diff options
Diffstat (limited to 'drivers/gpu')
117 files changed, 1363 insertions, 490 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index e392a90ca687..85b79a7fee63 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -228,6 +228,7 @@ source "drivers/gpu/drm/arm/Kconfig" config DRM_RADEON tristate "ATI Radeon" depends on DRM && PCI && MMU + depends on AGP || !AGP select FW_LOADER select DRM_KMS_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index b6879d97c9c9..29885febc0b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -180,6 +180,7 @@ extern uint amdgpu_smu_memory_pool_size; extern uint amdgpu_dc_feature_mask; extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dm_abm_level; +extern int amdgpu_backlight; extern struct amdgpu_mgpu_info mgpu_info; extern int amdgpu_ras_enable; extern uint amdgpu_ras_mask; @@ -1006,13 +1007,9 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; - bool in_hibernate; - - /* - * The combination flag in_poweroff_reboot_com used to identify the poweroff - * and reboot opt in the s0i3 system-wide suspend. - */ - bool in_poweroff_reboot_com; + bool in_s3; + bool in_s4; + bool in_s0ix; atomic_t in_gpu_reset; enum pp_mp1_state mp1_state; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 36a741d63ddc..2e9b16fb3fcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -903,7 +903,7 @@ void amdgpu_acpi_fini(struct amdgpu_device *adev) */ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { -#if defined(CONFIG_AMD_PMC) +#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE) if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { if (adev->flags & AMD_IS_APU) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6447cd6ca5a8..8a5a8ff5d362 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2371,6 +2371,10 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip CG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2402,6 +2406,10 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip PG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2678,11 +2686,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) { - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) @@ -2722,6 +2727,9 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) { int i, r; + if (adev->in_s0ix) + amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) continue; @@ -2734,6 +2742,17 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; continue; } + + /* skip suspend of gfx and psp for S0ix + * gfx is in gfxoff state, so on resume it will exit gfxoff just + * like at runtime. PSP is also part of the always on hardware + * so no need to suspend it. + */ + if (adev->in_s0ix && + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)) + continue; + /* XXX handle errors */ r = adev->ip_blocks[i].version->funcs->suspend(adev); /* XXX handle errors */ @@ -3673,14 +3692,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev) */ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) { - struct amdgpu_device *adev; - struct drm_crtc *crtc; - struct drm_connector *connector; - struct drm_connector_list_iter iter; + struct amdgpu_device *adev = drm_to_adev(dev); int r; - adev = drm_to_adev(dev); - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; @@ -3692,61 +3706,19 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) cancel_delayed_work_sync(&adev->delayed_init_work); - if (!amdgpu_device_has_dc_support(adev)) { - /* turn off display hw */ - drm_modeset_lock_all(dev); - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_OFF); - drm_connector_list_iter_end(&iter); - drm_modeset_unlock_all(dev); - /* unpin the front buffers and cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_framebuffer *fb = crtc->primary->fb; - struct amdgpu_bo *robj; - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - amdgpu_bo_unpin(aobj); - amdgpu_bo_unreserve(aobj); - } - } - - if (fb == NULL || fb->obj[0] == NULL) { - continue; - } - robj = gem_to_amdgpu_bo(fb->obj[0]); - /* don't unpin kernel fb objects */ - if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { - r = amdgpu_bo_reserve(robj, true); - if (r == 0) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); - } - } - } - } - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); - amdgpu_amdkfd_suspend(adev, adev->in_runpm); + if (!adev->in_s0ix) + amdgpu_amdkfd_suspend(adev, adev->in_runpm); /* evict vram memory */ amdgpu_bo_evict_vram(adev); amdgpu_fence_driver_suspend(adev); - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) - r = amdgpu_device_ip_suspend_phase2(adev); - else - amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + r = amdgpu_device_ip_suspend_phase2(adev); /* evict remaining vram memory * This second call to evict vram is to evict the gart page table * using the CPU. @@ -3768,16 +3740,13 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) */ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) { - struct drm_connector *connector; - struct drm_connector_list_iter iter; struct amdgpu_device *adev = drm_to_adev(dev); - struct drm_crtc *crtc; int r = 0; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - if (amdgpu_acpi_is_s0ix_supported(adev)) + if (adev->in_s0ix) amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry); /* post card */ @@ -3802,50 +3771,17 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) queue_delayed_work(system_wq, &adev->delayed_init_work, msecs_to_jiffies(AMDGPU_RESUME_MS)); - if (!amdgpu_device_has_dc_support(adev)) { - /* pin cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); - if (r != 0) - dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); - amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); - amdgpu_bo_unreserve(aobj); - } - } - } + if (!adev->in_s0ix) { + r = amdgpu_amdkfd_resume(adev, adev->in_runpm); + if (r) + return r; } - r = amdgpu_amdkfd_resume(adev, adev->in_runpm); - if (r) - return r; /* Make sure IB tests flushed */ flush_delayed_work(&adev->delayed_init_work); - /* blat the mode back in */ - if (fbcon) { - if (!amdgpu_device_has_dc_support(adev)) { - /* pre DCE11 */ - drm_helper_resume_force_mode(dev); - - /* turn on display hw */ - drm_modeset_lock_all(dev); - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_ON); - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock_all(dev); - } + if (fbcon) amdgpu_fbdev_set_suspend(adev, 0); - } drm_kms_helper_poll_enable(dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 48cb33e5b382..f753e04fee99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1310,3 +1310,92 @@ bool amdgpu_crtc_get_scanout_position(struct drm_crtc *crtc, return amdgpu_display_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos, stime, etime, mode); } + +int amdgpu_display_suspend_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_crtc *crtc; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + int r; + + /* turn off display hw */ + drm_modeset_lock_all(dev); + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_OFF); + drm_connector_list_iter_end(&iter); + drm_modeset_unlock_all(dev); + /* unpin the front buffers and cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + struct drm_framebuffer *fb = crtc->primary->fb; + struct amdgpu_bo *robj; + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); + } + } + + if (fb == NULL || fb->obj[0] == NULL) { + continue; + } + robj = gem_to_amdgpu_bo(fb->obj[0]); + /* don't unpin kernel fb objects */ + if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { + r = amdgpu_bo_reserve(robj, true); + if (r == 0) { + amdgpu_bo_unpin(robj); + amdgpu_bo_unreserve(robj); + } + } + } + return r; +} + +int amdgpu_display_resume_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_connector *connector; + struct drm_connector_list_iter iter; + struct drm_crtc *crtc; + int r; + + /* pin cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); + if (r != 0) + dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); + amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); + amdgpu_bo_unreserve(aobj); + } + } + } + + drm_helper_resume_force_mode(dev); + + /* turn on display hw */ + drm_modeset_lock_all(dev); + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_ON); + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock_all(dev); + + return 0; +} + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h index dc7b7d116549..7b6d83e2b13c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h @@ -47,4 +47,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, const struct drm_format_info * amdgpu_lookup_format_info(u32 format, uint64_t modifier); +int amdgpu_display_suspend_helper(struct amdgpu_device *adev); +int amdgpu_display_resume_helper(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 4575192d9b08..e92e7dea71da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -781,6 +781,10 @@ uint amdgpu_dm_abm_level; MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) "); module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444); +int amdgpu_backlight = -1; +MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))"); +module_param_named(backlight, amdgpu_backlight, bint, 0444); + /** * DOC: tmz (int) * Trusted Memory Zone (TMZ) is a method to protect data being written @@ -1103,6 +1107,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, /* Van Gogh */ @@ -1270,24 +1275,35 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) */ if (!amdgpu_passthrough(adev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; - adev->in_poweroff_reboot_com = true; amdgpu_device_ip_suspend(adev); - adev->in_poweroff_reboot_com = false; adev->mp1_state = PP_MP1_STATE_NONE; } static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_suspend(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = true; + adev->in_s3 = true; + r = amdgpu_device_suspend(drm_dev, true); + adev->in_s3 = false; + + return r; } static int amdgpu_pmops_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_resume(drm_dev, true); + r = amdgpu_device_resume(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = false; + return r; } static int amdgpu_pmops_freeze(struct device *dev) @@ -1296,9 +1312,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_to_adev(drm_dev); int r; - adev->in_hibernate = true; + adev->in_s4 = true; r = amdgpu_device_suspend(drm_dev, true); - adev->in_hibernate = false; + adev->in_s4 = false; if (r) return r; return amdgpu_asic_reset(adev); @@ -1314,13 +1330,8 @@ static int amdgpu_pmops_thaw(struct device *dev) static int amdgpu_pmops_poweroff(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; - adev->in_poweroff_reboot_com = true; - r = amdgpu_device_suspend(drm_dev, true); - adev->in_poweroff_reboot_com = false; - return r; + return amdgpu_device_suspend(drm_dev, true); } static int amdgpu_pmops_restore(struct device *dev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 51cd49c6f38f..24010cacf7d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, size = mode_cmd->pitches[0] * height; aligned_size = ALIGN(size, PAGE_SIZE); ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags, - ttm_bo_type_kernel, NULL, &gobj); + ttm_bo_type_device, NULL, &gobj); if (ret) { pr_err("failed to allocate framebuffer (%d)\n", aligned_size); return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 64beb3399604..a4e2cf7cada1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -778,9 +778,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) dev_info->high_va_offset = AMDGPU_GMC_HOLE_END; dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size; } - dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); + dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE; - dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE; + dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->cu_active_number = adev->gfx.cu_info.number; dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask; dev_info->ce_ram_size = adev->gfx.ce_ram_size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4b29b8205442..072050429a2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1028,13 +1028,10 @@ int amdgpu_bo_evict_vram(struct amdgpu_device *adev) { struct ttm_resource_manager *man; - /* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */ -#ifndef CONFIG_HIBERNATION - if (adev->flags & AMD_IS_APU) { - /* Useless to evict on IGP chips */ + if (adev->in_s3 && (adev->flags & AMD_IS_APU)) { + /* No need to evict vram on APUs for suspend to ram */ return 0; } -#endif man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); return ttm_resource_manager_evict_all(&adev->mman.bdev, man); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9fd2157b133a..5efa331e3ee8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -906,7 +906,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, /* Allocate an SG array and squash pages into it */ r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ad91c0c3c423..7d2c8b169827 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2197,8 +2197,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, uint64_t eaddr; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2263,8 +2263,8 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, int r; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2409,7 +2409,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, after->start = eaddr + 1; after->last = tmp->last; after->offset = tmp->offset; - after->offset += after->start - tmp->start; + after->offset += (after->start - tmp->start) << PAGE_SHIFT; after->flags = tmp->flags; after->bo_va = tmp->bo_va; list_add(&after->list, &tmp->bo_va->invalids); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 7944781e1086..19abb740a169 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2897,6 +2897,11 @@ static int dce_v10_0_hw_fini(void *handle) static int dce_v10_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2921,8 +2926,10 @@ static int dce_v10_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v10_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 1b6ff0470011..320ec35bfd37 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3027,6 +3027,11 @@ static int dce_v11_0_hw_fini(void *handle) static int dce_v11_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -3051,8 +3056,10 @@ static int dce_v11_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v11_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 83a88385b762..13322000ebd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -2770,7 +2770,11 @@ static int dce_v6_0_hw_fini(void *handle) static int dce_v6_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2794,8 +2798,10 @@ static int dce_v6_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v6_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 224b30214427..04ebf02e5b8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2796,6 +2796,11 @@ static int dce_v8_0_hw_fini(void *handle) static int dce_v8_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2820,8 +2825,10 @@ static int dce_v8_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v8_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 