diff options
author | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2024-09-17 19:49:44 -0400 |
---|---|---|
committer | Rodrigo Vivi <rodrigo.vivi@intel.com> | 2024-09-17 19:49:44 -0400 |
commit | 089726a48f6f9ca2ff05e929ee238fcd49199090 (patch) | |
tree | 76f329112a99b835762a1d4ac12eca10a00b6e8e | |
parent | 1926272ee33ecea7ed1c5c92b4bd7910bfdfafbd (diff) |
2024y-09m-17d-23h-48m-33s UTC: drm-tip rerere cache update
git version 2.46.0
5 files changed, 2725 insertions, 2942 deletions
diff --git a/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/postimage b/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/postimage new file mode 100644 index 000000000000..2b39878cf670 --- /dev/null +++ b/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/postimage @@ -0,0 +1,471 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2023 Intel Corporation + */ + +#include "xe_display.h" +#include "regs/xe_regs.h" + +#include <linux/fb.h> + +#include <drm/drm_drv.h> +#include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> +#include <uapi/drm/xe_drm.h> + +#include "soc/intel_dram.h" +#include "i915_drv.h" /* FIXME: HAS_DISPLAY() depends on this */ +#include "intel_acpi.h" +#include "intel_audio.h" +#include "intel_bw.h" +#include "intel_display.h" +#include "intel_display_driver.h" +#include "intel_display_irq.h" +#include "intel_display_types.h" +#include "intel_dmc.h" +#include "intel_dp.h" +#include "intel_encoder.h" +#include "intel_fbdev.h" +#include "intel_hdcp.h" +#include "intel_hotplug.h" +#include "intel_opregion.h" +#include "xe_module.h" + +/* Xe device functions */ + +static bool has_display(struct xe_device *xe) +{ + return HAS_DISPLAY(xe); +} + +/** + * xe_display_driver_probe_defer - Detect if we need to wait for other drivers + * early on + * @pdev: PCI device + * + * Returns: true if probe needs to be deferred, false otherwise + */ +bool xe_display_driver_probe_defer(struct pci_dev *pdev) +{ + if (!xe_modparam.probe_display) + return 0; + + return intel_display_driver_probe_defer(pdev); +} + +/** + * xe_display_driver_set_hooks - Add driver flags and hooks for display + * @driver: DRM device driver + * + * Set features and function hooks in @driver that are needed for driving the + * display IP. This sets the driver's capability of driving display, regardless + * if the device has it enabled + */ +void xe_display_driver_set_hooks(struct drm_driver *driver) +{ + if (!xe_modparam.probe_display) + return; + + driver->driver_features |= DRIVER_MODESET | DRIVER_ATOMIC; +} + +static void unset_display_features(struct xe_device *xe) +{ + xe->drm.driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); +} + +static void display_destroy(struct drm_device *dev, void *dummy) +{ + struct xe_device *xe = to_xe_device(dev); + + destroy_workqueue(xe->display.hotplug.dp_wq); +} + +/** + * xe_display_create - create display struct + * @xe: XE device instance + * + * Initialize all fields used by the display part. + * + * TODO: once everything can be inside a single struct, make the struct opaque + * to the rest of xe and return it to be xe->display. + * + * Returns: 0 on success + */ +int xe_display_create(struct xe_device *xe) +{ + spin_lock_init(&xe->display.fb_tracking.lock); + + xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); + + return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); +} + +static void xe_display_fini_nommio(struct drm_device *dev, void *dummy) +{ + struct xe_device *xe = to_xe_device(dev); + + if (!xe->info.probe_display) + return; + + intel_power_domains_cleanup(xe); +} + +int xe_display_init_nommio(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return 0; + + /* Fake uncore lock */ + spin_lock_init(&xe->uncore.lock); + + /* This must be called before any calls to HAS_PCH_* */ + intel_detect_pch(xe); + + return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe); +} + +static void xe_display_fini_noirq(void *arg) +{ + struct xe_device *xe = arg; + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + intel_display_driver_remove_noirq(xe); + intel_opregion_cleanup(display); +} + +int xe_display_init_noirq(struct xe_device *xe) +{ + struct intel_display *display = &xe->display; + int err; + + if (!xe->info.probe_display) + return 0; + + intel_display_driver_early_probe(xe); + + /* Early display init.. */ + intel_opregion_setup(display); + + /* + * Fill the dram structure to get the system dram info. This will be + * used for memory latency calculation. + */ + intel_dram_detect(xe); + + intel_bw_init_hw(xe); + + intel_display_device_info_runtime_init(xe); + + err = intel_display_driver_probe_noirq(xe); + if (err) { + intel_opregion_cleanup(display); + return err; + } + + return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe); +} + +static void xe_display_fini_noaccel(void *arg) +{ + struct xe_device *xe = arg; + + if (!xe->info.probe_display) + return; + + intel_display_driver_remove_nogem(xe); +} + +int xe_display_init_noaccel(struct xe_device *xe) +{ + int err; + + if (!xe->info.probe_display) + return 0; + + err = intel_display_driver_probe_nogem(xe); + if (err) + return err; + + return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noaccel, xe); +} + +int xe_display_init(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return 0; + + return intel_display_driver_probe(xe); +} + +void xe_display_fini(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_hpd_poll_fini(xe); + + intel_hdcp_component_fini(xe); + intel_audio_deinit(xe); +} + +void xe_display_register(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_register(xe); + intel_register_dsm_handler(); + intel_power_domains_enable(xe); +} + +void xe_display_unregister(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_unregister_dsm_handler(); + intel_power_domains_disable(xe); + intel_display_driver_unregister(xe); +} + +void xe_display_driver_remove(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_remove(xe); +} + +/* IRQ-related functions */ + +void xe_display_irq_handler(struct xe_device *xe, u32 master_ctl) +{ + if (!xe->info.probe_display) + return; + + if (master_ctl & DISPLAY_IRQ) + gen11_display_irq_handler(xe); +} + +void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir) +{ + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + if (gu_misc_iir & GU_MISC_GSE) + intel_opregion_asle_intr(display); +} + +void xe_display_irq_reset(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + gen11_display_irq_reset(xe); +} + +void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) +{ + if (!xe->info.probe_display) + return; + + if (gt->info.id == XE_GT0) + gen11_de_irq_postinstall(xe); +} + +static bool suspend_to_idle(void) +{ +#if IS_ENABLED(CONFIG_ACPI_SLEEP) + if (acpi_target_system_state() < ACPI_STATE_S3) + return true; +#endif + return false; +} + +static void xe_display_flush_cleanup_work(struct xe_device *xe) +{ + struct intel_crtc *crtc; + + for_each_intel_crtc(&xe->drm, crtc) { + struct drm_crtc_commit *commit; + + spin_lock(&crtc->base.commit_lock); + commit = list_first_entry_or_null(&crtc->base.commit_list, + struct drm_crtc_commit, commit_entry); + if (commit) + drm_crtc_commit_get(commit); + spin_unlock(&crtc->base.commit_lock); + + if (commit) { + wait_for_completion(&commit->cleanup_done); + drm_crtc_commit_put(commit); + } + } +} + +/* TODO: System and runtime suspend/resume sequences will be sanitized as a follow-up. */ +static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) +{ + struct intel_display *display = &xe->display; + bool s2idle = suspend_to_idle(); + if (!xe->info.probe_display) + return; + + /* + * We do a lot of poking in a lot of registers, make sure they work + * properly. + */ + intel_power_domains_disable(xe); + if (!runtime) + intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + + if (!runtime && has_display(xe)) { + drm_kms_helper_poll_disable(&xe->drm); + intel_display_driver_disable_user_access(xe); + intel_display_driver_suspend(xe); + } + + xe_display_flush_cleanup_work(xe); + + intel_hpd_cancel_work(xe); + + if (!runtime && has_display(xe)) { + intel_display_driver_suspend_access(xe); + intel_encoder_suspend_all(&xe->display); + } + + intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold); + + intel_dmc_suspend(display); +} + +void xe_display_pm_suspend(struct xe_device *xe) +{ + __xe_display_pm_suspend(xe, false); +} + +void xe_display_pm_shutdown(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown(xe); +} + +void xe_display_pm_shutdown_noirq(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown_noirq(xe); +} + +void xe_display_pm_shutdown_noaccel(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown_nogem(xe); +} + +void xe_display_pm_runtime_suspend(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + if (xe->d3cold.allowed) + __xe_display_pm_suspend(xe, true); + + intel_hpd_poll_enable(xe); +} + +void xe_display_pm_suspend_late(struct xe_device *xe) +{ + bool s2idle = suspend_to_idle(); + if (!xe->info.probe_display) + return; + + intel_power_domains_suspend(xe, s2idle); + + intel_display_power_suspend_late(xe); +} + +void xe_display_pm_resume_early(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_power_resume_early(xe); + + intel_power_domains_resume(xe); +} + +static void __xe_display_pm_resume(struct