diff options
Diffstat (limited to '')
62 files changed, 684 insertions, 227 deletions
diff --git a/Documentation/gpu/amdgpu/driver-misc.rst b/Documentation/gpu/amdgpu/driver-misc.rst index be131e963d87..4321c38fef21 100644 --- a/Documentation/gpu/amdgpu/driver-misc.rst +++ b/Documentation/gpu/amdgpu/driver-misc.rst @@ -11,19 +11,19 @@ via sysfs product_name ------------ -.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c :doc: product_name product_number -------------- -.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c - :doc: product_name +.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c + :doc: product_number serial_number ------------- -.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c :doc: serial_number unique_id diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c index 831bfd2b2d39..bdddef2c59ee 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.c +++ b/drivers/accel/ivpu/ivpu_jsm_msg.c @@ -118,8 +118,7 @@ int ivpu_jsm_dyndbg_control(struct ivpu_device *vdev, char *command, size_t size struct vpu_jsm_msg resp; int ret; - if (!strncpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN - 1)) - return -ENOMEM; + strscpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN); ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DYNDBG_CONTROL_RSP, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index df633e9ce920..cdf6087706aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -442,9 +442,7 @@ void amdgpu_amdkfd_get_local_mem_info(struct amdgpu_device *adev, mem_info->local_mem_size_public, mem_info->local_mem_size_private); - if (amdgpu_sriov_vf(adev)) - mem_info->mem_clk_max = adev->clock.default_mclk / 100; - else if (adev->pm.dpm_enabled) { + if (adev->pm.dpm_enabled) { if (amdgpu_emu_mode == 1) mem_info->mem_clk_max = 0; else @@ -463,9 +461,7 @@ uint64_t amdgpu_amdkfd_get_gpu_clock_counter(struct amdgpu_device *adev) uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct amdgpu_device *adev) { /* the sclk is in quantas of 10kHz */ - if (amdgpu_sriov_vf(adev)) - return adev->clock.default_sclk / 100; - else if (adev->pm.dpm_enabled) + if (adev->pm.dpm_enabled) return amdgpu_dpm_get_sclk(adev, false) / 100; else return 100; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 835980e94b9e..fb2681dd6b33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -217,6 +217,7 @@ union umc_info { struct atom_umc_info_v3_1 v31; struct atom_umc_info_v3_2 v32; struct atom_umc_info_v3_3 v33; + struct atom_umc_info_v4_0 v40; }; union vram_info { @@ -508,9 +509,8 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev) if (amdgpu_atom_parse_data_header(mode_info->atom_context, index, &size, &frev, &crev, &data_offset)) { + umc_info = (union umc_info *)(mode_info->atom_context->bios + data_offset); if (frev == 3) { - umc_info = (union umc_info *) - (mode_info->atom_context->bios + data_offset); switch (crev) { case 1: umc_config = le32_to_cpu(umc_info->v31.umc_config); @@ -533,6 +533,20 @@ bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev) /* unsupported crev */ return false; } + } else if (frev == 4) { + switch (crev) { + case 0: + umc_config1 = le32_to_cpu(umc_info->v40.umc_config1); + ecc_default_enabled = + (umc_config1 & UMC_CONFIG1__ENABLE_ECC_CAPABLE) ? true : false; + break; + default: + /* unsupported crev */ + return false; + } + } else { + /* unsupported frev */ + return false; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 49dd9aa8da70..efdb1c48f431 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -127,7 +127,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, { struct drm_gem_object *gobj; unsigned long size; - int r; gobj = drm_gem_object_lookup(p->filp, data->handle); if (gobj == NULL) @@ -137,23 +136,14 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, drm_gem_object_put(gobj); size = amdgpu_bo_size(p->uf_bo); - if (size != PAGE_SIZE || (data->offset + 8) > size) { - r = -EINVAL; - goto error_unref; - } + if (size != PAGE_SIZE || data->offset > (size - 8)) + return -EINVAL; - if (amdgpu_ttm_tt_get_usermm(p->uf_bo->tbo.ttm)) { - r = -EINVAL; - goto error_unref; - } + if (amdgpu_ttm_tt_get_usermm(p->uf_bo->tbo.ttm)) + return -EINVAL; *offset = data->offset; - return 0; - -error_unref: - amdgpu_bo_unref(&p->uf_bo); - return r; } static int amdgpu_cs_p1_bo_handles(struct amdgpu_cs_parser *p, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e77f048c99d8..3f001a50b34a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -885,13 +885,20 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev, */ static int amdgpu_device_asic_init(struct amdgpu_device *adev) { + int ret; + amdgpu_asic_pre_asic_init(adev); if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3) || - adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) - return amdgpu_atomfirmware_asic_init(adev, true); - else + adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) { + amdgpu_psp_wait_for_bootloader(adev); + ret = amdgpu_atomfirmware_asic_init(adev, true); + return ret; + } else { return amdgpu_atom_asic_init(adev->mode_info.atom_context); + } + + return 0; } /** @@ -4694,9 +4701,12 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) } if (ret) - dev_err(adev->dev, "GPU mode1 reset failed\n"); + goto mode1_reset_failed; amdgpu_device_load_pci_state(adev->pdev); + ret = amdgpu_psp_wait_for_bootloader(adev); + if (ret) + goto mode1_reset_failed; /* wait for asic to come out of reset */ for (i = 0; i < adev->usec_timeout; i++) { @@ -4707,7 +4717,17 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) udelay(1); } + if (i >= adev->usec_timeout) { + ret = -ETIMEDOUT; + goto mode1_reset_failed; + } + amdgpu_atombios_scratch_regs_engine_hung(adev, false); + + return 0; + +mode1_reset_failed: + dev_err(adev->dev, "GPU mode1 reset failed\n"); return ret; } @@ -4849,7 +4869,7 @@ static void amdgpu_reset_capture_coredumpm(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); ktime_get_ts64(&adev->reset_time); - dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_KERNEL, + dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_NOWAIT, amdgpu_devcoredump_read, amdgpu_devcoredump_free); } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 74ffe6581c85..7d5e7ad28ba8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1390,6 +1390,7 @@ union gc_info { struct gc_info_v1_1 v1_1; struct gc_info_v1_2 v1_2; struct gc_info_v2_0 v2; + struct gc_info_v2_1 v2_1; }; static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) @@ -1465,6 +1466,15 @@ static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) / le32_to_cpu(gc_info->v2.gc_num_sh_per_se); adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc); + if (gc_info->v2.header.version_minor == 1) { + adev->gfx.config.gc_num_tcp_per_sa = le32_to_cpu(gc_info->v2_1.gc_num_tcp_per_sh); + adev->gfx.config.gc_tcp_size_per_cu = le32_to_cpu(gc_info->v2_1.gc_tcp_size_per_cu); + adev->gfx.config.gc_num_sdp_interface = le32_to_cpu(gc_info->v2_1.gc_num_sdp_interface); /* per XCD */ + adev->gfx.config.gc_num_cu_per_sqc = le32_to_cpu(gc_info->v2_1.gc_num_cu_per_sqc); + adev->gfx.config.gc_l1_instruction_cache_size_per_sqc = le32_to_cpu(gc_info->v2_1.gc_instruction_cache_size_per_sqc); + adev->gfx.config.gc_l1_data_cache_size_per_sqc = le32_to_cpu(gc_info->v2_1.gc_scalar_data_cache_size_per_sqc); + adev->gfx.config.gc_tcc_size = le32_to_cpu(gc_info->v2_1.gc_tcc_size); /* per XCD */ + } break; default: dev_err(adev->dev, @@ -1478,6 +1488,7 @@ static int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) union mall_info { struct mall_info_v1_0 v1; + struct mall_info_v2_0 v2; }; static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev) @@ -1518,6 +1529,10 @@ static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev) adev->gmc.mall_size = mall_size; adev->gmc.m_half_use = half_use; break; + case 2: + mall_size_per_umc = le32_to_cpu(mall_info->v2.mall_size_per_umc); + adev->gmc.mall_size = mall_size_per_umc * adev->gmc.num_umc; + break; default: dev_err(adev->dev, "Unhandled MALL info table %d.