9810af712cc0..5c11144da051 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -39,6 +39,7 @@ #include "dce_v11_0.h" #include "dce_virtual.h" #include "ivsrcid/ivsrcid_vislands30.h" +#include "amdgpu_display.h" #define DCE_VIRTUAL_VBLANK_PERIOD 16666666 @@ -491,12 +492,24 @@ static int dce_virtual_hw_fini(void *handle) static int dce_virtual_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; return dce_virtual_hw_fini(handle); } static int dce_virtual_resume(void *handle) { - return dce_virtual_hw_init(handle); + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = dce_virtual_hw_init(handle); + if (r) + return r; + return amdgpu_display_resume_helper(adev); } static bool dce_virtual_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index b258a3dae767..159add0f5aaa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev, /* Wait till CP writes sync code: */ status = amdkfd_fence_wait_timeout( - (unsigned int *) rm_state, + rm_state, QUEUESTATE__ACTIVE, 1500); kfd_gtt_sa_free(dbgdev->dev, mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e686ce2bf3b3..4598a9a58125 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1167,7 +1167,7 @@ static int start_cpsch(struct device_queue_manager *dqm) if (retval) goto fail_allocate_vidmem; - dqm->fence_addr = dqm->fence_mem->cpu_ptr; + dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr; dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr; init_interrupts(dqm); @@ -1340,8 +1340,8 @@ out: return retval; } -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms) { unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 7351dd195274..45f815946554 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -192,7 +192,7 @@ struct device_queue_manager { uint16_t vmid_pasid[VMID_NUM]; uint64_t pipelines_addr; uint64_t fence_gpu_addr; - unsigned int *fence_addr; + uint64_t *fence_addr; struct kfd_mem_obj *fence_mem; bool active_runlist; int sched_policy; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index 5d541e0cc8ca..f71a7fa6680c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -347,7 +347,7 @@ fail_create_runlist_ib: } int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value) + uint64_t fence_value) { uint32_t *buffer, size; int retval = 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c index dfaf771a42e6..e3ba0cd3b6fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c @@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c index a852e0d7d804..08442e7d9944 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c @@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 09599efa41fc..f304d1f8df5f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1003,8 +1003,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm, u32 *ctl_stack_used_size, u32 *save_area_used_size); -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms); /* Packet Manager */ @@ -1040,7 +1040,7 @@ struct packet_manager_funcs { uint32_t filter_param, bool reset, unsigned int sdma_engine); int (*query_status)(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value); + uint64_t fence_address, uint64_t fence_value); int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer); /* Packet sizes */ @@ -1062,7 +1062,7 @@ int pm_send_set_resources(struct packet_manager *pm, struct scheduling_resources *res); int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues); int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value); + uint64_t fence_value); int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type, enum kfd_unmap_queues_filter mode, 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 3e1fd1e7d09f..573cf17262da 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2267,6 +2267,11 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->ext_caps->bits.hdr_aux_backlight_control == 1) caps->aux_support = true; + if (amdgpu_backlight == 0) + caps->aux_support = false; + else if (amdgpu_backlight == 1) + caps->aux_support = true; + /* From the specification (CTA-861-G), for calculating the maximum * luminance we need to use: * Luminance = 50*2**(CV/32) @@ -3185,19 +3190,6 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #endif } -static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness) -{ - bool rc; - - if (!link) - return 1; - - rc = dc_link_set_backlight_level_nits(link, true, brightness, - AUX_BL_DEFAULT_TRANSITION_TIME_MS); - - return rc ? 0 : 1; -} - static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, unsigned *min, unsigned *max) { @@ -3260,9 +3252,10 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) brightness = convert_brightness_from_user(&caps, bd->props.brightness); // Change brightness based on AUX property if (caps.aux_support) - return set_backlight_via_aux(link, brightness); - - rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0); + rc = dc_link_set_backlight_level_nits(link, true, brightness, + AUX_BL_DEFAULT_TRANSITION_TIME_MS); + else + rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0); return rc ? 0 : 1; } @@ -3270,11 +3263,27 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - int ret = dc_link_get_backlight_level(dm->backlight_link); + struct amdgpu_dm_backlight_caps caps; + + amdgpu_dm_update_backlight_caps(dm); + caps = dm->backlight_caps; + + if (caps.aux_support) { + struct dc_link *link = (struct dc_link *)dm->backlight_link; + u32 avg, peak; + bool rc; - if (ret == DC_ERROR_UNEXPECTED) - return bd->props.brightness; - return convert_brightness_to_user(&dm->backlight_caps, ret); + rc = dc_link_get_backlight_level_nits(link, &avg, &peak); + if (!rc) + return bd->props.brightness; + return convert_brightness_to_user(&caps, avg); + } else { + int ret = dc_link_get_backlight_level(dm->backlight_link); + + if (ret == DC_ERROR_UNEXPECTED) + return bd->props.brightness; + return convert_brightness_to_user(&caps, ret); + } } static const struct backlight_ops amdgpu_dm_backlight_ops = { @@ -4716,6 +4725,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, dc_plane_state->global_alpha_value = plane_info.global_alpha_value; dc_plane_state->dcc = plane_info.dcc; dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0 + dc_plane_state->flip_int_enabled = true; /* * Always set input transfer function, since plane state is refreshed diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fa5059f71727..bd0101013ec8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2602,7 +2602,6 @@ bool dc_link_set_backlight_level(const struct dc_link *link, if (pipe_ctx->plane_state == NULL) frame_ramp = 0; } else { - ASSERT(false); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4eee3a55fa30..18ed0d3f247e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -887,6 +887,7 @@ struct dc_plane_state { int layer_index; union surface_update_flags update_flags; + bool flip_int_enabled; /* private to DC core */ struct dc_plane_status status; struct dc_context *ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index 9e796dfeac20..714c71a5fbde 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1257,6 +1257,16 @@ void hubp1_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_DISABLE, reset ? 1 : 0); } +void hubp1_set_flip_int(struct hubp *hubp) +{ + struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); + + REG_UPDATE(DCSURF_SURFACE_FLIP_INTERRUPT, + SURFACE_FLIP_INT_MASK, 1); + + return; +} + void hubp1_init(struct hubp *hubp) { //do nothing @@ -1290,6 +1300,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = { .dmdata_load = NULL, .hubp_soft_reset = hubp1_soft_reset, .hubp_in_blank = hubp1_in_blank, + .hubp_set_flip_int = hubp1_set_flip_int, }; /*****************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h index a9a6ed7f4f99..e2f2f6995935 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h @@ -74,6 +74,7 @@ SRI(DCSURF_SURFACE_EARLIEST_INUSE_C, HUBPREQ, id),\ SRI(DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, HUBPREQ, id),\ SRI(DCSURF_SURFACE_CONTROL, HUBPREQ, id),\ + SRI(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id),\ SRI(HUBPRET_CONTROL, HUBPRET, id),\ SRI(DCN_EXPANSION_MODE, HUBPREQ, id),\ SRI(DCHUBP_REQ_SIZE_CONFIG, HUBP, id),\ @@ -183,6 +184,7 @@ uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C; \ uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C; \ uint32_t DCSURF_SURFACE_CONTROL; \ + uint32_t DCSURF_SURFACE_FLIP_INTERRUPT; \ uint32_t HUBPRET_CONTROL; \ uint32_t DCN_EXPANSION_MODE; \ uint32_t DCHUBP_REQ_SIZE_CONFIG; \ @@ -332,6 +334,7 @@ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ_C, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\ + HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ @@ -531,6 +534,7 @@ type PRIMARY_SURFACE_DCC_IND_64B_BLK;\ type SECONDARY_SURFACE_DCC_EN;\ type SECONDARY_SURFACE_DCC_IND_64B_BLK;\ + type SURFACE_FLIP_INT_MASK;\ type DET_BUF_PLANE1_BASE_ADDRESS;\ type CROSSBAR_SRC_CB_B;\ type CROSSBAR_SRC_CR_R;\ @@ -777,4 +781,6 @@ void hubp1_read_state_common(struct hubp *hubp); bool hubp1_in_blank(struct hubp *hubp); void hubp1_soft_reset(struct hubp *hubp, bool reset); +void hubp1_set_flip_int(struct hubp *hubp); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 89912bb5014f..9ba5c624770d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2196,6 +2196,13 @@ static void dcn10_enable_plane( if (dc->debug.sanity_checks) { hws->funcs.verify_allow_pstate_change_high(dc); } + + if (!pipe_ctx->top_pipe + && pipe_ctx->plane_state + && pipe_ctx->plane_state->flip_int_enabled + && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int) + pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp); + } void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 0df0da2e6a4d..bec7059f6d5d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1597,6 +1597,7 @@ static struct hubp_funcs dcn20_hubp_funcs = { .validate_dml_output = hubp2_validate_dml_output, .hubp_in_blank = hubp1_in_blank, .hubp_soft_reset = hubp1_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, }; 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 0726fb435e2a..aece1103331d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1146,6 +1146,12 @@ void dcn20_enable_plane( pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt); } + if (!pipe_ctx->top_pipe + && pipe_ctx->plane_state + && pipe_ctx->plane_state->flip_int_enabled + && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int) + pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp); + // if (dc->debug.sanity_checks) { // dcn10_verify_allow_pstate_change_high(dc); // } @@ -1501,38 +1507,8 @@ static void dcn20_update_dchubp_dpp( if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || pipe_ctx->stream->update_flags.bits.gamut_remap || pipe_ctx->stream->update_flags.bits.out_csc) { - struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; - - if (mpc->funcs->set_gamut_remap) { - int i; - int mpcc_id = hubp->inst; - struct mpc_grph_gamut_adjustment adjust; - bool enable_remap_dpp = false; - - memset(&adjust, 0, sizeof(adjust)); - adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS; - - /* save the enablement of gamut remap for dpp */ - enable_remap_dpp = pipe_ctx->stream->gamut_remap_matrix.enable_remap; - - /* force bypass gamut remap for dpp/cm */ - pipe_ctx->stream->gamut_remap_matrix.enable_remap = false; - dc->hwss.program_gamut_remap(pipe_ctx); - - /* restore gamut remap flag and use this remap into mpc */ - pipe_ctx->stream->gamut_remap_matrix.enable_remap = enable_remap_dpp; - - /* build remap matrix for top plane if enabled */ - if (enable_remap_dpp && pipe_ctx->top_pipe == NULL) { - adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW; - for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++) - adjust.temperature_matrix[i] = - pipe_ctx->stream->gamut_remap_matrix.matrix[i]; - } - mpc->funcs->set_gamut_remap(mpc, mpcc_id, &adjust); - } else - /* dpp/cm gamut remap*/ - dc->hwss.program_gamut_remap(pipe_ctx); + /* dpp/cm gamut remap*/ + dc->hwss.program_gamut_remap(pipe_ctx); /*call the dcn2 method which uses mpc csc*/ dc->hwss.program_output_csc(dc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c index fa013496e26b..2f9bfaeaba8d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c @@ -341,8 +341,7 @@ void enc2_hw_init(struct link_encoder *enc) } else { AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110); - AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d); - + AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a); } //AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c index f9045852728f..b0c9180b808f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -838,6 +838,7 @@ static struct hubp_funcs dcn21_hubp_funcs = { .hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl, .hubp_init = hubp21_init, .validate_dml_output = hubp21_validate_dml_output, + .hubp_set_flip_int = hubp1_set_flip_int, }; bool hubp21_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 072f8c880924..4a3df13c9e49 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 23.84, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, @@ -1062,8 +1062,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s { int i; - DC_FP_START(); - if (dc->bb_overrides.sr_exit_time_ns) { for (i = 0; i < WM_SET_COUNT; i++) { dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us = @@ -1088,8 +1086,6 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s dc->bb_overrides.dram_clock_change_latency_ns / 1000.0; } } - - DC_FP_END(); } void dcn21_calculate_wm( @@ -1339,7 +1335,7 @@ static noinline bool dcn21_validate_bandwidth_fp(struct dc *dc, int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + 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); BW_VAL_TRACE_COUNT(); @@ -1599,6 +1595,11 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn2_1_soc.num_chans = bw_params->num_channels; ASSERT(clk_table->num_entries); + /* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */ + for (i = 0; i < dcn2_1_soc.num_states + 1; i++) { + clock_limits[i] = dcn2_1_soc.clock_limits[i]; + } + for (i = 0; i < clk_table->num_entries; i++) { /* loop backwards*/ for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index 41a1d0e9b7e2..e0df9b0065f9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -113,6 +113,7 @@ bool cm3_helper_translate_curve_to_hw_format( struct pwl_result_data *rgb_resulted; struct pwl_result_data *rgb; struct pwl_result_data *rgb_plus_1; + struct pwl_result_data *rgb_minus_1; struct fixed31_32 end_value; int32_t region_start, region_end; @@ -140,7 +141,7 @@ bool cm3_helper_translate_curve_to_hw_format( region_start = -MAX_LOW_POINT; region_end = NUMBER_REGIONS - MAX_LOW_POINT; } else { - /* 10 segments + /* 11 segments * segment is from 2^-10 to 2^0 * There are less than 256 points, for optimization */ @@ -154,9 +155,10 @@ bool cm3_helper_translate_curve_to_hw_format( seg_distr[7] = 4; seg_distr[8] = 4; seg_distr[9] = 4; + seg_distr[10] = 1; region_start = -10; - region_end = 0; + region_end = 1; } for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++) @@ -189,6 +191,10 @@ bool