist default_priolist; /** + * @yield: CCID at the time of the last semaphore-wait interrupt. + * + * Instead of leaving a semaphore busy-spinning on an engine, we would + * like to switch to another ready context, i.e. yielding the semaphore + * timeslice. + */ + u32 yield; + + /** * @error_interrupt: CS Master EIR * * The CS generates an interrupt when it detects an error. We capture @@ -308,6 +317,9 @@ struct intel_engine_cs { struct list_head hold; /* ready requests, but on hold */ } active; + /* keep a request in reserve for a [pm] barrier under oom */ + struct i915_request *request_pool; + struct llist_head barrier_tasks; struct intel_context *kernel_context; /* pinned */ diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index aed498a0d032..eebd1190506f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -65,7 +65,7 @@ static int ggtt_init_hw(struct i915_ggtt *ggtt) ggtt->mappable_end); } - i915_ggtt_init_fences(ggtt); + intel_ggtt_init_fences(ggtt); return 0; } @@ -191,10 +191,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level level, u32 flags) { - 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_ggtt_pte_encode(0, level, 0); + struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); + gen8_pte_t __iomem *gte; + gen8_pte_t __iomem *end; + struct sgt_iter iter; dma_addr_t addr; /* @@ -202,10 +203,17 @@ 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 @@ -241,13 +249,22 @@ 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 @@ -698,11 +715,13 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt) */ void i915_ggtt_driver_release(struct drm_i915_private *i915) { + struct i915_ggtt *ggtt = &i915->ggtt; struct pagevec *pvec; - fini_aliasing_ppgtt(&i915->ggtt); + fini_aliasing_ppgtt(ggtt); - ggtt_cleanup_hw(&i915->ggtt); + intel_ggtt_fini_fences(ggtt); + ggtt_cleanup_hw(ggtt); pvec = &i915->mm.wc_stash.pvec; if (pvec->nr) { @@ -767,13 +786,13 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) else ggtt->gsm = ioremap_wc(phys_addr, size); if (!ggtt->gsm) { - DRM_ERROR("Failed to map the ggtt page table\n"); + drm_err(&i915->drm, "Failed to map the ggtt page table\n"); return -ENOMEM; } ret = setup_scratch_page(&ggtt->vm, GFP_DMA32); if (ret) { - DRM_ERROR("Scratch setup failed\n"); + drm_err(&i915->drm, "Scratch setup failed\n"); /* iounmap will also get called at remove, but meh */ iounmap(ggtt->gsm); return ret; @@ -833,7 +852,8 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) if (!err) err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); if (err) - DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err); + drm_err(&i915->drm, + "Can't set DMA mask/consistent mask (%d)\n", err); pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); if (IS_CHERRYVIEW(i915)) @@ -980,7 +1000,8 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) * just a coarse sanity check. */ if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) { - DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end); + drm_err(&i915->drm, "Unknown GMADR size (%pa)\n", + &ggtt->mappable_end); return -ENXIO; } @@ -988,7 +1009,8 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) if (!err) err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40)); if (err) - DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err); + drm_err(&i915->drm, + "Can't set DMA mask/consistent mask (%d)\n", err); pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); size = gen6_get_total_gtt_size(snb_gmch_ctl); @@ -1035,7 +1057,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL); if (!ret) { - DRM_ERROR("failed to set up gmch\n"); + drm_err(&i915->drm, "failed to set up gmch\n"); return -EIO; } @@ -1058,7 +1080,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.vma_ops.clear_pages = clear_pages; if (unlikely(ggtt->do_idle_maps)) - dev_notice(i915->drm.dev, + drm_notice(&i915->drm, "Applying Ironlake quirks for intel_iommu\n"); return 0; @@ -1083,26 +1105,29 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt) return ret; if ((ggtt->vm.total - 1) >> 32) { - DRM_ERROR("We never expected a Global GTT with more than 32bits" - " of address space! Found %lldM!\n", - ggtt->vm.total >> 20); + drm_err(&i915->drm, + "We never expected a Global GTT with more than 32bits" + " of address space! Found %lldM!\n", + ggtt->vm.total >> 20); ggtt->vm.total = 1ULL << 32; ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->vm.total); } if (ggtt->mappable_end > ggtt->vm.total) { - DRM_ERROR("mappable aperture extends past end of GGTT," - " aperture=%pa, total=%llx\n", - &ggtt->mappable_end, ggtt->vm.total); + drm_err(&i915->drm, + "mappable aperture extends past end of GGTT," + " aperture=%pa, total=%llx\n", + &ggtt->mappable_end, ggtt->vm.total); ggtt->mappable_end = ggtt->vm.total; } /* GMADR is the PCI mmio aperture into the global GTT. */ - DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20); - DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20); - DRM_DEBUG_DRIVER("DSM size = %lluM\n", - (u64)resource_size(&intel_graphics_stolen_res) >> 20); + drm_dbg(&i915->drm, "GGTT size = %lluM\n", ggtt->vm.total >> 20); + drm_dbg(&i915->drm, "GMADR size = %lluM\n", + (u64)ggtt->mappable_end >> 20); + drm_dbg(&i915->drm, "DSM size = %lluM\n", + (u64)resource_size(&intel_graphics_stolen_res) >> 20); return 0; } @@ -1120,7 +1145,7 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915) return ret; if (intel_vtd_active()) - dev_info(i915->drm.dev, "VT-d active for gfx access\n"); + drm_info(&i915->drm, "VT-d active for gfx access\n"); return 0; } @@ -1195,6 +1220,8 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt) if (INTEL_GEN(ggtt->vm.i915) >= 8) setup_private_pat(ggtt->vm.gt->uncore); + + intel_ggtt_restore_fences(ggtt); } static struct scatterlist * diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index d152b648c73c..7fb36b12fe7a 100644 --- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -68,8 +68,7 @@ static struct intel_uncore *fence_to_uncore(struct i915_fence_reg *fence) return fence->ggtt->vm.gt->uncore; } -static void i965_write_fence_reg(struct i915_fence_reg *fence, - struct i915_vma *vma) +static void i965_write_fence_reg(struct i915_fence_reg *fence) { i915_reg_t fence_reg_lo, fence_reg_hi; int fence_pitch_shift; @@ -87,18 +86,16 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence, } val = 0; - if (vma) { - unsigned int stride = i915_gem_object_get_stride(vma->obj); + if (fence->tiling) { + unsigned int stride = fence->stride; - GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma)); - GEM_BUG_ON(!IS_ALIGNED(vma->node.start, I965_FENCE_PAGE)); - GEM_BUG_ON(!IS_ALIGNED(vma->fence_size, I965_FENCE_PAGE)); GEM_BUG_ON(!IS_ALIGNED(stride, 128)); - val = (vma->node.start + vma->fence_size - I965_FENCE_PAGE) << 32; - val |= vma->node.start; + val = fence->start + fence->size - I965_FENCE_PAGE; + val <<= 32; + val |= fence->start; val |= (u64)((stride / 128) - 1) << fence_pitch_shift; - if (i915_gem_object_get_tiling(vma->obj) == I915_TILING_Y) + if (fence->tiling == I915_TILING_Y) val |= BIT(I965_FENCE_TILING_Y_SHIFT); val |= I965_FENCE_REG_VALID; } @@ -125,21 +122,15 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence, } } -static void i915_write_fence_reg(struct i915_fence_reg *fence, - struct i915_vma *vma) +static void i915_write_fence_reg(struct i915_fence_reg *fence) { u32 val; val = 0; - if (vma) { - unsigned int tiling = i915_gem_object_get_tiling(vma->obj); + if (fence->tiling) { + unsigned int stride = fence->stride; + unsigned int tiling = fence->tiling; bool is_y_tiled = tiling == I915_TILING_Y; - unsigned int stride = i915_gem_object_get_stride(vma->obj); - - GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma)); - GEM_BUG_ON(vma->node.start & ~I915_FENCE_START_MASK); - GEM_BUG_ON(!is_power_of_2(vma->fence_size)); - GEM_BUG_ON(!IS_ALIGNED(vma->node.start, vma->fence_size)); if (is_y_tiled && HAS_128_BYTE_Y_TILING(fence_to_i915(fence))) stride /= 128; @@ -147,10 +138,10 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence, stride /= 512; GEM_BUG_ON(!is_power_of_2(stride)); - val = vma->node.start; + val = fence->start; if (is_y_tiled) val |= BIT(I830_FENCE_TILING_Y_SHIFT); - val |= I915_FENCE_SIZE_BITS(vma->fence_size); + val |= I915_FENCE_SIZE_BITS(fence->size); val |= ilog2(stride) << I830_FENCE_PITCH_SHIFT; val |= I830_FENCE_REG_VALID; @@ -165,25 +156,18 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence, } } -static void i830_write_fence_reg(struct i915_fence_reg *fence, - struct i915_vma *vma) +static void i830_write_fence_reg(struct i915_fence_reg *fence) { u32 val; val = 0; - if (vma) { - unsigned int stride = i915_gem_object_get_stride(vma->obj); - - GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma)); - GEM_BUG_ON(vma->node.start & ~I830_FENCE_START_MASK); - GEM_BUG_ON(!is_power_of_2(vma->fence_size)); - GEM_BUG_ON(!is_power_of_2(stride / 128)); - GEM_BUG_ON(!IS_ALIGNED(vma->node.start, vma->fence_size)); + if (fence->tiling) { + unsigned int stride = fence->stride; - val = vma->node.start; - if (i915_gem_object_get_tiling(vma->obj) == I915_TILING_Y) + val = fence->start; + if (fence->tiling == I915_TILING_Y) val |= BIT(I830_FENCE_TILING_Y_SHIFT); - val |= I830_FENCE_SIZE_BITS(vma->fence_size); + val |= I830_FENCE_SIZE_BITS(fence->size); val |= ilog2(stride / 128) << I830_FENCE_PITCH_SHIFT; val |= I830_FENCE_REG_VALID; } @@ -197,8 +181,7 @@ static void i830_write_fence_reg(struct i915_fence_reg *fence, } } -static void fence_write(struct i915_fence_reg *fence, - struct i915_vma *vma) +static void fence_write(struct i915_fence_reg *fence) { struct drm_i915_private *i915 = fence_to_i915(fence); @@ -209,18 +192,21 @@ static void fence_write(struct i915_fence_reg *fence, */ if (IS_GEN(i915, 2)) - i830_write_fence_reg(fence, vma); + i830_write_fence_reg(fence); else if (IS_GEN(i915, 3)) - i915_write_fence_reg(fence, vma); + i915_write_fence_reg(fence); else - i965_write_fence_reg(fence, vma); + i965_write_fence_reg(fence); /* * Access through the fenced region afterwards is * ordered by the posting reads whilst writing the registers. */ +} - fence->dirty = false; +static bool gpu_uses_fence_registers(struct i915_fence_reg *fence) +{ + return INTEL_GEN(fence_to_i915(fence)) < 4; } static int fence_update(struct i915_fence_reg *fence, @@ -232,27 +218,32 @@ static int fence_update(struct i915_fence_reg *fence, struct i915_vma *old; int ret; + fence->tiling = 0; if (vma) { + GEM_BUG_ON(!i915_gem_object_get_stride(vma->obj) || + !i915_gem_object_get_tiling(vma->obj)); + if (!i915_vma_is_map_and_fenceable(vma)) return -EINVAL; - if (drm_WARN(&uncore->i915->drm, - !i915_gem_object_get_stride(vma->obj) || - !i915_gem_object_get_tiling(vma->obj), - "bogus fence setup with stride: 0x%x, tiling mode: %i\n", - i915_gem_object_get_stride(vma->obj), - i915_gem_object_get_tiling(vma->obj))) - return -EINVAL; + if (gpu_uses_fence_registers(fence)) { + /* implicit 'unfenced' GPU blits */ + ret = i915_vma_sync(vma); + if (ret) + return ret; + } - ret = i915_vma_sync(vma); - if (ret) - return ret; + fence->start = vma->node.start; + fence->size = vma->fence_size; + fence->stride = i915_gem_object_get_stride(vma->obj); + fence->tiling = i915_gem_object_get_tiling(vma->obj); } + WRITE_ONCE(fence->dirty, false); old = xchg(&fence->vma, NULL); if (old) { /* XXX Ideally we would move the waiting to outside the mutex */ - ret = i915_vma_sync(old); + ret = i915_active_wait(&fence->active); if (ret) { fence->vma = old; return ret; @@ -276,7 +267,7 @@ static int fence_update(struct i915_fence_reg *fence, /* * We only need to update the register itself if the device is awake. * If the device is currently powered down, we will defer the write - * to the runtime resume, see i915_gem_restore_fences(). + * to the runtime resume, see intel_ggtt_restore_fences(). * * This only works for removing the fence register, on acquisition * the caller must hold the rpm wakeref. The fence register must @@ -290,7 +281,7 @@ static int fence_update(struct i915_fence_reg *fence, } WRITE_ONCE(fence->vma, vma); - fence_write(fence, vma); + fence_write(fence); if (vma) { vma->fence = fence; @@ -307,23 +298,26 @@ static int fence_update(struct i915_fence_reg *fence, * * This function force-removes any fence from the given object, which is useful * if the kernel wants to do untiled GTT access. - * - * Returns: - * - * 0 on success, negative error code on failure. */ -int i915_vma_revoke_fence(struct i915_vma *vma) +void i915_vma_revoke_fence(struct i915_vma *vma) { struct i915_fence_reg *fence = vma->fence; + intel_wakeref_t wakeref; lockdep_assert_held(&vma->vm->mutex); if (!fence) - return 0; + return; - if (atomic_read(&fence->pin_count)) - return -EBUSY; + GEM_BUG_ON(fence->vma != vma); + GEM_BUG_ON(!i915_active_is_idle(&fence->active)); + GEM_BUG_ON(atomic_read(&fence->pin_count)); - return fence_update(fence, NULL); + fence->tiling = 0; + WRITE_ONCE(fence->vma, NULL); + vma->fence = NULL; + + with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref) + fence_write(fence); } static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt) @@ -487,34 +481,19 @@ void i915_unreserve_fence(struct i915_fence_reg *fence) } /** - * i915_gem_restore_fences - restore fence state + * intel_ggtt_restore_fences - restore fence state * @ggtt: Global GTT * * Restore the hw fence state to match the software tracking again, to be called * after a gpu reset and on resume. Note that on runtime suspend we only cancel * the fences, to be reacquired by the user later. */ -void i915_gem_restore_fences(struct i915_ggtt *ggtt) +void intel_ggtt_restore_fences(struct i915_ggtt *ggtt) { int i; - rcu_read_lock(); /* keep obj alive as we dereference */ - for (i = 0; i < ggtt->num_fences; i++) { - struct i915_fence_reg *reg = &ggtt->fence_regs[i]; - struct i915_vma *vma = READ_ONCE(reg->vma); - - GEM_BUG_ON(vma && vma->fence != reg); - - /* - * Commit delayed tiling changes if we have an object still - * attached to the fence, otherwise just clear the fence. - */ - if (vma && !i915_gem_object_is_tiled(vma->obj)) - vma = NULL; - - fence_write(reg, vma); - } - rcu_read_unlock(); + for (i = 0; i < ggtt->num_fences; i++) + fence_write(&ggtt->fence_regs[i]); } /** @@ -746,7 +725,7 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * bit 17 of its physical address and therefore being interpreted differently * by the GPU. */ -static void i915_gem_swizzle_page(struct page *page) +static void swizzle_page(struct page *page) { char temp[64]; char *vaddr; @@ -791,7 +770,7 @@ i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj, for_each_sgt_page(page, sgt_iter, pages) { char new_bit_17 = page_to_phys(page) >> 17; if ((new_bit_17 & 0x1) != (test_bit(i, obj->bit_17) != 0)) { - i915_gem_swizzle_page(page); + swizzle_page(page); set_page_dirty(page); } i++; @@ -836,7 +815,7 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj, } } -void i915_ggtt_init_fences(struct i915_ggtt *ggtt) +void intel_ggtt_init_fences(struct i915_ggtt *ggtt) { struct drm_i915_private *i915 = ggtt->vm.i915; struct intel_uncore *uncore = ggtt->vm.gt->uncore; @@ -864,18 +843,37 @@ void i915_ggtt_init_fences(struct i915_ggtt *ggtt) if (intel_vgpu_active(i915)) num_fences = intel_uncore_read(uncore, vgtif_reg(avail_rs.fence_num)); + ggtt->fence_regs = kcalloc(num_fences, + sizeof(*ggtt->fence_regs), + GFP_KERNEL); + if (!ggtt->fence_regs) + num_fences = 0; /* Initialize fence registers to zero */ for (i = 0; i < num_fences; i++) { struct i915_fence_reg *fence = &ggtt->fence_regs[i]; + i915_active_init(&fence->active, NULL, NULL); fence->ggtt = ggtt; fence->id = i; list_add_tail(&fence->link, &ggtt->fence_list); } ggtt->num_fences = num_fences; - i915_gem_restore_fences(ggtt); + intel_ggtt_restore_fences(ggtt); +} + +void intel_ggtt_fini_fences(struct i915_ggtt *ggtt) +{ + int i; + + for (i = 0; i < ggtt->num_fences; i++) { + struct i915_fence_reg *fence = &ggtt->fence_regs[i]; + + i915_active_fini(&fence->active); + } + + kfree(ggtt->fence_regs); } void intel_gt_init_swizzling(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.h b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h index 7bd521cd7cd7..9eef679e1311 100644 --- a/drivers/gpu/drm/i915/i915_gem_fence_reg.h +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h @@ -22,12 +22,14 @@ * */ -#ifndef __I915_FENCE_REG_H__ -#define __I915_FENCE_REG_H__ +#ifndef __INTEL_GGTT_FENCING_H__ +#define __INTEL_GGTT_FENCING_H__ #include <linux/list.h> #include <linux/types.h> +#include "i915_active.h" + struct drm_i915_gem_object; struct i915_ggtt; struct i915_vma; @@ -41,6 +43,7 @@ struct i915_fence_reg { struct i915_ggtt *ggtt; struct i915_vma *vma; atomic_t pin_count; + struct i915_active active; int id; /** * Whether the tiling parameters for the currently @@ -51,20 +54,24 @@ struct i915_fence_reg { * command (such as BLT on gen2/3), as a "fence". */ bool dirty; + u32 start; + u32 size; + u32 tiling; + u32 stride; }; -/* i915_gem_fence_reg.c */ struct i915_fence_reg *i915_reserve_fence(struct i915_ggtt *ggtt); void i915_unreserve_fence(struct i915_fence_reg *fence); -void i915_gem_restore_fences(struct i915_ggtt *ggtt); +void intel_ggtt_restore_fences(struct i915_ggtt *ggtt); void i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj, struct sg_table *pages); void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj, struct sg_table *pages); -void i915_ggtt_init_fences(struct i915_ggtt *ggtt); +void intel_ggtt_init_fences(struct i915_ggtt *ggtt); +void intel_ggtt_fini_fences(struct i915_ggtt *ggtt); void intel_gt_init_swizzling(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index d09f7596cb98..1c99cc72305a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -635,8 +635,7 @@ void intel_gt_driver_remove(struct intel_gt *gt) { __intel_gt_disable(gt); - intel_uc_fini_hw(>->uc); - intel_uc_fini(>->uc); + intel_uc_driver_remove(>->uc); intel_engines_release(gt); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f0e7fd95165a..0cc7dd54f4f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) } } + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 8b653c0f5e5f..3e8a56c7d818 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -204,7 +204,7 @@ int intel_gt_resume(struct intel_gt *gt) /* Only when the HW is re-initialised, can we replay the requests */ err = intel_gt_init_hw(gt); if (err) { - dev_err(gt->i915->drm.dev, + drm_err(>->i915->drm, "Failed to initialize GPU, declaring it wedged!\n"); goto err_wedged; } @@ -220,7 +220,7 @@ int intel_gt_resume(struct intel_gt *gt) intel_engine_pm_put(engine); if (err) { - dev_err(gt->i915->drm.dev, + drm_err(>->i915->drm, "Failed to restart %s (%d)\n", engine->name, err); goto err_wedged; @@ -324,6 +324,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt) { GT_TRACE(gt, "\n"); intel_gt_init_swizzling(gt); + intel_ggtt_restore_fences(gt->ggtt); return intel_uc_runtime_resume(>->uc); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index 24c99d0838af..835ec184763e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -38,7 +38,7 @@ static bool flush_submission(struct intel_gt *gt) for_each_engine(engine, gt, id) { intel_engine_flush_submission(engine); active |= flush_work(&engine->retire_work); - active |= flush_work(&engine->wakeref.work); + active |= flush_delayed_work(&engine->wakeref.work); } return active; diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index b3116fe8d180..d93ebdf3fa0e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -26,7 +26,6 @@ #include <drm/drm_mm.h> #include "gt/intel_reset.h" -#include "i915_gem_fence_reg.h" #include "i915_selftest.h" #include "i915_vma_types.h" @@ -135,6 +134,8 @@ typedef u64 gen8_pte_t; #define GEN8_PDE_IPS_64K BIT(11) #define GEN8_PDE_PS_2M BIT(7) +struct i915_fence_reg; + #define for_each_sgt_daddr(__dp, __iter, __sgt) \ __for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE) @@ -333,7 +334,7 @@ struct i915_ggtt { u32 pin_bias; unsigned int num_fences; - struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; + struct i915_fence_reg *fence_regs; struct list_head fence_list; /** diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 112531b29f59..6fbad5e2343f 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -238,6 +238,17 @@ __execlists_update_reg_state(const struct intel_context *ce, const struct intel_engine_cs *engine, u32 head); +static u32 intel_context_get_runtime(const struct intel_context *ce) +{ + /* + * We can use either ppHWSP[16] which is recorded before the context + * switch (and so excludes the cost of context switches) or use the + * value from the context image itself, which is saved/restored earlier + * and so includes the cost of the save. + */ + return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]); +} + static void mark_eio(struct i915_request *rq) { if (i915_request_completed(rq)) @@ -1154,6 +1165,7 @@ static void restore_default_state(struct intel_context *ce, engine->context_size - PAGE_SIZE); execlists_init_reg_state(regs, ce, engine, ce->ring, false); + ce->runtime.last = intel_context_get_runtime(ce); } static void reset_active(struct i915_request *rq, @@ -1195,17 +1207,6 @@ static void reset_active(struct i915_request *rq, ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; } -static u32 intel_context_get_runtime(const struct intel_context *ce) -{ - /* - * We can use either ppHWSP[16] which is recorded before the context - * switch (and so excludes the cost of context switches) or use the - * value from the context image itself, which is saved/restored earlier - * and so includes the cost of the save. - */ - return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]); -} - static void st_update_runtime_underflow(struct intel_context *ce, s32 dt) { #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) @@ -1415,6 +1416,23 @@ static inline void write_desc(struct intel_engine_execlists *execlists, u64 desc } } +static __maybe_unused char * +dump_port(char *buf, int buflen, const char *prefix, struct i915_request *rq) +{ + if (!rq) + return ""; + + snprintf(buf, buflen, "%s%llx:%lld%s prio %d", + prefix, + rq->fence.context, rq->fence.seqno, + i915_request_completed(rq) ? "!" : + i915_request_started(rq) ? "*" : + "", + rq_prio(rq)); + + return buf; +} + static __maybe_unused void trace_ports(const struct intel_engine_execlists *execlists, const char *msg, @@ -1422,18 +1440,14 @@ trace_ports(const struct intel_engine_execlists *execlists, { const struct intel_engine_cs *engine = container_of(execlists, typeof(*engine), execlists); + char __maybe_unused p0[40], p1[40]; if (!ports[0]) return; - ENGINE_TRACE(engine, "%s { %llx:%lld%s, %llx:%lld }\n", msg, - ports[0]->fence.context, - ports[0]->fence.seqno, - i915_request_completed(ports[0]) ? "!" : - i915_request_started(ports[0]) ? "*" : - "", - ports[1] ? ports[1]->fence.context : 0, - ports[1] ? ports[1]->fence.seqno : 0); + ENGINE_TRACE(engine, "%s { %s%s }\n", msg, + dump_port(p0, sizeof(p0), "", ports[0]), + dump_port(p1, sizeof(p1), ", ", ports[1])); } static inline bool @@ -1663,7 +1677,7 @@ static bool virtual_matches(const struct virtual_engine *ve, } static void virtual_xfer_breadcrumbs(struct virtual_engine *ve, - struct intel_engine_cs *engine) + struct i915_request *rq) { struct intel_engine_cs *old = ve->siblings[0]; @@ -1671,9 +1685,19 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve, spin_lock(&old->breadcrumbs.irq_lock); if (!list_empty(&ve->context.signal_link)) { - list_move_tail(&ve->context.signal_link, - &engine->breadcrumbs.signalers); - intel_engine_signal_breadcrumbs(engine); + list_del_init(&ve->context.signal_link); + + /* + * We cannot acquire the new engine->breadcrumbs.irq_lock + * (as we are holding a breadcrumbs.irq_lock already), + * so attach this request to the signaler on submission. + * The queued irq_work will occur when we finally drop + * the engine->active.lock after dequeue. + */ + set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags); + + /* Also transfer the pending irq_work for the old breadcrumb. */ + intel_engine_signal_breadcrumbs(rq->engine); } spin_unlock(&old->breadcrumbs.irq_lock); } @@ -1744,7 +1768,8 @@ static void defer_active(struct intel_engine_cs *engine) } static bool -need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) +need_timeslice(const struct intel_engine_cs *engine, + const struct i915_request *rq) { int hint; @@ -1758,6 +1783,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) return hint >= effective_prio(rq); } +static bool +timeslice_yield(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + /* + * Once bitten, forever smitten! + * + * If the active context ever busy-waited on a semaphore, + * it will be treated as a hog until the end of its timeslice (i.e. + * until it is scheduled out and replaced by a new submission, + * possibly even its own lite-restore). The HW only sends an interrupt + * on the first miss, and we do know if that semaphore has been + * signaled, or even if it is now stuck on another semaphore. Play + * safe, yield if it might be stuck -- it will be given a fresh + * timeslice in the near future. + */ + return upper_32_bits(rq->context->lrc_desc) == READ_ONCE(el->yield); +} + +static bool +timeslice_expired(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + return timer_expired(&el->timer) || timeslice_yield(el, rq); +} + static int switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq) { @@ -1773,8 +1824,7 @@ timeslice(const struct intel_engine_cs *engine) return READ_ONCE(engine->props.timeslice_duration_ms); } -static unsigned long -active_timeslice(const struct intel_engine_cs *engine) +static unsigned long active_timeslice(const struct intel_engine_cs *engine) { const struct intel_engine_execlists *execlists = &engine->execlists; const struct i915_request *rq = *execlists->active; @@ -1790,16 +1840,25 @@ active_timeslice(const struct intel_engine_cs *engine) static void set_timeslice(struct intel_engine_cs *engine) { + unsigned long duration; + if (!intel_engine_has_timeslices(engine)) return; - set_timer_ms(&engine->execlists.timer, active_timeslice(engine)); + duration = active_timeslice(engine); + ENGINE_TRACE(engine, "bump timeslicing, interval:%lu", duration); + + set_timer_ms(&engine->execlists.timer, duration); } static void start_timeslice(struct intel_engine_cs *engine) { struct intel_engine_execlists *execlists = &engine->execlists; - int prio = queue_prio(execlists); + const int prio = queue_prio(execlists); + unsigned long duration; + + if (!intel_engine_has_timeslices(engine)) + return; WRITE_ONCE(execlists->switch_priority_hint, prio); if (prio == INT_MIN) @@ -1808,7 +1867,12 @@ static void start_timeslice(struct intel_engine_cs *engine) if (timer_pending(&execlists->timer)) return; - set_timer_ms(&execlists->timer, timeslice(engine)); + duration = timeslice(engine); + ENGINE_TRACE(engine, + "start timeslicing, prio:%d, interval:%lu", + prio, duration); + + set_timer_ms(&execlists->timer, duration); } static void record_preemption(struct intel_engine_execlists *execlists) @@ -1905,11 +1969,26 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * of trouble. */ active = READ_ONCE(execlists->active); - while ((last = *active) && i915_request_completed(last)) - active++; - if (last) { + /* + * In theory we can skip over completed contexts that have not + * yet been processed by events (as those events are in flight): + * + * while ((last = *active) && i915_request_completed(last)) + * active++; + * + * However, the GPU cannot handle this as it will ultimately + * find itself trying to jump back into a context it has just + * completed and barf. + */ + + if ((last = *active)) { if (need_preempt(engine, last, rb)) { + if (i915_request_completed(last)) { + tasklet_hi_schedule(&execlists->tasklet); + return; + } + ENGINE_TRACE(engine, "preempting last=%llx:%lld, prio=%d, hint=%d\n", last->fence.context, @@ -1936,13 +2015,19 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last = NULL; } else if (need_timeslice(engine, last) && - timer_expired(&engine->execlists.timer)) { + timeslice_expired(execlists, last)) { + if (i915_request_completed(last)) { + tasklet_hi_schedule(&execlists->tasklet); + return; + } + ENGINE_TRACE(engine, - "expired last=%llx:%lld, prio=%d, hint=%d\n", + "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n", last->fence.context, last->fence.seqno, last->sched.attr.priority, - execlists->queue_priority_hint); + execlists->queue_priority_hint, + yesno(timeslice_yield(execlists, last))); ring_set_paused(engine, 1); defer_active(engine); @@ -2045,7 +2130,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) engine); if (!list_empty(&ve->context.signals)) - virtual_xfer_breadcrumbs(ve, engine); + virtual_xfer_breadcrumbs(ve, rq); /* * Move the bound engine to the top of the list @@ -2203,6 +2288,7 @@ done: } clear_ports(port + 1, last_port - port); + WRITE_ONCE(execlists->yield, -1); execlists_submit_ports(engine); set_preempt_timeout(engine, *active); } else { @@ -2298,6 +2384,13 @@ gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) return *csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED); } +static inline void flush_hwsp(const struct i915_request *rq) +{ + mb(); + clflush((void *)READ_ONCE(rq->hwsp_seqno)); + mb(); +} + static void process_csb(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -2374,8 +2467,6 @@ static void process_csb(struct intel_engine_cs *engine) if (promote) { struct i915_request * const *old = execlists->active; - GEM_BUG_ON(!assert_pending_valid(execlists, "promote")); - ring_set_paused(engine, 0); /* Point active to the new ELSP; prevent overwriting */ @@ -2388,6 +2479,7 @@ static void process_csb(struct intel_engine_cs *engine) execlists_schedule_out(*old++); /* switch pending to inflight */ + GEM_BUG_ON(!assert_pending_valid(execlists, "promote")); memcpy(execlists->inflight, execlists->pending, execlists_num_ports(execlists) * @@ -2409,13 +2501,24 @@ static void process_csb(struct intel_engine_cs *engine) * user interrupt and CSB is processed. */ if (GEM_SHOW_DEBUG() && - !i915_request_completed(*execlists->active) && - !reset_in_progress(execlists)) { - struct i915_request *rq __maybe_unused = - *execlists->active; + !i915_request_completed(*execlists->active)) { + struct i915_request *rq = *execlists->active; const u32 *regs __maybe_unused = rq->context->lrc_reg_state; + /* + * Flush the breadcrumb before crying foul. + * + * Since we have hit this on icl and seen the + * breadcrumb advance as we print out the debug + * info (so the problem corrected itself without + * lasting damage), and we know that icl suffers + * from missing global observation points in + * execlists, presume that affects even more + * coherency. + */ + flush_hwsp(rq); + ENGINE_TRACE(engine, "ring:{start:0x%08x, head:%04x, tail:%04x, ctl:%08x, mode:%08x}\n", ENGINE_READ(engine, RING_START), @@ -2436,7 +2539,10 @@ static void process_csb(struct intel_engine_cs *engine) regs[CTX_RING_HEAD], regs[CTX_RING_TAIL]); - GEM_BUG_ON("context completed before request"); + /* Still? Declare it caput! */ + if (!i915_request_completed(rq) && + !reset_in_progress(execlists)) + GEM_BUG_ON("context completed before request"); } execlists_schedule_out(*execlists->active++); @@ -2726,6 +2832,45 @@ err_cap: return NULL; } +static struct i915_request * +active_context(struct intel_engine_cs *engine, u32 ccid) +{ + const struct intel_engine_execlists * const el = &engine->execlists; + struct i915_request * const *port, *rq; + + /* + * Use the most recent result from process_csb(), but just in case + * we trigger an error (via interrupt) before the first CS event has + * been written, peek at the next submission. + */ + + for (port = el->active; (rq = *port); port++) { + if (upper_32_bits(rq->context->lrc_desc) == ccid) { + ENGINE_TRACE(engine, + "ccid found at active:%zd\n", + port - el->active); + return rq; + } + } + + for (port = el->pending; (rq = *port); port++) { + if (upper_32_bits(rq->context->lrc_desc) == ccid) { + ENGINE_TRACE(engine, + "ccid found at pending:%zd\n", + port - el->pending); + return rq; + } + } + + ENGINE_TRACE(engine, "ccid:%x not found\n", ccid); + return NULL; +} + +static u32 active_ccid(struct intel_engine_cs *engine) +{ + return ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI); +} + static bool execlists_capture(struct intel_engine_cs *engine) { struct execlists_capture *cap; @@ -2743,7 +2888,7 @@ static bool execlists_capture(struct intel_engine_cs *engine) return true; spin_lock_irq(&engine->active.lock); - cap->rq = execlists_active(&engine->execlists); + cap->rq = active_context(engine, active_ccid(engine)); if (cap->rq) { cap->rq = active_request(cap->rq->context->timeline, cap->rq); cap->rq = i915_request_get_rcu(cap->rq); @@ -2891,10 +3036,14 @@ static void __submit_queue_imm(struct intel_engine_cs *engine) if (reset_in_progress(execlists)) return; /* defer until we restart the engine following reset */ - if (execlists->tasklet.func == execlists_submission_tasklet) - __execlists_submission_tasklet(engine); - else - tasklet_hi_schedule(&execlists->tasklet); + /* Hopefully we clear execlists->pending[] to let us through */ + if (READ_ONCE(execlists->pending[0]) && + tasklet_trylock(&execlists->tasklet)) { + process_csb(engine); + tasklet_unlock(&execlists->tasklet); + } + + __execlists_submission_tasklet(engine); } static void submit_queue(struct intel_engine_cs *engine, @@ -2980,7 +3129,7 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine) vaddr += engine->context_size; if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE)) - dev_err_once(engine->i915->drm.dev, + drm_err_once(&engine->i915->drm, "%s context redzone overwritten!\n", engine->name); } @@ -3432,7 +3581,8 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine) ret = lrc_setup_wa_ctx(engine); if (ret) { - DRM_DEBUG_DRIVER("Failed to setup context WA page: %d\n", ret); + drm_dbg(&engine->i915->drm, + "Failed to setup context WA page: %d\n", ret); return ret; } @@ -3475,7 +3625,7 @@ static void enable_error_interrupt(struct intel_engine_cs *engine) status = ENGINE_READ(engine, RING_ESR); if (unlikely(status)) { - dev_err(engine->i915->drm.dev, + drm_err(&engine->i915->drm, "engine '%s' resumed still in error: %08x\n", engine->name, status); __intel_gt_reset(engine->gt, engine->mask); @@ -3539,7 +3689,8 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine) bool unexpected = false; if (ENGINE_READ_FW(engine, RING_MI_MODE) & STOP_RING) { - DRM_DEBUG_DRIVER("STOP_RING still set in RING_MI_MODE\n"); + drm_dbg(&engine->i915->drm, + "STOP_RING still set in RING_MI_MODE\n"); unexpected = true; } @@ -3599,6 +3750,7 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine) * * FIXME: Wa for more modern gens needs to be validated */ + ring_set_paused(engine, 1); intel_engine_stop_cs(engine); } @@ -4439,6 +4591,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift; + engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4483,7 +4636,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) * because we only expect rare glitches but nothing * critical to prevent us from using GPU */ - DRM_ERROR("WA batch buffer initialization failed\n"); + drm_err(&i915->drm, "WA batch buffer initialization failed\n"); if (HAS_LOGICAL_RING_ELSQ(i915)) { execlists->submit_reg = uncore->regs + @@ -4565,6 +4718,7 @@ static void init_common_reg_state(u32 * const regs, regs[CTX_CONTEXT_CONTROL] = ctl; regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID; + regs[CTX_TIMESTAMP] = 0; } static void init_wa_bb_reg_state(u32 * const regs, @@ -4658,7 +4812,8 @@ populate_lr_context(struct intel_context *ce, vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB); if (IS_ERR(vaddr)) { ret = PTR_ERR(vaddr); - DRM_DEBUG_DRIVER("Could not map object pages! (%d)\n", ret); + drm_dbg(&engine->i915->drm, + "Could not map object pages! (%d)\n", ret); return ret; } @@ -4751,7 +4906,8 @@ static int __execlists_context_alloc(struct intel_context *ce, ret = populate_lr_context(ce, ctx_obj, engine, ring); if (ret) { - DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret); + drm_dbg(&engine->i915->drm, + "Failed to populate LRC: %d\n", ret); goto error_ring_free; } @@ -4804,6 +4960,8 @@ static void virtual_context_destroy(struct kref *kref) __execlists_context_fini(&ve->context); intel_context_fini(&ve->context); + intel_engine_free_request_pool(&ve->base); + kfree(ve->bonds); kfree(ve); } @@ -4984,10 +5142,8 @@ static void virtual_submission_tasklet(unsigned long data) submit_engine: GEM_BUG_ON(RB_EMPTY_NODE(&node->rb)); node->prio = prio; - if (first && prio > sibling->execlists.queue_priority_hint) { - sibling->execlists.queue_priority_hint = prio; + if (first && prio > sibling->execlists.queue_priority_hint) tasklet_hi_schedule(&sibling->execlists.tasklet); - } spin_unlock(&sibling->active.lock); } diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 66c07c32745c..1c1923ec8be7 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -246,16 +246,18 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6) ret = sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS, &rc6vids, NULL); if (IS_GEN(i915, 6) && ret) { - DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n"); + drm_dbg(&i915->drm, "Couldn't check for BIOS workaround\n"); } else if (IS_GEN(i915, 6) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) { - DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n", - GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450); + drm_dbg(&i915->drm, + "You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n", + GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450); rc6vids &= 0xffff00; rc6vids |= GEN6_ENCODE_RC6_VID(450); ret = sandybridge_pcode_write(i915, GEN6_PCODE_WRITE_RC6VIDS, rc6vids); if (ret) - DRM_ERROR("Couldn't fix incorrect rc6 voltage\n"); + drm_err(&i915->drm, + "Couldn't fix incorrect rc6 voltage\n"); } } @@ -263,14 +265,15 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6) static int chv_rc6_init(struct intel_rc6 *rc6) { struct intel_uncore *uncore = rc6_to_uncore(rc6); + struct drm_i915_private *i915 = rc6_to_i915(rc6); resource_size_t pctx_paddr, paddr; resource_size_t pctx_size = 32 * SZ_1K; u32 pcbr; pcbr = intel_uncore_read(uncore, VLV_PCBR); if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) { - DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n"); - paddr = rc6_to_i915(rc6)->dsm.end + 1 - pctx_size; + drm_dbg(&i915->drm, "BIOS didn't set up PCBR, fixing up\n"); + paddr = i915->dsm.end + 1 - pctx_size; GEM_BUG_ON(paddr > U32_MAX); pctx_paddr = (paddr & ~4095); @@ -304,7 +307,7 @@ static int vlv_rc6_init(struct intel_rc6 *rc6) goto out; } - DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n"); + drm_dbg(&i915->drm, "BIOS didn't set up PCBR, fixing up\n"); /* * From the Gunit register HAS: @@ -316,7 +319,8 @@ static int vlv_rc6_init(struct intel_rc6 *rc6) */ pctx = i915_gem_object_create_stolen(i915, pctx_size); if (IS_ERR(pctx)) { - DRM_DEBUG("not enough stolen space for PCTX, disabling\n"); + drm_dbg(&i915->drm, + "not enough stolen space for PCTX, disabling\n"); return PTR_ERR(pctx); } @@ -398,14 +402,14 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6) rc_sw_target = intel_uncore_read(uncore, GEN6_RC_STATE); rc_sw_target &= RC_SW_TARGET_STATE_MASK; rc_sw_target >>= RC_SW_TARGET_STATE_SHIFT; - DRM_DEBUG_DRIVER("BIOS enabled RC states: " + drm_dbg(&i915->drm, "BIOS enabled RC states: " "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n", onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE), onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE), rc_sw_target); if (!(intel_uncore_read(uncore, RC6_LOCATION) & RC6_CTX_IN_DRAM)) { - DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n"); + drm_dbg(&i915->drm, "RC6 Base location not set properly.\n"); enable_rc6 = false; } @@ -417,7 +421,7 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6) intel_uncore_read(uncore, RC6_CTX_BASE) & RC6_CTX_BASE_MASK; if (!(rc6_ctx_base >= i915->dsm_reserved.start && rc6_ctx_base + PAGE_SIZE < i915->dsm_reserved.end)) { - DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n"); + drm_dbg(&i915->drm, "RC6 Base address not as expected.\n"); enable_rc6 = false; } @@ -425,24 +429,25 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6) (intel_uncore_read(uncore, PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1 && (intel_uncore_read(uncore, PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1 && (intel_uncore_read(uncore, PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1)) { - DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n"); + drm_dbg(&i915->drm, + "Engine Idle wait time not set properly.\n"); enable_rc6 = false; } if (!intel_uncore_read(uncore, GEN8_PUSHBUS_CONTROL) || !intel_uncore_read(uncore, GEN8_PUSHBUS_ENABLE) || !intel_uncore_read(uncore, GEN8_PUSHBUS_SHIFT)) { - DRM_DEBUG_DRIVER("Pushbus not setup properly.\n"); + drm_dbg(&i915->drm, "Pushbus not setup properly.\n"); enable_rc6 = false; } if (!intel_uncore_read(uncore, GEN6_GFXPAUSE)) { - DRM_DEBUG_DRIVER("GFX pause not setup properly.\n"); + drm_dbg(&i915->drm, "GFX pause not setup properly.\n"); enable_rc6 = false; } if (!intel_uncore_read(uncore, GEN8_MISC_CTRL0)) { - DRM_DEBUG_DRIVER("GPM control not setup properly.\n"); + drm_dbg(&i915->drm, "GPM control not setup properly.