%d\n", diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index d20dd3f852fc..363e6a2cad8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,6 +38,8 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_fb_helper.h> #include <drm/drm_gem_framebuffer_helper.h> @@ -532,11 +534,29 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, return true; } +static int amdgpu_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, unsigned int num_clips) +{ + + if (file) + return -ENOSYS; + + return drm_atomic_helper_dirtyfb(fb, file, flags, color, clips, + num_clips); +} + static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, }; +static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { + .destroy = drm_gem_fb_destroy, + .create_handle = drm_gem_fb_create_handle, + .dirty = amdgpu_dirtyfb +}; + uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags) { @@ -1139,7 +1159,11 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, if (ret) goto err; - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (drm_drv_uses_atomic_modeset(dev)) + ret = drm_framebuffer_init(dev, &rfb->base, + &amdgpu_fb_funcs_atomic); + else + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); if (ret) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index a4ff515ce896..395c1768b9fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -241,6 +241,9 @@ struct amdgpu_gfx_config { uint32_t gc_gl1c_per_sa; uint32_t gc_gl1c_size_per_instance; uint32_t gc_gl2c_per_gpu; + uint32_t gc_tcp_size_per_cu; + uint32_t gc_num_cu_per_sqc; + uint32_t gc_tcc_size; }; struct amdgpu_cu_info { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8fdca54bb8a1..429ef212c1f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2078,6 +2078,17 @@ int psp_securedisplay_invoke(struct psp_context *psp, uint32_t ta_cmd_id) } /* SECUREDISPLAY end */ +int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev) +{ + struct psp_context *psp = &adev->psp; + int ret = 0; + + if (!amdgpu_sriov_vf(adev) && psp->funcs && psp->funcs->wait_for_bootloader != NULL) + ret = psp->funcs->wait_for_bootloader(psp); + + return ret; +} + static int psp_hw_start(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 3384eb94fde0..3e67ed63e638 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -109,6 +109,7 @@ enum psp_reg_prog_id { struct psp_funcs { int (*init_microcode)(struct psp_context *psp); + int (*wait_for_bootloader)(struct psp_context *psp); int (*bootloader_load_kdb)(struct psp_context *psp); int (*bootloader_load_spl)(struct psp_context *psp); int (*bootloader_load_sysdrv)(struct psp_context *psp); @@ -533,4 +534,6 @@ int psp_spatial_partition(struct psp_context *psp, int mode); int is_psp_fw_valid(struct psp_bin_desc bin); +int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 7689395e44fd..3c4600e15b86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -764,7 +764,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); union ta_ras_cmd_input *info; - int ret = 0; + int ret; if (!con) return -EINVAL; @@ -773,7 +773,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, if (enable && head->block != AMDGPU_RAS_BLOCK__GFX && !amdgpu_ras_is_feature_allowed(adev, head)) - goto out; + return 0; /* Only enable gfx ras feature from host side */ if (head->block == AMDGPU_RAS_BLOCK__GFX && @@ -801,16 +801,16 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, enable ? "enable":"disable", get_ras_block_str(head), amdgpu_ras_is_poison_mode_supported(adev), ret); - goto out; + return ret; } + + kfree(info); } /* setup the obj */ __amdgpu_ras_feature_enable(adev, head, enable); -out: - if (head->block == AMDGPU_RAS_BLOCK__GFX) - kfree(info); - return ret; + + return 0; } /* Only used in device probe stage and called only once. */ @@ -2399,6 +2399,7 @@ static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev)) { switch (adev->ip_versions[MP0_HWIP][0]) { case IP_VERSION(13, 0, 2): + case IP_VERSION(13, 0, 6): return true; default: return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 4764d2171f92..595d5e535aca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -158,9 +158,10 @@ static bool __is_ras_eeprom_supported(struct amdgpu_device *adev) case IP_VERSION(11, 0, 7): /* Sienna cichlid */ case IP_VERSION(13, 0, 0): case IP_VERSION(13, 0, 2): /* Aldebaran */ - case IP_VERSION(13, 0, 6): case IP_VERSION(13, 0, 10): return true; + case IP_VERSION(13, 0, 6): + return (adev->gmc.is_app_apu) ? false : true; default: return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 57ed4e5c294c..0a26a00074a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -203,6 +203,9 @@ static void gfx_v9_4_3_init_golden_registers(struct amdgpu_device *adev) if (adev->rev_id == 0) { WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL1, REDUCE_FIFO_DEPTH_BY_2, 2); + } else { + WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, + SPARE, 0x1); } } } @@ -860,11 +863,15 @@ static int gfx_v9_4_3_sw_init(void *handle) if (r) return r; - r = amdgpu_gfx_sysfs_init(adev); + r = amdgpu_gfx_ras_sw_init(adev); if (r) return r; - return amdgpu_gfx_ras_sw_init(adev); + + if (!amdgpu_sriov_vf(adev)) + r = amdgpu_gfx_sysfs_init(adev); + + return r; } static int gfx_v9_4_3_sw_fini(void *handle) @@ -885,7 +892,8 @@ static int gfx_v9_4_3_sw_fini(void *handle) gfx_v9_4_3_mec_fini(adev); amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj); gfx_v9_4_3_free_microcode(adev); - amdgpu_gfx_sysfs_fini(adev); + if (!amdgpu_sriov_vf(adev)) + amdgpu_gfx_sysfs_fini(adev); return 0; } @@ -2219,15 +2227,6 @@ static void gfx_v9_4_3_xcc_update_sram_fgcg(struct amdgpu_device *adev, WREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CGTT_MGCG_OVERRIDE, data); - def = data = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CLK_CNTL); - - if (enable) - data &= ~RLC_CLK_CNTL__RLC_SRAM_CLK_GATER_OVERRIDE_MASK; - else - data |= RLC_CLK_CNTL__RLC_SRAM_CLK_GATER_OVERRIDE_MASK; - - if (def != data) - WREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CLK_CNTL, data); } static void gfx_v9_4_3_xcc_update_repeater_fgcg(struct amdgpu_device *adev, @@ -4048,7 +4047,8 @@ static void gfx_v9_4_3_inst_enable_watchdog_timer(struct amdgpu_device *adev, uint32_t i; uint32_t data; - data = REG_SET_FIELD(0, SQ_TIMEOUT_CONFIG, TIMEOUT_FATAL_DISABLE, + data = RREG32_SOC15(GC, GET_INST(GC, 0), regSQ_TIMEOUT_CONFIG); + data = REG_SET_FIELD(data, SQ_TIMEOUT_CONFIG, TIMEOUT_FATAL_DISABLE, amdgpu_watchdog_timer.timeout_fatal_disable ? 1 : 0); if (amdgpu_watchdog_timer.timeout_fatal_disable && diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 15612915bb6c..1de79d660285 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -360,8 +360,10 @@ static int jpeg_v4_0_3_hw_fini(void *handle) cancel_delayed_work_sync(&adev->jpeg.idle_work); - if (adev->jpeg.cur_state != AMD_PG_STATE_GATE) - ret = jpeg_v4_0_3_set_powergating_state(adev, AMD_PG_STATE_GATE); + if (!amdgpu_sriov_vf(adev)) { + if (adev->jpeg.cur_state != AMD_PG_STATE_GATE) + ret = jpeg_v4_0_3_set_powergating_state(adev, AMD_PG_STATE_GATE); + } return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c index 9ea072374cb7..f85eec05d218 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c @@ -437,6 +437,24 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev) XCC_DOORBELL_FENCE__SHUB_SLV_MODE_MASK); } + + if (!amdgpu_sriov_vf(adev)) { + u32 baco_cntl; + for_each_inst(i, adev->aid_mask) { + baco_cntl = RREG32_SOC15(NBIO, i, regBIF_BX0_BACO_CNTL); + if (baco_cntl & (BIF_BX0_BACO_CNTL__BACO_DUMMY_EN_MASK | + BIF_BX0_BACO_CNTL__BACO_EN_MASK)) { + baco_cntl &= ~( + BIF_BX0_BACO_CNTL__BACO_DUMMY_EN_MASK | + BIF_BX0_BACO_CNTL__BACO_EN_MASK); + dev_dbg(adev->dev, + "Unsetting baco dummy mode %x", + baco_cntl); + WREG32_SOC15(NBIO, i, regBIF_BX0_BACO_CNTL, + baco_cntl); + } + } + } } static u64 nbio_v7_9_get_pcie_replay_count(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 10b17bd5aebe..469eed084976 