cm3_helper_translate_curve_to_hw_format( rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index]; rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index]; + rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red; + rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green; + rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue; + // All 3 color channels have same x corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2), dc_fixpt_from_int(region_start)); @@ -259,15 +265,18 @@ bool cm3_helper_translate_curve_to_hw_format( rgb = rgb_resulted; rgb_plus_1 = rgb_resulted + 1; + rgb_minus_1 = rgb; i = 1; while (i != hw_points + 1) { - if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) - rgb_plus_1->red = rgb->red; - if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) - rgb_plus_1->green = rgb->green; - if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) - rgb_plus_1->blue = rgb->blue; + if (i >= hw_points - 1) { + if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) + rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red); + if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) + rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green); + if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) + rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue); + } rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red); rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green); @@ -283,6 +292,7 @@ bool cm3_helper_translate_curve_to_hw_format( } ++rgb_plus_1; + rgb_minus_1 = rgb; ++rgb; ++i; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c index 88ffa9ff1ed1..f24612523248 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c @@ -511,6 +511,7 @@ static struct hubp_funcs dcn30_hubp_funcs = { .hubp_init = hubp3_init, .hubp_in_blank = hubp1_in_blank, .hubp_soft_reset = hubp1_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, }; bool hubp3_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h index 705fbfc37502..8a32772d4e91 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h @@ -134,6 +134,7 @@ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK_C, mask_sh),\ + HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 8d0f663489ac..fb7f1dea3c46 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -2508,6 +2508,19 @@ static const struct resource_funcs dcn30_res_pool_funcs = { .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, }; +#define CTX ctx + +#define REG(reg_name) \ + (DCN_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name) + +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* Support for max 6 pipes */ + value = value & 0x3f; + return value; +} + static bool dcn30_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -2517,6 +2530,15 @@ static bool dcn30_resource_construct( struct dc_context *ctx = dc->ctx; struct irq_service_init_data init_data; struct ddc_service_init_data ddc_init_data; + uint32_t pipe_fuses = read_pipe_fuses(ctx); + uint32_t num_pipes = 0; + + if (!(pipe_fuses == 0 || pipe_fuses == 0x3e)) { + BREAK_TO_DEBUGGER(); + dm_error("DC: Unexpected fuse recipe for navi2x !\n"); + /* fault to single pipe */ + pipe_fuses = 0x3e; + } DC_FP_START(); @@ -2650,6 +2672,15 @@ static bool dcn30_resource_construct( /* PP Lib and SMU interfaces */ init_soc_bounding_box(dc, pool); + num_pipes = dcn3_0_ip.max_num_dpp; + + for (i = 0; i < dcn3_0_ip.max_num_dpp; i++) + if (pipe_fuses & 1 << i) + num_pipes--; + + dcn3_0_ip.max_num_dpp = num_pipes; + dcn3_0_ip.max_num_otg = num_pipes; + dml_init_instance(&dc->dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30); /* IRQ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 5d4b2c60192e..c494235016e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1619,12 +1619,106 @@ static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); } +static void calculate_wm_set_for_vlevel( + int vlevel, + struct wm_range_table_entry *table_entry, + struct dcn_watermarks *wm_set, + struct display_mode_lib *dml, + display_e2e_pipe_params_st *pipes, + int pipe_cnt) +{ + double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; + + ASSERT(vlevel < dml->soc.num_states); + /* only pipe 0 is read for voltage and dcf/soc clocks */ + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; + + dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; + + wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; + wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; + wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; + dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; + +} + +static void dcn301_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel_req) +{ + int i, pipe_idx; + int vlevel, vlevel_max; + struct wm_range_table_entry *table_entry; + struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; + + ASSERT(bw_params); + + vlevel_max = bw_params->clk_table.num_entries - 1; + + /* WM Set D */ + table_entry = &bw_params->wm_table.entries[WM_D]; + if (table_entry->wm_type == WM_TYPE_RETRAINING) + vlevel = 0; + else + vlevel = vlevel_max; + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set C */ + table_entry = &bw_params->wm_table.entries[WM_C]; + vlevel = min(max(vlevel_req, 2), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set B */ + table_entry = &bw_params->wm_table.entries[WM_B]; + vlevel = min(max(vlevel_req, 1), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, + &context->bw_ctx.dml, pipes, pipe_cnt); + + /* WM Set A */ + table_entry = &bw_params->wm_table.entries[WM_A]; + vlevel = min(vlevel_req, vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, + &context->bw_ctx.dml, pipes, pipe_cnt); + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); + pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + + if (dc->config.forced_clocks) { + pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; + pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; + } + if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; + if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; + + pipe_idx++; + } + + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); +} + static struct resource_funcs dcn301_res_pool_funcs = { .destroy = dcn301_destroy_resource_pool, .link_enc_create = dcn301_link_encoder_create, .panel_cntl_create = dcn301_panel_cntl_create, .validate_bandwidth = dcn30_validate_bandwidth, - .calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg, + .calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg, .populate_dml_pipes = dcn30_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 22f3f643ed1b..346dcd87dc10 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -191,6 +191,8 @@ struct hubp_funcs { bool (*hubp_in_blank)(struct hubp *hubp); void (*hubp_soft_reset)(struct hubp *hubp, bool reset); + void (*hubp_set_flip_int)(struct hubp *hubp); + }; #endif diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index c57dc9ae81f2..c0565a932a12 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -587,6 +587,48 @@ static int smu7_force_switch_to_arbf0(struct pp_hwmgr *hwmgr) tmp, MC_CG_ARB_FREQ_F0); } +static uint16_t smu7_override_pcie_speed(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + uint16_t pcie_gen = 0; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + return pcie_gen; +} + +static uint16_t smu7_override_pcie_width(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + uint16_t pcie_width = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 16; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 12; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 8; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + return pcie_width; +} + static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); @@ -683,6 +725,11 @@ static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr) PP_Min_PCIEGen), get_pcie_lane_support(data->pcie_lane_cap, PP_Max_PCIELane)); + + if (data->pcie_dpm_key_disabled) + phm_setup_pcie_table_entry(&data->dpm_table.pcie_speed_table, + data->dpm_table.pcie_speed_table.count, + smu7_override_pcie_speed(hwmgr), smu7_override_pcie_width(hwmgr)); } return 0; } @@ -1177,7 +1224,8 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (hwmgr->chip_id == CHIP_POLARIS10) || (hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12) || - (hwmgr->chip_id == CHIP_TONGA)) + (hwmgr->chip_id == CHIP_TONGA) || + (hwmgr->chip_id == CHIP_TOPAZ)) PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1); @@ -1248,6 +1296,13 @@ static int smu7_start_dpm(struct pp_hwmgr *hwmgr) NULL)), "Failed to enable pcie DPM during DPM Start Function!", return -EINVAL); + } else { + PP_ASSERT_WITH_CODE( + (0 == smum_send_msg_to_smc(hwmgr, + PPSMC_MSG_PCIeDPM_Disable, + NULL)), + "Failed to disble pcie DPM during DPM Start Function!", + return -EINVAL); } if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, @@ -3276,7 +3331,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) && !hwmgr->display_config->multi_monitor_in_sync) || - smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time); + (hwmgr->display_config->num_display && + smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time)); disable_mclk_switching = disable_mclk_switching_for_frame_lock || disable_mclk_switching_for_display; @@ -5216,10 +5272,10 @@ static int smu7_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr, for (j = 0; j < dep_sclk_table->count; j++) { valid_entry = false; for (k = 0; k < watermarks->num_wm_sets; k++) { - if (dep_sclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz && - dep_sclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz && - dep_mclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz && - dep_mclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz) { + if (dep_sclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz / 10 && + dep_sclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz / 10 && + dep_mclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz / 10 && + dep_mclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz / 10) { valid_entry = true; table->DisplayWatermark[i][j] = watermarks->wm_clk_ranges[k].wm_set_id; break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 29c99642d22d..599ec9726601 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -54,6 +54,9 @@ #include "smuio/smuio_9_0_offset.h" #include "smuio/smuio_9_0_sh_mask.h" +#define smnPCIE_LC_SPEED_CNTL 0x11140290 +#define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288 + #define HBM_MEMORY_CHANNEL_WIDTH 128 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2}; @@ -443,8 +446,7 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) if (PP_CAP(PHM_PlatformCaps_VCEDPM)) data->smu_features[GNLD_DPM_VCE].supported = true; - if (!data->registry_data.pcie_dpm_key_disabled) - data->smu_features[GNLD_DPM_LINK].supported = true; + data->smu_features[GNLD_DPM_LINK].supported = true; if (!data->registry_data.dcefclk_dpm_key_disabled) data->smu_features[GNLD_DPM_DCEFCLK].supported = true; @@ -1505,6 +1507,55 @@ static int vega10_populate_single_lclk_level(struct pp_hwmgr *hwmgr, return 0; } +static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + struct vega10_hwmgr *data = + (struct vega10_hwmgr *)(hwmgr->backend); + uint32_t pcie_gen = 0, pcie_width = 0; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 6; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 5; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 3; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + for (i = 0; i < NUM_LINK_LEVELS; i++) { + if (pp_table->PcieGenSpeed[i] > pcie_gen) + pp_table->PcieGenSpeed[i] = pcie_gen; + + if (pp_table->PcieLaneCount[i] > pcie_width) + pp_table->PcieLaneCount[i] = pcie_width; + } + + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + } + + return 0; +} + static int vega10_populate_smc_link_levels(struct pp_hwmgr *hwmgr) { int result = -1; @@ -2556,6 +2607,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr) "Failed to initialize Link Level!", return result); + result = vega10_override_pcie_parameters(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "Failed to override pcie parameters!", + return result); + result = vega10_populate_all_graphic_levels(hwmgr); PP_ASSERT_WITH_CODE(!result, "Failed to initialize Graphics Level!", @@ -2919,9 +2975,18 @@ static int vega10_start_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap) } } + if (data->registry_data.pcie_dpm_key_disabled) { + PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr, + false, data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap), + "Attempt to Disable Link DPM feature Failed!", return -EINVAL); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } + return 0; } + static int vega10_enable_disable_PCC_limit_feature(struct pp_hwmgr *hwmgr, bool enable) { struct vega10_hwmgr *data = hwmgr->backend; @@ -4536,6 +4601,24 @@ static int vega10_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return 0; } +static int vega10_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = hwmgr->adev; + + return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) & + PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK) + >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT; +} + +static int vega10_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = hwmgr->adev; + + return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & + PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) + >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT; +} + static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf) { @@ -4544,8 +4627,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); struct vega10_single_dpm_table *soc_table = &(data->dpm_table.soc_table); struct vega10_single_dpm_table *dcef_table = &(data->dpm_table.dcef_table); - struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table); struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL; + uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; + PPTable_t *pptable = &(data->smc_state_table.pp_table); int i, now, size = 0, count = 0; @@ -4602,15 +4686,31 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, "*" : ""); break; case PP_PCIE: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentLinkIndex, &now); - - for (i = 0; i < pcie_table->count; i++) - size += sprintf(buf + size, "%d: %s %s\n", i, - (pcie_table->pcie_gen[i] == 0) ? "2.5GT/s, x1" : - (pcie_table->pcie_gen[i] == 1) ? "5.0GT/s, x16" : - (pcie_table->pcie_gen[i] == 2) ? "8.0GT/s, x16" : "", - (i == now) ? "*" : ""); + current_gen_speed = + vega10_get_current_pcie_link_speed_level(hwmgr); + current_lane_width = + vega10_get_current_pcie_link_width_level(hwmgr); + for (i = 0; i < NUM_LINK_LEVELS; i++) { + gen_speed = pptable->PcieGenSpeed[i]; + lane_width = pptable->PcieLaneCount[i]; + + size += sprintf(buf + size, "%d: %s %s %s\n", i, + (gen_speed == 0) ? "2.5GT/s," : + (gen_speed == 1) ? "5.0GT/s," : + (gen_speed == 2) ? "8.0GT/s," : + (gen_speed == 3) ? "16.0GT/s," : "", + (lane_width == 1) ? "x1" : + (lane_width == 2) ? "x2" : + (lane_width == 3) ? "x4" : + (lane_width == 4) ? "x8" : + (lane_width == 5) ? "x12" : + (lane_width == 6) ? "x16" : "", + (current_gen_speed == gen_speed) && + (current_lane_width == lane_width) ? + "*" : ""); + } break; + case OD_SCLK: if (hwmgr->od_enabled) { size = sprintf(buf, "%s:\n", "OD_SCLK"); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index c0753029a8e2..4f6da11e8f10 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -133,6 +133,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; data->registry_data.auto_wattman_threshold = 50; + data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); } static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr) @@ -481,6 +482,90 @@ static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state) dpm_state->hard_max_level = 0xffff; } +static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + struct vega12_hwmgr *data = + (struct vega12_hwmgr *)(hwmgr->backend); + uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; + int ret; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 6; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 5; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 3; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + /* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1 + * Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4 + * Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32 + */ + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen : + pp_table->PcieGenSpeed[i]; + pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width : + pp_table->PcieLaneCount[i]; + + if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg != + pp_table->PcieLaneCount[i]) { + smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + } + + /* update the pptable */ + pp_table->PcieGenSpeed[i] = pcie_gen_arg; + pp_table->PcieLaneCount[i] = pcie_width_arg; + } + + /* override to the highest if it's disabled from ppfeaturmask */ + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + ret = vega12_enable_smc_features(hwmgr, + false, + data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap); + PP_ASSERT_WITH_CODE(!ret, + "Attempt to Disable DPM LINK Failed!", + return ret); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } + return 0; +} + static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr, PPCLK_e clk_id, uint32_t *num_of_levels) { @@ -968,6 +1053,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "Failed to enable all smu features!", return result); + result = vega12_override_pcie_parameters(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to override pcie parameters!", + return result); + tmp_result = vega12_power_control_set_level(hwmgr); PP_ASSERT_WITH_CODE(!tmp_result, "Failed to power control set level!", diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 87811b005b85..b6ee3a285c9d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -171,6 +171,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; data->counter_gfxoff = 0; + data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); } static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr) @@ -831,7 +832,9 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr) struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg; + uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg; + PPTable_t *pp_table = &(data->smc_state_table.pp_table); + int i; int ret; if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4) @@ -860,17 +863,51 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr) * Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4 * Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32 */ - smu_pcie_arg = (1 << 16) | (pcie_gen << 8) | pcie_width; - ret = smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, - NULL); - PP_ASSERT_WITH_CODE(!ret, - "[OverridePcieParameters] Attempt to override pcie params failed!", - return ret); + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen : + pp_table->PcieGenSpeed[i]; + pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width : + pp_table->PcieLaneCount[i]; + + if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg != + pp_table->PcieLaneCount[i]) { + smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + } + + /* update the pptable */ + pp_table->PcieGenSpeed[i] = pcie_gen_arg; + pp_table->PcieLaneCount[i] = pcie_width_arg; + } + + /* override to the highest if it's disabled from ppfeaturmask */ + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); - data->pcie_parameters_override = true; - data->pcie_gen_level1 = pcie_gen; - data->pcie_width_level1 = pcie_width; + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + ret = vega20_enable_smc_features(hwmgr, + false, + data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap); + PP_ASSERT_WITH_CODE(!ret, + "Attempt to Disable DPM LINK Failed!", + return ret); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } return 0; } @@ -3319,9 +3356,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, data->od8_settings.od8_settings_array; OverDriveTable_t *od_table = &(data->smc_state_table.overdrive_table); - struct phm_ppt_v3_information *pptable_information = - (struct phm_ppt_v3_information *)hwmgr->pptable; - PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable; + PPTable_t *pptable = &(data->smc_state_table.pp_table); struct pp_clock_levels_with_latency clocks; struct vega20_single_dpm_table *fclk_dpm_table = &(data->dpm_table.fclk_table); @@ -3420,13 +3455,9 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, current_lane_width = vega20_get_current_pcie_link_width_level(hwmgr); for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (i == 1 && data->pcie_parameters_override) { - gen_speed = data->pcie_gen_level1; - lane_width = data->pcie_width_level1; - } else { - gen_speed = pptable->PcieGenSpeed[i]; - lane_width = pptable->PcieLaneCount[i]; - } + gen_speed = pptable->PcieGenSpeed[i]; + lane_width = pptable->PcieLaneCount[i]; + size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, (gen_speed == 0) ? "2.5GT/s," : (gen_speed == 1) ? "5.0GT/s," : diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index d143ef1b460b..cd905e41080e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1294,7 +1294,7 @@ static int smu_disable_dpms(struct smu_context *smu) bool use_baco = !smu->is_apu && ((amdgpu_in_reset(adev) && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev))); /* * For custom pptable uploading, skip the DPM features @@ -1431,7 +1431,8 @@ static int smu_suspend(void *handle) smu->watermarks_bitmap &= ~(WATERMARKS_LOADED); - if (smu->is_apu) + /* skip CGPG when in S0ix */ + if (smu->is_apu && !adev->in_s0ix) smu_set_gfx_cgpg(&adev->smu, false); return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 7ddbaecb11c2..101eaa20db9b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -384,10 +384,15 @@ static int vangogh_dpm_set_jpeg_enable(struct smu_context *smu, bool enable) static bool vangogh_is_dpm_running(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; int ret = 0; uint32_t feature_mask[2]; uint64_t feature_enabled; + /* we need to re-init after suspend so return false */ + if (adev->in_suspend) + return false; + ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2); if (ret) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index b9a616737c0e..f6baa2046124 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -2048,7 +2048,7 @@ static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper) if (shadow) vfree(shadow); - else + else if (fb_helper->buffer) drm_client_buffer_vunmap(fb_helper->buffer); drm_client_framebuffer_delete(fb_helper->buffer); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 9825c378dfa6..6d625cee7a6a 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -357,13 +357,14 @@ static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem, if (--shmem->vmap_use_count > 0) return; - if (obj->import_attach) + if (obj->import_attach) { dma_buf_vunmap(obj->import_attach->dmabuf, map); - else + } else { vunmap(shmem->vaddr); + drm_gem_shmem_put_pages(shmem); + } shmem->vaddr = NULL; - drm_gem_shmem_put_pages(shmem); } /* @@ -525,14 +526,28 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) struct drm_gem_object *obj = vma->vm_private_data; struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); loff_t num_pages = obj->size >> PAGE_SHIFT; + vm_fault_t ret; struct page *page; + pgoff_t page_offset; - if (vmf->pgoff >= num_pages || WARN_ON_ONCE(!shmem->pages)) - return VM_FAULT_SIGBUS; + /* We don't use vmf->pgoff since that has the fake offset */ + page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT; - page = shmem->pages[vmf->pgoff]; + mutex_lock(&shmem->pages_lock); - return vmf_insert_page(vma, vmf->address, page); + if (page_offset >= num_pages || + WARN_ON_ONCE(!shmem->pages) || + shmem->madv < 0) { + ret = VM_FAULT_SIGBUS; + } else { + page = shmem->pages[page_offset]; + + ret = vmf_insert_page(vma, vmf->address, page); + } + + mutex_unlock(&shmem->pages_lock); + + return ret; } static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) @@ -581,9 +596,6 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) struct drm_gem_shmem_object *shmem; int ret; - /* Remove the fake offset */ - vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); - if (obj->import_attach) { /* Drop the reference drm_gem_mmap_obj() acquired.*/ drm_gem_object_put(obj); diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c index f86448ab1fe0..dc734d4828a1 100644 --- a/drivers/gpu/drm/drm_ioc32.c +++ b/drivers/gpu/drm/drm_ioc32.c @@ -99,6 +99,8 @@ static int compat_drm_version(struct file *file, unsigned int cmd, if (copy_from_user(&v32, (void __user *)arg, sizeof(v32))) return -EFAULT; + memset(&v, 0, sizeof(v)); + v = (struct drm_version) { .name_len = v32.name_len, .name = compat_ptr(v32.name), @@ -137,6 +139,9 @@ static int compat_drm_getunique(struct file *file, unsigned int cmd, if (copy_from_user(&uq32, (void __user *)arg, sizeof(uq32))) return -EFAULT; + + memset(&uq, 0, sizeof(uq)); + uq = (struct drm_unique){ .unique_len = uq32.unique_len, .unique = compat_ptr(uq32.unique), @@ -265,6 +270,8 @@ static int compat_drm_getclient(struct file *file, unsigned int cmd, if (copy_from_user(&c32, argp, sizeof(c32))) return -EFAULT; + memset(&client, 0, sizeof(client)); + client.idx = c32.idx; err = drm_ioctl_kernel(file, drm_getclient, &client, 0); @@ -852,6 +859,8 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd, if (copy_from_user(&req32, argp, sizeof(req32))) return -EFAULT; + memset(&req, 0, sizeof(req)); + req.request.type = req32.request.type; req.request.sequence = req32.request.sequence; req.request.signal = req32.request.signal; @@ -889,6 +898,8 @@ static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd, struct drm_mode_fb_cmd2 req64; int err; + memset(&req64, 0, sizeof(req64)); + if (copy_from_user(&req64, argp, offsetof(drm_mode_fb_cmd232_t, modifier))) return -EFAULT; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 6d38c5c17f23..db69f19ab5bc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -689,7 +689,8 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) struct page **pages = pvec + pinned; ret = pin_user_pages_fast(ptr, num_pages, - !userptr->ro ? FOLL_WRITE : 0, pages); + FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM, + pages); if (ret < 0) { unpin_user_pages(pvec, pinned); kvfree(pvec); diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 1f79bc2a881e..1510e4e2973c 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -13,7 +13,6 @@ #include <linux/irq.h> #include <linux/mfd/syscon.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c index e21fb14d5e07..833d0c1be4f1 100644 --- a/drivers/gpu/drm/i915/display/intel_acpi.c +++ b/drivers/gpu/drm/i915/display/intel_acpi.c @@ -84,13 +84,31 @@ static void intel_dsm_platform_mux_info(acpi_handle dhandle) return; } + if (!pkg->package.count) { + DRM_DEBUG_DRIVER("no connection in _DSM\n"); + return; + } + connector_count = &pkg->package.elements[0]; DRM_DEBUG_DRIVER("MUX info connectors: %lld\n", (unsigned long long)connector_count->integer.value); for (i = 1; i < pkg->package.count; i++) { union acpi_object *obj = &pkg->package.elements[i]; - union acpi_object *connector_id = &obj->package.elements[0]; - union acpi_object *info = &obj->package.elements[1]; + union acpi_object *connector_id; + union acpi_object *info; + + if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) { + DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i); + continue; + } + + connector_id = &obj->package.elements[0]; + info = &obj->package.elements[1]; + if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) { + DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i); + continue; + } + DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n", (unsigned long long)connector_id->integer.value); DRM_DEBUG_DRIVER(" port id: %s\n", diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 4683f98f7e54..c3f2962aa1eb 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -317,12 +317,13 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc) return 0; - new_crtc_state->enabled_planes |= BIT(plane->id); - ret = plane->check_plane(new_crtc_state, new_plane_state); if (ret) return ret; + if (fb) + new_crtc_state->enabled_planes |= BIT(plane->id); + /* FIXME pre-g4x don't work like this */ if (new_plane_state->uapi.visible) new_crtc_state->active_planes |= BIT(plane->id); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 8c12d5375607..775d89b6c3fc 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3619,9 +3619,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) { int ret; - intel_dp_lttpr_init(intel_dp); - - if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) + if (intel_dp_init_lttpr_and_dprx_caps(intel_dp) < 0) return false; /* diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index eaebf123310a..10fe17b7280d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -133,6 +133,7 @@ static u32 g4x_get_aux_send_ctl(struct intel_dp *intel_dp, else precharge = 5; + /* Max timeout value on G4x-BDW: 1.6ms */ if (IS_BROADWELL(dev_priv)) timeout = DP_AUX_CH_CTL_TIME_OUT_600us; else @@ -159,6 +160,12 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, enum phy phy = intel_port_to_phy(i915, dig_port->base.port); u32 ret; + /* + * Max timeout values: + * SKL-GLK: 1.6ms + * CNL: 3.2ms + * ICL+: 4ms + */ ret = DP_AUX_CH_CTL_SEND_BUSY | DP_AUX_CH_CTL_DONE | DP_AUX_CH_CTL_INTERRUPT | diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 651884390137..4f8337c7fd2e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -646,7 +646,6 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) break; case INTEL_BACKLIGHT_DISPLAY_DDI: try_intel_interface = true; - try_vesa_interface = true; break; default: return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 892d7db7d94f..be6ac0dd846e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -34,6 +34,11 @@ intel_dp_dump_link_status(const u8 