diff options
Diffstat (limited to 'drivers/gpu')
131 files changed, 1417 insertions, 582 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 164141bc8b4a..39018f784f9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1272,6 +1272,7 @@ void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); +bool amdgpu_device_aspm_support_quirk(void); void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes, u64 num_vis_bytes); @@ -1391,10 +1392,12 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev); void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps); +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev); void amdgpu_acpi_detect(void); #else static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; } static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { } +static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; } static inline void amdgpu_acpi_detect(void) { } static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; } static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev, @@ -1405,11 +1408,9 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev, #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev); -bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev); bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); #else static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } -static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; } static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index d4196fcb85a0..aeeec211861c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -971,6 +971,34 @@ static bool amdgpu_atcs_pci_probe_handle(struct pci_dev *pdev) return true; } + +/** + * amdgpu_acpi_should_gpu_reset + * + * @adev: amdgpu_device_pointer + * + * returns true if should reset GPU, false if not + */ +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) +{ + if ((adev->flags & AMD_IS_APU) && + adev->gfx.imu.funcs) /* Not need to do mode2 reset for IMU enabled APUs */ + return false; + + if ((adev->flags & AMD_IS_APU) && + amdgpu_acpi_is_s3_active(adev)) + return false; + + if (amdgpu_sriov_vf(adev)) + return false; + +#if IS_ENABLED(CONFIG_SUSPEND) + return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; +#else + return true; +#endif +} + /* * amdgpu_acpi_detect - detect ACPI ATIF/ATCS methods * @@ -1043,24 +1071,6 @@ bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) } /** - * amdgpu_acpi_should_gpu_reset - * - * @adev: amdgpu_device_pointer - * - * returns true if should reset GPU, false if not - */ -bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) -{ - if (adev->flags & AMD_IS_APU) - return false; - - if (amdgpu_sriov_vf(adev)) - return false; - - return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; -} - -/** * amdgpu_acpi_is_s0ix_active * * @adev: amdgpu_device_pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index c4a4e2fe6681..3d98fc2ad36b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,6 +80,10 @@ #include <drm/drm_drv.h> +#if IS_ENABLED(CONFIG_X86) +#include <asm/intel-family.h> +#endif + MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin"); @@ -1356,6 +1360,17 @@ bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev) return pcie_aspm_enabled(adev->pdev); } +bool amdgpu_device_aspm_support_quirk(void) +{ +#if IS_ENABLED(CONFIG_X86) + struct cpuinfo_x86 *c = &cpu_data(0); + + return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE); +#else + return true; +#endif +} + /* if we get transitioned to only one device, take VGA back */ /** * amdgpu_device_vga_set_decode - enable/disable vga decode @@ -4145,8 +4160,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3)) DRM_WARN("smart shift update failed\n"); - drm_kms_helper_poll_disable(dev); - if (fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); @@ -4243,8 +4256,6 @@ exit: if (fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false); - drm_kms_helper_poll_enable(dev); - amdgpu_ras_resume(adev); if (adev->mode_info.num_crtc) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index b719852daa07..1a3cb53d2e0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -543,6 +543,7 @@ static void amdgpu_discovery_read_from_harvest_table(struct amdgpu_device *adev, struct harvest_table *harvest_info; u16 offset; int i; + uint32_t umc_harvest_config = 0; bhdr = (struct binary_header *)adev->mman.discovery_bin; offset = le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset); @@ -570,12 +571,17 @@ static void amdgpu_discovery_read_from_harvest_table(struct amdgpu_device *adev, adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; break; case UMC_HWID: + umc_harvest_config |= + 1 << (le16_to_cpu(harvest_info->list[i].number_instance)); (*umc_harvest_count)++; break; default: break; } } + + adev->umc.active_mask = ((1 << adev->umc.node_inst_num) - 1) & + ~umc_harvest_config; } /* ================================================== */ @@ -1156,8 +1162,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) AMDGPU_MAX_SDMA_INSTANCES); } - if (le16_to_cpu(ip->hw_id) == UMC_HWID) + if (le16_to_cpu(ip->hw_id) == UMC_HWID) { adev->gmc.num_umc++; + adev->umc.node_inst_num++; + } for (k = 0; k < num_base_address; k++) { /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 503f89a766c3..d60fe7eb5579 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1618,6 +1618,8 @@ int amdgpu_display_suspend_helper(struct amdgpu_device *adev) struct drm_connector_list_iter iter; int r; + drm_kms_helper_poll_disable(dev); + /* turn off display hw */ drm_modeset_lock_all(dev); drm_connector_list_iter_begin(dev, &iter); @@ -1694,6 +1696,8 @@ int amdgpu_display_resume_helper(struct amdgpu_device *adev) drm_modeset_unlock_all(dev); + drm_kms_helper_poll_enable(dev); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f5ffca24def4..ba5def374368 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2467,7 +2467,10 @@ static int amdgpu_pmops_freeze(struct device *dev) adev->in_s4 = false; if (r) return r; - return amdgpu_asic_reset(adev); + + if (amdgpu_acpi_should_gpu_reset(adev)) + return amdgpu_asic_reset(adev); + return 0; } static int amdgpu_pmops_thaw(struct device *dev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index faff4a3f96e6..f52d0ba91a77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -678,6 +678,15 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring) ptr = &ring->fence_drv.fences[i]; old = rcu_dereference_protected(*ptr, 1); if (old && old->ops == &amdgpu_job_fence_ops) { + struct amdgpu_job *job; + + /* For non-scheduler bad job, i.e. failed ib test, we need to signal + * it right here or we won't be able to track them in fence_drv + * and they will remain unsignaled during sa_bo free. + */ + job = container_of(old, struct amdgpu_job, hw_fence); + if (!job->base.s_fence && !dma_fence_is_signaled(old)) + dma_fence_signal(old); RCU_INIT_POINTER(*ptr, NULL); dma_fence_put(old); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e3e1ed4314dd..6c7d672412b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1315,7 +1315,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || - adev->in_suspend || adev->shutdown) + adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev))) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 28fe6d941054..3f5d13035aff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -602,27 +602,14 @@ psp_cmd_submit_buf(struct psp_context *psp, struct psp_gfx_cmd_resp *cmd, uint64_t fence_mc_addr) { int ret; - int index, idx; + int index; int timeout = 20000; bool ras_intr = false; bool skip_unsupport = false; - bool dev_entered; if (psp->adev->no_hw_access) return 0; - dev_entered = drm_dev_enter(adev_to_drm(psp->adev), &idx); - /* - * We allow sending PSP messages LOAD_ASD and UNLOAD_TA without acquiring - * a lock in drm_dev_enter during driver unload because we must call - * drm_dev_unplug as the beginning of unload driver sequence . It is very - * crucial that userspace can't access device instances anymore. - */ - if (!dev_entered) - WARN_ON(psp->cmd_buf_mem->cmd_id != GFX_CMD_ID_LOAD_ASD && - psp->cmd_buf_mem->cmd_id != GFX_CMD_ID_UNLOAD_TA && - psp->cmd_buf_mem->cmd_id != GFX_CMD_ID_INVOKE_CMD); - memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE); memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp)); @@ -686,8 +673,6 @@ psp_cmd_submit_buf(struct psp_context *psp, } exit: - if (dev_entered) - drm_dev_exit(idx); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index f2bf979af588..36e19336f3b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -42,7 +42,7 @@ #define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst)) #define LOOP_UMC_NODE_INST(node_inst) \ - for ((node_inst) = 0; (node_inst) < adev->umc.node_inst_num; (node_inst)++) + for_each_set_bit((node_inst), &(adev->umc.active_mask), adev->umc.node_inst_num) #define LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) \ LOOP_UMC_NODE_INST((node_inst)) LOOP_UMC_INST_AND_CH((umc_inst), (ch_inst)) @@ -69,7 +69,7 @@ struct amdgpu_umc { /* number of umc instance with memory map register access */ uint32_t umc_inst_num; - /*number of umc node instance with memory map register access*/ + /* Total number of umc node instance including harvest one */ uint32_t node_inst_num; /* UMC regiser per channel offset */ @@ -82,6 +82,9 @@ struct amdgpu_umc { const struct amdgpu_umc_funcs *funcs; struct amdgpu_umc_ras *ras; + + /* active mask for umc node instance */ + unsigned long active_mask; }; int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 25217b05c0ea..e7974de8b035 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -26,6 +26,7 @@ #include <linux/firmware.h> #include <linux/module.h> +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/debugfs.h> #include <drm/drm_drv.h> @@ -114,6 +115,24 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) adev->vcn.indirect_sram = true; + /* + * Some Steam Deck's BIOS versions are incompatible with the + * indirect SRAM mode, leading to amdgpu being unable to get + * properly probed (and even potentially crashing the kernel). + * Hence, check for these versions here - notice this is + * restricted to Vangogh (Deck's APU). + */ + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 0, 2)) { + const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION); + + if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) || + !strncmp("F7A0114", bios_ver, 7))) { + adev->vcn.indirect_sram = false; + dev_info(adev->dev, + "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); + } + } + hdr = (const struct common_firmware_header *)adev->vcn.fw->data; adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index b9e9480448af..4f7bab52282a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -124,6 +124,8 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_PP_ONE_VF = (1 << 4), /* Indirect Reg Access enabled */ AMDGIM_FEATURE_INDIRECT_REG_ACCESS = (1 << 5), + /* AV1 Support MODE*/ + AMDGIM_FEATURE_AV1_SUPPORT = (1 << 6), }; enum AMDGIM_REG_ACCESS_FLAG { @@ -322,6 +324,8 @@ static inline bool is_virtual_machine(void) ((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug) #define amdgpu_sriov_is_normal(adev) \ ((!amdgpu_in_reset(adev)) && (!adev->virt.tdr_debug)) +#define amdgpu_sriov_is_av1_support(adev) \ + ((adev)->virt.gim_feature & AMDGIM_FEATURE_AV1_SUPPORT) bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev); void amdgpu_virt_init_setting(struct amdgpu_device *adev); void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 6c97148ca0ed..24d42d24e6a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -93,7 +93,8 @@ union amd_sriov_msg_feature_flags { uint32_t mm_bw_management : 1; uint32_t pp_one_vf_mode : 1; uint32_t reg_indirect_acc : 1; - uint32_t reserved : 26; + uint32_t av1_support : 1; + uint32_t reserved : 25; } flags; uint32_t all; }; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 3bf697a80cf2..ecf8ceb53311 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1287,6 +1287,11 @@ static int gfx_v11_0_sw_init(void *handle) break; } + /* Enable CG flag in one VF mode for enabling RLC safe mode enter/exit */ + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 3) && + amdgpu_sriov_is_pp_one_vf(adev)) + adev->cg_flags = AMD_CG_SUPPORT_GFX_CGCG; + /* EOP Event */ r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP, GFX_11_0_0__SRCID__CP_EOP_INTERRUPT, @@ -4655,6 +4660,14 @@ static bool gfx_v11_0_check_soft_reset(void *handle) return false; } +static int gfx_v11_0_post_soft_reset(void *handle) +{ + /** + * GFX soft reset will impact MES, need resume MES when do GFX soft reset + */ + return amdgpu_mes_resume((struct amdgpu_device *)handle); +} + static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; @@ -6166,6 +6179,7 @@ static const struct amd_ip_funcs gfx_v11_0_ip_funcs = { .wait_for_idle = gfx_v11_0_wait_for_idle, .soft_reset = gfx_v11_0_soft_reset, .check_soft_reset = gfx_v11_0_check_soft_reset, + .post_soft_reset = gfx_v11_0_post_soft_reset, .set_clockgating_state = gfx_v11_0_set_clockgating_state, .set_powergating_state = gfx_v11_0_set_powergating_state, .get_clockgating_state = gfx_v11_0_get_clockgating_state, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 85e0afc3d4f7..af7b3ba1ca00 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -567,7 +567,6 @@ static void gmc_v11_0_set_umc_funcs(struct amdgpu_device *adev) case IP_VERSION(8, 10, 0): adev->umc.channel_inst_num = UMC_V8_10_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V8_10_UMC_INSTANCE_NUM; - adev->umc.node_inst_num = adev->gmc.num_umc; adev->umc.max_ras_err_cnt_per_query = UMC_V8_10_TOTAL_CHANNEL_NUM(adev); adev->umc.channel_offs = UMC_V8_10_PER_CHANNEL_OFFSET; adev->umc.retire_unit = UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c index 4b0d563c6522..4ef1fa4603c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c @@ -382,11 +382,6 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_PCIE_PORT(SOC15_REG_OFFSET(NBIO, 0, regBIF1_PCIE_MST_CTRL_3), data); break; - case IP_VERSION(7, 5, 1): - data = RREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2); - data &= ~RCC_DEV2_EPF0_STRAP2__STRAP_NO_SOFT_RESET_DEV2_F0_MASK; - WREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2, data); - fallthrough; default: def = data = RREG32_PCIE_PORT(SOC15_REG_OFFSET(NBIO, 0, regPCIE_CONFIG_CNTL)); data = REG_SET_FIELD(data, PCIE_CONFIG_CNTL, @@ -399,6 +394,15 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev) break; } + switch (adev->ip_versions[NBIO_HWIP][0]) { + case IP_VERSION(7, 3, 0): + case IP_VERSION(7, 5, 1): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2); + data &= ~RCC_DEV2_EPF0_STRAP2__STRAP_NO_SOFT_RESET_DEV2_F0_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2, data); + break; + } + if (amdgpu_sriov_vf(adev)) adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index d972025f0d20..ebe0e2d7dbd1 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -444,9 +444,10 @@ static int nv_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(nv_allowed_read_registers); i++) { en = &nv_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] - + en->reg_offset)) + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + + en->reg_offset)) continue; *value = nv_get_register_value(adev, @@ -577,7 +578,7 @@ static void nv_pcie_gen3_enable(struct amdgpu_device *adev) static void nv_program_aspm(struct amdgpu_device *adev) { - if (!amdgpu_device_should_use_aspm(adev)) + if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_aspm_support_quirk()) return; if (!(adev->flags & AMD_IS_APU) && @@ -1054,8 +1055,8 @@ static int nv_common_late_init(void *handle) amdgpu_virt_update_sriov_video_codec(adev, sriov_sc_video_codecs_encode_array, ARRAY_SIZE(sriov_sc_video_codecs_encode_array), - sriov_sc_video_codecs_decode_array_vcn1, - ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1)); + sriov_sc_video_codecs_decode_array_vcn0, + ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn0)); } } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 7cd17dda32ce..2eddd7f6cd41 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -439,8 +439,9 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(soc15_allowed_read_registers); i++) { en = &soc15_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + en->reg_offset)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 620f7409825d..c82b3a7ea5f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -102,6 +102,59 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = .codec_array = vcn_4_0_0_video_codecs_decode_array_vcn1, }; +/* SRIOV SOC21, not const since data is controlled by host */ +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0), + .codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn0, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn1 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1), + .codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn1, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn0[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn1[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn0 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0), + .codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn0, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn1 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1), + .codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn1, +}; + static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode, const struct amdgpu_video_codecs **codecs) { @@ -111,16 +164,32 @@ static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode, switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(4, 0, 0): case IP_VERSION(4, 0, 2): - if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { - if (encode) - *codecs = &vcn_4_0_0_video_codecs_encode_vcn1; - else - *codecs = &vcn_4_0_0_video_codecs_decode_vcn1; + case IP_VERSION(4, 0, 4): + if (amdgpu_sriov_vf(adev)) { + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) || + !amdgpu_sriov_is_av1_support(adev)) { + if (encode) + *codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn1; + else + *codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn0; + else + *codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn0; + } } else { - if (encode) - *codecs = &vcn_4_0_0_video_codecs_encode_vcn0; - else - *codecs = &vcn_4_0_0_video_codecs_decode_vcn0; + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)) { + if (encode) + *codecs = &vcn_4_0_0_video_codecs_encode_vcn1; + else + *codecs = &vcn_4_0_0_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &vcn_4_0_0_video_codecs_encode_vcn0; + else + *codecs = &vcn_4_0_0_video_codecs_decode_vcn0; + } } return 0; default: @@ -291,9 +360,10 @@ static int soc21_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(soc21_allowed_read_registers); i++) { en = &soc21_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] - + en->reg_offset)) + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + + en->reg_offset)) continue; *value = soc21_get_register_value(adev, @@ -728,8 +798,23 @@ static int soc21_common_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { xgpu_nv_mailbox_get_irq(adev); + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) || + !amdgpu_sriov_is_av1_support(adev)) { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_vcn_4_0_0_video_codecs_encode_array_vcn1, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1), + sriov_vcn_4_0_0_video_codecs_decode_array_vcn1, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1)); + } else { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_vcn_4_0_0_video_codecs_encode_array_vcn0, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0), + sriov_vcn_4_0_0_video_codecs_decode_array_vcn0, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0)); + } + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h index 25eaf4af5fcf..c6dfd433fec7 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h @@ -31,9 +31,9 @@ /* number of umc instance with memory map register access */ #define UMC_V8_10_UMC_INSTANCE_NUM 2 -/* Total channel instances for all umc nodes */ +/* Total channel instances for all available umc nodes */ #define UMC_V8_10_TOTAL_CHANNEL_NUM(adev) \ - (UMC_V8_10_CHANNEL_INSTANCE_NUM * UMC_V8_10_UMC_INSTANCE_NUM * (adev)->umc.node_inst_num) + (UMC_V8_10_CHANNEL_INSTANCE_NUM * UMC_V8_10_UMC_INSTANCE_NUM * (adev)->gmc.num_umc) /* UMC regiser per channel offset */ #define UMC_V8_10_PER_CHANNEL_OFFSET 0x400 diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 12ef782eb478..ceab8783575c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -81,10 +81,6 @@ #include "mxgpu_vi.h" #include "amdgpu_dm.h" -#if IS_ENABLED(CONFIG_X86) -#include <asm/intel-family.h> -#endif - #define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6 #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L @@ -1138,24 +1134,13 @@ static void vi_enable_aspm(struct amdgpu_device *adev) WREG32_PCIE(ixPCIE_LC_CNTL, data); } -static bool aspm_support_quirk_check(void) -{ -#if IS_ENABLED(CONFIG_X86) - struct cpuinfo_x86 *c = &cpu_data(0); - - return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE); -#else - return true; -#endif -} - static void vi_program_aspm(struct amdgpu_device *adev) { u32 data, data1, orig; bool bL1SS = false; bool bClkReqSupport = true; - if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check()) + if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_aspm_support_quirk()) return; if (adev->flags & AMD_IS_APU || diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a0e30f21e12e..de310ed367ca 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1312,14 +1312,14 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, args->n_success = i+1; } - mutex_unlock(&p->mutex); - err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev, (struct kgd_mem *) mem, true); if (err) { pr_debug("Sync memory failed, wait interrupted by user signal\n"); goto sync_memory_failed; } + mutex_unlock(&p->mutex); + /* Flush TLBs after waiting for the page table updates to complete */ for (i = 0; i < args->n_devices; i++) { peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); @@ -1335,9 +1335,9 @@ get_process_device_data_failed: bind_process_to_device_failed: get_mem_obj_from_handle_failed: map_memory_to_gpu_failed: +sync_memory_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr); return err; @@ -1351,6 +1351,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, void *mem; long err = 0; uint32_t *devices_arr = NULL, i; + bool flush_tlb; if (!args->n_devices) { pr_debug("Device IDs array empty\n"); @@ -1403,16 +1404,19 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, } args->n_success = i+1; } - mutex_unlock(&p->mutex); - if (kfd_flush_tlb_after_unmap(pdd->dev)) { + flush_tlb = kfd_flush_tlb_after_unmap(pdd->dev); + if (flush_tlb) { err = amdgpu_amdkfd_gpuvm_sync_memory(pdd->dev->adev, (struct kgd_mem *) mem, true); if (err) { pr_debug("Sync memory failed, wait interrupted by user signal\n"); goto sync_memory_failed; } + } + mutex_unlock(&p->mutex); + if (flush_tlb) { /* Flush TLBs after waiting for the page table updates to complete */ for (i = 0; i < args->n_devices; i++) { peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); @@ -1428,9 +1432,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, bind_process_to_device_failed: get_mem_obj_from_handle_failed: unmap_memory_from_gpu_failed: +sync_memory_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr); return err; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 3de7f616a001..ec70a1658dc3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -59,6 +59,7 @@ static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size, unsigned int chunk_size); static void kfd_gtt_sa_fini(struct kfd_dev *kfd); +static int kfd_resume_iommu(struct kfd_dev *kfd); static int kfd_resume(struct kfd_dev *kfd); static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd) @@ -624,7 +625,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, svm_migrate_init(kfd->adev); - if (kgd2kfd_resume_iommu(kfd)) + if (kfd_resume_iommu(kfd)) goto device_iommu_error; if (kfd_resume(kfd)) @@ -773,6 +774,14 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) int kgd2kfd_resume_iommu(struct kfd_dev *kfd) { + if (!kfd->init_complete) + return 0; + + return kfd_resume_iommu(kfd); +} + +static int kfd_resume_iommu(struct kfd_dev *kfd) +{ int err = 0; err = kfd_iommu_resume(kfd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index cbef2e147da5..38c9e1ca6691 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -280,7 +280,7 @@ phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd) if (!pdd->doorbell_index) { int r = kfd_alloc_process_doorbells(pdd->dev, &pdd->doorbell_index); - if (r) + if (r < 0) return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index de8ce72344fc..54933903bcb8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -289,7 +289,7 @@ static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate) static int svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, - dma_addr_t *scratch) + dma_addr_t *scratch, uint64_t ttm_res_offset) { uint64_t npages = migrate->npages; struct device *dev = adev->dev; @@ -299,19 +299,13 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t i, j; int r; - pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, - prange->last); + pr_debug("svms 0x%p [0x%lx 0x%lx 0x%llx]\n", prange->svms, prange->start, + prange->last, ttm_res_offset); src = scratch; dst = (uint64_t *)(scratch + npages); - r = svm_range_vram_node_new(adev, prange, true); - if (r) { - dev_dbg(adev->dev, "fail %d to alloc vram\n", r); - goto out; - } - - amdgpu_res_first(prange->ttm_res, prange->offset << PAGE_SHIFT, + amdgpu_res_first(prange->ttm_res, ttm_res_offset, npages << PAGE_SHIFT, &cursor); for (i = j = 0; i < npages; i++) { struct page *spage; @@ -391,14 +385,14 @@ out_free_vram_pages: migrate->dst[i + 3] = 0; } #endif -out: + return r; } static long svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, - uint64_t end, uint32_t trigger) + uint64_t end, uint32_t trigger, uint64_t ttm_res_offset) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; @@ -451,7 +445,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, else pr_debug("0x%lx pages migrated\n", cpages); - r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch); + r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch, ttm_res_offset); migrate_vma_pages(&migrate); pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n", @@ -499,6 +493,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, unsigned long addr, start, end; struct vm_area_struct *vma; struct amdgpu_device *adev; + uint64_t ttm_res_offset; unsigned long cpages = 0; long r = 0; @@ -520,6 +515,13 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, start = prange->start << PAGE_SHIFT; end = (prange->last + 1) << PAGE_SHIFT; + r = svm_range_vram_node_new(adev, prange, true); + if (r) { + dev_dbg(adev->dev, "fail %ld to alloc vram\n", r); + return r; + } + ttm_res_offset = prange->offset << PAGE_SHIFT; + for (addr = start; addr < end;) { unsigned long next; @@ -528,18 +530,21 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, break; next = min(vma->vm_end, end); - r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger); + r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger, ttm_res_offset); if (r < 0) { pr_debug("failed %ld to migrate\n", r); break; } else { cpages += r; } + ttm_res_offset += next - addr; addr = next; } if (cpages) prange->actual_loc = best_loc; + else + svm_range_vram_node_free(prange); return r < 0 ? r : 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c index 09b966dc3768..aee2212e52f6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c @@ -77,6 +77,7 @@ err_ioctl: static void kfd_exit(void) { + kfd_cleanup_processes(); kfd_debugfs_fini(); kfd_process_destroy_wq(); kfd_procfs_shutdown(); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index bfa30d12406b..7e4d992e48b3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -928,6 +928,7 @@ bool kfd_dev_is_large_bar(struct kfd_dev *dev); int kfd_process_create_wq(void); void kfd_process_destroy_wq(void); +void kfd_cleanup_processes(void); struct kfd_process *kfd_create_process(struct file *filep); struct kfd_process *kfd_get_process(const struct task_struct *task); struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 7acd55a814b2..4208e0f01064 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1167,6 +1167,17 @@ static void kfd_process_free_notifier(struct mmu_notifier *mn) kfd_unref_process(container_of(mn, struct kfd_process, mmu_notifier)); } +static void kfd_process_notifier_release_internal(struct kfd_process *p) +{ + cancel_delayed_work_sync(&p->eviction_work); + cancel_delayed_work_sync(&p->restore_work); + + /* Indicate to other users that MM is no longer valid */ + p->mm = NULL; + + mmu_notifier_put(&p->mmu_notifier); +} + static void kfd_process_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { @@ -1181,17 +1192,22 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, return; mutex_lock(&kfd_processes_mutex); + /* + * Do early return if table is empty. + * + * This could potentially happen if this function is called concurrently + * by mmu_notifier and by kfd_cleanup_pocesses. + * + */ + if (hash_empty(kfd_processes_table)) { + mutex_unlock(&kfd_processes_mutex); + return; + } hash_del_rcu(&p->kfd_processes); mutex_unlock(&kfd_processes_mutex); synchronize_srcu(&kfd_processes_srcu); - cancel_delayed_work_sync(&p->eviction_work); - cancel_delayed_work_sync(&p->restore_work); - - /* Indicate to other users that MM is no longer valid */ - p->mm = NULL; - - mmu_notifier_put(&p->mmu_notifier); + kfd_process_notifier_release_internal(p); } static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { @@ -1200,6 +1216,43 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { .free_notifier = kfd_process_free_notifier, }; +/* + * This code handles the case when driver is being unloaded before all + * mm_struct are released. We need to safely free the kfd_process and + * avoid race conditions with mmu_notifier that might try to free them. + * + */ +void kfd_cleanup_processes(void) +{ + struct kfd_process *p; + struct hlist_node *p_temp; + unsigned int temp; + HLIST_HEAD(cleanup_list); + + /* + * Move all remaining kfd_process from the process table to a + * temp list for processing. Once done, callback from mmu_notifier + * release will not see the kfd_process in the table and do early return, + * avoiding double free issues. + */ + mutex_lock(&kfd_processes_mutex); + hash_for_each_safe(kfd_processes_table, temp, p_temp, p, kfd_processes) { + hash_del_rcu(&p->kfd_processes); + synchronize_srcu(&kfd_processes_srcu); + hlist_add_head(&p->kfd_processes, &cleanup_list); + } + mutex_unlock(&kfd_processes_mutex); + + hlist_for_each_entry_safe(p, p_temp, &cleanup_list, kfd_processes) + kfd_process_notifier_release_internal(p); + + /* + * Ensures that all outstanding free_notifier get called, triggering + * the release of the kfd_process struct. + */ + mmu_notifier_synchronize(); +} + static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep) { unsigned long offset; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 5137476ec18e..4236539d9f93 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -218,8 +218,8 @@ static int init_user_queue(struct process_queue_manager *pqm, return 0; cleanup: - if (dev->shared_resources.enable_mes) - uninit_queue(*q); + uninit_queue(*q); + *q = NULL; return retval; } 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 009ef917dad4..a01fd41643fc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5105,9 +5105,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, for (; flip_addrs->dirty_rect_count < num_clips; clips++) fill_dc_dirty_rect(new_plane_state->plane, - &dirty_rects[i], clips->x1, - clips->y1, clips->x2 - clips->x1, - clips->y2 - clips->y1, + &dirty_rects[flip_addrs->dirty_rect_count], + clips->x1, clips->y1, + clips->x2 - clips->x1, clips->y2 - clips->y1, &flip_addrs->dirty_rect_count, false); return; @@ -7244,7 +7244,6 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, if (!aconnector->mst_root) 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 = 16; aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc; 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 8e572f07ec47..4abfd2c9679f 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 @@ -561,7 +561,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.mst_enabled = config->mst_enabled; link->dp.usb4_enabled = config->usb4_enabled; display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION; - link->adjust.auth_delay = 0; + link->adjust.auth_delay = 2; link->adjust.hdcp1.disable = 0; conn_state = aconnector->base.state; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 1583157da355..efd025d8961e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -177,6 +177,40 @@ void dm_helpers_dp_update_branch_info( const struct dc_link *link) {} +static void dm_helpers_construct_old_payload( + struct dc_link *link, + int pbn_per_slot, + struct drm_dp_mst_atomic_payload *new_payload, + struct drm_dp_mst_atomic_payload *old_payload) +{ + struct link_mst_stream_allocation_table current_link_table = + link->mst_stream_alloc_table; + struct link_mst_stream_allocation *dc_alloc; + int i; + + *old_payload = *new_payload; + + /* Set correct time_slots/PBN of old payload. + * other fields (delete & dsc_enabled) in + * struct drm_dp_mst_atomic_payload are don't care fields + * while calling drm_dp_remove_payload() + */ + for (i = 0; i < current_link_table.stream_count; i++) { + dc_alloc = + ¤t_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == new_payload->vcpi) { + old_payload->time_slots = dc_alloc->slot_count; + old_payload->pbn = dc_alloc->slot_count * pbn_per_slot; + break; + } + } + + /* make sure there is an old payload*/ + ASSERT(i != current_link_table.stream_count); + +} + /* * Writes payload allocation table in immediate downstream device. */ @@ -188,7 +222,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( { struct amdgpu_dm_connector *aconnector; struct drm_dp_mst_topology_state *mst_state; - struct drm_dp_mst_atomic_payload *payload; + struct drm_dp_mst_atomic_payload *target_payload, *new_payload, old_payload; struct drm_dp_mst_topology_mgr *mst_mgr; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; @@ -204,17 +238,26 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); /* It's OK for this to fail */ - payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - if (enable) - drm_dp_add_payload_part1(mst_mgr, mst_state, payload); - else - drm_dp_remove_payload(mst_mgr, mst_state, payload, payload); + new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); + + if (enable) { + target_payload = new_payload; + + drm_dp_add_payload_part1(mst_mgr, mst_state, new_payload); + } else { + /* construct old payload by VCPI*/ + dm_helpers_construct_old_payload(stream->link, mst_state->pbn_div, + new_payload, &old_payload); + target_payload = &old_payload; + + drm_dp_remove_payload(mst_mgr, mst_state, &old_payload, new_payload); + } /* mst_mgr->->payloads are VC payload notify MST branch using DPCD or * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, target_payload, proposed_table); return true; } 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 e25e1b2bf194..8dc442f90eaf 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 @@ -212,6 +212,21 @@ bool needs_dsc_aux_workaround(struct dc_link *link) return false; } +bool is_synaptics_cascaded_panamera(struct dc_link *link, struct drm_dp_mst_port *port) +{ + u8 branch_vendor_data[4] = { 0 }; // Vendor data 0x50C ~ 0x50F + + if (drm_dp_dpcd_read(port->mgr->aux, DP_BRANCH_VENDOR_SPECIFIC_START, &branch_vendor_data, 4) == 4) { + if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + IS_SYNAPTICS_CASCADED_PANAMERA(link->dpcd_caps.branch_dev_name, branch_vendor_data)) { + DRM_INFO("Synaptics Cascaded MST hub\n"); + return true; + } + } + + return false; +} + static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector) { struct dc_sink *dc_sink = aconnector->dc_sink; @@ -235,6 +250,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto needs_dsc_aux_workaround(aconnector->dc_link)) aconnector->dsc_aux = &aconnector->mst_root->dm_dp_aux.aux; + /* synaptics cascaded MST hub case */ + if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port)) + aconnector->dsc_aux = port->mgr->aux; + if (!aconnector->dsc_aux) return false; @@ -662,12 +681,25 @@ struct dsc_mst_fairness_params { struct amdgpu_dm_connector *aconnector; }; -static int kbps_to_peak_pbn(int kbps) +static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link) +{ + u8 link_coding_cap; + uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B; + + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link); + if (link_coding_cap == DP_128b_132b_ENCODING) + fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B; + + return fec_overhead_multiplier_x1000; +} + +static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000) { u64 peak_kbps = kbps; peak_kbps *= 1006; - peak_kbps = div_u64(peak_kbps, 1000); + peak_kbps *= fec_overhead_multiplier_x1000; + peak_kbps = div_u64(peak_kbps, 1000 * 1000); return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); } @@ -761,11 +793,12 @@ static int increase_dsc_bpp(struct drm_atomic_state *state, int link_timeslots_used; int fair_pbn_alloc; int ret = 0; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { initial_slack[i] = - kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i + k].pbn; + kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -861,6 +894,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, int next_index; int remaining_to_try = 0; int ret; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled @@ -890,7 +924,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, if (next_index == -1) break; - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps); + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -903,7 +937,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, vars[next_index].dsc_enabled = false; vars[next_index].bpp_x16 = 0; } else { - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps); + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -932,6 +966,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, int count = 0; int i, k, ret; bool debugfs_overwrite = false; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); memset(params, 0, sizeof(params)); @@ -993,7 +1028,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, /* Try no compression */ for (i = 0; i < count; i++) { vars[i + k].aconnector = params[i].aconnector; - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, @@ -1012,7 +1047,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, /* Try max compression */ for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1020,7 +1055,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (ret < 0) return ret; } else { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 97fd70df531b..1e4ede1e57ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -34,6 +34,21 @@ #define SYNAPTICS_RC_OFFSET 0x4BC #define SYNAPTICS_RC_DATA 0x4C0 +#define DP_BRANCH_VENDOR_SPECIFIC_START 0x50C + +/** + * Panamera MST Hub detection + * Offset DPCD 050Eh == 0x5A indicates cascaded MST hub case + * Check from beginning of branch device vendor specific field (050Ch) + */ +#define IS_SYNAPTICS_PANAMERA(branchDevName) (((int)branchDevName[4] & 0xF0) == 0x50 ? 