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -133,12 +133,32 @@ static bool psp_v13_0_is_sos_alive(struct psp_context *psp) return sol_reg != 0x0; } -static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) +static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; + int retry_loop, ret; - int ret; - int retry_loop; + for (retry_loop = 0; retry_loop < 70; retry_loop++) { + /* Wait for bootloader to signify that is + ready having bit 31 of C2PMSG_33 set to 1 */ + ret = psp_wait_for( + psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_33), + 0x80000000, 0xffffffff, false); + + if (ret == 0) + break; + } + + if (ret) + dev_warn(adev->dev, "Bootloader wait timed out"); + + return ret; +} + +static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + int retry_loop, ret; /* Wait for bootloader to signify that it is ready having bit 31 of * C2PMSG_35 set to 1. All other bits are expected to be cleared. @@ -157,6 +177,19 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) return ret; } +static int psp_v13_0_wait_for_bootloader_steady_state(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + + if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6)) { + psp_v13_0_wait_for_vmbx_ready(psp); + + return psp_v13_0_wait_for_bootloader(psp); + } + + return 0; +} + static int psp_v13_0_bootloader_load_component(struct psp_context *psp, struct psp_bin_desc *bin_desc, enum psp_bootloader_cmd bl_cmd) @@ -714,6 +747,7 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp) static const struct psp_funcs psp_v13_0_funcs = { .init_microcode = psp_v13_0_init_microcode, + .wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state, .bootloader_load_kdb = psp_v13_0_bootloader_load_kdb, .bootloader_load_spl = psp_v13_0_bootloader_load_spl, .bootloader_load_sysdrv = psp_v13_0_bootloader_load_sysdrv, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index c45721ca916e..f5be40d7ba36 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -559,8 +559,10 @@ soc15_asic_reset_method(struct amdgpu_device *adev) */ if (amdgpu_gpu_recovery == 4 || amdgpu_gpu_recovery == 5) return AMD_RESET_METHOD_MODE2; + else if (!(adev->flags & AMD_IS_APU)) + return AMD_RESET_METHOD_MODE1; else - return AMD_RESET_METHOD_NONE; + return AMD_RESET_METHOD_MODE2; default: break; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index f0731a6a5306..830396b1c3b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -384,7 +384,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, default: break; } - kfd_signal_event_interrupt(pasid, context_id0 & 0xffffff, 24); + kfd_signal_event_interrupt(pasid, sq_int_data, 24); } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 2319467d2d95..0bbf0edbabd4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -457,6 +457,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, mqd->is_occupied = kfd_is_occupied_cp; mqd->mqd_size = sizeof(struct v11_compute_mqd); mqd->get_wave_state = get_wave_state; + mqd->mqd_stride = kfd_mqd_stride; #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd; #endif @@ -472,6 +473,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, mqd->destroy_mqd = destroy_hiq_mqd; mqd->is_occupied = kfd_is_occupied_cp; mqd->mqd_size = sizeof(struct v11_compute_mqd); + mqd->mqd_stride = kfd_mqd_stride; #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd; #endif @@ -501,6 +503,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type, mqd->destroy_mqd = kfd_destroy_mqd_sdma; mqd->is_occupied = kfd_is_occupied_sdma; mqd->mqd_size = sizeof(struct v11_sdma_mqd); + mqd->mqd_stride = kfd_mqd_stride; #if defined(CONFIG_DEBUG_FS) mqd->debugfs_show_mqd = debugfs_show_mqd_sdma; #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 011561605983..bb16b795d1bc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1686,6 +1686,8 @@ static int svm_range_validate_and_map(struct mm_struct *mm, WRITE_ONCE(p->svms.faulting_task, NULL); if (r) { pr_debug("failed %d to get svm range pages\n", r); + if (r == -EBUSY) + r = -EAGAIN; goto unreserve_out; } 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 268cb99a4c4b..88ba8b66de1f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -65,6 +65,7 @@ #include "amdgpu_dm_debugfs.h" #endif #include "amdgpu_dm_psr.h" +#include "amdgpu_dm_replay.h" #include "ivsrcid/ivsrcid_vislands30.h" @@ -4265,6 +4266,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) enum dc_connection_type new_connection_type = dc_connection_none; const struct dc_plane_cap *plane; bool psr_feature_enabled = false; + bool replay_feature_enabled = false; int max_overlay = dm->dc->caps.max_slave_planes; dm->display_indexes_num = dm->dc->caps.max_streams; @@ -4374,6 +4376,20 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) } } + if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) { + switch (adev->ip_versions[DCE_HWIP][0]) { + case IP_VERSION(3, 1, 4): + case IP_VERSION(3, 1, 5): + case IP_VERSION(3, 1, 6): + case IP_VERSION(3, 2, 0): + case IP_VERSION(3, 2, 1): + replay_feature_enabled = true; + break; + default: + replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK; + break; + } + } /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { struct dc_link *link = NULL; @@ -4422,6 +4438,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) amdgpu_dm_update_connector_after_detect(aconnector); setup_backlight_device(dm, aconnector); + /* + * Disable psr if replay can be enabled + */ + if (replay_feature_enabled && amdgpu_dm_setup_replay(link, aconnector)) + psr_feature_enabled = false; + if (psr_feature_enabled) amdgpu_dm_set_psr_caps(link); @@ -6004,7 +6026,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) drm_mode_set_crtcinfo(&saved_mode, 0); - else + else if (!old_stream) drm_mode_set_crtcinfo(&mode, 0); /* diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 30d4c6fd95f5..97b7a0b8a1c2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -29,6 +29,7 @@ #include "dc.h" #include "amdgpu.h" #include "amdgpu_dm_psr.h" +#include "amdgpu_dm_replay.h" #include "amdgpu_dm_crtc.h" #include "amdgpu_dm_plane.h" #include "amdgpu_dm_trace.h" @@ -123,7 +124,12 @@ static void vblank_control_worker(struct work_struct *work) * fill_dc_dirty_rects(). */ if (vblank_work->stream && vblank_work->stream->link) { - if (vblank_work->enable) { + /* + * Prioritize replay, instead of psr + */ + if (vblank_work->stream->link->replay_settings.replay_feature_enabled) + amdgpu_dm_replay_enable(vblank_work->stream, false); + else if (vblank_work->enable) { if (vblank_work->stream->link->psr_settings.psr_version < DC_PSR_VERSION_SU_1 && vblank_work->stream->link->psr_settings.psr_allow_active) amdgpu_dm_psr_disable(vblank_work->stream); @@ -132,6 +138,7 @@ static void vblank_control_worker(struct work_struct *work) #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY !amdgpu_dm_crc_window_is_activated(&vblank_work->acrtc->base) && #endif + vblank_work->stream->link->panel_config.psr.disallow_replay && vblank_work->acrtc->dm_irq_params.allow_psr_entry) { amdgpu_dm_psr_enable(vblank_work->stream); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 8eeca160d434..cc74dd69acf2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1269,6 +1269,13 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane, attributes.rotation_angle = 0; attributes.attribute_flags.value = 0; + /* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM + * legacy gamma setup. + */ + if (crtc_state->cm_is_degamma_srgb && + adev->dm.dc->caps.color.dpp.gamma_corr) + attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1; + attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; if (crtc_state->stream) { @@ -1468,6 +1475,15 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, drm_plane_create_blend_mode_property(plane, blend_caps); } + if (plane->type == DRM_PLANE_TYPE_PRIMARY) { + drm_plane_create_zpos_immutable_property(plane, 0); + } else if (plane->type == DRM_PLANE_TYPE_OVERLAY) { + unsigned int zpos = 