\n"); enable_rc6 = false; } @@ -463,7 +468,7 @@ static bool rc6_supported(struct intel_rc6 *rc6) return false; if (IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(rc6)) { - dev_notice(i915->drm.dev, + drm_notice(&i915->drm, "RC6 and powersaving disabled by BIOS\n"); return false; } @@ -495,7 +500,7 @@ static bool pctx_corrupted(struct intel_rc6 *rc6) if (intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO)) return false; - dev_notice(i915->drm.dev, + drm_notice(&i915->drm, "RC6 context corruption, disabling runtime power management\n"); return true; } @@ -603,6 +608,7 @@ void intel_rc6_unpark(struct intel_rc6 *rc6) void intel_rc6_park(struct intel_rc6 *rc6) { struct intel_uncore *uncore = rc6_to_uncore(rc6); + unsigned int target; if (!rc6->enabled) return; @@ -617,7 +623,14 @@ void intel_rc6_park(struct intel_rc6 *rc6) /* Turn off the HW timers and go directly to rc6 */ set(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE); - set(uncore, GEN6_RC_STATE, 0x4 << RC_SW_TARGET_STATE_SHIFT); + + if (HAS_RC6pp(rc6_to_i915(rc6))) + target = 0x6; /* deepest rc6 */ + else if (HAS_RC6p(rc6_to_i915(rc6))) + target = 0x5; /* deep rc6 */ + else + target = 0x4; /* normal rc6 */ + set(uncore, GEN6_RC_STATE, target << RC_SW_TARGET_STATE_SHIFT); } void intel_rc6_disable(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c index 5954ecc3207f..26e78db33675 100644 --- a/drivers/gpu/drm/i915/gt/intel_renderstate.c +++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c @@ -102,7 +102,7 @@ static int render_state_setup(struct intel_renderstate *so, } if (rodata->reloc[reloc_index] != -1) { - DRM_ERROR("only %d relocs resolved\n", reloc_index); + drm_err(&i915->drm, "only %d relocs resolved\n", reloc_index); goto err; } diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 8b170c1876b3..39070b514e65 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -88,6 +88,11 @@ static bool mark_guilty(struct i915_request *rq) bool banned; int i; + if (intel_context_is_closed(rq->context)) { + intel_context_set_banned(rq->context); + return true; + } + rcu_read_lock(); ctx = rcu_dereference(rq->context->gem_context); if (ctx && !kref_get_unless_zero(&ctx->ref)) @@ -104,7 +109,7 @@ static bool mark_guilty(struct i915_request *rq) goto out; } - dev_notice(ctx->i915->drm.dev, + drm_notice(&ctx->i915->drm, "%s context reset due to GPU hang\n", ctx->name); @@ -750,7 +755,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) for_each_engine(engine, gt, id) __intel_engine_reset(engine, stalled_mask & engine->mask); - i915_gem_restore_fences(gt->ggtt); + intel_ggtt_restore_fences(gt->ggtt); return err; } @@ -1026,7 +1031,7 @@ void intel_gt_reset(struct intel_gt *gt, goto unlock; if (reason) - dev_notice(gt->i915->drm.dev, + drm_notice(>->i915->drm, "Resetting chip for %s\n", reason); atomic_inc(>->i915->gpu_error.reset_count); @@ -1034,7 +1039,7 @@ void intel_gt_reset(struct intel_gt *gt, if (!intel_has_gpu_reset(gt)) { if (i915_modparams.reset) - dev_err(gt->i915->drm.dev, "GPU reset not supported\n"); + drm_err(>->i915->drm, "GPU reset not supported\n"); else drm_dbg(>->i915->drm, "GPU reset disabled\n"); goto error; @@ -1044,7 +1049,7 @@ void intel_gt_reset(struct intel_gt *gt, intel_runtime_pm_disable_interrupts(gt->i915); if (do_reset(gt, stalled_mask)) { - dev_err(gt->i915->drm.dev, "Failed to reset chip\n"); + drm_err(>->i915->drm, "Failed to reset chip\n"); goto taint; } @@ -1106,7 +1111,7 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine) /** * intel_engine_reset - reset GPU engine to recover from a hang * @engine: engine to reset - * @msg: reason for GPU reset; or NULL for no dev_notice() + * @msg: reason for GPU reset; or NULL for no drm_notice() * * Reset a specific GPU engine. Useful if a hang is detected. * Returns zero on successful reset or otherwise an error code. @@ -1131,7 +1136,7 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg) reset_prepare_engine(engine); if (msg) - dev_notice(engine->i915->drm.dev, + drm_notice(&engine->i915->drm, "Resetting %s for %s\n", engine->name, msg); atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); @@ -1376,7 +1381,7 @@ static void intel_wedge_me(struct work_struct *work) { struct intel_wedge_me *w = container_of(work, typeof(*w), work.work); - dev_err(w->gt->i915->drm.dev, + drm_err(&w->gt->i915->drm, "%s timed out, cancelling all in-flight rendering.\n", w->name); intel_gt_set_wedged(w->gt); diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h index 5bdce24994aa..cc0ebca65167 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.h +++ b/drivers/gpu/drm/i915/gt/intel_ring.h @@ -88,6 +88,8 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr) static inline void assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail) { + unsigned int head = READ_ONCE(ring->head); + GEM_BUG_ON(!intel_ring_offset_valid(ring, tail)); /* @@ -105,8 +107,7 @@ assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail) * into the same cacheline as ring->head. */ #define cacheline(a) round_down(a, CACHELINE_BYTES) - GEM_BUG_ON(cacheline(tail) == cacheline(ring->head) && - tail < ring->head); + GEM_BUG_ON(cacheline(tail) == cacheline(head) && tail < head); #undef cacheline } diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 1424582e4a9b..d015f7b8b28e 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -577,8 +577,9 @@ static void flush_cs_tlb(struct intel_engine_cs *engine) RING_INSTPM(engine->mmio_base), INSTPM_SYNC_FLUSH, 0, 1000)) - DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n", - engine->name); + drm_err(&dev_priv->drm, + "%s: wait for SyncFlush to complete for TLB invalidation timed out\n", + engine->name); } static void ring_setup_status_page(struct intel_engine_cs *engine) @@ -601,8 +602,9 @@ static bool stop_ring(struct intel_engine_cs *engine) MODE_IDLE, MODE_IDLE, 1000)) { - DRM_ERROR("%s : timed out trying to stop ring\n", - engine->name); + drm_err(&dev_priv->drm, + "%s : timed out trying to stop ring\n", + engine->name); /* * Sometimes we observe that the idle flag is not @@ -661,22 +663,23 @@ static int xcs_resume(struct intel_engine_cs *engine) /* WaClearRingBufHeadRegAtInit:ctg,elk */ if (!stop_ring(engine)) { /* G45 ring initialization often fails to reset head to zero */ - DRM_DEBUG_DRIVER("%s head not reset to zero " + drm_dbg(&dev_priv->drm, "%s head not reset to zero " + "ctl %08x head %08x tail %08x start %08x\n", + engine->name, + ENGINE_READ(engine, RING_CTL), + ENGINE_READ(engine, RING_HEAD), + ENGINE_READ(engine, RING_TAIL), + ENGINE_READ(engine, RING_START)); + + if (!stop_ring(engine)) { + drm_err(&dev_priv->drm, + "failed to set %s head to zero " "ctl %08x head %08x tail %08x start %08x\n", engine->name, ENGINE_READ(engine, RING_CTL), ENGINE_READ(engine, RING_HEAD), ENGINE_READ(engine, RING_TAIL), ENGINE_READ(engine, RING_START)); - - if (!stop_ring(engine)) { - DRM_ERROR("failed to set %s head to zero " - "ctl %08x head %08x tail %08x start %08x\n", - engine->name, - ENGINE_READ(engine, RING_CTL), - ENGINE_READ(engine, RING_HEAD), - ENGINE_READ(engine, RING_TAIL), - ENGINE_READ(engine, RING_START)); ret = -EIO; goto out; } @@ -719,7 +722,7 @@ static int xcs_resume(struct intel_engine_cs *engine) RING_CTL(engine->mmio_base), RING_VALID, RING_VALID, 50)) { - DRM_ERROR("%s initialization failed " + drm_err(&dev_priv->drm, "%s initialization failed " "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", engine->name, ENGINE_READ(engine, RING_CTL), @@ -2088,7 +2091,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine) GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma); - if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) { + if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) { err = gen7_ctx_switch_bb_init(engine); if (err) goto err_ring_unpin; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 87f9638d2cbf..4dcfae16a7ce 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -81,13 +81,14 @@ static void rps_enable_interrupts(struct intel_rps *rps) events = (GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT); - WRITE_ONCE(rps->pm_events, events); + spin_lock_irq(>->irq_lock); 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) @@ -120,7 +121,9 @@ static void rps_disable_interrupts(struct intel_rps *rps) struct intel_gt *gt = rps_to_gt(rps); WRITE_ONCE(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); @@ -183,14 +186,12 @@ static void gen5_rps_init(struct intel_rps *rps) fmin = (rgvmodectl & MEMMODE_FMIN_MASK); fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT; - DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n", - fmax, fmin, fstart); + drm_dbg(&i915->drm, "fmax: %d, fmin: %d, fstart: %d\n", + fmax, fmin, fstart); rps->min_freq = fmax; + rps->efficient_freq = fstart; rps->max_freq = fmin; - - rps->idle_freq = rps->min_freq; - rps->cur_freq = rps->idle_freq; } static unsigned long @@ -453,7 +454,8 @@ static bool gen5_rps_enable(struct intel_rps *rps) if (wait_for_atomic((intel_uncore_read(uncore, MEMSWCTL) & MEMCTL_CMD_STS) == 0, 10)) - DRM_ERROR("stuck trying to change perf mode\n"); + drm_err(&uncore->i915->drm, + "stuck trying to change perf mode\n"); mdelay(1); gen5_rps_set(rps, rps->cur_freq); @@ -712,8 +714,6 @@ static int rps_set(struct intel_rps *rps, u8 val, bool update) void intel_rps_unpark(struct intel_rps *rps) { - u8 freq; - if (!rps->enabled) return; @@ -725,9 +725,10 @@ void intel_rps_unpark(struct intel_rps *rps) WRITE_ONCE(rps->active, true); - freq = max(rps->cur_freq, rps->efficient_freq), - freq = clamp(freq, rps->min_freq_softlimit, rps->max_freq_softlimit); - intel_rps_set(rps, freq); + intel_rps_set(rps, + clamp(rps->cur_freq, + rps->min_freq_softlimit, + rps->max_freq_softlimit)); rps->last_adj = 0; @@ -770,6 +771,19 @@ 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) @@ -880,12 +894,13 @@ static void gen6_rps_init(struct intel_rps *rps) static bool rps_reset(struct intel_rps *rps) { + struct drm_i915_private *i915 = rps_to_i915(rps); /* force a reset */ rps->power.mode = -1; rps->last_freq = -1; if (rps_set(rps, rps->min_freq, true)) { - DRM_ERROR("Failed to reset RPS to initial values\n"); + drm_err(&i915->drm, "Failed to reset RPS to initial values\n"); return false; } @@ -1036,8 +1051,8 @@ static bool chv_rps_enable(struct intel_rps *rps) drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0, "GPLL not enabled\n"); - DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE)); - DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val); + drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE)); + drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val); return rps_reset(rps); } @@ -1134,8 +1149,8 @@ static bool vlv_rps_enable(struct intel_rps *rps) drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0, "GPLL not enabled\n"); - DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE)); - DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val); + drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE)); + drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val); return rps_reset(rps); } @@ -1292,7 +1307,8 @@ static void vlv_init_gpll_ref_freq(struct intel_rps *rps) CCK_GPLL_CLOCK_CONTROL, i915->czclk_freq); - DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n", rps->gpll_ref_freq); + drm_dbg(&i915->drm, "GPLL reference freq: %d kHz\n", + rps->gpll_ref_freq); } static void vlv_rps_init(struct intel_rps *rps) @@ -1320,28 +1336,24 @@ static void vlv_rps_init(struct intel_rps *rps) i915->mem_freq = 1333; break; } - DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq); + drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq); rps->max_freq = vlv_rps_max_freq(rps); rps->rp0_freq = rps->max_freq; - DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->max_freq), - rps->max_freq); + drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->max_freq), rps->max_freq); rps->efficient_freq = vlv_rps_rpe_freq(rps); - DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->efficient_freq), - rps->efficient_freq); + drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq); rps->rp1_freq = vlv_rps_guar_freq(rps); - DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->rp1_freq), - rps->rp1_freq); + drm_dbg(&i915->drm, "RP1(Guar Freq) GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq); rps->min_freq = vlv_rps_min_freq(rps); - DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->min_freq), - rps->min_freq); + drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->min_freq), rps->min_freq); vlv_iosf_sb_put(i915, BIT(VLV_IOSF_SB_PUNIT) | @@ -1371,28 +1383,24 @@ static void chv_rps_init(struct intel_rps *rps) i915->mem_freq = 1600; break; } - DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq); + drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq); rps->max_freq = chv_rps_max_freq(rps); rps->rp0_freq = rps->max_freq; - DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->max_freq), - rps->max_freq); + drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->max_freq), rps->max_freq); rps->efficient_freq = chv_rps_rpe_freq(rps); - DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->efficient_freq), - rps->efficient_freq); + drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq); rps->rp1_freq = chv_rps_guar_freq(rps); - DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->rp1_freq), - rps->rp1_freq); + drm_dbg(&i915->drm, "RP1(Guar) GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq); rps->min_freq = chv_rps_min_freq(rps); - DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n", - intel_gpu_freq(rps, rps->min_freq), - rps->min_freq); + drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n", + intel_gpu_freq(rps, rps->min_freq), rps->min_freq); vlv_iosf_sb_put(i915, BIT(VLV_IOSF_SB_PUNIT) | @@ -1455,6 +1463,7 @@ static void rps_work(struct work_struct *work) { struct intel_rps *rps = container_of(work, typeof(*rps), work); struct intel_gt *gt = rps_to_gt(rps); + struct drm_i915_private *i915 = rps_to_i915(rps); bool client_boost = false; int new_freq, adj, min, max; u32 pm_iir = 0; @@ -1530,7 +1539,7 @@ static void rps_work(struct work_struct *work) new_freq = clamp_t(int, new_freq, min, max); if (intel_rps_set(rps, new_freq)) { - DRM_DEBUG_DRIVER("Failed to set new GPU frequency\n"); + drm_dbg(&i915->drm, "Failed to set new GPU frequency\n"); rps->last_adj = 0; } @@ -1652,9 +1661,10 @@ void intel_rps_init(struct intel_rps *rps) sandybridge_pcode_read(i915, GEN6_READ_OC_PARAMS, ¶ms, NULL); if (params & BIT(31)) { /* OC supported */ - DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n", - (rps->max_freq & 0xff) * 50, - (params & 0xff) * 50); + drm_dbg(&i915->drm, + "Overclocking supported, max: %dMHz, overclock: %dMHz\n", + (rps->max_freq & 0xff) * 50, + (params & 0xff) * 50); rps->max_freq = params & 0xff; } } @@ -1662,7 +1672,9 @@ void intel_rps_init(struct intel_rps *rps) /* Finally allow us to boost to max by default */ rps->boost_freq = rps->max_freq; rps->idle_freq = rps->min_freq; - rps->cur_freq = rps->idle_freq; + + /* Start in the middle, from here we will autotune based on workload */ + rps->cur_freq = rps->efficient_freq; rps->pm_intrmsk_mbz = 0; @@ -1914,3 +1926,7 @@ bool i915_gpu_turbo_disable(void) return ret; } EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable); + +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#include "selftest_rps.c" +#endif diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index 74f793423231..d173271c7397 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -65,7 +65,6 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915, { const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu; bool subslice_pg = sseu->has_subslice_pg; - struct intel_sseu ctx_sseu; u8 slices, subslices; u32 rpcs = 0; @@ -78,31 +77,13 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915, /* * If i915/perf is active, we want a stable powergating configuration - * on the system. - * - * We could choose full enablement, but on ICL we know there are use - * cases which disable slices for functional, apart for performance - * reasons. So in this case we select a known stable subset. + * on the system. Use the configuration pinned by i915/perf. */ - if (!i915->perf.exclusive_stream) { - ctx_sseu = *req_sseu; - } else { - ctx_sseu = intel_sseu_from_device_info(sseu); - - if (IS_GEN(i915, 11)) { - /* - * We only need subslice count so it doesn't matter - * which ones we select - just turn off low bits in the - * amount of half of all available subslices per slice. - */ - ctx_sseu.subslice_mask = - ~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2)); - ctx_sseu.slice_mask = 0x1; - } - } + if (i915->perf.exclusive_stream) + req_sseu = &i915->perf.sseu; - slices = hweight8(ctx_sseu.slice_mask); - subslices = hweight8(ctx_sseu.subslice_mask); + slices = hweight8(req_sseu->slice_mask); + subslices = hweight8(req_sseu->subslice_mask); /* * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits @@ -175,13 +156,13 @@ u32 intel_sseu_make_rpcs(struct drm_i915_private *i915, if (sseu->has_eu_pg) { u32 val; - val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT; + val = req_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT; GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK); val &= GEN8_RPCS_EU_MIN_MASK; rpcs |= val; - val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT; + val = req_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT; GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK); val &= GEN8_RPCS_EU_MAX_MASK; diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 91debbc97c9a..3779c2ae0d65 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -119,6 +119,15 @@ static void __idle_hwsp_free(struct intel_timeline_hwsp *hwsp, int cacheline) spin_unlock_irqrestore(>->hwsp_lock, flags); } +static void __rcu_cacheline_free(struct rcu_head *rcu) +{ + struct intel_timeline_cacheline *cl = + container_of(rcu, typeof(*cl), rcu); + + i915_active_fini(&cl->active); + kfree(cl); +} + static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) { GEM_BUG_ON(!i915_active_is_idle(&cl->active)); @@ -127,8 +136,7 @@ static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) i915_vma_put(cl->hwsp->vma); __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); - i915_active_fini(&cl->active); - kfree_rcu(cl, rcu); + call_rcu(&cl->rcu, __rcu_cacheline_free); } __i915_active_call diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 5176ad1a3976..adddc5c93b48 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -837,7 +837,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3) & GEN10_L3BANK_MASK; - DRM_DEBUG_DRIVER("L3 fuse = %x\n", l3_fuse); + drm_dbg(&i915->drm, "L3 fuse = %x\n", l3_fuse); l3_en = ~(l3_fuse << GEN10_L3BANK_PAIR_COUNT | l3_fuse); } else { l3_en = ~0; @@ -846,7 +846,8 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) slice = fls(sseu->slice_mask) - 1; subslice = fls(l3_en & intel_sseu_get_subslices(sseu, slice)); if (!subslice) { - DRM_WARN("No common index found between subslice mask %x and L3 bank mask %x!\n", + drm_warn(&i915->drm, + "No common index found between subslice mask %x and L3 bank mask %x!\n", intel_sseu_get_subslices(sseu, slice), l3_en); subslice = fls(l3_en); drm_WARN_ON(&i915->drm, !subslice); @@ -861,7 +862,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) mcr_mask = GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK; } - DRM_DEBUG_DRIVER("MCR slice/subslice = %x\n", mcr); + drm_dbg(&i915->drm, "MCR slice/subslice = %x\n", mcr); wa_write_masked_or(wal, GEN8_MCR_SELECTOR, mcr_mask, mcr); } @@ -942,6 +943,8 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) static void tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) { + wa_init_mcr(i915, wal); + /* Wa_1409420604:tgl */ if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) wa_write_or(wal, @@ -1379,12 +1382,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); - /* - * Wa_1409085225:tgl - * Wa_14010229206:tgl - */ - wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); - /* Wa_1408615072:tgl */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, VSUNIT_CLKGATE_DIS_TGL); @@ -1402,6 +1399,12 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_masked_en(wal, GEN9_CS_DEBUG_MODE1, FF_DOP_CLOCK_GATE_DISABLE); + + /* + * Wa_1409085225:tgl + * Wa_14010229206:tgl + */ + wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); } if (IS_GEN(i915, 11)) { diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index 09ff8e4f88af..c50bb502fe03 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -7,6 +7,7 @@ #include "selftest_llc.h" #include "selftest_rc6.h" +#include "selftest_rps.h" static int live_gt_resume(void *arg) { @@ -52,6 +53,7 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(live_rc6_manual), + SUBTEST(live_rps_interrupt), SUBTEST(live_gt_resume), }; diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 6f06ba750a0a..6f5e35afe1b2 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -68,26 +68,41 @@ static void engine_heartbeat_enable(struct intel_engine_cs *engine, engine->props.heartbeat_interval_ms = saved; } +static bool is_active(struct i915_request *rq) +{ + if (i915_request_is_active(rq)) + return true; + + if (i915_request_on_hold(rq)) + return true; + + if (i915_request_started(rq)) + return true; + + return false; +} + static int wait_for_submit(struct intel_engine_cs *engine, struct i915_request *rq, unsigned long timeout) { timeout += jiffies; do { - cond_resched(); - intel_engine_flush_submission(engine); - - if (READ_ONCE(engine->execlists.pending[0])) - continue; + bool done = time_after(jiffies, timeout); - if (i915_request_is_active(rq)) + if (i915_request_completed(rq)) /* that was quick! */ return 0; - if (i915_request_started(rq)) /* that was quick! */ + /* Wait until the HW has acknowleged the submission (or err) */ + intel_engine_flush_submission(engine); + if (!READ_ONCE(engine->execlists.pending[0]) && is_active(rq)) return 0; - } while (time_before(jiffies, timeout)); - return -ETIME; + if (done) + return -ETIME; + + cond_resched(); + } while (1); } static int wait_for_reset(struct intel_engine_cs *engine, @@ -634,9 +649,9 @@ static int live_error_interrupt(void *arg) error_repr(p->error[i])); if (!i915_request_started(client[i])) { - pr_debug("%s: %s request not stated!\n", - engine->name, - error_repr(p->error[i])); + pr_err("%s: %s request not started!\n", + engine->name, + error_repr(p->error[i])); err = -ETIME; goto out; } @@ -644,9 +659,10 @@ static int live_error_interrupt(void *arg) /* Kick the tasklet to process the error */ intel_engine_flush_submission(engine); if (client[i]->fence.error != p->error[i]) { - pr_err("%s: %s request completed with wrong error code: %d\n", + pr_err("%s: %s request (%s) with wrong error code: %d\n", engine->name, error_repr(p->error[i]), + i915_request_completed(client[i]) ? "completed" : "running", client[i]->fence.error); err = -EINVAL; goto out; @@ -929,7 +945,7 @@ create_rewinder(struct intel_context *ce, goto err; } - cs = intel_ring_begin(rq, 10); + cs = intel_ring_begin(rq, 14); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err; @@ -941,8 +957,8 @@ create_rewinder(struct intel_context *ce, *cs++ = MI_SEMAPHORE_WAIT | MI_SEMAPHORE_GLOBAL_GTT | MI_SEMAPHORE_POLL | - MI_SEMAPHORE_SAD_NEQ_SDD; - *cs++ = 0; + MI_SEMAPHORE_SAD_GTE_SDD; + *cs++ = idx; *cs++ = offset; *cs++ = 0; @@ -951,6 +967,11 @@ create_rewinder(struct intel_context *ce, *cs++ = offset + idx * sizeof(u32); *cs++ = 0; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = offset; + *cs++ = 0; + *cs++ = idx + 1; + intel_ring_advance(rq, cs); rq->sched.attr.priority = I915_PRIORITY_MASK; @@ -984,7 +1005,7 @@ static int live_timeslice_rewind(void *arg) for_each_engine(engine, gt, id) { enum { A1, A2, B1 }; - enum { X = 1, Y, Z }; + enum { X = 1, Z, Y }; struct i915_request *rq[3] = {}; struct intel_context *ce; unsigned long heartbeat; @@ -1017,13 +1038,13 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[0] = create_rewinder(ce, NULL, slot, 1); + rq[0] = create_rewinder(ce, NULL, slot, X); if (IS_ERR(rq[0])) { intel_context_put(ce); goto err; } - rq[1] = create_rewinder(ce, NULL, slot, 2); + rq[1] = create_rewinder(ce, NULL, slot, Y); intel_context_put(ce); if (IS_ERR(rq[1])) goto err; @@ -1041,7 +1062,7 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[2] = create_rewinder(ce, rq[0], slot, 3); + rq[2] = create_rewinder(ce, rq[0], slot, Z); intel_context_put(ce); if (IS_ERR(rq[2])) goto err; @@ -1052,18 +1073,14 @@ static int live_timeslice_rewind(void *arg) engine->name); goto err; } - GEM_BUG_ON(!timer_pending(&engine->execlists.timer)); /* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */ - GEM_BUG_ON(!i915_request_is_active(rq[A1])); - GEM_BUG_ON(!i915_request_is_active(rq[A2])); - GEM_BUG_ON(!i915_request_is_active(rq[B1])); - - /* Wait for the timeslice to kick in */ - del_timer(&engine->execlists.timer); - tasklet_hi_schedule(&engine->execlists.tasklet); - intel_engine_flush_submission(engine); - + if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */ + /* Wait for the timeslice to kick in */ + del_timer(&engine->execlists.timer); + tasklet_hi_schedule(&engine->execlists.tasklet); + intel_engine_flush_submission(engine); + } /* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */ GEM_BUG_ON(!i915_request_is_active(rq[A1])); GEM_BUG_ON(!i915_request_is_active(rq[B1])); @@ -1228,8 +1245,14 @@ static int live_timeslice_queue(void *arg) if (err) goto err_rq; - intel_engine_flush_submission(engine); + /* Wait until we ack the release_queue and start timeslicing */ + do { + cond_resched(); + intel_engine_flush_submission(engine); + } while (READ_ONCE(engine->execlists.pending[0])); + if (!READ_ONCE(engine->execlists.timer.expires) && + execlists_active(&engine->execlists) == rq && !i915_request_completed(rq)) { struct drm_printer p = drm_info_printer(gt->i915->drm.dev); @@ -2030,6 +2053,9 @@ static int __cancel_hostile(struct live_preempt_cancel *arg) if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) return 0; + if (!intel_has_reset_engine(arg->engine->gt)) + return 0; + GEM_TRACE("%s(%s)\n", __func__, arg->engine->name); rq = spinner_create_request(&arg->a.spin, arg->a.ctx, arg->engine, @@ -2630,7 +2656,7 @@ static int create_gang(struct intel_engine_cs *engine, if (IS_ERR(rq)) goto err_obj; - rq->batch = vma; + rq->batch = i915_vma_get(vma); i915_request_get(rq); i915_vma_lock(vma); @@ -2654,6 +2680,7 @@ static int create_gang(struct intel_engine_cs *engine, return 0; err_rq: + i915_vma_put(rq->batch); i915_request_put(rq); err_obj: i915_gem_object_put(obj); @@ -2750,6 +2777,7 @@ static int live_preempt_gang(void *arg) err = -ETIME; } + i915_vma_put(rq->batch); i915_request_put(rq); rq = n; } @@ -5155,7 +5183,6 @@ static int compare_isolation(struct intel_engine_cs *engine, A[0][x], B[0][x], B[1][x], poison, lrc[dw + 1]); err = -EINVAL; - break; } } dw += 2; @@ -5294,6 +5321,7 @@ static int live_lrc_isolation(void *arg) 0xffffffff, 0xffff0000, }; + int err = 0; /* * Our goal is try and verify that per-context state cannot be @@ -5304,7 +5332,6 @@ static int live_lrc_isolation(void *arg) */ for_each_engine(engine, gt, id) { - int err = 0; int i; /* Just don't even ask */ @@ -5315,23 +5342,25 @@ static int live_lrc_isolation(void *arg) intel_engine_pm_get(engine); if (engine->pinned_default_state) { for (i = 0; i < ARRAY_SIZE(poison); i++) { - err = __lrc_isolation(engine, poison[i]); - if (err) - break; + int result; - err = __lrc_isolation(engine, ~poison[i]); - if (err) - break; + result = __lrc_isolation(engine, poison[i]); + if (result && !err) + err = result; + + result = __lrc_isolation(engine, ~poison[i]); + if (result && !err) + err = result; } } intel_engine_pm_put(engine); - if (igt_flush_test(gt->i915)) + if (igt_flush_test(gt->i915)) { err = -EIO; - if (err) - return err; + break; + } } - return 0; + return err; } static void garbage_reset(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index 5f7e2dcf5686..08c3dbd41b12 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -12,11 +12,44 @@ #include "selftests/i915_random.h" +static u64 energy_uJ(struct intel_rc6 *rc6) +{ + unsigned long long power; + u32 units; + + if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &power)) + return 0; + + units = (power & 0x1f00) >> 8; + + if (rdmsrl_safe(MSR_PP1_ENERGY_STATUS, &power)) + return 0; + + return (1000000 * power) >> units; /* convert to uJ */ +} + +static u64 rc6_residency(struct intel_rc6 *rc6) +{ + u64 result; + + /* XXX VLV_GT_MEDIA_RC6? */ + + result = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + if (HAS_RC6p(rc6_to_i915(rc6))) + result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6p); + if (HAS_RC6pp(rc6_to_i915(rc6))) + result += intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6pp); + + return result; +} + int live_rc6_manual(void *arg) { struct intel_gt *gt = arg; struct intel_rc6 *rc6 = >->rc6; + u64 rc0_power, rc6_power; intel_wakeref_t wakeref; + ktime_t dt; u64 res[2]; int err = 0; @@ -38,9 +71,14 @@ int live_rc6_manual(void *arg) __intel_rc6_disable(rc6); msleep(1); /* wakeup is not immediate, takes about 100us on icl */ - res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + res[0] = rc6_residency(rc6); + + dt = ktime_get(); + rc0_power = energy_uJ(rc6); msleep(250); - res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + rc0_power = energy_uJ(rc6) - rc0_power; + dt = ktime_sub(ktime_get(), dt); + res[1] = rc6_residency(rc6); if ((res[1] - res[0]) >> 10) { pr_err("RC6 residency increased by %lldus while disabled for 250ms!\n", (res[1] - res[0]) >> 10); @@ -48,13 +86,24 @@ int live_rc6_manual(void *arg) goto out_unlock; } + rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, ktime_to_ns(dt)); + if (!rc0_power) { + pr_err("No power measured while in RC0\n"); + err = -EINVAL; + goto out_unlock; + } + /* Manually enter RC6 */ intel_rc6_park(rc6); - res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); + res[0] = rc6_residency(rc6); + intel_uncore_forcewake_flush(rc6_to_uncore(rc6), FORCEWAKE_ALL); + dt = ktime_get(); + rc6_power = energy_uJ(rc6); msleep(100); - res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6); - + rc6_power = energy_uJ(rc6) - rc6_power; + dt = ktime_sub(ktime_get(), dt); + res[1] = rc6_residency(rc6); if (res[1] == res[0]) { pr_err("Did not enter RC6! RC6_STATE=%08x, RC6_CONTROL=%08x, residency=%lld\n", intel_uncore_read_fw(gt->uncore, GEN6_RC_STATE), @@ -63,6 +112,15 @@ int live_rc6_manual(void *arg) err = -EINVAL; } + rc6_power = div64_u64(NSEC_PER_SEC * rc6_power, ktime_to_ns(dt)); + pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n", + rc0_power, rc6_power); + if (2 * rc6_power > rc0_power) { + pr_err("GPU leaked energy while in RC6!\n"); + err = -EINVAL; + goto out_unlock; + } + /* Restore what should have been the original state! */ intel_rc6_unpark(rc6); diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c new file mode 100644 index 000000000000..26aadc2ae3be --- /dev/null +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +#include "intel_engine_pm.h" +#include "intel_gt_pm.h" +#include "intel_rc6.h" +#include "selftest_rps.h" +#include "selftests/igt_flush_test.h" +#include "selftests/igt_spinner.h" + +static void dummy_rps_work(struct work_struct *wrk) +{ +} + +static int __rps_up_interrupt(struct intel_rps *rps, + struct intel_engine_cs *engine, + struct igt_spinner *spin) +{ + struct intel_uncore *uncore = engine->uncore; + struct i915_request *rq; + u32 timeout; + + if (!intel_engine_can_store_dword(engine)) + return 0; + + intel_gt_pm_wait_for_idle(engine->gt); + GEM_BUG_ON(rps->active); + + rps->pm_iir = 0; + rps->cur_freq = rps->min_freq; + + rq = igt_spinner_create_request(spin, engine->kernel_context, MI_NOOP); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_get(rq); + i915_request_add(rq); + + if (!igt_wait_for_spinner(spin, rq)) { + pr_err("%s: RPS spinner did not start\n", + engine->name); + i915_request_put(rq); + intel_gt_set_wedged(engine->gt); + return -EIO; + } + + if (!rps->active) { + pr_err("%s: RPS not enabled on starting spinner\n", + engine->name); + igt_spinner_end(spin); + i915_request_put(rq); + return -EINVAL; + } + + if (!(rps->pm_events & GEN6_PM_RP_UP_THRESHOLD)) { + pr_err("%s: RPS did not register UP interrupt\n", + engine->name); + i915_request_put(rq); + return -EINVAL; + } + + if (rps->last_freq != rps->min_freq) { + pr_err("%s: RPS did not program min frequency\n", + engine->name); + i915_request_put(rq); + return -EINVAL; + } + + timeout = intel_uncore_read(uncore, GEN6_RP_UP_EI); + timeout = GT_PM_INTERVAL_TO_US(engine->i915, timeout); + + usleep_range(2 * timeout, 3 * timeout); + GEM_BUG_ON(i915_request_completed(rq)); + + igt_spinner_end(spin); + i915_request_put(rq); + + if (rps->cur_freq != rps->min_freq) { + pr_err("%s: Frequency unexpectedly changed [up], now %d!\n", + engine->name, intel_rps_read_actual_frequency(rps)); + return -EINVAL; + } + + if (!(rps->pm_iir & GEN6_PM_RP_UP_THRESHOLD)) { + pr_err("%s: UP interrupt not recorded for spinner, pm_iir:%x, prev_up:%x, up_threshold:%x, up_ei:%x\n", + engine->name, rps->pm_iir, + intel_uncore_read(uncore, GEN6_RP_PREV_UP), + intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD), + intel_uncore_read(uncore, GEN6_RP_UP_EI)); + return -EINVAL; + } + + intel_gt_pm_wait_for_idle(engine->gt); + return 0; +} + +static int __rps_down_interrupt(struct intel_rps *rps, + struct intel_engine_cs *engine) +{ + struct intel_uncore *uncore = engine->uncore; + u32 timeout; + + mutex_lock(&rps->lock); + GEM_BUG_ON(!rps->active); + intel_rps_set(rps, rps->max_freq); + mutex_unlock(&rps->lock); + + if (!(rps->pm_events & GEN6_PM_RP_DOWN_THRESHOLD)) { + pr_err("%s: RPS did not register DOWN interrupt\n", + engine->name); + return -EINVAL; + } + + if (rps->last_freq != rps->max_freq) { + pr_err("%s: RPS did not program max frequency\n", + engine->name); + return -EINVAL; + } + + timeout = intel_uncore_read(uncore, GEN6_RP_DOWN_EI); + timeout = GT_PM_INTERVAL_TO_US(engine->i915, timeout); + + /* Flush any previous EI */ + usleep_range(timeout, 2 * timeout); + + /* Reset the interrupt status */ + rps_disable_interrupts(rps); + GEM_BUG_ON(rps->pm_iir); + rps_enable_interrupts(rps); + + /* And then wait for the timeout, for real this time */ + usleep_range(2 * timeout, 3 * timeout); + + if (rps->cur_freq != rps->max_freq) { + pr_err("%s: Frequency unexpectedly changed [down], now %d!\n", + engine->name, + intel_rps_read_actual_frequency(rps)); + return -EINVAL; + } + + if (!(rps->pm_iir & (GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT))) { + pr_err("%s: DOWN interrupt not recorded for idle, pm_iir:%x, prev_down:%x, down_threshold:%x, down_ei:%x [prev_up:%x, up_threshold:%x, up_ei:%x]\n", + engine->name, rps->pm_iir, + intel_uncore_read(uncore, GEN6_RP_PREV_DOWN), + intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD), + intel_uncore_read(uncore, GEN6_RP_DOWN_EI), + intel_uncore_read(uncore, GEN6_RP_PREV_UP), + intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD), + intel_uncore_read(uncore, GEN6_RP_UP_EI)); + return -EINVAL; + } + + return 0; +} + +int live_rps_interrupt(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_rps *rps = >->rps; + void (*saved_work)(struct work_struct *wrk); + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct igt_spinner spin; + u32 pm_events; + int err = 0; + + /* + * First, let's check whether or not we are receiving interrupts. + */ + + if (!rps->enabled || rps->max_freq <= rps->min_freq) + return 0; + + intel_gt_pm_get(gt); + pm_events = rps->pm_events; + intel_gt_pm_put(gt); + if (!pm_events) { + pr_err("No RPS PM events registered, but RPS is enabled?\n"); + return -ENODEV; + } + + if (igt_spinner_init(&spin, gt)) + return -ENOMEM; + + intel_gt_pm_wait_for_idle(gt); + saved_work = rps->work.func; + rps->work.func = dummy_rps_work; + + for_each_engine(engine, gt, id) { + /* Keep the engine busy with a spinner; expect an UP! */ + if (pm_events & GEN6_PM_RP_UP_THRESHOLD) { + err = __rps_up_interrupt(rps, engine, &spin); + if (err) + goto out; + } + + /* Keep the engine awake but idle and check for DOWN */ + if (pm_events & GEN6_PM_RP_DOWN_THRESHOLD) { + intel_engine_pm_get(engine); + intel_rc6_disable(>->rc6); + + err = __rps_down_interrupt(rps, engine); + + intel_rc6_enable(>->rc6); + intel_engine_pm_put(engine); + if (err) + goto out; + } + } + +out: + if (igt_flush_test(gt->i915)) + err = -EIO; + + igt_spinner_fini(&spin); + + intel_gt_pm_wait_for_idle(gt); + rps->work.func = saved_work; + + return err; +} diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.h b/drivers/gpu/drm/i915/gt/selftest_rps.h new file mode 100644 index 000000000000..abba66420996 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/selftest_rps.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef SELFTEST_RPS_H +#define SELFTEST_RPS_H + +int live_rps_interrupt(void *arg); + +#endif /* SELFTEST_RPS_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 819f09ef51fc..861657897c0f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -169,7 +169,7 @@ void intel_guc_init_early(struct intel_guc *guc) { struct drm_i915_private *i915 = guc_to_gt(guc)->i915; - intel_guc_fw_init_early(guc); + intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC); intel_guc_ct_init_early(&guc->ct); intel_guc_log_init_early(&guc->log); intel_guc_submission_init_early(guc); @@ -723,3 +723,47 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size, return 0; } + +/** + * intel_guc_load_status - dump information about GuC load status + * @guc: the GuC + * @p: the &drm_printer + * + * Pretty printer for GuC load status. + */ +void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_uncore *uncore = gt->uncore; + intel_wakeref_t wakeref; + + if (!intel_guc_is_supported(guc)) { + drm_printf(p, "GuC not supported\n"); + return; + } + + if (!intel_guc_is_wanted(guc)) { + drm_printf(p, "GuC disabled\n"); + return; + } + + intel_uc_fw_dump(&guc->fw, p); + + with_intel_runtime_pm(uncore->rpm, wakeref) { + u32 status = intel_uncore_read(uncore, GUC_STATUS); + u32 i; + + drm_printf(p, "\nGuC status 0x%08x:\n", status); + drm_printf(p, "\tBootrom status = 0x%x\n", + (status & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT); + drm_printf(p, "\tuKernel status = 0x%x\n", + (status & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT); + drm_printf(p, "\tMIA Core status = 0x%x\n", + (status & GS_MIA_MASK) >> GS_MIA_SHIFT); + drm_puts(p, "\nScratch registers:\n"); + for (i = 0; i < 16; i++) { + drm_printf(p, "\t%2d: \t0x%x\n", + i, intel_uncore_read(uncore, SOFT_SCRATCH(i))); + } + } +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 4594ccbeaa34..e84ab67b317d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -74,6 +74,11 @@ struct intel_guc { struct mutex send_mutex; }; +static inline struct intel_guc *log_to_guc(struct intel_guc_log *log) +{ + return container_of(log, struct intel_guc, log); +} + static inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len) { @@ -190,4 +195,6 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask) int intel_guc_reset_engine(struct intel_guc *guc, struct intel_engine_cs *engine); +void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p); + #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c new file mode 100644 index 000000000000..fe7cb7b29a1e --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +#include <drm/drm_print.h> + +#include "gt/debugfs_gt.h" +#include "intel_guc.h" +#include "intel_guc_debugfs.h" +#include "intel_guc_log_debugfs.h" + +static int guc_info_show(struct seq_file *m, void *data) +{ + struct intel_guc *guc = m->private; + struct drm_printer p = drm_seq_file_printer(m); + + if (!intel_guc_is_supported(guc)) + return -ENODEV; + + intel_guc_load_status(guc, &p); + drm_puts(&p, "\n"); + intel_guc_log_info(&guc->log, &p); + + /* Add more as required ... */ + + return 0; +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info); + +void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root) +{ + static const struct debugfs_gt_file files[] = { + { "guc_info", &guc_info_fops, NULL }, + }; + + if (!intel_guc_is_supported(guc)) + return; + + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), guc); + intel_guc_log_debugfs_register(&guc->log, root); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h new file mode 100644 index 000000000000..424c26665cf1 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef DEBUGFS_GUC_H +#define DEBUGFS_GUC_H + +struct intel_guc; +struct dentry; + +void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root); + +#endif /* DEBUGFS_GUC_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index 3a1c47d600ea..d4a87f4c9421 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -13,20 +13,6 @@ #include "intel_guc_fw.h" #include "i915_drv.h" -/** - * intel_guc_fw_init_early() - initializes GuC firmware struct - * @guc: intel_guc struct - * - * On platforms with GuC selects firmware for uploading - */ -void intel_guc_fw_init_early(struct intel_guc *guc) -{ - struct drm_i915_private *i915 = guc_to_gt(guc)->i915; - - intel_uc_fw_init_early(&guc->fw, INTEL_UC_FW_TYPE_GUC, HAS_GT_UC(i915), - INTEL_INFO(i915)->platform, INTEL_REVID(i915)); -} - static void guc_prepare_xfer(struct intel_uncore *uncore) { u32 shim_flags = GUC_DISABLE_SRAM_INIT_TO_ZEROES | diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h index b5ab639d7259..0b4d2a9c9435 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.h @@ -8,7 +8,6 @@ struct intel_guc; -void intel_guc_fw_init_early(struct intel_guc *guc); int intel_guc_fw_upload(struct intel_guc *guc); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index caed0d57e704..fb10f3597ea5 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -55,11 +55,6 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable, return intel_guc_send(guc, action, ARRAY_SIZE(action)); } -static inline struct intel_guc *log_to_guc(struct intel_guc_log *log) -{ - return container_of(log, struct intel_guc, log); -} - static void guc_log_enable_flush_events(struct intel_guc_log *log) { intel_guc_enable_msg(log_to_guc(log), @@ -672,3 +667,95 @@ void intel_guc_log_handle_flush_event(struct intel_guc_log *log) { queue_work(system_highpri_wq, &log->relay.flush_work); } + +static const char * +stringify_guc_log_type(enum guc_log_buffer_type type) +{ + switch (type) { + case GUC_ISR_LOG_BUFFER: + return "ISR"; + case GUC_DPC_LOG_BUFFER: + return "DPC"; + case GUC_CRASH_DUMP_LOG_BUFFER: + return "CRASH"; + default: + MISSING_CASE(type); + } + + return ""; +} + +/** + * intel_guc_log_info - dump information about GuC log relay + * @log: the GuC log + * @p: the &drm_printer + * + * Pretty printer for GuC log info + */ +void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p) +{ + enum guc_log_buffer_type type; + + if (!intel_guc_log_relay_created(log)) { + drm_puts(p, "GuC log relay not created\n"); + return; + } + + drm_puts(p, "GuC logging stats:\n"); + + drm_printf(p, "\tRelay full count: %u\n", log->relay.full_count); + + for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { + drm_printf(p, "\t%s:\tflush count %10u, overflow count %10u\n", + stringify_guc_log_type(type), + log->stats[type].flush, + log->stats[type].sampled_overflow); + } +} + +/** + * intel_guc_log_dump - dump the contents of the GuC log + * @log: the GuC log + * @p: the &drm_printer + * @dump_load_err: dump the log saved on GuC load error + * + * Pretty printer for the GuC log + */ +int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p, + bool dump_load_err) +{ + struct intel_guc *guc = log_to_guc(log); + struct intel_uc *uc = container_of(guc, struct intel_uc, guc); + struct drm_i915_gem_object *obj = NULL; + u32 *map; + int i = 0; + + if (!intel_guc_is_supported(guc)) + return -ENODEV; + + if (dump_load_err) + obj = uc->load_err_log; + else if (guc->log.vma) + obj = guc->log.vma->obj; + + if (!obj) + return 0; + + map = i915_gem_object_pin_map(obj, I915_MAP_WC); + if (IS_ERR(map)) { + DRM_DEBUG("Failed to pin object\n"); + drm_puts(p, "(log data unaccessible)\n"); + return PTR_ERR(map); + } + + for (i = 0; i < obj->base.size / sizeof(u32); i += 4) + drm_printf(p, "0x%08x 0x%08x 0x%08x 0x%08x\n", + *(map + i), *(map + i + 1), + *(map + i + 2), *(map + i + 3)); + + drm_puts(p, "\n"); + + i915_gem_object_unpin_map(obj); + + return 0; +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h index c252c022c5fc..11fccd0b2294 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h @@ -79,4 +79,8 @@ static inline u32 intel_guc_log_get_level(struct intel_guc_log *log) return log->level; } +void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p); +int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p, + bool dump_load_err); + #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c new file mode 100644 index 000000000000..129e0cf7dfe2 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +#include <linux/fs.h> +#include <drm/drm_print.h> + +#include "gt/debugfs_gt.h" +#include "intel_guc.h" +#include "intel_guc_log.h" +#include "intel_guc_log_debugfs.h" + +static int guc_log_dump_show(struct seq_file *m, void *data) +{ + struct drm_printer p = drm_seq_file_printer(m); + + return intel_guc_log_dump(m->private, &p, false); +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_log_dump); + +static int guc_load_err_log_dump_show(struct seq_file *m, void *data) +{ + struct drm_printer p = drm_seq_file_printer(m); + + return intel_guc_log_dump(m->private, &p, true); +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_load_err_log_dump); + +static int guc_log_level_get(void *data, u64 *val) +{ + struct intel_guc_log *log = data; + + if (!intel_guc_is_used(log_to_guc(log))) + return -ENODEV; + + *val = intel_guc_log_get_level(log); + + return 0; +} + +static int guc_log_level_set(void *data, u64 val) +{ + struct intel_guc_log *log = data; + + if (!intel_guc_is_used(log_to_guc(log))) + return -ENODEV; + + return intel_guc_log_set_level(log, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(guc_log_level_fops, + guc_log_level_get, guc_log_level_set, + "%lld\n"); + +static int guc_log_relay_open(struct inode *inode, struct file *file) +{ + struct intel_guc_log *log = inode->i_private; + + if (!intel_guc_is_ready(log_to_guc(log))) + return -ENODEV; + + file->private_data = log; + + return intel_guc_log_relay_open(log); +} + +static ssize_t +guc_log_relay_write(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + struct intel_guc_log *log = filp->private_data; + int val; + int ret; + + ret = kstrtoint_from_user(ubuf, cnt, 0, &val); + if (ret < 0) + return ret; + + /* + * Enable and start the guc log relay on value of 1. + * Flush log relay for any other value. + */ + if (val == 1) + ret = intel_guc_log_relay_start(log); + else + intel_guc_log_relay_flush(log); + + return ret ?: cnt; +} + +static int guc_log_relay_release(struct inode *inode, struct file *file) +{ + struct intel_guc_log *log = inode->i_private; + + intel_guc_log_relay_close(log); + return 0; +} + +static const struct file_operations guc_log_relay_fops = { + .owner = THIS_MODULE, + .open = guc_log_relay_open, + .write = guc_log_relay_write, + .release = guc_log_relay_release, +}; + +void intel_guc_log_debugfs_register(struct intel_guc_log *log, + struct dentry *root) +{ + static const struct debugfs_gt_file files[] = { + { "guc_log_dump", &guc_log_dump_fops, NULL }, + { "guc_load_err_log_dump", &guc_load_err_log_dump_fops, NULL }, + { "guc_log_level", &guc_log_level_fops, NULL }, + { "guc_log_relay", &guc_log_relay_fops, NULL }, + }; + + if (!intel_guc_is_supported(log_to_guc(log))) + return; + + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), log); +} + diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h new file mode 100644 index 000000000000..e8900e3d74ea --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef DEBUGFS_GUC_LOG_H +#define DEBUGFS_GUC_LOG_H + +struct intel_guc_log; +struct dentry; + +void intel_guc_log_debugfs_register(struct intel_guc_log *log, + struct dentry *root); + +#endif /* DEBUGFS_GUC_LOG_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index a74b65694512..65eeb44b397d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -41,7 +41,7 @@ void intel_huc_init_early(struct intel_huc *huc) { struct drm_i915_private *i915 = huc_to_gt(huc)->i915; - intel_huc_fw_init_early(huc); + intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC); if (INTEL_GEN(i915) >= 11) { huc->status.reg = GEN11_HUC_KERNEL_LOAD_INFO; @@ -200,9 +200,13 @@ fail: * This function reads status register to verify if HuC * firmware was successfully loaded. * - * Returns: 1 if HuC firmware is loaded and verified, - * 0 if HuC firmware is not loaded and -ENODEV if HuC - * is not present on this platform. + * Returns: + * * -ENODEV if HuC is not present on this platform, + * * -EOPNOTSUPP if HuC firmware is disabled, + * * -ENOPKG if HuC firmware was not installed, + * * -ENOEXEC if HuC firmware is invalid or mismatched, + * * 0 if HuC firmware is not running, + * * 1 if HuC firmware is authenticated and running. */ int intel_huc_check_status(struct intel_huc *huc) { @@ -210,11 +214,50 @@ int intel_huc_check_status(struct intel_huc *huc) intel_wakeref_t wakeref; u32 status = 0; - if (!intel_huc_is_supported(huc)) + switch (__intel_uc_fw_status(&huc->fw)) { + case INTEL_UC_FIRMWARE_NOT_SUPPORTED: return -ENODEV; + case INTEL_UC_FIRMWARE_DISABLED: + return -EOPNOTSUPP; + case INTEL_UC_FIRMWARE_MISSING: + return -ENOPKG; + case INTEL_UC_FIRMWARE_ERROR: + return -ENOEXEC; + default: + break; + } with_intel_runtime_pm(gt->uncore->rpm, wakeref) status = intel_uncore_read(gt->uncore, huc->status.reg); return (status & huc->status.mask) == huc->status.value; } + +/** + * intel_huc_load_status - dump information about HuC load status + * @huc: the HuC + * @p: the &drm_printer + * + * Pretty printer for HuC load status. + */ +void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p) +{ + struct intel_gt *gt = huc_to_gt(huc); + intel_wakeref_t wakeref; + + if (!intel_huc_is_supported(huc)) { + drm_printf(p, "HuC not supported\n"); + return; + } + + if (!intel_huc_is_wanted(huc)) { + drm_printf(p, "HuC disabled\n"); + return; + } + + intel_uc_fw_dump(&huc->fw, p); + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + drm_printf(p, "HuC status: 0x%08x\n", + intel_uncore_read(gt->uncore, huc->status.reg)); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index a40b9cfc6c22..daee43b661d4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -57,4 +57,6 @@ static inline bool intel_huc_is_authenticated(struct intel_huc *huc) return intel_uc_fw_is_running(&huc->fw); } +void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p); + #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c new file mode 100644 index 000000000000..5733c15fd123 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +#include <drm/drm_print.h> + +#include "gt/debugfs_gt.h" +#include "intel_huc.h" +#include "intel_huc_debugfs.h" + +static int huc_info_show(struct seq_file *m, void *data) +{ + struct intel_huc *huc = m->private; + struct drm_printer p = drm_seq_file_printer(m); + + if (!intel_huc_is_supported(huc)) + return -ENODEV; + + intel_huc_load_status(huc, &p); + + return 0; +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(huc_info); + +void intel_huc_debugfs_register(struct intel_huc *huc, struct dentry *root) +{ + static const struct debugfs_gt_file files[] = { + { "huc_info", &huc_info_fops, NULL }, + }; + + if (!intel_huc_is_supported(huc)) + return; + + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), huc); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h new file mode 100644 index 000000000000..be79e992f976 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef DEBUGFS_HUC_H +#define DEBUGFS_HUC_H + +struct intel_huc; +struct dentry; + +void intel_huc_debugfs_register(struct intel_huc *huc, struct dentry *root); + +#endif /* DEBUGFS_HUC_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c index 9cdf4cbe691c..e5ef509c70e8 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c @@ -8,23 +8,6 @@ #include "i915_drv.h" /** - * intel_huc_fw_init_early() - initializes HuC firmware struct - * @huc: intel_huc struct - * - * On platforms with HuC selects firmware for uploading - */ -void intel_huc_fw_init_early(struct intel_huc *huc) -{ - struct intel_gt *gt = huc_to_gt(huc); - struct intel_uc *uc = >->uc; - struct drm_i915_private *i915 = gt->i915; - - intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC, - intel_uc_wants_guc(uc), - INTEL_INFO(i915)->platform, INTEL_REVID(i915)); -} - -/** * intel_huc_fw_upload() - load HuC uCode to device * @huc: intel_huc structure * diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h index b791269ce923..12f264ee3e0b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.h @@ -8,7 +8,6 @@ struct intel_huc; -void intel_huc_fw_init_early(struct intel_huc *huc); int intel_huc_fw_upload(struct intel_huc *huc); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index a4cbe06e06bd..f518fe05c6f9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -45,12 +45,12 @@ static void __confirm_options(struct intel_uc *uc) { struct drm_i915_private *i915 = uc_to_gt(uc)->i915; - DRM_DEV_DEBUG_DRIVER(i915->drm.dev, - "enable_guc=%d (guc:%s submission:%s huc:%s)\n", - i915_modparams.enable_guc, - yesno(intel_uc_wants_guc(uc)), - yesno(intel_uc_wants_guc_submission(uc)), - yesno(intel_uc_wants_huc(uc))); + drm_dbg(&i915->drm, + "enable_guc=%d (guc:%s submission:%s huc:%s)\n", + i915_modparams.enable_guc, + yesno(intel_uc_wants_guc(uc)), + yesno(intel_uc_wants_guc_submission(uc)), + yesno(intel_uc_wants_huc(uc))); if (i915_modparams.enable_guc == -1) return; @@ -63,25 +63,25 @@ static void __confirm_options(struct intel_uc *uc) } if (!intel_uc_supports_guc(uc)) - dev_info(i915->drm.dev, + drm_info(&i915->drm, "Incompatible option enable_guc=%d - %s\n", i915_modparams.enable_guc, "GuC is not supported!"); if (i915_modparams.enable_guc & ENABLE_GUC_LOAD_HUC && !intel_uc_supports_huc(uc)) - dev_info(i915->drm.dev, + drm_info(&i915->drm, "Incompatible option enable_guc=%d - %s\n", i915_modparams.enable_guc, "HuC is not supported!"); if (i915_modparams.enable_guc & ENABLE_GUC_SUBMISSION && !intel_uc_supports_guc_submission(uc)) - dev_info(i915->drm.dev, + drm_info(&i915->drm, "Incompatible option enable_guc=%d - %s\n", i915_modparams.enable_guc, "GuC submission is N/A"); if (i915_modparams.enable_guc & ~(ENABLE_GUC_SUBMISSION | ENABLE_GUC_LOAD_HUC)) - dev_info(i915->drm.dev, + drm_info(&i915->drm, "Incompatible option enable_guc=%d - %s\n", i915_modparams.enable_guc, "undocumented flag"); } @@ -131,6 +131,13 @@ static void __uc_free_load_err_log(struct intel_uc *uc) i915_gem_object_put(log); } +void intel_uc_driver_remove(struct intel_uc *uc) +{ + intel_uc_fini_hw(uc); + intel_uc_fini(uc); + __uc_free_load_err_log(uc); +} + static inline bool guc_communication_enabled(struct intel_guc *guc) { return intel_guc_ct_enabled(&guc->ct); @@ -311,8 +318,6 @@ static void __uc_fini(struct intel_uc *uc) { intel_huc_fini(&uc->huc); intel_guc_fini(&uc->guc); - - __uc_free_load_err_log(uc); } static int __uc_sanitize(struct intel_uc *uc) @@ -475,14 +480,14 @@ static int __uc_init_hw(struct intel_uc *uc) if (intel_uc_uses_guc_submission(uc)) intel_guc_submission_enable(guc); - dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n", + drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path, guc->fw.major_ver_found, guc->fw.minor_ver_found, "submission", enableddisabled(intel_uc_uses_guc_submission(uc))); if (intel_uc_uses_huc(uc)) { - dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n", + drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), huc->fw.path, huc->fw.major_ver_found, huc->fw.minor_ver_found, @@ -503,7 +508,7 @@ err_out: __uc_sanitize(uc); if (!ret) { - dev_notice(i915->drm.dev, "GuC is uninitialized\n"); + drm_notice(&i915->drm, "GuC is uninitialized\n"); /* We want to run without GuC submission */ return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h index 5ae7b50b7dc1..9c954c589edf 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h @@ -34,6 +34,7 @@ struct intel_uc { void intel_uc_init_early(struct intel_uc *uc); void intel_uc_driver_late_release(struct intel_uc *uc); +void intel_uc_driver_remove(struct intel_uc *uc); void intel_uc_init_mmio(struct intel_uc *uc); void intel_uc_reset_prepare(struct intel_uc *uc); void intel_uc_suspend(struct intel_uc *uc); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c new file mode 100644 index 000000000000..9d16b784aa0d --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +#include <linux/debugfs.h> + +#include "intel_guc_debugfs.h" +#include "intel_huc_debugfs.h" +#include "intel_uc.h" +#include "intel_uc_debugfs.h" + +void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root) +{ + struct dentry *root; + + if (!gt_root) + return; + + /* GuC and HuC go always in pair, no need to check both */ + if (!intel_uc_supports_guc(uc)) + return; + + root = debugfs_create_dir("uc", gt_root); + if (IS_ERR(root)) + return; + + intel_guc_debugfs_register(&uc->guc, root); + intel_huc_debugfs_register(&uc->huc, root); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h new file mode 100644 index 000000000000..010ce250d223 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef DEBUGFS_UC_H +#define DEBUGFS_UC_H + +struct intel_uc; +struct dentry; + +void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root); + +#endif /* DEBUGFS_UC_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 18c755203688..e1caae93996d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -11,26 +11,32 @@ #include "intel_uc_fw_abi.h" #include "i915_drv.h" -static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw) +static inline struct intel_gt * +____uc_fw_to_gt(struct intel_uc_fw *uc_fw, enum intel_uc_fw_type type) { - GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED); - if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) + if (type == INTEL_UC_FW_TYPE_GUC) return container_of(uc_fw, struct intel_gt, uc.guc.fw); - GEM_BUG_ON(uc_fw->type != INTEL_UC_FW_TYPE_HUC); + GEM_BUG_ON(type != INTEL_UC_FW_TYPE_HUC); return container_of(uc_fw, struct intel_gt, uc.huc.fw); } +static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw) +{ + GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED); + return ____uc_fw_to_gt(uc_fw, uc_fw->type); +} + #ifdef CONFIG_DRM_I915_DEBUG_GUC void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, enum intel_uc_fw_status status) { uc_fw->__status = status; - DRM_DEV_DEBUG_DRIVER(__uc_fw_to_gt(uc_fw)->i915->drm.dev, - "%s firmware -> %s\n", - intel_uc_fw_type_repr(uc_fw->type), - status == INTEL_UC_FIRMWARE_SELECTED ? - uc_fw->path : intel_uc_fw_status_repr(status)); + drm_dbg(&__uc_fw_to_gt(uc_fw)->i915->drm, + "%s firmware -> %s\n", + intel_uc_fw_type_repr(uc_fw->type), + status == INTEL_UC_FIRMWARE_SELECTED ? + uc_fw->path : intel_uc_fw_status_repr(status)); } #endif @@ -187,17 +193,15 @@ static void __uc_fw_user_override(struct intel_uc_fw *uc_fw) * intel_uc_fw_init_early - initialize the uC object and select the firmware * @uc_fw: uC firmware * @type: type of uC - * @supported: is uC support possible - * @platform: platform identifier - * @rev: hardware revision * * Initialize the state of our uC object and relevant tracking and select the * firmware to fetch and load. */ void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw, - enum intel_uc_fw_type type, bool supported, - enum intel_platform platform, u8 rev) + enum intel_uc_fw_type type) { + struct drm_i915_private *i915 = ____uc_fw_to_gt(uc_fw, type)->i915; + /* * we use FIRMWARE_UNINITIALIZED to detect checks against uc_fw->status * before we're looked at the HW caps to see if we have uc support @@ -208,8 +212,10 @@ void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw, uc_fw->type = type; - if (supported) { - __uc_fw_auto_select(uc_fw, platform, rev); + if (HAS_GT_UC(i915)) { + __uc_fw_auto_select(uc_fw, + INTEL_INFO(i915)->platform, + INTEL_REVID(i915)); __uc_fw_user_override(uc_fw); } @@ -290,7 +296,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) /* Check the size of the blob before examining buffer contents */ if (unlikely(fw->size < sizeof(struct uc_css_header))) { - dev_warn(dev, "%s firmware %s: invalid size: %zu < %zu\n", + drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, fw->size, sizeof(struct uc_css_header)); err = -ENODATA; @@ -303,7 +309,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) size = (css->header_size_dw - css->key_size_dw - css->modulus_size_dw - css->exponent_size_dw) * sizeof(u32); if (unlikely(size != sizeof(struct uc_css_header))) { - dev_warn(dev, + drm_warn(&i915->drm, "%s firmware %s: unexpected header size: %zu != %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, fw->size, sizeof(struct uc_css_header)); @@ -316,7 +322,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) /* now RSA */ if (unlikely(css->key_size_dw != UOS_RSA_SCRATCH_COUNT)) { - dev_warn(dev, "%s firmware %s: unexpected key size: %u != %u\n", + drm_warn(&i915->drm, "%s firmware %s: unexpected key size: %u != %u\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, css->key_size_dw, UOS_RSA_SCRATCH_COUNT); err = -EPROTO; @@ -327,7 +333,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) /* At least, it should have header, uCode and RSA. Size of all three. */ size = sizeof(struct uc_css_header) + uc_fw->ucode_size + uc_fw->rsa_size; if (unlikely(fw->size < size)) { - dev_warn(dev, "%s firmware %s: invalid size: %zu < %zu\n", + drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu < %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, fw->size, size); err = -ENOEXEC; @@ -337,7 +343,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) /* Sanity check whether this fw is not larger than whole WOPCM memory */ size = __intel_uc_fw_get_upload_size(uc_fw); if (unlikely(size >= i915->wopcm.size)) { - dev_warn(dev, "%s firmware %s: invalid size: %zu > %zu\n", + drm_warn(&i915->drm, "%s firmware %s: invalid size: %zu > %zu\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, size, (size_t)i915->wopcm.size); err = -E2BIG; @@ -352,7 +358,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (uc_fw->major_ver_found != uc_fw->major_ver_wanted || uc_fw->minor_ver_found < uc_fw->minor_ver_wanted) { - dev_notice(dev, "%s firmware %s: unexpected version: %u.%u != %u.%u\n", + drm_notice(&i915->drm, "%s firmware %s: unexpected version: %u.%u != %u.%u\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, uc_fw->major_ver_found, uc_fw->minor_ver_found, uc_fw->major_ver_wanted, uc_fw->minor_ver_wanted); @@ -380,9 +386,9 @@ fail: INTEL_UC_FIRMWARE_MISSING : INTEL_UC_FIRMWARE_ERROR); - dev_notice(dev, "%s firmware %s: fetch failed with error %d\n", + drm_notice(&i915->drm, "%s firmware %s: fetch failed with error %d\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err); - dev_info(dev, "%s firmware(s) can be downloaded from %s\n", + drm_info(&i915->drm, "%s firmware(s) can be downloaded from %s\n", intel_uc_fw_type_repr(uc_fw->type), INTEL_UC_FIRMWARE_URL); release_firmware(fw); /* OK even if fw is NULL */ @@ -467,7 +473,7 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags) /* Wait for DMA to finish */ ret = intel_wait_for_register_fw(uncore, DMA_CTRL, START_DMA, 0, 100); if (ret) - dev_err(gt->i915->drm.dev, "DMA for %s fw failed, DMA_CTRL=%u\n", + drm_err(>->i915->drm, "DMA for %s fw failed, DMA_CTRL=%u\n", intel_uc_fw_type_repr(uc_fw->type), intel_uncore_read_fw(uncore, DMA_CTRL)); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index 888ff0de0244..23d3a423ac0f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -239,8 +239,7 @@ static inline u32 intel_uc_fw_get_upload_size(struct intel_uc_fw *uc_fw) } void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw, - enum intel_uc_fw_type type, bool supported, - enum intel_platform platform, u8 rev); + enum intel_uc_fw_type type); int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw); void intel_uc_fw_cleanup_fetch(struct intel_uc_fw *uc_fw); int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 offset, u32 dma_flags); diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 8b13f091cee2..0d6d59871308 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -35,7 +35,7 @@ */ #include "i915_drv.h" -#include "i915_gem_fence_reg.h" +#include "gt/intel_ggtt_fencing.h" #include "gvt.h" static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 9e065ad0658f..a3cc080a46c6 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -164,6 +164,7 @@ struct decode_info { #define OP_STATE_BASE_ADDRESS OP_3D_MEDIA(0x0, 0x1, 0x01) #define OP_STATE_SIP OP_3D_MEDIA(0x0, 0x1, 0x02) #define OP_3D_MEDIA_0_1_4 OP_3D_MEDIA(0x0, 0x1, 0x04) +#define OP_SWTESS_BASE_ADDRESS OP_3D_MEDIA(0x0, 0x1, 0x03) #define OP_3DSTATE_VF_STATISTICS_GM45 OP_3D_MEDIA(0x1, 0x0, 0x0B) @@ -967,18 +968,6 @@ static int cmd_handler_lri(struct parser_exec_state *s) { int i, ret = 0; int cmd_len = cmd_length(s); - u32 valid_len = CMD_LEN(1); - - /* - * Official intel docs are somewhat sloppy , check the definition of - * MI_LOAD_REGISTER_IMM. - */ - #define MAX_VALID_LEN 127 - if ((cmd_len < valid_len) || (cmd_len > MAX_VALID_LEN)) { - gvt_err("len is not valid: len=%u valid_len=%u\n", - cmd_len, valid_len); - return -EFAULT; - } for (i = 1; i < cmd_len; i += 2) { if (IS_BROADWELL(s->engine->i915) && s->engine->id != RCS0) { @@ -2485,6 +2474,9 @@ static const struct cmd_info cmd_info[] = { {"OP_3D_MEDIA_0_1_4", OP_3D_MEDIA_0_1_4, F_LEN_VAR, R_RCS, D_ALL, ADDR_FIX_1(1), 8, NULL}, + {"OP_SWTESS_BASE_ADDRESS", OP_SWTESS_BASE_ADDRESS, + F_LEN_VAR, R_RCS, D_ALL, ADDR_FIX_2(1, 2), 3, NULL}, + {"3DSTATE_VS", OP_3DSTATE_VS, F_LEN_VAR, R_RCS, D_ALL, 0, 8, NULL}, {"3DSTATE_SF", OP_3DSTATE_SF, F_LEN_VAR, R_RCS, D_ALL, 0, 8, NULL}, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 6e5c9885d9fe..a83df2f84eb9 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -221,7 +221,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_B << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { @@ -241,7 +241,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_C << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { @@ -261,7 +261,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_D << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 0182e2a5acff..2faf50e1b051 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -462,11 +462,14 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, return 0; } -/* ascendingly sorted */ +/* sorted in ascending order */ static i915_reg_t force_nonpriv_white_list[] = { + _MMIO(0xd80), GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec) GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248) - PS_INVOCATION_COUNT,//_MMIO(0x2348) + CL_PRIMITIVES_COUNT, //_MMIO(0x2340) + PS_INVOCATION_COUNT, //_MMIO(0x2348) + PS_DEPTH_COUNT, //_MMIO(0x2350) GEN8_CS_CHICKEN1,//_MMIO(0x2580) _MMIO(0x2690), _MMIO(0x2694), @@ -491,6 +494,7 @@ static i915_reg_t force_nonpriv_white_list[] = { _MMIO(0xe18c), _MMIO(0xe48c), _MMIO(0xe5f4), + _MMIO(0x64844), }; /* a simple bsearch */ diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 074c4efb58eb..eee530453aa6 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -131,6 +131,7 @@ struct kvmgt_vdev { struct work_struct release_work; atomic_t released; struct vfio_device *vfio_device; + struct vfio_group *vfio_group; }; static inline struct kvmgt_vdev *kvmgt_vdev(struct intel_vgpu *vgpu) @@ -151,6 +152,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size) { struct drm_i915_private *i915 = vgpu->gvt->gt->i915; + struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); int total_pages; int npage; int ret; @@ -160,7 +162,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, for (npage = 0; npage < total_pages; npage++) { unsigned long cur_gfn = gfn + npage; - ret = vfio_unpin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1); + ret = vfio_group_unpin_pages(vdev->vfio_group, &cur_gfn, 1); drm_WARN_ON(&i915->drm, ret != 1); } } @@ -169,6 +171,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size, struct page **page) { + struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); unsigned long base_pfn = 0; int total_pages; int npage; @@ -183,8 +186,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long cur_gfn = gfn + npage; unsigned long pfn; - ret = vfio_pin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1, - IOMMU_READ | IOMMU_WRITE, &pfn); + ret = vfio_group_pin_pages(vdev->vfio_group, &cur_gfn, 1, + IOMMU_READ | IOMMU_WRITE, &pfn); if (ret != 1) { gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n", cur_gfn, ret); @@ -792,6 +795,7 @@ static int intel_vgpu_open(struct mdev_device *mdev) struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); unsigned long events; int ret; + struct vfio_group *vfio_group; vdev->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier; vdev->group_notifier.notifier_call = intel_vgpu_group_notifier; @@ -814,6 +818,14 @@ static int intel_vgpu_open(struct mdev_device *mdev) goto undo_iommu; } + vfio_group = vfio_group_get_external_user_from_dev(mdev_dev(mdev)); + if (IS_ERR_OR_NULL(vfio_group)) { + ret = !vfio_group ? -EFAULT : PTR_ERR(vfio_group); + gvt_vgpu_err("vfio_group_get_external_user_from_dev failed\n"); + goto undo_register; + } + vdev->vfio_group = vfio_group; + /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ @@ -830,6 +842,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) return ret; undo_group: + vfio_group_put_external_user(vdev->vfio_group); + vdev->vfio_group = NULL; + +undo_register: vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &vdev->group_notifier); @@ -884,6 +900,7 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu) kvmgt_guest_exit(info); intel_vgpu_release_msi_eventfd_ctx(vgpu); + vfio_group_put_external_user(vdev->vfio_group); vdev->kvm = NULL; vgpu->handle = 0; @@ -2035,33 +2052,14 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, void *buf, unsigned long len, bool write) { struct kvmgt_guest_info *info; - struct kvm *kvm; - int idx, ret; - bool kthread = current->mm == NULL; if (!handle_valid(handle)) return -ESRCH; info = (struct kvmgt_guest_info *)handle; - kvm = info->kvm; - - if (kthread) { - if (!mmget_not_zero(kvm->mm)) - return -EFAULT; - use_mm(kvm->mm); - } - - idx = srcu_read_lock(&kvm->srcu); - ret = write ? kvm_write_guest(kvm, gpa, buf, len) : - kvm_read_guest(kvm, gpa, buf, len); - srcu_read_unlock(&kvm->srcu, idx); - - if (kthread) { - unuse_mm(kvm->mm); - mmput(kvm->mm); - } - return ret; + return vfio_dma_rw(kvmgt_vdev(info->vgpu)->vfio_group, + gpa, buf, len, write); } static int kvmgt_read_gpa(unsigned long handle, unsigned long gpa, diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 867e7629025b..33569b910ed5 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v) /* there's features depending on version! */ v->header.version = 155; v->header.header_size = sizeof(v->header); - v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header); + v->header.vbt_size = sizeof(struct vbt); v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); - v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) - - sizeof(struct bdb_header); + v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header); /* general features */ v->general_features_header.id = BDB_GENERAL_FEATURES; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 1c95bf8cbed0..cb11c3184085 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -296,8 +296,8 @@ shadow_context_descriptor_update(struct intel_context *ce, * Update bits 0-11 of the context descriptor which includes flags * like GEN8_CTX_* cached in desc_template */ - desc &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT); - desc |= workload->ctx_desc.addressing_mode << + desc &= ~(0x3ull << GEN8_CTX_ADDRESSING_MODE_SHIFT); + desc |= (u64)workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; ce->lrc_desc = desc; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 78f14f04d2ea..1d5ff88078bd 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -274,10 +274,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *i915 = gvt->gt->i915; - mutex_lock(&vgpu->vgpu_lock); - drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n"); + /* + * remove idr first so later clean can judge if need to stop + * service if no active vgpu. + */ + mutex_lock(&gvt->lock); + idr_remove(&gvt->vgpu_idr, vgpu->id); + mutex_unlock(&gvt->lock); + + mutex_lock(&vgpu->vgpu_lock); intel_gvt_debugfs_remove_vgpu(vgpu); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_submission(vgpu); @@ -292,7 +299,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) mutex_unlock(&vgpu->vgpu_lock); mutex_lock(&gvt->lock); - idr_remove(&gvt->vgpu_idr, vgpu->id); if (idr_is_empty(&gvt->vgpu_idr)) intel_gvt_clean_irq(gvt); intel_gvt_update_vgpu_types(gvt); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index c4048628188a..d960d0be5bd2 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -496,7 +496,7 @@ static int flush_lazy_signals(struct i915_active *ref) return err; } -int i915_active_wait(struct i915_active *ref) +int __i915_active_wait(struct i915_active *ref, int state) { int err; @@ -511,7 +511,9 @@ int i915_active_wait(struct i915_active *ref) if (err) return err; - if (wait_var_event_interruptible(ref, i915_active_is_idle(ref))) + if (!i915_active_is_idle(ref) && + ___wait_var_event(ref, i915_active_is_idle(ref), + state, 0, 0, schedule())) return -EINTR; flush_work(&ref->work); @@ -540,34 +542,88 @@ static int __await_active(struct i915_active_fence *active, return 0; } +struct wait_barrier { + struct wait_queue_entry base; + struct i915_active *ref; +}; + +static int +barrier_wake(wait_queue_entry_t *wq, unsigned int mode, int flags, void *key) +{ + struct wait_barrier *wb = container_of(wq, typeof(*wb), base); + + if (i915_active_is_idle(wb->ref)) { + list_del(&wq->entry); + i915_sw_fence_complete(wq->private); + kfree(wq); + } + + return 0; +} + +static int __await_barrier(struct i915_active *ref, struct i915_sw_fence *fence) +{ + struct wait_barrier *wb; + + wb = kmalloc(sizeof(*wb), GFP_KERNEL); + if (unlikely(!wb)) + return -ENOMEM; + + GEM_BUG_ON(i915_active_is_idle(ref)); + if (!i915_sw_fence_await(fence)) { + kfree(wb); + return -EINVAL; + } + + wb->base.flags = 0; + wb->base.func = barrier_wake; + wb->base.private = fence; + wb->ref = ref; + + add_wait_queue(__var_waitqueue(ref), &wb->base); + return 0; +} + static int await_active(struct i915_active *ref, unsigned int flags, int (*fn)(void *arg, struct dma_fence *fence), - void *arg) + void *arg, struct i915_sw_fence *barrier) { int err = 0; - /* We must always wait for the exclusive fence! */ - if (rcu_access_pointer(ref->excl.fence)) { + if (!i915_active_acquire_if_busy(ref)) + return 0; + + if (flags & I915_ACTIVE_AWAIT_EXCL && + rcu_access_pointer(ref->excl.fence)) { err = __await_active(&ref->excl, fn, arg); if (err) - return err; + goto out; } - if (flags & I915_ACTIVE_AWAIT_ALL && i915_active_acquire_if_busy(ref)) { + if (flags & I915_ACTIVE_AWAIT_ACTIVE) { struct active_node *it, *n; rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) { err = __await_active(&it->base, fn, arg); if (err) - break; + goto out; } - i915_active_release(ref); + } + + if (flags & I915_ACTIVE_AWAIT_BARRIER) { + err = flush_lazy_signals(ref); if (err) - return err; + goto out; + + err = __await_barrier(ref, barrier); + if (err) + goto out; } - return 0; +out: + i915_active_release(ref); + return err; } static int rq_await_fence(void *arg, struct dma_fence *fence) @@ -579,7 +635,7 @@ int i915_request_await_active(struct i915_request *rq, struct i915_active *ref, unsigned int flags) { - return await_active(ref, flags, rq_await_fence, rq); + return await_active(ref, flags, rq_await_fence, rq, &rq->submit); } static int sw_await_fence(void *arg, struct dma_fence *fence) @@ -592,7 +648,7 @@ int i915_sw_fence_await_active(struct i915_sw_fence *fence, struct i915_active *ref, unsigned int flags) { - return await_active(ref, flags, sw_await_fence, fence); + return await_active(ref, flags, sw_await_fence, fence, fence); } #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) @@ -818,7 +874,7 @@ void i915_active_acquire_barrier(struct i915_active *ref) GEM_BUG_ON(!intel_engine_pm_is_awake(engine)); llist_add(barrier_to_ll(node), &engine->barrier_tasks); - intel_engine_pm_put(engine); + intel_engine_pm_put_delay(engine, 1); } } @@ -937,6 +993,59 @@ void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb) active_fence_cb(fence, cb); } +struct auto_active { + struct i915_active base; + struct kref ref; +}; + +struct i915_active *i915_active_get(struct i915_active *ref) +{ + struct auto_active *aa = container_of(ref, typeof(*aa), base); + + kref_get(&aa->ref); + return &aa->base; +} + +static void auto_release(struct kref *ref) +{ + struct auto_active *aa = container_of(ref, typeof(*aa), ref); + + i915_active_fini(&aa->base); + kfree(aa); +} + +void i915_active_put(struct i915_active *ref) +{ + struct auto_active *aa = container_of(ref, typeof(*aa), base); + + kref_put(&aa->ref, auto_release); +} + +static int auto_active(struct i915_active *ref) +{ + i915_active_get(ref); + return 0; +} + +static void auto_retire(struct i915_active *ref) +{ + i915_active_put(ref); +} + +struct i915_active *i915_active_create(void) +{ + struct auto_active *aa; + + aa = kmalloc(sizeof(*aa), GFP_KERNEL); + if (!aa) + return NULL; + + kref_init(&aa->ref); + i915_active_init(&aa->base, auto_active, auto_retire); + + return &aa->base; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/i915_active.c" #endif diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index b3282ae7913c..cf4058150966 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -181,7 +181,11 @@ static inline bool i915_active_has_exclusive(struct i915_active *ref) return rcu_access_pointer(ref->excl.fence); } -int i915_active_wait(struct i915_active *ref); +int __i915_active_wait(struct i915_active *ref, int state); +static inline int i915_active_wait(struct i915_active *ref) +{ + return __i915_active_wait(ref, TASK_INTERRUPTIBLE); +} int i915_sw_fence_await_active(struct i915_sw_fence *fence, struct i915_active *ref, @@ -189,7 +193,9 @@ int i915_sw_fence_await_active(struct i915_sw_fence *fence, int i915_request_await_active(struct i915_request *rq, struct i915_active *ref, unsigned int flags); -#define I915_ACTIVE_AWAIT_ALL BIT(0) +#define I915_ACTIVE_AWAIT_EXCL BIT(0) +#define I915_ACTIVE_AWAIT_ACTIVE BIT(1) +#define I915_ACTIVE_AWAIT_BARRIER BIT(2) int i915_active_acquire(struct i915_active *ref); bool i915_active_acquire_if_busy(struct i915_active *ref); @@ -221,4 +227,8 @@ void i915_request_add_active_barriers(struct i915_request *rq); void i915_active_print(struct i915_active *ref, struct drm_printer *m); void i915_active_unlock_wait(struct i915_active *ref); +struct i915_active *i915_active_create(void); +struct i915_active *i915_active_get(struct i915_active *ref); +void i915_active_put(struct i915_active *ref); + #endif /* _I915_ACTIVE_H_ */ diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 25bf997e2dd1..aa35a59f1c7d 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -37,7 +37,6 @@ #include "gt/intel_reset.h" #include "gt/intel_rc6.h" #include "gt/intel_rps.h" -#include "gt/uc/intel_guc_submission.h" #include "i915_debugfs.h" #include "i915_debugfs_params.h" @@ -218,7 +217,7 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) struct file_stats { struct i915_address_space *vm; unsigned long count; - u64 total, unbound; + u64 total; u64 active, inactive; u64 closed; }; @@ -234,8 +233,6 @@ static int per_file_stats(int id, void *ptr, void *data) stats->count++; stats->total += obj->base.size; - if (!atomic_read(&obj->bind_count)) - stats->unbound += obj->base.size; spin_lock(&obj->vma.lock); if (!stats->vm) { @@ -285,13 +282,12 @@ static int per_file_stats(int id, void *ptr, void *data) #define print_file_stats(m, name, stats) do { \ if (stats.count) \ - seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu unbound, %llu closed)\n", \ + seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu closed)\n", \ name, \ stats.count, \ stats.total, \ stats.active, \ stats.inactive, \ - stats.unbound, \ stats.closed); \ } while (0) @@ -745,7 +741,7 @@ i915_error_state_write(struct file *filp, if (!error) return 0; - DRM_DEBUG_DRIVER("Resetting error state\n"); + drm_dbg(&error->i915->drm, "Resetting error state\n"); i915_reset_error_state(error->i915); return cnt; @@ -1251,286 +1247,6 @@ static int i915_llc(struct seq_file *m, void *data) return 0; } -static int i915_huc_load_status_info(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - intel_wakeref_t wakeref; - struct drm_printer p; - - if (!HAS_GT_UC(dev_priv)) - return -ENODEV; - - p = drm_seq_file_printer(m); - intel_uc_fw_dump(&dev_priv->gt.uc.huc.fw, &p); - - with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) - seq_printf(m, "\nHuC status 0x%08x:\n", I915_READ(HUC_STATUS2)); - - return 0; -} - -static int i915_guc_load_status_info(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - intel_wakeref_t wakeref; - struct drm_printer p; - - if (!HAS_GT_UC(dev_priv)) - return -ENODEV; - - p = drm_seq_file_printer(m); - intel_uc_fw_dump(&dev_priv->gt.uc.guc.fw, &p); - - with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) { - u32 tmp = I915_READ(GUC_STATUS); - u32 i; - - seq_printf(m, "\nGuC status 0x%08x:\n", tmp); - seq_printf(m, "\tBootrom status = 0x%x\n", - (tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT); - seq_printf(m, "\tuKernel status = 0x%x\n", - (tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT); - seq_printf(m, "\tMIA Core status = 0x%x\n", - (tmp & GS_MIA_MASK) >> GS_MIA_SHIFT); - seq_puts(m, "\nScratch registers:\n"); - for (i = 0; i < 16; i++) { - seq_printf(m, "\t%2d: \t0x%x\n", - i, I915_READ(SOFT_SCRATCH(i))); - } - } - - return 0; -} - -static const char * -stringify_guc_log_type(enum guc_log_buffer_type type) -{ - switch (type) { - case GUC_ISR_LOG_BUFFER: - return "ISR"; - case GUC_DPC_LOG_BUFFER: - return "DPC"; - case GUC_CRASH_DUMP_LOG_BUFFER: - return "CRASH"; - default: - MISSING_CASE(type); - } - - return ""; -} - -static void i915_guc_log_info(struct seq_file *m, struct intel_guc_log *log) -{ - enum guc_log_buffer_type type; - - if (!intel_guc_log_relay_created(log)) { - seq_puts(m, "GuC log relay not created\n"); - return; - } - - seq_puts(m, "GuC logging stats:\n"); - - seq_printf(m, "\tRelay full count: %u\n", - log->relay.full_count); - - for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { - seq_printf(m, "\t%s:\tflush count %10u, overflow count %10u\n", - stringify_guc_log_type(type), - log->stats[type].flush, - log->stats[type].sampled_overflow); - } -} - -static int i915_guc_info(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct intel_uc *uc = &dev_priv->gt.uc; - - if (!intel_uc_uses_guc(uc)) - return -ENODEV; - - i915_guc_log_info(m, &uc->guc.log); - - /* Add more as required ... */ - - return 0; -} - -static int i915_guc_stage_pool(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct intel_uc *uc = &dev_priv->gt.uc; - struct guc_stage_desc *desc = uc->guc.stage_desc_pool_vaddr; - int index; - - if (!intel_uc_uses_guc_submission(uc)) - return -ENODEV; - - for (index = 0; index < GUC_MAX_STAGE_DESCRIPTORS; index++, desc++) { - struct intel_engine_cs *engine; - - if (!