1 : 0) +#define BRANCH_HW_REVISION_PANAMERA_A2 0x10 +#define SYNAPTICS_CASCADED_HUB_ID 0x5A +#define IS_SYNAPTICS_CASCADED_PANAMERA(devName, data) ((IS_SYNAPTICS_PANAMERA(devName) && ((int)data[2] == SYNAPTICS_CASCADED_HUB_ID)) ? 1 : 0) + +#define PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B 1031 +#define PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B 1000 + struct amdgpu_display_manager; struct amdgpu_dm_connector; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c index 24715ca2fa94..01383aac6b41 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c @@ -529,6 +529,19 @@ static struct clk_bw_params vg_bw_params = { }; +static uint32_t find_max_clk_value(const uint32_t clocks[], uint32_t num_clocks) +{ + uint32_t max = 0; + int i; + + for (i = 0; i < num_clocks; ++i) { + if (clocks[i] > max) + max = clocks[i]; + } + + return max; +} + static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_table, unsigned int voltage) { @@ -572,12 +585,16 @@ static void vg_clk_mgr_helper_populate_bw_params( bw_params->clk_table.num_entries = j + 1; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { + for (i = 0; i < bw_params->clk_table.num_entries - 1; i++, j--) { bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].fclk; bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].memclk; bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].voltage; bw_params->clk_table.entries[i].dcfclk_mhz = find_dcfclk_for_voltage(clock_table, clock_table->DfPstateTable[j].voltage); } + bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].memclk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_max_clk_value(clock_table->DcfClocks, VG_NUM_DCFCLK_DPM_LEVELS); bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 3b4d4d68359b..df787fcf8e86 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -998,8 +998,5 @@ void dcn30_prepare_bandwidth(struct dc *dc, dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); - - dc_dmub_srv_p_state_delegate(dc, - context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching, context); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index e4472c6be6c3..3fb4bcc34353 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -271,8 +271,7 @@ static void dccg32_set_dpstreamclk( dccg32_set_dtbclk_p_src(dccg, src, otg_inst); /* enabled to select one of the DTBCLKs for pipe */ - switch (otg_inst) - { + switch (dp_hpo_inst) { case 0: REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK0_EN, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 16f892125b6f..9d14045cccd6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1104,7 +1104,7 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign *k2_div = PIXEL_RATE_DIV_BY_2; else *k2_div = PIXEL_RATE_DIV_BY_4; - } else if (dc_is_dp_signal(stream->signal) || dc_is_virtual_signal(stream->signal)) { + } else if (dc_is_dp_signal(stream->signal)) { if (two_pix_per_container) { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 74e50c09bb62..4b7abb4af623 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1915,6 +1915,7 @@ int dcn32_populate_dml_pipes_from_context( bool subvp_in_use = false; uint8_t is_pipe_split_expected[MAX_PIPES] = {0}; struct dc_crtc_timing *timing; + bool vsr_odm_support = false; dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate); @@ -1932,12 +1933,15 @@ int dcn32_populate_dml_pipes_from_context( timing = &pipe->stream->timing; pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + vsr_odm_support = (res_ctx->pipe_ctx[i].stream->src.width >= 5120 && + res_ctx->pipe_ctx[i].stream->src.width > res_ctx->pipe_ctx[i].stream->dst.width); if (context->stream_count == 1 && context->stream_status[0].plane_count == 1 && !dc_is_hdmi_signal(res_ctx->pipe_ctx[i].stream->signal) && is_h_timing_divisible_by_2(res_ctx->pipe_ctx[i].stream) && pipe->stream->timing.pix_clk_100hz * 100 > DCN3_2_VMIN_DISPCLK_HZ && - dc->debug.enable_single_display_2to1_odm_policy) { + dc->debug.enable_single_display_2to1_odm_policy && + !vsr_odm_support) { //excluding 2to1 ODM combine on >= 5k vsr pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; } pipe_cnt++; @@ -2182,6 +2186,7 @@ static bool dcn32_resource_construct( dc->caps.edp_dsc_support = true; dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; + dc->caps.seamless_odm = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 38216c789d77..f70025ef7b69 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -855,6 +855,7 @@ static bool detect_link_and_local_sink(struct dc_link *link, struct dc_sink *prev_sink = NULL; struct dpcd_caps prev_dpcd_caps; enum dc_connection_type new_connection_type = dc_connection_none; + enum dc_connection_type pre_connection_type = link->type; const uint32_t post_oui_delay = 30; // 30ms DC_LOGGER_INIT(link->ctx->logger); @@ -957,6 +958,8 @@ static bool detect_link_and_local_sink(struct dc_link *link, } if (!detect_dp(link, &sink_caps, reason)) { + link->type = pre_connection_type; + if (prev_sink) dc_sink_release(prev_sink); return false; @@ -1244,11 +1247,16 @@ bool link_detect(struct dc_link *link, enum dc_detect_reason reason) bool is_delegated_to_mst_top_mgr = false; enum dc_connection_type pre_link_type = link->type; + DC_LOGGER_INIT(link->ctx->logger); + is_local_sink_detect_success = detect_link_and_local_sink(link, reason); if (is_local_sink_detect_success && link->local_sink) verify_link_capability(link, link->local_sink, reason); + DC_LOG_DC("%s: link_index=%d is_local_sink_detect_success=%d pre_link_type=%d link_type=%d\n", __func__, + link->link_index, is_local_sink_detect_success, pre_link_type, link->type); + if (is_local_sink_detect_success && link->local_sink && dc_is_dp_signal(link->local_sink->sink_signal) && link->dpcd_caps.is_mst_capable) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h index f77401709d83..2162ecd1057d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h @@ -27,7 +27,7 @@ // *** IMPORTANT *** // SMU TEAM: Always increment the interface version if // any structure is changed in this file -#define PMFW_DRIVER_IF_VERSION 7 +#define PMFW_DRIVER_IF_VERSION 8 typedef struct { int32_t value; @@ -198,7 +198,7 @@ typedef struct { uint16_t SkinTemp; uint16_t DeviceState; uint16_t CurTemp; //[centi-Celsius] - uint16_t spare2; + uint16_t FilterAlphaValue; uint16_t AverageGfxclkFrequency; uint16_t AverageFclkFrequency; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 1c0ae2cb757b..85a090b9e3d9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -29,7 +29,7 @@ #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x08 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37 @@ -61,6 +61,12 @@ #define CTF_OFFSET_HOTSPOT 5 #define CTF_OFFSET_MEM 5 +static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; +static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; + +#define DECODE_GEN_SPEED(gen_speed_idx) (pmfw_decoded_link_speed[gen_speed_idx]) +#define DECODE_LANE_WIDTH(lane_width_idx) (pmfw_decoded_link_width[lane_width_idx]) + struct smu_13_0_max_sustainable_clocks { uint32_t display_clock; uint32_t phy_clock; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 697e98a0a20a..75f18681e984 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2143,16 +2143,9 @@ static int sienna_cichlid_set_default_od_settings(struct smu_context *smu) (OverDriveTable_t *)smu->smu_table.boot_overdrive_table; OverDriveTable_t *user_od_table = (OverDriveTable_t *)smu->smu_table.user_overdrive_table; + OverDriveTable_t user_od_table_bak; int ret = 0; - /* - * For S3/S4/Runpm resume, no need to setup those overdrive tables again as - * - either they already have the default OD settings got during cold bootup - * - or they have some user customized OD settings which cannot be overwritten - */ - if (smu->adev->in_suspend) - return 0; - ret = smu_cmn_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)boot_od_table, false); if (ret) { @@ -2163,7 +2156,23 @@ static int sienna_cichlid_set_default_od_settings(struct smu_context *smu) sienna_cichlid_dump_od_table(smu, boot_od_table); memcpy(od_table, boot_od_table, sizeof(OverDriveTable_t)); - memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t)); + + /* + * For S3/S4/Runpm resume, we need to setup those overdrive tables again, + * but we have to preserve user defined values in "user_od_table". + */ + if (!smu->adev->in_suspend) { + memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t)); + smu->user_dpm_profile.user_od = false; + } else if (smu->user_dpm_profile.user_od) { + memcpy(&user_od_table_bak, user_od_table, sizeof(OverDriveTable_t)); + memcpy(user_od_table, boot_od_table, sizeof(OverDriveTable_t)); + user_od_table->GfxclkFmin = user_od_table_bak.GfxclkFmin; + user_od_table->GfxclkFmax = user_od_table_bak.GfxclkFmax; + user_od_table->UclkFmin = user_od_table_bak.UclkFmin; + user_od_table->UclkFmax = user_od_table_bak.UclkFmax; + user_od_table->VddGfxOffset = user_od_table_bak.VddGfxOffset; + } return 0; } @@ -2373,6 +2382,20 @@ static int sienna_cichlid_od_edit_dpm_table(struct smu_context *smu, return ret; } +static int sienna_cichlid_restore_user_od_settings(struct smu_context *smu) +{ + struct smu_table_context *table_context = &smu->smu_table; + OverDriveTable_t *od_table = table_context->overdrive_table; + OverDriveTable_t *user_od_table = table_context->user_overdrive_table; + int res; + + res = smu_v11_0_restore_user_od_settings(smu); + if (res == 0) + memcpy(od_table, user_od_table, sizeof(OverDriveTable_t)); + + return res; +} + static int sienna_cichlid_run_btc(struct smu_context *smu) { int res; @@ -4400,7 +4423,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, .set_default_od_settings = sienna_cichlid_set_default_od_settings, .od_edit_dpm_table = sienna_cichlid_od_edit_dpm_table, - .restore_user_od_settings = smu_v11_0_restore_user_od_settings, + .restore_user_od_settings = sienna_cichlid_restore_user_od_settings, .run_btc = sienna_cichlid_run_btc, .set_power_source = smu_v11_0_set_power_source, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 923a9fb3c887..a5c97d61e92a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -46,6 +46,7 @@ #include "asic_reg/mp/mp_13_0_0_sh_mask.h" #include "smu_cmn.h" #include "amdgpu_ras.h" +#include "umc_v8_10.h" /* * DO NOT use these for err/warn/info/debug messages. @@ -90,6 +91,12 @@ #define DEBUGSMC_MSG_Mode1Reset 2 +/* + * SMU_v13_0_10 supports ECCTABLE since version 80.34.0, + * use this to check ECCTABLE feature whether support + */ +#define SUPPORT_ECCTABLE_SMU_13_0_10_VERSION 0x00502200 + static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 1), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 1), @@ -229,6 +236,7 @@ static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = { TAB_MAP(ACTIVITY_MONITOR_COEFF), [SMU_TABLE_COMBO_PPTABLE] = {1, TABLE_COMBO_PPTABLE}, TAB_MAP(I2C_COMMANDS), + TAB_MAP(ECCINFO), }; static struct cmn2asic_mapping smu_v13_0_0_pwr_src_map[SMU_POWER_SOURCE_COUNT] = { @@ -462,6 +470,8 @@ static int smu_v13_0_0_tables_init(struct smu_context *smu) AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_COMBO_PPTABLE, MP0_MP1_DATA_REGION_SIZE_COMBOPPTABLE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); + SMU_TABLE_INIT(tables, SMU_TABLE_ECCINFO, sizeof(EccInfoTable_t), + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); smu_table->metrics_table = kzalloc(sizeof(SmuMetricsExternal_t), GFP_KERNEL); if (!smu_table->metrics_table) @@ -477,8 +487,14 @@ static int smu_v13_0_0_tables_init(struct smu_context *smu) if (!smu_table->watermarks_table) goto err2_out; + smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL); + if (!smu_table->ecc_table) + goto err3_out; + return 0; +err3_out: + kfree(smu_table->watermarks_table); err2_out: kfree(smu_table->gpu_metrics_table); err1_out: @@ -1128,8 +1144,8 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - ((gen_speed - 1) == pcie_table->pcie_gen[i]) && - (lane_width == link_width[pcie_table->pcie_lane[i]]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? "*" : ""); break; @@ -2036,6 +2052,64 @@ static int smu_v13_0_0_send_bad_mem_channel_flag(struct smu_context *smu, return ret; } +static int smu_v13_0_0_check_ecc_table_support(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t if_version = 0xff, smu_version = 0xff; + int ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); + if (ret) + return -EOPNOTSUPP; + + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 10)) && + (smu_version >= SUPPORT_ECCTABLE_SMU_13_0_10_VERSION)) + return ret; + else + return -EOPNOTSUPP; +} + +static ssize_t smu_v13_0_0_get_ecc_info(struct smu_context *smu, + void *table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct amdgpu_device *adev = smu->adev; + EccInfoTable_t *ecc_table = NULL; + struct ecc_info_per_ch *ecc_info_per_channel = NULL; + int i, ret = 0; + struct umc_ecc_info *eccinfo = (struct umc_ecc_info *)table; + + ret = smu_v13_0_0_check_ecc_table_support(smu); + if (ret) + return ret; + + ret = smu_cmn_update_table(smu, + SMU_TABLE_ECCINFO, + 0, + smu_table->ecc_table, + false); + if (ret) { + dev_info(adev->dev, "Failed to export SMU ecc table!\n"); + return ret; + } + + ecc_table = (EccInfoTable_t *)smu_table->ecc_table; + + for (i = 0; i < UMC_V8_10_TOTAL_CHANNEL_NUM(adev); i++) { + ecc_info_per_channel = &(eccinfo->ecc[i]); + ecc_info_per_channel->ce_count_lo_chip = + ecc_table->EccInfo[i].ce_count_lo_chip; + ecc_info_per_channel->ce_count_hi_chip = + ecc_table->EccInfo[i].ce_count_hi_chip; + ecc_info_per_channel->mca_umc_status = + ecc_table->EccInfo[i].mca_umc_status; + ecc_info_per_channel->mca_umc_addr = + ecc_table->EccInfo[i].mca_umc_addr; + } + + return ret; +} + static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .get_allowed_feature_mask = smu_v13_0_0_get_allowed_feature_mask, .set_default_dpm_table = smu_v13_0_0_set_default_dpm_table, @@ -2111,6 +2185,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .send_hbm_bad_pages_num = smu_v13_0_0_smu_send_bad_mem_page_num, .send_hbm_bad_channel_flag = smu_v13_0_0_send_bad_mem_channel_flag, .gpo_control = smu_v13_0_gpo_control, + .get_ecc_info = smu_v13_0_0_get_ecc_info, }; void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 9e1967d8049e..4399416dd9b8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -575,6 +575,14 @@ static int smu_v13_0_7_set_default_dpm_table(struct smu_context *smu) dpm_table); if (ret) return ret; + + if (skutable->DriverReportedClocks.GameClockAc && + (dpm_table->dpm_levels[dpm_table->count - 1].value > + skutable->DriverReportedClocks.GameClockAc)) { + dpm_table->dpm_levels[dpm_table->count - 1].value = + skutable->DriverReportedClocks.GameClockAc; + dpm_table->max = skutable->DriverReportedClocks.GameClockAc; + } } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; @@ -828,6 +836,57 @@ static int smu_v13_0_7_get_smu_metrics_data(struct smu_context *smu, return ret; } +static int smu_v13_0_7_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + struct smu_13_0_dpm_context *dpm_context = + smu->smu_dpm.dpm_context; + struct smu_13_0_dpm_table *dpm_table; + + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + /* uclk dpm table */ + dpm_table = &dpm_context->dpm_tables.uclk_table; + break; + case SMU_GFXCLK: + case SMU_SCLK: + /* gfxclk dpm table */ + dpm_table = &dpm_context->dpm_tables.gfx_table; + break; + case SMU_SOCCLK: + /* socclk dpm table */ + dpm_table = &dpm_context->dpm_tables.soc_table; + break; + case SMU_FCLK: + /* fclk dpm table */ + dpm_table = &dpm_context->dpm_tables.fclk_table; + break; + case SMU_VCLK: + case SMU_VCLK1: + /* vclk dpm table */ + dpm_table = &dpm_context->dpm_tables.vclk_table; + break; + case SMU_DCLK: + case SMU_DCLK1: + /* dclk dpm table */ + dpm_table = &dpm_context->dpm_tables.dclk_table; + break; + default: + dev_err(smu->adev->dev, "Unsupported clock type!