1 + drm_plane_index(plane); + drm_plane_create_zpos_property(plane, zpos, 1, 254); + } else if (plane->type == DRM_PLANE_TYPE_CURSOR) { + drm_plane_create_zpos_immutable_property(plane, 255); + } + if (plane->type == DRM_PLANE_TYPE_PRIMARY && plane_cap && (plane_cap->pixel_format_support.nv12 || diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile index 69ffd4424dc7..1b8c2aef4633 100644 --- a/drivers/gpu/drm/amd/display/dc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/Makefile @@ -78,3 +78,4 @@ DC_EDID += dc_edid_parser.o AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB)) AMD_DISPLAY_EDID = $(addprefix $(AMDDALPATH)/dc/,$(DC_EDID)) AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB) $(AMD_DISPLAY_EDID) + diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 3e0da873cf4c..1042cf1a3ab0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -32,6 +32,7 @@ #define MAX_INSTANCE 6 #define MAX_SEGMENT 6 +#define SMU_REGISTER_WRITE_RETRY_COUNT 5 struct IP_BASE_INSTANCE { unsigned int segment[MAX_SEGMENT]; @@ -132,6 +133,8 @@ static int dcn315_smu_send_msg_with_param( unsigned int msg_id, unsigned int param) { uint32_t result; + uint32_t i = 0; + uint32_t read_back_data; result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); @@ -148,10 +151,19 @@ static int dcn315_smu_send_msg_with_param( /* Set the parameter register for the SMU message, unit is Mhz */ REG_WRITE(MP1_SMN_C2PMSG_37, param); - /* Trigger the message transaction by writing the message ID */ - generic_write_indirect_reg(CTX, - REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), - mmMP1_C2PMSG_3, msg_id); + for (i = 0; i < SMU_REGISTER_WRITE_RETRY_COUNT; i++) { + /* Trigger the message transaction by writing the message ID */ + generic_write_indirect_reg(CTX, + REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), + mmMP1_C2PMSG_3, msg_id); + read_back_data = generic_read_indirect_reg(CTX, + REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), + mmMP1_C2PMSG_3); + if (read_back_data == msg_id) + break; + udelay(2); + smu_print("SMU msg id write fail %x times. \n", i + 1); + } result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 566d7045b2de..3a9077b60029 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2073,12 +2073,12 @@ enum dc_status dc_commit_streams(struct dc *dc, } } - /* Check for case where we are going from odm 2:1 to max - * pipe scenario. For these cases, we will call - * commit_minimal_transition_state() to exit out of odm 2:1 - * first before processing new streams + /* ODM Combine 2:1 power optimization is only applied for single stream + * scenario, it uses extra pipes than needed to reduce power consumption + * We need to switch off this feature to make room for new streams. */ - if (stream_count == dc->res_pool->pipe_count) { + if (stream_count > dc->current_state->stream_count && + dc->current_state->stream_count == 1) { for (i = 0; i < dc->res_pool->pipe_count; i++) { pipe = &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->next_odm_pipe) @@ -3501,6 +3501,45 @@ static void commit_planes_for_stream_fast(struct dc *dc, top_pipe_to_program->stream->update_flags.raw = 0; } +static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context) +{ +/* + * This function calls HWSS to wait for any potentially double buffered + * operations to complete. It should be invoked as a pre-amble prior + * to full update programming before asserting any HW locks. + */ + int pipe_idx; + int opp_inst; + int opp_count = dc->res_pool->pipe_count; + struct hubp *hubp; + int mpcc_inst; + const struct pipe_ctx *pipe_ctx; + + for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) { + pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx]; + + if (!pipe_ctx->stream) + continue; + + if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear) + pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg); + + hubp = pipe_ctx->plane_res.hubp; + if (!hubp) + continue; + + mpcc_inst = hubp->inst; + // MPCC inst is equal to pipe index in practice + for (opp_inst = 0; opp_inst < opp_count; opp_inst++) { + if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) { + dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst); + dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false; + break; + } + } + } +} + static void commit_planes_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, @@ -3519,24 +3558,9 @@ static void commit_planes_for_stream(struct dc *dc, // dc->current_state anymore, so we have to cache it before we apply // the new SubVP context subvp_prev_use = false; - - dc_z10_restore(dc); - - if (update_type == UPDATE_TYPE_FULL) { - /* wait for all double-buffer activity to clear on all pipes */ - int pipe_idx; - - for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx]; - - if (!pipe_ctx->stream) - continue; - - if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear) - pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg); - } - } + if (update_type == UPDATE_TYPE_FULL) + wait_for_outstanding_hw_updates(dc, context); if (update_type == UPDATE_TYPE_FULL) { dc_allow_idle_optimizations(dc, false); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 65fa9e21ad9c..e72f15ac0048 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1106,29 +1106,6 @@ void dcn20_blank_pixel_data( v_active, offset); - if (!blank && dc->debug.enable_single_display_2to1_odm_policy) { - /* when exiting dynamic ODM need to reinit DPG state for unused pipes */ - struct pipe_ctx *old_odm_pipe = dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx].next_odm_pipe; - - odm_pipe = pipe_ctx->next_odm_pipe; - - while (old_odm_pipe) { - if (!odm_pipe || old_odm_pipe->pipe_idx != odm_pipe->pipe_idx) - dc->hwss.set_disp_pattern_generator(dc, - old_odm_pipe, - CONTROLLER_DP_TEST_PATTERN_VIDEOMODE, - CONTROLLER_DP_COLOR_SPACE_UDEFINED, - COLOR_DEPTH_888, - NULL, - 0, - 0, - 0); - old_odm_pipe = old_odm_pipe->next_odm_pipe; - if (odm_pipe) - odm_pipe = odm_pipe->next_odm_pipe; - } - } - if (!blank) if (stream_res->abm) { dc->hwss.set_pipe(pipe_ctx); @@ -1584,17 +1561,6 @@ static void dcn20_update_dchubp_dpp( || plane_state->update_flags.bits.global_alpha_change || plane_state->update_flags.bits.per_pixel_alpha_change) { // MPCC inst is equal to pipe index in practice - int mpcc_inst = hubp->inst; - int opp_inst; - int opp_count = dc->res_pool->pipe_count; - - for (opp_inst = 0; opp_inst < opp_count; opp_inst++) { - if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) { - dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst); - dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false; - break; - } - } hws->funcs.update_mpcc(dc, pipe_ctx); } @@ -1722,11 +1688,16 @@ static void dcn20_program_pipe( struct dc_state *context) { struct dce_hwseq *hws = dc->hwseq; - /* Only need to unblank on top pipe */ - if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level) - && !