link_status[DP_LINK_STATUS_SIZE]) link_status[3], link_status[4], link_status[5]); } +static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp) +{ + memset(&intel_dp->lttpr_common_caps, 0, sizeof(intel_dp->lttpr_common_caps)); +} + static void intel_dp_reset_lttpr_count(struct intel_dp *intel_dp) { intel_dp->lttpr_common_caps[DP_PHY_REPEATER_CNT - @@ -81,19 +86,36 @@ static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp, static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp) { - if (drm_dp_read_lttpr_common_caps(&intel_dp->aux, - intel_dp->lttpr_common_caps) < 0) { - memset(intel_dp->lttpr_common_caps, 0, - sizeof(intel_dp->lttpr_common_caps)); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + if (intel_dp_is_edp(intel_dp)) return false; - } + + /* + * Detecting LTTPRs must be avoided on platforms with an AUX timeout + * period < 3.2ms. (see DP Standard v2.0, 2.11.2, 3.6.6.1). + */ + if (INTEL_GEN(i915) < 10) + return false; + + if (drm_dp_read_lttpr_common_caps(&intel_dp->aux, + intel_dp->lttpr_common_caps) < 0) + goto reset_caps; drm_dbg_kms(&dp_to_i915(intel_dp)->drm, "LTTPR common capabilities: %*ph\n", (int)sizeof(intel_dp->lttpr_common_caps), intel_dp->lttpr_common_caps); + /* The minimum value of LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV is 1.4 */ + if (intel_dp->lttpr_common_caps[0] < 0x14) + goto reset_caps; + return true; + +reset_caps: + intel_dp_reset_lttpr_common_caps(intel_dp); + return false; } static bool @@ -106,33 +128,49 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) } /** - * intel_dp_lttpr_init - detect LTTPRs and init the LTTPR link training mode + * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode * @intel_dp: Intel DP struct * - * Read the LTTPR common capabilities, switch to non-transparent link training - * mode if any is detected and read the PHY capabilities for all detected - * LTTPRs. In case of an LTTPR detection error or if the number of + * Read the LTTPR common and DPRX capabilities and switch to non-transparent + * link training mode if any is detected and read the PHY capabilities for all + * detected LTTPRs. In case of an LTTPR detection error or if the number of * LTTPRs is more than is supported (8), fall back to the no-LTTPR, * transparent mode link training mode. * * Returns: - * >0 if LTTPRs were detected and the non-transparent LT mode was set + * >0 if LTTPRs were detected and the non-transparent LT mode was set. The + * DPRX capabilities are read out. * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a - * detection failure and the transparent LT mode was set + * detection failure and the transparent LT mode was set. The DPRX + * capabilities are read out. + * <0 Reading out the DPRX capabilities failed. */ -int intel_dp_lttpr_init(struct intel_dp *intel_dp) +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) { int lttpr_count; bool ret; int i; - if (intel_dp_is_edp(intel_dp)) - return 0; - ret = intel_dp_read_lttpr_common_caps(intel_dp); + + /* The DPTX shall read the DPRX caps after LTTPR detection. */ + if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return -EIO; + } + if (!ret) return 0; + /* + * The 0xF0000-0xF02FF range is only valid if the DPCD revision is + * at least 1.4. + */ + if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return 0; + } + lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps); /* * Prevent setting LTTPR transparent mode explicitly if no LTTPRs are @@ -172,7 +210,7 @@ int intel_dp_lttpr_init(struct intel_dp *intel_dp) return lttpr_count; } -EXPORT_SYMBOL(intel_dp_lttpr_init); +EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps); static u8 dp_voltage_max(u8 preemph) { @@ -807,7 +845,10 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp, * TODO: Reiniting LTTPRs here won't be needed once proper connector * HW state readout is added. */ - int lttpr_count = intel_dp_lttpr_init(intel_dp); + int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp); + + if (lttpr_count < 0) + return; if (!intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count)) intel_dp_schedule_fallback_link_training(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h index 6a1f76bd8c75..9cb7c28027f0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h @@ -11,7 +11,7 @@ struct intel_crtc_state; struct intel_dp; -int intel_dp_lttpr_init(struct intel_dp *intel_dp); +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp); void intel_dp_get_adjust_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index f58cc5700784..a86c57d117f2 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -1014,20 +1014,14 @@ static i915_reg_t dss_ctl1_reg(const struct intel_crtc_state *crtc_state) { enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - if (crtc_state->cpu_transcoder == TRANSCODER_EDP) - return DSS_CTL1; - - return ICL_PIPE_DSS_CTL1(pipe); + return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL1(pipe) : DSS_CTL1; } static i915_reg_t dss_ctl2_reg(const struct intel_crtc_state *crtc_state) { enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - if (crtc_state->cpu_transcoder == TRANSCODER_EDP) - return DSS_CTL2; - - return ICL_PIPE_DSS_CTL2(pipe); + return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL2(pipe) : DSS_CTL2; } void intel_dsc_enable(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index f94025ec603a..a9a8ba1d3aba 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -992,14 +992,14 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state, * FIXME As we do with eDP, just make a note of the time here * and perform the wait before the next panel power on. */ - intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static void intel_dsi_shutdown(struct intel_encoder *encoder) { struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index fb1b1d096975..9cf555d6842b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -713,9 +713,12 @@ static int engine_setup_common(struct intel_engine_cs *engine) goto err_status; } + err = intel_engine_init_cmd_parser(engine); + if (err) + goto err_cmd_parser; + intel_engine_init_active(engine, ENGINE_PHYSICAL); intel_engine_init_execlists(engine); - intel_engine_init_cmd_parser(engine); intel_engine_init__pm(engine); intel_engine_init_retire(engine); @@ -732,6 +735,8 @@ static int engine_setup_common(struct intel_engine_cs *engine) return 0; +err_cmd_parser: + intel_breadcrumbs_free(engine->breadcrumbs); err_status: cleanup_status_page(engine); return err; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index a357bb431815..67de2b189598 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -316,7 +316,18 @@ void i915_vma_revoke_fence(struct i915_vma *vma) WRITE_ONCE(fence->vma, NULL); vma->fence = NULL; - with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref) + /* + * Skip the write to HW if and only if the device is currently + * suspended. + * + * If the driver does not currently hold a wakeref (if_in_use == 0), + * the device may currently be runtime suspended, or it may be woken + * up before the suspend takes place. If the device is not suspended + * (powered down) and we skip clearing the fence register, the HW is + * left in an undefined state where we may end up with multiple + * registers overlapping. + */ + with_intel_runtime_pm_if_active(fence_to_uncore(fence)->rpm, wakeref) fence_write(fence); } diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index ced9a96d7c34..5f86f5b2caf6 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -940,7 +940,7 @@ static void fini_hash_table(struct intel_engine_cs *engine) * struct intel_engine_cs based on whether the platform requires software * command parsing. */ -void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) +int intel_engine_init_cmd_parser(struct intel_engine_cs *engine) { const struct drm_i915_cmd_table *cmd_tables; int cmd_table_count; @@ -948,7 +948,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) && engine->class == COPY_ENGINE_CLASS)) - return; + return 0; switch (engine->class) { case RENDER_CLASS: @@ -1013,19 +1013,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) break; default: MISSING_CASE(engine->class); - return; + goto out; } if (!validate_cmds_sorted(engine, cmd_tables, cmd_table_count)) { drm_err(&engine->i915->drm, "%s: command descriptions are not sorted\n", engine->name); - return; + goto out; } if (!validate_regs_sorted(engine)) { drm_err(&engine->i915->drm, "%s: registers are not sorted\n", engine->name); - return; + goto out; } ret = init_hash_table(engine, cmd_tables, cmd_table_count); @@ -1033,10 +1033,17 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) drm_err(&engine->i915->drm, "%s: initialised failed!\n", engine->name); fini_hash_table(engine); - return; + goto out; } engine->flags |= I915_ENGINE_USING_CMD_PARSER; + +out: + if (intel_engine_requires_cmd_parser(engine) && + !intel_engine_using_cmd_parser(engine)) + return -EINVAL; + + return 0; } /** diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 26d69d06aa6d..cb62ddba2035 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1952,7 +1952,7 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); /* i915_cmd_parser.c */ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); -void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); +int intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); int intel_engine_cmd_parser(struct intel_engine_cs *engine, struct i915_vma *batch, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 112ba5f2ce90..e62ad69606f6 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -603,7 +603,6 @@ static int append_oa_sample(struct i915_perf_stream *stream, { int report_size = stream->oa_buffer.format_size; struct drm_i915_perf_record_header header; - u32 sample_flags = stream->sample_flags; header.type = DRM_I915_PERF_RECORD_SAMPLE; header.pad = 0; @@ -617,10 +616,8 @@ static int append_oa_sample(struct i915_perf_stream *stream, return -EFAULT; buf += sizeof(header); - if (sample_flags & SAMPLE_OA_REPORT) { - if (copy_to_user(buf, report, report_size)) - return -EFAULT; - } + if (copy_to_user(buf, report, report_size)) + return -EFAULT; (*offset) += header.size; @@ -2682,7 +2679,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream) stream->perf->ops.oa_enable(stream); - if (stream->periodic) + if (stream->sample_flags & SAMPLE_OA_REPORT) hrtimer_start(&stream->poll_check_timer, ns_to_ktime(stream->poll_oa_period), HRTIMER_MODE_REL_PINNED); @@ -2745,7 +2742,7 @@ static void i915_oa_stream_disable(struct i915_perf_stream *stream) { stream->perf->ops.oa_disable(stream); - if (stream->periodic) + if (stream->sample_flags & SAMPLE_OA_REPORT) hrtimer_cancel(&stream->poll_check_timer); } @@ -3028,7 +3025,7 @@ static ssize_t i915_perf_read(struct file *file, * disabled stream as an error. In particular it might otherwise lead * to a deadlock for blocking file descriptors... */ - if (!stream->enabled) + if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT)) return -EIO; if (!(file->f_flags & O_NONBLOCK)) { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7146cd0f3256..aaf1f0045b16 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3316,7 +3316,18 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ILK_DISPLAY_CHICKEN1 _MMIO(0x42000) #define ILK_FBCQ_DIS (1 << 22) -#define ILK_PABSTRETCH_DIS (1 << 21) +#define ILK_PABSTRETCH_DIS REG_BIT(21) +#define ILK_SABSTRETCH_DIS REG_BIT(20) +#define IVB_PRI_STRETCH_MAX_MASK REG_GENMASK(21, 20) +#define IVB_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0) +#define IVB_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1) +#define IVB_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2) +#define IVB_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3) +#define IVB_SPR_STRETCH_MAX_MASK REG_GENMASK(19, 18) +#define IVB_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0) +#define IVB_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1) +#define IVB_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2) +#define IVB_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3) /* @@ -8039,6 +8050,16 @@ enum { #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 +#define HSW_PRI_STRETCH_MAX_MASK REG_GENMASK(28, 27) +#define HSW_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0) +#define HSW_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1) +#define HSW_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2) +#define HSW_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3) +#define HSW_SPR_STRETCH_MAX_MASK REG_GENMASK(26, 25) +#define HSW_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0) +#define HSW_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1) +#define HSW_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2) +#define HSW_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3) #define HSW_FBCQ_DIS (1 << 22) #define BDW_DPRS_MASK_VBLANK_SRD (1 << 0) #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 0c3e63f27c29..4b4d8d034782 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5471,12 +5471,12 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state, struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; int ret; - memset(wm, 0, sizeof(*wm)); - /* Watermarks calculated in master */ if (plane_state->planar_slave) return 0; + memset(wm, 0, sizeof(*wm)); + if (plane_state->planar_linked_plane) { const struct drm_framebuffer *fb = plane_state->hw.fb; enum plane_id y_plane_id = plane_state->planar_linked_plane->id; @@ -7245,11 +7245,16 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD); - /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ for_each_pipe(dev_priv, pipe) { + /* WaPsrDPRSUnmaskVBlankInSRD:bdw */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) | BDW_DPRS_MASK_VBLANK_SRD); + + /* Undocumented but fixes async flip + VT-d corruption */ + if (intel_vtd_active()) + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); } /* WaVSRefCountFullforceMissDisable:bdw */ @@ -7285,11 +7290,20 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) static void hsw_init_clock_gating(struct drm_i915_private *dev_priv) { + enum pipe pipe; + /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) | HSW_FBCQ_DIS); + for_each_pipe(dev_priv, pipe) { + /* Undocumented but fixes async flip + VT-d corruption */ + if (intel_vtd_active()) + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); + } + /* This is required by WaCatErrorRejectionIssue:hsw */ intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 153ca9e65382..8b725efb2254 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -412,12 +412,20 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm) } /** - * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active * @rpm: the intel_runtime_pm structure + * @ignore_usecount: get a ref even if dev->power.usage_count is 0 * * This function grabs a device-level runtime pm reference if the device is - * already in use and ensures that it is powered up. It is illegal to try - * and access the HW should intel_runtime_pm_get_if_in_use() report failure. + * already active and ensures