xe_device *xe, bool runtime) +{ + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + intel_dmc_resume(display); + + if (has_display(xe)) + drm_mode_config_reset(&xe->drm); + + intel_display_driver_init_hw(xe); + + if (!runtime) + intel_display_driver_resume(xe); +} + +void xe_display_pm_resume(struct xe_device *xe) +{ + __xe_display_pm_resume(xe, false); +} + +void xe_display_pm_runtime_resume(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_hpd_poll_disable(xe); + + if (xe->d3cold.allowed) + __xe_display_pm_resume(xe, true); +} + + +static void display_device_remove(struct drm_device *dev, void *arg) +{ + struct xe_device *xe = arg; + + intel_display_device_remove(xe); +} + +int xe_display_probe(struct xe_device *xe) +{ + int err; + + if (!xe->info.probe_display) + goto no_display; + + intel_display_device_probe(xe); + + err = drmm_add_action_or_reset(&xe->drm, display_device_remove, xe); + if (err) + return err; + + if (has_display(xe)) + return 0; + +no_display: + xe->info.probe_display = false; + unset_display_features(xe); + return 0; +} diff --git a/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/preimage b/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/preimage new file mode 100644 index 000000000000..eaa3494d8d4d --- /dev/null +++ b/rr-cache/81579c8fec2fc49e618dd2283303b5d58dbd9033/preimage @@ -0,0 +1,488 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2023 Intel Corporation + */ + +#include "xe_display.h" +#include "regs/xe_regs.h" + +#include <linux/fb.h> + +#include <drm/drm_drv.h> +#include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> +#include <uapi/drm/xe_drm.h> + +#include "soc/intel_dram.h" +#include "i915_drv.h" /* FIXME: HAS_DISPLAY() depends on this */ +#include "intel_acpi.h" +#include "intel_audio.h" +#include "intel_bw.h" +#include "intel_display.h" +#include "intel_display_driver.h" +#include "intel_display_irq.h" +#include "intel_display_types.h" +#include "intel_dmc.h" +#include "intel_dp.h" +#include "intel_encoder.h" +#include "intel_fbdev.h" +#include "intel_hdcp.h" +#include "intel_hotplug.h" +#include "intel_opregion.h" +#include "xe_module.h" + +/* Xe device functions */ + +static bool has_display(struct xe_device *xe) +{ + return HAS_DISPLAY(xe); +} + +/** + * xe_display_driver_probe_defer - Detect if we need to wait for other drivers + * early on + * @pdev: PCI device + * + * Returns: true if probe needs to be deferred, false otherwise + */ +bool xe_display_driver_probe_defer(struct pci_dev *pdev) +{ + if (!xe_modparam.probe_display) + return 0; + + return intel_display_driver_probe_defer(pdev); +} + +/** + * xe_display_driver_set_hooks - Add driver flags and hooks for display + * @driver: DRM device driver + * + * Set features and function hooks in @driver that are needed for driving the + * display IP. This sets the driver's capability of driving display, regardless + * if the device has it enabled + */ +void xe_display_driver_set_hooks(struct drm_driver *driver) +{ + if (!xe_modparam.probe_display) + return; + + driver->driver_features |= DRIVER_MODESET | DRIVER_ATOMIC; +} + +static void unset_display_features(struct xe_device *xe) +{ + xe->drm.driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); +} + +static void display_destroy(struct drm_device *dev, void *dummy) +{ + struct xe_device *xe = to_xe_device(dev); + + destroy_workqueue(xe->display.hotplug.dp_wq); +} + +/** + * xe_display_create - create display struct + * @xe: XE device instance + * + * Initialize all fields used by the display part. + * + * TODO: once everything can be inside a single struct, make the struct opaque + * to the rest of xe and return it to be xe->display. + * + * Returns: 0 on success + */ +int xe_display_create(struct xe_device *xe) +{ + spin_lock_init(&xe->display.fb_tracking.lock); + + xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); + + return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); +} + +static void xe_display_fini_nommio(struct drm_device *dev, void *dummy) +{ + struct xe_device *xe = to_xe_device(dev); + + if (!xe->info.probe_display) + return; + + intel_power_domains_cleanup(xe); +} + +int xe_display_init_nommio(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return 0; + + /* Fake uncore lock */ + spin_lock_init(&xe->uncore.lock); + + /* This must be called before any calls to HAS_PCH_* */ + intel_detect_pch(xe); + + return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe); +} + +static void xe_display_fini_noirq(void *arg) +{ + struct xe_device *xe = arg; + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + intel_display_driver_remove_noirq(xe); + intel_opregion_cleanup(display); +} + +int