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe) - hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible); + /* Only need to unblank on top pipe */ + if (resource_is_pipe_type(pipe_ctx, OTG_MASTER)) { + if (pipe_ctx->update_flags.bits.enable || + pipe_ctx->update_flags.bits.odm || + pipe_ctx->stream->update_flags.bits.abm_level) + hws->funcs.blank_pixel_data(dc, pipe_ctx, + !pipe_ctx->plane_state || + !pipe_ctx->plane_state->visible); + } /* Only update TG on top pipe */ if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe 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 6cef62d7a2e5..255713ec29bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -987,3 +987,20 @@ void dcn30_prepare_bandwidth(struct dc *dc, } } +void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx, + int num_pipes, const struct dc_static_screen_params *params) +{ + unsigned int i; + unsigned int triggers = 0; + + if (params->triggers.surface_update) + triggers |= 0x100; + if (params->triggers.cursor_update) + triggers |= 0x8; + if (params->triggers.force_trigger) + triggers |= 0x1; + + for (i = 0; i < num_pipes; i++) + pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(pipe_ctx[i]->stream_res.tg, + triggers, params->num_frames); +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h index a24a8e33a3d2..ce19c54097f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h @@ -87,5 +87,7 @@ void dcn30_set_hubp_blank(const struct dc *dc, void dcn30_prepare_bandwidth(struct dc *dc, struct dc_state *context); +void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx, + int num_pipes, const struct dc_static_screen_params *params); #endif /* __DC_HWSS_DCN30_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c index 3d19acaa12f3..0de8b2783cf6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c @@ -64,7 +64,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = { .update_bandwidth = dcn20_update_bandwidth, .set_drr = dcn10_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn30_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c index 257df8660b4c..61205cdbe2d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c @@ -75,6 +75,7 @@ static const struct hw_sequencer_funcs dcn301_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index fc25cc300a17..1d7bc1e39afe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -67,7 +67,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .update_bandwidth = dcn20_update_bandwidth, .set_drr = dcn10_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn30_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index ca8fe55c33b8..4ef85c3a0688 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -69,7 +69,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = { .update_bandwidth = dcn20_update_bandwidth, .set_drr = dcn10_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn30_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index 777b2fac20c4..c7417147dff1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -65,7 +65,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .update_bandwidth = dcn20_update_bandwidth, .set_drr = dcn10_set_drr, .get_position = dcn10_get_position, - .set_static_screen_control = dcn10_set_static_screen_control, + .set_static_screen_control = dcn30_set_static_screen_control, .setup_stereo = dcn10_setup_stereo, .set_avmute = dcn30_set_avmute, .log_hw_state = dcn10_log_hw_state, 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 935cd23e6a01..f9d601c8c721 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -2564,18 +2564,128 @@ static int find_optimal_free_pipe_as_secondary_dpp_pipe( return free_pipe_idx; } +static struct pipe_ctx *find_idle_secondary_pipe_check_mpo( + struct resource_context *res_ctx, + const struct resource_pool *pool, + const struct pipe_ctx *primary_pipe) +{ + int i; + struct pipe_ctx *secondary_pipe = NULL; + struct pipe_ctx *next_odm_mpo_pipe = NULL; + int primary_index, preferred_pipe_idx; + struct pipe_ctx *old_primary_pipe = NULL; + + /* + * Modified from find_idle_secondary_pipe + * With windowed MPO and ODM, we want to avoid the case where we want a + * free pipe for the left side but the free pipe is being used on the + * right side. + * Add check on current_state if the primary_pipe is the left side, + * to check the right side ( primary_pipe->next_odm_pipe ) to see if + * it is using a pipe for MPO ( primary_pipe->next_odm_pipe->bottom_pipe ) + * - If so, then don't use this pipe + * EXCEPTION - 3 plane ( 2 MPO plane ) case + * - in this case, the primary pipe has already gotten a free pipe for the + * MPO window in the left + * - when it tries to get a free pipe for the MPO window on the right, + * it will see that it is already assigned to the right side + * ( primary_pipe->next_odm_pipe ). But in this case, we want this + * free pipe, since it will be for the right side. So add an + * additional condition, that skipping the free pipe on the right only + * applies if the primary pipe has no bottom pipe currently assigned + */ + if (primary_pipe) { + primary_index = primary_pipe->pipe_idx; + old_primary_pipe = &primary_pipe->stream->ctx->dc->current_state->res_ctx.pipe_ctx[primary_index]; + if ((old_primary_pipe->next_odm_pipe) && (old_primary_pipe->next_odm_pipe->bottom_pipe) + && (!primary_pipe->bottom_pipe)) + next_odm_mpo_pipe = old_primary_pipe->next_odm_pipe->bottom_pipe; + + preferred_pipe_idx = (pool->pipe_count - 1) - primary_pipe->pipe_idx; + if ((res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) && + !(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == preferred_pipe_idx)) { + secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx]; + secondary_pipe->pipe_idx = preferred_pipe_idx; + } + } + + /* + * search backwards for the second pipe to keep pipe + * assignment more consistent + */ + if (!secondary_pipe) + for (i = pool->pipe_count - 1; i >= 0; i--) { + if ((res_ctx->pipe_ctx[i].stream == NULL) && + !(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == i)) { + secondary_pipe = &res_ctx->pipe_ctx[i]; + secondary_pipe->pipe_idx = i; + break; + } + } + + return secondary_pipe; +} + +static struct pipe_ctx *dcn32_acquire_idle_pipe_for_head_pipe_in_layer( + struct dc_state *state, + const struct resource_pool *pool, + struct dc_stream_state *stream, + const struct pipe_ctx *head_pipe) +{ + struct resource_context *res_ctx = &state->res_ctx; + struct pipe_ctx *idle_pipe, *pipe; + struct resource_context *old_ctx = &stream->ctx->dc->current_state->res_ctx; + int head_index; + + if (!head_pipe) + ASSERT(0); + + /* + * Modified from dcn20_acquire_idle_pipe_for_layer + * Check if head_pipe in old_context already has bottom_pipe allocated. + * - If so, check if that pipe is available in the current context. + * -- If so, reuse pipe from old_context + */ + head_index = head_pipe->pipe_idx; + pipe = &old_ctx->pipe_ctx[head_index]; + if (pipe->bottom_pipe && res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx].stream == NULL) { + idle_pipe = &res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx]; + idle_pipe->pipe_idx = pipe->bottom_pipe->pipe_idx; + } else { + idle_pipe = find_idle_secondary_pipe_check_mpo(res_ctx, pool, head_pipe); + if (!idle_pipe) + return NULL; + } + + idle_pipe->stream = head_pipe->stream; + idle_pipe->stream_res.tg = head_pipe->stream_res.tg; + idle_pipe->stream_res.opp = head_pipe->stream_res.opp; + + idle_pipe->plane_res.hubp = pool->hubps[idle_pipe->pipe_idx]; + idle_pipe->plane_res.ipp = pool->ipps[idle_pipe->pipe_idx]; + idle_pipe->plane_res.dpp = pool->dpps[idle_pipe->pipe_idx]; + idle_pipe->plane_res.mpcc_inst = pool->dpps[idle_pipe->pipe_idx]->inst; + + return idle_pipe; +} + struct pipe_ctx *dcn32_acquire_free_pipe_as_secondary_dpp_pipe( const struct dc_state *cur_ctx, struct dc_state *new_ctx, const struct resource_pool *pool, const struct pipe_ctx *opp_head_pipe) { - int free_pipe_idx = - find_optimal_free_pipe_as_secondary_dpp_pipe( - &cur_ctx->res_ctx, &new_ctx->res_ctx, - pool, opp_head_pipe); + + int free_pipe_idx; struct pipe_ctx *free_pipe; + if (!opp_head_pipe->stream->ctx->dc->config.enable_windowed_mpo_odm) + return dcn32_acquire_idle_pipe_for_head_pipe_in_layer( + new_ctx, pool, opp_head_pipe->stream, opp_head_pipe); + + free_pipe_idx = find_optimal_free_pipe_as_secondary_dpp_pipe( + &cur_ctx->res_ctx, &new_ctx->res_ctx, + pool, opp_head_pipe); if (free_pipe_idx >= 0) { free_pipe = &new_ctx->res_ctx.pipe_ctx[free_pipe_idx]; free_pipe->pipe_idx = free_pipe_idx; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 8afda5ecc0cd..5805fb02af14 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -1099,6 +1099,11 @@ void dcn20_calculate_dlg_params(struct dc *dc, context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest; + if (dc->ctx->dce_version < DCN_VERSION_3_1 && + context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid) + dcn20_adjust_freesync_v_startup( + &context->res_ctx.pipe_ctx[i].stream->timing, + &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start); pipe_idx++; } @@ -1927,7 +1932,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - int i = 0; display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); @@ -1951,15 +1955,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid) - dcn20_adjust_freesync_v_startup( - &context->res_ctx.pipe_ctx[i].stream->timing, - &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start); - } - BW_VAL_TRACE_END_WATERMARKS(); goto validate_out; @@ -2232,7 +2227,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc, int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - int i = 0; display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); @@ -2261,15 +2255,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc, dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate); dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid) - dcn20_adjust_freesync_v_startup( - &context->res_ctx.pipe_ctx[i].stream->timing, - &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start); - } - BW_VAL_TRACE_END_WATERMARKS(); goto validate_out; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 07adb614366e..fb21572750e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -293,6 +293,17 @@ static unsigned int micro_sec_to_vert_lines(unsigned int num_us, struct dc_crtc_ return num_lines; } +static unsigned int get_vertical_back_porch(struct dc_crtc_timing *timing) +{ + unsigned int v_active = 0, v_blank = 0, v_back_porch = 0; + + v_active = timing->v_border_top + timing->v_addressable + timing->v_border_bottom; + v_blank = timing->v_total - v_active; + v_back_porch = v_blank - timing->v_front_porch - timing->v_sync_width; + + return v_back_porch; +} + int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, bool fast_validate) @@ -310,6 +321,7 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) { struct dc_crtc_timing *timing; unsigned int num_lines = 0; + unsigned int v_back_porch = 0; if (!res_ctx->pipe_ctx[i].stream) continue; @@ -323,9 +335,16 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c else pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total; + v_back_porch = get_vertical_back_porch(timing); + pipes[pipe_cnt].pipe.dest.vblank_nom = timing->v_total - pipes[pipe_cnt].pipe.dest.vactive; pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, num_lines); - pipes[pipe_cnt].pipe.dest.vblank_nom = max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width); + // vblank_nom should not smaller than (VSync (timing->v_sync_width + v_back_porch) + 2) + // + 2 is because + // 1 -> VStartup_start should be 1 line before VSync + // 1 -> always reserve 1 line between start of vblank to vstartup signal + pipes[pipe_cnt].pipe.dest.vblank_nom = + max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width + v_back_porch + 2); pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, max_allowed_vblank_nom); if (pipe->plane_state && diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index dbd60811f95d..ef3a67409021 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -338,7 +338,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync, * - Delta for CEIL: delta_from_mid_point_in_us_1 * - Delta for FLOOR: delta_from_mid_point_in_us_2 */ - if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) { + if (mid_point_frames_ceil && + (last_render_time_in_us / mid_point_frames_ceil) < + in_out_vrr->min_duration_in_us) { /* Check for out of range. * If using CEIL produces a value that is out of range, * then we are forced to use FLOOR. @@ -385,8 +387,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Either we've calculated the number of frames to insert, * or we need to insert min duration frames */ - if (last_render_time_in_us / frames_to_insert < - in_out_vrr->min_duration_in_us){ + if (frames_to_insert && + (last_render_time_in_us / frames_to_insert) < + in_out_vrr->min_duration_in_us){ frames_to_insert -= (frames_to_insert > 1) ? 1 : 0; } diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index abe829bbd54a..67d7b7ee8a2a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -240,6 +240,7 @@ enum DC_FEATURE_MASK { DC_DISABLE_LTTPR_DP2_0 = (1 << 6), //0x40, disabled by default DC_PSR_ALLOW_SMU_OPT = (1 << 7), //0x80, disabled by default DC_PSR_ALLOW_MULTI_DISP_OPT = (1 << 8), //0x100, disabled by default + DC_REPLAY_MASK = (1 << 9), //0x200, disabled by default for dcn < 3.1.4 }; enum DC_DEBUG_MASK { @@ -250,6 +251,7 @@ enum DC_DEBUG_MASK { DC_DISABLE_PSR = 0x10, DC_FORCE_SUBVP_MCLK_SWITCH = 0x20, DC_DISABLE_MPO = 0x40, + DC_DISABLE_REPLAY = 0x50, DC_ENABLE_DPIA_TRACE = 0x80, }; diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index e68c1e280322..fa7d6ced786f 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -3117,6 +3117,24 @@ enum atom_umc_config1_def { UMC_CONFIG1__ENABLE_ECC_CAPABLE = 0x00010000, }; +struct atom_umc_info_v4_0 { + struct atom_common_table_header table_header; + uint32_t ucode_reserved[5]; + uint8_t umcip_min_ver; + uint8_t umcip_max_ver; + uint8_t vram_type; + uint8_t umc_config; + uint32_t mem_refclk_10khz; + uint32_t clk_reserved[4]; + uint32_t golden_reserved; + uint32_t umc_config1; + uint32_t reserved[2]; + uint8_t channel_num; + uint8_t channel_width; + uint8_t channel_reserve[2]; + uint8_t umc_info_reserved[16]; +}; + /* *************************************************************************** Data Table vram_info structure diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h index f43e29722ef7..7a9d473d0917 100644 --- a/drivers/gpu/drm/amd/include/discovery.h +++ b/drivers/gpu/drm/amd/include/discovery.h @@ -30,7 +30,7 @@ #define GC_TABLE_ID 0x4347 #define HARVEST_TABLE_SIGNATURE 0x56524148 #define VCN_INFO_TABLE_ID 0x004E4356 -#define MALL_INFO_TABLE_ID 0x4D414C4C +#define MALL_INFO_TABLE_ID 0x4C4C414D typedef enum { @@ -280,6 +280,36 @@ struct gc_info_v2_0 { uint32_t gc_num_packer_per_sc; }; +struct gc_info_v2_1 { + struct gpu_info_header header; + + uint32_t gc_num_se; + uint32_t gc_num_cu_per_sh; + uint32_t gc_num_sh_per_se; + uint32_t gc_num_rb_per_se; + uint32_t gc_num_tccs; + uint32_t gc_num_gprs; + uint32_t gc_num_max_gs_thds; + uint32_t gc_gs_table_depth; + uint32_t gc_gsprim_buff_depth; + uint32_t gc_parameter_cache_depth; + uint32_t gc_double_offchip_lds_buffer; + uint32_t gc_wave_size; + uint32_t gc_max_waves_per_simd; + uint32_t gc_max_scratch_slots_per_cu; + uint32_t gc_lds_size; + uint32_t gc_num_sc_per_se; + uint32_t gc_num_packer_per_sc; + /* new for v2_1 */ + uint32_t gc_num_tcp_per_sh; + uint32_t gc_tcp_size_per_cu; + uint32_t gc_num_sdp_interface; + uint32_t gc_num_cu_per_sqc; + uint32_t gc_instruction_cache_size_per_sqc; + uint32_t gc_scalar_data_cache_size_per_sqc; + uint32_t gc_tcc_size; +}; + typedef struct harvest_info_header { uint32_t signature; /* Table Signature */ uint32_t version; /* Table Version */ @@ -312,6 +342,12 @@ struct mall_info_v1_0 { uint32_t reserved[5]; }; +struct mall_info_v2_0 { + struct mall_info_header header; + uint32_t mall_size_per_umc; + uint32_t reserved[8]; +}; + #define VCN_INFO_TABLE_MAX_NUM_INSTANCES 4 struct vcn_info_header { diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 5b1d73b00ef7..41147da54458 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -3311,8 +3311,10 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, (gc_ver != IP_VERSION(9, 4, 3)) && (attr == &sensor_dev_attr_temp2_input.dev_attr.attr || attr == &sensor_dev_attr_temp2_label.dev_attr.attr || + attr == &sensor_dev_attr_temp2_crit.dev_attr.attr || attr == &sensor_dev_attr_temp3_input.dev_attr.attr || - attr == &sensor_dev_attr_temp3_label.dev_attr.attr)) + attr == &sensor_dev_attr_temp3_label.dev_attr.attr || + attr == &sensor_dev_attr_temp3_crit.dev_attr.attr)) return 0; /* hotspot temperature for gc 9,4,3*/ @@ -3324,9 +3326,7 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, /* only SOC15 dGPUs support hotspot and mem temperatures */ if (((adev->flags & AMD_IS_APU) || gc_ver < IP_VERSION(9, 0, 0) || (gc_ver == IP_VERSION(9, 4, 3))) && - (attr == &sensor_dev_attr_temp2_crit.dev_attr.attr || - attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr || - attr == &sensor_dev_attr_temp3_crit.dev_attr.attr || + (attr == &sensor_dev_attr_temp2_crit_hyst.dev_attr.attr || attr == &sensor_dev_attr_temp3_crit_hyst.dev_attr.attr || attr == &sensor_dev_attr_temp1_emergency.dev_attr.attr || attr == &sensor_dev_attr_temp2_emergency.dev_attr.attr || @@ -3471,6 +3471,9 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a size = sizeof(uint32_t); if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_AVG_POWER, (void *)&query, &size)) seq_printf(m, "\t%u.