that it is powered up. It is illegal to try + * and access the HW should intel_runtime_pm_get_if_active() report failure. + * + * If @ignore_usecount=true, a reference will be acquired even if there is no + * user requiring the device to be powered up (dev->power.usage_count == 0). + * If the function returns false in this case then it's guaranteed that the + * device's runtime suspend hook has been called already or that it will be + * called (and hence it's also guaranteed that the device's runtime resume + * hook will be called eventually). * * Any runtime pm reference obtained by this function must have a symmetric * call to intel_runtime_pm_put() to release the reference again. @@ -425,7 +433,8 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm) * Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates * as True if the wakeref was acquired, or False otherwise. */ -intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm, + bool ignore_usecount) { if (IS_ENABLED(CONFIG_PM)) { /* @@ -434,7 +443,7 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) * function, since the power state is undefined. This applies * atm to the late/early system suspend/resume handlers. */ - if (pm_runtime_get_if_in_use(rpm->kdev) <= 0) + if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0) return 0; } @@ -443,6 +452,16 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) return track_intel_runtime_pm_wakeref(rpm); } +intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, false); +} + +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, true); +} + /** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @rpm: the intel_runtime_pm structure diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h index ae64ff14c642..1e4ddd11c12b 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.h +++ b/drivers/gpu/drm/i915/intel_runtime_pm.h @@ -177,6 +177,7 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm); +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm); @@ -188,6 +189,10 @@ intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm); for ((wf) = intel_runtime_pm_get_if_in_use(rpm); (wf); \ intel_runtime_pm_put((rpm), (wf)), (wf) = 0) +#define with_intel_runtime_pm_if_active(rpm, wf) \ + for ((wf) = intel_runtime_pm_get_if_active(rpm); (wf); \ + intel_runtime_pm_put((rpm), (wf)), (wf) = 0) + void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm); #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM) void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref); diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index d1a9841adeed..e6a88c8cbd69 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -215,7 +215,7 @@ static int imx_drm_bind(struct device *dev) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto err_kms; ret = drm_vblank_init(drm, MAX_CRTC); if (ret) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index dbfe39e2f7f6..ffdc492c5bc5 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -197,6 +197,11 @@ static void imx_ldb_encoder_enable(struct drm_encoder *encoder) int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + drm_panel_prepare(imx_ldb_ch->panel); if (dual) { @@ -255,6 +260,11 @@ imx_ldb_encoder_atomic_mode_set(struct drm_encoder *encoder, int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); u32 bus_format = imx_ldb_ch->bus_format; + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + if (mode->clock > 170000) { dev_warn(ldb->dev, "%s: mode exceeds 170 MHz pixel clock\n", __func__); @@ -583,7 +593,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) struct imx_ldb_channel *channel = &imx_ldb->channel[i]; if (!channel->ldb) - break; + continue; ret = imx_ldb_register(drm, channel); if (ret) diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 42c5d3246cfc..453d8b4c5763 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -482,6 +482,16 @@ static int meson_probe_remote(struct platform_device *pdev, return count; } +static void meson_drv_shutdown(struct platform_device *pdev) +{ + struct meson_drm *priv = dev_get_drvdata(&pdev->dev); + struct drm_device *drm = priv->drm; + + DRM_DEBUG_DRIVER("\n"); + drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); +} + static int meson_drv_probe(struct platform_device *pdev) { struct component_match *match = NULL; @@ -553,6 +563,7 @@ static const struct dev_pm_ops meson_drv_pm_ops = { static struct platform_driver meson_drm_platform_driver = { .probe = meson_drv_probe, + .shutdown = meson_drv_shutdown, .driver = { .name = "meson-drm", .of_match_table = dt_match, diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 7e553d3efeb2..ce13d49e615b 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1386,8 +1386,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO, - REG_A5XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, + REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 5ccc9da455a1..c35b06b46fcc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -304,7 +304,7 @@ int a5xx_power_init(struct msm_gpu *gpu) /* Set up the limits management */ if (adreno_is_a530(adreno_gpu)) a530_lm_setup(gpu); - else + else if (adreno_is_a540(adreno_gpu)) a540_lm_setup(gpu); /* Set up SP/TP power collpase */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 71c917f909af..91cf46f84025 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -339,7 +339,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) else bit = a6xx_gmu_oob_bits[state].ack_new; - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit); + gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit); } /* Enable CPU control of SPTP power power collapse */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index ba8e9d3cf0fe..d553f62f4eeb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -522,28 +522,73 @@ static int a6xx_cp_init(struct msm_gpu *gpu) return a6xx_idle(gpu, ring) ? 0 : -EINVAL; } -static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, +/* + * Check that the microcode version is new enough to include several key + * security fixes. Return true if the ucode is safe. + */ +static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, struct drm_gem_object *obj) { + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; u32 *buf = msm_gem_get_vaddr(obj); + bool ret = false; if (IS_ERR(buf)) - return; + return false; /* - * If the lowest nibble is 0xa that is an indication that this microcode - * has been patched. The actual version is in dword [3] but we only care - * about the patchlevel which is the lowest nibble of dword [3] - * - * Otherwise check that the firmware is greater than or equal to 1.90 - * which was the first version that had this fix built in + * Targets up to a640 (a618, a630 and a640) need to check for a + * microcode version that is patched to support the whereami opcode or + * one that is new enough to include it by default. */ - if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) - a6xx_gpu->has_whereami = true; - else if ((buf[0] & 0xfff) > 0x190) - a6xx_gpu->has_whereami = true; + if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) || + adreno_is_a640(adreno_gpu)) { + /* + * If the lowest nibble is 0xa that is an indication that this + * microcode has been patched. The actual version is in dword + * [3] but we only care about the patchlevel which is the lowest + * nibble of dword [3] + * + * Otherwise check that the firmware is greater than or equal + * to 1.90 which was the first version that had this fix built + * in + */ + if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) || + (buf[0] & 0xfff) >= 0x190) { + a6xx_gpu->has_whereami = true; + ret = true; + goto out; + } + DRM_DEV_ERROR(&gpu->pdev->dev, + "a630 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x190); + } else { + /* + * a650 tier targets don't need whereami but still need to be + * equal to or newer than 0.95 for other security fixes + */ + if (adreno_is_a650(adreno_gpu)) { + if ((buf[0] & 0xfff) >= 0x095) { + ret = true; + goto out; + } + + DRM_DEV_ERROR(&gpu->pdev->dev, + "a650 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x095); + } + + /* + * When a660 is added those targets should return true here + * since those have all the critical security fixes built in + * from the start + */ + } +out: msm_gem_put_vaddr(obj); + return ret; } static int a6xx_ucode_init(struct msm_gpu *gpu) @@ -566,7 +611,13 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw"); - a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo); + if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) { + msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace); + drm_gem_object_put(a6xx_gpu->sqe_bo); + + a6xx_gpu->sqe_bo = NULL; + return -EPERM; + } } gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO, @@ -1177,8 +1228,8 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO, - REG_A6XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, + REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); mutex_unlock(&perfcounter_oob); @@ -1350,35 +1401,26 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu, u32 revn) { struct opp_table *opp_table; - struct nvmem_cell *cell; u32 supp_hw = UINT_MAX; - void *buf; + u16 speedbin; + int ret; - cell = nvmem_cell_get(dev, "speed_bin"); + ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin); /* * -ENOENT means that the platform doesn't support speedbin which is * fine */ - if (PTR_ERR(cell) == -ENOENT) + if (ret == -ENOENT) { return 0; - else if (IS_ERR(cell)) { - DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); - goto done; - } - - buf = nvmem_cell_read(cell, NULL); - if (IS_ERR(buf)) { - nvmem_cell_put(cell); + } else if (ret) { DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); + "failed to read speed-bin (%d). Some OPPs may not be supported by hardware", + ret); goto done; } + speedbin = le16_to_cpu(speedbin); - supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf)); - - kfree(buf); - nvmem_cell_put(cell); + supp_hw = fuse_to_supp_hw(dev, revn, speedbin); done: opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 8981cfa9dbc3..92e6f1b94738 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -496,7 +496,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); - DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0)); + if (cfg->merge_3d) + DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, + BIT(cfg->merge_3d - MERGE_3D_0)); } static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 5a8e3e1fc48c..85f2c3564c96 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -43,6 +43,8 @@ #define DPU_DEBUGFS_DIR "msm_dpu" #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" +#define MIN_IB_BW 400000000ULL /* Min ib vote 400MB */ + static int dpu_kms_hw_init(struct msm_kms *kms); static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); @@ -931,6 +933,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms) DPU_DEBUG("REG_DMA is not defined"); } + if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) + dpu_kms_parse_data_bus_icc_path(dpu_kms); + pm_runtime_get_sync(&dpu_kms->pdev->dev); dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0); @@ -1032,9 +1037,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms) dpu_vbif_init_memtypes(dpu_kms); - if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) - dpu_kms_parse_data_bus_icc_path(dpu_kms); - pm_runtime_put_sync(&dpu_kms->pdev->dev); return 0; @@ -1191,10 +1193,10 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) ddev = dpu_kms->dev; + WARN_ON(!(dpu_kms->num_paths)); /* Min vote of BW is required before turning on AXI clk */ for (i = 0; i < dpu_kms->num_paths; i++) - icc_set_bw(dpu_kms->path[i], 0, - dpu_kms->catalog->perf.min_dram_ib); + icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW)); rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); if (rc) { diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 1c6e1d2b947c..7c22bfe0fc7d 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -32,6 +32,8 @@ struct dp_aux_private { struct drm_dp_aux dp_aux; }; +#define MAX_AUX_RETRIES 5 + static const char *dp_aux_get_error(u32 aux_error) { switch (aux_error) { @@ -377,6 +379,11 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, ret = dp_aux_cmd_fifo_tx(aux, msg); if (ret < 0) { + if (aux->native) { + aux->retry_cnt++; + if (!(aux->retry_cnt % MAX_AUX_RETRIES)) + dp_catalog_aux_update_cfg(aux->catalog); + } usleep_range(400, 500); /* at least 400us to next try */ goto unlock_exit; } diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c index a45fe95aff49..3dc65877fa10 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c @@ -163,7 +163,7 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, break; case MSM_DSI_PHY_7NM: case MSM_DSI_PHY_7NM_V4_1: - pll = msm_dsi_pll_7nm_init(pdev, id); + pll = msm_dsi_pll_7nm_init(pdev, type, id); break; default: pll = ERR_PTR(-ENXIO); diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h index 3405982a092c..bbecb1de5678 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h @@ -117,10 +117,12 @@ msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) } #endif #ifdef CONFIG_DRM_MSM_DSI_7NM_PHY -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id); +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id); #else static inline struct msm_dsi_pll * -msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id) { return ERR_PTR(-ENODEV); } diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c index 93bf142e4a4e..e29b3bfd63d1 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c @@ -325,7 +325,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll) pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low); pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid); pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, reg->pll_lockdet_rate); pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */ pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters); @@ -509,6 +509,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, { struct msm_dsi_pll *pll = hw_clk_to_pll(hw); struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct dsi_pll_config *config = &pll_7nm->pll_configuration; void __iomem *base = pll_7nm->mmio; u64 ref_clk = pll_7nm->vco_ref_clk_rate; u64 vco_rate = 0x0; @@ -529,9 +530,8 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, /* * TODO: * 1. Assumes prescaler is disabled - * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits) */ - multiplier = 1 << 18; + multiplier = 1 << config->frac_bits; pll_freq = dec * (ref_clk * 2); tmp64 = (ref_clk * 2 * frac); pll_freq += div_u64(tmp64, multiplier); @@ -852,7 +852,8 @@ err_base_clk_hw: return ret; } -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id) { struct dsi_pll_7nm *pll_7nm; struct msm_dsi_pll *pll; @@ -885,7 +886,7 @@ struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) pll = &pll_7nm->base; pll->min_rate = 1000000000UL; pll->max_rate = 3500000000UL; - if (pll->type == MSM_DSI_PHY_7NM_V4_1) { + if (type == MSM_DSI_PHY_7NM_V4_1) { pll->min_rate = 600000000UL; pll->max_rate = (unsigned long)5000000000ULL; /* workaround for max rate overflowing on 32-bit builds: */ diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 6a326761dc4a..edcaccaa27e6 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -57,10 +57,13 @@ static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) { + int crtc_index; struct drm_crtc *crtc; - for_each_crtc_mask(kms->dev, crtc, crtc_mask) - mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]); + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + crtc_index = drm_crtc_index(crtc); + mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index); + } } static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 94525ac76d4e..196907689c82 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -570,6 +570,7 @@ err_free_priv: kfree(priv); err_put_drm_dev: drm_dev_put(ddev); + platform_set_drvdata(pdev, NULL); return ret; } @@ -1072,6 +1073,10 @@ static int __maybe_unused msm_pm_resume(struct device *dev) static int __maybe_unused msm_pm_prepare(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return 0; return drm_mode_config_helper_suspend(ddev); } @@ -1079,6 +1084,10 @@ static int __maybe_unused msm_pm_prepare(struct device *dev) static void __maybe_unused msm_pm_complete(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_mode_config_helper_resume(ddev); } @@ -1311,6 +1320,10 @@ static int msm_pdev_remove(struct platform_device *pdev) static void msm_pdev_shutdown(struct platform_device *pdev) { struct drm_device *drm = platform_get_drvdata(pdev); + struct msm_drm_private *priv = drm ? drm->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_atomic_helper_shutdown(drm); } diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index ad2703698b05..cd59a5918038 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -45,7 +45,7 @@ int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, int ret; if (fence > fctx->last_fence) { - DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n", + DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", fctx->name, fence, fctx->last_fence); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index 4735251a394d..d8151a89e163 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -157,7 +157,6 @@ struct msm_kms { * from the crtc's pending_timer close to end of the frame: */ struct mutex commit_lock[MAX_CRTCS]; - struct lock_class_key commit_lock_keys[MAX_CRTCS]; unsigned pending_crtc_mask; struct msm_pending_timer pending_timers[MAX_CRTCS]; }; @@ -167,11 +166,8 @@ static inline int msm_kms_init(struct msm_kms *kms, { unsigned i, ret; - for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) { - lockdep_register_key(&kms->commit_lock_keys[i]); - __mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]", - &kms->commit_lock_keys[i]); - } + for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) + mutex_init(&kms->commit_lock[i]); kms->funcs = funcs; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 196612addfd6..1c9c0cdf85db 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2693,9 +2693,20 @@ nv50_display_create(struct drm_device *dev) else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; - if (disp->disp->object.oclass >= GK104_DISP) { + /* FIXME: 256x256 cursors are supported on Kepler, however unlike Maxwell and later + * generations Kepler requires that we use small pages (4K) for cursor scanout surfaces. The + * proper fix for this is to teach nouveau to migrate fbs being used for the cursor plane to + * small page allocations in prepare_fb(). When this is implemented, we should also force + * large pages (128K) for ovly fbs in order to fix Kepler ovlys. + * But until then, just limit cursors to 128x128 - which is small enough to avoid ever using + * large pages. + */ + if (disp->disp->object.oclass >= GM107_DISP) { dev->mode_config.cursor_width = 256; dev->mode_config.cursor_height = 256; + } else if (disp->disp->object.oclass >= GK104_DISP) { + dev->mode_config.cursor_width = 128; + dev->mode_config.cursor_height = 128; } else { dev->mode_config.cursor_width = 64; dev->mode_config.cursor_height = 64; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2375711877cf..f2720a006199 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -551,12 +551,17 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; ++i) { + i = 0; + while (i < ttm_dma->num_pages) { struct page *p = ttm_dma->pages[i]; size_t num_pages = 1; @@ -582,12 +587,17 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) return; - for (i = 0; i < ttm_dma->num_pages; ++i) { + i = 0; + while (i < ttm_dma->num_pages) { struct page *p = ttm_dma->pages[i]; size_t num_pages = 1; diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 8e11612f5fe1..b31d750c425a 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -2149,11 +2149,12 @@ static int dsi_vc_send_short(struct dsi_data *dsi, int vc, const struct mipi_dsi_msg *msg) { struct mipi_dsi_packet pkt; + int ret; u32 r; - r = mipi_dsi_create_packet(&pkt, msg); - if (r < 0) - return r; + ret = mipi_dsi_create_packet(&pkt, msg); + if (ret < 0) + return ret; WARN_ON(!dsi_bus_is_locked(dsi)); diff --git a/drivers/gpu/drm/panel/panel-dsi-cm.c b/drivers/gpu/drm/panel/panel-dsi-cm.c index af381d756ac1..5fbfb71ca3d9 100644 --- a/drivers/gpu/drm/panel/panel-dsi-cm.c +++ b/drivers/gpu/drm/panel/panel-dsi-cm.c @@ -37,6 +37,7 @@ struct dsic_panel_data { u32 height_mm; u32 max_hs_rate; u32 max_lp_rate; + bool te_support; }; struct panel_drv_data { @@ -334,9 +335,11 @@ static int dsicm_power_on(struct panel_drv_data *ddata) if (r) goto err; - r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); - if (r) - goto err; + if (ddata->panel_data->te_support) { + r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); + if (r) + goto err; + } /* possible panel bug */ msleep(100); @@ -619,6 +622,7 @@ static const struct dsic_panel_data taal_data = { .height_mm = 0, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = true, }; static const struct dsic_panel_data himalaya_data = { @@ -629,6 +633,7 @@ static const struct dsic_panel_data himalaya_data = { .height_mm = 88, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct dsic_panel_data droid4_data = { @@ -639,6 +644,7 @@ static const struct dsic_panel_data droid4_data = { .height_mm = 89, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct of_device_id dsicm_of_match[] = { diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 012bce0cdb65..10738e04c09b 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -328,6 +328,7 @@ static void qxl_crtc_update_monitors_config(struct drm_crtc *crtc, head.id = i; head.flags = 0; + head.surface_id = 0; oldcount = qdev->monitors_config->count; if (crtc->state->active) { struct drm_display_mode *mode = &crtc->mode; diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 0fcfc952d5e9..b372455e2729 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -321,7 +321,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, int type, struct qxl_release **release, struct qxl_bo **rbo) { - struct qxl_bo *bo; + struct qxl_bo *bo, *free_bo = NULL; int idr_ret; int ret = 0; union qxl_release_info *info; @@ -347,7 +347,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, mutex_lock(&qdev->release_mutex); if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) { - qxl_bo_unref(&qdev->current_release_bo[cur_idx]); + free_bo = qdev->current_release_bo[cur_idx]; qdev->current_release_bo_offset[cur_idx] = 0; qdev->current_release_bo[cur_idx] = NULL; } @@ -355,6 +355,10 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, ret = qxl_release_bo_alloc(qdev, &qdev->current_release_bo[cur_idx]); if (ret) { mutex_unlock(&qdev->release_mutex); + if (free_bo) { + qxl_bo_unpin(free_bo); + qxl_bo_unref(&free_bo); + } qxl_release_free(qdev, *release); return ret; } @@ -370,6 +374,10 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, *rbo = bo; mutex_unlock(&qdev->release_mutex); + if (free_bo) { + qxl_bo_unpin(free_bo); + qxl_bo_unref(&free_bo); + } ret = qxl_release_list_add(*release, bo); qxl_bo_unref(&bo); diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index f09989bdce98..3effc8c71494 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -574,6 +574,8 @@ struct radeon_gem { struct list_head objects; }; +extern const struct drm_gem_object_funcs radeon_gem_object_funcs; + int radeon_gem_init(struct radeon_device *rdev); void radeon_gem_fini(struct radeon_device *rdev); int radeon_gem_object_create(struct radeon_device *rdev, unsigned long size, diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 941826923247..db14a82a2e4b 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -43,7 +43,7 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj); int radeon_gem_prime_pin(struct drm_gem_object *obj); void radeon_gem_prime_unpin(struct drm_gem_object *obj); -static const struct drm_gem_object_funcs radeon_gem_object_funcs; +const struct drm_gem_object_funcs radeon_gem_object_funcs; static void radeon_gem_object_free(struct drm_gem_object *gobj) { @@ -227,7 +227,7 @@ static int radeon_gem_handle_lockup(struct radeon_device *rdev, int r) return r; } -static const struct drm_gem_object_funcs radeon_gem_object_funcs = { +const struct drm_gem_object_funcs radeon_gem_object_funcs = { .free = radeon_gem_object_free, .open = radeon_gem_object_open, .close = radeon_gem_object_close, diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index ab29eb9e8667..42a87948e28c 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -56,6 +56,8 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, if (ret) return ERR_PTR(ret); + bo->tbo.base.funcs = &radeon_gem_object_funcs; + mutex_lock(&rdev->gem.mutex); list_add_tail(&bo->list, &rdev->gem.objects); mutex_unlock(&rdev->gem.mutex); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e8c66d10478f..78893bea85ae 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -364,7 +364,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt * if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) { /* check that we only pin down anonymous memory to prevent problems with writeback */ - unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE; + unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE; struct vm_area_struct *vma; vma = find_vma(gtt->usermm, gtt->userptr); if (!vma || vma->vm_file || vma->vm_end < end) @@ -386,7 +386,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt * } while (pinned < ttm->num_pages); r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c index ba8c6038cd63..ca3761772211 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c @@ -48,21 +48,12 @@ static unsigned int rcar_du_encoder_count_ports(struct device_node *node) static const struct drm_encoder_funcs rcar_du_encoder_funcs = { }; -static void rcar_du_encoder_release(struct drm_device *dev, void *res) -{ - struct rcar_du_encoder *renc = res; - - drm_encoder_cleanup(&renc->base); - kfree(renc); -} - int rcar_du_encoder_init(struct rcar_du_device *rcdu, enum rcar_du_output output, struct device_node *enc_node) { struct rcar_du_encoder *renc; struct drm_bridge *bridge; - int ret; /* * Locate the DRM bridge from the DT node. For the DPAD outputs, if the @@ -101,26 +92,16 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu, return -ENOLINK; } - renc = kzalloc(sizeof(*renc), GFP_KERNEL); - if (renc == NULL) - return -ENOMEM; - - renc->output = output; - dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n", enc_node, output); - ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs, - DRM_MODE_ENCODER_NONE, NULL); - if (ret < 0) { - kfree(renc); - return ret; - } + renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base, + &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE, + NULL); + if (!renc) + return -ENOMEM; - ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release, - renc); - if (ret) - return ret; + renc->output = output; /* * Attach the bridge to the encoder. The bridge will create the diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 0ae3a025efe9..134986dc2783 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1688,6 +1688,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, dev_err(dc->dev, "failed to set clock rate to %lu Hz\n", state->pclk); + + err = clk_set_rate(dc->clk, state->pclk); + if (err < 0) + dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", + dc->clk, state->pclk, err); } DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk), @@ -1698,11 +1703,6 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1; tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL); } - - err = clk_set_rate(dc->clk, state->pclk); - if (err < 0) - dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", - dc->clk, state->pclk, err); } static void tegra_dc_stop(struct tegra_dc *dc) @@ -2501,22 +2501,18 @@ static int tegra_dc_couple(struct tegra_dc *dc) * POWER_CONTROL registers during CRTC enabling. */ if (dc->soc->coupled_pm && dc->pipe == 1) { - u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; - struct device_link *link; - struct device *partner; + struct device *companion; + struct tegra_dc *parent; - partner = driver_find_device(dc->dev->driver, NULL, NULL, - tegra_dc_match_by_pipe); - if (!partner) + companion = driver_find_device(dc->dev->driver, NULL, (const void *)0, + tegra_dc_match_by_pipe); + if (!companion) return -EPROBE_DEFER; - link = device_link_add(dc->dev, partner, flags); - if (!link) { - dev_err(dc->dev, "failed to link controllers\n"); - return -EINVAL; - } + parent = dev_get_drvdata(companion); + dc->client.parent = &parent->client; - dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner)); + dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); } return 0; diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index f02a035dda45..7b88261f57bb 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3115,6 +3115,12 @@ static int tegra_sor_init(struct host1x_client *client) * kernel is possible. */ if (sor->rst) { + err = pm_runtime_resume_and_get(sor->dev); + if (err < 0) { + dev_err(sor->dev, "failed to get runtime PM: %d\n", err); + return err; + } + err = reset_control_acquire(sor->rst); if (err < 0) { dev_err(sor->dev, "failed to acquire SOR reset: %d\n", @@ -3148,6 +3154,7 @@ static int tegra_sor_init(struct host1x_client *client) } reset_control_release(sor->rst); + pm_runtime_put(sor->dev); } err = clk_prepare_enable(sor->clk_safe); diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c index 33f65f4626e5..23866a54e3f9 100644 --- a/drivers/gpu/drm/tiny/gm12u320.c +++ b/drivers/gpu/drm/tiny/gm12u320.c @@ -83,6 +83,7 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)"); struct gm12u320_device { struct drm_device dev; + struct device *dmadev; struct drm_simple_display_pipe pipe; struct drm_connector conn; unsigned char *cmd_buf; @@ -601,6 +602,22 @@ static const uint64_t gm12u320_pipe_modifiers[] = { DRM_FORMAT_MOD_INVALID }; +/* + * FIXME: Dma-buf sharing requires DMA support by the importing device. + * This function is a workaround to make USB