(desc->attribute & GUC_STAGE_DESC_ATTR_ACTIVE)) - continue; - - seq_printf(m, "GuC stage descriptor %u:\n", index); - seq_printf(m, "\tIndex: %u\n", desc->stage_id); - seq_printf(m, "\tAttribute: 0x%x\n", desc->attribute); - seq_printf(m, "\tPriority: %d\n", desc->priority); - seq_printf(m, "\tDoorbell id: %d\n", desc->db_id); - seq_printf(m, "\tEngines used: 0x%x\n", - desc->engines_used); - seq_printf(m, "\tDoorbell trigger phy: 0x%llx, cpu: 0x%llx, uK: 0x%x\n", - desc->db_trigger_phy, - desc->db_trigger_cpu, - desc->db_trigger_uk); - seq_printf(m, "\tProcess descriptor: 0x%x\n", - desc->process_desc); - seq_printf(m, "\tWorkqueue address: 0x%x, size: 0x%x\n", - desc->wq_addr, desc->wq_size); - seq_putc(m, '\n'); - - for_each_uabi_engine(engine, dev_priv) { - u32 guc_engine_id = engine->guc_id; - struct guc_execlist_context *lrc = - &desc->lrc[guc_engine_id]; - - seq_printf(m, "\t%s LRC:\n", engine->name); - seq_printf(m, "\t\tContext desc: 0x%x\n", - lrc->context_desc); - seq_printf(m, "\t\tContext id: 0x%x\n", lrc->context_id); - seq_printf(m, "\t\tLRCA: 0x%x\n", lrc->ring_lrca); - seq_printf(m, "\t\tRing begin: 0x%x\n", lrc->ring_begin); - seq_printf(m, "\t\tRing end: 0x%x\n", lrc->ring_end); - seq_putc(m, '\n'); - } - } - - return 0; -} - -static int i915_guc_log_dump(struct seq_file *m, void *data) -{ - struct drm_info_node *node = m->private; - struct drm_i915_private *dev_priv = node_to_i915(node); - bool dump_load_err = !!node->info_ent->data; - struct drm_i915_gem_object *obj = NULL; - u32 *log; - int i = 0; - - if (!HAS_GT_UC(dev_priv)) - return -ENODEV; - - if (dump_load_err) - obj = dev_priv->gt.uc.load_err_log; - else if (dev_priv->gt.uc.guc.log.vma) - obj = dev_priv->gt.uc.guc.log.vma->obj; - - if (!obj) - return 0; - - log = i915_gem_object_pin_map(obj, I915_MAP_WC); - if (IS_ERR(log)) { - DRM_DEBUG("Failed to pin object\n"); - seq_puts(m, "(log data unaccessible)\n"); - return PTR_ERR(log); - } - - for (i = 0; i < obj->base.size / sizeof(u32); i += 4) - seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n", - *(log + i), *(log + i + 1), - *(log + i + 2), *(log + i + 3)); - - seq_putc(m, '\n'); - - i915_gem_object_unpin_map(obj); - - return 0; -} - -static int i915_guc_log_level_get(void *data, u64 *val) -{ - struct drm_i915_private *dev_priv = data; - struct intel_uc *uc = &dev_priv->gt.uc; - - if (!intel_uc_uses_guc(uc)) - return -ENODEV; - - *val = intel_guc_log_get_level(&uc->guc.log); - - return 0; -} - -static int i915_guc_log_level_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - struct intel_uc *uc = &dev_priv->gt.uc; - - if (!intel_uc_uses_guc(uc)) - return -ENODEV; - - return intel_guc_log_set_level(&uc->guc.log, val); -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_level_fops, - i915_guc_log_level_get, i915_guc_log_level_set, - "%lld\n"); - -static int i915_guc_log_relay_open(struct inode *inode, struct file *file) -{ - struct drm_i915_private *i915 = inode->i_private; - struct intel_guc *guc = &i915->gt.uc.guc; - struct intel_guc_log *log = &guc->log; - - if (!intel_guc_is_ready(guc)) - return -ENODEV; - - file->private_data = log; - - return intel_guc_log_relay_open(log); -} - -static ssize_t -i915_guc_log_relay_write(struct file *filp, - const char __user *ubuf, - size_t cnt, - loff_t *ppos) -{ - struct intel_guc_log *log = filp->private_data; - int val; - int ret; - - ret = kstrtoint_from_user(ubuf, cnt, 0, &val); - if (ret < 0) - return ret; - - /* - * Enable and start the guc log relay on value of 1. - * Flush log relay for any other value. - */ - if (val == 1) - ret = intel_guc_log_relay_start(log); - else - intel_guc_log_relay_flush(log); - - return ret ?: cnt; -} - -static int i915_guc_log_relay_release(struct inode *inode, struct file *file) -{ - struct drm_i915_private *i915 = inode->i_private; - struct intel_guc *guc = &i915->gt.uc.guc; - - intel_guc_log_relay_close(&guc->log); - return 0; -} - -static const struct file_operations i915_guc_log_relay_fops = { - .owner = THIS_MODULE, - .open = i915_guc_log_relay_open, - .write = i915_guc_log_relay_write, - .release = i915_guc_log_relay_release, -}; - static int i915_runtime_pm_status(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -2139,12 +1855,6 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_objects", i915_gem_object_info, 0}, {"i915_gem_fence_regs", i915_gem_fence_regs_info, 0}, {"i915_gem_interrupt", i915_interrupt_info, 0}, - {"i915_guc_info", i915_guc_info, 0}, - {"i915_guc_load_status", i915_guc_load_status_info, 0}, - {"i915_guc_log_dump", i915_guc_log_dump, 0}, - {"i915_guc_load_err_log_dump", i915_guc_log_dump, 0, (void *)1}, - {"i915_guc_stage_pool", i915_guc_stage_pool, 0}, - {"i915_huc_load_status", i915_huc_load_status_info, 0}, {"i915_frequency_info", i915_frequency_info, 0}, {"i915_ring_freq_table", i915_ring_freq_table, 0}, {"i915_context_status", i915_context_status, 0}, @@ -2172,8 +1882,6 @@ static const struct i915_debugfs_files { {"i915_error_state", &i915_error_state_fops}, {"i915_gpu_info", &i915_gpu_info_fops}, #endif - {"i915_guc_log_level", &i915_guc_log_level_fops}, - {"i915_guc_log_relay", &i915_guc_log_relay_fops}, }; void i915_debugfs_register(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 6116dab3d059..641f5e03b661 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -432,8 +432,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) mutex_init(&dev_priv->backlight_lock); mutex_init(&dev_priv->sb_lock); - pm_qos_add_request(&dev_priv->sb_qos, - PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE); mutex_init(&dev_priv->av_mutex); mutex_init(&dev_priv->wm.wm_mutex); @@ -497,7 +496,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv) vlv_suspend_cleanup(dev_priv); i915_workqueues_cleanup(dev_priv); - pm_qos_remove_request(&dev_priv->sb_qos); + cpu_latency_qos_remove_request(&dev_priv->sb_qos); mutex_destroy(&dev_priv->sb_lock); } @@ -674,8 +673,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) } } - pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY, - PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE); intel_gt_init_workarounds(dev_priv); @@ -721,7 +719,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) err_msi: if (pdev->msi_enabled) pci_disable_msi(pdev); - pm_qos_remove_request(&dev_priv->pm_qos); + cpu_latency_qos_remove_request(&dev_priv->pm_qos); err_mem_regions: intel_memory_regions_driver_release(dev_priv); err_ggtt: @@ -744,7 +742,7 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) if (pdev->msi_enabled) pci_disable_msi(pdev); - pm_qos_remove_request(&dev_priv->pm_qos); + cpu_latency_qos_remove_request(&dev_priv->pm_qos); } /** @@ -1284,7 +1282,6 @@ static int i915_drm_resume(struct drm_device *dev) drm_err(&dev_priv->drm, "failed to re-enable GGTT\n"); i915_ggtt_resume(&dev_priv->ggtt); - i915_gem_restore_fences(&dev_priv->ggtt); intel_csr_ucode_resume(dev_priv); @@ -1602,8 +1599,6 @@ static int intel_runtime_suspend(struct device *kdev) intel_gt_runtime_resume(&dev_priv->gt); - i915_gem_restore_fences(&dev_priv->ggtt); - enable_rpm_wakeref_asserts(rpm); return ret; @@ -1683,7 +1678,6 @@ static int intel_runtime_resume(struct device *kdev) * we can do is to hope that things will still work (and disable RPM). */ intel_gt_runtime_resume(&dev_priv->gt); - i915_gem_restore_fences(&dev_priv->ggtt); /* * On VLV/CHV display interrupts are part of the display diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e0a83b8e34dc..b00f0845cbc3 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -92,7 +92,6 @@ #include "intel_wopcm.h" #include "i915_gem.h" -#include "i915_gem_fence_reg.h" #include "i915_gem_gtt.h" #include "i915_gpu_error.h" #include "i915_perf_types.h" @@ -109,8 +108,8 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20200313" -#define DRIVER_TIMESTAMP 1584144591 +#define DRIVER_DATE "20200417" +#define DRIVER_TIMESTAMP 1587105300 struct drm_i915_gem_object; @@ -417,6 +416,7 @@ struct intel_fbc { struct { const struct drm_format_info *format; unsigned int stride; + u64 modifier; } fb; u16 gen9_wa_cfb_stride; s8 fence_id; @@ -540,7 +540,6 @@ struct i915_suspend_saved_registers { u32 saveSWF0[16]; u32 saveSWF1[16]; u32 saveSWF3[3]; - u64 saveFENCE[I915_MAX_NUM_FENCES]; u32 savePCH_PORT_HOTPLUG; u16 saveGCDGMBUS; }; @@ -888,7 +887,6 @@ struct drm_i915_private { struct pci_dev *bridge_dev; - struct intel_engine_cs *engine[I915_NUM_ENGINES]; struct rb_root uabi_engines; struct resource mch_res; @@ -1510,6 +1508,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_ICELAKE(p) && IS_REVID(p, since, until)) #define TGL_REVID_A0 0x0 +#define TGL_REVID_B0 0x1 +#define TGL_REVID_C0 0x2 #define IS_TGL_REVID(p, since, until) \ (IS_TIGERLAKE(p) && IS_REVID(p, since, until)) @@ -1607,7 +1607,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_DDI(dev_priv) (INTEL_INFO(dev_priv)->display.has_ddi) #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->has_fpga_dbg) #define HAS_PSR(dev_priv) (INTEL_INFO(dev_priv)->display.has_psr) -#define HAS_TRANSCODER_EDP(dev_priv) (INTEL_INFO(dev_priv)->trans_offsets[TRANSCODER_EDP] != 0) +#define HAS_TRANSCODER(dev_priv, trans) ((INTEL_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0) #define HAS_RC6(dev_priv) (INTEL_INFO(dev_priv)->has_rc6) #define HAS_RC6p(dev_priv) (INTEL_INFO(dev_priv)->has_rc6p) @@ -1741,6 +1741,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, unsigned long flags); #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) #define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1) +#define I915_GEM_OBJECT_UNBIND_TEST BIT(2) void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index ca5420012a22..0cbcb9f54e7d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -118,7 +118,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, struct i915_vma *vma; int ret; - if (!atomic_read(&obj->bind_count)) + if (list_empty(&obj->vma.list)) return 0; /* @@ -141,6 +141,11 @@ try_again: if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK)) continue; + if (flags & I915_GEM_OBJECT_UNBIND_TEST) { + ret = -EBUSY; + break; + } + ret = -EAGAIN; if (!i915_vm_tryopen(vm)) break; @@ -993,18 +998,16 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, return ERR_PTR(ret); } + ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + if (ret) + return ERR_PTR(ret); + if (vma->fence && !i915_gem_object_is_tiled(obj)) { mutex_lock(&ggtt->vm.mutex); - ret = i915_vma_revoke_fence(vma); + i915_vma_revoke_fence(vma); mutex_unlock(&ggtt->vm.mutex); - if (ret) - return ERR_PTR(ret); } - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); - if (ret) - return ERR_PTR(ret); - ret = i915_vma_wait_for_bind(vma); if (ret) { i915_vma_unpin(vma); @@ -1156,7 +1159,6 @@ err_unlock: /* Minimal basic recovery for KMS */ ret = i915_ggtt_enable_hw(dev_priv); i915_ggtt_resume(&dev_priv->ggtt); - i915_gem_restore_fences(&dev_priv->ggtt); intel_init_clock_gating(dev_priv); } diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 4518b9b35c3d..0ba7b1e881c0 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -228,7 +228,12 @@ found: while (ret == 0 && (node = drm_mm_scan_color_evict(&scan))) { vma = container_of(node, struct i915_vma, node); - ret = __i915_vma_unbind(vma); + + /* If we find any non-objects (!vma), we cannot evict them */ + if (vma->node.color != I915_COLOR_UNEVICTABLE) + ret = __i915_vma_unbind(vma); + else + ret = -ENOSPC; /* XXX search failed, try again? */ } return ret; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a4cd0ba5464..424ad975a360 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1858,7 +1858,7 @@ void i915_error_state_store(struct i915_gpu_coredump *error) return; i915 = error->i915; - dev_info(i915->drm.dev, "%s\n", error_msg(error)); + drm_info(&i915->drm, "%s\n", error_msg(error)); if (error->simulated || cmpxchg(&i915->gpu_error.first_error, NULL, error)) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9f0653cf0510..1502ab44f1a5 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3658,7 +3658,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg) intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]); + intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); if (iir & I915_MASTER_ERROR_INTERRUPT) i8xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -3763,7 +3763,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg) I915_WRITE(GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]); + intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); if (iir & I915_MASTER_ERROR_INTERRUPT) i9xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -3905,10 +3905,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) I915_WRITE(GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]); + intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); if (iir & I915_BSD_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->engine[VCS0]); + intel_engine_signal_breadcrumbs(dev_priv->gt.engine[VCS0]); if (iir & I915_MASTER_ERROR_INTERRUPT) i9xx_error_irq_handler(dev_priv, eir, eir_stuck); diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c index fdd550405fd3..7b3b83bd5ab8 100644 --- a/drivers/gpu/drm/i915/i915_memcpy.c +++ b/drivers/gpu/drm/i915/i915_memcpy.c @@ -35,7 +35,6 @@ static DEFINE_STATIC_KEY_FALSE(has_movntdqa); -#ifdef CONFIG_AS_MOVNTDQA static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) { kernel_fpu_begin(); @@ -93,10 +92,6 @@ static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) kernel_fpu_end(); } -#else -static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) {} -static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) {} -#endif /** * i915_memcpy_from_wc: perform an accelerated *aligned* read from WC diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 2c80a0194c80..66738f2c4f28 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -160,6 +160,7 @@ GEN(2), \ .is_mobile = 1, \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_overlay = 1, \ .display.cursor_needs_physical = 1, \ .display.overlay_needs_physical = 1, \ @@ -179,6 +180,7 @@ #define I845_FEATURES \ GEN(2), \ .pipe_mask = BIT(PIPE_A), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A), \ .display.has_overlay = 1, \ .display.overlay_needs_physical = 1, \ .display.has_gmch = 1, \ @@ -218,6 +220,7 @@ static const struct intel_device_info i865g_info = { #define GEN3_FEATURES \ GEN(3), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ .engine_mask = BIT(RCS0), \ @@ -303,6 +306,7 @@ static const struct intel_device_info pnv_m_info = { #define GEN4_FEATURES \ GEN(4), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ @@ -354,6 +358,7 @@ static const struct intel_device_info gm45_info = { #define GEN5_FEATURES \ GEN(5), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .engine_mask = BIT(RCS0) | BIT(VCS0), \ .has_snoop = true, \ @@ -381,6 +386,7 @@ static const struct intel_device_info ilk_m_info = { #define GEN6_FEATURES \ GEN(6), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .display.has_fbc = 1, \ .engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ @@ -430,6 +436,7 @@ static const struct intel_device_info snb_m_gt2_info = { #define GEN7_FEATURES \ GEN(7), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \ .display.has_hotplug = 1, \ .display.has_fbc = 1, \ .engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ @@ -482,6 +489,7 @@ static const struct intel_device_info ivb_q_info = { PLATFORM(INTEL_IVYBRIDGE), .gt = 2, .pipe_mask = 0, /* legal, last one wins */ + .cpu_transcoder_mask = 0, .has_l3_dpf = 1, }; @@ -490,6 +498,7 @@ static const struct intel_device_info vlv_info = { GEN(7), .is_lp = 1, .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), .has_runtime_pm = 1, .has_rc6 = 1, .has_rps = true, @@ -511,6 +520,8 @@ static const struct intel_device_info vlv_info = { #define G75_FEATURES \ GEN7_FEATURES, \ .engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP), \ .display.has_ddi = 1, \ .has_fpga_dbg = 1, \ .display.has_psr = 1, \ @@ -581,6 +592,7 @@ static const struct intel_device_info chv_info = { PLATFORM(INTEL_CHERRYVIEW), GEN(8), .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), .display.has_hotplug = 1, .is_lp = 1, .engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), @@ -656,6 +668,9 @@ static const struct intel_device_info skl_gt4_info = { .display.has_hotplug = 1, \ .engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ + BIT(TRANSCODER_DSI_A) | BIT(TRANSCODER_DSI_C), \ .has_64bit_reloc = 1, \ .display.has_ddi = 1, \ .has_fpga_dbg = 1, \ @@ -759,6 +774,9 @@ static const struct intel_device_info cnl_info = { #define GEN11_FEATURES \ GEN10_FEATURES, \ GEN11_DEFAULT_PAGE_SIZES, \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ + BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .pipe_offsets = { \ [TRANSCODER_A] = PIPE_A_OFFSET, \ [TRANSCODER_B] = PIPE_B_OFFSET, \ @@ -799,6 +817,10 @@ static const struct intel_device_info ehl_info = { #define GEN12_FEATURES \ GEN11_FEATURES, \ GEN(12), \ + .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ + .cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | \ + BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .pipe_offsets = { \ [TRANSCODER_A] = PIPE_A_OFFSET, \ [TRANSCODER_B] = PIPE_B_OFFSET, \ @@ -822,7 +844,6 @@ static const struct intel_device_info ehl_info = { static const struct intel_device_info tgl_info = { GEN12_FEATURES, PLATFORM(INTEL_TIGERLAKE), - .pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), .display.has_modular_fia = 1, .engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 1b074bb4a7fe..5cde3e4e7be6 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -204,21 +204,6 @@ #include "i915_drv.h" #include "i915_perf.h" -#include "oa/i915_oa_hsw.h" -#include "oa/i915_oa_bdw.h" -#include "oa/i915_oa_chv.h" -#include "oa/i915_oa_sklgt2.h" -#include "oa/i915_oa_sklgt3.h" -#include "oa/i915_oa_sklgt4.h" -#include "oa/i915_oa_bxt.h" -#include "oa/i915_oa_kblgt2.h" -#include "oa/i915_oa_kblgt3.h" -#include "oa/i915_oa_glk.h" -#include "oa/i915_oa_cflgt2.h" -#include "oa/i915_oa_cflgt3.h" -#include "oa/i915_oa_cnl.h" -#include "oa/i915_oa_icl.h" -#include "oa/i915_oa_tgl.h" /* HW requires this to be a power of two, between 128k and 16M, though driver * is currently generally designed assuming the largest 16M size is used such @@ -238,26 +223,17 @@ * * Although this can be observed explicitly while copying reports to userspace * by checking for a zeroed report-id field in tail reports, we want to account - * for this earlier, as part of the oa_buffer_check to avoid lots of redundant - * read() attempts. - * - * In effect we define a tail pointer for reading that lags the real tail - * pointer by at least %OA_TAIL_MARGIN_NSEC nanoseconds, which gives enough - * time for the corresponding reports to become visible to the CPU. - * - * To manage this we actually track two tail pointers: - * 1) An 'aging' tail with an associated timestamp that is tracked until we - * can trust the corresponding data is visible to the CPU; at which point - * it is considered 'aged'. - * 2) An 'aged' tail that can be used for read()ing. - * - * The two separate pointers let us decouple read()s from tail pointer aging. - * - * The tail pointers are checked and updated at a limited rate within a hrtimer - * callback (the same callback that is used for delivering EPOLLIN events) - * - * Initially the tails are marked invalid with %INVALID_TAIL_PTR which - * indicates that an updated tail pointer is needed. + * for this earlier, as part of the oa_buffer_check_unlocked to avoid lots of + * redundant read() attempts. + * + * We workaround this issue in oa_buffer_check_unlocked() by reading the reports + * in the OA buffer, starting from the tail reported by the HW until we find a + * report with its first 2 dwords not 0 meaning its previous report is + * completely in memory and ready to be read. Those dwords are also set to 0 + * once read and the whole buffer is cleared upon OA buffer initialization. The + * first dword is the reason for this report while the second is the timestamp, + * making the chances of having those 2 fields at 0 fairly unlikely. A more + * detailed explanation is available in oa_buffer_check_unlocked(). * * Most of the implementation details for this workaround are in * oa_buffer_check_unlocked() and _append_oa_reports() @@ -272,11 +248,11 @@ #define OA_TAIL_MARGIN_NSEC 100000ULL #define INVALID_TAIL_PTR 0xffffffff -/* frequency for checking whether the OA unit has written new reports to the - * circular OA buffer... +/* The default frequency for checking whether the OA unit has written new + * reports to the circular OA buffer... */ -#define POLL_FREQUENCY 200 -#define POLL_PERIOD (NSEC_PER_SEC / POLL_FREQUENCY) +#define DEFAULT_POLL_FREQUENCY_HZ 200 +#define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ) /* for sysctl proc_dointvec_minmax of dev.i915.perf_stream_paranoid */ static u32 i915_perf_stream_paranoid = true; @@ -359,6 +335,12 @@ static const struct i915_oa_format gen12_oa_formats[I915_OA_FORMAT_MAX] = { * @oa_periodic: Whether to enable periodic OA unit sampling * @oa_period_exponent: The OA unit sampling period is derived from this * @engine: The engine (typically rcs0) being monitored by the OA unit + * @has_sseu: Whether @sseu was specified by userspace + * @sseu: internal SSEU configuration computed either from the userspace + * specified configuration in the opening parameters or a default value + * (see get_default_sseu_config()) + * @poll_oa_period: The period in nanoseconds at which the CPU will check for OA + * data availability * * As read_properties_unlocked() enumerates and validates the properties given * to open a stream of metrics the configuration is built up in the structure @@ -378,6 +360,11 @@ struct perf_open_properties { int oa_period_exponent; struct intel_engine_cs *engine; + + bool has_sseu; + struct intel_sseu sseu; + + u64 poll_oa_period; }; struct i915_oa_config_bo { @@ -409,10 +396,7 @@ i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set) struct i915_oa_config *oa_config; rcu_read_lock(); - if (metrics_set == 1) - oa_config = &perf->test_config; - else - oa_config = idr_find(&perf->metrics_idr, metrics_set); + oa_config = idr_find(&perf->metrics_idr, metrics_set); if (oa_config) oa_config = i915_oa_config_get(oa_config); rcu_read_unlock(); @@ -465,8 +449,8 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream) * (See description of OA_TAIL_MARGIN_NSEC above for further details.) * * Besides returning true when there is data available to read() this function - * also has the side effect of updating the oa_buffer.tails[], .aging_timestamp - * and .aged_tail_idx state used for reading. + * also updates the tail, aging_tail and aging_timestamp in the oa_buffer + * object. * * Note: It's safe to read OA config state here unlocked, assuming that this is * only called while the stream is enabled, while the global OA configuration @@ -476,28 +460,19 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream) */ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) { + u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma); int report_size = stream->oa_buffer.format_size; unsigned long flags; - unsigned int aged_idx; - u32 head, hw_tail, aged_tail, aging_tail; + bool pollin; + u32 hw_tail; u64 now; /* We have to consider the (unlikely) possibility that read() errors - * could result in an OA buffer reset which might reset the head, - * tails[] and aged_tail state. + * could result in an OA buffer reset which might reset the head and + * tail state. */ spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); - /* NB: The head we observe here might effectively be a little out of - * date (between head and tails[aged_idx].offset if there is currently - * a read() in progress. - */ - head = stream->oa_buffer.head; - - aged_idx = stream->oa_buffer.aged_tail_idx; - aged_tail = stream->oa_buffer.tails[aged_idx].offset; - aging_tail = stream->oa_buffer.tails[!aged_idx].offset; - hw_tail = stream->perf->ops.oa_hw_tail_read(stream); /* The tail pointer increases in 64 byte increments, @@ -507,64 +482,63 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) now = ktime_get_mono_fast_ns(); - /* Update the aged tail - * - * Flip the tail pointer available for read()s once the aging tail is - * old enough to trust that the corresponding data will be visible to - * the CPU... - * - * Do this before updating the aging pointer in case we may be able to - * immediately start aging a new pointer too (if new data has become - * available) without needing to wait for a later hrtimer callback. - */ - if (aging_tail != INVALID_TAIL_PTR && - ((now - stream->oa_buffer.aging_timestamp) > - OA_TAIL_MARGIN_NSEC)) { - - aged_idx ^= 1; - stream->oa_buffer.aged_tail_idx = aged_idx; + if (hw_tail == stream->oa_buffer.aging_tail && + (now - stream->oa_buffer.aging_timestamp) > OA_TAIL_MARGIN_NSEC) { + /* If the HW tail hasn't move since the last check and the HW + * tail has been aging for long enough, declare it the new + * tail. + */ + stream->oa_buffer.tail = stream->oa_buffer.aging_tail; + } else { + u32 head, tail, aged_tail; - aged_tail = aging_tail; + /* NB: The head we observe here might effectively be a little + * out of date. If a read() is in progress, the head could be + * anywhere between this head and stream->oa_buffer.tail. + */ + head = stream->oa_buffer.head - gtt_offset; + aged_tail = stream->oa_buffer.tail - gtt_offset; + + hw_tail -= gtt_offset; + tail = hw_tail; + + /* Walk the stream backward until we find a report with dword 0 + * & 1 not at 0. Since the circular buffer pointers progress by + * increments of 64 bytes and that reports can be up to 256 + * bytes long, we can't tell whether a report has fully landed + * in memory before the first 2 dwords of the following report + * have effectively landed. + * + * This is assuming that the writes of the OA unit land in + * memory in the order they were written to. + * If not : (╯°□°）╯︵ ┻━┻ + */ + while (OA_TAKEN(tail, aged_tail) >= report_size) { + u32 *report32 = (void *)(stream->oa_buffer.vaddr + tail); - /* Mark that we need a new pointer to start aging... */ - stream->oa_buffer.tails[!aged_idx].offset = INVALID_TAIL_PTR; - aging_tail = INVALID_TAIL_PTR; - } + if (report32[0] != 0 || report32[1] != 0) + break; - /* Update the aging tail - * - * We throttle aging tail updates until we have a new tail that - * represents >= one report more data than is already available for - * reading. This ensures there will be enough data for a successful - * read once this new pointer has aged and ensures we will give the new - * pointer time to age. - */ - if (aging_tail == INVALID_TAIL_PTR && - (aged_tail == INVALID_TAIL_PTR || - OA_TAKEN(hw_tail, aged_tail) >= report_size)) { - struct i915_vma *vma = stream->oa_buffer.vma; - u32 gtt_offset = i915_ggtt_offset(vma); - - /* Be paranoid and do a bounds check on the pointer read back - * from hardware, just in case some spurious hardware condition - * could put the tail out of bounds... - */ - if (hw_tail >= gtt_offset && - hw_tail < (gtt_offset + OA_BUFFER_SIZE)) { - stream->oa_buffer.tails[!aged_idx].offset = - aging_tail = hw_tail; - stream->oa_buffer.aging_timestamp = now; - } else { - drm_err(&stream->perf->i915->drm, - "Ignoring spurious out of range OA buffer tail pointer = %x\n", - hw_tail); + tail = (tail - report_size) & (OA_BUFFER_SIZE - 1); } + + if (OA_TAKEN(hw_tail, tail) > report_size && + __ratelimit(&stream->perf->tail_pointer_race)) + DRM_NOTE("unlanded report(s) head=0x%x " + "tail=0x%x hw_tail=0x%x\n", + head, tail, hw_tail); + + stream->oa_buffer.tail = gtt_offset + tail; + stream->oa_buffer.aging_tail = gtt_offset + hw_tail; + stream->oa_buffer.aging_timestamp = now; } + pollin = OA_TAKEN(stream->oa_buffer.tail - gtt_offset, + stream->oa_buffer.head - gtt_offset) >= report_size; + spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); - return aged_tail == INVALID_TAIL_PTR ? - false : OA_TAKEN(aged_tail, head) >= report_size; + return pollin; } /** @@ -682,7 +656,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, u32 mask = (OA_BUFFER_SIZE - 1); size_t start_offset = *offset; unsigned long flags; - unsigned int aged_tail_idx; u32 head, tail; u32 taken; int ret = 0; @@ -693,19 +666,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); head = stream->oa_buffer.head; - aged_tail_idx = stream->oa_buffer.aged_tail_idx; - tail = stream->oa_buffer.tails[aged_tail_idx].offset; + tail = stream->oa_buffer.tail; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); /* - * An invalid tail pointer here means we're still waiting for the poll - * hrtimer callback to give us a pointer - */ - if (tail == INVALID_TAIL_PTR) - return -EAGAIN; - - /* * NB: oa_buffer.head/tail include the gtt_offset which we don't want * while indexing relative to oa_buf_base. */ @@ -838,13 +803,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, } /* - * The above reason field sanity check is based on - * the assumption that the OA buffer is initially - * zeroed and we reset the field after copying so the - * check is still meaningful once old reports start - * being overwritten. + * Clear out the first 2 dword as a mean to detect unlanded + * reports. */ report32[0] = 0; + report32[1] = 0; } if (start_offset != *offset) { @@ -985,7 +948,6 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, u32 mask = (OA_BUFFER_SIZE - 1); size_t start_offset = *offset; unsigned long flags; - unsigned int aged_tail_idx; u32 head, tail; u32 taken; int ret = 0; @@ -996,17 +958,10 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); head = stream->oa_buffer.head; - aged_tail_idx = stream->oa_buffer.aged_tail_idx; - tail = stream->oa_buffer.tails[aged_tail_idx].offset; + tail = stream->oa_buffer.tail; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); - /* An invalid tail pointer here means we're still waiting for the poll - * hrtimer callback to give us a pointer - */ - if (tail == INVALID_TAIL_PTR) - return -EAGAIN; - /* NB: oa_buffer.head/tail include the gtt_offset which we don't want * while indexing relative to oa_buf_base. */ @@ -1064,13 +1019,11 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, if (ret) break; - /* The above report-id field sanity check is based on - * the assumption that the OA buffer is initially - * zeroed and we reset the field after copying so the - * check is still meaningful once old reports start - * being overwritten. + /* Clear out the first 2 dwords as a mean to detect unlanded + * reports. */ report32[0] = 0; + report32[1] = 0; } if (start_offset != *offset) { @@ -1449,8 +1402,8 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream) gtt_offset | OABUFFER_SIZE_16M); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR; - stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR; + stream->oa_buffer.aging_tail = INVALID_TAIL_PTR; + stream->oa_buffer.tail = gtt_offset; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); @@ -1472,8 +1425,6 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream) * memory... */ memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE); - - stream->pollin = false; } static void gen8_init_oa_buffer(struct i915_perf_stream *stream) @@ -1503,8 +1454,8 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream) intel_uncore_write(uncore, GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR; - stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR; + stream->oa_buffer.aging_tail = INVALID_TAIL_PTR; + stream->oa_buffer.tail = gtt_offset; /* * Reset state used to recognise context switches, affecting which @@ -1528,8 +1479,6 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream) * memory... */ memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE); - - stream->pollin = false; } static void gen12_init_oa_buffer(struct i915_perf_stream *stream) @@ -1559,8 +1508,8 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) gtt_offset & GEN12_OAG_OATAILPTR_MASK); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR; - stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR; + stream->oa_buffer.aging_tail = INVALID_TAIL_PTR; + stream->oa_buffer.tail = gtt_offset; /* * Reset state used to recognise context switches, affecting which @@ -1585,8 +1534,6 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) */ memset(stream->oa_buffer.vaddr, 0, stream->oa_buffer.vma->size); - - stream->pollin = false; } static int alloc_oa_buffer(struct i915_perf_stream *stream) @@ -1972,10 +1919,11 @@ out: return i915_vma_get(oa_bo->vma); } -static struct i915_request * +static int emit_oa_config(struct i915_perf_stream *stream, struct i915_oa_config *oa_config, - struct intel_context *ce) + struct intel_context *ce, + struct i915_active *active) { struct i915_request *rq; struct i915_vma *vma; @@ -1983,7 +1931,7 @@ emit_oa_config(struct i915_perf_stream *stream, vma = get_oa_vma(stream, oa_config); if (IS_ERR(vma)) - return ERR_CAST(vma); + return PTR_ERR(vma); err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); if (err) @@ -1997,6 +1945,18 @@ emit_oa_config(struct i915_perf_stream *stream, goto err_vma_unpin; } + if (!IS_ERR_OR_NULL(active)) { + /* After all individual context modifications */ + err = i915_request_await_active(rq, active, + I915_ACTIVE_AWAIT_ACTIVE); + if (err) + goto err_add_request; + + err = i915_active_add_request(active, rq); + if (err) + goto err_add_request; + } + i915_vma_lock(vma); err = i915_request_await_object(rq, vma->obj, 0); if (!err) @@ -2011,14 +1971,13 @@ emit_oa_config(struct i915_perf_stream *stream, if (err) goto err_add_request; - i915_request_get(rq); err_add_request: i915_request_add(rq); err_vma_unpin: i915_vma_unpin(vma); err_vma_put: i915_vma_put(vma); - return err ? ERR_PTR(err) : rq; + return err; } static struct intel_context *oa_context(struct i915_perf_stream *stream) @@ -2026,8 +1985,9 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream) return stream->pinned_ctx ?: stream->engine->kernel_context; } -static struct i915_request * -hsw_enable_metric_set(struct i915_perf_stream *stream) +static int +hsw_enable_metric_set(struct i915_perf_stream *stream, + struct i915_active *active) { struct intel_uncore *uncore = stream->uncore; @@ -2046,7 +2006,9 @@ hsw_enable_metric_set(struct i915_perf_stream *stream) intel_uncore_rmw(uncore, GEN6_UCGCTL1, 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE); - return emit_oa_config(stream, stream->oa_config, oa_context(stream)); + return emit_oa_config(stream, + stream->oa_config, oa_context(stream), + active); } static void hsw_disable_metric_set(struct i915_perf_stream *stream) @@ -2116,9 +2078,6 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce, for (i = 0; i < ARRAY_SIZE(flex_regs); i++) reg_state[ctx_flexeu0 + i * 2 + 1] = oa_config_flex_reg(stream->oa_config, flex_regs[i]); - - reg_state[CTX_R_PWR_CLK_STATE] = - intel_sseu_make_rpcs(ce->engine->i915, &ce->sseu); } struct flex { @@ -2196,8 +2155,10 @@ static int gen8_modify_context(struct intel_context *ce, return err; } -static int gen8_modify_self(struct intel_context *ce, - const struct flex *flex, unsigned int count) +static int +gen8_modify_self(struct intel_context *ce, + const struct flex *flex, unsigned int count, + struct i915_active *active) { struct i915_request *rq; int err; @@ -2208,8 +2169,17 @@ static int gen8_modify_self(struct intel_context *ce, if (IS_ERR(rq)) return PTR_ERR(rq); + if (!IS_ERR_OR_NULL(active)) { + err = i915_active_add_request(active, rq); + if (err) + goto err_add_request; + } + err = gen8_load_flex(rq, ce, flex, count); + if (err) + goto err_add_request; +err_add_request: i915_request_add(rq); return err; } @@ -2243,7 +2213,8 @@ static int gen8_configure_context(struct i915_gem_context *ctx, return err; } -static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable) +static int gen12_configure_oar_context(struct i915_perf_stream *stream, + struct i915_active *active) { int err; struct intel_context *ce = stream->pinned_ctx; @@ -2252,7 +2223,7 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena { GEN8_OACTXCONTROL, stream->perf->ctx_oactxctrl_offset + 1, - enable ? GEN8_OA_COUNTER_RESUME : 0, + active ? GEN8_OA_COUNTER_RESUME : 0, }, }; /* Offsets in regs_lri are not used since this configuration is only @@ -2264,13 +2235,13 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena GEN12_OAR_OACONTROL, GEN12_OAR_OACONTROL_OFFSET + 1, (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | - (enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0) + (active ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0) }, { RING_CONTEXT_CONTROL(ce->engine->mmio_base), CTX_CONTEXT_CONTROL, _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE, - enable ? + active ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0) }, @@ -2287,7 +2258,7 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena return err; /* Apply regs_lri using LRI with pinned context */ - return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri)); + return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri), active); } /* @@ -2315,9 +2286,11 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool ena * Note: it's only the RCS/Render context that has any OA state. * Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int oa_configure_all_contexts(struct i915_perf_stream *stream, - struct flex *regs, - size_t num_regs) +static int +oa_configure_all_contexts(struct i915_perf_stream *stream, + struct flex *regs, + size_t num_regs, + struct i915_active *active) { struct drm_i915_private *i915 = stream->perf->i915; struct intel_engine_cs *engine; @@ -2374,7 +2347,7 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream, regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu); - err = gen8_modify_self(ce, regs, num_regs); + err = gen8_modify_self(ce, regs, num_regs, active); if (err) return err; } @@ -2382,8 +2355,10 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream, return 0; } -static int gen12_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config) +static int +gen12_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config, + struct i915_active *active) { struct flex regs[] = { { @@ -2392,11 +2367,15 @@ static int gen12_configure_all_contexts(struct i915_perf_stream *stream, }, }; - return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); + return oa_configure_all_contexts(stream, + regs, ARRAY_SIZE(regs), + active); } -static int lrc_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config) +static int +lrc_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config, + struct i915_active *active) { /* The MMIO offsets for Flex EU registers aren't contiguous */ const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; @@ -2429,11 +2408,14 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, for (i = 2; i < ARRAY_SIZE(regs); i++) regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg); - return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); + return oa_configure_all_contexts(stream, + regs, ARRAY_SIZE(regs), + active); } -static struct i915_request * -gen8_enable_metric_set(struct i915_perf_stream *stream) +static int +gen8_enable_metric_set(struct i915_perf_stream *stream, + struct i915_active *active) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2473,11 +2455,13 @@ gen8_enable_metric_set(struct i915_perf_stream *stream) * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = lrc_configure_all_contexts(stream, oa_config); + ret = lrc_configure_all_contexts(stream, oa_config, active); if (ret) - return ERR_PTR(ret); + return ret; - return emit_oa_config(stream, oa_config, oa_context(stream)); + return emit_oa_config(stream, + stream->oa_config, oa_context(stream), + active); } static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream) @@ -2487,8 +2471,9 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream) 0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS); } -static struct i915_request * -gen12_enable_metric_set(struct i915_perf_stream *stream) +static int +gen12_enable_metric_set(struct i915_perf_stream *stream, + struct i915_active *active) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2517,9 +2502,9 @@ gen12_enable_metric_set(struct i915_perf_stream *stream) * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = gen12_configure_all_contexts(stream, oa_config); + ret = gen12_configure_all_contexts(stream, oa_config, active); if (ret) - return ERR_PTR(ret); + return ret; /* * For Gen12, performance counters are context @@ -2527,12 +2512,14 @@ gen12_enable_metric_set(struct i915_perf_stream *stream) * requested this. */ if (stream->ctx) { - ret = gen12_configure_oar_context(stream, true); + ret = gen12_configure_oar_context(stream, active); if (ret) - return ERR_PTR(ret); + return ret; } - return emit_oa_config(stream, oa_config, oa_context(stream)); + return emit_oa_config(stream, + stream->oa_config, oa_context(stream), + active); } static void gen8_disable_metric_set(struct i915_perf_stream *stream) @@ -2540,7 +2527,7 @@ static void gen8_disable_metric_set(struct i915_perf_stream *stream) struct intel_uncore *uncore = stream->uncore; /* Reset all contexts' slices/subslices configurations. */ - lrc_configure_all_contexts(stream, NULL); + lrc_configure_all_contexts(stream, NULL, NULL); intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0); } @@ -2550,7 +2537,7 @@ static void gen10_disable_metric_set(struct i915_perf_stream *stream) struct intel_uncore *uncore = stream->uncore; /* Reset all contexts' slices/subslices configurations. */ - lrc_configure_all_contexts(stream, NULL); + lrc_configure_all_contexts(stream, NULL, NULL); /* Make sure we disable noa to save power. */ intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0); @@ -2561,11 +2548,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) struct intel_uncore *uncore = stream->uncore; /* Reset all contexts' slices/subslices configurations. */ - gen12_configure_all_contexts(stream, NULL); + gen12_configure_all_contexts(stream, NULL, NULL); /* disable the context save/restore or OAR counters */ if (stream->ctx) - gen12_configure_oar_context(stream, false); + gen12_configure_oar_context(stream, NULL); /* Make sure we disable noa to save power. */ intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0); @@ -2657,11 +2644,13 @@ static void gen12_oa_enable(struct i915_perf_stream *stream) */ static void i915_oa_stream_enable(struct i915_perf_stream *stream) { + stream->pollin = false; + stream->perf->ops.oa_enable(stream); if (stream->periodic) hrtimer_start(&stream->poll_check_timer, - ns_to_ktime(POLL_PERIOD), + ns_to_ktime(stream->poll_oa_period), HRTIMER_MODE_REL_PINNED); } @@ -2700,6 +2689,14 @@ static void gen12_oa_disable(struct i915_perf_stream *stream) 50)) drm_err(&stream->perf->i915->drm, "wait for OA to be disabled timed out\n"); + + intel_uncore_write(uncore, GEN12_OA_TLB_INV_CR, 1); + if (intel_wait_for_register(uncore, + GEN12_OA_TLB_INV_CR, + 1, 0, + 50)) + drm_err(&stream->perf->i915->drm, + "wait for OA tlb invalidate timed out\n"); } /** @@ -2729,16 +2726,52 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = { static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream) { - struct i915_request *rq; + struct i915_active *active; + int err; - rq = stream->perf->ops.enable_metric_set(stream); - if (IS_ERR(rq)) - return PTR_ERR(rq); + active = i915_active_create(); + if (!active) + return -ENOMEM; - i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); - i915_request_put(rq); + err = stream->perf->ops.enable_metric_set(stream, active); + if (err == 0) + __i915_active_wait(active, TASK_UNINTERRUPTIBLE); - return 0; + i915_active_put(active); + return err; +} + +static void +get_default_sseu_config(struct intel_sseu *out_sseu, + struct intel_engine_cs *engine) +{ + const struct sseu_dev_info *devinfo_sseu = + &RUNTIME_INFO(engine->i915)->sseu; + + *out_sseu = intel_sseu_from_device_info(devinfo_sseu); + + if (IS_GEN(engine->i915, 11)) { + /* + * We only need subslice count so it doesn't matter which ones + * we select - just turn off low bits in the amount of half of + * all available subslices per slice. + */ + out_sseu->subslice_mask = + ~(~0 << (hweight8(out_sseu->subslice_mask) / 2)); + out_sseu->slice_mask = 0x1; + } +} + +static int +get_sseu_config(struct intel_sseu *out_sseu, + struct intel_engine_cs *engine, + const struct drm_i915_gem_context_param_sseu *drm_sseu) +{ + if (drm_sseu->engine.engine_class != engine->uabi_class || + drm_sseu->engine.engine_instance != engine->uabi_instance) + return -EINVAL; + + return i915_gem_user_to_context_sseu(engine->i915, drm_sseu, out_sseu); } /** @@ -2873,6 +2906,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, goto err_oa_buf_alloc; stream->ops = &i915_oa_stream_ops; + + perf->sseu = props->sseu; WRITE_ONCE(perf->exclusive_stream, stream); ret = i915_perf_stream_enable_sync(stream); @@ -2924,58 +2959,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce, /* perf.exclusive_stream serialised by lrc_configure_all_contexts() */ stream = READ_ONCE(engine->i915->perf.exclusive_stream); - /* - * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller - * is already doing that, so nothing to be done for gen12 here. - */ if (stream && INTEL_GEN(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } /** - * 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 @@ -3000,7 +2988,8 @@ 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 @@ -3023,13 +3012,12 @@ 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); } @@ -3040,15 +3028,15 @@ 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) @@ -3061,7 +3049,8 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) wake_up(&stream->poll_wq); } - hrtimer_forward_now(hrtimer, ns_to_ktime(POLL_PERIOD)); + hrtimer_forward_now(hrtimer, + ns_to_ktime(stream->poll_oa_period)); return HRTIMER_RESTART; } @@ -3192,7 +3181,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, return -EINVAL; if (config != stream->oa_config) { - struct i915_request *rq; + int err; /* * If OA is bound to a specific context, emit the @@ -3203,13 +3192,11 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, * When set globally, we use a low priority kernel context, * so it will effectively take effect when idle. */ - rq = emit_oa_config(stream, config, oa_context(stream)); - if (!IS_ERR(rq)) { + err = emit_oa_config(stream, config, oa_context(stream), NULL); + if (!err) config = xchg(&stream->oa_config, config); - i915_request_put(rq); - } else { - ret = PTR_ERR(rq); - } + else + ret = err; } i915_oa_config_put(config); @@ -3422,6 +3409,14 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, privileged_op = true; } + /* + * Asking for SSEU configuration is a priviliged operation. + */ + if (props->has_sseu) + privileged_op = true; + else + get_default_sseu_config(&props->sseu, props->engine); + /* Similar to perf's kernel.perf_paranoid_cpu sysctl option * we check a dev.i915.perf_stream_paranoid sysctl option * to determine if it's ok to access system wide OA counters @@ -3442,6 +3437,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, stream->perf = perf; stream->ctx = specific_ctx; + stream->poll_oa_period = props->poll_oa_period; ret = i915_oa_stream_init(stream, param, props); if (ret) @@ -3517,8 +3513,10 @@ static int read_properties_unlocked(struct i915_perf *perf, { u64 __user *uprop = uprops; u32 i; + int ret; memset(props, 0, sizeof(struct perf_open_properties)); + props->poll_oa_period = DEFAULT_POLL_PERIOD_NS; if (!n_props) { DRM_DEBUG("No i915 perf properties given\n"); @@ -3548,7 +3546,6 @@ static int read_properties_unlocked(struct i915_perf *perf, for (i = 0; i < n_props; i++) { u64 oa_period, oa_freq_hz; u64 id, value; - int ret; ret = get_user(id, uprop); if (ret) @@ -3634,6 +3631,32 @@ static int read_properties_unlocked(struct i915_perf *perf, case DRM_I915_PERF_PROP_HOLD_PREEMPTION: props->hold_preemption = !!value; break; + case DRM_I915_PERF_PROP_GLOBAL_SSEU: { + struct drm_i915_gem_context_param_sseu user_sseu; + + if (copy_from_user(&user_sseu, + u64_to_user_ptr(value), + sizeof(user_sseu))) { + DRM_DEBUG("Unable to copy global sseu parameter\n"); + return -EFAULT; + } + + ret = get_sseu_config(&props->sseu, props->engine, &user_sseu); + if (ret) { + DRM_DEBUG("Invalid SSEU configuration\n"); + return ret; + } + props->has_sseu = true; + break; + } + case DRM_I915_PERF_PROP_POLL_OA_PERIOD: + if (value < 100000 /* 100us */) { + DRM_DEBUG("OA availability timer too small (%lluns < 100us)\n", + value); + return -EINVAL; + } + props->poll_oa_period = value; + break; case DRM_I915_PERF_PROP_MAX: MISSING_CASE(id); return -EINVAL; @@ -3716,7 +3739,6 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, void i915_perf_register(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; - int ret; if (!perf->i915) return; @@ -3730,64 +3752,7 @@ void i915_perf_register(struct drm_i915_private *i915) perf->metrics_kobj = kobject_create_and_add("metrics", &i915->drm.primary->kdev->kobj); - if (!perf->metrics_kobj) - goto exit; - - sysfs_attr_init(&perf->test_config.sysfs_metric_id.attr); - - if (IS_TIGERLAKE(i915)) { - i915_perf_load_test_config_tgl(i915); - } else if (INTEL_GEN(i915) >= 11) { - i915_perf_load_test_config_icl(i915); - } else if (IS_CANNONLAKE(i915)) { - i915_perf_load_test_config_cnl(i915); - } else if (IS_COFFEELAKE(i915)) { - if (IS_CFL_GT2(i915)) - i915_perf_load_test_config_cflgt2(i915); - if (IS_CFL_GT3(i915)) - i915_perf_load_test_config_cflgt3(i915); - } else if (IS_GEMINILAKE(i915)) { - i915_perf_load_test_config_glk(i915); - } else if (IS_KABYLAKE(i915)) { - if (IS_KBL_GT2(i915)) - i915_perf_load_test_config_kblgt2(i915); - else if (IS_KBL_GT3(i915)) - i915_perf_load_test_config_kblgt3(i915); - } else if (IS_BROXTON(i915)) { - i915_perf_load_test_config_bxt(i915); - } else if (IS_SKYLAKE(i915)) { - if (IS_SKL_GT2(i915)) - i915_perf_load_test_config_sklgt2(i915); - else if (IS_SKL_GT3(i915)) - i915_perf_load_test_config_sklgt3(i915); - else if (IS_SKL_GT4(i915)) - i915_perf_load_test_config_sklgt4(i915); - } else if (IS_CHERRYVIEW(i915)) { - i915_perf_load_test_config_chv(i915); - } else if (IS_BROADWELL(i915)) { - i915_perf_load_test_config_bdw(i915); - } else if (IS_HASWELL(i915)) { - i915_perf_load_test_config_hsw(i915); - } - - if (perf->test_config.id == 0) - goto sysfs_error; - - ret = sysfs_create_group(perf->metrics_kobj, - &perf->test_config.sysfs_metric); - if (ret) - goto sysfs_error; - - perf->test_config.perf = perf; - kref_init(&perf->test_config.ref); - goto exit; - -sysfs_error: - kobject_put(perf->metrics_kobj); - perf->metrics_kobj = NULL; - -exit: mutex_unlock(&perf->lock); } @@ -3807,9 +3772,6 @@ void i915_perf_unregister(struct drm_i915_private *i915) if (!perf->metrics_kobj) return; - sysfs_remove_group(perf->metrics_kobj, - &perf->test_config.sysfs_metric); - kobject_put(perf->metrics_kobj); perf->metrics_kobj = NULL; } @@ -4408,6 +4370,11 @@ void i915_perf_init(struct drm_i915_private *i915) ratelimit_set_flags(&perf->spurious_report_rs, RATELIMIT_MSG_ON_RELEASE); + ratelimit_state_init(&perf->tail_pointer_race, + 5 * HZ, 10); + ratelimit_set_flags(&perf->tail_pointer_race, + RATELIMIT_MSG_ON_RELEASE); + atomic64_set(&perf->noa_programming_delay, 500 * 1000 /* 500us */); @@ -4468,8 +4435,15 @@ int i915_perf_ioctl_version(void) * preemption on a particular context so that performance data is * accessible from a delta of MI_RPC reports without looking at the * OA buffer. + * + * 4: Add DRM_I915_PERF_PROP_ALLOWED_SSEU to limit what contexts can + * be run for the duration of the performance recording based on + * their SSEU configuration. + * + * 5: Add DRM_I915_PERF_PROP_POLL_OA_PERIOD parameter that controls the + * interval for the hrtimer used to check for OA data. */ - return 3; + return 5; } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index a0e22f00f6cf..a36a455ae336 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -16,11 +16,13 @@ #include <linux/uuid.h> #include <linux/wait.h> +#include "gt/intel_sseu.h" #include "i915_reg.h" #include "intel_wakeref.h" struct drm_i915_private; struct file; +struct i915_active; struct i915_gem_context; struct i915_perf; struct i915_vma; @@ -272,21 +274,10 @@ struct i915_perf_stream { spinlock_t ptr_lock; /** - * @tails: One 'aging' tail pointer and one 'aged' tail pointer ready to - * used for reading. - * - * Initial values of 0xffffffff are invalid and imply that an - * update is required (and should be ignored by an attempted - * read) - */ - struct { - u32 offset; - } tails[2]; - - /** - * @aged_tail_idx: Index for the aged tail ready to read() data up to. + * @aging_tail: The last HW tail reported by HW. The data + * might not have made it to memory yet though. */ - unsigned int aged_tail_idx; + u32 aging_tail; /** * @aging_timestamp: A monotonic timestamp for when the current aging tail pointer @@ -302,6 +293,11 @@ struct i915_perf_stream { * OA buffer data to userspace. */ u32 head; + + /** + * @tail: The last verified tail that can be read by userspace. + */ + u32 tail; } oa_buffer; /** @@ -309,6 +305,12 @@ struct i915_perf_stream { * reprogrammed. */ struct i915_vma *noa_wait; + + /** + * @poll_oa_period: The period in nanoseconds at which the OA + * buffer should be checked for available data. + */ + u64 poll_oa_period; }; /** @@ -339,8 +341,8 @@ struct i915_oa_ops { * counter reports being sampled. May apply system constraints such as * disabling EU clock gating as required. */ - struct i915_request * - (*enable_metric_set)(struct i915_perf_stream *stream); + int (*enable_metric_set)(struct i915_perf_stream *stream, + struct i915_active *active); /** * @disable_metric_set: Remove system constraints associated with using @@ -408,12 +410,22 @@ struct i915_perf { struct i915_perf_stream *exclusive_stream; /** + * @sseu: sseu configuration selected to run while perf is active, + * applies to all contexts. + */ + struct intel_sseu sseu; + + /** * For rate limiting any notifications of spurious * invalid OA reports */ struct ratelimit_state spurious_report_rs; - struct i915_oa_config test_config; + /** + * For rate limiting any notifications of tail pointer + * race. + */ + struct ratelimit_state tail_pointer_race; u32 gen7_latched_oastatus1; u32 ctx_oactxctrl_offset; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 2c062534eac1..230e9256ab30 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -1115,7 +1115,7 @@ void i915_pmu_register(struct drm_i915_private *i915) int ret = -ENOMEM; if (INTEL_GEN(i915) <= 2) { - dev_info(i915->drm.dev, "PMU not supported for this GPU."); + drm_info(&i915->drm, "PMU not supported for this GPU."); return; } @@ -1178,7 +1178,7 @@ err_name: if (!is_igp(i915)) kfree(pmu->name); err: - dev_notice(i915->drm.dev, "Failed to register PMU!