%u W (average GPU)\n", query >> 8, query & 0xff); + size = sizeof(uint32_t); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER, (void *)&query, &size)) + seq_printf(m, "\t%u.%u W (current GPU)\n", query >> 8, query & 0xff); size = sizeof(value); seq_printf(m, "\n"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 95eb8a5eb54f..5a52098bcf16 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1031,10 +1031,7 @@ struct pptable_funcs { enum smu_feature_mask mask); /** - * @notify_display_change: Enable fast memory clock switching. - * - * Allows for fine grained memory clock switching but has more stringent - * timing requirements. + * @notify_display_change: General interface call to let SMU know about DC change */ int (*notify_display_change)(struct smu_context *smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h index 10cff75b44d5..e2ee855c7748 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_0_ppsmc.h @@ -138,7 +138,10 @@ #define PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel 0x4A #define PPSMC_MSG_SetPriorityDeltaGain 0x4B #define PPSMC_MSG_AllowIHHostInterrupt 0x4C -#define PPSMC_Message_Count 0x4D + +#define PPSMC_MSG_DALNotPresent 0x4E + +#define PPSMC_Message_Count 0x4F //Debug Dump Message #define DEBUGSMC_MSG_TestMessage 0x1 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index 252aef190c5c..9be4051c0865 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0x5 +#define SMU_METRICS_TABLE_VERSION 0x7 typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -198,7 +198,7 @@ typedef struct __attribute__((packed, aligned(4))) { uint32_t SocketThmResidencyAcc; uint32_t VrThmResidencyAcc; uint32_t HbmThmResidencyAcc; - uint32_t spare; + uint32_t GfxLockXCDMak; // New Items at end to maintain driver compatibility uint32_t GfxclkFrequency[8]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h index ae4f44c4b877..70a4a717fd3f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h @@ -83,13 +83,27 @@ #define PPSMC_MSG_GetMinGfxDpmFreq 0x32 #define PPSMC_MSG_GetMaxGfxDpmFreq 0x33 #define PPSMC_MSG_PrepareForDriverUnload 0x34 -#define PPSMC_Message_Count 0x35 +#define PPSMC_MSG_ReadThrottlerLimit 0x35 +#define PPSMC_MSG_QueryValidMcaCount 0x36 +#define PPSMC_MSG_McaBankDumpDW 0x37 +#define PPSMC_MSG_GetCTFLimit 0x38 +#define PPSMC_Message_Count 0x39 //PPSMC Reset Types for driver msg argument #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET 0x1 #define PPSMC_RESET_TYPE_DRIVER_MODE_2_RESET 0x2 #define PPSMC_RESET_TYPE_DRIVER_MODE_3_RESET 0x3 +//PPSMC Reset Types for driver msg argument +#define PPSMC_THROTTLING_LIMIT_TYPE_SOCKET 0x1 +#define PPSMC_THROTTLING_LIMIT_TYPE_HBM 0x2 + +//CTF/Throttle Limit types +#define PPSMC_AID_THM_TYPE 0x1 +#define PPSMC_CCD_THM_TYPE 0x2 +#define PPSMC_XCD_THM_TYPE 0x3 +#define PPSMC_HBM_THM_TYPE 0x4 + typedef uint32_t PPSMC_Result; typedef uint32_t PPSMC_MSG; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 297b70b9388f..e57265cf637c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -84,6 +84,7 @@ __SMU_DUMMY_MAP(SetTjMax), \ __SMU_DUMMY_MAP(SetFanTemperatureTarget), \ __SMU_DUMMY_MAP(PrepareMp1ForUnload), \ + __SMU_DUMMY_MAP(GetCTFLimit), \ __SMU_DUMMY_MAP(DramLogSetDramAddrHigh), \ __SMU_DUMMY_MAP(DramLogSetDramAddrLow), \ __SMU_DUMMY_MAP(DramLogSetDramSize), \ @@ -245,7 +246,8 @@ __SMU_DUMMY_MAP(AllowGpo), \ __SMU_DUMMY_MAP(Mode2Reset), \ __SMU_DUMMY_MAP(RequestI2cTransaction), \ - __SMU_DUMMY_MAP(GetMetricsTable), + __SMU_DUMMY_MAP(GetMetricsTable), \ + __SMU_DUMMY_MAP(DALNotPresent), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index f1282fc4b90a..0232adb95df3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -837,12 +837,8 @@ int smu_v13_0_notify_display_change(struct smu_context *smu) { int ret = 0; - if (!smu->pm_enabled) - return ret; - - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT) && - smu->adev->gmc.vram_type == AMDGPU_VRAM_TYPE_HBM) - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetUclkFastSwitch, 1, NULL); + if (!amdgpu_device_has_dc_support(smu->adev)) + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DALNotPresent, NULL); return ret; } 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 8b7403ba89d7..3903a47669e4 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 @@ -162,6 +162,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0), MSG_MAP(ReenableAcDcInterrupt, PPSMC_MSG_ReenableAcDcInterrupt, 0), + MSG_MAP(DALNotPresent, PPSMC_MSG_DALNotPresent, 0), }; static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = { @@ -2687,6 +2688,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .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, + .notify_display_change = smu_v13_0_notify_display_change, }; 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_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 6ed9cd0a1e4e..199a673b8120 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -132,6 +132,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU MSG_MAP(SetSoftMinGfxclk, PPSMC_MSG_SetSoftMinGfxClk, 0), MSG_MAP(SetSoftMaxGfxClk, PPSMC_MSG_SetSoftMaxGfxClk, 0), MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareForDriverUnload, 0), + MSG_MAP(GetCTFLimit, PPSMC_MSG_GetCTFLimit, 0), }; static const struct cmn2asic_mapping smu_v13_0_6_clk_map[SMU_CLK_COUNT] = { @@ -2081,6 +2082,55 @@ out: return ret; } +static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu, + struct smu_temperature_range *range) +{ + struct amdgpu_device *adev = smu->adev; + u32 aid_temp, xcd_temp, mem_temp; + uint32_t smu_version; + u32 ccd_temp = 0; + int ret; + + if (amdgpu_sriov_vf(smu->adev)) + return 0; + + if (!range) + return -EINVAL; + + /*Check smu version, GetCtfLimit message only supported for smu version 85.69 or higher */ + smu_cmn_get_smc_version(smu, NULL, &smu_version); + if (smu_version < 0x554500) + return 0; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit, + PPSMC_AID_THM_TYPE, &aid_temp); + if (ret) + goto failed; + + if (adev->flags & AMD_IS_APU) { + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit, + PPSMC_CCD_THM_TYPE, &ccd_temp); + if (ret) + goto failed; + } + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit, + PPSMC_XCD_THM_TYPE, &xcd_temp); + if (ret) + goto failed; + + range->hotspot_crit_max = max3(aid_temp, xcd_temp, ccd_temp) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetCTFLimit, + PPSMC_HBM_THM_TYPE, &mem_temp); + if (ret) + goto failed; + + range->mem_crit_max = mem_temp * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; +failed: + return ret; +} + static int smu_v13_0_6_mode1_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -2108,8 +2158,7 @@ static int smu_v13_0_6_mode1_reset(struct smu_context *smu) static bool smu_v13_0_6_is_mode1_reset_supported(struct smu_context *smu) { - /* TODO: Enable this when FW support is added */ - return false; + return true; } static bool smu_v13_0_6_is_mode2_reset_supported(struct smu_context *smu) @@ -2177,6 +2226,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, .get_gpu_metrics = smu_v13_0_6_get_gpu_metrics, + .get_thermal_temperature_range = smu_v13_0_6_get_thermal_temperature_range, .mode1_reset_is_support = smu_v13_0_6_is_mode1_reset_supported, .mode2_reset_is_support = smu_v13_0_6_is_mode2_reset_supported, .mode1_reset = smu_v13_0_6_mode1_reset, diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index