xe_display_init_noirq(struct xe_device *xe) +{ + struct intel_display *display = &xe->display; + int err; + + if (!xe->info.probe_display) + return 0; + + intel_display_driver_early_probe(xe); + + /* Early display init.. */ + intel_opregion_setup(display); + + /* + * Fill the dram structure to get the system dram info. This will be + * used for memory latency calculation. + */ + intel_dram_detect(xe); + + intel_bw_init_hw(xe); + + intel_display_device_info_runtime_init(xe); + + err = intel_display_driver_probe_noirq(xe); + if (err) { + intel_opregion_cleanup(display); + return err; + } + + return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe); +} + +static void xe_display_fini_noaccel(void *arg) +{ + struct xe_device *xe = arg; + + if (!xe->info.probe_display) + return; + + intel_display_driver_remove_nogem(xe); +} + +int xe_display_init_noaccel(struct xe_device *xe) +{ + int err; + + if (!xe->info.probe_display) + return 0; + + err = intel_display_driver_probe_nogem(xe); + if (err) + return err; + + return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noaccel, xe); +} + +int xe_display_init(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return 0; + + return intel_display_driver_probe(xe); +} + +void xe_display_fini(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_hpd_poll_fini(xe); + + intel_hdcp_component_fini(xe); + intel_audio_deinit(xe); +} + +void xe_display_register(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_register(xe); + intel_register_dsm_handler(); + intel_power_domains_enable(xe); +} + +void xe_display_unregister(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_unregister_dsm_handler(); + intel_power_domains_disable(xe); + intel_display_driver_unregister(xe); +} + +void xe_display_driver_remove(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_remove(xe); +} + +/* IRQ-related functions */ + +void xe_display_irq_handler(struct xe_device *xe, u32 master_ctl) +{ + if (!xe->info.probe_display) + return; + + if (master_ctl & DISPLAY_IRQ) + gen11_display_irq_handler(xe); +} + +void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir) +{ + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + if (gu_misc_iir & GU_MISC_GSE) + intel_opregion_asle_intr(display); +} + +void xe_display_irq_reset(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + gen11_display_irq_reset(xe); +} + +void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) +{ + if (!xe->info.probe_display) + return; + + if (gt->info.id == XE_GT0) + gen11_de_irq_postinstall(xe); +} + +static bool suspend_to_idle(void) +{ +#if IS_ENABLED(CONFIG_ACPI_SLEEP) + if (acpi_target_system_state() < ACPI_STATE_S3) + return true; +#endif + return false; +} + +static void xe_display_flush_cleanup_work(struct xe_device *xe) +{ + struct intel_crtc *crtc; + + for_each_intel_crtc(&xe->drm, crtc) { + struct drm_crtc_commit *commit; + + spin_lock(&crtc->base.commit_lock); + commit = list_first_entry_or_null(&crtc->base.commit_list, + struct drm_crtc_commit, commit_entry); + if (commit) + drm_crtc_commit_get(commit); + spin_unlock(&crtc->base.commit_lock); + + if (commit) { + wait_for_completion(&commit->cleanup_done); + drm_crtc_commit_put(commit); + } + } +} + +/* TODO: System and runtime suspend/resume sequences will be sanitized as a follow-up. */ +static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) +{ + struct intel_display *display = &xe->display; + bool s2idle = suspend_to_idle(); + if (!xe->info.probe_display) + return; + + /* + * We do a lot of poking in a lot of registers, make sure they work + * properly. + */ + intel_power_domains_disable(xe); + if (!runtime) + intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_SUSPENDED, true); + + if (!runtime && has_display(xe)) { + drm_kms_helper_poll_disable(&xe->drm); + intel_display_driver_disable_user_access(xe); + intel_display_driver_suspend(xe); + } + + xe_display_flush_cleanup_work(xe); + + intel_hpd_cancel_work(xe); + + if (!runtime && has_display(xe)) { + intel_display_driver_suspend_access(xe); + intel_encoder_suspend_all(&xe->display); + } + + intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold); + + intel_dmc_suspend(display); +} + +void xe_display_pm_suspend(struct xe_device *xe) +{ + __xe_display_pm_suspend(xe, false); +} + +void xe_display_pm_shutdown(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown(xe); +} + +void xe_display_pm_shutdown_noirq(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown_noirq(xe); +} + +void xe_display_pm_shutdown_noaccel(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_driver_shutdown_nogem(xe); +} + +void