\n"); + drm_notice(&i915->drm, "Failed to register PMU!\n"); } void i915_pmu_unregister(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 309cb7d96b35..edda3f29c8aa 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -693,6 +693,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define OABUFFER_SIZE_8M (6 << 3) #define OABUFFER_SIZE_16M (7 << 3) +#define GEN12_OA_TLB_INV_CR _MMIO(0xceec) + /* Gen12 OAR unit */ #define GEN12_OAR_OACONTROL _MMIO(0x2960) #define GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1 @@ -3092,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GT_BSD_CS_ERROR_INTERRUPT (1 << 15) #define GT_BSD_USER_INTERRUPT (1 << 12) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 (1 << 11) /* hsw+; rsvd on snb, ivb, vlv */ +#define GT_WAIT_SEMAPHORE_INTERRUPT REG_BIT(11) /* bdw+ */ #define GT_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT (1 << 5) /* !snb */ #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT (1 << 4) @@ -4322,6 +4325,96 @@ enum { #define EXITLINE_MASK REG_GENMASK(12, 0) #define EXITLINE_SHIFT 0 +/* VRR registers */ +#define _TRANS_VRR_CTL_A 0x60420 +#define _TRANS_VRR_CTL_B 0x61420 +#define _TRANS_VRR_CTL_C 0x62420 +#define _TRANS_VRR_CTL_D 0x63420 +#define TRANS_VRR_CTL(trans) _MMIO_TRANS2(trans, _TRANS_VRR_CTL_A) +#define VRR_CTL_VRR_ENABLE REG_BIT(31) +#define VRR_CTL_IGN_MAX_SHIFT REG_BIT(30) +#define VRR_CTL_FLIP_LINE_EN REG_BIT(29) +#define VRR_CTL_LINE_COUNT_MASK REG_GENMASK(10, 3) +#define VRR_CTL_SW_FULLLINE_COUNT REG_BIT(0) + +#define _TRANS_VRR_VMAX_A 0x60424 +#define _TRANS_VRR_VMAX_B 0x61424 +#define _TRANS_VRR_VMAX_C 0x62424 +#define _TRANS_VRR_VMAX_D 0x63424 +#define TRANS_VRR_VMAX(trans) _MMIO_TRANS2(trans, _TRANS_VRR_VMAX_A) +#define VRR_VMAX_MASK REG_GENMASK(19, 0) + +#define _TRANS_VRR_VMIN_A 0x60434 +#define _TRANS_VRR_VMIN_B 0x61434 +#define _TRANS_VRR_VMIN_C 0x62434 +#define _TRANS_VRR_VMIN_D 0x63434 +#define TRANS_VRR_VMIN(trans) _MMIO_TRANS2(trans, _TRANS_VRR_VMIN_A) +#define VRR_VMIN_MASK REG_GENMASK(15, 0) + +#define _TRANS_VRR_VMAXSHIFT_A 0x60428 +#define _TRANS_VRR_VMAXSHIFT_B 0x61428 +#define _TRANS_VRR_VMAXSHIFT_C 0x62428 +#define _TRANS_VRR_VMAXSHIFT_D 0x63428 +#define TRANS_VRR_VMAXSHIFT(trans) _MMIO_TRANS2(trans, \ + _TRANS_VRR_VMAXSHIFT_A) +#define VRR_VMAXSHIFT_DEC_MASK REG_GENMASK(29, 16) +#define VRR_VMAXSHIFT_DEC REG_BIT(16) +#define VRR_VMAXSHIFT_INC_MASK REG_GENMASK(12, 0) + +#define _TRANS_VRR_STATUS_A 0x6042C +#define _TRANS_VRR_STATUS_B 0x6142C +#define _TRANS_VRR_STATUS_C 0x6242C +#define _TRANS_VRR_STATUS_D 0x6342C +#define TRANS_VRR_STATUS(trans) _MMIO_TRANS2(trans, _TRANS_VRR_STATUS_A) +#define VRR_STATUS_VMAX_REACHED REG_BIT(31) +#define VRR_STATUS_NOFLIP_TILL_BNDR REG_BIT(30) +#define VRR_STATUS_FLIP_BEF_BNDR REG_BIT(29) +#define VRR_STATUS_NO_FLIP_FRAME REG_BIT(28) +#define VRR_STATUS_VRR_EN_LIVE REG_BIT(27) +#define VRR_STATUS_FLIPS_SERVICED REG_BIT(26) +#define VRR_STATUS_VBLANK_MASK REG_GENMASK(22, 20) +#define STATUS_FSM_IDLE REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 0) +#define STATUS_FSM_WAIT_TILL_FDB REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 1) +#define STATUS_FSM_WAIT_TILL_FS REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 2) +#define STATUS_FSM_WAIT_TILL_FLIP REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 3) +#define STATUS_FSM_PIPELINE_FILL REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 4) +#define STATUS_FSM_ACTIVE REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 5) +#define STATUS_FSM_LEGACY_VBLANK REG_FIELD_PREP(VRR_STATUS_VBLANK_MASK, 6) + +#define _TRANS_VRR_VTOTAL_PREV_A 0x60480 +#define _TRANS_VRR_VTOTAL_PREV_B 0x61480 +#define _TRANS_VRR_VTOTAL_PREV_C 0x62480 +#define _TRANS_VRR_VTOTAL_PREV_D 0x63480 +#define TRANS_VRR_VTOTAL_PREV(trans) _MMIO_TRANS2(trans, \ + _TRANS_VRR_VTOTAL_PREV_A) +#define VRR_VTOTAL_FLIP_BEFR_BNDR REG_BIT(31) +#define VRR_VTOTAL_FLIP_AFTER_BNDR REG_BIT(30) +#define VRR_VTOTAL_FLIP_AFTER_DBLBUF REG_BIT(29) +#define VRR_VTOTAL_PREV_FRAME_MASK REG_GENMASK(19, 0) + +#define _TRANS_VRR_FLIPLINE_A 0x60438 +#define _TRANS_VRR_FLIPLINE_B 0x61438 +#define _TRANS_VRR_FLIPLINE_C 0x62438 +#define _TRANS_VRR_FLIPLINE_D 0x63438 +#define TRANS_VRR_FLIPLINE(trans) _MMIO_TRANS2(trans, \ + _TRANS_VRR_FLIPLINE_A) +#define VRR_FLIPLINE_MASK REG_GENMASK(19, 0) + +#define _TRANS_VRR_STATUS2_A 0x6043C +#define _TRANS_VRR_STATUS2_B 0x6143C +#define _TRANS_VRR_STATUS2_C 0x6243C +#define _TRANS_VRR_STATUS2_D 0x6343C +#define TRANS_VRR_STATUS2(trans) _MMIO_TRANS2(trans, _TRANS_VRR_STATUS2_A) +#define VRR_STATUS2_VERT_LN_CNT_MASK REG_GENMASK(19, 0) + +#define _TRANS_PUSH_A 0x60A70 +#define _TRANS_PUSH_B 0x61A70 +#define _TRANS_PUSH_C 0x62A70 +#define _TRANS_PUSH_D 0x63A70 +#define TRANS_PUSH(trans) _MMIO_TRANS2(trans, _TRANS_PUSH_A) +#define TRANS_PUSH_EN REG_BIT(31) +#define TRANS_PUSH_SEND REG_BIT(30) + /* * HSW+ eDP PSR registers * @@ -6762,7 +6855,7 @@ enum { #define PLANE_CTL_FORMAT_P012 (5 << 24) #define PLANE_CTL_FORMAT_XRGB_16161616F (6 << 24) #define PLANE_CTL_FORMAT_P016 (7 << 24) -#define PLANE_CTL_FORMAT_AYUV (8 << 24) +#define PLANE_CTL_FORMAT_XYUV (8 << 24) #define PLANE_CTL_FORMAT_INDEXED (12 << 24) #define PLANE_CTL_FORMAT_RGB_565 (14 << 24) #define ICL_PLANE_CTL_FORMAT_MASK (0x1f << 23) @@ -9698,8 +9791,11 @@ enum skl_power_gate { #define TRANS_DDI_BPC_10 (1 << 20) #define TRANS_DDI_BPC_6 (2 << 20) #define TRANS_DDI_BPC_12 (3 << 20) +#define TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK REG_GENMASK(19, 18) /* bdw-cnl */ +#define TRANS_DDI_PORT_SYNC_MASTER_SELECT(x) REG_FIELD_PREP(TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK, (x)) #define TRANS_DDI_PVSYNC (1 << 17) #define TRANS_DDI_PHSYNC (1 << 16) +#define TRANS_DDI_PORT_SYNC_ENABLE REG_BIT(15) /* bdw-cnl */ #define TRANS_DDI_EDP_INPUT_MASK (7 << 12) #define TRANS_DDI_EDP_INPUT_A_ON (0 << 12) #define TRANS_DDI_EDP_INPUT_A_ONOFF (4 << 12) @@ -9726,12 +9822,10 @@ enum skl_power_gate { #define _TRANS_DDI_FUNC_CTL2_EDP 0x6f404 #define _TRANS_DDI_FUNC_CTL2_DSI0 0x6b404 #define _TRANS_DDI_FUNC_CTL2_DSI1 0x6bc04 -#define TRANS_DDI_FUNC_CTL2(tran) _MMIO_TRANS2(tran, \ - _TRANS_DDI_FUNC_CTL2_A) -#define PORT_SYNC_MODE_ENABLE (1 << 4) -#define PORT_SYNC_MODE_MASTER_SELECT(x) ((x) << 0) -#define PORT_SYNC_MODE_MASTER_SELECT_MASK (0x7 << 0) -#define PORT_SYNC_MODE_MASTER_SELECT_SHIFT 0 +#define TRANS_DDI_FUNC_CTL2(tran) _MMIO_TRANS2(tran, _TRANS_DDI_FUNC_CTL2_A) +#define PORT_SYNC_MODE_ENABLE REG_BIT(4) +#define PORT_SYNC_MODE_MASTER_SELECT_MASK REG_GENMASK(2, 0) +#define PORT_SYNC_MODE_MASTER_SELECT(x) REG_FIELD_PREP(PORT_SYNC_MODE_MASTER_SELECT_MASK, (x)) /* DisplayPort Transport Control */ #define _DP_TP_CTL_A 0x64040 @@ -9792,6 +9886,24 @@ enum skl_power_gate { #define DDI_BUF_BALANCE_LEG_ENABLE (1 << 31) #define DDI_BUF_TRANS_HI(port, i) _MMIO(_PORT(port, _DDI_BUF_TRANS_A, _DDI_BUF_TRANS_B) + (i) * 8 + 4) +/* DDI DP Compliance Control */ +#define _DDI_DP_COMP_CTL_A 0x605F0 +#define _DDI_DP_COMP_CTL_B 0x615F0 +#define DDI_DP_COMP_CTL(pipe) _MMIO_PIPE(pipe, _DDI_DP_COMP_CTL_A, _DDI_DP_COMP_CTL_B) +#define DDI_DP_COMP_CTL_ENABLE (1 << 31) +#define DDI_DP_COMP_CTL_D10_2 (0 << 28) +#define DDI_DP_COMP_CTL_SCRAMBLED_0 (1 << 28) +#define DDI_DP_COMP_CTL_PRBS7 (2 << 28) +#define DDI_DP_COMP_CTL_CUSTOM80 (3 << 28) +#define DDI_DP_COMP_CTL_HBR2 (4 << 28) +#define DDI_DP_COMP_CTL_SCRAMBLED_1 (5 << 28) +#define DDI_DP_COMP_CTL_HBR2_RESET (0xFC << 0) + +/* DDI DP Compliance Pattern */ +#define _DDI_DP_COMP_PAT_A 0x605F4 +#define _DDI_DP_COMP_PAT_B 0x615F4 +#define DDI_DP_COMP_PAT(pipe, i) _MMIO(_PIPE(pipe, _DDI_DP_COMP_PAT_A, _DDI_DP_COMP_PAT_B) + (i) * 4) + /* Sideband Interface (SBI) is programmed indirectly, via * SBI_ADDR, which contains the register offset; and SBI_DATA, * which contains the payload */ @@ -10739,6 +10851,12 @@ enum skl_power_gate { #define _PAL_PREC_MULTI_SEG_DATA_A 0x4A40C #define _PAL_PREC_MULTI_SEG_DATA_B 0x4AC0C +#define PAL_PREC_MULTI_SEG_RED_LDW_MASK REG_GENMASK(29, 24) +#define PAL_PREC_MULTI_SEG_RED_UDW_MASK REG_GENMASK(29, 20) +#define PAL_PREC_MULTI_SEG_GREEN_LDW_MASK REG_GENMASK(19, 14) +#define PAL_PREC_MULTI_SEG_GREEN_UDW_MASK REG_GENMASK(19, 10) +#define PAL_PREC_MULTI_SEG_BLUE_LDW_MASK REG_GENMASK(9, 4) +#define PAL_PREC_MULTI_SEG_BLUE_UDW_MASK REG_GENMASK(9, 0) #define PREC_PAL_MULTI_SEG_INDEX(pipe) _MMIO_PIPE(pipe, \ _PAL_PREC_MULTI_SEG_INDEX_A, \ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0df71d7d0ff..22635bbabf06 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -101,6 +101,11 @@ static signed long i915_fence_wait(struct dma_fence *fence, timeout); } +struct kmem_cache *i915_request_slab_cache(void) +{ + return global.slab_requests; +} + static void i915_fence_release(struct dma_fence *fence) { struct i915_request *rq = to_request(fence); @@ -115,6 +120,10 @@ static void i915_fence_release(struct dma_fence *fence) i915_sw_fence_fini(&rq->submit); i915_sw_fence_fini(&rq->semaphore); + /* Keep one request on each engine for reserved use under mempressure */ + if (!cmpxchg(&rq->engine->request_pool, NULL, rq)) + return; + kmem_cache_free(global.slab_requests, rq); } @@ -629,14 +638,22 @@ static void retire_requests(struct intel_timeline *tl) } static noinline struct i915_request * -request_alloc_slow(struct intel_timeline *tl, gfp_t gfp) +request_alloc_slow(struct intel_timeline *tl, + struct i915_request **rsvd, + gfp_t gfp) { struct i915_request *rq; - if (list_empty(&tl->requests)) - goto out; + /* If we cannot wait, dip into our reserves */ + if (!gfpflags_allow_blocking(gfp)) { + rq = xchg(rsvd, NULL); + if (!rq) /* Use the normal failure path for one final WARN */ + goto out; - if (!gfpflags_allow_blocking(gfp)) + return rq; + } + + if (list_empty(&tl->requests)) goto out; /* Move our oldest request to the slab-cache (if not in use!) */ @@ -721,7 +738,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq = kmem_cache_alloc(global.slab_requests, gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (unlikely(!rq)) { - rq = request_alloc_slow(tl, gfp); + rq = request_alloc_slow(tl, &ce->engine->request_pool, gfp); if (!rq) { ret = -ENOMEM; goto err_unreserve; @@ -1444,9 +1461,7 @@ void i915_request_add(struct i915_request *rq) if (list_empty(&rq->sched.signalers_list)) attr.priority |= I915_PRIORITY_WAIT; - local_bh_disable(); __i915_request_queue(rq, &attr); - local_bh_enable(); /* Kick the execlists tasklet if just scheduled */ mutex_unlock(&tl->mutex); } diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 3c552bfea67a..d8ce908e1346 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -300,6 +300,8 @@ static inline bool dma_fence_is_i915(const struct dma_fence *fence) return fence->ops == &i915_fence_ops; } +struct kmem_cache *i915_request_slab_cache(void); + struct i915_request * __must_check __i915_request_create(struct intel_context *ce, gfp_t gfp); struct i915_request * __must_check diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 68b06a7ba667..37cfcf5b321b 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -209,6 +209,12 @@ static void kick_submission(struct intel_engine_cs *engine, if (!inflight) goto unlock; + ENGINE_TRACE(engine, + "bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n", + prio, + rq->fence.context, rq->fence.seqno, + inflight->fence.context, inflight->fence.seqno, + inflight->sched.attr.priority); engine->execlists.queue_priority_hint = prio; /* @@ -464,11 +470,15 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, if (!dep) return -ENOMEM; + local_bh_disable(); + if (!__i915_sched_node_add_dependency(node, signal, dep, I915_DEPENDENCY_EXTERNAL | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); + local_bh_enable(); /* kick submission tasklet */ + return 0; } diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index a3d38e089b6e..7daf81f55c90 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -421,7 +421,7 @@ static void timer_i915_sw_fence_wake(struct timer_list *t) if (!fence) return; - pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%pS)\n", + pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%ps)\n", cb->dma->ops->get_driver_name(cb->dma), cb->dma->ops->get_timeline_name(cb->dma), cb->dma->seqno, diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c index 997b2998f1f2..a3a81bb8f2c3 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence_work.c +++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c @@ -38,7 +38,10 @@ fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) if (!f->dma.error) { dma_fence_get(&f->dma); - queue_work(system_unbound_wq, &f->work); + if (test_bit(DMA_FENCE_WORK_IMM, &f->dma.flags)) + fence_work(&f->work); + else + queue_work(system_unbound_wq, &f->work); } else { fence_complete(f); } diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.h b/drivers/gpu/drm/i915/i915_sw_fence_work.h index 3a22b287e201..2c409f11c5c5 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence_work.h +++ b/drivers/gpu/drm/i915/i915_sw_fence_work.h @@ -32,6 +32,10 @@ struct dma_fence_work { const struct dma_fence_work_ops *ops; }; +enum { + DMA_FENCE_WORK_IMM = DMA_FENCE_FLAG_USER_BITS, +}; + void dma_fence_work_init(struct dma_fence_work *f, const struct dma_fence_work_ops *ops); int dma_fence_work_chain(struct dma_fence_work *f, struct dma_fence *signal); @@ -41,4 +45,23 @@ static inline void dma_fence_work_commit(struct dma_fence_work *f) i915_sw_fence_commit(&f->chain); } +/** + * dma_fence_work_commit_imm: Commit the fence, and if possible execute locally. + * @f: the fenced worker + * + * Instead of always scheduling a worker to execute the callback (see + * dma_fence_work_commit()), we try to execute the callback immediately in + * the local context. It is required that the fence be committed before it + * is published, and that no other threads try to tamper with the number + * of asynchronous waits on the fence (or else the callback will be + * executed in the wrong context, i.e. not the callers). + */ +static inline void dma_fence_work_commit_imm(struct dma_fence_work *f) +{ + if (atomic_read(&f->chain.pending) <= 1) + __set_bit(DMA_FENCE_WORK_IMM, &f->dma.flags); + + dma_fence_work_commit(f); +} + #endif /* I915_SW_FENCE_WORK_H */ diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c index ed69b5d4a375..b3a24eac21f1 100644 --- a/drivers/gpu/drm/i915/i915_switcheroo.c +++ b/drivers/gpu/drm/i915/i915_switcheroo.c @@ -20,14 +20,14 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, } if (state == VGA_SWITCHEROO_ON) { - pr_info("switched on\n"); + drm_info(&i915->drm, "switched on\n"); i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING; /* i915 resume handler doesn't set to D0 */ pci_set_power_state(pdev, PCI_D0); i915_resume_switcheroo(i915); i915->drm.switch_power_state = DRM_SWITCH_POWER_ON; } else { - pr_info("switched off\n"); + drm_info(&i915->drm, "switched off\n"); i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING; i915_suspend_switcheroo(i915, pmm); i915->drm.switch_power_state = DRM_SWITCH_POWER_OFF; diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index 029854ae65fc..e28eae4a8f70 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -101,5 +101,6 @@ void set_timer_ms(struct timer_list *t, unsigned long timeout) */ barrier(); - mod_timer(t, jiffies + timeout); + /* Keep t->expires = 0 reserved to indicate a canceled timer. */ + mod_timer(t, jiffies + timeout ?: 1); } diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 5b3efb43a8ef..f0383a68c981 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -608,18 +608,6 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color) return true; } -static void assert_bind_count(const struct drm_i915_gem_object *obj) -{ - /* - * Combine the assertion that the object is bound and that we have - * pinned its pages. But we should never have bound the object - * more than we have pinned its pages. (For complete accuracy, we - * assume that no else is pinning the pages, but as a rough assertion - * that we will not run into problems later, this will do!) - */ - GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < atomic_read(&obj->bind_count)); -} - /** * i915_vma_insert - finds a slot for the vma in its address space * @vma: the vma @@ -738,12 +726,6 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color)); - if (vma->obj) { - struct drm_i915_gem_object *obj = vma->obj; - - atomic_inc(&obj->bind_count); - assert_bind_count(obj); - } list_add_tail(&vma->vm_link, &vma->vm->bound_list); return 0; @@ -761,12 +743,6 @@ i915_vma_detach(struct i915_vma *vma) * it to be reaped by the shrinker. */ list_del(&vma->vm_link); - if (vma->obj) { - struct drm_i915_gem_object *obj = vma->obj; - - assert_bind_count(obj); - atomic_dec(&obj->bind_count); - } } static bool try_qad_pin(struct i915_vma *vma, unsigned int flags) @@ -913,11 +889,30 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) if (flags & PIN_GLOBAL) wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); - /* No more allocations allowed once we hold vm->mutex */ - err = mutex_lock_interruptible(&vma->vm->mutex); + /* + * Differentiate between user/kernel vma inside the aliasing-ppgtt. + * + * We conflate the Global GTT with the user's vma when using the + * aliasing-ppgtt, but it is still vitally important to try and + * keep the use cases distinct. For example, userptr objects are + * not allowed inside the Global GTT as that will cause lock + * inversions when we have to evict them the mmu_notifier callbacks - + * but they are allowed to be part of the user ppGTT which can never + * be mapped. As such we try to give the distinct users of the same + * mutex, distinct lockclasses [equivalent to how we keep i915_ggtt + * and i915_ppgtt separate]. + * + * NB this may cause us to mask real lock inversions -- while the + * code is safe today, lockdep may not be able to spot future + * transgressions. + */ + err = mutex_lock_interruptible_nested(&vma->vm->mutex, + !(flags & PIN_GLOBAL)); if (err) goto err_fence; + /* No more allocations allowed now we hold vm->mutex */ + if (unlikely(i915_vma_is_closed(vma))) { err = -ENOENT; goto err_unlock; @@ -980,7 +975,7 @@ err_unlock: mutex_unlock(&vma->vm->mutex); err_fence: if (work) - dma_fence_work_commit(&work->base); + dma_fence_work_commit_imm(&work->base); if (wakeref) intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); err_pages: @@ -1097,6 +1092,7 @@ void i915_vma_release(struct kref *ref) void i915_vma_parked(struct intel_gt *gt) { struct i915_vma *vma, *next; + LIST_HEAD(closed); spin_lock_irq(>->closed_lock); list_for_each_entry_safe(vma, next, >->closed_vma, closed_link) { @@ -1108,28 +1104,26 @@ void i915_vma_parked(struct intel_gt *gt) if (!kref_get_unless_zero(&obj->base.refcount)) continue; - if (i915_vm_tryopen(vm)) { - list_del_init(&vma->closed_link); - } else { + if (!i915_vm_tryopen(vm)) { i915_gem_object_put(obj); - obj = NULL; + continue; } - spin_unlock_irq(>->closed_lock); + list_move(&vma->closed_link, &closed); + } + spin_unlock_irq(>->closed_lock); - if (obj) { - __i915_vma_put(vma); - i915_gem_object_put(obj); - } + /* As the GT is held idle, no vma can be reopened as we destroy them */ + list_for_each_entry_safe(vma, next, &closed, closed_link) { + struct drm_i915_gem_object *obj = vma->obj; + struct i915_address_space *vm = vma->vm; - i915_vm_close(vm); + INIT_LIST_HEAD(&vma->closed_link); + __i915_vma_put(vma); - /* Restart after dropping lock */ - spin_lock_irq(>->closed_lock); - next = list_first_entry(>->closed_vma, - typeof(*next), closed_link); + i915_gem_object_put(obj); + i915_vm_close(vm); } - spin_unlock_irq(>->closed_lock); } static void __i915_vma_iounmap(struct i915_vma *vma) @@ -1173,7 +1167,8 @@ int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) GEM_BUG_ON(!i915_vma_is_pinned(vma)); /* Wait for the vma to be bound before we start! */ - err = i915_request_await_active(rq, &vma->active, 0); + err = i915_request_await_active(rq, &vma->active, + I915_ACTIVE_AWAIT_EXCL); if (err) return err; @@ -1214,6 +1209,10 @@ int i915_vma_move_to_active(struct i915_vma *vma, dma_resv_add_shared_fence(vma->resv, &rq->fence); obj->write_domain = 0; } + + if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence) + i915_active_add_request(&vma->fence->active, rq); + obj->read_domains |= I915_GEM_GPU_DOMAINS; obj->mm.dirty = true; @@ -1227,18 +1226,6 @@ int __i915_vma_unbind(struct i915_vma *vma) lockdep_assert_held(&vma->vm->mutex); - /* - * First wait upon any activity as retiring the request may - * have side-effects such as unpinning or even unbinding this vma. - * - * XXX Actually waiting under the vm->mutex is a hinderance and - * should be pipelined wherever possible. In cases where that is - * unavoidable, we should lift the wait to before the mutex. - */ - ret = i915_vma_sync(vma); - if (ret) - return ret; - if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; @@ -1260,6 +1247,9 @@ int __i915_vma_unbind(struct i915_vma *vma) GEM_BUG_ON(i915_vma_is_active(vma)); if (i915_vma_is_map_and_fenceable(vma)) { + /* Force a pagefault for domain tracking on next user access */ + i915_vma_revoke_mmap(vma); + /* * Check that we have flushed all writes through the GGTT * before the unbind, other due to non-strict nature of those @@ -1276,12 +1266,7 @@ int __i915_vma_unbind(struct i915_vma *vma) i915_vma_flush_writes(vma); /* release the fence reg _after_ flushing */ - ret = i915_vma_revoke_fence(vma); - if (ret) - return ret; - - /* Force a pagefault for domain tracking on next user access */ - i915_vma_revoke_mmap(vma); + i915_vma_revoke_fence(vma); __i915_vma_iounmap(vma); clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma)); @@ -1312,16 +1297,21 @@ int i915_vma_unbind(struct i915_vma *vma) if (!drm_mm_node_allocated(&vma->node)) return 0; - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - /* XXX not always required: nop_clear_range */ - wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); - /* Optimistic wait before taking the mutex */ err = i915_vma_sync(vma); if (err) goto out_rpm; - err = mutex_lock_interruptible(&vm->mutex); + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + /* XXX not always required: nop_clear_range */ + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + + err = mutex_lock_interruptible_nested(&vma->vm->mutex, !wakeref); if (err) goto out_rpm; diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index e1ced1df13e1..8ad1daabcd58 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -30,10 +30,10 @@ #include <drm/drm_mm.h> +#include "gt/intel_ggtt_fencing.h" #include "gem/i915_gem_object.h" #include "i915_gem_gtt.h" -#include "i915_gem_fence_reg.h" #include "i915_active.h" #include "i915_request.h" @@ -326,7 +326,7 @@ static inline struct page *i915_vma_first_page(struct i915_vma *vma) * True if the vma has a fence, false otherwise. */ int __must_check i915_vma_pin_fence(struct i915_vma *vma); -int __must_check i915_vma_revoke_fence(struct i915_vma *vma); +void i915_vma_revoke_fence(struct i915_vma *vma); int __i915_vma_pin_fence(struct i915_vma *vma); diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index d7fe12734db8..db8496b4c38d 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -980,35 +980,32 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) drm_info(&dev_priv->drm, "Display fused off, disabling\n"); info->pipe_mask = 0; + info->cpu_transcoder_mask = 0; } else if (fuse_strap & IVB_PIPE_C_DISABLE) { drm_info(&dev_priv->drm, "PipeC fused off\n"); info->pipe_mask &= ~BIT(PIPE_C); + info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } } else if (HAS_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 9) { u32 dfsm = I915_READ(SKL_DFSM); - u8 enabled_mask = info->pipe_mask; - - if (dfsm & SKL_DFSM_PIPE_A_DISABLE) - enabled_mask &= ~BIT(PIPE_A); - if (dfsm & SKL_DFSM_PIPE_B_DISABLE) - enabled_mask &= ~BIT(PIPE_B); - if (dfsm & SKL_DFSM_PIPE_C_DISABLE) - enabled_mask &= ~BIT(PIPE_C); - if (INTEL_GEN(dev_priv) >= 12 && - (dfsm & TGL_DFSM_PIPE_D_DISABLE)) - enabled_mask &= ~BIT(PIPE_D); - /* - * At least one pipe should be enabled and if there are - * disabled pipes, they should be the last ones, with no holes - * in the mask. - */ - if (enabled_mask == 0 || !is_power_of_2(enabled_mask + 1)) - drm_err(&dev_priv->drm, - "invalid pipe fuse configuration: enabled_mask=0x%x\n", - enabled_mask); - else - info->pipe_mask = enabled_mask; + if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { + info->pipe_mask &= ~BIT(PIPE_A); + info->cpu_transcoder_mask &= ~BIT(TRANSCODER_A); + } + if (dfsm & SKL_DFSM_PIPE_B_DISABLE) { + info->pipe_mask &= ~BIT(PIPE_B); + info->cpu_transcoder_mask &= ~BIT(TRANSCODER_B); + } + if (dfsm & SKL_DFSM_PIPE_C_DISABLE) { + info->pipe_mask &= ~BIT(PIPE_C); + info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); + } + if (INTEL_GEN(dev_priv) >= 12 && + (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { + info->pipe_mask &= ~BIT(PIPE_D); + info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); + } if (dfsm & SKL_DFSM_DISPLAY_HDCP_DISABLE) info->display.has_hdcp = 0; diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 1ecb9df2de91..cce6a72c5ebc 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -168,6 +168,7 @@ struct intel_device_info { u32 display_mmio_offset; u8 pipe_mask; + u8 cpu_transcoder_mask; #define DEFINE_FLAG(name) u8 name:1 DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG); diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 6b922efb1d7c..8aa12cad93ce 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -495,6 +495,5 @@ void intel_dram_edram_detect(struct drm_i915_private *i915) else i915->edram_size_mb = gen9_edram_size_mb(i915, edram_cap); - dev_info(i915->drm.dev, - "Found %uMB of eDRAM\n", i915->edram_size_mb); + drm_info(&i915->drm, "Found %uMB of eDRAM\n", i915->edram_size_mb); } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8375054ba27d..b632b6bb9c3e 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4016,6 +4016,7 @@ static int skl_compute_wm_params(const struct intel_crtc_state *crtc_state, int color_plane); static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, int level, + unsigned int latency, const struct skl_wm_params *wp, const struct skl_wm_level *result_prev, struct skl_wm_level *result /* out */); @@ -4038,7 +4039,9 @@ skl_cursor_allocation(const struct intel_crtc_state *crtc_state, drm_WARN_ON(&dev_priv->drm, ret); for (level = 0; level <= max_level; level++) { - skl_compute_plane_wm(crtc_state, level, &wp, &wm, &wm); + unsigned int latency = dev_priv->wm.skl_latency[level]; + + skl_compute_plane_wm(crtc_state, level, latency, &wp, &wm, &wm); if (wm.min_ddb_alloc == U16_MAX) break; @@ -4972,12 +4975,12 @@ static bool skl_wm_has_lines(struct drm_i915_private *dev_priv, int level) static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, int level, + unsigned int latency, const struct skl_wm_params *wp, const struct skl_wm_level *result_prev, struct skl_wm_level *result /* out */) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - u32 latency = dev_priv->wm.skl_latency[level]; uint_fixed_16_16_t method1, method2; uint_fixed_16_16_t selected_result; u32 res_blocks, res_lines, min_ddb_alloc = 0; @@ -5106,9 +5109,10 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state, for (level = 0; level <= max_level; level++) { struct skl_wm_level *result = &levels[level]; + unsigned int latency = dev_priv->wm.skl_latency[level]; - skl_compute_plane_wm(crtc_state, level, wm_params, - result_prev, result); + skl_compute_plane_wm(crtc_state, level, latency, + wm_params, result_prev, result); result_prev = result; } diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 1447e7516cb7..3f13baaef058 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -60,7 +60,7 @@ static void __vlv_punit_get(struct drm_i915_private *i915) * to the Valleyview P-unit and not all sideband communications. */ if (IS_VALLEYVIEW(i915)) { - pm_qos_update_request(&i915->sb_qos, 0); + cpu_latency_qos_update_request(&i915->sb_qos, 0); on_each_cpu(ping, NULL, 1); } } @@ -68,7 +68,8 @@ static void __vlv_punit_get(struct drm_i915_private *i915) static void __vlv_punit_put(struct drm_i915_private *i915) { if (IS_VALLEYVIEW(i915)) - pm_qos_update_request(&i915->sb_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&i915->sb_qos, + PM_QOS_DEFAULT_VALUE); iosf_mbi_punit_release(); } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index abb18b90d7c3..fa86b7ab2d99 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -665,7 +665,7 @@ void intel_uncore_forcewake_user_put(struct intel_uncore *uncore) mmio_debug_resume(uncore->debug); if (check_for_unclaimed_mmio(uncore)) - dev_info(uncore->i915->drm.dev, + drm_info(&uncore->i915->drm, "Invalid mmio detected during user access\n"); spin_unlock(&uncore->debug->lock); @@ -735,6 +735,28 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore, } /** + * intel_uncore_forcewake_flush - flush the delayed release + * @uncore: the intel_uncore structure + * @fw_domains: forcewake domains to flush + */ +void intel_uncore_forcewake_flush(struct intel_uncore *uncore, + enum forcewake_domains fw_domains) +{ + struct intel_uncore_forcewake_domain *domain; + unsigned int tmp; + + if (!uncore->funcs.force_wake_put) + return; + + fw_domains &= uncore->fw_domains; + for_each_fw_domain_masked(domain, fw_domains, uncore, tmp) { + WRITE_ONCE(domain->active, false); + if (hrtimer_cancel(&domain->timer)) + intel_uncore_fw_release_timer(&domain->timer); + } +} + +/** * intel_uncore_forcewake_put__locked - grab forcewake domain references * @uncore: the intel_uncore structure * @fw_domains: forcewake domains to get reference on diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index dcfa243892c6..8d3aa8b9acf9 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -209,7 +209,11 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore, enum forcewake_domains domains); void intel_uncore_forcewake_put(struct intel_uncore *uncore, enum forcewake_domains domains); -/* Like above but the caller must manage the uncore.lock itself. +void intel_uncore_forcewake_flush(struct intel_uncore *uncore, + enum forcewake_domains fw_domains); + +/* + * Like above but the caller must manage the uncore.lock itself. * Must be used with I915_READ_FW and friends. */ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore, diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c index 8fbf6f4d3f26..dfd87d082218 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.c +++ b/drivers/gpu/drm/i915/intel_wakeref.c @@ -70,11 +70,12 @@ unlock: void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags) { - INTEL_WAKEREF_BUG_ON(work_pending(&wf->work)); + INTEL_WAKEREF_BUG_ON(delayed_work_pending(&wf->work)); /* Assume we are not in process context and so cannot sleep. */ if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) { - schedule_work(&wf->work); + mod_delayed_work(system_wq, &wf->work, + FIELD_GET(INTEL_WAKEREF_PUT_DELAY, flags)); return; } @@ -83,7 +84,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags) static void __intel_wakeref_put_work(struct work_struct *wrk) { - struct intel_wakeref *wf = container_of(wrk, typeof(*wf), work); + struct intel_wakeref *wf = container_of(wrk, typeof(*wf), work.work); if (atomic_add_unless(&wf->count, -1, 1)) return; @@ -104,8 +105,9 @@ void __intel_wakeref_init(struct intel_wakeref *wf, atomic_set(&wf->count, 0); wf->wakeref = 0; - INIT_WORK(&wf->work, __intel_wakeref_put_work); - lockdep_init_map(&wf->work.lockdep_map, "wakeref.work", &key->work, 0); + INIT_DELAYED_WORK(&wf->work, __intel_wakeref_put_work); + lockdep_init_map(&wf->work.work.lockdep_map, + "wakeref.work", &key->work, 0); } int intel_wakeref_wait_for_idle(struct intel_wakeref *wf) diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h index 7d1e676b71ef..545c8f277c46 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.h +++ b/drivers/gpu/drm/i915/intel_wakeref.h @@ -8,6 +8,7 @@ #define INTEL_WAKEREF_H #include <linux/atomic.h> +#include <linux/bitfield.h> #include <linux/bits.h> #include <linux/lockdep.h> #include <linux/mutex.h> @@ -41,7 +42,7 @@ struct intel_wakeref { struct intel_runtime_pm *rpm; const struct intel_wakeref_ops *ops; - struct work_struct work; + struct delayed_work work; }; struct intel_wakeref_lockclass { @@ -117,6 +118,11 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf) return atomic_inc_not_zero(&wf->count); } +enum { + INTEL_WAKEREF_PUT_ASYNC_BIT = 0, + __INTEL_WAKEREF_PUT_LAST_BIT__ +}; + /** * intel_wakeref_put_flags: Release the wakeref * @wf: the wakeref @@ -134,7 +140,9 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf) */ static inline void __intel_wakeref_put(struct intel_wakeref *wf, unsigned long flags) -#define INTEL_WAKEREF_PUT_ASYNC BIT(0) +#define INTEL_WAKEREF_PUT_ASYNC BIT(INTEL_WAKEREF_PUT_ASYNC_BIT) +#define INTEL_WAKEREF_PUT_DELAY \ + GENMASK(BITS_PER_LONG - 1, __INTEL_WAKEREF_PUT_LAST_BIT__) { INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0); if (unlikely(!atomic_add_unless(&wf->count, -1, 1))) @@ -154,6 +162,14 @@ intel_wakeref_put_async(struct intel_wakeref *wf) __intel_wakeref_put(wf, INTEL_WAKEREF_PUT_ASYNC); } +static inline void +intel_wakeref_put_delay(struct intel_wakeref *wf, unsigned long delay) +{ + __intel_wakeref_put(wf, + INTEL_WAKEREF_PUT_ASYNC | + FIELD_PREP(INTEL_WAKEREF_PUT_DELAY, delay)); +} + /** * intel_wakeref_lock: Lock the wakeref (mutex) * @wf: the wakeref @@ -194,7 +210,7 @@ intel_wakeref_unlock_wait(struct intel_wakeref *wf) { mutex_lock(&wf->mutex); mutex_unlock(&wf->mutex); - flush_work(&wf->work); + flush_delayed_work(&wf->work); } /** diff --git a/drivers/gpu/drm/i915/intel_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c index 2bb9f9f9a50a..2186386a45c8 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/intel_wopcm.c @@ -86,7 +86,7 @@ void intel_wopcm_init_early(struct intel_wopcm *wopcm) else wopcm->size = GEN9_WOPCM_SIZE; - DRM_DEV_DEBUG_DRIVER(i915->drm.dev, "WOPCM: %uK\n", wopcm->size / 1024); + drm_dbg(&i915->drm, "WOPCM: %uK\n", wopcm->size / 1024); } static inline u32 context_reserved_size(struct drm_i915_private *i915) @@ -112,7 +112,7 @@ static inline bool gen9_check_dword_gap(struct drm_i915_private *i915, offset = guc_wopcm_base + GEN9_GUC_WOPCM_OFFSET; if (offset > guc_wopcm_size || (guc_wopcm_size - offset) < sizeof(u32)) { - dev_err(i915->drm.dev, + drm_err(&i915->drm, "WOPCM: invalid GuC region size: %uK < %uK\n", guc_wopcm_size / SZ_1K, (u32)(offset + sizeof(u32)) / SZ_1K); @@ -131,7 +131,7 @@ static inline bool gen9_check_huc_fw_fits(struct drm_i915_private *i915, * firmware uploading would fail. */ if (huc_fw_size > guc_wopcm_size - GUC_WOPCM_RESERVED) { - dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n", + drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), (guc_wopcm_size - GUC_WOPCM_RESERVED) / SZ_1K, huc_fw_size / 1024); @@ -166,7 +166,7 @@ static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, size = wopcm_size - ctx_rsvd; if (unlikely(range_overflows(guc_wopcm_base, guc_wopcm_size, size))) { - dev_err(i915->drm.dev, + drm_err(&i915->drm, "WOPCM: invalid GuC region layout: %uK + %uK > %uK\n", guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K, size / SZ_1K); @@ -175,7 +175,7 @@ static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, size = guc_fw_size + GUC_WOPCM_RESERVED + GUC_WOPCM_STACK_RESERVED; if (unlikely(guc_wopcm_size < size)) { - dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n", + drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc_wopcm_size / SZ_1K, size / SZ_1K); return false; @@ -183,7 +183,7 @@ static inline bool __check_layout(struct drm_i915_private *i915, u32 wopcm_size, size = huc_fw_size + WOPCM_RESERVED_SIZE; if (unlikely(guc_wopcm_base < size)) { - dev_err(i915->drm.dev, "WOPCM: no space for %s: %uK < %uK\n", + drm_err(&i915->drm, "WOPCM: no space for %s: %uK < %uK\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), guc_wopcm_base / SZ_1K, size / SZ_1K); return false; @@ -242,10 +242,8 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) return; if (__wopcm_regs_locked(gt->uncore, &guc_wopcm_base, &guc_wopcm_size)) { - DRM_DEV_DEBUG_DRIVER(i915->drm.dev, - "GuC WOPCM is already locked [%uK, %uK)\n", - guc_wopcm_base / SZ_1K, - guc_wopcm_size / SZ_1K); + drm_dbg(&i915->drm, "GuC WOPCM is already locked [%uK, %uK)\n", + guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K); goto check; } @@ -266,8 +264,8 @@ void intel_wopcm_init(struct intel_wopcm *wopcm) guc_wopcm_size = wopcm->size - ctx_rsvd - guc_wopcm_base; guc_wopcm_size &= GUC_WOPCM_SIZE_MASK; - DRM_DEV_DEBUG_DRIVER(i915->drm.dev, "Calculated GuC WOPCM [%uK, %uK)\n", - guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K); + drm_dbg(&i915->drm, "Calculated GuC WOPCM [%uK, %uK)\n", + guc_wopcm_base / SZ_1K, guc_wopcm_size / SZ_1K); check: if (__check_layout(i915, wopcm->size, guc_wopcm_base, guc_wopcm_size, diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bdw.c b/drivers/gpu/drm/i915/oa/i915_oa_bdw.c deleted file mode 100644 index 14da5c3b569d..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_bdw.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_bdw.