diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
45 files changed, 684 insertions, 175 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, |