xe_display_pm_runtime_suspend(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + if (xe->d3cold.allowed) + __xe_display_pm_suspend(xe, true); + + intel_hpd_poll_enable(xe); +} + +void xe_display_pm_suspend_late(struct xe_device *xe) +{ + bool s2idle = suspend_to_idle(); + if (!xe->info.probe_display) + return; + + intel_power_domains_suspend(xe, s2idle); + + intel_display_power_suspend_late(xe); +} + +void xe_display_pm_resume_early(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_display_power_resume_early(xe); + + intel_power_domains_resume(xe); +} + +static void __xe_display_pm_resume(struct xe_device *xe, bool runtime) +{ + struct intel_display *display = &xe->display; + + if (!xe->info.probe_display) + return; + + intel_dmc_resume(display); + + if (has_display(xe)) + drm_mode_config_reset(&xe->drm); + + intel_display_driver_init_hw(xe); +<<<<<<< +======= + + if (!runtime && has_display(xe)) + intel_display_driver_resume_access(xe); + + intel_hpd_init(xe); + + if (!runtime && has_display(xe)) { + intel_display_driver_resume(xe); + drm_kms_helper_poll_enable(&xe->drm); + intel_display_driver_enable_user_access(xe); + intel_hpd_poll_disable(xe); + } + + intel_opregion_resume(display); +>>>>>>> + + if (!runtime) + intel_display_driver_resume(xe); +} + +void xe_display_pm_resume(struct xe_device *xe) +{ + __xe_display_pm_resume(xe, false); +} + +void xe_display_pm_runtime_resume(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + intel_hpd_poll_disable(xe); + + if (xe->d3cold.allowed) + __xe_display_pm_resume(xe, true); +} + + +static void display_device_remove(struct drm_device *dev, void *arg) +{ + struct xe_device *xe = arg; + + intel_display_device_remove(xe); +} + +int xe_display_probe(struct xe_device *xe) +{ + int err; + + if (!xe->info.probe_display) + goto no_display; + + intel_display_device_probe(xe); + + err = drmm_add_action_or_reset(&xe->drm, display_device_remove, xe); + if (err) + return err; + + if (has_display(xe)) + return 0; + +no_display: + xe->info.probe_display = false; + unset_display_features(xe); + return 0; +} diff --git a/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/postimage b/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/postimage deleted file mode 100644 index d607aa9c4ec2..000000000000 --- a/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/postimage +++ /dev/null @@ -1,1395 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2014-2018 Broadcom - * Copyright (C) 2023 Raspberry Pi - */ - -#include <drm/drm_syncobj.h> - -#include "v3d_drv.h" -#include "v3d_regs.h" -#include "v3d_trace.h" - -/* Takes the reservation lock on all the BOs being referenced, so that - * at queue submit time we can update the reservations. - * - * We don't lock the RCL the tile alloc/state BOs, or overflow memory - * (all of which are on exec->unref_list). They're entirely private - * to v3d, so we don't attach dma-buf fences to them. - */ -static int -v3d_lock_bo_reservations(struct v3d_job *job, - struct ww_acquire_ctx *acquire_ctx) -{ - int i, ret; - - ret = drm_gem_lock_reservations(job->bo, job->bo_count, acquire_ctx); - if (ret) - return ret; - - for (i = 0; i < job->bo_count; i++) { - ret = dma_resv_reserve_fences(job->bo[i]->resv, 1); - if (ret) - goto fail; - - ret = drm_sched_job_add_implicit_dependencies(&job->base, - job->bo[i], true); - if (ret) - goto fail; - } - - return 0; - -fail: - drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); - return ret; -} - -/** - * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects - * referenced by the job. - * @dev: DRM device - * @file_priv: DRM file for this fd - * @job: V3D job being set up - * @bo_handles: GEM handles - * @bo_count: Number of GEM handles passed in - * - * The command validator needs to reference BOs by their index within - * the submitted job's BO list. This does the validation of the job's - * BO list and reference counting for the lifetime of the job. - * - * Note that this function doesn't need to unreference the BOs on - * failure, because that will happen at v3d_exec_cleanup() time. - */ -static int -v3d_lookup_bos(struct drm_device *dev, - struct drm_file *file_priv, - struct v3d_job *job, - u64 bo_handles, - u32 bo_count) -{ - job->bo_count = bo_count; - - if (!job->bo_count) { - /* See comment on bo_index for why we have to check - * this. - */ - DRM_DEBUG("Rendering requires BOs\n"); - return -EINVAL; - } - - return drm_gem_objects_lookup(file_priv, - (void __user *)(uintptr_t)bo_handles, - job->bo_count, &job->bo); -} - -static void -v3d_job_free(struct kref *ref) -{ - struct v3d_job *job = container_of(ref, struct v3d_job, refcount); - int