\n"); + return -EINVAL; + } + + if (min) + *min = dpm_table->min; + if (max) + *max = dpm_table->max; + + return 0; +} + static int smu_v13_0_7_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, @@ -1074,8 +1133,8 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu, (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - (gen_speed == pcie_table->pcie_gen[i]) && - (lane_width == pcie_table->pcie_lane[i]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break; @@ -1329,9 +1388,17 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) &dpm_context->dpm_tables.fclk_table; struct smu_umd_pstate_table *pstate_table = &smu->pstate_table; + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *pptable = table_context->driver_pptable; + DriverReportedClocks_t driver_clocks = + pptable->SkuTable.DriverReportedClocks; pstate_table->gfxclk_pstate.min = gfx_table->min; - pstate_table->gfxclk_pstate.peak = gfx_table->max; + if (driver_clocks.GameClockAc && + (driver_clocks.GameClockAc < gfx_table->max)) + pstate_table->gfxclk_pstate.peak = driver_clocks.GameClockAc; + else + pstate_table->gfxclk_pstate.peak = gfx_table->max; pstate_table->uclk_pstate.min = mem_table->min; pstate_table->uclk_pstate.peak = mem_table->max; @@ -1348,12 +1415,12 @@ static int smu_v13_0_7_populate_umd_state_clk(struct smu_context *smu) pstate_table->fclk_pstate.min = fclk_table->min; pstate_table->fclk_pstate.peak = fclk_table->max; - /* - * For now, just use the mininum clock frequency. - * TODO: update them when the real pstate settings available - */ - pstate_table->gfxclk_pstate.standard = gfx_table->min; - pstate_table->uclk_pstate.standard = mem_table->min; + if (driver_clocks.BaseClockAc && + driver_clocks.BaseClockAc < gfx_table->max) + pstate_table->gfxclk_pstate.standard = driver_clocks.BaseClockAc; + else + pstate_table->gfxclk_pstate.standard = gfx_table->max; + pstate_table->uclk_pstate.standard = mem_table->max; pstate_table->socclk_pstate.standard = soc_table->min; pstate_table->vclk_pstate.standard = vclk_table->min; pstate_table->dclk_pstate.standard = dclk_table->min; @@ -1676,7 +1743,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .dpm_set_jpeg_enable = smu_v13_0_set_jpeg_enable, .init_pptable_microcode = smu_v13_0_init_pptable_microcode, .populate_umd_state_clk = smu_v13_0_7_populate_umd_state_clk, - .get_dpm_ultimate_freq = smu_v13_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v13_0_7_get_dpm_ultimate_freq, .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .read_sensor = smu_v13_0_7_read_sensor, .feature_is_enabled = smu_cmn_feature_is_enabled, diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 0643887800b4..142668cd6d7c 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -99,7 +99,6 @@ static int armada_drm_bind(struct device *dev) if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); - kfree(priv); return ret; } diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 2019a8167d69..b40baced1331 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -676,8 +676,8 @@ static int lt8912_parse_dt(struct lt8912 *lt) lt->hdmi_port = of_drm_find_bridge(port_node); if (!lt->hdmi_port) { - dev_err(lt->dev, "%s: Failed to get hdmi port\n", __func__); - ret = -ENODEV; + ret = -EPROBE_DEFER; + dev_err_probe(lt->dev, ret, "%s: Failed to get hdmi port\n", __func__); goto err_free_host_node; } diff --git a/drivers/gpu/drm/display/drm_hdmi_helper.c b/drivers/gpu/drm/display/drm_hdmi_helper.c index 0264abe55278..faf5e9efa7d3 100644 --- a/drivers/gpu/drm/display/drm_hdmi_helper.c +++ b/drivers/gpu/drm/display/drm_hdmi_helper.c @@ -44,10 +44,8 @@ int drm_hdmi_infoframe_set_hdr_metadata(struct hdmi_drm_infoframe *frame, /* Sink EOTF is Bit map while infoframe is absolute values */ if (!is_eotf_supported(hdr_metadata->hdmi_metadata_type1.eotf, - connector->hdr_sink_metadata.hdmi_type1.eotf)) { - DRM_DEBUG_KMS("EOTF Not Supported\n"); - return -EINVAL; - } + connector->hdr_sink_metadata.hdmi_type1.eotf)) + DRM_DEBUG_KMS("Unknown EOTF %d\n", hdr_metadata->hdmi_metadata_type1.eotf); err = hdmi_drm_infoframe_init(frame); if (err < 0) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 5457c02ca1ab..fed41800fea7 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1070,6 +1070,7 @@ static void drm_atomic_connector_print_state(struct drm_printer *p, drm_printf(p, "connector[%u]: %s\n", connector->base.id, connector->name); drm_printf(p, "\tcrtc=%s\n", state->crtc ? state->crtc->name : "(null)"); drm_printf(p, "\tself_refresh_aware=%d\n", state->self_refresh_aware); + drm_printf(p, "\tmax_requested_bpc=%d\n", state->max_requested_bpc); if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) if (state->writeback_job && state->writeback_job->fb) diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 3d1f50f481cf..7098f125b54a 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -146,8 +146,8 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) unsigned int order; u64 root_size; - root_size = rounddown_pow_of_two(size); - order = ilog2(root_size) - ilog2(chunk_size); + order = ilog2(size) - ilog2(chunk_size); + root_size = chunk_size << order; root = drm_block_alloc(mm, NULL, order, offset); if (!root) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 3d0a4da661bc..261a62e15934 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2796,7 +2796,7 @@ u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) * the EDID then we'll just return 0. */ - base_block = kmalloc(EDID_LENGTH, GFP_KERNEL); + base_block = kzalloc(EDID_LENGTH, GFP_KERNEL); if (!base_block) return 0; diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 7a3cb08dc942..a5d392f7e11f 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1388,10 +1388,13 @@ EXPORT_SYMBOL(drm_gem_lru_move_tail); * * @lru: The LRU to scan * @nr_to_scan: The number of pages to try to reclaim + * @remaining: The number of pages left to reclaim, should be initialized by caller * @shrink: Callback to try to shrink/reclaim the object. */ unsigned long -drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned nr_to_scan, +drm_gem_lru_scan(struct drm_gem_lru *lru, + unsigned int nr_to_scan, + unsigned long *remaining, bool (*shrink)(struct drm_gem_object *obj)) { struct drm_gem_lru still_in_lru; @@ -1430,8 +1433,10 @@ drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned nr_to_scan, * hit shrinker in response to trying to get backing pages * for this obj (ie. while it's lock is already held) */ - if (!dma_resv_trylock(obj->resv)) + if (!dma_resv_trylock(obj->resv)) { + *remaining += obj->size >> PAGE_SHIFT; goto tail; + } if (shrink(obj)) { freed += obj->size >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 75185a960fc4..2b2163c8138e 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -619,11 +619,14 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct int ret; if (obj->import_attach) { - /* Drop the reference drm_gem_mmap_obj() acquired.*/ - drm_gem_object_put(obj); vma->vm_private_data = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); + + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + if (!ret) + drm_gem_object_put(obj); - return dma_buf_mmap(obj->dma_buf, vma, 0); + return ret; } ret = drm_gem_shmem_get_pages(shmem); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 5522d610c5cf..b1a38e6ce2f8 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -328,10 +328,17 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, - }, { /* Lenovo Yoga Book X90F / X91F / X91L */ + }, { /* Lenovo Yoga Book X90F / X90L */ .matches = { - /* Non exact match to match all versions */ - DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"), + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Yoga Book X91F / X91L */ + .matches = { + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* Lenovo Yoga Tablet 2 830F / 830L */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 44ca803237a5..31a7f59ccb49 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -22,7 +22,6 @@ #include "etnaviv_gem.h" #include "etnaviv_mmu.h" #include "etnaviv_perfmon.h" -#include "common.xml.h" /* * DRM operations: @@ -476,47 +475,7 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = { ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW), }; -static void etnaviv_fop_show_fdinfo(struct seq_file *m, struct file *f) -{ - struct drm_file *file = f->private_data; - struct drm_device *dev = file->minor->dev; - struct etnaviv_drm_private *priv = dev->dev_private; - struct etnaviv_file_private *ctx = file->driver_priv; - - /* - * For a description of the text output format used here, see - * Documentation/gpu/drm-usage-stats.rst. - */ - seq_printf(m, "drm-driver:\t%s\n", dev->driver->name); - seq_printf(m, "drm-client-id:\t%u\n", ctx->id); - - for (int i = 0; i < ETNA_MAX_PIPES; i++) { - struct etnaviv_gpu *gpu = priv->gpu[i]; - char engine[10] = "UNK"; - int cur = 0; - - if (!gpu) - continue; - - if (gpu->identity.features & chipFeatures_PIPE_2D) - cur = snprintf(engine, sizeof(engine), "2D"); - if (gpu->identity.features & chipFeatures_PIPE_3D) - cur = snprintf(engine + cur, sizeof(engine) - cur, - "%s3D", cur ? "/" : ""); - if (gpu->identity.nn_core_count > 0) - cur = snprintf(engine + cur, sizeof(engine) - cur, - "%sNN", cur ? "/" : ""); - - seq_printf(m, "drm-engine-%s:\t%llu ns\n", engine, - ctx->sched_entity[i].elapsed_ns); - } -} - -static const struct file_operations fops = { - .owner = THIS_MODULE, - DRM_GEM_FOPS, - .show_fdinfo = etnaviv_fop_show_fdinfo, -}; +DEFINE_DRM_GEM_FOPS(fops); static const struct drm_driver etnaviv_drm_driver = { .driver_features = DRIVER_GEM | DRIVER_RENDER, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index 7031db145a77..3524b5811682 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -91,7 +91,15 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj, struct vm_area_struct *vma) { - return dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + int ret; + + ret = dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + if (!ret) { + /* Drop the reference acquired by drm_gem_mmap_obj(). */ + drm_gem_object_put(&etnaviv_obj->base); + } + + return ret; } static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = { diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 468a792e6a40..fc0eaf40dc94 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -300,9 +300,21 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + i915_reg_t dss_ctl1_reg, dss_ctl2_reg; u32 dss_ctl1; - dss_ctl1 = intel_de_read(dev_priv, DSS_CTL1); + /* FIXME: Move all DSS handling to intel_vdsc.c */ + if (DISPLAY_VER(dev_priv) >= 12) { + struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); + + dss_ctl1_reg = ICL_PIPE_DSS_CTL1(crtc->pipe); + dss_ctl2_reg = ICL_PIPE_DSS_CTL2(crtc->pipe); + } else { + dss_ctl1_reg = DSS_CTL1; + dss_ctl2_reg = DSS_CTL2; + } + + dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg); dss_ctl1 |= SPLITTER_ENABLE; dss_ctl1 &= ~OVERLAP_PIXELS_MASK; dss_ctl1 |= OVERLAP_PIXELS(intel_dsi->pixel_overlap); @@ -323,16 +335,16 @@ static void configure_dual_link_mode(struct intel_encoder *encoder, dss_ctl1 &= ~LEFT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl1 |= LEFT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - dss_ctl2 = intel_de_read(dev_priv, DSS_CTL2); + dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg); dss_ctl2 &= ~RIGHT_DL_BUF_TARGET_DEPTH_MASK; dss_ctl2 |= RIGHT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); - intel_de_write(dev_priv, DSS_CTL2, dss_ctl2); + intel_de_write(dev_priv, dss_ctl2_reg, dss_ctl2); } else { /* Interleave */ dss_ctl1 |= DUAL_LINK_MODE_INTERLEAVE; } - intel_de_write(dev_priv, DSS_CTL1, dss_ctl1); + intel_de_write(dev_priv, dss_ctl1_reg, dss_ctl1); } /* aka DSI 8X clock */ diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 8d97c299e657..bd598a7f5047 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -47,6 +47,11 @@ struct intel_color_funcs { */ void (*color_commit_arm)(const struct intel_crtc_state *crtc_state); /* + * Perform any extra tasks needed after all the + * double buffered registers have been latched. + */ + void (*color_post_update)(const struct intel_crtc_state *crtc_state); + /* * Load LUTs (and other single buffered color management * registers). Will (hopefully) be called during the vblank * following the latching of any double buffered registers @@ -614,9 +619,33 @@ static void ilk_lut_12p4_pack(struct drm_color_lut *entry, u32 ldw, u32 udw) static void icl_color_commit_noarm(const struct intel_crtc_state *crtc_state) { + /* + * Despite Wa_1406463849, ICL no longer suffers from the SKL + * DC5/PSR CSC black screen issue (see skl_color_commit_noarm()). + * Possibly due to the extra sticky CSC arming + * (see icl_color_post_update()). + * + * On TGL+ all CSC arming issues have been properly fixed. + */ icl_load_csc_matrix(crtc_state); } +static void skl_color_commit_noarm(const struct intel_crtc_state *crtc_state) +{ + /* + * Possibly related to display WA #1184, SKL CSC loses the latched + * CSC coeff/offset register values if the CSC registers are disarmed + * between DC5 exit and PSR exit. This will cause the plane(s) to + * output all black (until CSC_MODE is rearmed and properly latched). + * Once PSR exit (and proper register latching) has occurred the + * danger is over. Thus when PSR is enabled the CSC coeff/offset + * register programming will be peformed from skl_color_commit_arm() + * which is called after PSR exit. + */ + if (!crtc_state->has_psr) + ilk_load_csc_matrix(crtc_state); +} + static void ilk_color_commit_noarm(const struct intel_crtc_state *crtc_state) { ilk_load_csc_matrix(crtc_state); @@ -659,6 +688,9 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state) enum pipe pipe = crtc->pipe; u32 val = 0; + if (crtc_state->has_psr) + ilk_load_csc_matrix(crtc_state); + /* * We don't (yet) allow userspace to control the pipe background color, * so force it to black, but apply pipe gamma and CSC appropriately @@ -677,6 +709,47 @@ static void skl_color_commit_arm(const struct intel_crtc_state *crtc_state) crtc_state->csc_mode); } +static void icl_color_commit_arm(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); + enum pipe pipe = crtc->pipe; + + /* + * We don't (yet) allow userspace to control the pipe background color, + * so force it to black. + */ + intel_de_write(i915, SKL_BOTTOM_COLOR(pipe), 0); + + intel_de_write(i915, GAMMA_MODE(crtc->pipe), + crtc_state->gamma_mode); + + intel_de_write_fw(i915, PIPE_CSC_MODE(crtc->pipe), + crtc_state->csc_mode); +} + +static void icl_color_post_update(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); + + /* + * Despite Wa_1406463849, ICL CSC is no longer disarmed by + * coeff/offset register *writes*. Instead, once CSC_MODE + * is armed it stays armed, even after it has been latched. + * Afterwards the coeff/offset registers become effectively + * self-arming. That self-arming must be disabled before the + * next icl_color_commit_noarm() tries to write the next set + * of coeff/offset registers. Fortunately register *reads* + * do still disarm the CSC. Naturally this must not be done + * until the previously written CSC registers have actually + * been latched. + * + * TGL+ no longer need this workaround. + */ + intel_de_read_fw(i915, PIPE_CSC_PREOFF_HI(crtc->pipe)); +} + static struct drm_property_blob * create_linear_lut(struct drm_i915_private *i915, int lut_size) { @@ -1373,6 +1446,14 @@ void intel_color_commit_arm(const struct intel_crtc_state *crtc_state) i915->display.funcs.color->color_commit_arm(crtc_state); } +void intel_color_post_update(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + + if (i915->display.funcs.color->color_post_update) + i915->display.funcs.color->color_post_update(crtc_state); +} + void intel_color_prepare_commit(struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -3064,10 +3145,20 @@ static const struct intel_color_funcs i9xx_color_funcs = { .lut_equal = i9xx_lut_equal, }; +static const struct intel_color_funcs tgl_color_funcs = { + .color_check = icl_color_check, + .color_commit_noarm = icl_color_commit_noarm, + .color_commit_arm = icl_color_commit_arm, + .load_luts = icl_load_luts, + .read_luts = icl_read_luts, + .lut_equal = icl_lut_equal, +}; + static const struct intel_color_funcs icl_color_funcs = { .color_check = icl_color_check, .color_commit_noarm = icl_color_commit_noarm, - .color_commit_arm = skl_color_commit_arm, + .color_commit_arm = icl_color_commit_arm, + .color_post_update = icl_color_post_update, .load_luts = icl_load_luts, .read_luts = icl_read_luts, .lut_equal = icl_lut_equal, @@ -3075,7 +3166,7 @@ static const struct intel_color_funcs icl_color_funcs = { static const struct intel_color_funcs glk_color_funcs = { .color_check = glk_color_check, - .color_commit_noarm = ilk_color_commit_noarm, + .color_commit_noarm = skl_color_commit_noarm, .color_commit_arm = skl_color_commit_arm, .load_luts = glk_load_luts, .read_luts = glk_read_luts, @@ -3084,7 +3175,7 @@ static const struct intel_color_funcs glk_color_funcs = { static const struct intel_color_funcs skl_color_funcs = { .color_check = ivb_color_check, - .color_commit_noarm = ilk_color_commit_noarm, + .color_commit_noarm = skl_color_commit_noarm, .color_commit_arm = skl_color_commit_arm, .load_luts = bdw_load_luts, .read_luts = bdw_read_luts, @@ -3180,7 +3271,9 @@ void intel_color_init_hooks(struct drm_i915_private *i915) else i915->display.funcs.color = &i9xx_color_funcs; } else { - if (DISPLAY_VER(i915) >= 11) + if (DISPLAY_VER(i915) >= 12) + i915->display.funcs.color = &tgl_color_funcs; + else if (DISPLAY_VER(i915) == 11) i915->display.funcs.color = &icl_color_funcs; else if (DISPLAY_VER(i915) == 10) i915->display.funcs.color = &glk_color_funcs; diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h index d620b5b1e2a6..8002492be709 100644 --- a/drivers/gpu/drm/i915/display/intel_color.h +++ b/drivers/gpu/drm/i915/display/intel_color.h @@ -21,6 +21,7 @@ void intel_color_prepare_commit(struct intel_crtc_state *crtc_state); void intel_color_cleanup_commit(struct intel_crtc_state *crtc_state); void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state); void intel_color_commit_arm(const struct intel_crtc_state *crtc_state); +void intel_color_post_update(const struct intel_crtc_state *crtc_state); void intel_color_load_luts(const struct intel_crtc_state *crtc_state); void intel_color_get_config(struct intel_crtc_state *crtc_state); bool intel_color_lut_equal(const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c index 82be0fbe9934..d5b5d40ed817 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc.c +++ b/drivers/gpu/drm/i915/display/intel_crtc.c @@ -683,6 +683,14 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) */ intel_vrr_send_push(new_crtc_state); + /* + * Seamless M/N update may need to update frame timings. + * + * FIXME Should be synchronized with the start of vblank somehow... + */ + if (new_crtc_state->seamless_m_n && intel_crtc_needs_fastset(new_crtc_state)) + intel_crtc_update_active_timings(new_crtc_state); + local_irq_enable(); if (intel_vgpu_active(dev_priv)) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index d3994e2a7d63..63b4b73f47c6 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1209,6 +1209,9 @@ static void intel_post_plane_update(struct intel_atomic_state *state, if (needs_cursorclk_wa(old_crtc_state) && !needs_cursorclk_wa(new_crtc_state)) icl_wa_cursorclkgating(dev_priv, pipe, false); + + if (intel_crtc_needs_color_update(new_crtc_state)) + intel_color_post_update(new_crtc_state); } static void intel_crtc_enable_flip_done(struct intel_atomic_state *state, @@ -5145,6 +5148,7 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state, * only fields that are know to not cause problems are preserved. */ saved_state->uapi = crtc_state->uapi; + saved_state->inherited = crtc_state->inherited; saved_state->scaler_state = crtc_state->scaler_state; saved_state->shared_dpll = crtc_state->shared_dpll; saved_state->dpll_hw_state = crtc_state->dpll_hw_state; @@ -7090,6 +7094,8 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_fbc_update(state, crtc); + drm_WARN_ON(&i915->drm, !intel_display_power_is_enabled(i915, POWER_DOMAIN_DC_OFF)); + if (!modeset && intel_crtc_needs_color_update(new_crtc_state)) intel_color_commit_noarm(new_crtc_state); @@ -7457,8 +7463,28 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) drm_atomic_helper_wait_for_dependencies(&state->base); drm_dp_mst_atomic_wait_for_dependencies(&state->base); - if (state->modeset) - wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET); + /* + * During full modesets we write a lot of registers, wait + * for PLLs, etc. Doing that while DC states are enabled + * is not a good idea. + * + * During fastsets and other updates we also need to + * disable DC states due to the following scenario: + * 1. DC5 exit and PSR exit happen + * 2. Some or all _noarm() registers are written + * 3. Due to some long delay PSR is re-entered + * 4. DC5 entry -> DMC saves the already written new + * _noarm() registers and the old not yet written + * _arm() registers + * 5. DC5 exit -> DMC restores a mixture of old and + * new register values and arms the update + * 6. PSR exit -> hardware latches a mixture of old and + * new register values -> corrupted frame, or worse + * 7. New _arm() registers are finally written + * 8. Hardware finally latches a complete set of new + * register values, and subsequent frames will be OK again + */ + wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_DC_OFF); intel_atomic_prepare_plane_clear_colors(state); @@ -7607,8 +7633,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * the culprit. */ intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore); - intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET, wakeref); } + intel_display_power_put(dev_priv, POWER_DOMAIN_DC_OFF, wakeref); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); /* diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 54c517ca9632..582234f0c49a 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1631,6 +1631,8 @@ struct intel_psr { bool psr2_sel_fetch_cff_enabled; bool req_psr2_sdp_prior_scanline; u8 sink_sync_latency; + u8 io_wake_lines; + u8 fast_wake_lines; ktime_t last_entry_attempt; ktime_t last_exit; bool sink_not_reliable; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 257aa2b7cf20..3485d5e6dd3c 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -384,15 +384,12 @@ static void disable_all_event_handlers(struct drm_i915_private *i915) } } -static void pipedmc_clock_gating_wa(struct drm_i915_private *i915, bool enable) +static void adlp_pipedmc_clock_gating_wa(struct drm_i915_private *i915, bool enable) { enum pipe pipe; - if (DISPLAY_VER(i915) < 13) - return; - /* - * Wa_16015201720:adl-p,dg2, mtl + * Wa_16015201720:adl-p,dg2 * The WA requires clock gating to be disabled all the time * for pipe A and B. * For pipe C and D clock gating needs to be disabled only @@ -408,6 +405,25 @@ static void pipedmc_clock_gating_wa(struct drm_i915_private *i915, bool enable) PIPEDMC_GATING_DIS, 0); } +static void mtl_pipedmc_clock_gating_wa(struct drm_i915_private *i915) +{ + /* + * Wa_16015201720 + * The WA requires clock gating to be disabled all the time + * for pipe A and B. + */ + intel_de_rmw(i915, GEN9_CLKGATE_DIS_0, 0, + MTL_PIPEDMC_GATING_DIS_A | MTL_PIPEDMC_GATING_DIS_B); +} + +static void pipedmc_clock_gating_wa(struct drm_i915_private *i915, bool enable) +{ + if (DISPLAY_VER(i915) >= 14 && enable) + mtl_pipedmc_clock_gating_wa(i915); + else if (DISPLAY_VER(i915) == 13) + adlp_pipedmc_clock_gating_wa(i915, enable); +} + void intel_dmc_enable_pipe(struct drm_i915_private *i915, enum pipe pipe) { if (!has_dmc_id_fw(i915, PIPE_TO_DMC_ID(pipe))) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 054a009e800d..7c9b328bc2d7 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -232,7 +232,7 @@ static int intel_dp_dsc_mst_compute_link_config(struct intel_encoder *encoder, return slots; } - intel_link_compute_m_n(crtc_state->pipe_bpp, + intel_link_compute_m_n(crtc_state->dsc.compressed_bpp, crtc_state->lane_count, adjusted_mode->crtc_clock, crtc_state->port_clock, @@ -265,6 +265,19 @@ static int intel_dp_mst_update_slots(struct intel_encoder *encoder, return 0; } +static bool intel_dp_mst_has_audio(const struct drm_connector_state *conn_state) +{ + const struct intel_digital_connector_state *intel_conn_state = + to_intel_digital_connector_state(conn_state); + struct intel_connector *connector = + to_intel_connector(conn_state->connector); + + if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) + return connector->port->has_audio; + else + return intel_conn_state->force_audio == HDMI_AUDIO_ON; +} + static int intel_dp_mst_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) @@ -272,10 +285,6 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder, 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; - struct intel_connector *connector = - to_intel_connector(conn_state->connector); - struct intel_digital_connector_state *intel_conn_state = - to_intel_digital_connector_state(conn_state); const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; struct link_config_limits limits; @@ -287,11 +296,9 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder, pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; pipe_config->has_pch_encoder = false; - if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO) - pipe_config->has_audio = connector->port->has_audio; - else - pipe_config->has_audio = - intel_conn_state->force_audio == HDMI_AUDIO_ON; + pipe_config->has_audio = + intel_dp_mst_has_audio(conn_state) && + intel_audio_compute_config(encoder, pipe_config, conn_state); /* * for MST we always configure max link bw - the spec doesn't diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index ad1a37b515fb..2a9f40a2b3ed 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -301,6 +301,7 @@ intel_dpt_create(struct intel_framebuffer *fb) vm->pte_encode = gen8_ggtt_pte_encode; dpt->obj = dpt_obj; + dpt->obj->is_dpt = true; return &dpt->vm; } @@ -309,5 +310,6 @@ void intel_dpt_destroy(struct i915_address_space *vm) { struct i915_dpt *dpt = i915_vm_to_dpt(vm); + dpt->obj->is_dpt = false; i915_vm_put(&dpt->vm); } diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index f76b06293eb9..38825b30db16 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -210,6 +210,7 @@ static int intelfb_create(struct drm_fb_helper *helper, bool prealloc = false; void __iomem *vaddr; struct drm_i915_gem_object *obj; + struct i915_gem_ww_ctx ww; int ret; mutex_lock(&ifbdev->hpd_lock); @@ -283,13 +284,24 @@ static int intelfb_create(struct drm_fb_helper *helper, info->fix.smem_len = vma->size; } - vaddr = i915_vma_pin_iomap(vma); - if (IS_ERR(vaddr)) { - drm_err(&dev_priv->drm, - "Failed to remap framebuffer into virtual memory (%pe)\n", vaddr); - ret = PTR_ERR(vaddr); - goto out_unpin; + for_i915_gem_ww(&ww, ret, false) { + ret = i915_gem_object_lock(vma->obj, &ww); + + if (ret) + continue; + + vaddr = i915_vma_pin_iomap(vma); + if (IS_ERR(vaddr)) { + drm_err(&dev_priv->drm, + "Failed to remap framebuffer into virtual memory (%pe)\n", vaddr); + ret = PTR_ERR(vaddr); + continue; + } } + + if (ret) + goto out_unpin; + info->screen_base = vaddr; info->screen_size = vma->size; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 7a72e15e6836..9f1a0bebae24 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -542,6 +542,14 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) val |= EDP_PSR2_FRAME_BEFORE_SU(max_t(u8, intel_dp->psr.sink_sync_latency + 1, 2)); val |= intel_psr2_get_tp_time(intel_dp); + if (DISPLAY_VER(dev_priv) >= 12) { + if (intel_dp->psr.io_wake_lines < 9 && + intel_dp->psr.fast_wake_lines < 9) + val |= TGL_EDP_PSR2_BLOCK_COUNT_NUM_2; + else + val |= TGL_EDP_PSR2_BLOCK_COUNT_NUM_3; + } + /* Wa_22012278275:adl-p */ if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_E0)) { static const u8 map[] = { @@ -558,31 +566,21 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) * Still using the default IO_BUFFER_WAKE and FAST_WAKE, see * comments bellow for more information */ - u32 tmp, lines = 7; - - val |= TGL_EDP_PSR2_BLOCK_COUNT_NUM_2; + u32 tmp; - tmp = map[lines - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES]; + tmp = map[intel_dp->psr.io_wake_lines - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES]; tmp = tmp << TGL_EDP_PSR2_IO_BUFFER_WAKE_SHIFT; val |= tmp; - tmp = map[lines - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES]; + tmp = map[intel_dp->psr.fast_wake_lines - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES]; tmp = tmp << TGL_EDP_PSR2_FAST_WAKE_MIN_SHIFT; val |= tmp; } else if (DISPLAY_VER(dev_priv) >= 12) { - /* - * TODO: 7 lines of IO_BUFFER_WAKE and FAST_WAKE are default - * values from BSpec. In order to setting an optimal power - * consumption, lower than 4k resolution mode needs to decrease - * IO_BUFFER_WAKE and FAST_WAKE. And higher than 4K resolution - * mode needs to increase IO_BUFFER_WAKE and FAST_WAKE. - */ - val |= TGL_EDP_PSR2_BLOCK_COUNT_NUM_2; - val |= TGL_EDP_PSR2_IO_BUFFER_WAKE(7); - val |= TGL_EDP_PSR2_FAST_WAKE(7); + val |= TGL_EDP_PSR2_IO_BUFFER_WAKE(intel_dp->psr.io_wake_lines); + val |= TGL_EDP_PSR2_FAST_WAKE(intel_dp->psr.fast_wake_lines); } else if (DISPLAY_VER(dev_priv) >= 9) { - val |= EDP_PSR2_IO_BUFFER_WAKE(7); - val |= EDP_PSR2_FAST_WAKE(7); + val |= EDP_PSR2_IO_BUFFER_WAKE(intel_dp->psr.io_wake_lines); + val |= EDP_PSR2_FAST_WAKE(intel_dp->psr.fast_wake_lines); } if (intel_dp->psr.req_psr2_sdp_prior_scanline) @@ -842,6 +840,46 @@ static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_d return true; } +static bool _compute_psr2_wake_times(struct intel_dp *intel_dp, + struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + int io_wake_lines, io_wake_time, fast_wake_lines, fast_wake_time; + u8 max_wake_lines; + + if (DISPLAY_VER(i915) >= 12) { + io_wake_time = 42; + /* + * According to Bspec it's 42us, but based on testing + * it is not enough -> use 45 us. + */ + fast_wake_time = 45; + max_wake_lines = 12; + } else { + io_wake_time = 50; + fast_wake_time = 32; + max_wake_lines = 8; + } + + io_wake_lines = intel_usecs_to_scanlines( + &crtc_state->uapi.adjusted_mode, io_wake_time); + fast_wake_lines = intel_usecs_to_scanlines( + &crtc_state->uapi.adjusted_mode, fast_wake_time); + + if (io_wake_lines > max_wake_lines || + fast_wake_lines > max_wake_lines) + return false; + + if (i915->params.psr_safest_params) + io_wake_lines = fast_wake_lines = max_wake_lines; + + /* According to Bspec lower limit should be set as 7 lines. */ + intel_dp->psr.io_wake_lines = max(io_wake_lines, 7); + intel_dp->psr.fast_wake_lines = max(fast_wake_lines, 7); + + return true; +} + static bool intel_psr2_config_valid(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state) { @@ -936,6 +974,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + if (!_compute_psr2_wake_times(intel_dp, crtc_state)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, Unable to use long enough wake times\n"); + return false; + } + if (HAS_PSR2_SEL_FETCH(dev_priv)) { if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) && !HAS_PSR_HW_TRACKING(dev_priv)) { diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index c65c771f5c46..1cfb94b5cedb 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -1419,6 +1419,36 @@ static const struct intel_mpllb_state dg2_hdmi_262750 = { REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), }; +static const struct intel_mpllb_state dg2_hdmi_267300 = { + .clock = 267300, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 74) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 30146) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 36699), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + static const struct intel_mpllb_state dg2_hdmi_268500 = { .clock = 268500, .ref_control = @@ -1509,6 +1539,36 @@ static const struct intel_mpllb_state dg2_hdmi_241500 = { REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), }; +static const struct intel_mpllb_state dg2_hdmi_319890 = { + .clock = 319890, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 94) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 64094) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13631), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + static const struct intel_mpllb_state dg2_hdmi_497750 = { .clock = 497750, .ref_control = @@ -1696,8 +1756,10 @@ static const struct intel_mpllb_state * const dg2_hdmi_tables[] = { &dg2_hdmi_209800, &dg2_hdmi_241500, &dg2_hdmi_262750, + &dg2_hdmi_267300, &dg2_hdmi_268500, &dg2_hdmi_296703, + &dg2_hdmi_319890, &dg2_hdmi_497750, &dg2_hdmi_592000, &dg2_hdmi_593407, diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index f45328712bff..be510b9c0d07 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -418,9 +418,9 @@ static bool icl_tc_phy_is_owned(struct intel_digital_port *dig_port) val = intel_de_read(i915, PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia)); if (val == 0xffffffff) { drm_dbg_kms(&i915->drm, - "Port %s: PHY in TCCOLD, assume safe mode\n", + "Port %s: PHY in TCCOLD, assume not owned\n", dig_port->tc_port_name); - return true; + return false; } return val & DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 8949fb0a944f..3198b64ad7db 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -127,7 +127,8 @@ i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915, memcpy(map, data, size); - i915_gem_object_unpin_map(obj); + i915_gem_object_flush_map(obj); + __i915_gem_object_release_map(obj); return obj; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index f9a8acbba715..885ccde9dc3c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -303,7 +303,7 @@ i915_gem_object_never_mmap(const struct drm_i915_gem_object *obj) static inline bool i915_gem_object_is_framebuffer(const struct drm_i915_gem_object *obj) { - return READ_ONCE(obj->frontbuffer); + return READ_ONCE(obj->frontbuffer) || obj->is_dpt; } static inline unsigned int 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 19c9bdd8f905..5dcbbef31d44 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -491,6 +491,9 @@ struct drm_i915_gem_object { */ unsigned int cache_dirty:1; + /* @is_dpt: Object houses a display page table (DPT) */ + unsigned int is_dpt:1; + /** * @read_domains: Read memory domains. * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 7420276827a5..4758f21c91e1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1067,11 +1067,12 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) .interruptible = true, .no_wait_gpu = true, /* should be idle already */ }; + int err; GEM_BUG_ON(!bo->ttm || !(bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED)); - ret = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); - if (ret) { + err = ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); + if (err) { dma_resv_unlock(bo->base.resv); return VM_FAULT_SIGBUS; } diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 1bbe6708d0a7..750326434677 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -2018,6 +2018,8 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive) * inspecting the queue to see if we need to resumbit. */ if (*prev != *execlists->active) { /* elide lite-restores */ + struct intel_context *prev_ce = NULL, *active_ce = NULL; + /* * Note the inherent discrepancy between the HW runtime, * recorded as part of the context switch, and the CPU @@ -2029,9 +2031,15 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive) * and correct overselves later when updating from HW. */ if (*prev) - lrc_runtime_stop((*prev)->context); + prev_ce = (*prev)->context; if (*execlists->active) - lrc_runtime_start((*execlists->active)->context); + active_ce = (*execlists->active)->context; + if (prev_ce != active_ce) { + if (prev_ce) + lrc_runtime_stop(prev_ce); + if (active_ce) + lrc_runtime_start(active_ce); + } new_timeslice(execlists); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f0dbfc434e07..40d357cf8b04 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -737,12 +737,12 @@ int intel_gt_init(struct intel_gt *gt) if (err) goto err_gt; - intel_uc_init_late(>->uc); - err = i915_inject_probe_error(gt->i915, -EIO); if (err) goto err_gt; + intel_uc_init_late(>->uc); + intel_migrate_init(>->migrate, gt); goto out_fw; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index cef3d6f5c34e..56b993f6e7dc 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -21,31 +21,10 @@ #include "intel_rc6.h" #include "intel_rps.h" #include "intel_wakeref.h" -#include "intel_pcode.h" #include "pxp/intel_pxp_pm.h" #define I915_GT_SUSPEND_IDLE_TIMEOUT (HZ / 2) -static void mtl_media_busy(struct intel_gt *gt) -{ - /* Wa_14017073508: mtl */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, - PCODE_MBOX_GT_STATE_MEDIA_BUSY, - PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); -} - -static void mtl_media_idle(struct intel_gt *gt) -{ - /* Wa_14017073508: mtl */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - snb_pcode_write_p(gt->uncore, PCODE_MBOX_GT_STATE, - PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY, - PCODE_MBOX_GT_STATE_DOMAIN_MEDIA, 0); -} - static void user_forcewake(struct intel_gt *gt, bool suspend) { int count = atomic_read(>->user_wakeref); @@ -93,9 +72,6 @@ static int __gt_unpark(struct intel_wakeref *wf) GT_TRACE(gt, "\n"); - /* Wa_14017073508: mtl */ - mtl_media_busy(gt); - /* * It seems that the DMC likes to transition between the DC states a lot * when there are no connected displays (no active power domains) during @@ -145,9 +121,6 @@ static int __gt_park(struct intel_wakeref *wf) GEM_BUG_ON(!wakeref); intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref); - /* Wa_14017073508: mtl */ - mtl_media_idle(gt); - return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index 83df4cd5e06c..80dbbef86b1d 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -580,7 +580,7 @@ static bool perf_limit_reasons_eval(void *data) } DEFINE_SIMPLE_ATTRIBUTE(perf_limit_reasons_fops, perf_limit_reasons_get, - perf_limit_reasons_clear, "%llu\n"); + perf_limit_reasons_clear, "0x%llx\n"); void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root) { diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 5c91622dfca4..f4150f61f39c 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -486,6 +486,7 @@ static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6) static bool rc6_supported(struct intel_rc6 *rc6) { struct drm_i915_private *i915 = rc6_to_i915(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); if (!HAS_RC6(i915)) return false; @@ -502,6 +503,13 @@ static bool rc6_supported(struct intel_rc6 *rc6) return false; } + if (IS_MTL_MEDIA_STEP(gt->i915, STEP_A0, STEP_B0) && + gt->type == GT_MEDIA) { + drm_notice(&i915->drm, + "Media RC6 disabled on A step\n"); + return false; + } + return true; } diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index f5d7b5126433..2c92fa9d1942 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -2075,16 +2075,6 @@ void intel_rps_sanitize(struct intel_rps *rps) rps_disable_interrupts(rps); } -u32 intel_rps_read_rpstat_fw(struct intel_rps *rps) -{ - struct drm_i915_private *i915 = rps_to_i915(rps); - i915_reg_t rpstat; - - rpstat = (GRAPHICS_VER(i915) >= 12) ? GEN12_RPSTAT1 : GEN6_RPSTAT1; - - return intel_uncore_read_fw(rps_to_gt(rps)->uncore, rpstat); -} - u32 intel_rps_read_rpstat(struct intel_rps *rps) { struct drm_i915_private *i915 = rps_to_i915(rps); @@ -2095,7 +2085,7 @@ u32 intel_rps_read_rpstat(struct intel_rps *rps) return intel_uncore_read(rps_to_gt(rps)->uncore, rpstat); } -u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat) +static u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat) { struct drm_i915_private *i915 = rps_to_i915(rps); u32 cagf; @@ -2118,10 +2108,11 @@ u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat) return cagf; } -static u32 read_cagf(struct intel_rps *rps) +static u32 __read_cagf(struct intel_rps *rps, bool take_fw) { struct drm_i915_private *i915 = rps_to_i915(rps); struct intel_uncore *uncore = rps_to_uncore(rps); + i915_reg_t r = INVALID_MMIO_REG; u32 freq; /* @@ -2129,22 +2120,30 @@ static u32 read_cagf(struct intel_rps *rps) * registers will return 0 freq when GT is in RC6 */ if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) { - freq = intel_uncore_read(uncore, MTL_MIRROR_TARGET_WP1); + r = MTL_MIRROR_TARGET_WP1; } else if (GRAPHICS_VER(i915) >= 12) { - freq = intel_uncore_read(uncore, GEN12_RPSTAT1); + r = GEN12_RPSTAT1; } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { vlv_punit_get(i915); freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS); vlv_punit_put(i915); } else if (GRAPHICS_VER(i915) >= 6) { - freq = intel_uncore_read(uncore, GEN6_RPSTAT1); + r = GEN6_RPSTAT1; } else { - freq = intel_uncore_read(uncore, MEMSTAT_ILK); + r = MEMSTAT_ILK; } + if (i915_mmio_reg_valid(r)) + freq = take_fw ? intel_uncore_read(uncore, r) : intel_uncore_read_fw(uncore, r); + return intel_rps_get_cagf(rps, freq); } +static u32 read_cagf(struct intel_rps *rps) +{ + return __read_cagf(rps, true); +} + u32 intel_rps_read_actual_frequency(struct intel_rps *rps) { struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm; @@ -2157,7 +2156,12 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps) return freq; } -u32 intel_rps_read_punit_req(struct intel_rps *rps) +u32 intel_rps_read_actual_frequency_fw(struct intel_rps *rps) +{ + return intel_gpu_freq(rps, __read_cagf(rps, false)); +} + +static u32 intel_rps_read_punit_req(struct intel_rps *rps) { struct intel_uncore *uncore = rps_to_uncore(rps); struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index c622962c6bef..a3fa987aa91f 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -37,8 +37,8 @@ void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive); int intel_gpu_freq(struct intel_rps *rps, int val); int intel_freq_opcode(struct intel_rps *rps, int val); -u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1); u32 intel_rps_read_actual_frequency(struct intel_rps *rps); +u32 intel_rps_read_actual_frequency_fw(struct intel_rps *rps); u32 intel_rps_get_requested_frequency(struct intel_rps *rps); u32 intel_rps_get_min_frequency(struct intel_rps *rps); u32 intel_rps_get_min_raw_freq(struct intel_rps *rps); @@ -49,10 +49,8 @@ int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_rp0_frequency(struct intel_rps *rps); u32 intel_rps_get_rp1_frequency(struct intel_rps *rps); u32 intel_rps_get_rpn_frequency(struct intel_rps *rps); -u32 intel_rps_read_punit_req(struct intel_rps *rps); u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps); u32 intel_rps_read_rpstat(struct intel_rps *rps); -u32 intel_rps_read_rpstat_fw(struct intel_rps *rps); void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *caps); void intel_rps_raise_unslice(struct intel_rps *rps); void intel_rps_lower_unslice(struct intel_rps *rps); diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h index aa87d3832d60..d7e8c374f153 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.h +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h @@ -27,7 +27,7 @@ struct drm_printer; * is only relevant to pre-Xe_HP platforms (Xe_HP and beyond use the * I915_MAX_SS_FUSE_BITS value below). */ -#define GEN_MAX_SS_PER_HSW_SLICE 6 +#define GEN_MAX_SS_PER_HSW_SLICE 8 /* * Maximum number of 32-bit registers used by hardware to express the diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index fc3b994626a4..710999d7189e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -1571,6 +1571,27 @@ int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf, #endif //CONFIG_DRM_I915_CAPTURE_ERROR +static void guc_capture_find_ecode(struct intel_engine_coredump *ee) +{ + struct gcap_reg_list_info *reginfo; + struct guc_mmio_reg *regs; + i915_reg_t reg_ipehr = RING_IPEHR(0); + i915_reg_t reg_instdone = RING_INSTDONE(0); + int i; + + if (!ee->guc_capture_node) + return; + + reginfo = ee->guc_capture_node->reginfo + GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE; + regs = reginfo->regs; + for (i = 0; i < reginfo->num_regs; i++) { + if (regs[i].offset == reg_ipehr.reg) + ee->ipehr = regs[i].value; + else if (regs[i].offset == reg_instdone.reg) + ee->instdone.instdone = regs[i].value; + } +} + void intel_guc_capture_free_node(struct intel_engine_coredump *ee) { if (!ee || !ee->guc_capture_node) @@ -1612,6 +1633,7 @@ void intel_guc_capture_get_matching_node(struct intel_gt *gt, list_del(&n->link); ee->guc_capture_node = n; ee->guc_capture = guc->capture; + guc_capture_find_ecode(ee); return; } } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c index b5855091cf6a..8f8dd05835c5 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c @@ -11,20 +11,9 @@ static bool __guc_rc_supported(struct intel_guc *guc) { - struct intel_gt *gt = guc_to_gt(guc); - - /* - * Wa_14017073508: mtl - * Do not enable gucrc to avoid additional interrupts which - * may disrupt pcode wa. - */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) - return false; - /* GuC RC is unavailable for pre-Gen12 */ return guc->submission_supported && - GRAPHICS_VER(gt->i915) >= 12; + GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; } static bool __guc_rc_selected(struct intel_guc *guc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 410905da8e97..0c103ca160d1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -235,6 +235,13 @@ static void delayed_huc_load_fini(struct intel_huc *huc) i915_sw_fence_fini(&huc->delayed_load.fence); } +int intel_huc_sanitize(struct intel_huc *huc) +{ + delayed_huc_load_complete(huc); + intel_uc_fw_sanitize(&huc->fw); + return 0; +} + static bool vcs_supported(struct intel_gt *gt) { intel_engine_mask_t mask = gt->info.engine_mask; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index 52db03620c60..db555b3c1f56 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -41,6 +41,7 @@ struct intel_huc { } delayed_load; }; +int intel_huc_sanitize(struct intel_huc *huc); void intel_huc_init_early(struct intel_huc *huc); int intel_huc_init(struct intel_huc *huc); void intel_huc_fini(struct intel_huc *huc); @@ -54,12 +55,6 @@ bool intel_huc_is_authenticated(struct intel_huc *huc); void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); -static inline int intel_huc_sanitize(struct intel_huc *huc) -{ - intel_uc_fw_sanitize(&huc->fw); - return 0; -} - static inline bool intel_huc_is_supported(struct intel_huc *huc) { return intel_uc_fw_is_supported(&huc->fw); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 7412abf166a8..8ef93889061a 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -92,8 +92,7 @@ static void debug_active_init(struct i915_active *ref) static void debug_active_activate(struct i915_active *ref) { lockdep_assert_held(&ref->tree_lock); - if (!atomic_read(&ref->count)) /* before the first inc */ - debug_object_activate(ref, &active_debug_desc); + debug_object_activate(ref, &active_debug_desc); } static void debug_active_deactivate(struct i915_active *ref) @@ -422,12 +421,12 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) * we can use it to substitute for the pending idle-barrer * request that we want to emit on the kernel_context. */ - __active_del_barrier(ref, node_from_active(active)); - return true; + return __active_del_barrier(ref, node_from_active(active)); } int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) { + u64 idx = i915_request_timeline(rq)->fence_context; struct dma_fence *fence = &rq->fence; struct i915_active_fence *active; int err; @@ -437,16 +436,19 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) if (err) return err; - active = active_instance(ref, i915_request_timeline(rq)->fence_context); - if (!active) { - err = -ENOMEM; - goto out; - } + do { + active = active_instance(ref, idx); + if (!active) { + err = -ENOMEM; + goto out; + } + + if (replace_barrier(ref, active)) { + RCU_INIT_POINTER(active->fence, NULL); + atomic_dec(&ref->count); + } + } while (unlikely(is_barrier(active))); - if (replace_barrier(ref, active)) { - RCU_INIT_POINTER(active->fence, NULL); - atomic_dec(&ref->count); - } if (!__i915_active_fence_set(active, fence)) __i915_active_acquire(ref); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 824a34ec0b83..004074936300 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1592,9 +1592,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) /* * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6. */ - if (intel_uc_uses_guc_rc(>->uc) && - (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) + if (stream->override_gucrc) drm_WARN_ON(>->i915->drm, intel_guc_slpc_unset_gucrc_mode(>->uc.guc.slpc)); @@ -3305,8 +3303,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, if (ret) { drm_dbg(&stream->perf->i915->drm, "Unable to override gucrc mode\n"); - goto err_config; + goto err_gucrc; } + + stream->override_gucrc = true; } ret = alloc_oa_buffer(stream); @@ -3345,11 +3345,15 @@ err_enable: free_oa_buffer(stream); err_oa_buf_alloc: - free_oa_configs(stream); + if (stream->override_gucrc) + intel_guc_slpc_unset_gucrc_mode(>->uc.guc.slpc); +err_gucrc: intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL); intel_engine_pm_put(stream->engine); + free_oa_configs(stream); + err_config: free_noa_wait(stream); @@ -4634,13 +4638,13 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, err = oa_config->id; goto sysfs_err; } - - mutex_unlock(&perf->metrics_lock); + id = oa_config->id; drm_dbg(&perf->i915->drm, "Added config %s id=%i\n", oa_config->uuid, oa_config->id); + mutex_unlock(&perf->metrics_lock); - return oa_config->id; + return id; sysfs_err: mutex_unlock(&perf->metrics_lock); diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index ca150b7af3f2..4d5d8c365d9e 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -316,6 +316,12 @@ struct i915_perf_stream { * buffer should be checked for available data. */ u64 poll_oa_period; + + /** + * @override_gucrc: GuC RC has been overridden for the perf stream, + * and we need to restore the default configuration on release. + */ + bool override_gucrc; }; /** diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 52531ab28c5f..6d422b056f8a 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -393,14 +393,12 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) * case we assume the system is running at the intended * frequency. Fortunately, the read should rarely fail! */ - val = intel_rps_read_rpstat_fw(rps); - if (val) - val = intel_rps_get_cagf(rps, val); - else - val = rps->cur_freq; + val = intel_rps_read_actual_frequency_fw(rps); + if (!val) + val = intel_gpu_freq(rps, rps->cur_freq); add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT], - intel_gpu_freq(rps, val), period_ns / 1000); + val, period_ns / 1000); } if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3b2642397b82..747b53b567a0 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1786,9 +1786,11 @@ * GEN9 clock gating regs */ #define GEN9_CLKGATE_DIS_0 _MMIO(0x46530) -#define DARBF_GATING_DIS (1 << 27) -#define PWM2_GATING_DIS (1 << 14) -#define PWM1_GATING_DIS (1 << 13) +#define DARBF_GATING_DIS REG_BIT(27) +#define MTL_PIPEDMC_GATING_DIS_A REG_BIT(15) +#define MTL_PIPEDMC_GATING_DIS_B REG_BIT(14) +#define PWM2_GATING_DIS REG_BIT(14) +#define PWM1_GATING_DIS REG_BIT(13) #define GEN9_CLKGATE_DIS_3 _MMIO(0x46538) #define TGL_VRH_GATING_DIS REG_BIT(31) @@ -6596,15 +6598,6 @@ /* XEHP_PCODE_FREQUENCY_CONFIG param2 */ #define PCODE_MBOX_DOMAIN_NONE 0x0 #define PCODE_MBOX_DOMAIN_MEDIAFF 0x3 - -/* Wa_14017210380: mtl */ -#define PCODE_MBOX_GT_STATE 0x50 -/* sub-commands (param1) */ -#define PCODE_MBOX_GT_STATE_MEDIA_BUSY 0x1 -#define PCODE_MBOX_GT_STATE_MEDIA_NOT_BUSY 0x2 -/* param2 */ -#define PCODE_MBOX_GT_STATE_DOMAIN_MEDIA 0x1 - #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 79bfe3938d3c..7caf937c3c90 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -325,23 +325,23 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) ret = meson_encoder_hdmi_init(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = meson_plane_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = meson_overlay_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = meson_crtc_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm); if (ret) - goto exit_afbcd; + goto unbind_all; drm_mode_config_reset(drm); @@ -359,6 +359,9 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) uninstall_irq: free_irq(priv->vsync_irq, drm); +unbind_all: + if (has_components) + component_unbind_all(drm->dev, drm); exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index 534621a13a34..3d046878ce6c 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -718,7 +718,7 @@ static int meson_dw_hdmi_bind(struct device *dev, struct device *master, dw_plat_data = &meson_dw_hdmi->dw_plat_data; ret = devm_regulator_get_enable_optional(dev, "hdmi"); - if (ret < 0) + if (ret < 0 && ret != -ENODEV) return ret; meson_dw_hdmi->hdmitx_apb = devm_reset_control_get_exclusive(dev, diff --git a/drivers/gpu/drm/meson/meson_vpp.c b/drivers/gpu/drm/meson/meson_vpp.c index 154837688ab0..5df1957c8e41 100644 --- a/drivers/gpu/drm/meson/meson_vpp.c +++ b/drivers/gpu/drm/meson/meson_vpp.c @@ -100,6 +100,8 @@ void meson_vpp_init(struct meson_drm *priv) priv->io_base + _REG(VPP_DOLBY_CTRL)); writel_relaxed(0x1020080, priv->io_base + _REG(VPP_DUMMY_DATA1)); + writel_relaxed(0x42020, + priv->io_base + _REG(VPP_DUMMY_DATA)); } else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) writel_relaxed(0xf, priv->io_base + _REG(DOLBY_PATH_CTRL)); diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 871870ddf7ec..949b18a29a55 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -23,7 +23,6 @@ config DRM_MSM select SHMEM select TMPFS select QCOM_SCM - select DEVFREQ_GOV_SIMPLE_ONDEMAND select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index d09221f97f71..a1e006ec5dce 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -151,8 +151,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, 1); /* Enable local preemption for finegrain preemption */ - OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); - OUT_RING(ring, 0x02); + OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); + OUT_RING(ring, 0x1); /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ OUT_PKT7(ring, CP_YIELD_ENABLE, 1); @@ -806,7 +806,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F); /* Set the highest bank bit */ - if (adreno_is_a540(adreno_gpu)) + if (adreno_is_a540(adreno_gpu) || adreno_is_a530(adreno_gpu)) regbit = 2; else regbit = 1; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 7658e89844b4..f58dd564d122 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -63,7 +63,7 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) struct msm_ringbuffer *ring = gpu->rb[i]; spin_lock_irqsave(&ring->preempt_lock, flags); - empty = (get_wptr(ring) == ring->memptrs->rptr); + empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring)); spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) @@ -207,6 +207,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) a5xx_gpu->preempt[i]->wptr = 0; a5xx_gpu->preempt[i]->rptr = 0; a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; + a5xx_gpu->preempt[i]->rptr_addr = shadowptr(a5xx_gpu, gpu->rb[i]); } /* Write a 0 to signal that we aren't switching pagetables */ @@ -257,7 +258,6 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->data = 0; ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE; - ptr->rptr_addr = shadowptr(a5xx_gpu, ring); ptr->counter = counters_iova; return 0; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index f3c9600221d4..7f5bc73b2040 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -974,7 +974,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) int status, ret; if (WARN(!gmu->initialized, "The GMU is not set up yet\n")) - return 0; + return -EINVAL; gmu->hung = false; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index aae60cbd9164..6faea5049f76 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1746,7 +1746,9 @@ static void a6xx_destroy(struct msm_gpu *gpu) a6xx_llc_slices_destroy(a6xx_gpu); + mutex_lock(&a6xx_gpu->gmu.lock); a6xx_gmu_remove(a6xx_gpu); + mutex_unlock(&a6xx_gpu->gmu.lock); adreno_gpu_cleanup(adreno_gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 36f062c7582f..c5c4c93b3689 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -558,7 +558,8 @@ static void adreno_unbind(struct device *dev, struct device *master, struct msm_drm_private *priv = dev_get_drvdata(master); struct msm_gpu *gpu = dev_to_gpu(dev); - WARN_ON_ONCE(adreno_system_suspend(dev)); + if (pm_runtime_enabled(dev)) + WARN_ON_ONCE(adreno_system_suspend(dev)); gpu->funcs->destroy(gpu); priv->gpu_pdev = NULL; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index cf053e8f081e..497c9e1673ab 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -12,11 +12,15 @@ #include "dpu_hw_catalog.h" #include "dpu_kms.h" -#define VIG_MASK \ +#define VIG_BASE_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\ - BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) |\ + BIT(DPU_SSPP_CDP) |\ BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT)) +#define VIG_MASK \ + (VIG_BASE_MASK | \ + BIT(DPU_SSPP_CSC_10BIT)) + #define VIG_MSM8998_MASK \ (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3)) @@ -26,10 +30,7 @@ #define VIG_SC7180_MASK \ (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED4)) -#define VIG_SM8250_MASK \ - (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3LITE)) - -#define VIG_QCM2290_MASK (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL)) +#define VIG_QCM2290_MASK (VIG_BASE_MASK | BIT(DPU_SSPP_QOS_8LVL)) #define DMA_MSM8998_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\ @@ -51,7 +52,7 @@ (DMA_MSM8998_MASK | BIT(DPU_SSPP_CURSOR)) #define MIXER_MSM8998_MASK \ - (BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER)) + (BIT(DPU_MIXER_SOURCESPLIT)) #define MIXER_SDM845_MASK \ (BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER) | BIT(DPU_MIXER_COMBINED_ALPHA)) @@ -314,10 +315,9 @@ static const struct dpu_caps msm8998_dpu_caps = { }; static const struct dpu_caps qcm2290_dpu_caps = { - .