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x000000a0 }, - { _MMIO(0x9888), 0x198b0000 }, - { _MMIO(0x9888), 0x078b0066 }, - { _MMIO(0x9888), 0x118b0000 }, - { _MMIO(0x9888), 0x258b0000 }, - { _MMIO(0x9888), 0x21850008 }, - { _MMIO(0x9888), 0x0d834000 }, - { _MMIO(0x9888), 0x07844000 }, - { _MMIO(0x9888), 0x17804000 }, - { _MMIO(0x9888), 0x21800000 }, - { _MMIO(0x9888), 0x4f800000 }, - { _MMIO(0x9888), 0x41800000 }, - { _MMIO(0x9888), 0x31800000 }, - { _MMIO(0x9840), 0x00000080 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_bdw(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "d6de6f55-e526-4f79-a6a6-d7315c09044e", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "d6de6f55-e526-4f79-a6a6-d7315c09044e"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bdw.h b/drivers/gpu/drm/i915/oa/i915_oa_bdw.h deleted file mode 100644 index 0cee3334f0a6..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_bdw.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_BDW_H__ -#define __I915_OA_BDW_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_bdw(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bxt.c b/drivers/gpu/drm/i915/oa/i915_oa_bxt.c deleted file mode 100644 index 3e785bafcf99..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_bxt.c +++ /dev/null @@ -1,88 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_bxt.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x19800000 }, - { _MMIO(0x9888), 0x07800063 }, - { _MMIO(0x9888), 0x11800000 }, - { _MMIO(0x9888), 0x23810008 }, - { _MMIO(0x9888), 0x1d950400 }, - { _MMIO(0x9888), 0x0f922000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x55900000 }, - { _MMIO(0x9888), 0x47900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_bxt(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "5ee72f5c-092f-421e-8b70-225f7c3e9612", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "5ee72f5c-092f-421e-8b70-225f7c3e9612"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_bxt.h b/drivers/gpu/drm/i915/oa/i915_oa_bxt.h deleted file mode 100644 index 0bdf391323ec..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_bxt.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_BXT_H__ -#define __I915_OA_BXT_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_bxt(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c deleted file mode 100644 index 0ea86f70a06c..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_cflgt2.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_cflgt2(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "74fb4902-d3d3-4237-9e90-cbdc68d0a446", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "74fb4902-d3d3-4237-9e90-cbdc68d0a446"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h deleted file mode 100644 index 6b862280ab78..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt2.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_CFLGT2_H__ -#define __I915_OA_CFLGT2_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_cflgt2(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c deleted file mode 100644 index fc632dd890bf..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_cflgt3.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "577e8e2c-3fa0-4875-8743-3538d585e3b0", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "577e8e2c-3fa0-4875-8743-3538d585e3b0"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h deleted file mode 100644 index 4ca9d8f89b2f..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cflgt3.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_CFLGT3_H__ -#define __I915_OA_CFLGT3_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_chv.c b/drivers/gpu/drm/i915/oa/i915_oa_chv.c deleted file mode 100644 index 6cd4e9921a8a..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_chv.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_chv.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x000000a0 }, - { _MMIO(0x9888), 0x59800000 }, - { _MMIO(0x9888), 0x59800001 }, - { _MMIO(0x9888), 0x338b0000 }, - { _MMIO(0x9888), 0x258b0066 }, - { _MMIO(0x9888), 0x058b0000 }, - { _MMIO(0x9888), 0x038b0000 }, - { _MMIO(0x9888), 0x03844000 }, - { _MMIO(0x9888), 0x47800080 }, - { _MMIO(0x9888), 0x57800000 }, - { _MMIO(0x1823a4), 0x00000000 }, - { _MMIO(0x9888), 0x59800000 }, - { _MMIO(0x9840), 0x00000080 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_chv(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "4a534b07-cba3-414d-8d60-874830e883aa", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "4a534b07-cba3-414d-8d60-874830e883aa"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_chv.h b/drivers/gpu/drm/i915/oa/i915_oa_chv.h deleted file mode 100644 index 3cac7bbc9c71..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_chv.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_CHV_H__ -#define __I915_OA_CHV_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_chv(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cnl.c b/drivers/gpu/drm/i915/oa/i915_oa_cnl.c deleted file mode 100644 index 1041e8914993..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cnl.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_cnl.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x0000ffff }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x0000ffff }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x0000ffff }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0xd04), 0x00000200 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x17060000 }, - { _MMIO(0x9840), 0x00000000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x13034000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x07060066 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x05060000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x0f080040 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x07091000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x0f041000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x1d004000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x35000000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x49000000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x3d000000 }, - { _MMIO(0x9884), 0x00000007 }, - { _MMIO(0x9888), 0x31000000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "db41edd4-d8e7-4730-ad11-b9a2d6833503", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "db41edd4-d8e7-4730-ad11-b9a2d6833503"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_cnl.h b/drivers/gpu/drm/i915/oa/i915_oa_cnl.h deleted file mode 100644 index db379f5fcbb9..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_cnl.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_CNL_H__ -#define __I915_OA_CNL_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_glk.c b/drivers/gpu/drm/i915/oa/i915_oa_glk.c deleted file mode 100644 index bd15ebe9aeeb..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_glk.c +++ /dev/null @@ -1,88 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_glk.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x19800000 }, - { _MMIO(0x9888), 0x07800063 }, - { _MMIO(0x9888), 0x11800000 }, - { _MMIO(0x9888), 0x23810008 }, - { _MMIO(0x9888), 0x1d950400 }, - { _MMIO(0x9888), 0x0f922000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x55900000 }, - { _MMIO(0x9888), 0x47900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_glk(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "dd3fd789-e783-4204-8cd0-b671bbccb0cf", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "dd3fd789-e783-4204-8cd0-b671bbccb0cf"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_glk.h b/drivers/gpu/drm/i915/oa/i915_oa_glk.h deleted file mode 100644 index 779f343efd11..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_glk.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_GLK_H__ -#define __I915_OA_GLK_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_glk(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_hsw.c b/drivers/gpu/drm/i915/oa/i915_oa_hsw.c deleted file mode 100644 index 133721a8619f..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_hsw.c +++ /dev/null @@ -1,118 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_hsw.h" - -static const struct i915_oa_reg b_counter_config_render_basic[] = { - { _MMIO(0x2724), 0x00800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2714), 0x00800000 }, - { _MMIO(0x2710), 0x00000000 }, -}; - -static const struct i915_oa_reg flex_eu_config_render_basic[] = { -}; - -static const struct i915_oa_reg mux_config_render_basic[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x253a4), 0x01600000 }, - { _MMIO(0x25440), 0x00100000 }, - { _MMIO(0x25128), 0x00000000 }, - { _MMIO(0x2691c), 0x00000800 }, - { _MMIO(0x26aa0), 0x01500000 }, - { _MMIO(0x26b9c), 0x00006000 }, - { _MMIO(0x2791c), 0x00000800 }, - { _MMIO(0x27aa0), 0x01500000 }, - { _MMIO(0x27b9c), 0x00006000 }, - { _MMIO(0x2641c), 0x00000400 }, - { _MMIO(0x25380), 0x00000010 }, - { _MMIO(0x2538c), 0x00000000 }, - { _MMIO(0x25384), 0x0800aaaa }, - { _MMIO(0x25400), 0x00000004 }, - { _MMIO(0x2540c), 0x06029000 }, - { _MMIO(0x25410), 0x00000002 }, - { _MMIO(0x25404), 0x5c30ffff }, - { _MMIO(0x25100), 0x00000016 }, - { _MMIO(0x25110), 0x00000400 }, - { _MMIO(0x25104), 0x00000000 }, - { _MMIO(0x26804), 0x00001211 }, - { _MMIO(0x26884), 0x00000100 }, - { _MMIO(0x26900), 0x00000002 }, - { _MMIO(0x26908), 0x00700000 }, - { _MMIO(0x26904), 0x00000000 }, - { _MMIO(0x26984), 0x00001022 }, - { _MMIO(0x26a04), 0x00000011 }, - { _MMIO(0x26a80), 0x00000006 }, - { _MMIO(0x26a88), 0x00000c02 }, - { _MMIO(0x26a84), 0x00000000 }, - { _MMIO(0x26b04), 0x00001000 }, - { _MMIO(0x26b80), 0x00000002 }, - { _MMIO(0x26b8c), 0x00000007 }, - { _MMIO(0x26b84), 0x00000000 }, - { _MMIO(0x27804), 0x00004844 }, - { _MMIO(0x27884), 0x00000400 }, - { _MMIO(0x27900), 0x00000002 }, - { _MMIO(0x27908), 0x0e000000 }, - { _MMIO(0x27904), 0x00000000 }, - { _MMIO(0x27984), 0x00004088 }, - { _MMIO(0x27a04), 0x00000044 }, - { _MMIO(0x27a80), 0x00000006 }, - { _MMIO(0x27a88), 0x00018040 }, - { _MMIO(0x27a84), 0x00000000 }, - { _MMIO(0x27b04), 0x00004000 }, - { _MMIO(0x27b80), 0x00000002 }, - { _MMIO(0x27b8c), 0x000000e0 }, - { _MMIO(0x27b84), 0x00000000 }, - { _MMIO(0x26104), 0x00002222 }, - { _MMIO(0x26184), 0x0c006666 }, - { _MMIO(0x26284), 0x04000000 }, - { _MMIO(0x26304), 0x04000000 }, - { _MMIO(0x26400), 0x00000002 }, - { _MMIO(0x26410), 0x000000a0 }, - { _MMIO(0x26404), 0x00000000 }, - { _MMIO(0x25420), 0x04108020 }, - { _MMIO(0x25424), 0x1284a420 }, - { _MMIO(0x2541c), 0x00000000 }, - { _MMIO(0x25428), 0x00042049 }, -}; - -static ssize_t -show_render_basic_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_hsw(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "403d8832-1a27-4aa6-a64e-f5389ce7b212", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_render_basic; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_render_basic); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_render_basic; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_render_basic); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_render_basic; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_render_basic); - - dev_priv->perf.test_config.sysfs_metric.name = "403d8832-1a27-4aa6-a64e-f5389ce7b212"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_render_basic_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_hsw.h b/drivers/gpu/drm/i915/oa/i915_oa_hsw.h deleted file mode 100644 index ba97f732f136..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_hsw.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_HSW_H__ -#define __I915_OA_HSW_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_hsw(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_icl.c b/drivers/gpu/drm/i915/oa/i915_oa_icl.c deleted file mode 100644 index 2d92041b754f..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_icl.c +++ /dev/null @@ -1,98 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_icl.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x0000ffff }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x0000ffff }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x0000ffff }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0xd04), 0x00000200 }, - { _MMIO(0x9840), 0x00000000 }, - { _MMIO(0x9884), 0x00000000 }, - { _MMIO(0x9888), 0x10060000 }, - { _MMIO(0x9888), 0x22060000 }, - { _MMIO(0x9888), 0x16060000 }, - { _MMIO(0x9888), 0x24060000 }, - { _MMIO(0x9888), 0x18060000 }, - { _MMIO(0x9888), 0x1a060000 }, - { _MMIO(0x9888), 0x12060000 }, - { _MMIO(0x9888), 0x14060000 }, - { _MMIO(0x9888), 0x10060000 }, - { _MMIO(0x9888), 0x22060000 }, - { _MMIO(0x9884), 0x00000003 }, - { _MMIO(0x9888), 0x16130000 }, - { _MMIO(0x9888), 0x24000001 }, - { _MMIO(0x9888), 0x0e130056 }, - { _MMIO(0x9888), 0x10130000 }, - { _MMIO(0x9888), 0x1a130000 }, - { _MMIO(0x9888), 0x541f0001 }, - { _MMIO(0x9888), 0x181f0000 }, - { _MMIO(0x9888), 0x4c1f0000 }, - { _MMIO(0x9888), 0x301f0000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "a291665e-244b-4b76-9b9a-01de9d3c8068", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "a291665e-244b-4b76-9b9a-01de9d3c8068"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_icl.h b/drivers/gpu/drm/i915/oa/i915_oa_icl.h deleted file mode 100644 index 5c64112d720e..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_icl.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_ICL_H__ -#define __I915_OA_ICL_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_icl(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c deleted file mode 100644 index 1c3a67c9cfe0..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_kblgt2.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_kblgt2(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "baa3c7e4-52b6-4b85-801e-465a94b746dd", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "baa3c7e4-52b6-4b85-801e-465a94b746dd"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h deleted file mode 100644 index 810532fa6b63..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt2.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_KBLGT2_H__ -#define __I915_OA_KBLGT2_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_kblgt2(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c deleted file mode 100644 index ebbe5a9c9fdc..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_kblgt3.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_kblgt3(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "f1792f32-6db2-4b50-b4b2-557128f1688d", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "f1792f32-6db2-4b50-b4b2-557128f1688d"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h deleted file mode 100644 index 13d70456fabd..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_kblgt3.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_KBLGT3_H__ -#define __I915_OA_KBLGT3_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_kblgt3(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c deleted file mode 100644 index 1bc359ed34e8..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.c +++ /dev/null @@ -1,88 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_sklgt2.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810016 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_sklgt2(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "1651949f-0ac0-4cb1-a06f-dafd74a407d1", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "1651949f-0ac0-4cb1-a06f-dafd74a407d1"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h deleted file mode 100644 index fda70c51a6ec..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt2.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_SKLGT2_H__ -#define __I915_OA_SKLGT2_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_sklgt2(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c deleted file mode 100644 index 6e352f881310..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_sklgt3.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_sklgt3(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "2b985803-d3c9-4629-8a4f-634bfecba0e8", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "2b985803-d3c9-4629-8a4f-634bfecba0e8"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h deleted file mode 100644 index df74eba5799e..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt3.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_SKLGT3_H__ -#define __I915_OA_SKLGT3_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_sklgt3(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c b/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c deleted file mode 100644 index 8f345115a306..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.c +++ /dev/null @@ -1,89 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_sklgt4.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0x2740), 0x00000000 }, - { _MMIO(0x2744), 0x00800000 }, - { _MMIO(0x2714), 0xf0800000 }, - { _MMIO(0x2710), 0x00000000 }, - { _MMIO(0x2724), 0xf0800000 }, - { _MMIO(0x2720), 0x00000000 }, - { _MMIO(0x2770), 0x00000004 }, - { _MMIO(0x2774), 0x00000000 }, - { _MMIO(0x2778), 0x00000003 }, - { _MMIO(0x277c), 0x00000000 }, - { _MMIO(0x2780), 0x00000007 }, - { _MMIO(0x2784), 0x00000000 }, - { _MMIO(0x2788), 0x00100002 }, - { _MMIO(0x278c), 0x0000fff7 }, - { _MMIO(0x2790), 0x00100002 }, - { _MMIO(0x2794), 0x0000ffcf }, - { _MMIO(0x2798), 0x00100082 }, - { _MMIO(0x279c), 0x0000ffef }, - { _MMIO(0x27a0), 0x001000c2 }, - { _MMIO(0x27a4), 0x0000ffe7 }, - { _MMIO(0x27a8), 0x00100001 }, - { _MMIO(0x27ac), 0x0000ffe7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x9840), 0x00000080 }, - { _MMIO(0x9888), 0x11810000 }, - { _MMIO(0x9888), 0x07810013 }, - { _MMIO(0x9888), 0x1f810000 }, - { _MMIO(0x9888), 0x1d810000 }, - { _MMIO(0x9888), 0x1b930040 }, - { _MMIO(0x9888), 0x07e54000 }, - { _MMIO(0x9888), 0x1f908000 }, - { _MMIO(0x9888), 0x11900000 }, - { _MMIO(0x9888), 0x37900000 }, - { _MMIO(0x9888), 0x53900000 }, - { _MMIO(0x9888), 0x45900000 }, - { _MMIO(0x9888), 0x33900000 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_sklgt4(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "882fa433-1f4a-4a67-a962-c741888fe5f5", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "882fa433-1f4a-4a67-a962-c741888fe5f5"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h b/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h deleted file mode 100644 index 378ab7ab78d5..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_sklgt4.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018-2019 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_SKLGT4_H__ -#define __I915_OA_SKLGT4_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_sklgt4(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.c b/drivers/gpu/drm/i915/oa/i915_oa_tgl.c deleted file mode 100644 index a29d93707345..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_tgl.c +++ /dev/null @@ -1,121 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2018 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#include <linux/sysfs.h> - -#include "i915_drv.h" -#include "i915_oa_tgl.h" - -static const struct i915_oa_reg b_counter_config_test_oa[] = { - { _MMIO(0xD920), 0x00000000 }, - { _MMIO(0xD900), 0x00000000 }, - { _MMIO(0xD904), 0xF0800000 }, - { _MMIO(0xD910), 0x00000000 }, - { _MMIO(0xD914), 0xF0800000 }, - { _MMIO(0xDC40), 0x00FF0000 }, - { _MMIO(0xD940), 0x00000004 }, - { _MMIO(0xD944), 0x0000FFFF }, - { _MMIO(0xDC00), 0x00000004 }, - { _MMIO(0xDC04), 0x0000FFFF }, - { _MMIO(0xD948), 0x00000003 }, - { _MMIO(0xD94C), 0x0000FFFF }, - { _MMIO(0xDC08), 0x00000003 }, - { _MMIO(0xDC0C), 0x0000FFFF }, - { _MMIO(0xD950), 0x00000007 }, - { _MMIO(0xD954), 0x0000FFFF }, - { _MMIO(0xDC10), 0x00000007 }, - { _MMIO(0xDC14), 0x0000FFFF }, - { _MMIO(0xD958), 0x00100002 }, - { _MMIO(0xD95C), 0x0000FFF7 }, - { _MMIO(0xDC18), 0x00100002 }, - { _MMIO(0xDC1C), 0x0000FFF7 }, - { _MMIO(0xD960), 0x00100002 }, - { _MMIO(0xD964), 0x0000FFCF }, - { _MMIO(0xDC20), 0x00100002 }, - { _MMIO(0xDC24), 0x0000FFCF }, - { _MMIO(0xD968), 0x00100082 }, - { _MMIO(0xD96C), 0x0000FFEF }, - { _MMIO(0xDC28), 0x00100082 }, - { _MMIO(0xDC2C), 0x0000FFEF }, - { _MMIO(0xD970), 0x001000C2 }, - { _MMIO(0xD974), 0x0000FFE7 }, - { _MMIO(0xDC30), 0x001000C2 }, - { _MMIO(0xDC34), 0x0000FFE7 }, - { _MMIO(0xD978), 0x00100001 }, - { _MMIO(0xD97C), 0x0000FFE7 }, - { _MMIO(0xDC38), 0x00100001 }, - { _MMIO(0xDC3C), 0x0000FFE7 }, -}; - -static const struct i915_oa_reg flex_eu_config_test_oa[] = { -}; - -static const struct i915_oa_reg mux_config_test_oa[] = { - { _MMIO(0x0D04), 0x00000200 }, - { _MMIO(0x9840), 0x00000000 }, - { _MMIO(0x9884), 0x00000000 }, - { _MMIO(0x9888), 0x280E0000 }, - { _MMIO(0x9888), 0x1E0E0147 }, - { _MMIO(0x9888), 0x180E0000 }, - { _MMIO(0x9888), 0x160E0000 }, - { _MMIO(0x9888), 0x1E0F1000 }, - { _MMIO(0x9888), 0x1E104000 }, - { _MMIO(0x9888), 0x2E020100 }, - { _MMIO(0x9888), 0x2C030004 }, - { _MMIO(0x9888), 0x38003000 }, - { _MMIO(0x9888), 0x1E0A8000 }, - { _MMIO(0x9884), 0x00000003 }, - { _MMIO(0x9888), 0x49110000 }, - { _MMIO(0x9888), 0x5D101400 }, - { _MMIO(0x9888), 0x1D140020 }, - { _MMIO(0x9888), 0x1D1103A3 }, - { _MMIO(0x9888), 0x01110000 }, - { _MMIO(0x9888), 0x61111000 }, - { _MMIO(0x9888), 0x1F128000 }, - { _MMIO(0x9888), 0x17100000 }, - { _MMIO(0x9888), 0x55100630 }, - { _MMIO(0x9888), 0x57100000 }, - { _MMIO(0x9888), 0x31100000 }, - { _MMIO(0x9884), 0x00000003 }, - { _MMIO(0x9888), 0x65100002 }, - { _MMIO(0x9884), 0x00000000 }, - { _MMIO(0x9888), 0x42000001 }, -}; - -static ssize_t -show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "1\n"); -} - -void -i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv) -{ - strlcpy(dev_priv->perf.test_config.uuid, - "80a833f0-2504-4321-8894-e9277844ce7b", - sizeof(dev_priv->perf.test_config.uuid)); - dev_priv->perf.test_config.id = 1; - - dev_priv->perf.test_config.mux_regs = mux_config_test_oa; - dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa); - - dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa; - dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa); - - dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa; - dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa); - - dev_priv->perf.test_config.sysfs_metric.name = "80a833f0-2504-4321-8894-e9277844ce7b"; - dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs; - - dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr; - - dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id"; - dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444; - dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id; -} diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.h b/drivers/gpu/drm/i915/oa/i915_oa_tgl.h deleted file mode 100644 index 4c25f0be825c..000000000000 --- a/drivers/gpu/drm/i915/oa/i915_oa_tgl.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2018 Intel Corporation - * - * Autogenerated file by GPU Top : https://github.com/rib/gputop - * DO NOT EDIT manually! - */ - -#ifndef __I915_OA_TGL_H__ -#define __I915_OA_TGL_H__ - -struct drm_i915_private; - -void i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv); - -#endif diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c index 68bbb1580162..4002c984c2e0 100644 --- a/drivers/gpu/drm/i915/selftests/i915_active.c +++ b/drivers/gpu/drm/i915/selftests/i915_active.c @@ -153,7 +153,7 @@ static int live_active_wait(void *arg) if (IS_ERR(active)) return PTR_ERR(active); - i915_active_wait(&active->base); + __i915_active_wait(&active->base, TASK_UNINTERRUPTIBLE); if (!READ_ONCE(active->retired)) { struct drm_printer p = drm_err_printer(__func__); @@ -228,11 +228,11 @@ static int live_active_barrier(void *arg) } i915_active_release(&active->base); + if (err) + goto out; - if (err == 0) - err = i915_active_wait(&active->base); - - if (err == 0 && !READ_ONCE(active->retired)) { + __i915_active_wait(&active->base, TASK_UNINTERRUPTIBLE); + if (!READ_ONCE(active->retired)) { pr_err("i915_active not retired after flushing barriers!\n"); err = -EINVAL; } @@ -277,7 +277,7 @@ static struct intel_engine_cs *node_to_barrier(struct active_node *it) void i915_active_print(struct i915_active *ref, struct drm_printer *m) { - drm_printf(m, "active %pS:%pS\n", ref->active, ref->retire); + drm_printf(m, "active %ps:%ps\n", ref->active, ref->retire); drm_printf(m, "\tcount: %d\n", atomic_read(&ref->count)); drm_printf(m, "\tpreallocated barriers? %s\n", yesno(!llist_empty(&ref->preallocated_barriers))); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index 623759b73bb4..88d400b9df88 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -125,8 +125,6 @@ static void pm_resume(struct drm_i915_private *i915) */ with_intel_runtime_pm(&i915->runtime_pm, wakeref) { i915_ggtt_resume(&i915->ggtt); - i915_gem_restore_fences(&i915->ggtt); - i915_gem_resume(i915); } } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index 06ef88510209..028baae9631f 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -45,8 +45,8 @@ static void quirk_add(struct drm_i915_gem_object *obj, static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects) { - unsigned long unbound, bound, count; struct drm_i915_gem_object *obj; + unsigned long count; count = 0; do { @@ -72,30 +72,6 @@ static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects) pr_debug("Filled GGTT with %lu pages [%llu total]\n", count, ggtt->vm.total / PAGE_SIZE); - bound = 0; - unbound = 0; - list_for_each_entry(obj, objects, st_link) { - GEM_BUG_ON(!obj->mm.quirked); - - if (atomic_read(&obj->bind_count)) - bound++; - else - unbound++; - } - GEM_BUG_ON(bound + unbound != count); - - if (unbound) { - pr_err("%s: Found %lu objects unbound, expected %u!\n", - __func__, unbound, 0); - return -EINVAL; - } - - if (bound != count) { - pr_err("%s: Found %lu objects bound, expected %lu!\n", - __func__, bound, count); - return -EINVAL; - } - if (list_empty(&ggtt->vm.bound_list)) { pr_err("No objects on the GGTT inactive list!\n"); return -EINVAL; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index b342bef5e7c9..5d2a02fcf595 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1229,7 +1229,6 @@ static void track_vma_bind(struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; - atomic_inc(&obj->bind_count); /* track for eviction later */ __i915_gem_object_pin_pages(obj); GEM_BUG_ON(vma->pages); diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c index d1a1568c47ba..5608fab98d5d 100644 --- a/drivers/gpu/drm/i915/selftests/i915_perf.c +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c @@ -14,10 +14,85 @@ #include "igt_flush_test.h" #include "lib_sw_fence.h" +#define TEST_OA_CONFIG_UUID "12345678-1234-1234-1234-1234567890ab" + +static int +alloc_empty_config(struct i915_perf *perf) +{ + struct i915_oa_config *oa_config; + + oa_config = kzalloc(sizeof(*oa_config), GFP_KERNEL); + if (!oa_config) + return -ENOMEM; + + oa_config->perf = perf; + kref_init(&oa_config->ref); + + strlcpy(oa_config->uuid, TEST_OA_CONFIG_UUID, sizeof(oa_config->uuid)); + + mutex_lock(&perf->metrics_lock); + + oa_config->id = idr_alloc(&perf->metrics_idr, oa_config, 2, 0, GFP_KERNEL); + if (oa_config->id < 0) { + mutex_unlock(&perf->metrics_lock); + i915_oa_config_put(oa_config); + return -ENOMEM; + } + + mutex_unlock(&perf->metrics_lock); + + return 0; +} + +static void +destroy_empty_config(struct i915_perf *perf) +{ + struct i915_oa_config *oa_config = NULL, *tmp; + int id; + + mutex_lock(&perf->metrics_lock); + + idr_for_each_entry(&perf->metrics_idr, tmp, id) { + if (!strcmp(tmp->uuid, TEST_OA_CONFIG_UUID)) { + oa_config = tmp; + break; + } + } + + if (oa_config) + idr_remove(&perf->metrics_idr, oa_config->id); + + mutex_unlock(&perf->metrics_lock); + + if (oa_config) + i915_oa_config_put(oa_config); +} + +static struct i915_oa_config * +get_empty_config(struct i915_perf *perf) +{ + struct i915_oa_config *oa_config = NULL, *tmp; + int id; + + mutex_lock(&perf->metrics_lock); + + idr_for_each_entry(&perf->metrics_idr, tmp, id) { + if (!strcmp(tmp->uuid, TEST_OA_CONFIG_UUID)) { + oa_config = i915_oa_config_get(tmp); + break; + } + } + + mutex_unlock(&perf->metrics_lock); + + return oa_config; +} + static struct i915_perf_stream * test_stream(struct i915_perf *perf) { struct drm_i915_perf_open_param param = {}; + struct i915_oa_config *oa_config = get_empty_config(perf); struct perf_open_properties props = { .engine = intel_engine_lookup_user(perf->i915, I915_ENGINE_CLASS_RENDER, @@ -25,13 +100,19 @@ test_stream(struct i915_perf *perf) .sample_flags = SAMPLE_OA_REPORT, .oa_format = IS_GEN(perf->i915, 12) ? I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8, - .metrics_set = 1, }; struct i915_perf_stream *stream; + if (!oa_config) + return NULL; + + props.metrics_set = oa_config->id; + stream = kzalloc(sizeof(*stream), GFP_KERNEL); - if (!stream) + if (!stream) { + i915_oa_config_put(oa_config); return NULL; + } stream->perf = perf; @@ -42,6 +123,8 @@ test_stream(struct i915_perf *perf) } mutex_unlock(&perf->lock); + i915_oa_config_put(oa_config); + return stream; } @@ -206,6 +289,7 @@ int i915_perf_live_selftests(struct drm_i915_private *i915) SUBTEST(live_noa_delay), }; struct i915_perf *perf = &i915->perf; + int err; if (!perf->metrics_kobj || !perf->ops.enable_metric_set) return 0; @@ -213,5 +297,13 @@ int i915_perf_live_selftests(struct drm_i915_private *i915) if (intel_gt_is_wedged(&i915->gt)) return 0; - return i915_subtests(tests, i915); + err = alloc_empty_config(&i915->perf); + if (err) + return err; + + err = i915_subtests(tests, i915); + + destroy_empty_config(&i915->perf); + + return err; } diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index f89d9c42f1fa..1dab0360f76a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -28,6 +28,7 @@ #include "gem/selftests/mock_context.h" #include "gt/intel_engine_pm.h" +#include "gt/intel_engine_user.h" #include "gt/intel_gt.h" #include "i915_random.h" @@ -51,6 +52,11 @@ static unsigned int num_uabi_engines(struct drm_i915_private *i915) return count; } +static struct intel_engine_cs *rcs0(struct drm_i915_private *i915) +{ + return intel_engine_lookup_user(i915, I915_ENGINE_CLASS_RENDER, 0); +} + static int igt_add_request(void *arg) { struct drm_i915_private *i915 = arg; @@ -58,7 +64,7 @@ static int igt_add_request(void *arg) /* Basic preliminary test to create a request and let it loose! */ - request = mock_request(i915->engine[RCS0]->kernel_context, HZ / 10); + request = mock_request(rcs0(i915)->kernel_context, HZ / 10); if (!request) return -ENOMEM; @@ -76,7 +82,7 @@ static int igt_wait_request(void *arg) /* Submit a request, then wait upon it */ - request = mock_request(i915->engine[RCS0]->kernel_context, T); + request = mock_request(rcs0(i915)->kernel_context, T); if (!request) return -ENOMEM; @@ -145,7 +151,7 @@ static int igt_fence_wait(void *arg) /* Submit a request, treat it as a fence and wait upon it */ - request = mock_request(i915->engine[RCS0]->kernel_context, T); + request = mock_request(rcs0(i915)->kernel_context, T); if (!request) return -ENOMEM; @@ -420,7 +426,7 @@ static int mock_breadcrumbs_smoketest(void *arg) { struct drm_i915_private *i915 = arg; struct smoketest t = { - .engine = i915->engine[RCS0], + .engine = rcs0(i915), .ncontexts = 1024, .max_batch = 1024, .request_alloc = __mock_request_alloc @@ -1233,7 +1239,7 @@ static int live_parallel_engines(void *arg) struct igt_live_test t; unsigned int idx; - snprintf(name, sizeof(name), "%pS", fn); + snprintf(name, sizeof(name), "%ps", fn); err = igt_live_test_begin(&t, i915, __func__, name); if (err) break; diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 2a1d4ba1f9f3..6e80d99048e4 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -594,8 +594,11 @@ create_region_for_mapping(struct intel_memory_region *mr, u64 size, u32 type, void *addr; obj = i915_gem_object_create_region(mr, size, 0); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + if (PTR_ERR(obj) == -ENOSPC) /* Stolen memory */ + return ERR_PTR(-ENODEV); return obj; + } addr = i915_gem_object_pin_map(obj, type); if (IS_ERR(addr)) { diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 2b4407ac26de..9b105b811f1f 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -192,11 +192,11 @@ struct drm_i915_private *mock_gem_device(void) mkwrite_device_info(i915)->engine_mask = BIT(0); - i915->engine[RCS0] = mock_engine(i915, "mock", RCS0); - if (!i915->engine[RCS0]) + i915->gt.engine[RCS0] = mock_engine(i915, "mock", RCS0); + if (!i915->gt.engine[RCS0]) goto err_unlock; - if (mock_engine_init(i915->engine[RCS0])) + if (mock_engine_init(i915->gt.engine[RCS0])) goto err_context; __clear_bit(I915_WEDGED, &i915->gt.reset.flags); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index a8b20557539b..ff43a3d80410 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> +#include <linux/mutex.h> #include <linux/of_platform.h> #include <linux/of.h> #include <linux/of_gpio.h> @@ -169,6 +170,9 @@ struct mtk_hdmi { bool audio_enable; bool powered; bool enabled; + hdmi_codec_plugged_cb plugged_cb; + struct device *codec_dev; + struct mutex update_plugged_status_lock; }; static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) @@ -1194,13 +1198,26 @@ static void mtk_hdmi_clk_disable_audio(struct mtk_hdmi *hdmi) clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_SPDIF]); } +static enum drm_connector_status +mtk_hdmi_update_plugged_status(struct mtk_hdmi *hdmi) +{ + bool connected; + + mutex_lock(&hdmi->update_plugged_status_lock); + connected = mtk_cec_hpd_high(hdmi->cec_dev); + if (hdmi->plugged_cb && hdmi->codec_dev) + hdmi->plugged_cb(hdmi->codec_dev, connected); + mutex_unlock(&hdmi->update_plugged_status_lock); + + return connected ? + connector_status_connected : connector_status_disconnected; +} + static enum drm_connector_status hdmi_conn_detect(struct drm_connector *conn, bool force) { struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn); - - return mtk_cec_hpd_high(hdmi->cec_dev) ? - connector_status_connected : connector_status_disconnected; + return mtk_hdmi_update_plugged_status(hdmi); } static void hdmi_conn_destroy(struct drm_connector *conn) @@ -1657,20 +1674,39 @@ static int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, return 0; } +static int mtk_hdmi_audio_hook_plugged_cb(struct device *dev, void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + struct mtk_hdmi *hdmi = data; + + mutex_lock(&hdmi->update_plugged_status_lock); + hdmi->plugged_cb = fn; + hdmi->codec_dev = codec_dev; + mutex_unlock(&hdmi->update_plugged_status_lock); + + mtk_hdmi_update_plugged_status(hdmi); + + return 0; +} + static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = { .hw_params = mtk_hdmi_audio_hw_params, .audio_startup = mtk_hdmi_audio_startup, .audio_shutdown = mtk_hdmi_audio_shutdown, .digital_mute = mtk_hdmi_audio_digital_mute, .get_eld = mtk_hdmi_audio_get_eld, + .hook_plugged_cb = mtk_hdmi_audio_hook_plugged_cb, }; -static void mtk_hdmi_register_audio_driver(struct device *dev) +static int mtk_hdmi_register_audio_driver(struct device *dev) { + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); struct hdmi_codec_pdata codec_data = { .ops = &mtk_hdmi_audio_codec_ops, .max_i2s_channels = 2, .i2s = 1, + .data = hdmi, }; struct platform_device *pdev; @@ -1678,9 +1714,10 @@ static void mtk_hdmi_register_audio_driver(struct device *dev) PLATFORM_DEVID_AUTO, &codec_data, sizeof(codec_data)); if (IS_ERR(pdev)) - return; + return PTR_ERR(pdev); DRM_INFO("%s driver bound to HDMI\n", HDMI_CODEC_DRV_NAME); + return 0; } static int mtk_drm_hdmi_probe(struct platform_device *pdev) @@ -1706,6 +1743,7 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev) return ret; } + mutex_init(&hdmi->update_plugged_status_lock); platform_set_drvdata(pdev, hdmi); ret = mtk_hdmi_output_init(hdmi); @@ -1714,7 +1752,11 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev) return ret; } - mtk_hdmi_register_audio_driver(dev); + ret = mtk_hdmi_register_audio_driver(dev); + if (ret) { + dev_err(dev, "Failed to register audio driver: %d\n", ret); + return ret; + } hdmi->bridge.funcs = &mtk_hdmi_bridge_funcs; hdmi->bridge.of_node = pdev->dev.of_node; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 7d9e63e20ded..724024a2243a 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1446,18 +1446,31 @@ static const struct adreno_gpu_funcs funcs = { static void check_speed_bin(struct device *dev) { struct nvmem_cell *cell; - u32 bin, val; + u32 val; + + /* + * If the OPP table specifies a opp-supported-hw property then we have + * to set something with dev_pm_opp_set_supported_hw() or the table + * doesn't get populated so pick an arbitrary value that should + * ensure the default frequencies are selected but not conflict with any + * actual bins + */ + val = 0x80; cell = nvmem_cell_get(dev, "speed_bin"); - /* If a nvmem cell isn't defined, nothing to do */ - if (IS_ERR(cell)) - return; + if (!IS_ERR(cell)) { + void *buf = nvmem_cell_read(cell, NULL); + + if (!IS_ERR(buf)) { + u8 bin = *((u8 *) buf); - bin = *((u32 *) nvmem_cell_read(cell, NULL)); - nvmem_cell_put(cell); + val = (1 << bin); + kfree(buf); + } - val = (1 << bin); + nvmem_cell_put(cell); + } dev_pm_opp_set_supported_hw(dev, &val, 1); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 748cd379065f..c4e71abbdd53 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */ #include <linux/clk.h> +#include <linux/dma-mapping.h> #include <linux/interconnect.h> #include <linux/pm_domain.h> #include <linux/pm_opp.h> @@ -920,21 +921,10 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo) { - int count, i; - u64 iova; - if (IS_ERR_OR_NULL(bo)) return; - count = bo->size >> PAGE_SHIFT; - iova = bo->iova; - - for (i = 0; i < count; i++, iova += PAGE_SIZE) { - iommu_unmap(gmu->domain, iova, PAGE_SIZE); - __free_pages(bo->pages[i], 0); - } - - kfree(bo->pages); + dma_free_wc(gmu->dev, bo->size, bo->virt, bo->iova); kfree(bo); } @@ -942,7 +932,6 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, size_t size) { struct a6xx_gmu_bo *bo; - int ret, count, i; bo = kzalloc(sizeof(*bo), GFP_KERNEL); if (!bo) @@ -950,86 +939,14 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, bo->size = PAGE_ALIGN(size); - count = bo->size >> PAGE_SHIFT; + bo->virt = dma_alloc_wc(gmu->dev, bo->size, &bo->iova, GFP_KERNEL); - bo->pages = kcalloc(count, sizeof(struct page *), GFP_KERNEL); - if (!bo->pages) { + if (!bo->virt) { kfree(bo); return ERR_PTR(-ENOMEM); } - for (i = 0; i < count; i++) { - bo->pages[i] = alloc_page(GFP_KERNEL); - if (!bo->pages[i]) - goto err; - } - - bo->iova = gmu->uncached_iova_base; - - for (i = 0; i < count; i++) { - ret = iommu_map(gmu->domain, - bo->iova + (PAGE_SIZE * i), - page_to_phys(bo->pages[i]), PAGE_SIZE, - IOMMU_READ | IOMMU_WRITE); - - if (ret) { - DRM_DEV_ERROR(gmu->dev, "Unable to map GMU buffer object\n"); - - for (i = i - 1 ; i >= 0; i--) - iommu_unmap(gmu->domain, - bo->iova + (PAGE_SIZE * i), - PAGE_SIZE); - - goto err; - } - } - - bo->virt = vmap(bo->pages, count, VM_IOREMAP, - pgprot_writecombine(PAGE_KERNEL)); - if (!bo->virt) - goto err; - - /* Align future IOVA addresses on 1MB boundaries */ - gmu->uncached_iova_base += ALIGN(size, SZ_1M); - return bo; - -err: - for (i = 0; i < count; i++) { - if (bo->pages[i]) - __free_pages(bo->pages[i], 0); - } - - kfree(bo->pages); - kfree(bo); - - return ERR_PTR(-ENOMEM); -} - -static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) -{ - int ret; - - /* - * The GMU address space is hardcoded to treat the range - * 0x60000000 - 0x80000000 as un-cached memory. All buffers shared - * between the GMU and the CPU will live in this space - */ - gmu->uncached_iova_base = 0x60000000; - - - gmu->domain = iommu_domain_alloc(&platform_bus_type); - if (!gmu->domain) - return -ENODEV; - - ret = iommu_attach_device(gmu->domain, gmu->dev); - - if (ret) { - iommu_domain_free(gmu->domain); - gmu->domain = NULL; - } - - return ret; } /* Return the 'arc-level' for the given frequency */ @@ -1289,10 +1206,6 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) a6xx_gmu_memory_free(gmu, gmu->hfi); - iommu_detach_device(gmu->domain, gmu->dev); - - iommu_domain_free(gmu->domain); - free_irq(gmu->gmu_irq, gmu); free_irq(gmu->hfi_irq, gmu); @@ -1313,7 +1226,15 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) gmu->dev = &pdev->dev; - of_dma_configure(gmu->dev, node, true); + /* Pass force_dma false to require the DT to set the dma region */ + ret = of_dma_configure(gmu->dev, node, false); + if (ret) + return ret; + + /* Set the mask after the of_dma_configure() */ + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(31)); + if (ret) + return ret; /* Fow now, don't do anything fancy until we get our feet under us */ gmu->idle_level = GMU_IDLE_STATE_ACTIVE; @@ -1325,11 +1246,6 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) if (ret) goto err_put_device; - /* Set up the IOMMU context bank */ - ret = a6xx_gmu_memory_probe(gmu); - if (ret) - goto err_put_device; - /* Allocate memory for for the HFI queues */ gmu->hfi = a6xx_gmu_memory_alloc(gmu, SZ_16K); if (IS_ERR(gmu->hfi)) @@ -1375,11 +1291,6 @@ err_mmio: err_memory: a6xx_gmu_memory_free(gmu, gmu->hfi); - if (gmu->domain) { - iommu_detach_device(gmu->domain, gmu->dev); - - iommu_domain_free(gmu->domain); - } ret = -ENODEV; err_put_device: diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 2af91ed7ed0c..4af65a36d5ca 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -12,8 +12,7 @@ struct a6xx_gmu_bo { void *virt; size_t size; - u64 iova; - struct page **pages; + dma_addr_t iova; }; /* @@ -49,9 +48,6 @@ struct a6xx_gmu { int hfi_irq; int gmu_irq; - struct iommu_domain *domain; - u64 uncached_iova_base; - struct device *gxpd; int idle_level; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index e67c20c415af..24c974c293e5 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -379,7 +379,7 @@ static const struct a6xx_indexed_registers { }; static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { - "CP_MEMPOOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 7fd29829b2fa..1d5c43c22269 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -673,7 +673,7 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len) return NULL; for (i = 0; i < l; i++) - buf_itr += snprintf(buf + buf_itr, buffer_size - buf_itr, "%s", + buf_itr += scnprintf(buf + buf_itr, buffer_size - buf_itr, "%s", ascii85_encode(src[i], out)); return buf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 58d3400668f5..a1b79ee2bd9d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -164,7 +164,6 @@ enum dpu_enc_rc_states { * clks and resources after IDLE_TIMEOUT time. * @vsync_event_work: worker to handle vsync event for autorefresh * @topology: topology of the display - * @mode_set_complete: flag to indicate modeset completion * @idle_timeout: idle timeout duration in milliseconds */ struct dpu_encoder_virt { @@ -202,7 +201,6 @@ struct dpu_encoder_virt { struct delayed_work delayed_off_work; struct kthread_work vsync_event_work; struct msm_display_topology topology; - bool mode_set_complete; u32 idle_timeout; }; @@ -461,7 +459,7 @@ void dpu_encoder_helper_split_config( struct msm_display_info *disp_info; if (!phys_enc->hw_mdptop || !phys_enc->parent) { - DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0); + DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL); return; } @@ -562,12 +560,13 @@ static int dpu_encoder_virt_atomic_check( const struct drm_display_mode *mode; struct drm_display_mode *adj_mode; struct msm_display_topology topology; + struct dpu_global_state *global_state; int i = 0; int ret = 0; if (!drm_enc || !crtc_state || !conn_state) { DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n", - drm_enc != 0, crtc_state != 0, conn_state != 0); + drm_enc != NULL, crtc_state != NULL, conn_state != NULL); return -EINVAL; } @@ -578,6 +577,7 @@ static int dpu_encoder_virt_atomic_check( dpu_kms = to_dpu_kms(priv->kms); mode = &crtc_state->mode; adj_mode = &crtc_state->adjusted_mode; + global_state = dpu_kms_get_existing_global_state(dpu_kms); trace_dpu_enc_atomic_check(DRMID(drm_enc)); /* @@ -609,17 +609,15 @@ static int dpu_encoder_virt_atomic_check( topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode); - /* Reserve dynamic resources now. Indicating AtomicTest phase */ + /* Reserve dynamic resources now. */ if (!ret) { /* * Avoid reserving resources when mode set is pending. Topology * info may not be available to complete reservation. */ - if (drm_atomic_crtc_needs_modeset(crtc_state) - && dpu_enc->mode_set_complete) { - ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state, - topology, true); - dpu_enc->mode_set_complete = false; + if (drm_atomic_crtc_needs_modeset(crtc_state)) { + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + drm_enc, crtc_state, topology); } } @@ -956,12 +954,13 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, struct drm_connector *conn = NULL, *conn_iter; struct drm_crtc *drm_crtc; struct dpu_crtc_state *cstate; - struct dpu_rm_hw_iter hw_iter; + struct dpu_global_state *global_state; struct msm_display_topology topology; - struct dpu_hw_ctl *hw_ctl[MAX_CHANNELS_PER_ENC] = { NULL }; - struct dpu_hw_mixer *hw_lm[MAX_CHANNELS_PER_ENC] = { NULL }; - int num_lm = 0, num_ctl = 0; - int i, j, ret; + struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; + int num_lm, num_ctl, num_pp; + int i, j; if (!drm_enc) { DPU_ERROR("invalid encoder\n"); @@ -975,6 +974,12 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, dpu_kms = to_dpu_kms(priv->kms); connector_list = &dpu_kms->dev->mode_config.connector_list; + global_state = dpu_kms_get_existing_global_state(dpu_kms); + if (IS_ERR_OR_NULL(global_state)) { + DPU_ERROR("Failed to get global state"); + return; + } + trace_dpu_enc_mode_set(DRMID(drm_enc)); list_for_each_entry(conn_iter, connector_list, head) @@ -995,77 +1000,57 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode); - /* Reserve dynamic resources now. Indicating non-AtomicTest phase */ - ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_crtc->state, - topology, false); - if (ret) { - DPU_ERROR_ENC(dpu_enc, - "failed to reserve hw resources, %d\n", ret); - return; - } - - dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { - dpu_enc->hw_pp[i] = NULL; - if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter)) - break; - dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) hw_iter.hw; - } - - dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_CTL); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { - if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter)) - break; - hw_ctl[i] = (struct dpu_hw_ctl *)hw_iter.hw; - num_ctl++; - } + /* Query resource that have been reserved in atomic check step. */ + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp, + ARRAY_SIZE(hw_pp)); + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); + num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); - dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, DPU_HW_BLK_LM); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { - if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter)) - break; - hw_lm[i] = (struct dpu_hw_mixer *)hw_iter.hw; - num_lm++; - } + for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i]) + : NULL; cstate = to_dpu_crtc_state(drm_crtc->state); for (i = 0; i < num_lm; i++) { int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); - cstate->mixers[i].hw_lm = hw_lm[i]; - cstate->mixers[i].lm_ctl = hw_ctl[ctl_idx]; + cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); + cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); } cstate->num_mixers = num_lm; for (i = 0; i < dpu_enc->num_phys_encs; i++) { + int num_blk; + struct dpu_hw_blk *hw_blk[MAX_CHANNELS_PER_ENC]; struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; if (!dpu_enc->hw_pp[i]) { DPU_ERROR_ENC(dpu_enc, "no pp block assigned at idx: %d\n", i); - goto error; + return; } if (!hw_ctl[i]) { DPU_ERROR_ENC(dpu_enc, "no ctl block assigned at idx: %d\n", i); - goto error; + return; } phys->hw_pp = dpu_enc->hw_pp[i]; - phys->hw_ctl = hw_ctl[i]; + phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]); - dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id, - DPU_HW_BLK_INTF); - for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) { + num_blk = dpu_rm_get_assigned_resources(&dpu_kms->rm, + global_state, drm_enc->base.id, DPU_HW_BLK_INTF, + hw_blk, ARRAY_SIZE(hw_blk)); + for (j = 0; j < num_blk; j++) { struct dpu_hw_intf *hw_intf; - if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter)) - break; - - hw_intf = (struct dpu_hw_intf *)hw_iter.hw; + hw_intf = to_dpu_hw_intf(hw_blk[i]); if (hw_intf->idx == phys->intf_idx) phys->hw_intf = hw_intf; } @@ -1073,18 +1058,13 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, if (!phys->hw_intf) { DPU_ERROR_ENC(dpu_enc, "no intf block assigned at idx: %d\n", i); - goto error; + return; } phys->connector = conn->state->connector; if (phys->ops.mode_set) phys->ops.mode_set(phys, mode, adj_mode); } - - dpu_enc->mode_set_complete = true; - -error: - dpu_rm_release(&dpu_kms->rm, drm_enc); } static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc) @@ -1181,6 +1161,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) struct dpu_encoder_virt *dpu_enc = NULL; struct msm_drm_private *priv; struct dpu_kms *dpu_kms; + struct dpu_global_state *global_state; int i = 0; if (!drm_enc) { @@ -1199,6 +1180,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); + global_state = dpu_kms_get_existing_global_state(dpu_kms); trace_dpu_enc_disable(DRMID(drm_enc)); @@ -1228,7 +1210,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); - dpu_rm_release(&dpu_kms->rm, drm_enc); + dpu_rm_release(global_state, drm_enc); mutex_unlock(&dpu_enc->enc_lock); } @@ -1964,7 +1946,7 @@ static int dpu_encoder_virt_add_phys_encs( if (IS_ERR_OR_NULL(enc)) { DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n", PTR_ERR(enc)); - return enc == 0 ? -EINVAL : PTR_ERR(enc); + return enc == NULL ? -EINVAL : PTR_ERR(enc); } dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; @@ -1977,7 +1959,7 @@ static int dpu_encoder_virt_add_phys_encs( if (IS_ERR_OR_NULL(enc)) { DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n", PTR_ERR(enc)); - return enc == 0 ? -EINVAL : PTR_ERR(enc); + return enc == NULL ? -EINVAL : PTR_ERR(enc); } dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; @@ -2008,7 +1990,7 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, struct dpu_enc_phys_init_params phys_params; if (!dpu_enc) { - DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != 0); + DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != NULL); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index 39e1e280ba44..8493d68ad841 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -411,7 +411,7 @@ static void _dpu_encoder_phys_cmd_pingpong_config( to_dpu_encoder_phys_cmd(phys_enc); if (!phys_enc->hw_pp || !phys_enc->hw_ctl->ops.setup_intf_cfg) { - DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0); + DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != NULL); return; } @@ -440,7 +440,7 @@ static void dpu_encoder_phys_cmd_enable_helper( u32 flush_mask = 0; if (!phys_enc->hw_pp) { - DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0); + DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != NULL); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index c71c18de5966..b5a49050d131 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -239,7 +239,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine( struct dpu_hw_intf_cfg intf_cfg = { 0 }; if (!phys_enc->hw_ctl->ops.setup_intf_cfg) { - DPU_ERROR("invalid encoder %d\n", phys_enc != 0); + DPU_ERROR("invalid encoder %d\n", phys_enc != NULL); return; } @@ -559,7 +559,7 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc) if (!phys_enc->hw_intf) { DPU_ERROR("invalid hw_intf %d hw_ctl %d\n", - phys_enc->hw_intf != 0, phys_enc->hw_ctl != 0); + phys_enc->hw_intf != NULL, phys_enc->hw_ctl != NULL); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 85468981632d..0ead64d3f63d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -90,6 +90,16 @@ struct dpu_hw_intf { }; /** + * to_dpu_hw_intf - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_intf, base); +} + +/** * dpu_hw_intf_init(): Initializes the intf driver for the passed * interface idx. * @idx: interface index for which driver object is required diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h index 3d6f46b1db30..d73cb73e938b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h @@ -97,6 +97,16 @@ struct dpu_hw_pingpong { }; /** + * to_dpu_hw_pingpong - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_pingpong, base); +} + +/** * dpu_hw_pingpong_init - initializes the pingpong driver for the passed * pingpong idx. * @idx: Pingpong index for which driver object is required diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index cb08fafb1dc1..ce19f1d39367 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -138,16 +138,12 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data) { struct dpu_debugfs_regset32 *regset = s->private; struct dpu_kms *dpu_kms = regset->dpu_kms; - struct drm_device *dev; - struct msm_drm_private *priv; void __iomem *base; uint32_t i, addr; if (!dpu_kms->mmio) return 0; - dev = dpu_kms->dev; - priv = dev->dev_private; base = dpu_kms->mmio + regset->offset; /* insert padding spaces, if needed */ @@ -228,6 +224,85 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) } #endif +/* Global/shared object state funcs */ + +/* + * This is a helper that returns the private state currently in operation. + * Note that this would return the "old_state" if called in the atomic check + * path, and the "new_state" after the atomic swap has been done. + */ +struct dpu_global_state * +dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms) +{ + return to_dpu_global_state(dpu_kms->global_state.state); +} + +/* + * This acquires the modeset lock set aside for global state, creates + * a new duplicated private object state. + */ +struct dpu_global_state *dpu_kms_get_global_state(struct drm_atomic_state *s) +{ + struct msm_drm_private *priv = s->dev->dev_private; + struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); + struct drm_private_state *priv_state; + int ret; + + ret = drm_modeset_lock(&dpu_kms->global_state_lock, s->acquire_ctx); + if (ret) + return ERR_PTR(ret); + + priv_state = drm_atomic_get_private_obj_state(s, + &dpu_kms->global_state); + if (IS_ERR(priv_state)) + return ERR_CAST(priv_state); + + return to_dpu_global_state(priv_state); +} + +static struct drm_private_state * +dpu_kms_global_duplicate_state(struct drm_private_obj *obj) +{ + struct dpu_global_state *state; + + state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL); + if (!state) + return NULL; + + __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base); + + return &state->base; +} + +static void dpu_kms_global_destroy_state(struct drm_private_obj *obj, + struct drm_private_state *state) +{ + struct dpu_global_state *dpu_state = to_dpu_global_state(state); + + kfree(dpu_state); +} + +static const struct drm_private_state_funcs dpu_kms_global_state_funcs = { + .atomic_duplicate_state = dpu_kms_global_duplicate_state, + .atomic_destroy_state = dpu_kms_global_destroy_state, +}; + +static int dpu_kms_global_obj_init(struct dpu_kms *dpu_kms) +{ + struct dpu_global_state *state; + + drm_modeset_lock_init(&dpu_kms->global_state_lock); + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + drm_atomic_private_obj_init(dpu_kms->dev, &dpu_kms->global_state, + &state->base, + &dpu_kms_global_state_funcs); + return 0; +} + static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc) { return dpu_crtc_vblank(crtc, true); @@ -267,8 +342,6 @@ static ktime_t dpu_kms_vsync_time(struct msm_kms *kms, struct drm_crtc *crtc) static void dpu_kms_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state) { - struct dpu_kms *dpu_kms; - struct drm_device *dev; struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; struct drm_encoder *encoder; @@ -276,8 +349,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms, if (!kms) return; - dpu_kms = to_dpu_kms(kms); - dev = dpu_kms->dev; /* Call prepare_commit for all affected encoders */ for_each_new_crtc_in_state(state, crtc, crtc_state, i) { @@ -552,11 +623,8 @@ static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate, static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) { - struct drm_device *dev; int i; - dev = dpu_kms->dev; - if (dpu_kms->hw_intr) dpu_hw_intr_destroy(dpu_kms->hw_intr); dpu_kms->hw_intr = NULL; @@ -760,7 +828,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms) { struct dpu_kms *dpu_kms; struct drm_device *dev; - struct msm_drm_private *priv; int i, rc = -EINVAL; if (!kms) { @@ -770,7 +837,10 @@ static int dpu_kms_hw_init(struct msm_kms *kms) dpu_kms = to_dpu_kms(kms); dev = dpu_kms->dev; - priv = dev->dev_private; + + rc = dpu_kms_global_obj_init(dpu_kms); + if (rc) + return rc; atomic_set(&dpu_kms->bandwidth_ref, 0); @@ -1018,10 +1088,8 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev) int rc = -1; struct platform_device *pdev = to_platform_device(dev); struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); - struct drm_device *ddev; struct dss_module_power *mp = &dpu_kms->mp; - ddev = dpu_kms->dev; rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); if (rc) DPU_ERROR("clock disable failed rc:%d\n", rc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index c6169e7df19d..211f5de99a44 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -111,6 +111,13 @@ struct dpu_kms { struct dpu_core_perf perf; + /* + * Global private object state, Do not access directly, use + * dpu_kms_global_get_state() + */ + struct drm_modeset_lock global_state_lock; + struct drm_private_obj global_state; + struct dpu_rm rm; bool rm_init; @@ -139,6 +146,25 @@ struct vsync_info { #define to_dpu_kms(x) container_of(x, struct dpu_kms, base) +#define to_dpu_global_state(x) container_of(x, struct dpu_global_state, base) + +/* Global private object state for tracking resources that are shared across + * multiple kms objects (planes/crtcs/etc). + */ +struct dpu_global_state { + struct drm_private_state base; + + uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0]; + uint32_t mixer_to_enc_id[LM_MAX - LM_0]; + uint32_t ctl_to_enc_id[CTL_MAX - CTL_0]; + uint32_t intf_to_enc_id[INTF_MAX - INTF_0]; +}; + +struct dpu_global_state + *dpu_kms_get_existing_global_state(struct dpu_kms *dpu_kms); +struct dpu_global_state + *__must_check dpu_kms_get_global_state(struct drm_atomic_state *s); + /** * Debugfs functions - extra helper functions for debugfs support * diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 23f5b1433b35..9b62451b01ee 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -12,8 +12,12 @@ #include "dpu_encoder.h" #include "dpu_trace.h" -#define RESERVED_BY_OTHER(h, r) \ - ((h)->enc_id && (h)->enc_id != r) + +static inline bool reserved_by_other(uint32_t *res_map, int idx, + uint32_t enc_id) +{ + return res_map[idx] && res_map[idx] != enc_id; +} /** * struct dpu_rm_requirements - Reservation requirements parameter bundle @@ -25,171 +29,43 @@ struct dpu_rm_requirements { struct dpu_encoder_hw_resources hw_res; }; - -/** - * struct dpu_rm_hw_blk - hardware block tracking list member - * @list: List head for list of all hardware blocks tracking items - * @id: Hardware ID number, within it's own space, ie. LM_X - * @enc_id: Encoder id to which this blk is binded - * @hw: Pointer to the hardware register access object for this block - */ -struct dpu_rm_hw_blk { - struct list_head list; - uint32_t id; - uint32_t enc_id; - struct dpu_hw_blk *hw; -}; - -void dpu_rm_init_hw_iter( - struct dpu_rm_hw_iter *iter, - uint32_t enc_id, - enum dpu_hw_blk_type type) -{ - memset(iter, 0, sizeof(*iter)); - iter->enc_id = enc_id; - iter->type = type; -} - -static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i) +int dpu_rm_destroy(struct dpu_rm *rm) { - struct list_head *blk_list; - - if (!rm || !i || i->type >= DPU_HW_BLK_MAX) { - DPU_ERROR("invalid rm\n"); - return false; - } + int i; - i->hw = NULL; - blk_list = &rm->hw_blks[i->type]; + for (i = 0; i < ARRAY_SIZE(rm->pingpong_blks); i++) { + struct dpu_hw_pingpong *hw; - if (i->blk && (&i->blk->list == blk_list)) { - DPU_DEBUG("attempt resume iteration past last\n"); - return false; - } - - i->blk = list_prepare_entry(i->blk, blk_list, list); - - list_for_each_entry_continue(i->blk, blk_list, list) { - if (i->enc_id == i->blk->enc_id) { - i->hw = i->blk->hw; - DPU_DEBUG("found type %d id %d for enc %d\n", - i->type, i->blk->id, i->enc_id); - return true; + if (rm->pingpong_blks[i]) { + hw = to_dpu_hw_pingpong(rm->pingpong_blks[i]); + dpu_hw_pingpong_destroy(hw); } } + for (i = 0; i < ARRAY_SIZE(rm->mixer_blks); i++) { + struct dpu_hw_mixer *hw; - DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id); - - return false; -} - -bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i) -{ - bool ret; - - mutex_lock(&rm->rm_lock); - ret = _dpu_rm_get_hw_locked(rm, i); - mutex_unlock(&rm->rm_lock); - - return ret; -} - -static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw) -{ - switch (type) { - case DPU_HW_BLK_LM: - dpu_hw_lm_destroy(hw); - break; - case DPU_HW_BLK_CTL: - dpu_hw_ctl_destroy(hw); - break; - case DPU_HW_BLK_PINGPONG: - dpu_hw_pingpong_destroy(hw); - break; - case DPU_HW_BLK_INTF: - dpu_hw_intf_destroy(hw); - break; - case DPU_HW_BLK_SSPP: - /* SSPPs are not managed by the resource manager */ - case DPU_HW_BLK_TOP: - /* Top is a singleton, not managed in hw_blks list */ - case DPU_HW_BLK_MAX: - default: - DPU_ERROR("unsupported block type %d\n", type); - break; - } -} - -int dpu_rm_destroy(struct dpu_rm *rm) -{ - struct dpu_rm_hw_blk *hw_cur, *hw_nxt; - enum dpu_hw_blk_type type; - - for (type = 0; type < DPU_HW_BLK_MAX; type++) { - list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type], - list) { - list_del(&hw_cur->list); - _dpu_rm_hw_destroy(type, hw_cur->hw); - kfree(hw_cur); + if (rm->mixer_blks[i]) { + hw = to_dpu_hw_mixer(rm->mixer_blks[i]); + dpu_hw_lm_destroy(hw); } } + for (i = 0; i < ARRAY_SIZE(rm->ctl_blks); i++) { + struct dpu_hw_ctl *hw; - mutex_destroy(&rm->rm_lock); - - return 0; -} - -static int _dpu_rm_hw_blk_create( - struct dpu_rm *rm, - const struct dpu_mdss_cfg *cat, - void __iomem *mmio, - enum dpu_hw_blk_type type, - uint32_t id, - const void *hw_catalog_info) -{ - struct dpu_rm_hw_blk *blk; - void *hw; - - switch (type) { - case DPU_HW_BLK_LM: - hw = dpu_hw_lm_init(id, mmio, cat); - break; - case DPU_HW_BLK_CTL: - hw = dpu_hw_ctl_init(id, mmio, cat); - break; - case DPU_HW_BLK_PINGPONG: - hw = dpu_hw_pingpong_init(id, mmio, cat); - break; - case DPU_HW_BLK_INTF: - hw = dpu_hw_intf_init(id, mmio, cat); - break; - case DPU_HW_BLK_SSPP: - /* SSPPs are not managed by the resource manager */ - case DPU_HW_BLK_TOP: - /* Top is a singleton, not managed in hw_blks list */ - case DPU_HW_BLK_MAX: - default: - DPU_ERROR("unsupported block type %d\n", type); - return -EINVAL; - } - - if (IS_ERR_OR_NULL(hw)) { - DPU_ERROR("failed hw object creation: type %d, err %ld\n", - type, PTR_ERR(hw)); - return -EFAULT; + if (rm->ctl_blks[i]) { + hw = to_dpu_hw_ctl(rm->ctl_blks[i]); + dpu_hw_ctl_destroy(hw); + } } + for (i = 0; i < ARRAY_SIZE(rm->intf_blks); i++) { + struct dpu_hw_intf *hw; - blk = kzalloc(sizeof(*blk), GFP_KERNEL); - if (!blk) { - _dpu_rm_hw_destroy(type, hw); - return -ENOMEM; + if (rm->intf_blks[i]) { + hw = to_dpu_hw_intf(rm->intf_blks[i]); + dpu_hw_intf_destroy(hw); + } } - blk->id = id; - blk->hw = hw; - blk->enc_id = 0; - list_add_tail(&blk->list, &rm->hw_blks[type]); - return 0; } @@ -198,7 +74,6 @@ int dpu_rm_init(struct dpu_rm *rm, void __iomem *mmio) { int rc, i; - enum dpu_hw_blk_type type; if (!rm || !cat || !mmio) { DPU_ERROR("invalid kms\n"); @@ -208,13 +83,9 @@ int dpu_rm_init(struct dpu_rm *rm, /* Clear, setup lists */ memset(rm, 0, sizeof(*rm)); - mutex_init(&rm->rm_lock); - - for (type = 0; type < DPU_HW_BLK_MAX; type++) - INIT_LIST_HEAD(&rm->hw_blks[type]); - /* Interrogate HW catalog and create tracking items for hw blocks */ for (i = 0; i < cat->mixer_count; i++) { + struct dpu_hw_mixer *hw; const struct dpu_lm_cfg *lm = &cat->mixer[i]; if (lm->pingpong == PINGPONG_MAX) { @@ -222,12 +93,17 @@ int dpu_rm_init(struct dpu_rm *rm, continue; } - rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM, - cat->mixer[i].id, &cat->mixer[i]); - if (rc) { - DPU_ERROR("failed: lm hw not available\n"); + if (lm->id < LM_0 || lm->id >= LM_MAX) { + DPU_ERROR("skip mixer %d with invalid id\n", lm->id); + continue; + } + hw = dpu_hw_lm_init(lm->id, mmio, cat); + if (IS_ERR_OR_NULL(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed lm object creation: err %d\n", rc); goto fail; } + rm->mixer_blks[lm->id - LM_0] = &hw->base; if (!rm->lm_max_width) { rm->lm_max_width = lm->sblk->maxwidth; @@ -243,35 +119,59 @@ int dpu_rm_init(struct dpu_rm *rm, } for (i = 0; i < cat->pingpong_count; i++) { - rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG, - cat->pingpong[i].id, &cat->pingpong[i]); - if (rc) { - DPU_ERROR("failed: pp hw not available\n"); + struct dpu_hw_pingpong *hw; + const struct dpu_pingpong_cfg *pp = &cat->pingpong[i]; + + if (pp->id < PINGPONG_0 || pp->id >= PINGPONG_MAX) { + DPU_ERROR("skip pingpong %d with invalid id\n", pp->id); + continue; + } + hw = dpu_hw_pingpong_init(pp->id, mmio, cat); + if (IS_ERR_OR_NULL(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed pingpong object creation: err %d\n", + rc); goto fail; } + rm->pingpong_blks[pp->id - PINGPONG_0] = &hw->base; } for (i = 0; i < cat->intf_count; i++) { - if (cat->intf[i].type == INTF_NONE) { + struct dpu_hw_intf *hw; + const struct dpu_intf_cfg *intf = &cat->intf[i]; + + if (intf->type == INTF_NONE) { DPU_DEBUG("skip intf %d with type none\n", i); continue; } - - rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF, - cat->intf[i].id, &cat->intf[i]); - if (rc) { - DPU_ERROR("failed: intf hw not available\n"); + if (intf->id < INTF_0 || intf->id >= INTF_MAX) { + DPU_ERROR("skip intf %d with invalid id\n", intf->id); + continue; + } + hw = dpu_hw_intf_init(intf->id, mmio, cat); + if (IS_ERR_OR_NULL(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed intf object creation: err %d\n", rc); goto fail; } + rm->intf_blks[intf->id - INTF_0] = &hw->base; } for (i = 0; i < cat->ctl_count; i++) { - rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL, - cat->ctl[i].id, &cat->ctl[i]); - if (rc) { - DPU_ERROR("failed: ctl hw not available\n"); + struct dpu_hw_ctl *hw; + const struct dpu_ctl_cfg *ctl = &cat->ctl[i]; + + if (ctl->id < CTL_0 || ctl->id >= CTL_MAX) { + DPU_ERROR("skip ctl %d with invalid id\n", ctl->id); + continue; + } + hw = dpu_hw_ctl_init(ctl->id, mmio, cat); + if (IS_ERR_OR_NULL(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed ctl object creation: err %d\n", rc); goto fail; } + rm->ctl_blks[ctl->id - CTL_0] = &hw->base; } return 0; @@ -279,7 +179,7 @@ int dpu_rm_init(struct dpu_rm *rm, fail: dpu_rm_destroy(rm); - return rc; + return rc ? rc : -EFAULT; } static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top) @@ -288,85 +188,81 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top) } /** + * _dpu_rm_check_lm_peer - check if a mixer is a peer of the primary + * @rm: dpu resource manager handle + * @primary_idx: index of primary mixer in rm->mixer_blks[] + * @peer_idx: index of other mixer in rm->mixer_blks[] + * @Return: true if rm->mixer_blks[peer_idx] is a peer of + * rm->mixer_blks[primary_idx] + */ +static bool _dpu_rm_check_lm_peer(struct dpu_rm *rm, int primary_idx, + int peer_idx) +{ + const struct dpu_lm_cfg *prim_lm_cfg; + const struct dpu_lm_cfg *peer_cfg; + + prim_lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[primary_idx])->cap; + peer_cfg = to_dpu_hw_mixer(rm->mixer_blks[peer_idx])->cap; + + if (!test_bit(peer_cfg->id, &prim_lm_cfg->lm_pair_mask)) { + DPU_DEBUG("lm %d not peer of lm %d\n", peer_cfg->id, + peer_cfg->id); + return false; + } + return true; +} + +/** * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets * proposed use case requirements, incl. hardwired dependent blocks like * pingpong * @rm: dpu resource manager handle * @enc_id: encoder id requesting for allocation - * @reqs: proposed use case requirements - * @lm: proposed layer mixer, function checks if lm, and all other hardwired - * blocks connected to the lm (pp) is available and appropriate - * @pp: output parameter, pingpong block attached to the layer mixer. - * NULL if pp was not available, or not matching requirements. - * @primary_lm: if non-null, this function check if lm is compatible primary_lm - * as well as satisfying all other requirements + * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks + * if lm, and all other hardwired blocks connected to the lm (pp) is + * available and appropriate + * @pp_idx: output parameter, index of pingpong block attached to the layer + * mixer in rm->pongpong_blks[]. * @Return: true if lm matches all requirements, false otherwise */ -static bool _dpu_rm_check_lm_and_get_connected_blks( - struct dpu_rm *rm, - uint32_t enc_id, - struct dpu_rm_requirements *reqs, - struct dpu_rm_hw_blk *lm, - struct dpu_rm_hw_blk **pp, - struct dpu_rm_hw_blk *primary_lm) +static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t enc_id, int lm_idx, int *pp_idx) { - const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap; - struct dpu_rm_hw_iter iter; - - *pp = NULL; - - DPU_DEBUG("check lm %d pp %d\n", - lm_cfg->id, lm_cfg->pingpong); - - /* Check if this layer mixer is a peer of the proposed primary LM */ - if (primary_lm) { - const struct dpu_lm_cfg *prim_lm_cfg = - to_dpu_hw_mixer(primary_lm->hw)->cap; - - if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) { - DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id, - prim_lm_cfg->id); - return false; - } - } + const struct dpu_lm_cfg *lm_cfg; + int idx; /* Already reserved? */ - if (RESERVED_BY_OTHER(lm, enc_id)) { - DPU_DEBUG("lm %d already reserved\n", lm_cfg->id); + if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) { + DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0); return false; } - dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG); - while (_dpu_rm_get_hw_locked(rm, &iter)) { - if (iter.blk->id == lm_cfg->pingpong) { - *pp = iter.blk; - break; - } - } - - if (!*pp) { + lm_cfg = to_dpu_hw_mixer(rm->mixer_blks[lm_idx])->cap; + idx = lm_cfg->pingpong - PINGPONG_0; + if (idx < 0 || idx >= ARRAY_SIZE(rm->pingpong_blks)) { DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong); return false; } - if (RESERVED_BY_OTHER(*pp, enc_id)) { - DPU_DEBUG("lm %d pp %d already reserved\n", lm->id, - (*pp)->id); + if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) { + DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id, + lm_cfg->pingpong); return false; } - + *pp_idx = idx; return true; } -static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id, +static int _dpu_rm_reserve_lms(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t enc_id, struct dpu_rm_requirements *reqs) { - struct dpu_rm_hw_blk *lm[MAX_BLOCKS]; - struct dpu_rm_hw_blk *pp[MAX_BLOCKS]; - struct dpu_rm_hw_iter iter_i, iter_j; - int lm_count = 0; - int i, rc = 0; + int lm_idx[MAX_BLOCKS]; + int pp_idx[MAX_BLOCKS]; + int i, j, lm_count = 0; if (!reqs->topology.num_lm) { DPU_ERROR("invalid number of lm: %d\n", reqs->topology.num_lm); @@ -374,36 +270,40 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id, } /* Find a primary mixer */ - dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM); - while (lm_count != reqs->topology.num_lm && - _dpu_rm_get_hw_locked(rm, &iter_i)) { - memset(&lm, 0, sizeof(lm)); - memset(&pp, 0, sizeof(pp)); + for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) && + lm_count < reqs->topology.num_lm; i++) { + if (!rm->mixer_blks[i]) + continue; lm_count = 0; - lm[lm_count] = iter_i.blk; + lm_idx[lm_count] = i; - if (!_dpu_rm_check_lm_and_get_connected_blks( - rm, enc_id, reqs, lm[lm_count], - &pp[lm_count], NULL)) + if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, + enc_id, i, &pp_idx[lm_count])) { continue; + } ++lm_count; /* Valid primary mixer found, find matching peers */ - dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM); + for (j = i + 1; j < ARRAY_SIZE(rm->mixer_blks) && + lm_count < reqs->topology.num_lm; j++) { + if (!rm->mixer_blks[j]) + continue; - while (lm_count != reqs->topology.num_lm && - _dpu_rm_get_hw_locked(rm, &iter_j)) { - if (iter_i.blk == iter_j.blk) + if (!_dpu_rm_check_lm_peer(rm, i, j)) { + DPU_DEBUG("lm %d not peer of lm %d\n", LM_0 + j, + LM_0 + i); continue; + } - if (!_dpu_rm_check_lm_and_get_connected_blks( - rm, enc_id, reqs, iter_j.blk, - &pp[lm_count], iter_i.blk)) + if (!_dpu_rm_check_lm_and_get_connected_blks(rm, + global_state, enc_id, j, + &pp_idx[lm_count])) { continue; + } - lm[lm_count] = iter_j.blk; + lm_idx[lm_count] = j; ++lm_count; } } @@ -413,65 +313,65 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, uint32_t enc_id, return -ENAVAIL; } - for (i = 0; i < ARRAY_SIZE(lm); i++) { - if (!lm[i]) - break; + for (i = 0; i < lm_count; i++) { + global_state->mixer_to_enc_id[lm_idx[i]] = enc_id; + global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id; - lm[i]->enc_id = enc_id; - pp[i]->enc_id = enc_id; - - trace_dpu_rm_reserve_lms(lm[i]->id, enc_id, pp[i]->id); + trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id, + pp_idx[i] + PINGPONG_0); } - return rc; + return 0; } static int _dpu_rm_reserve_ctls( struct dpu_rm *rm, + struct dpu_global_state *global_state, uint32_t enc_id, const struct msm_display_topology *top) { - struct dpu_rm_hw_blk *ctls[MAX_BLOCKS]; - struct dpu_rm_hw_iter iter; - int i = 0, num_ctls = 0; - bool needs_split_display = false; - - memset(&ctls, 0, sizeof(ctls)); + int ctl_idx[MAX_BLOCKS]; + int i = 0, j, num_ctls; + bool needs_split_display; /* each hw_intf needs its own hw_ctrl to program its control path */ num_ctls = top->num_intf; needs_split_display = _dpu_rm_needs_split_display(top); - dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL); - while (_dpu_rm_get_hw_locked(rm, &iter)) { - const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw); - unsigned long features = ctl->caps->features; + for (j = 0; j < ARRAY_SIZE(rm->ctl_blks); j++) { + const struct dpu_hw_ctl *ctl; + unsigned long features; bool has_split_display; - if (RESERVED_BY_OTHER(iter.blk, enc_id)) + if (!rm->ctl_blks[j]) + continue; + if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id)) continue; + ctl = to_dpu_hw_ctl(rm->ctl_blks[j]); + features = ctl->caps->features; has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features; - DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features); + DPU_DEBUG("ctl %d caps 0x%lX\n", rm->ctl_blks[j]->id, features); if (needs_split_display != has_split_display) continue; - ctls[i] = iter.blk; - DPU_DEBUG("ctl %d match\n", iter.blk->id); + ctl_idx[i] = j; + DPU_DEBUG("ctl %d match\n", j + CTL_0); if (++i == num_ctls) break; + } if (i != num_ctls) return -ENAVAIL; - for (i = 0; i < ARRAY_SIZE(ctls) && i < num_ctls; i++) { - ctls[i]->enc_id = enc_id; - trace_dpu_rm_reserve_ctls(ctls[i]->id, enc_id); + for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) { + global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id; + trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id); } return 0; @@ -479,40 +379,34 @@ static int _dpu_rm_reserve_ctls( static int _dpu_rm_reserve_intf( struct dpu_rm *rm, + struct dpu_global_state *global_state, uint32_t enc_id, - uint32_t id, - enum dpu_hw_blk_type type) + uint32_t id) { - struct dpu_rm_hw_iter iter; - int ret = 0; - - /* Find the block entry in the rm, and note the reservation */ - dpu_rm_init_hw_iter(&iter, 0, type); - while (_dpu_rm_get_hw_locked(rm, &iter)) { - if (iter.blk->id != id) - continue; + int idx = id - INTF_0; - if (RESERVED_BY_OTHER(iter.blk, enc_id)) { - DPU_ERROR("type %d id %d already reserved\n", type, id); - return -ENAVAIL; - } - - iter.blk->enc_id = enc_id; - trace_dpu_rm_reserve_intf(iter.blk->id, enc_id); - break; + if (idx < 0 || idx >= ARRAY_SIZE(rm->intf_blks)) { + DPU_ERROR("invalid intf id: %d", id); + return -EINVAL; } - /* Shouldn't happen since intfs are fixed at probe */ - if (!iter.hw) { - DPU_ERROR("couldn't find type %d id %d\n", type, id); + if (!rm->intf_blks[idx]) { + DPU_ERROR("couldn't find intf id %d\n", id); return -EINVAL; } - return ret; + if (reserved_by_other(global_state->intf_to_enc_id, idx, enc_id)) { + DPU_ERROR("intf id %d already reserved\n", id); + return -ENAVAIL; + } + + global_state->intf_to_enc_id[idx] = enc_id; + return 0; } static int _dpu_rm_reserve_intf_related_hw( struct dpu_rm *rm, + struct dpu_global_state *global_state, uint32_t enc_id, struct dpu_encoder_hw_resources *hw_res) { @@ -523,8 +417,7 @@ static int _dpu_rm_reserve_intf_related_hw( if (hw_res->intfs[i] == INTF_MODE_NONE) continue; id = i + INTF_0; - ret = _dpu_rm_reserve_intf(rm, enc_id, id, - DPU_HW_BLK_INTF); + ret = _dpu_rm_reserve_intf(rm, global_state, enc_id, id); if (ret) return ret; } @@ -534,25 +427,27 @@ static int _dpu_rm_reserve_intf_related_hw( static int _dpu_rm_make_reservation( struct dpu_rm *rm, + struct dpu_global_state *global_state, struct drm_encoder *enc, - struct drm_crtc_state *crtc_state, struct dpu_rm_requirements *reqs) { int ret; - ret = _dpu_rm_reserve_lms(rm, enc->base.id, reqs); + ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, reqs); if (ret) { DPU_ERROR("unable to find appropriate mixers\n"); return ret; } - ret = _dpu_rm_reserve_ctls(rm, enc->base.id, &reqs->topology); + ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id, + &reqs->topology); if (ret) { DPU_ERROR("unable to find appropriate CTL\n"); return ret; } - ret = _dpu_rm_reserve_intf_related_hw(rm, enc->base.id, &reqs->hw_res); + ret = _dpu_rm_reserve_intf_related_hw(rm, global_state, enc->base.id, + &reqs->hw_res); if (ret) return ret; @@ -560,9 +455,7 @@ static int _dpu_rm_make_reservation( } static int _dpu_rm_populate_requirements( - struct dpu_rm *rm, struct drm_encoder *enc, - struct drm_crtc_state *crtc_state, struct dpu_rm_requirements *reqs, struct msm_display_topology req_topology) { @@ -577,37 +470,36 @@ static int _dpu_rm_populate_requirements( return 0; } -static void _dpu_rm_release_reservation(struct dpu_rm *rm, uint32_t enc_id) +static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, + uint32_t enc_id) { - struct dpu_rm_hw_blk *blk; - enum dpu_hw_blk_type type; - - for (type = 0; type < DPU_HW_BLK_MAX; type++) { - list_for_each_entry(blk, &rm->hw_blks[type], list) { - if (blk->enc_id == enc_id) { - blk->enc_id = 0; - DPU_DEBUG("rel enc %d %d %d\n", enc_id, - type, blk->id); - } - } + int i; + + for (i = 0; i < cnt; i++) { + if (res_mapping[i] == enc_id) + res_mapping[i] = 0; } } -void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc) +void dpu_rm_release(struct dpu_global_state *global_state, + struct drm_encoder *enc) { - mutex_lock(&rm->rm_lock); - - _dpu_rm_release_reservation(rm, enc->base.id); - - mutex_unlock(&rm->rm_lock); + _dpu_rm_clear_mapping(global_state->pingpong_to_enc_id, + ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id); + _dpu_rm_clear_mapping(global_state->mixer_to_enc_id, + ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id); + _dpu_rm_clear_mapping(global_state->ctl_to_enc_id, + ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id); + _dpu_rm_clear_mapping(global_state->intf_to_enc_id, + ARRAY_SIZE(global_state->intf_to_enc_id), enc->base.id); } int dpu_rm_reserve( struct dpu_rm *rm, + struct dpu_global_state *global_state, struct drm_encoder *enc, struct drm_crtc_state *crtc_state, - struct msm_display_topology topology, - bool test_only) + struct msm_display_topology topology) { struct dpu_rm_requirements reqs; int ret; @@ -616,31 +508,75 @@ int dpu_rm_reserve( if (!drm_atomic_crtc_needs_modeset(crtc_state)) return 0; - DRM_DEBUG_KMS("reserving hw for enc %d crtc %d test_only %d\n", - enc->base.id, crtc_state->crtc->base.id, test_only); + if (IS_ERR(global_state)) { + DPU_ERROR("failed to global state\n"); + return PTR_ERR(global_state); + } - mutex_lock(&rm->rm_lock); + DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n", + enc->base.id, crtc_state->crtc->base.id); - ret = _dpu_rm_populate_requirements(rm, enc, crtc_state, &reqs, - topology); + ret = _dpu_rm_populate_requirements(enc, &reqs, topology); if (ret) { DPU_ERROR("failed to populate hw requirements\n"); - goto end; + return ret; } - ret = _dpu_rm_make_reservation(rm, enc, crtc_state, &reqs); - if (ret) { + ret = _dpu_rm_make_reservation(rm, global_state, enc, &reqs); + if (ret) DPU_ERROR("failed to reserve hw resources: %d\n", ret); - _dpu_rm_release_reservation(rm, enc->base.id); - } else if (test_only) { - /* test_only: test the reservation and then undo */ - DPU_DEBUG("test_only: discard test [enc: %d]\n", - enc->base.id); - _dpu_rm_release_reservation(rm, enc->base.id); - } -end: - mutex_unlock(&rm->rm_lock); + return ret; } + +int dpu_rm_get_assigned_resources(struct dpu_rm *rm, + struct dpu_global_state *global_state, uint32_t enc_id, + enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size) +{ + struct dpu_hw_blk **hw_blks; + uint32_t *hw_to_enc_id; + int i, num_blks, max_blks; + + switch (type) { + case DPU_HW_BLK_PINGPONG: + hw_blks = rm->pingpong_blks; + hw_to_enc_id = global_state->pingpong_to_enc_id; + max_blks = ARRAY_SIZE(rm->pingpong_blks); + break; + case DPU_HW_BLK_LM: + hw_blks = rm->mixer_blks; + hw_to_enc_id = global_state->mixer_to_enc_id; + max_blks = ARRAY_SIZE(rm->mixer_blks); + break; + case DPU_HW_BLK_CTL: + hw_blks = rm->ctl_blks; + hw_to_enc_id = global_state->ctl_to_enc_id; + max_blks = ARRAY_SIZE(rm->ctl_blks); + break; + case DPU_HW_BLK_INTF: + hw_blks = rm->intf_blks; + hw_to_enc_id = global_state->intf_to_enc_id; + max_blks = ARRAY_SIZE(rm->intf_blks); + break; + default: + DPU_ERROR("blk type %d not managed by rm\n", type); + return 0; + } + + num_blks = 0; + for (i = 0; i < max_blks; i++) { + if (hw_to_enc_id[i] != enc_id) + continue; + + if (num_blks == blks_size) { + DPU_ERROR("More than %d resources assigned to enc %d\n", + blks_size, enc_id); + break; + } + blks[num_blks++] = hw_blks[i]; + } + + return num_blks; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index 9c580a017094..6d2b04f306f0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -11,37 +11,24 @@ #include "msm_kms.h" #include "dpu_hw_top.h" +struct dpu_global_state; + /** * struct dpu_rm - DPU dynamic hardware resource manager - * @hw_blks: array of lists of hardware resources present in the system, one - * list per type of hardware block + * @pingpong_blks: array of pingpong hardware resources + * @mixer_blks: array of layer mixer hardware resources + * @ctl_blks: array of ctl hardware resources + * @intf_blks: array of intf hardware resources * @lm_max_width: cached layer mixer maximum width * @rm_lock: resource manager mutex */ struct dpu_rm { - struct list_head hw_blks[DPU_HW_BLK_MAX]; - uint32_t lm_max_width; - struct mutex rm_lock; -}; + struct dpu_hw_blk *pingpong_blks[PINGPONG_MAX - PINGPONG_0]; + struct dpu_hw_blk *mixer_blks[LM_MAX - LM_0]; + struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0]; + struct dpu_hw_blk *intf_blks[INTF_MAX - INTF_0]; -/** - * struct dpu_rm_hw_blk - resource manager internal structure - * forward declaration for single iterator definition without void pointer - */ -struct dpu_rm_hw_blk; - -/** - * struct dpu_rm_hw_iter - iterator for use with dpu_rm - * @hw: dpu_hw object requested, or NULL on failure - * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator. - * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder - * @type: Hardware Block Type client wishes to search for. - */ -struct dpu_rm_hw_iter { - void *hw; - struct dpu_rm_hw_blk *blk; - uint32_t enc_id; - enum dpu_hw_blk_type type; + uint32_t lm_max_width; }; /** @@ -74,14 +61,13 @@ int dpu_rm_destroy(struct dpu_rm *rm); * @drm_enc: DRM Encoder handle * @crtc_state: Proposed Atomic DRM CRTC State handle * @topology: Pointer to topology info for the display - * @test_only: Atomic-Test phase, discard results (unless property overrides) * @Return: 0 on Success otherwise -ERROR */ int dpu_rm_reserve(struct dpu_rm *rm, + struct dpu_global_state *global_state, struct drm_encoder *drm_enc, struct drm_crtc_state *crtc_state, - struct msm_display_topology topology, - bool test_only); + struct msm_display_topology topology); /** * dpu_rm_reserve - Given the encoder for the display chain, release any @@ -90,31 +76,14 @@ int dpu_rm_reserve(struct dpu_rm *rm, * @enc: DRM Encoder handle * @Return: 0 on Success otherwise -ERROR */ -void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc); +void dpu_rm_release(struct dpu_global_state *global_state, + struct drm_encoder *enc); /** - * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list - * using dpu_rm_get_hw - * @iter: iter object to initialize - * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder - * @type: Hardware Block Type client wishes to search for. - */ -void dpu_rm_init_hw_iter( - struct dpu_rm_hw_iter *iter, - uint32_t enc_id, - enum dpu_hw_blk_type type); -/** - * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type - * Meant to do a single pass through the hardware list to iteratively - * retrieve hardware blocks of a given type for a given encoder. - * Initialize an iterator object. - * Set hw block type of interest. Set encoder id of interest, 0 for any. - * Function returns first hw of type for that encoder. - * Subsequent calls will return the next reserved hw of that type in-order. - * Iterator HW pointer will be null on failure to find hw. - * @rm: DPU Resource Manager handle - * @iter: iterator object - * @Return: true on match found, false on no match found + * Get hw resources of the given type that are assigned to this encoder. */ -bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter); +int dpu_rm_get_assigned_resources(struct dpu_rm *rm, + struct dpu_global_state *global_state, uint32_t enc_id, + enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); #endif /* __DPU_RM_H__ */ + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c index 93ab36bd8df3..5e8c3f3e6625 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c @@ -24,7 +24,7 @@ static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id) int rc; if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) { - DPU_ERROR("invalid arguments vbif %d\n", vbif != 0); + DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL); return -EINVAL; } @@ -106,7 +106,7 @@ static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif, u32 val; if (!vbif || !vbif->cap) { - DPU_ERROR("invalid arguments vbif %d\n", vbif != 0); + DPU_ERROR("invalid arguments vbif %d\n", vbif != NULL); return -EINVAL; } @@ -164,7 +164,7 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, if (!vbif || !mdp) { DPU_DEBUG("invalid arguments vbif %d mdp %d\n", - vbif != 0, mdp != 0); + vbif != NULL, mdp != NULL); return; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 41b461128bbc..c902c6503675 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -625,7 +625,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) if (config->platform.iommu) { iommu_dev = &pdev->dev; - if (!iommu_dev->iommu_fwspec) + if (!dev_iommu_fwspec_get(iommu_dev)) iommu_dev = iommu_dev->parent; aspace = msm_gem_address_space_create(iommu_dev, diff --git a/drivers/gpu/drm/msm/edp/edp.c b/drivers/gpu/drm/msm/edp/edp.c index a78d6077802b..106a67473af5 100644 --- a/drivers/gpu/drm/msm/edp/edp.c +++ b/drivers/gpu/drm/msm/edp/edp.c @@ -178,10 +178,6 @@ int msm_edp_modeset_init(struct msm_edp *edp, struct drm_device *dev, goto fail; } - ret = drm_bridge_attach(encoder, edp->bridge, NULL, 0); - if (ret) - goto fail; - priv->bridges[priv->num_bridges++] = edp->bridge; priv->connectors[priv->num_connectors++] = edp->connector; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 3a8646535c14..737453b6e596 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -327,10 +327,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - ret = drm_bridge_attach(encoder, hdmi->bridge, NULL, 0); - if (ret) - goto fail; - priv->bridges[priv->num_bridges++] = hdmi->bridge; priv->connectors[priv->num_connectors++] = hdmi->connector; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 2a82c23a6e4d..29295dee2a2e 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -444,8 +444,10 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) if (!dev->dma_parms) { dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; + if (!dev->dma_parms) { + ret = -ENOMEM; + goto err_msm_uninit; + } } dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 9e0953c2b7ce..30584eaf8cc8 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -157,7 +157,17 @@ struct msm_gem_submit { uint32_t handle; }; uint64_t iova; - } bos[0]; + } bos[]; }; +/* helper to determine of a buffer in submit should be dumped, used for both + * devcoredump and debugfs cmdstream dumping: + */ +static inline bool +should_dump(struct msm_gem_submit *submit, int idx) +{ + extern bool rd_full; + return rd_full || (submit->bos[idx].flags & MSM_SUBMIT_BO_DUMP); +} + #endif /* __MSM_GEM_H__ */ diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 18f3a5c53ffb..615c5cda5389 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -355,16 +355,34 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, state->cmd = kstrdup(cmd, GFP_KERNEL); if (submit) { - int i; - - state->bos = kcalloc(submit->nr_cmds, + int i, nr = 0; + + /* count # of buffers to dump: */ + for (i = 0; i < submit->nr_bos; i++) + if (should_dump(submit, i)) + nr++; + /* always dump cmd bo's, but don't double count them: */ + for (i = 0; i < submit->nr_cmds; i++) + if (!should_dump(submit, submit->cmd[i].idx)) + nr++; + + state->bos = kcalloc(nr, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); + for (i = 0; i < submit->nr_bos; i++) { + if (should_dump(submit, i)) { + msm_gpu_crashstate_get_bo(state, submit->bos[i].obj, + submit->bos[i].iova, submit->bos[i].flags); + } + } + for (i = 0; state->bos && i < submit->nr_cmds; i++) { int idx = submit->cmd[i].idx; - msm_gpu_crashstate_get_bo(state, submit->bos[idx].obj, - submit->bos[idx].iova, submit->bos[idx].flags); + if (!should_dump(submit, submit->cmd[i].idx)) { + msm_gpu_crashstate_get_bo(state, submit->bos[idx].obj, + submit->bos[idx].iova, submit->bos[idx].flags); + } } } diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index af7ceb246c7c..732f65df5c4f 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -43,7 +43,7 @@ #include "msm_gpu.h" #include "msm_gem.h" -static bool rd_full = false; +bool rd_full = false; MODULE_PARM_DESC(rd_full, "If true, $debugfs/.../rd will snapshot all buffer contents"); module_param_named(rd_full, rd_full, bool, 0600); @@ -336,12 +336,6 @@ static void snapshot_buf(struct msm_rd_state *rd, msm_gem_put_vaddr(&obj->base); } -static bool -should_dump(struct msm_gem_submit *submit, int idx) -{ - return rd_full || (submit->bos[idx].flags & MSM_SUBMIT_BO_DUMP); -} - /* called under struct_mutex */ void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit, const char *fmt, ...) diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c index e8eef88a8382..ffdd447d8706 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/dac.c +++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c @@ -35,7 +35,8 @@ #include <subdev/bios/gpio.h> #include <subdev/gpio.h> -#include <subdev/timer.h> + +#include <nvif/timer.h> int nv04_dac_output_offset(struct drm_encoder *encoder) { diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index 3fdfafa8b0ad..b674d68ef28a 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -26,6 +26,7 @@ #include "hw.h" #include <subdev/bios/pll.h> +#include <nvif/timer.h> #define CHIPSET_NFORCE 0x01a0 #define CHIPSET_NFORCE2 0x01f0 diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c index 00a85f1e1a4a..ee782151d332 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c @@ -23,6 +23,7 @@ #include <nvif/cl507c.h> #include <nvif/event.h> +#include <nvif/timer.