i; - - if (job->bo) { - for (i = 0; i < job->bo_count; i++) - drm_gem_object_put(job->bo[i]); - kvfree(job->bo); - } - - dma_fence_put(job->irq_fence); - dma_fence_put(job->done_fence); - - if (job->perfmon) - v3d_perfmon_put(job->perfmon); - - kfree(job); -} - -static void -v3d_render_job_free(struct kref *ref) -{ - struct v3d_render_job *job = container_of(ref, struct v3d_render_job, - base.refcount); - struct v3d_bo *bo, *save; - - list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) { - drm_gem_object_put(&bo->base.base); - } - - v3d_job_free(ref); -} - -void v3d_job_cleanup(struct v3d_job *job) -{ - if (!job) - return; - - drm_sched_job_cleanup(&job->base); - v3d_job_put(job); -} - -void v3d_job_put(struct v3d_job *job) -{ - if (!job) - return; - - kref_put(&job->refcount, job->free); -} - -static int -v3d_job_allocate(void **container, size_t size) -{ - *container = kcalloc(1, size, GFP_KERNEL); - if (!*container) { - DRM_ERROR("Cannot allocate memory for V3D job.\n"); - return -ENOMEM; - } - - return 0; -} - -static void -v3d_job_deallocate(void **container) -{ - kfree(*container); - *container = NULL; -} - -static int -v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, - struct v3d_job *job, void (*free)(struct kref *ref), - u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue) -{ - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); - int ret, i; - - job->v3d = v3d; - job->free = free; - job->file = file_priv; - - ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue], - 1, v3d_priv); - if (ret) - return ret; - - if (has_multisync) { - if (se->in_sync_count && se->wait_stage == queue) { - struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs); - - for (i = 0; i < se->in_sync_count; i++) { - struct drm_v3d_sem in; - - if (copy_from_user(&in, handle++, sizeof(in))) { - ret = -EFAULT; - DRM_DEBUG("Failed to copy wait dep handle.\n"); - goto fail_deps; - } - ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in.handle, 0); - - // TODO: Investigate why this was filtered out for the IOCTL. - if (ret && ret != -ENOENT) - goto fail_deps; - } - } - } else { - ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in_sync, 0); - - // TODO: Investigate why this was filtered out for the IOCTL. - if (ret && ret != -ENOENT) - goto fail_deps; - } - - kref_init(&job->refcount); - - return 0; - -fail_deps: - drm_sched_job_cleanup(&job->base); - return ret; -} - -static void -v3d_push_job(struct v3d_job *job) -{ - drm_sched_job_arm(&job->base); - - job->done_fence = dma_fence_get(&job->base.s_fence->finished); - - /* put by scheduler job completion */ - kref_get(&job->refcount); - - drm_sched_entity_push_job(&job->base); -} - -static void -v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, - struct v3d_job *job, - struct ww_acquire_ctx *acquire_ctx, - u32 out_sync, - struct v3d_submit_ext *se, - struct dma_fence *done_fence) -{ - struct drm_syncobj *sync_out; - bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); - int i; - - for (i = 0; i < job->bo_count; i++) { - /* XXX: Use shared fences for read-only objects. */ - dma_resv_add_fence(job->bo[i]->resv, job->done_fence, - DMA_RESV_USAGE_WRITE); - } - - drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); - - /* Update the return sync object for the job */ - /* If it only supports a single signal semaphore*/ - if (!has_multisync) { - sync_out = drm_syncobj_find(file_priv, out_sync); - if (sync_out) { - drm_syncobj_replace_fence(sync_out, done_fence); - drm_syncobj_put(sync_out); - } - return; - } - - /* If multiple semaphores extension is supported */ - if (se->out_sync_count) { - for (i = 0; i < se->out_sync_count; i++) { - drm_syncobj_replace_fence(se->out_syncs[i].syncobj, - done_fence); - drm_syncobj_put(se->out_syncs[i].syncobj); - } - kvfree(se->out_syncs); - } -} - -static int -v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv, - struct v3d_dev *v3d, - struct drm_v3d_submit_csd *args, - struct v3d_csd_job **job, - struct v3d_job **clean_job, - struct v3d_submit_ext *se, - struct ww_acquire_ctx *acquire_ctx) -{ - int ret; - - ret = v3d_job_allocate((void *)job, sizeof(**job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &(*job)->base, - v3d_job_free, args->in_sync, se, V3D_CSD); - if (ret) { - v3d_job_deallocate((void *)job); - return ret; - } - - ret = v3d_job_allocate((void *)clean_job, sizeof(**clean_job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, *clean_job, - v3d_job_free, 0, NULL, V3D_CACHE_CLEAN); - if (ret) { - v3d_job_deallocate((void *)clean_job); - return ret; - } - - (*job)->args = *args; - - ret = v3d_lookup_bos(&v3d->drm, file_priv, *clean_job, - args->bo_handles, args->bo_handle_count); - if (ret) - return ret; - - return v3d_lock_bo_reservations(*clean_job, acquire_ctx); -} - -static void -v3d_put_multisync_post_deps(struct v3d_submit_ext *se) -{ - unsigned int i; - - if (!