e99a6fa03d45..a7e677598004 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -58,6 +58,7 @@ struct i915_perf_group; typedef u32 intel_engine_mask_t; #define ALL_ENGINES ((intel_engine_mask_t)~0ul) +#define VIRTUAL_ENGINES BIT(BITS_PER_TYPE(intel_engine_mask_t) - 1) struct intel_hw_status_page { struct list_head timelines; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index a0e3ef1c65d2..b5b7f2fe8c78 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -5470,6 +5470,9 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, ve->base.flags = I915_ENGINE_IS_VIRTUAL; + BUILD_BUG_ON(ilog2(VIRTUAL_ENGINES) < I915_NUM_ENGINES); + ve->base.mask = VIRTUAL_ENGINES; + intel_context_init(&ve->context, &ve->base); for (n = 0; n < count; n++) { diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 7c7da284990d..f59081066a19 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -134,9 +134,7 @@ static void i915_fence_release(struct dma_fence *fence) i915_sw_fence_fini(&rq->semaphore); /* - * Keep one request on each engine for reserved use under mempressure - * do not use with virtual engines as this really is only needed for - * kernel contexts. + * Keep one request on each engine for reserved use under mempressure. * * We do not hold a reference to the engine here and so have to be * very careful in what rq->engine we poke. The virtual engine is @@ -166,8 +164,7 @@ static void i915_fence_release(struct dma_fence *fence) * know that if the rq->execution_mask is a single bit, rq->engine * can be a physical engine with the exact corresponding mask. */ - if (!intel_engine_is_virtual(rq->engine) && - is_power_of_2(rq->execution_mask) && + if (is_power_of_2(rq->execution_mask) && !cmpxchg(&rq->engine->request_pool, NULL, rq)) return; diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index a34924523133..a34917b048f9 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -1122,18 +1122,11 @@ nv04_page_flip_emit(struct nouveau_channel *chan, PUSH_NVSQ(push, NV_SW, NV_SW_PAGE_FLIP, 0x00000000); PUSH_KICK(push); - ret = nouveau_fence_new(pfence); + ret = nouveau_fence_new(pfence, chan); if (ret) goto fail; - ret = nouveau_fence_emit(*pfence, chan); - if (ret) - goto fail_fence_unref; - return 0; - -fail_fence_unref: - nouveau_fence_unref(pfence); fail: spin_lock_irqsave(&dev->event_lock, flags); list_del(&s->head); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 19cab37ac69c..0f3bd187ede6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -875,16 +875,10 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, if (ret) goto out_unlock; - ret = nouveau_fence_new(&fence); + ret = nouveau_fence_new(&fence, chan); if (ret) goto out_unlock; - ret = nouveau_fence_emit(fence, chan); - if (ret) { - nouveau_fence_unref(&fence); - goto out_unlock; - } - /* TODO: figure out a better solution here * * wait on the fence here explicitly as going through diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 1fd5ccf41128..bb3d6e5c122f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -70,11 +70,9 @@ nouveau_channel_idle(struct nouveau_channel *chan) struct nouveau_fence *fence = NULL; int ret; - ret = nouveau_fence_new(&fence); + ret = nouveau_fence_new(&fence, chan); if (!ret) { - ret = nouveau_fence_emit(fence, chan); - if (!ret) - ret = nouveau_fence_wait(fence, false, false); + ret = nouveau_fence_wait(fence, false, false); nouveau_fence_unref(&fence); } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 61e84562094a..12feecf71e75 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -209,8 +209,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) goto done; } - if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, dmem->migrate.chan); + nouveau_fence_new(&fence, dmem->migrate.chan); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -403,8 +402,7 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) } } - if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan); + nouveau_fence_new(&fence, chunk->drm->dmem->migrate.chan); migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); @@ -677,8 +675,7 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, addr += PAGE_SIZE; } - if (!nouveau_fence_new(&fence)) - nouveau_fence_emit(fence, drm->dmem->migrate.chan); + nouveau_fence_new(&fence, drm->dmem->migrate.chan); migrate_vma_pages(args); nouveau_dmem_fence_done(&fence); nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i); diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index a90c4cd8cbb2..19024ce21fbb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -96,7 +96,8 @@ nouveau_exec_job_submit(struct nouveau_job *job) unsigned long index; int ret; - ret = nouveau_fence_new(&exec_job->fence); + /* Create a new fence, but do not emit yet. */ + ret = nouveau_fence_create(&exec_job->fence, exec_job->chan); if (ret) return ret; @@ -170,13 +171,17 @@ nouveau_exec_job_run(struct nouveau_job *job) nv50_dma_push(chan, p->va, p->va_len, no_prefetch); } - ret = nouveau_fence_emit(fence, chan); + ret = nouveau_fence_emit(fence); if (ret) { + nouveau_fence_unref(&exec_job->fence); NV_PRINTK(err, job->cli, "error fencing pushbuf: %d\n", ret); WIND_RING(chan); return ERR_PTR(ret); } + /* The fence was emitted successfully, set the job's fence pointer to + * NULL in order to avoid freeing it up when the job is cleaned up. + */ exec_job->fence = NULL; return &fence->base; @@ -189,7 +194,7 @@ nouveau_exec_job_free(struct nouveau_job *job) nouveau_job_free(job); - nouveau_fence_unref(&exec_job->fence); + kfree(exec_job->fence); kfree(exec_job->push.s); kfree(exec_job); } diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 77c739a55b19..61d9e70da9fd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -205,16 +205,13 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha } int -nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) +nouveau_fence_emit(struct nouveau_fence *fence) { + struct nouveau_channel *chan = fence->channel; struct nouveau_fence_chan *fctx = chan->fence; struct nouveau_fence_priv *priv = (void*)chan->drm->fence; int ret; - if (unlikely(!chan->fence)) - return -ENODEV; - - fence->channel = chan; fence->timeout = jiffies + (15 * HZ); if (priv->uevent) @@ -406,18 +403,41 @@ nouveau_fence_unref(struct nouveau_fence **pfence) } int -nouveau_fence_new(struct nouveau_fence **pfence) +nouveau_fence_create(struct nouveau_fence **pfence, + struct nouveau_channel *chan) { struct nouveau_fence *fence; + if (unlikely(!chan->fence)) + return -ENODEV; + fence = kzalloc(sizeof(*fence), GFP_KERNEL); if (!fence) return -ENOMEM; + fence->channel = chan; + *pfence = fence; return 0; } +int +nouveau_fence_new(struct nouveau_fence **pfence, + struct nouveau_channel *chan) +{ + int ret = 0; + + ret = nouveau_fence_create(pfence, chan); + if (ret) + return ret; + + ret = nouveau_fence_emit(*pfence); + if (ret) + nouveau_fence_unref(pfence); + + return ret; +} + static const char *nouveau_fence_get_get_driver_name(struct dma_fence *fence) { return "nouveau"; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 2c72d96ef17d..64d33ae7f356 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -17,10 +17,11 @@ struct nouveau_fence { unsigned long timeout; }; -int nouveau_fence_new(struct nouveau_fence **); +int nouveau_fence_create(struct nouveau_fence **, struct nouveau_channel *); +int nouveau_fence_new(struct nouveau_fence **, struct nouveau_channel *); void nouveau_fence_unref(struct nouveau_fence **); -int nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *); +int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index c0b10d8d3d03..a0d303e5ce3d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -914,11 +914,8 @@ revalidate: } } - ret = nouveau_fence_new(&fence); - if (!ret) - ret = nouveau_fence_emit(fence, chan); + ret = nouveau_fence_new(&fence, chan); if (ret) { - nouveau_fence_unref(&fence); NV_PRINTK(err, cli, "error fencing pushbuf: %d\n", ret); WIND_RING(chan); goto out; |