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fourcc.h> diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index e7fcfa6e6467..c5152c39c684 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -23,6 +23,7 @@ #include "head.h" #include <nvif/cl507d.h> +#include <nvif/timer.h> #include "nouveau_bo.h" diff --git a/drivers/gpu/drm/nouveau/dispnv50/corec37d.c b/drivers/gpu/drm/nouveau/dispnv50/corec37d.c index 3b36dc8d36b2..c03cb987856b 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/corec37d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/corec37d.c @@ -24,6 +24,8 @@ #include <nouveau_bo.h> +#include <nvif/timer.h> + void corec37d_wndw_owner(struct nv50_core *core) { diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c index 397143b639c6..8c5cf096f69b 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c @@ -24,21 +24,36 @@ #include "head.h" #include <nvif/cl507a.h> +#include <nvif/timer.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_plane_helper.h> +bool +curs507a_space(struct nv50_wndw *wndw) +{ + nvif_msec(&nouveau_drm(wndw->plane.dev)->client.device, 2, + if (nvif_rd32(&wndw->wimm.base.user, 0x0008) >= 4) + return true; + ); + WARN_ON(1); + return false; +} + static void curs507a_update(struct nv50_wndw *wndw, u32 *interlock) { - nvif_wr32(&wndw->wimm.base.user, 0x0080, 0x00000000); + if (curs507a_space(wndw)) + nvif_wr32(&wndw->wimm.base.user, 0x0080, 0x00000000); } static void curs507a_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) { - nvif_wr32(&wndw->wimm.base.user, 0x0084, asyw->point.y << 16 | - asyw->point.x); + if (curs507a_space(wndw)) { + nvif_wr32(&wndw->wimm.base.user, 0x0084, asyw->point.y << 16 | + asyw->point.x); + } } const struct nv50_wimm_func diff --git a/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c b/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c index 23fb29d41efe..96dff4f09f57 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/cursc37a.c @@ -25,14 +25,17 @@ static void cursc37a_update(struct nv50_wndw *wndw, u32 *interlock) { - nvif_wr32(&wndw->wimm.base.user, 0x0200, 0x00000001); + if (curs507a_space(wndw)) + nvif_wr32(&wndw->wimm.base.user, 0x0200, 0x00000001); } static void cursc37a_point(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) { - nvif_wr32(&wndw->wimm.base.user, 0x0208, asyw->point.y << 16 | - asyw->point.x); + if (curs507a_space(wndw)) { + nvif_wr32(&wndw->wimm.base.user, 0x0208, asyw->point.y << 16 | + asyw->point.x); + } } static const struct nv50_wimm_func diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 4d1c58468dbc..6be9df1820c5 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -45,6 +45,7 @@ #include <nvif/cl5070.h> #include <nvif/cl507d.h> #include <nvif/event.h> +#include <nvif/timer.h> #include "nouveau_drv.h" #include "nouveau_dma.h" diff --git a/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c b/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c index 2e68fc736fe1..4f7ce57f2036 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/ovly827e.c @@ -24,6 +24,8 @@ #include <nouveau_bo.h> +#include <nvif/timer.h> + static void ovly827e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) { diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h index caf397475918..a7412b9d3a98 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h @@ -97,6 +97,7 @@ struct nv50_wimm_func { }; extern const struct nv50_wimm_func curs507a; +bool curs507a_space(struct nv50_wndw *); int wndwc37e_new(struct nouveau_drm *, enum drm_plane_type, int, s32, struct nv50_wndw **); diff --git a/drivers/gpu/drm/nouveau/include/nvif/device.h b/drivers/gpu/drm/nouveau/include/nvif/device.h index 25d969dcf67d..c2a572c67a76 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/device.h +++ b/drivers/gpu/drm/nouveau/include/nvif/device.h @@ -23,27 +23,6 @@ int nvif_device_init(struct nvif_object *, u32 handle, s32 oclass, void *, u32, void nvif_device_fini(struct nvif_device *); u64 nvif_device_time(struct nvif_device *); -/* Delay based on GPU time (ie. PTIMER). - * - * Will return -ETIMEDOUT unless the loop was terminated with 'break', - * where it will return the number of nanoseconds taken instead. - */ -#define nvif_nsec(d,n,cond...) ({ \ - struct nvif_device *_device = (d); \ - u64 _nsecs = (n), _time0 = nvif_device_time(_device); \ - s64 _taken = 0; \ - \ - do { \ - cond \ - } while (_taken = nvif_device_time(_device) - _time0, _taken < _nsecs);\ - \ - if (_taken >= _nsecs) \ - _taken = -ETIMEDOUT; \ - _taken; \ -}) -#define nvif_usec(d,u,cond...) nvif_nsec((d), (u) * 1000, ##cond) -#define nvif_msec(d,m,cond...) nvif_usec((d), (m) * 1000, ##cond) - /*XXX*/ #include <subdev/bios.h> #include <subdev/fb.h> diff --git a/drivers/gpu/drm/nouveau/include/nvif/timer.h b/drivers/gpu/drm/nouveau/include/nvif/timer.h new file mode 100644 index 000000000000..57587a985c4b --- /dev/null +++ b/drivers/gpu/drm/nouveau/include/nvif/timer.h @@ -0,0 +1,35 @@ +#ifndef __NVIF_TIMER_H__ +#define __NVIF_TIMER_H__ +#include <nvif/os.h> + +struct nvif_timer_wait { + struct nvif_device *device; + u64 limit; + u64 time0; + u64 time1; + int reads; +}; + +void nvif_timer_wait_init(struct nvif_device *, u64 nsec, + struct nvif_timer_wait *); +s64 nvif_timer_wait_test(struct nvif_timer_wait *); + +/* Delay based on GPU time (ie. PTIMER). + * + * Will return -ETIMEDOUT unless the loop was terminated with 'break', + * where it will return the number of nanoseconds taken instead. + */ +#define nvif_nsec(d,n,cond...) ({ \ + struct nvif_timer_wait _wait; \ + s64 _taken = 0; \ + \ + nvif_timer_wait_init((d), (n), &_wait); \ + do { \ + cond \ + } while ((_taken = nvif_timer_wait_test(&_wait)) >= 0); \ + \ + _taken; \ +}) +#define nvif_usec(d,u,cond...) nvif_nsec((d), (u) * 1000, ##cond) +#define nvif_msec(d,m,cond...) nvif_usec((d), (m) * 1000, ##cond) +#endif diff --git a/drivers/gpu/drm/nouveau/include/nvif/user.h b/drivers/gpu/drm/nouveau/include/nvif/user.h index 03c11826b693..6825574d93c2 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/user.h +++ b/drivers/gpu/drm/nouveau/include/nvif/user.h @@ -10,6 +10,7 @@ struct nvif_user { struct nvif_user_func { void (*doorbell)(struct nvif_user *, u32 token); + u64 (*time)(struct nvif_user *); }; int nvif_user_init(struct nvif_device *); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2b4b21b02e40..c40f127de3d0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1494,8 +1494,13 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg) ret = nvif_object_map_handle(&mem->mem.object, &args, argc, &handle, &length); - if (ret != 1) - return ret ? ret : -EINVAL; + if (ret != 1) { + if (WARN_ON(ret == 0)) + return -EINVAL; + if (ret == -ENOSPC) + return -EAGAIN; + return ret; + } reg->bus.base = 0; reg->bus.offset = handle; diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 0ad5d87b5a8e..ad89e09a0be3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -28,6 +28,7 @@ #include <nvif/class.h> #include <nvif/object.h> +#include <nvif/if000c.h> #include <nvif/if500b.h> #include <nvif/if900b.h> @@ -176,6 +177,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) .end = vmf->address + PAGE_SIZE, .src = &src, .dst = &dst, + .src_owner = drm->dev, }; /* @@ -526,6 +528,7 @@ nouveau_dmem_init(struct nouveau_drm *drm) drm->dmem->pagemap.type = MEMORY_DEVICE_PRIVATE; drm->dmem->pagemap.res = *res; drm->dmem->pagemap.ops = &nouveau_dmem_pagemap_ops; + drm->dmem->pagemap.owner = drm->dev; if (IS_ERR(devm_memremap_pages(device, &drm->dmem->pagemap))) goto out_free; @@ -669,12 +672,6 @@ out: return ret; } -static inline bool -nouveau_dmem_page(struct nouveau_drm *drm, struct page *page) -{ - return is_device_private_page(page) && drm->dmem == page_to_dmem(page); -} - void nouveau_dmem_convert_pfn(struct nouveau_drm *drm, struct hmm_range *range) @@ -690,18 +687,12 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, if (page == NULL) continue; - if (!(range->pfns[i] & range->flags[HMM_PFN_DEVICE_PRIVATE])) { + if (!is_device_private_page(page)) continue; - } - - if (!nouveau_dmem_page(drm, page)) { - WARN(1, "Some unknown device memory !\n"); - range->pfns[i] = 0; - continue; - } addr = nouveau_dmem_page_addr(page); range->pfns[i] &= ((1UL << range->pfn_shift) - 1); range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift; + range->pfns[i] |= NVIF_VMM_PFNMAP_V0_VRAM; } } diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 6b1629c14dd7..ca4087f5a15b 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..645fedd77e21 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); @@ -367,7 +373,6 @@ static const u64 nouveau_svm_pfn_flags[HMM_PFN_FLAG_MAX] = { [HMM_PFN_VALID ] = NVIF_VMM_PFNMAP_V0_V, [HMM_PFN_WRITE ] = NVIF_VMM_PFNMAP_V0_W, - [HMM_PFN_DEVICE_PRIVATE] = NVIF_VMM_PFNMAP_V0_VRAM, }; static const u64 @@ -541,7 +546,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, range.default_flags = 0; range.pfn_flags_mask = -1UL; down_read(&mm->mmap_sem); - ret = hmm_range_fault(&range, 0); + ret = hmm_range_fault(&range); up_read(&mm->mmap_sem); if (ret <= 0) { if (ret == 0 || ret == -EBUSY) @@ -657,9 +662,6 @@ nouveau_svm_fault(struct nvif_notify *notify) limit = start + (ARRAY_SIZE(args.phys) << PAGE_SHIFT); if (start < svmm->unmanaged.limit) limit = min_t(u64, limit, svmm->unmanaged.start); - else - if (limit > svmm->unmanaged.start) - start = max_t(u64, start, svmm->unmanaged.limit); SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit); mm = svmm->notifier.mm; diff --git a/drivers/gpu/drm/nouveau/nvif/Kbuild b/drivers/gpu/drm/nouveau/nvif/Kbuild index 50d583d63807..f194d354c1f5 100644 --- a/drivers/gpu/drm/nouveau/nvif/Kbuild +++ b/drivers/gpu/drm/nouveau/nvif/Kbuild @@ -8,6 +8,7 @@ nvif-y += nvif/fifo.o nvif-y += nvif/mem.o nvif-y += nvif/mmu.o nvif-y += nvif/notify.o +nvif-y += nvif/timer.o nvif-y += nvif/vmm.o # Usermode classes diff --git a/drivers/gpu/drm/nouveau/nvif/device.c b/drivers/gpu/drm/nouveau/nvif/device.c index 1ec101ba3b42..0e92db44bbc8 100644 --- a/drivers/gpu/drm/nouveau/nvif/device.c +++ b/drivers/gpu/drm/nouveau/nvif/device.c @@ -27,11 +27,15 @@ u64 nvif_device_time(struct nvif_device *device) { - struct nv_device_time_v0 args = {}; - int ret = nvif_object_mthd(&device->object, NV_DEVICE_V0_TIME, - &args, sizeof(args)); - WARN_ON_ONCE(ret != 0); - return args.time; + if (!device->user.func) { + struct nv_device_time_v0 args = {}; + int ret = nvif_object_mthd(&device->object, NV_DEVICE_V0_TIME, + &args, sizeof(args)); + WARN_ON_ONCE(ret != 0); + return args.time; + } + + return device->user.func->time(&device->user); } void diff --git a/drivers/gpu/drm/nouveau/nvif/timer.c b/drivers/gpu/drm/nouveau/nvif/timer.c new file mode 100644 index 000000000000..602c1a258d10 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvif/timer.c @@ -0,0 +1,56 @@ +/* + * Copyright 2020 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#include <nvif/timer.h> +#include <nvif/device.h> + +s64 +nvif_timer_wait_test(struct nvif_timer_wait *wait) +{ + u64 time = nvif_device_time(wait->device); + + if (wait->reads == 0) { + wait->time0 = time; + wait->time1 = time; + } + + if (wait->time1 == time) { + if (WARN_ON(wait->reads++ == 16)) + return -ETIMEDOUT; + } else { + wait->time1 = time; + wait->reads = 1; + } + + if (wait->time1 - wait->time0 > wait->limit) + return -ETIMEDOUT; + + return wait->time1 - wait->time0; +} + +void +nvif_timer_wait_init(struct nvif_device *device, u64 nsec, + struct nvif_timer_wait *wait) +{ + wait->device = device; + wait->limit = nsec; + wait->reads = 0; +} diff --git a/drivers/gpu/drm/nouveau/nvif/userc361.c b/drivers/gpu/drm/nouveau/nvif/userc361.c index 19f9958e7e01..1116f871b272 100644 --- a/drivers/gpu/drm/nouveau/nvif/userc361.c +++ b/drivers/gpu/drm/nouveau/nvif/userc361.c @@ -21,6 +21,19 @@ */ #include <nvif/user.h> +static u64 +nvif_userc361_time(struct nvif_user *user) +{ + u32 hi, lo; + + do { + hi = nvif_rd32(&user->object, 0x084); + lo = nvif_rd32(&user->object, 0x080); + } while (hi != nvif_rd32(&user->object, 0x084)); + + return ((u64)hi << 32 | lo); +} + static void nvif_userc361_doorbell(struct nvif_user *user, u32 token) { @@ -30,4 +43,5 @@ nvif_userc361_doorbell(struct nvif_user *user, u32 token) const struct nvif_user_func nvif_userc361 = { .doorbell = nvif_userc361_doorbell, + .time = nvif_userc361_time, }; 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/nouveau/nvkm/subdev/bios/shadowpci.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c index 9b91da09dc5f..8d9812a51ef6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c @@ -101,9 +101,13 @@ platform_init(struct nvkm_bios *bios, const char *name) else return ERR_PTR(-ENODEV); + if (!pdev->rom || pdev->romlen == 0) + return ERR_PTR(-ENODEV); + if ((priv = kmalloc(sizeof(*priv), GFP_KERNEL))) { + priv->size = pdev->romlen; if (ret = -ENODEV, - (priv->rom = pci_platform_rom(pdev, &priv->size))) + (priv->rom = ioremap(pdev->rom, pdev->romlen))) return priv; kfree(priv); } @@ -111,11 +115,20 @@ platform_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(ret); } +static void +platform_fini(void *data) +{ + struct priv *priv = data; + + iounmap(priv->rom); + kfree(priv); +} + const struct nvbios_source nvbios_platform = { .name = "PLATFORM", .init = platform_init, - .fini = (void(*)(void *))kfree, + .fini = platform_fini, .read = pcirom_read, .rw = true, }; diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index b76fc2b56227..4d5739fa4a5d 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1348,9 +1348,15 @@ static int dss_component_compare(struct device *dev, void *data) return dev == child; } +struct dss_component_match_data { + struct device *dev; + struct component_match **match; +}; + static int dss_add_child_component(struct device *dev, void *data) { - struct component_match **match = data; + struct dss_component_match_data *cmatch = data; + struct component_match **match = cmatch->match; /* * HACK @@ -1361,7 +1367,17 @@ static int dss_add_child_component(struct device *dev, void *data) if (strstr(dev_name(dev), "rfbi")) return 0; - component_match_add(dev->parent, match, dss_component_compare, dev); + /* + * Handle possible interconnect target modules defined within the DSS. + * The DSS components can be children of an interconnect target module + * after the device tree has been updated for the module data. + * See also omapdss_boot_init() for compatible fixup. + */ + if (strstr(dev_name(dev), "target-module")) + return device_for_each_child(dev, cmatch, + dss_add_child_component); + + component_match_add(cmatch->dev, match, dss_component_compare, dev); return 0; } @@ -1404,6 +1420,7 @@ static int dss_probe_hardware(struct dss_device *dss) static int dss_probe(struct platform_device *pdev) { const struct soc_device_attribute *soc; + struct dss_component_match_data cmatch; struct component_match *match = NULL; struct resource *dss_mem; struct dss_device *dss; @@ -1481,7 +1498,9 @@ static int dss_probe(struct platform_device *pdev) omapdss_gather_components(&pdev->dev); - device_for_each_child(&pdev->dev, &match, dss_add_child_component); + cmatch.dev = &pdev->dev; + cmatch.match = &match; + device_for_each_child(&pdev->dev, &cmatch, dss_add_child_component); r = component_master_add_with_match(&pdev->dev, &dss_component_ops, match); if (r) diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c index 00372f4ce711..72a7da7bfff1 100644 --- a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c +++ b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c @@ -178,9 +178,24 @@ static const struct of_device_id omapdss_of_fixups_whitelist[] __initconst = { {}, }; +static void __init omapdss_find_children(struct device_node *np) +{ + struct device_node *child; + + for_each_available_child_of_node(np, child) { + if (!of_find_property(child, "compatible", NULL)) + continue; + + omapdss_walk_device(child, true); + + if (of_device_is_compatible(child, "ti,sysc")) + omapdss_find_children(child); + } +} + static int __init omapdss_boot_init(void) { - struct device_node *dss, *child; + struct device_node *dss; INIT_LIST_HEAD(&dss_conv_list); @@ -190,13 +205,7 @@ static int __init omapdss_boot_init(void) goto put_node; omapdss_walk_device(dss, true); - - for_each_available_child_of_node(dss, child) { - if (!of_find_property(child, "compatible", NULL)) - continue; - - omapdss_walk_device(child, true); - } + omapdss_find_children(dss); while (!list_empty(&dss_conv_list)) { struct dss_conv_node *n; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 44a1f5dfb571..003b54ea90d5 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -361,7 +361,6 @@ static int panel_dpi_probe(struct device *dev, struct panel_desc *desc; unsigned int bus_flags; struct videomode vm; - const char *mapping; int ret; np = dev->of_node; @@ -386,16 +385,6 @@ static int panel_dpi_probe(struct device *dev, of_property_read_u32(np, "width-mm", &desc->size.width); of_property_read_u32(np, "height-mm", &desc->size.height); - of_property_read_string(np, "data-mapping", &mapping); - if (!strcmp(mapping, "rgb24")) - desc->bus_format = MEDIA_BUS_FMT_RGB888_1X24; - else if (!strcmp(mapping, "rgb565")) - desc->bus_format = MEDIA_BUS_FMT_RGB565_1X16; - else if (!strcmp(mapping, "bgr666")) - desc->bus_format = MEDIA_BUS_FMT_RGB666_1X18; - else if (!strcmp(mapping, "lvds666")) - desc->bus_format = MEDIA_BUS_FMT_RGB666_1X24_CPADHI; - /* Extract bus_flags from display_timing */ bus_flags = 0; vm.flags = timing->flags; diff --git a/drivers/gpu/drm/radeon/.gitignore b/drivers/gpu/drm/radeon/.gitignore index 403eb3a5891f..9c1a94153983 100644 --- a/drivers/gpu/drm/radeon/.gitignore +++ b/drivers/gpu/drm/radeon/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only mkregtable *_reg_safe.h diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index c42f73fad3e3..bb29cf02974d 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -108,25 +108,33 @@ static bool radeon_read_bios(struct radeon_device *rdev) static bool radeon_read_platform_bios(struct radeon_device *rdev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = rdev->pdev->rom; + size_t romlen = rdev->pdev->romlen; + void __iomem *bios; rdev->bios = NULL; - bios = pci_platform_rom(rdev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - } - if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + rdev->bios = kzalloc(romlen, GFP_KERNEL); + if (!rdev->bios) return false; - } - rdev->bios = kmemdup(bios, size, GFP_KERNEL); - if (rdev->bios == NULL) { - return false; - } + + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; + + memcpy_fromio(rdev->bios, bios, romlen); + iounmap(bios); + + if (rdev->bios[0] != 0x55 || rdev->bios[1] != 0xaa) + goto free_bios; return true; +free_bios: + kfree(rdev->bios); + return false; } #ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index badf1b6d1549..5d50c9edbe80 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -523,7 +523,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm) r = -ENOMEM; nents = dma_map_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction); - if (nents != ttm->sg->nents) + if (nents == 0) goto release_sg; drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages, diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 05e8b4d0af3f..2cb85dbe728f 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2979,7 +2979,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, if (rdev->family == CHIP_HAINAN) { if ((rdev->pdev->revision == 0x81) || - (rdev->pdev->revision == 0x83) || (rdev->pdev->revision == 0xC3) || (rdev->pdev->device == 0x6664) || (rdev->pdev->device == 0x6665) || diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 848522797314..ade2327a10e2 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -322,15 +322,9 @@ static int rockchip_dp_bind(struct device *dev, struct device *master, void *data) { struct rockchip_dp_device *dp = dev_get_drvdata(dev); - const struct rockchip_dp_chip_data *dp_data; struct drm_device *drm_dev = data; int ret; - dp_data = of_device_get_match_data(dev); - if (!dp_data) - return -ENODEV; - - dp->data = dp_data; dp->drm_dev = drm_dev; ret = rockchip_dp_drm_create_encoder(dp); @@ -341,16 +335,9 @@ static int rockchip_dp_bind(struct device *dev, struct device *master, dp->plat_data.encoder = &dp->encoder; - dp->plat_data.dev_type = dp->data->chip_type; - dp->plat_data.power_on_start = rockchip_dp_poweron_start; - dp->plat_data.power_off = rockchip_dp_powerdown; - dp->plat_data.get_modes = rockchip_dp_get_modes; - - dp->adp = analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data); - if (IS_ERR(dp->adp)) { - ret = PTR_ERR(dp->adp); + ret = analogix_dp_bind(dp->adp, drm_dev); + if (ret) goto err_cleanup_encoder; - } return 0; err_cleanup_encoder: @@ -365,8 +352,6 @@ static void rockchip_dp_unbind(struct device *dev, struct device *master, analogix_dp_unbind(dp->adp); dp->encoder.funcs->destroy(&dp->encoder); - - dp->adp = ERR_PTR(-ENODEV); } static const struct component_ops rockchip_dp_component_ops = { @@ -377,10 +362,15 @@ static const struct component_ops rockchip_dp_component_ops = { static int rockchip_dp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + const struct rockchip_dp_chip_data *dp_data; struct drm_panel *panel = NULL; struct rockchip_dp_device *dp; int ret; + dp_data = of_device_get_match_data(dev); + if (!dp_data) + return -ENODEV; + ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); if (ret < 0) return ret; @@ -391,7 +381,12 @@ static int rockchip_dp_probe(struct platform_device *pdev) dp->dev = dev; dp->adp = ERR_PTR(-ENODEV); + dp->data = dp_data; dp->plat_data.panel = panel; + dp->plat_data.dev_type = dp->data->chip_type; + dp->plat_data.power_on_start = rockchip_dp_poweron_start; + dp->plat_data.power_off = rockchip_dp_powerdown; + dp->plat_data.get_modes = rockchip_dp_get_modes; ret = rockchip_dp_of_probe(dp); if (ret < 0) @@ -399,12 +394,19 @@ static int rockchip_dp_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dp); + dp->adp = analogix_dp_probe(dev, &dp->plat_data); + if (IS_ERR(dp->adp)) + return PTR_ERR(dp->adp); + return component_add(dev, &rockchip_dp_component_ops); } static int rockchip_dp_remove(struct platform_device *pdev) { + struct rockchip_dp_device *dp = platform_get_drvdata(pdev); + component_del(&pdev->dev, &rockchip_dp_component_ops); + analogix_dp_remove(dp->adp); return 0; } diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index a18eabf692e4..8e731ed0d9d9 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -651,7 +651,9 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb) trace_drm_sched_process_job(s_fence); + dma_fence_get(&s_fence->finished); drm_sched_fence_finished(s_fence); + dma_fence_put(&s_fence->finished); wake_up_interruptible(&sched->wake_up_worker); } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 389128b8c4dd..0ad30b112982 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -59,9 +59,10 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, /* * If possible, avoid waiting for GPU with mmap_sem - * held. + * held. We only do this if the fault allows retry and this + * is the first attempt. */ - if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault_flag_allow_retry_first(vmf->flags)) { ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out_unlock; @@ -135,7 +136,12 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, * for the buffer to become unreserved. */ if (unlikely(!dma_resv_trylock(bo->base.resv))) { - if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) { + /* + * If the fault allows retry and this is the first + * fault attempt, we try to release the mmap_sem + * before waiting + */ + if (fault_flag_allow_retry_first(vmf->flags)) { if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { ttm_bo_get(bo); up_read(&vmf->vma->vm_mm->mmap_sem); @@ -156,6 +162,89 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_vm_reserve); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults + * @vmf: Fault data + * @bo: The buffer object + * @page_offset: Page offset from bo start + * @fault_page_size: The size of the fault in pages. + * @pgprot: The page protections. + * Does additional checking whether it's possible to insert a PUD or PMD + * pfn and performs the insertion. + * + * Return: VM_FAULT_NOPAGE on successful insertion, VM_FAULT_FALLBACK if + * a huge fault was not possible, or on insertion error. + */ +static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, + struct ttm_buffer_object *bo, + pgoff_t page_offset, + pgoff_t fault_page_size, + pgprot_t pgprot) +{ + pgoff_t i; + vm_fault_t ret; + unsigned long pfn; + pfn_t pfnt; + struct ttm_tt *ttm = bo->ttm; + bool write = vmf->flags & FAULT_FLAG_WRITE; + + /* Fault should not cross bo boundary. */ + page_offset &= ~(fault_page_size - 1); + if (page_offset + fault_page_size > bo->num_pages) + goto out_fallback; + + if (bo->mem.bus.is_iomem) + pfn = ttm_bo_io_mem_pfn(bo, page_offset); + else + pfn = page_to_pfn(ttm->pages[page_offset]); + + /* pfn must be fault_page_size aligned. */ + if ((pfn & (fault_page_size - 1)) != 0) + goto out_fallback; + + /* Check that memory is contiguous. */ + if (!bo->mem.bus.is_iomem) { + for (i = 1; i < fault_page_size; ++i) { + if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i) + goto out_fallback; + } + } else if (bo->bdev->driver->io_mem_pfn) { + for (i = 1; i < fault_page_size; ++i) { + if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i) + goto out_fallback; + } + } + + pfnt = __pfn_to_pfn_t(pfn, PFN_DEV); + if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT)) + ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write); +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT)) + ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write); +#endif + else + WARN_ON_ONCE(ret = VM_FAULT_FALLBACK); + + if (ret != VM_FAULT_NOPAGE) + goto out_fallback; + + return VM_FAULT_NOPAGE; +out_fallback: + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; +} +#else +static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, + struct ttm_buffer_object *bo, + pgoff_t page_offset, + pgoff_t fault_page_size, + pgprot_t pgprot) +{ + return VM_FAULT_FALLBACK; +} +#endif + /** * ttm_bo_vm_fault_reserved - TTM fault helper * @vmf: The struct vm_fault given as argument to the fault callback @@ -163,6 +252,7 @@ EXPORT_SYMBOL(ttm_bo_vm_reserve); * @num_prefault: Maximum number of prefault pages. The caller may want to * specify this based on madvice settings and the size of the GPU object * backed by the memory. + * @fault_page_size: The size of the fault in pages. * * This function inserts one or more page table entries pointing to the * memory backing the buffer object, and then returns a return code @@ -176,7 +266,8 @@ EXPORT_SYMBOL(ttm_bo_vm_reserve); */ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, pgprot_t prot, - pgoff_t num_prefault) + pgoff_t num_prefault, + pgoff_t fault_page_size) { struct vm_area_struct *vma = vmf->vma; struct ttm_buffer_object *bo = vma->vm_private_data; @@ -268,6 +359,13 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, prot = pgprot_decrypted(prot); } + /* We don't prefault on huge faults. Yet. */ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1) { + ret = ttm_bo_vm_insert_huge(vmf, bo, page_offset, + fault_page_size, prot); + goto out_io_unlock; + } + /* * Speculatively prefault a number of pages. Only error on * first page. @@ -334,7 +432,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) return ret; prot = vma->vm_page_prot; - ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT); + ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) return ret; @@ -445,7 +543,7 @@ static const struct vm_operations_struct ttm_bo_vm_ops = { .fault = ttm_bo_vm_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close, - .access = ttm_bo_vm_access + .access = ttm_bo_vm_access, }; static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev, diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index d2112b43395a..282348e071fe 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -42,6 +42,10 @@ 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 8f956156eb8e..625bfcf52dc4 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -673,11 +673,23 @@ 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; diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile index 5c3515e8cce1..31f85f09f1fc 100644 --- a/drivers/gpu/drm/vmwgfx/Makefile +++ b/drivers/gpu/drm/vmwgfx/Makefile @@ -11,4 +11,5 @@ vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \ vmwgfx_validation.o vmwgfx_page_dirty.o vmwgfx_streamoutput.o \ ttm_object.o ttm_lock.o +vmwgfx-$(CONFIG_TRANSPARENT_HUGEPAGE) += vmwgfx_thp.o obj-$(CONFIG_DRM_VMWGFX) := vmwgfx.o diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 71e45b568511..c2247a893ed4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1247,6 +1247,18 @@ static void vmw_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static unsigned long +vmw_get_unmapped_area(struct file *file, unsigned long uaddr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct drm_file *file_priv = file->private_data; + struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); + + return drm_get_unmapped_area(file, uaddr, len, pgoff, flags, + &dev_priv->vma_manager); +} + static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, void *ptr) { @@ -1418,6 +1430,7 @@ static const struct file_operations vmwgfx_driver_fops = { .compat_ioctl = vmw_compat_ioctl, #endif .llseek = noop_llseek, + .get_unmapped_area = vmw_get_unmapped_area, }; static struct drm_driver driver = { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5ddbcb9f6df4..8cdcd6e5f9e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1000,6 +1000,7 @@ extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma); extern void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, size_t gran); + /** * TTM buffer object driver - vmwgfx_ttm_buffer.c */ @@ -1510,6 +1511,17 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, pgoff_t start, pgoff_t end); vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf); vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, + enum page_entry_size pe_size); +#endif + +/* Transparent hugepage support - vmwgfx_thp.c */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern const struct ttm_mem_type_manager_func vmw_thp_func; +#else +#define vmw_thp_func ttm_bo_manager_func +#endif /** * VMW_DEBUG_KMS - Debug output for kernel mode-setting diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 60cfbfadd3f2..d4d66532f9c9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -473,11 +473,11 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) * a lot of unnecessary write faults. */ if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE) - prot = vma->vm_page_prot; + prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED); else prot = vm_get_page_prot(vma->vm_flags); - ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault); + ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault, 1); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) return ret; @@ -486,3 +486,75 @@ out_unlock: return ret; } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, + enum page_entry_size pe_size) +{ + struct vm_area_struct *vma = vmf->vma; + struct ttm_buffer_object *bo = (struct ttm_buffer_object *) + vma->vm_private_data; + struct vmw_buffer_object *vbo = + container_of(bo, struct vmw_buffer_object, base); + pgprot_t prot; + vm_fault_t ret; + pgoff_t fault_page_size; + bool write = vmf->flags & FAULT_FLAG_WRITE; + bool is_cow_mapping = + (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + + switch (pe_size) { + case PE_SIZE_PMD: + fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT; + break; +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + case PE_SIZE_PUD: + fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT; + break; +#endif + default: + WARN_ON_ONCE(1); + return VM_FAULT_FALLBACK; + } + + /* Always do write dirty-tracking and COW on PTE level. */ + if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping)) + return VM_FAULT_FALLBACK; + + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + if (vbo->dirty) { + pgoff_t allowed_prefault; + unsigned long page_offset; + + page_offset = vmf->pgoff - + drm_vma_node_start(&bo->base.vma_node); + if (page_offset >= bo->num_pages || + vmw_resources_clean(vbo, page_offset, + page_offset + PAGE_SIZE, + &allowed_prefault)) { + ret = VM_FAULT_SIGBUS; + goto out_unlock; + } + + /* + * Write protect, so we get a new fault on write, and can + * split. + */ + prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED); + } else { + prot = vm_get_page_prot(vma->vm_flags); + } + + ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size); + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) + return ret; + +out_unlock: + dma_resv_unlock(bo->base.resv); + + return ret; +} +#endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c new file mode 100644 index 000000000000..b7c816ba7166 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Huge page-table-entry support for IO memory. + * + * Copyright (C) 2007-2019 Vmware, Inc. All rights reservedd. + */ +#include "vmwgfx_drv.h" +#include <drm/ttm/ttm_module.h> +#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_placement.h> + +/** + * struct vmw_thp_manager - Range manager implementing huge page alignment + * + * @mm: The underlying range manager. Protected by @lock. + * @lock: Manager lock. + */ +struct vmw_thp_manager { + struct drm_mm mm; + spinlock_t lock; +}; + +static int vmw_thp_insert_aligned(struct drm_mm *mm, struct drm_mm_node *node, + unsigned long align_pages, + const struct ttm_place *place, + struct ttm_mem_reg *mem, + unsigned long lpfn, + enum drm_mm_insert_mode mode) +{ + if (align_pages >= mem->page_alignment && + (!mem->page_alignment || align_pages % mem->page_alignment == 0)) { + return drm_mm_insert_node_in_range(mm, node, + mem->num_pages, + align_pages, 0, + place->fpfn, lpfn, mode); + } + + return -ENOSPC; +} + +static int vmw_thp_get_node(struct ttm_mem_type_manager *man, + struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_mem_reg *mem) +{ + struct vmw_thp_manager *rman = (struct vmw_thp_manager *) man->priv; + struct drm_mm *mm = &rman->mm; + struct drm_mm_node *node; + unsigned long align_pages; + unsigned long lpfn; + enum drm_mm_insert_mode mode = DRM_MM_INSERT_BEST; + int ret; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + + lpfn = place->lpfn; + if (!lpfn) + lpfn = man->size; + + mode = DRM_MM_INSERT_BEST; + if (place->flags & TTM_PL_FLAG_TOPDOWN) + mode = DRM_MM_INSERT_HIGH; + + spin_lock(&rman->lock); + if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) { + align_pages = (HPAGE_PUD_SIZE >> PAGE_SHIFT); + if (mem->num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(mm, node, align_pages, + place, mem, lpfn, mode); + if (!ret) + goto found_unlock; + } + } + + align_pages = (HPAGE_PMD_SIZE >> PAGE_SHIFT); + if (mem->num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(mm, node, align_pages, place, mem, + lpfn, mode); + if (!ret) + goto found_unlock; + } + + ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages, + mem->page_alignment, 0, + place->fpfn, lpfn, mode); +found_unlock: + spin_unlock(&rman->lock); + + if (unlikely(ret)) { + kfree(node); + } else { + mem->mm_node = node; + mem->start = node->start; + } + + return 0; +} + + + +static void vmw_thp_put_node(struct ttm_mem_type_manager *man, + struct ttm_mem_reg *mem) +{ + struct vmw_thp_manager *rman = (struct vmw_thp_manager *) man->priv; + + if (mem->mm_node) { + spin_lock(&rman->lock); + drm_mm_remove_node(mem->mm_node); + spin_unlock(&rman->lock); + + kfree(mem->mm_node); + mem->mm_node = NULL; + } +} + +static int vmw_thp_init(struct ttm_mem_type_manager *man, + unsigned long p_size) +{ + struct vmw_thp_manager *rman; + + rman = kzalloc(sizeof(*rman), GFP_KERNEL); + if (!rman) + return -ENOMEM; + + drm_mm_init(&rman->mm, 0, p_size); + spin_lock_init(&rman->lock); + man->priv = rman; + return 0; +} + +static int vmw_thp_takedown(struct ttm_mem_type_manager *man) +{ + struct vmw_thp_manager *rman = (struct vmw_thp_manager *) man->priv; + struct drm_mm *mm = &rman->mm; + + spin_lock(&rman->lock); + if (drm_mm_clean(mm)) { + drm_mm_takedown(mm); + spin_unlock(&rman->lock); + kfree(rman); + man->priv = NULL; + return 0; + } + spin_unlock(&rman->lock); + return -EBUSY; +} + +static void vmw_thp_debug(struct ttm_mem_type_manager *man, + struct drm_printer *printer) +{ + struct vmw_thp_manager *rman = (struct vmw_thp_manager *) man->priv; + + spin_lock(&rman->lock); + drm_mm_print(&rman->mm, printer); + spin_unlock(&rman->lock); +} + +const struct ttm_mem_type_manager_func vmw_thp_func = { + .init = vmw_thp_init, + .takedown = vmw_thp_takedown, + .get_node = vmw_thp_get_node, + .put_node = vmw_thp_put_node, + .debug = vmw_thp_debug +}; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 3f3b2c7a208a..bf0bc4697959 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -749,7 +749,7 @@ static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, break; case TTM_PL_VRAM: /* "On-card" video ram */ - man->func = &ttm_bo_manager_func; + man->func = &vmw_thp_func; man->gpu_offset = 0; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_CACHED; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index aa7e50f63b94..3c03b1746661 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -34,7 +34,10 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) .page_mkwrite = vmw_bo_vm_mkwrite, .fault = vmw_bo_vm_fault, .open = ttm_bo_vm_open, - .close = ttm_bo_vm_close + .close = ttm_bo_vm_close, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + .huge_fault = vmw_bo_vm_huge_fault, +#endif }; struct drm_file *file_priv = filp->private_data; struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index b91d23b5f3ae..1fd458e877ca 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -401,7 +401,7 @@ static int xen_drm_drv_dumb_create(struct drm_file *filp, obj = xen_drm_front_gem_create(dev, args->size); if (IS_ERR_OR_NULL(obj)) { - ret = PTR_ERR(obj); + ret = PTR_ERR_OR_ZERO(obj); goto fail; } |