(se && se->out_sync_count)) - return; - - for (i = 0; i < se->out_sync_count; i++) - drm_syncobj_put(se->out_syncs[i].syncobj); - kvfree(se->out_syncs); -} - -static int -v3d_get_multisync_post_deps(struct drm_file *file_priv, - struct v3d_submit_ext *se, - u32 count, u64 handles) -{ - struct drm_v3d_sem __user *post_deps; - int i, ret; - - if (!count) - return 0; - - se->out_syncs = (struct v3d_submit_outsync *) - kvmalloc_array(count, - sizeof(struct v3d_submit_outsync), - GFP_KERNEL); - if (!se->out_syncs) - return -ENOMEM; - - post_deps = u64_to_user_ptr(handles); - - for (i = 0; i < count; i++) { - struct drm_v3d_sem out; - - if (copy_from_user(&out, post_deps++, sizeof(out))) { - ret = -EFAULT; - DRM_DEBUG("Failed to copy post dep handles\n"); - goto fail; - } - - se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, - out.handle); - if (!se->out_syncs[i].syncobj) { - ret = -EINVAL; - goto fail; - } - } - se->out_sync_count = count; - - return 0; - -fail: - for (i--; i >= 0; i--) - drm_syncobj_put(se->out_syncs[i].syncobj); - kvfree(se->out_syncs); - - return ret; -} - -/* Get data for multiple binary semaphores synchronization. Parse syncobj - * to be signaled when job completes (out_sync). - */ -static int -v3d_get_multisync_submit_deps(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_submit_ext *se) -{ - struct drm_v3d_multi_sync multisync; - int ret; - - if (se->in_sync_count || se->out_sync_count) { - DRM_DEBUG("Two multisync extensions were added to the same job."); - return -EINVAL; - } - - if (copy_from_user(&multisync, ext, sizeof(multisync))) - return -EFAULT; - - if (multisync.pad) - return -EINVAL; - - ret = v3d_get_multisync_post_deps(file_priv, se, multisync.out_sync_count, - multisync.out_syncs); - if (ret) - return ret; - - se->in_sync_count = multisync.in_sync_count; - se->in_syncs = multisync.in_syncs; - se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC; - se->wait_stage = multisync.wait_stage; - - return 0; -} - -/* Get data for the indirect CSD job submission. */ -static int -v3d_get_cpu_indirect_csd_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct v3d_dev *v3d = v3d_priv->v3d; - struct drm_v3d_indirect_csd indirect_csd; - struct v3d_indirect_csd_info *info = &job->indirect_csd; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&indirect_csd, ext, sizeof(indirect_csd))) - return -EFAULT; - - if (!v3d_has_csd(v3d)) { - DRM_DEBUG("Attempting CSD submit on non-CSD hardware.\n"); - return -EINVAL; - } - - job->job_type = V3D_CPU_JOB_TYPE_INDIRECT_CSD; - info->offset = indirect_csd.offset; - info->wg_size = indirect_csd.wg_size; - memcpy(&info->wg_uniform_offsets, &indirect_csd.wg_uniform_offsets, - sizeof(indirect_csd.wg_uniform_offsets)); - - info->indirect = drm_gem_object_lookup(file_priv, indirect_csd.indirect); - - return v3d_setup_csd_jobs_and_bos(file_priv, v3d, &indirect_csd.submit, - &info->job, &info->clean_job, - NULL, &info->acquire_ctx); -} - -/* Get data for the query timestamp job submission. */ -static int -v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *offsets, *syncs; - struct drm_v3d_timestamp_query timestamp; - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(×tamp, ext, sizeof(timestamp))) - return -EFAULT; - - if (timestamp.pad) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(timestamp.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - offsets = u64_to_user_ptr(timestamp.offsets); - syncs = u64_to_user_ptr(timestamp.syncs); - - for (i = 0; i < timestamp.count; i++) { - u32 offset, sync; - - if (get_user(offset, offsets++)) { - err = -EFAULT; - goto error; - } - - query_info->queries[i].offset = offset; - - if (get_user(sync, syncs++)) { - err = -EFAULT; - goto error; - } - - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { - err = -ENOENT; - goto error; - } - } - query_info->count = timestamp.count; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -} - -static int -v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *syncs; - struct drm_v3d_reset_timestamp_query reset; - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&reset, ext, sizeof(reset))) - return -EFAULT; - - job->job_type = V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(reset.