devices work as well. + * See todo.rst for how to fix the issue in the dma-buf framework. + */ +static struct drm_gem_object *gm12u320_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct gm12u320_device *gm12u320 = to_gm12u320(dev); + + if (!gm12u320->dmadev) + return ERR_PTR(-ENODEV); + + return drm_gem_prime_import_dev(dev, dma_buf, gm12u320->dmadev); +} + DEFINE_DRM_GEM_FOPS(gm12u320_fops); static const struct drm_driver gm12u320_drm_driver = { @@ -614,6 +631,7 @@ static const struct drm_driver gm12u320_drm_driver = { .fops = &gm12u320_fops, DRM_GEM_SHMEM_DRIVER_OPS, + .gem_prime_import = gm12u320_gem_prime_import, }; static const struct drm_mode_config_funcs gm12u320_mode_config_funcs = { @@ -640,15 +658,18 @@ static int gm12u320_usb_probe(struct usb_interface *interface, struct gm12u320_device, dev); if (IS_ERR(gm12u320)) return PTR_ERR(gm12u320); + dev = &gm12u320->dev; + + gm12u320->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev)); + if (!gm12u320->dmadev) + drm_warn(dev, "buffer sharing not supported"); /* not an error */ INIT_DELAYED_WORK(&gm12u320->fb_update.work, gm12u320_fb_update_work); mutex_init(&gm12u320->fb_update.lock); - dev = &gm12u320->dev; - ret = drmm_mode_config_init(dev); if (ret) - return ret; + goto err_put_device; dev->mode_config.min_width = GM12U320_USER_WIDTH; dev->mode_config.max_width = GM12U320_USER_WIDTH; @@ -658,15 +679,15 @@ static int gm12u320_usb_probe(struct usb_interface *interface, ret = gm12u320_usb_alloc(gm12u320); if (ret) - return ret; + goto err_put_device; ret = gm12u320_set_ecomode(gm12u320); if (ret) - return ret; + goto err_put_device; ret = gm12u320_conn_init(gm12u320); if (ret) - return ret; + goto err_put_device; ret = drm_simple_display_pipe_init(&gm12u320->dev, &gm12u320->pipe, @@ -676,24 +697,31 @@ static int gm12u320_usb_probe(struct usb_interface *interface, gm12u320_pipe_modifiers, &gm12u320->conn); if (ret) - return ret; + goto err_put_device; drm_mode_config_reset(dev); usb_set_intfdata(interface, dev); ret = drm_dev_register(dev, 0); if (ret) - return ret; + goto err_put_device; drm_fbdev_generic_setup(dev, 0); return 0; + +err_put_device: + put_device(gm12u320->dmadev); + return ret; } static void gm12u320_usb_disconnect(struct usb_interface *interface) { struct drm_device *dev = usb_get_intfdata(interface); + struct gm12u320_device *gm12u320 = to_gm12u320(dev); + put_device(gm12u320->dmadev); + gm12u320->dmadev = NULL; drm_dev_unplug(dev); drm_atomic_helper_shutdown(dev); } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 20a25660b35b..101a68dc615b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -136,7 +136,8 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, struct ttm_bo_device *bdev = bo->bdev; struct ttm_resource_manager *man; - dma_resv_assert_held(bo->base.resv); + if (!bo->deleted) + dma_resv_assert_held(bo->base.resv); if (bo->pin_count) { ttm_bo_del_from_lru(bo); @@ -508,8 +509,11 @@ static void ttm_bo_release(struct kref *kref) * Make pinned bos immediately available to * shrinkers, now that they are queued for * destruction. + * + * FIXME: QXL is triggering this. Can be removed when the + * driver is fixed. */ - if (WARN_ON(bo->pin_count)) { + if (WARN_ON_ONCE(bo->pin_count)) { bo->pin_count = 0; ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); } diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 6e27cb1bf48b..4eb6efb8b8c0 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -268,13 +268,13 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool, /* Remove a pool_type from the global shrinker list and free all pages */ static void ttm_pool_type_fini(struct ttm_pool_type *pt) { - struct page *p, *tmp; + struct page *p; mutex_lock(&shrinker_lock); list_del(&pt->shrinker_list); mutex_unlock(&shrinker_lock); - list_for_each_entry_safe(p, tmp, &pt->pages, lru) + while ((p = ttm_pool_type_take(pt))) ttm_pool_free_page(pt->pool, pt->caching, pt->order, p); } diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 9269092697d8..5703277c6f52 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -32,6 +32,22 @@ static int udl_usb_resume(struct usb_interface *interface) return drm_mode_config_helper_resume(dev); } +/* + * FIXME: Dma-buf sharing requires DMA support by the importing device. + * This function is a workaround to make USB devices work as well. + * See todo.rst for how to fix the issue in the dma-buf framework. + */ +static struct drm_gem_object *udl_driver_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct udl_device *udl = to_udl(dev); + + if (!udl->dmadev) + return ERR_PTR(-ENODEV); + + return drm_gem_prime_import_dev(dev, dma_buf, udl->dmadev); +} + DEFINE_DRM_GEM_FOPS(udl_driver_fops); static const struct drm_driver driver = { @@ -40,6 +56,7 @@ static const struct drm_driver driver = { /* GEM hooks */ .fops = &udl_driver_fops, DRM_GEM_SHMEM_DRIVER_OPS, + .gem_prime_import = udl_driver_gem_prime_import, .name = DRIVER_NAME, .desc = DRIVER_DESC, diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index 875e73551ae9..cc16a13316e4 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -50,6 +50,7 @@ struct urb_list { struct udl_device { struct drm_device drm; struct device *dev; + struct device *dmadev; struct drm_simple_display_pipe display_pipe; diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index 0e2a376cb075..853f147036f6 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -315,6 +315,10 @@ int udl_init(struct udl_device *udl) DRM_DEBUG("\n"); + udl->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev)); + if (!udl->dmadev) + drm_warn(dev, "buffer sharing not supported"); /* not an error */ + mutex_init(&udl->gem_lock); if (!udl_parse_vendor_descriptor(udl)) { @@ -343,12 +347,18 @@ int udl_init(struct udl_device *udl) err: if (udl->urbs.count) udl_free_urb_list(dev); + put_device(udl->dmadev); DRM_ERROR("%d\n", ret); return ret; } int udl_drop_usb(struct drm_device *dev) { + struct udl_device *udl = to_udl(dev); + udl_free_urb_list(dev); + put_device(udl->dmadev); + udl->dmadev = NULL; + return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 269390bc586e..76657dcdf9b0 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -210,6 +210,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) { const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc); const struct vc4_pv_data *pv_data = vc4_crtc_to_vc4_pv_data(vc4_crtc); + struct vc4_dev *vc4 = to_vc4_dev(vc4_crtc->base.dev); u32 fifo_len_bytes = pv_data->fifo_depth; /* @@ -238,6 +239,22 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) if (crtc_data->hvs_output == 5) return 32; + /* + * It looks like in some situations, we will overflow + * the PixelValve FIFO (with the bit 10 of PV stat being + * set) and stall the HVS / PV, eventually resulting in + * a page flip timeout. + * + * Displaying the video overlay during a playback with + * Kodi on an RPi3 seems to be a great solution with a + * failure rate around 50%. + * + * Removing 1 from the FIFO full level however + * seems to completely remove that issue. + */ + if (!vc4->hvs->hvs5) + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1; + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX; } } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 7322169c0682..1e9c84cf614a 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -1146,7 +1146,6 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = state->src_y; plane->state->src_w = state->src_w; plane->state->src_h = state->src_h; - plane->state->src_h = state->src_h; plane->state->alpha = state->alpha; plane->state->pixel_blend_mode = state->pixel_blend_mode; plane->state->rotation = state->rotation; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index ba658fa9cf6c..183571c387b7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -481,11 +481,15 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) vmw_bo_unreference(&old_buf); res->id = vcotbl->type; + /* Release the pin acquired in vmw_bo_init */ + ttm_bo_unpin(bo); + return 0; out_map_new: ttm_bo_kunmap(&old_map); out_wait: + ttm_bo_unpin(bo); ttm_bo_unreserve(bo); vmw_bo_unreference(&buf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index dd69b51c40e4..6fa24645fbbf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -712,17 +712,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) dev_priv->last_read_seqno = (uint32_t) -100; dev_priv->drm.dev_private = dev_priv; - ret = vmw_setup_pci_resources(dev_priv, pci_id); - if (ret) - return ret; - ret = vmw_detect_version(dev_priv); - if (ret) - goto out_no_pci_or_version; - mutex_init(&dev_priv->cmdbuf_mutex); - mutex_init(&dev_priv->release_mutex); mutex_init(&dev_priv->binding_mutex); - mutex_init(&dev_priv->global_kms_state_mutex); ttm_lock_init(&dev_priv->reservation_sem); spin_lock_init(&dev_priv->resource_lock); spin_lock_init(&dev_priv->hw_lock); @@ -730,6 +721,14 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) spin_lock_init(&dev_priv->cap_lock); spin_lock_init(&dev_priv->cursor_lock); + ret = vmw_setup_pci_resources(dev_priv, pci_id); + if (ret) + return ret; + ret = vmw_detect_version(dev_priv); + if (ret) + goto out_no_pci_or_version; + + for (i = vmw_res_context; i < vmw_res_max; ++i) { idr_init(&dev_priv->res_idr[i]); INIT_LIST_HEAD(&dev_priv->res_lru[i]); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5fa5bcd20cc5..eb76a6b9ebca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -529,7 +529,6 @@ struct vmw_private { struct vmw_overlay *overlay_priv; struct drm_property *hotplug_mode_update_property; struct drm_property *implicit_placement_property; - struct mutex global_kms_state_mutex; spinlock_t cursor_lock; struct drm_atomic_state *suspend_state; @@ -592,7 +591,6 @@ struct vmw_private { bool refuse_hibernation; bool suspend_locked; - struct mutex release_mutex; atomic_t num_fifo_resources; /* @@ -1524,9 +1522,8 @@ static inline void vmw_bo_unreference(struct vmw_buffer_object **buf) struct vmw_buffer_object *tmp_buf = *buf; *buf = NULL; - if (tmp_buf != NULL) { + if (tmp_buf != NULL) ttm_bo_put(&tmp_buf->base); - } } static inline struct vmw_buffer_object * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index a372980fe6a5..f2d625415458 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -94,6 +94,16 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, struct vmw_piter data_iter, unsigned long num_data_pages); + +static inline void vmw_bo_unpin_unlocked(struct ttm_buffer_object *bo) +{ + int ret = ttm_bo_reserve(bo, false, true, NULL); + BUG_ON(ret != 0); + ttm_bo_unpin(bo); + ttm_bo_unreserve(bo); +} + + /* * vmw_setup_otable_base - Issue an object table base setup command to * the device @@ -277,6 +287,7 @@ out_no_setup: &batch->otables[i]); } + vmw_bo_unpin_unlocked(batch->otable_bo); ttm_bo_put(batch->otable_bo); batch->otable_bo = NULL; return ret; @@ -340,6 +351,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv, BUG_ON(ret != 0); vmw_bo_fence_single(bo, NULL); + ttm_bo_unpin(bo); ttm_bo_unreserve(bo); ttm_bo_put(batch->otable_bo); @@ -528,6 +540,7 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, void vmw_mob_destroy(struct vmw_mob *mob) { if (mob->pt_bo) { + vmw_bo_unpin_unlocked(mob->pt_bo); ttm_bo_put(mob->pt_bo); mob->pt_bo = NULL; } @@ -643,6 +656,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv, out_no_cmd_space: vmw_fifo_resource_dec(dev_priv); if (pt_set_up) { + vmw_bo_unpin_unlocked(mob->pt_bo); ttm_bo_put(mob->pt_bo); mob->pt_bo = NULL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 0a900afc66ff..45c9c6a7f1d6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -500,8 +500,6 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, vm_fault_t ret; pgoff_t fault_page_size; bool write = vmf->flags & FAULT_FLAG_WRITE; - bool is_cow_mapping = - (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; switch (pe_size) { case PE_SIZE_PMD: @@ -518,7 +516,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, } /* Always do write dirty-tracking and COW on PTE level. */ - if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping)) + if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping(vma->vm_flags))) return VM_FAULT_FALLBACK; ret = ttm_bo_vm_reserve(bo, vmf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index 3c03b1746661..cb9975889e2f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -49,7 +49,7 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_ops = &vmw_vm_ops; /* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */ - if ((vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) != VM_MAYWRITE) + if (!is_cow_mapping(vma->vm_flags)) vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP; return 0; diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 30d9adf31c84..9f14d99c763c 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -521,7 +521,7 @@ static int xen_drm_drv_init(struct xen_drm_front_info *front_info) drm_dev = drm_dev_alloc(&xen_drm_driver, dev); if (IS_ERR(drm_dev)) { ret = PTR_ERR(drm_dev); - goto fail; + goto fail_dev; } drm_info->drm_dev = drm_dev; @@ -551,8 +551,10 @@ fail_modeset: drm_kms_helper_poll_fini(drm_dev); drm_mode_config_cleanup(drm_dev); drm_dev_put(drm_dev); -fail: +fail_dev: kfree(drm_info); + front_info->drm_info = NULL; +fail: return ret; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h index 3adacba9a23b..e5f4314899ee 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_conn.h +++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h @@ -16,7 +16,6 @@ struct drm_connector; struct xen_drm_front_drm_info; -struct xen_drm_front_drm_info; int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info, struct drm_connector *connector); diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 347fb962b6c9..68a766ff0e9d 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -705,8 +705,9 @@ void host1x_driver_unregister(struct host1x_driver *driver) EXPORT_SYMBOL(host1x_driver_unregister); /** - * host1x_client_register() - register a host1x client + * __host1x_client_register() - register a host1x client * @client: host1x client + * @key: lock class key for the client-specific mutex * * Registers a host1x client with each host1x controller instance. Note that * each client will only match their parent host1x controller and will only be @@ -715,13 +716,14 @@ EXPORT_SYMBOL(host1x_driver_unregister); * device and call host1x_device_init(), which will in turn call each client's * &host1x_client_ops.init implementation. */ -int host1x_client_register(struct host1x_client *client) +int __host1x_client_register(struct host1x_client *client, + struct lock_class_key *key) { struct host1x *host1x; int err; INIT_LIST_HEAD(&client->list); - mutex_init(&client->lock); + __mutex_init(&client->lock, "host1x client lock", key); client->usecount = 0; mutex_lock(&devices_lock); @@ -742,7 +744,7 @@ int host1x_client_register(struct host1x_client *client) return 0; } -EXPORT_SYMBOL(host1x_client_register); +EXPORT_SYMBOL(__host1x_client_register); /** * host1x_client_unregister() - unregister a host1x client |