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_width = DEFAULT_DPU_LINE_WIDTH, .max_mixer_blendstages = 0x4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, - .ubwc_version = DPU_HW_UBWC_VER_20, .has_dim_layer = true, .has_idle_pc = true, .max_linewidth = 2160, @@ -353,9 +353,9 @@ static const struct dpu_caps sc7180_dpu_caps = { }; static const struct dpu_caps sm6115_dpu_caps = { - .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_width = DEFAULT_DPU_LINE_WIDTH, .max_mixer_blendstages = 0x4, - .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .qseed_type = DPU_SSPP_SCALER_QSEED4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_10, .has_dim_layer = true, @@ -399,7 +399,7 @@ static const struct dpu_caps sc8180x_dpu_caps = { static const struct dpu_caps sc8280xp_dpu_caps = { .max_mixer_width = 2560, .max_mixer_blendstages = 11, - .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .qseed_type = DPU_SSPP_SCALER_QSEED4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_40, .has_src_split = true, @@ -413,7 +413,7 @@ static const struct dpu_caps sc8280xp_dpu_caps = { static const struct dpu_caps sm8250_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, - .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .qseed_type = DPU_SSPP_SCALER_QSEED4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_40, .has_src_split = true, @@ -427,7 +427,7 @@ static const struct dpu_caps sm8250_dpu_caps = { static const struct dpu_caps sm8350_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, - .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .qseed_type = DPU_SSPP_SCALER_QSEED4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_40, .has_src_split = true, @@ -455,7 +455,7 @@ static const struct dpu_caps sm8450_dpu_caps = { static const struct dpu_caps sm8550_dpu_caps = { .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .max_mixer_blendstages = 0xb, - .qseed_type = DPU_SSPP_SCALER_QSEED3LITE, + .qseed_type = DPU_SSPP_SCALER_QSEED4, .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */ .ubwc_version = DPU_HW_UBWC_VER_40, .has_src_split = true, @@ -525,9 +525,9 @@ static const struct dpu_mdp_cfg sdm845_mdp[] = { .reg_off = 0x2AC, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2BC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2C4, .bit_off = 8}, }, }; @@ -542,9 +542,9 @@ static const struct dpu_mdp_cfg sc7180_mdp[] = { .reg_off = 0x2AC, .bit_off = 0}, .clk_ctrls[DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2AC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2C4, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_WB2] = { .reg_off = 0x3B8, .bit_off = 24}, @@ -569,9 +569,9 @@ static const struct dpu_mdp_cfg sc8180x_mdp[] = { .reg_off = 0x2AC, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2BC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2C4, .bit_off = 8}, }, }; @@ -609,9 +609,9 @@ static const struct dpu_mdp_cfg sm8250_mdp[] = { .reg_off = 0x2AC, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2BC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2C4, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2BC, .bit_off = 20}, @@ -638,9 +638,9 @@ static const struct dpu_mdp_cfg sm8350_mdp[] = { .reg_off = 0x2ac, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20}, @@ -666,9 +666,9 @@ static const struct dpu_mdp_cfg sm8450_mdp[] = { .reg_off = 0x2AC, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2BC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2C4, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2BC, .bit_off = 20}, @@ -685,9 +685,9 @@ static const struct dpu_mdp_cfg sc7280_mdp[] = { .reg_off = 0x2AC, .bit_off = 0}, .clk_ctrls[DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2AC, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2B4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2C4, .bit_off = 8}, }, }; @@ -696,7 +696,7 @@ static const struct dpu_mdp_cfg sc8280xp_mdp[] = { { .name = "top_0", .id = MDP_TOP, .base = 0x0, .len = 0x494, - .features = 0, + .features = BIT(DPU_MDP_PERIPH_0_REMOVED), .highest_bank_bit = 2, .ubwc_swizzle = 6, .clk_ctrls[DPU_CLK_CTRL_VIG0] = { .reg_off = 0x2ac, .bit_off = 0}, @@ -705,8 +705,8 @@ static const struct dpu_mdp_cfg sc8280xp_mdp[] = { .clk_ctrls[DPU_CLK_CTRL_VIG3] = { .reg_off = 0x2c4, .bit_off = 0}, .clk_ctrls[DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2ac, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { .reg_off = 0x2bc, .bit_off = 8}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { .reg_off = 0x2c4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8}, .clk_ctrls[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20}, }, }; @@ -734,9 +734,9 @@ static const struct dpu_mdp_cfg sm8550_mdp[] = { .reg_off = 0x28330, .bit_off = 0}, .clk_ctrls[DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2a330, .bit_off = 0}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .clk_ctrls[DPU_CLK_CTRL_DMA4] = { .reg_off = 0x2c330, .bit_off = 0}, - .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .clk_ctrls[DPU_CLK_CTRL_DMA5] = { .reg_off = 0x2e330, .bit_off = 0}, .clk_ctrls[DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20}, @@ -828,19 +828,19 @@ static const struct dpu_ctl_cfg sdm845_ctl[] = { static const struct dpu_ctl_cfg sc7180_ctl[] = { { .name = "ctl_0", .id = CTL_0, - .base = 0x1000, .len = 0xE4, + .base = 0x1000, .len = 0x1dc, .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, - .base = 0x1200, .len = 0xE4, + .base = 0x1200, .len = 0x1dc, .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, - .base = 0x1400, .len = 0xE4, + .base = 0x1400, .len = 0x1dc, .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), }, @@ -1190,9 +1190,9 @@ static const struct dpu_sspp_cfg msm8998_sspp[] = { SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_MSM8998_MASK, sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_MSM8998_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_MSM8998_MASK, - sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), }; static const struct dpu_sspp_cfg sdm845_sspp[] = { @@ -1209,9 +1209,9 @@ static const struct dpu_sspp_cfg sdm845_sspp[] = { SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_SDM845_MASK, sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), }; static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 = @@ -1226,57 +1226,57 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), }; static const struct dpu_sspp_sub_blks sm6115_vig_sblk_0 = - _VIG_SBLK("0", 2, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("0", 2, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_cfg sm6115_sspp[] = { - SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK, + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, sm6115_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), }; static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 = - _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 = - _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 = - _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 = - _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_cfg sm8250_sspp[] = { - SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK, + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, sm8250_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), - SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SM8250_MASK, + SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SC7180_MASK, sm8250_vig_sblk_1, 4, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1), - SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SM8250_MASK, + SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SC7180_MASK, sm8250_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2), - SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SM8250_MASK, + SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SC7180_MASK, sm8250_vig_sblk_3, 12, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3), SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_SDM845_MASK, sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), }; static const struct dpu_sspp_sub_blks sm8450_vig_sblk_0 = - _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8450_vig_sblk_1 = - _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8450_vig_sblk_2 = - _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8450_vig_sblk_3 = - _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_cfg sm8450_sspp[] = { SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, @@ -1292,21 +1292,21 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = { SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_SDM845_MASK, sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), }; static const struct dpu_sspp_sub_blks sm8550_vig_sblk_0 = - _VIG_SBLK("0", 7, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("0", 7, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_1 = - _VIG_SBLK("1", 8, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("1", 8, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_2 = - _VIG_SBLK("2", 9, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("2", 9, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8550_vig_sblk_3 = - _VIG_SBLK("3", 10, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("3", 10, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sm8550_dma_sblk_4 = _DMA_SBLK("12", 5); -static const struct dpu_sspp_sub_blks sd8550_dma_sblk_5 = _DMA_SBLK("13", 6); +static const struct dpu_sspp_sub_blks sm8550_dma_sblk_5 = _DMA_SBLK("13", 6); static const struct dpu_sspp_cfg sm8550_sspp[] = { SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, @@ -1326,9 +1326,9 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = { SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_SDM845_MASK, sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), SSPP_BLK("sspp_12", SSPP_DMA4, 0x2c000, DMA_CURSOR_SDM845_MASK, - sm8550_dma_sblk_4, 14, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sm8550_dma_sblk_4, 14, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA4), SSPP_BLK("sspp_13", SSPP_DMA5, 0x2e000, DMA_CURSOR_SDM845_MASK, - sd8550_dma_sblk_5, 15, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sm8550_dma_sblk_5, 15, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA5), }; static const struct dpu_sspp_cfg sc7280_sspp[] = { @@ -1337,37 +1337,37 @@ static const struct dpu_sspp_cfg sc7280_sspp[] = { SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), }; static const struct dpu_sspp_sub_blks sc8280xp_vig_sblk_0 = - _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sc8280xp_vig_sblk_1 = - _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sc8280xp_vig_sblk_2 = - _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_sub_blks sc8280xp_vig_sblk_3 = - _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3LITE); + _VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED4); static const struct dpu_sspp_cfg sc8280xp_sspp[] = { - SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK, + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, sc8280xp_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), - SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SM8250_MASK, + SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SC7180_MASK, sc8280xp_vig_sblk_1, 4, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1), - SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SM8250_MASK, + SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SC7180_MASK, sc8280xp_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2), - SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SM8250_MASK, + SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SC7180_MASK, sc8280xp_vig_sblk_3, 12, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3), SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_SDM845_MASK, sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1), SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA2), SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000, DMA_CURSOR_SDM845_MASK, - sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), + sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA3), }; #define _VIG_SBLK_NOSCALE(num, sdma_pri) \ @@ -1517,7 +1517,7 @@ static const struct dpu_lm_cfg sc7280_lm[] = { /* QCM2290 */ static const struct dpu_lm_sub_blks qcm2290_lm_sblk = { - .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxwidth = DEFAULT_DPU_LINE_WIDTH, .maxblendstages = 4, /* excluding base layer */ .blendstage_base = { /* offsets relative to mixer base */ 0x20, 0x38, 0x50, 0x68 @@ -1714,7 +1714,7 @@ static const struct dpu_pingpong_cfg sm8350_pp[] = { }; static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x59000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), @@ -2841,8 +2841,6 @@ static const struct dpu_mdss_cfg qcm2290_dpu_cfg = { .intf = qcm2290_intf, .vbif_count = ARRAY_SIZE(sdm845_vbif), .vbif = sdm845_vbif, - .reg_dma_count = 1, - .dma_cfg = &sdm845_regdma, .perf = &qcm2290_perf_data, .mdss_irqs = IRQ_SC7180_MASK, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index ddab9caebb18..e6590302b3bf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -515,6 +515,8 @@ enum dpu_clk_ctrl_type { DPU_CLK_CTRL_DMA1, DPU_CLK_CTRL_DMA2, DPU_CLK_CTRL_DMA3, + DPU_CLK_CTRL_DMA4, + DPU_CLK_CTRL_DMA5, DPU_CLK_CTRL_CURSOR0, DPU_CLK_CTRL_CURSOR1, DPU_CLK_CTRL_INLINE_ROT0_SSPP, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index b88a2f3724e6..6c53ea560ffa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -446,7 +446,9 @@ static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx, * CTL_LAYER has 3-bit field (and extra bits in EXT register), * all EXT registers has 4-bit fields. */ - if (cfg->idx == 0) { + if (cfg->idx == -1) { + continue; + } else if (cfg->idx == 0) { mixercfg[0] |= mix << cfg->shift; mixercfg[1] |= ext << cfg->ext_shift; } else { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 396429e63756..66c1b70d244f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -577,6 +577,8 @@ void dpu_rm_release(struct dpu_global_state *global_state, ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id); _dpu_rm_clear_mapping(global_state->dsc_to_enc_id, ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id); + _dpu_rm_clear_mapping(global_state->dspp_to_enc_id, + ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id); } int dpu_rm_reserve( diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 051bdbc093cf..f38296ad8743 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -107,6 +107,7 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) bool (*shrink)(struct drm_gem_object *obj); bool cond; unsigned long freed; + unsigned long remaining; } stages[] = { /* Stages of progressively more aggressive/expensive reclaim: */ { &priv->lru.dontneed, purge, true }, @@ -116,14 +117,18 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) }; long nr = sc->nr_to_scan; unsigned long freed = 0; + unsigned long remaining = 0; for (unsigned i = 0; (nr > 0) && (i < ARRAY_SIZE(stages)); i++) { if (!stages[i].cond) continue; stages[i].freed = - drm_gem_lru_scan(stages[i].lru, nr, stages[i].shrink); + drm_gem_lru_scan(stages[i].lru, nr, + &stages[i].remaining, + stages[i].shrink); nr -= stages[i].freed; freed += stages[i].freed; + remaining += stages[i].remaining; } if (freed) { @@ -132,7 +137,7 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) stages[3].freed); } - return (freed > 0) ? freed : SHRINK_STOP; + return (freed > 0 && remaining > 0) ? freed : SHRINK_STOP; } #ifdef CONFIG_DEBUG_FS @@ -182,10 +187,12 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) NULL, }; unsigned idx, unmapped = 0; + unsigned long remaining = 0; for (idx = 0; lrus[idx] && unmapped < vmap_shrink_limit; idx++) { unmapped += drm_gem_lru_scan(lrus[idx], vmap_shrink_limit - unmapped, + &remaining, vmap_shrink); } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index be4bf77103cd..ac8ed731f76d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -637,8 +637,8 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, int ret = 0; uint32_t i, j; - post_deps = kmalloc_array(nr_syncobjs, sizeof(*post_deps), - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + post_deps = kcalloc(nr_syncobjs, sizeof(*post_deps), + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (!post_deps) return ERR_PTR(-ENOMEM); @@ -653,7 +653,6 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, } post_deps[i].point = syncobj_desc.point; - post_deps[i].chain = NULL; if (syncobj_desc.flags) { ret = -EINVAL; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index ed9d374147b8..5bb777ff1313 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -363,6 +363,35 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder, return 0; } +static void +nv50_outp_atomic_fix_depth(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state) +{ + struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct drm_display_mode *mode = &asyh->state.adjusted_mode; + unsigned int max_rate, mode_rate; + + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + max_rate = nv_encoder->dp.link_nr * nv_encoder->dp.link_bw; + + /* we don't support more than 10 anyway */ + asyh->or.bpc = min_t(u8, asyh->or.bpc, 10); + + /* reduce the bpc until it works out */ + while (asyh->or.bpc > 6) { + mode_rate = DIV_ROUND_UP(mode->clock * asyh->or.bpc * 3, 8); + if (mode_rate <= max_rate) + break; + + asyh->or.bpc -= 2; + } + break; + default: + break; + } +} + static int nv50_outp_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, @@ -381,6 +410,9 @@ nv50_outp_atomic_check(struct drm_encoder *encoder, if (crtc_state->mode_changed || crtc_state->connectors_changed) asyh->or.bpc = connector->display_info.bpc; + /* We might have to reduce the bpc */ + nv50_outp_atomic_fix_depth(encoder, crtc_state); + return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h index 591c852f326b..76a6ae5d5652 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h @@ -35,8 +35,9 @@ struct nv50_wndw { int nv50_wndw_new_(const struct nv50_wndw_func *, struct drm_device *, enum drm_plane_type, const char *name, int index, - const u32 *format, enum nv50_disp_interlock_type, - u32 interlock_data, u32 heads, struct nv50_wndw **); + const u32 *format, u32 heads, + enum nv50_disp_interlock_type, u32 interlock_data, + struct nv50_wndw **); void nv50_wndw_flush_set(struct nv50_wndw *, u32 *interlock, struct nv50_wndw_atom *); void nv50_wndw_flush_clr(struct nv50_wndw *, u32 *interlock, bool flush, diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index c5a4f49ee206..01a22a13b452 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -2,6 +2,7 @@ #ifndef __NVKM_FB_H__ #define __NVKM_FB_H__ #include <core/subdev.h> +#include <core/falcon.h> #include <core/mm.h> /* memory type/access flags, do not match hardware values */ @@ -33,7 +34,7 @@ struct nvkm_fb { const struct nvkm_fb_func *func; struct nvkm_subdev subdev; - struct nvkm_blob vpr_scrubber; + struct nvkm_falcon_fw vpr_scrubber; struct { struct page *flush_page; diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index 40409a29f5b6..91b5ecc57538 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -33,6 +33,7 @@ #include <linux/apple-gmux.h> #include <linux/backlight.h> #include <linux/idr.h> +#include <drm/drm_probe_helper.h> #include "nouveau_drv.h" #include "nouveau_reg.h" @@ -299,8 +300,12 @@ nv50_backlight_init(struct nouveau_backlight *bl, struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nvif_object *device = &drm->client.device.object; + /* + * Note when this runs the connectors have not been probed yet, + * so nv_conn->base.status is not set yet. + */ if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1)) || - nv_conn->base.status != connector_status_connected) + drm_helper_probe_detect(&nv_conn->base, NULL, false) != connector_status_connected) return -ENODEV; if (nv_conn->type == DCB_CONNECTOR_eDP) { diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index e00876f92aee..d49b4875fc3c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -263,8 +263,6 @@ nouveau_dp_irq(struct work_struct *work) } /* TODO: - * - Use the minimum possible BPC here, once we add support for the max bpc - * property. * - Validate against the DP caps advertised by the GPU (we don't check these * yet) */ @@ -276,7 +274,11 @@ nv50_dp_mode_valid(struct drm_connector *connector, { const unsigned int min_clock = 25000; unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock; - const u8 bpp = connector->display_info.bpc * 3; + /* Check with the minmum bpc always, so we can advertise better modes. + * In particlar not doing this causes modes to be dropped on HDR + * displays as we might check with a bpc of 16 even. + */ + const u8 bpp = 6 * 3; if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace) return MODE_NO_INTERLACE; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c index bac7dcc4c2c1..0955340cc421 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c @@ -143,6 +143,10 @@ nvkm_fb_mem_unlock(struct nvkm_fb *fb) if (!fb->func->vpr.scrub_required) return 0; + ret = nvkm_subdev_oneinit(subdev); + if (ret) + return ret; + if (!fb->func->vpr.scrub_required(fb)) { nvkm_debug(subdev, "VPR not locked\n"); return 0; @@ -150,7 +154,7 @@ nvkm_fb_mem_unlock(struct nvkm_fb *fb) nvkm_debug(subdev, "VPR locked, running scrubber binary\n"); - if (!fb->vpr_scrubber.size) { + if (!fb->vpr_scrubber.fw.img) { nvkm_warn(subdev, "VPR locked, but no scrubber binary!\n"); return 0; } @@ -229,7 +233,7 @@ nvkm_fb_dtor(struct nvkm_subdev *subdev) nvkm_ram_del(&fb->ram); - nvkm_blob_dtor(&fb->vpr_scrubber); + nvkm_falcon_fw_dtor(&fb->vpr_scrubber); if (fb->sysmem.flush_page) { dma_unmap_page(subdev->device->dev, fb->sysmem.flush_page_addr, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c index 5098f219e3e6..a7456e786463 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c @@ -37,5 +37,5 @@ ga100_fb = { int ga100_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) { - return gp102_fb_new_(&ga100_fb, device, type, inst, pfb); + return gf100_fb_new_(&ga100_fb, device, type, inst, pfb); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c index 5a21b0ae4595..dd476e079fe1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c @@ -25,25 +25,20 @@ #include <engine/nvdec.h> static int -ga102_fb_vpr_scrub(struct nvkm_fb *fb) +ga102_fb_oneinit(struct nvkm_fb *fb) { - struct nvkm_falcon_fw fw = {}; - int ret; + struct nvkm_subdev *subdev = &fb->subdev; - ret = nvkm_falcon_fw_ctor_hs_v2(&ga102_flcn_fw, "mem-unlock", &fb->subdev, "nvdec/scrubber", - 0, &fb->subdev.device->nvdec[0]->falcon, &fw); - if (ret) - return ret; + nvkm_falcon_fw_ctor_hs_v2(&ga102_flcn_fw, "mem-unlock", subdev, "nvdec/scrubber", + 0, &subdev->device->nvdec[0]->falcon, &fb->vpr_scrubber); - ret = nvkm_falcon_fw_boot(&fw, &fb->subdev, true, NULL, NULL, 0, 0); - nvkm_falcon_fw_dtor(&fw); - return ret; + return gf100_fb_oneinit(fb); } static const struct nvkm_fb_func ga102_fb = { .dtor = gf100_fb_dtor, - .oneinit = gf100_fb_oneinit, + .oneinit = ga102_fb_oneinit, .init = gm200_fb_init, .init_page = gv100_fb_init_page, .init_unkn = gp100_fb_init_unkn, @@ -51,13 +46,13 @@ ga102_fb = { .ram_new = ga102_ram_new, .default_bigpage = 16, .vpr.scrub_required = tu102_fb_vpr_scrub_required, - .vpr.scrub = ga102_fb_vpr_scrub, + .vpr.scrub = gp102_fb_vpr_scrub, }; int ga102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) { - return gp102_fb_new_(&ga102_fb, device, type, inst, pfb); + return gf100_fb_new_(&ga102_fb, device, type, inst, pfb); } MODULE_FIRMWARE("nvidia/ga102/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c index 76678dd60f93..c4c6f67af7cc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c @@ -31,6 +31,7 @@ gf108_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gf108_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c index f73442ccb424..433fa966ba23 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c @@ -77,6 +77,7 @@ gk104_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk104_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c index 45d6cdffafee..4dc283dedf8b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c @@ -59,6 +59,7 @@ gk110_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gk104_ram_new, .default_bigpage = 17, .clkgate_pack = gk110_fb_clkgate_pack, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c index de52462a92bf..90bfff616d35 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c @@ -31,6 +31,7 @@ gm107_fb = { .init = gf100_fb_init, .init_page = gf100_fb_init_page, .intr = gf100_fb_intr, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = gm107_ram_new, .default_bigpage = 17, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c index 2658481d575b..14d942e8b857 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c @@ -29,18 +29,7 @@ int gp102_fb_vpr_scrub(struct nvkm_fb *fb) { - struct nvkm_subdev *subdev = &fb->subdev; - struct nvkm_falcon_fw fw = {}; - int ret; - - ret = nvkm_falcon_fw_ctor_hs(&gm200_flcn_fw, "mem-unlock", subdev, NULL, - "nvdec/scrubber", 0, &subdev->device->nvdec[0]->falcon, &fw); - if (ret) - return ret; - - ret = nvkm_falcon_fw_boot(&fw, subdev, true, NULL, NULL, 0, 0x00000000); - nvkm_falcon_fw_dtor(&fw); - return ret; + return nvkm_falcon_fw_boot(&fb->vpr_scrubber, &fb->subdev, true, NULL, NULL, 0, 0x00000000); } bool @@ -51,10 +40,21 @@ gp102_fb_vpr_scrub_required(struct nvkm_fb *fb) return (nvkm_rd32(device, 0x100cd0) & 0x00000010) != 0; } +int +gp102_fb_oneinit(struct nvkm_fb *fb) +{ + struct nvkm_subdev *subdev = &fb->subdev; + + nvkm_falcon_fw_ctor_hs(&gm200_flcn_fw, "mem-unlock", subdev, NULL, "nvdec/scrubber", + 0, &subdev->device->nvdec[0]->falcon, &fb->vpr_scrubber); + + return gf100_fb_oneinit(fb); +} + static const struct nvkm_fb_func gp102_fb = { .dtor = gf100_fb_dtor, - .oneinit = gf100_fb_oneinit, + .oneinit = gp102_fb_oneinit, .init = gm200_fb_init, .init_remapper = gp100_fb_init_remapper, .init_page = gm200_fb_init_page, @@ -65,22 +65,9 @@ gp102_fb = { }; int -gp102_fb_new_(const struct nvkm_fb_func *func, struct nvkm_device *device, - enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) -{ - int ret = gf100_fb_new_(func, device, type, inst, pfb); - if (ret) - return ret; - - nvkm_firmware_load_blob(&(*pfb)->subdev, "nvdec/scrubber", "", 0, - &(*pfb)->vpr_scrubber); - return 0; -} - -int gp102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) { - return gp102_fb_new_(&gp102_fb, device, type, inst, pfb); + return gf100_fb_new_(&gp102_fb, device, type, inst, pfb); } MODULE_FIRMWARE("nvidia/gp102/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 0e3c0a8f5d71..4d8a286a7a34 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -31,7 +31,7 @@ gv100_fb_init_page(struct nvkm_fb *fb) static const struct nvkm_fb_func gv100_fb = { .dtor = gf100_fb_dtor, - .oneinit = gf100_fb_oneinit, + .oneinit = gp102_fb_oneinit, .init = gm200_fb_init, .init_page = gv100_fb_init_page, .init_unkn = gp100_fb_init_unkn, @@ -45,7 +45,7 @@ gv100_fb = { int gv100_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) { - return gp102_fb_new_(&gv100_fb, device, type, inst, pfb); + return gf100_fb_new_(&gv100_fb, device, type, inst, pfb); } MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index f517751f94ac..726c30c8bf95 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -83,8 +83,7 @@ int gm200_fb_init_page(struct nvkm_fb *); void gp100_fb_init_remapper(struct nvkm_fb *); void gp100_fb_init_unkn(struct nvkm_fb *); -int gp102_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *, enum nvkm_subdev_type, int, - struct nvkm_fb **); +int gp102_fb_oneinit(struct nvkm_fb *); bool gp102_fb_vpr_scrub_required(struct nvkm_fb *); int gp102_fb_vpr_scrub(struct nvkm_fb *); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c index be82af0364ee..b8803c124c3b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c @@ -31,7 +31,7 @@ tu102_fb_vpr_scrub_required(struct nvkm_fb *fb) static const struct nvkm_fb_func tu102_fb = { .dtor = gf100_fb_dtor, - .oneinit = gf100_fb_oneinit, + .oneinit = gp102_fb_oneinit, .init = gm200_fb_init, .init_page = gv100_fb_init_page, .init_unkn = gp100_fb_init_unkn, @@ -45,7 +45,7 @@ tu102_fb = { int tu102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) { - return gp102_fb_new_(&tu102_fb, device, type, inst, pfb); + return gf100_fb_new_(&tu102_fb, device, type, inst, pfb); } MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 4e83a1891f3e..e961fa27702c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -282,7 +282,7 @@ static void panfrost_mmu_flush_range(struct panfrost_device *pfdev, if (pm_runtime_active(pfdev->dev)) mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT); - pm_runtime_put_sync_autosuspend(pfdev->dev); + pm_runtime_put_autosuspend(pfdev->dev); } static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, @@ -504,6 +504,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, if (IS_ERR(pages[i])) { mutex_unlock(&bo->base.pages_lock); ret = PTR_ERR(pages[i]); + pages[i] = NULL; goto err_pages; } } diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 15d04a0ec623..e0a8890a62e2 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -507,12 +507,19 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) { struct drm_sched_entity *entity = sched_job->entity; bool first; + ktime_t submit_ts; trace_drm_sched_job(sched_job, entity); atomic_inc(entity->rq->sched->score); WRITE_ONCE(entity->last_user, current->group_leader); + + /* + * After the sched_job is pushed into the entity queue, it may be + * completed and freed up at any time. We can no longer access it. + * Make sure to set the submit_ts first, to avoid a race. + */ + sched_job->submit_ts = submit_ts = ktime_get(); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node); - sched_job->submit_ts = ktime_get(); /* first job wakes up scheduler */ if (first) { @@ -529,7 +536,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job) spin_unlock(&entity->rq_lock); if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) - drm_sched_rq_update_fifo(entity, sched_job->submit_ts); + drm_sched_rq_update_fifo(entity, submit_ts); drm_sched_wakeup(entity->rq->sched); } diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 4e6ad6e122bc..0e4378420271 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -906,12 +906,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) spin_unlock(&sched->job_list_lock); - if (job) { - job->entity->elapsed_ns += ktime_to_ns( - ktime_sub(job->s_fence->finished.timestamp, - job->s_fence->scheduled.timestamp)); - } - return job; } diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index cc94efbbf2d4..d6c741716167 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -95,12 +95,12 @@ static int sun4i_drv_bind(struct device *dev) /* drm_vblank_init calls kcalloc, which can fail */ ret = drm_vblank_init(drm, drm->mode_config.num_crtc); if (ret) - goto cleanup_mode_config; + goto unbind_all; /* Remove early framebuffers (ie. simplefb) */ ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); if (ret) - goto cleanup_mode_config; + goto unbind_all; sun4i_framebuffer_init(drm); @@ -119,6 +119,8 @@ static int sun4i_drv_bind(struct device *dev) finish_poll: drm_kms_helper_poll_fini(drm); +unbind_all: + component_unbind_all(dev, NULL); cleanup_mode_config: drm_mode_config_cleanup(drm); of_reserved_mem_device_release(dev); diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index f8ee714df396..09ee6f6af896 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -89,7 +89,8 @@ static int check_block(struct kunit *test, struct drm_buddy *mm, err = -EINVAL; } - if (!is_power_of_2(block_size)) { + /* We can't use is_power_of_2() for a u64 on 32-bit systems. */ + if (block_size & (block_size - 1)) { kunit_err(test, "block size not power of two\n"); err = -EINVAL; } diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c index cf35b6090503..accfa52e78c5 100644 --- a/drivers/gpu/drm/tiny/cirrus.c +++ b/drivers/gpu/drm/tiny/cirrus.c @@ -455,7 +455,7 @@ static void cirrus_pipe_update(struct drm_simple_display_pipe *pipe, if (state->fb && cirrus->cpp != cirrus_cpp(state->fb)) cirrus_mode_set(cirrus, &crtc->mode, state->fb); - if (drm_atomic_helper_damage_merged(old_state, state, &rect)) + if (state->fb && drm_atomic_helper_damage_merged(old_state, state, &rect)) cirrus_fb_blit_rect(state->fb, &shadow_plane_state->data[0], &rect); } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 326a3d13a829..c286c6ffe07f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -295,8 +295,6 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, if (unlock_resv) dma_resv_unlock(bo->base.resv); - ttm_bo_put(bo); - return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index c7a1862f322a..ae2f19dc9f81 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -158,7 +158,7 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo = res->bo; uint32_t num_pages; - if (!bo) + if (!bo || bo->resource != res) continue; num_pages = PFN_UP(bo->base.size); diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index a04a9b20896d..1778a2081fd6 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -604,7 +604,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) - dma_sync_sgtable_for_device(&vgdev->vdev->dev, + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, bo->base.sgt, DMA_TO_DEVICE); cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); @@ -1026,7 +1026,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) - dma_sync_sgtable_for_device(&vgdev->vdev->dev, + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, bo->base.sgt, DMA_TO_DEVICE); cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 4872d183d860..aae2efeef503 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -487,7 +487,6 @@ static int host1x_get_resets(struct host1x *host) static int host1x_probe(struct platform_device *pdev) { struct host1x *host; - int syncpt_irq; int err; host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL); @@ -517,8 +516,8 @@ static int host1x_probe(struct platform_device *pdev) } host->syncpt_irq = platform_get_irq(pdev, 0); - if (syncpt_irq < 0) - return syncpt_irq; + if (host->syncpt_irq < 0) + return host->syncpt_irq; mutex_init(&host->devices_lock); INIT_LIST_HEAD(&host->devices); |