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - syncs = u64_to_user_ptr(reset.syncs); - - for (i = 0; i < reset.count; i++) { - u32 sync; - - query_info->queries[i].offset = reset.offset + 8 * i; - - if (get_user(sync, syncs++)) { - err = -EFAULT; - goto error; - } - - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { - err = -ENOENT; - goto error; - } - } - query_info->count = reset.count; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -} - -/* Get data for the copy timestamp query results job submission. */ -static int -v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *offsets, *syncs; - struct drm_v3d_copy_timestamp_query copy; - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(©, ext, sizeof(copy))) - return -EFAULT; - - if (copy.pad) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(copy.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - offsets = u64_to_user_ptr(copy.offsets); - syncs = u64_to_user_ptr(copy.syncs); - - for (i = 0; i < copy.count; i++) { - u32 offset, sync; - - if (get_user(offset, offsets++)) { - err = -EFAULT; - goto error; - } - - query_info->queries[i].offset = offset; - - if (get_user(sync, syncs++)) { - err = -EFAULT; - goto error; - } - - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { - err = -ENOENT; - goto error; - } - } - query_info->count = copy.count; - - job->copy.do_64bit = copy.do_64bit; - job->copy.do_partial = copy.do_partial; - job->copy.availability_bit = copy.availability_bit; - job->copy.offset = copy.offset; - job->copy.stride = copy.stride; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -} - -static int -v3d_copy_query_info(struct v3d_performance_query_info *query_info, - unsigned int count, - unsigned int nperfmons, - u32 __user *syncs, - u64 __user *kperfmon_ids, - struct drm_file *file_priv) -{ - unsigned int i, j; - int err; - - for (i = 0; i < count; i++) { - struct v3d_performance_query *query = &query_info->queries[i]; - u32 __user *ids_pointer; - u32 sync, id; - u64 ids; - - if (get_user(sync, syncs++)) { - err = -EFAULT; - goto error; - } - - if (get_user(ids, kperfmon_ids++)) { - err = -EFAULT; - goto error; - } - - query->kperfmon_ids = - kvmalloc_array(nperfmons, - sizeof(struct v3d_performance_query *), - GFP_KERNEL); - if (!query->kperfmon_ids) { - err = -ENOMEM; - goto error; - } - - ids_pointer = u64_to_user_ptr(ids); - - for (j = 0; j < nperfmons; j++) { - if (get_user(id, ids_pointer++)) { - kvfree(query->kperfmon_ids); - err = -EFAULT; - goto error; - } - - query->kperfmon_ids[j] = id; - } - - query->syncobj = drm_syncobj_find(file_priv, sync); - if (!query->syncobj) { - kvfree(query->kperfmon_ids); - err = -ENOENT; - goto error; - } - } - - return 0; - -error: - v3d_performance_query_info_free(query_info, i); - return err; -} - -static int -v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_performance_query_info *query_info = &job->performance_query; - struct drm_v3d_reset_performance_query reset; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&reset, ext, sizeof(reset))) - return -EFAULT; - - job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY; - - query_info->queries = - kvmalloc_array(reset.count, - sizeof(struct v3d_performance_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - err = v3d_copy_query_info(query_info, - reset.count, - reset.nperfmons, - u64_to_user_ptr(reset.syncs), - u64_to_user_ptr(reset.kperfmon_ids), - file_priv); - if (err) - return err; - - query_info->count = reset.count; - query_info->nperfmons = reset.nperfmons; - - return 0; -} - -static int -v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_performance_query_info *query_info = &job->performance_query; - struct drm_v3d_copy_performance_query copy; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(©, ext, sizeof(copy))) - return -EFAULT; - - if (copy.pad) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY; - - query_info->queries = - kvmalloc_array(copy.count, - sizeof(struct v3d_performance_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - err = v3d_copy_query_info(query_info, - copy.count, - copy.nperfmons, - u64_to_user_ptr(copy.syncs), - u64_to_user_ptr(copy.kperfmon_ids), - file_priv); - if (err) - return err; - - query_info->count = copy.count; - query_info->nperfmons = copy.nperfmons; - query_info->ncounters = copy.ncounters; - - job->copy.do_64bit = copy.do_64bit; - job->copy.do_partial = copy.do_partial; - job->copy.availability_bit = copy.availability_bit; - job->copy.offset = copy.offset; - job->copy.stride = copy.stride; - - return 0; -} - -/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data - * according to the extension id (name). - */ -static int -v3d_get_extensions(struct drm_file *file_priv, - u64 ext_handles, - struct v3d_submit_ext *se, - struct v3d_cpu_job *job) -{ - struct drm_v3d_extension __user *user_ext; - int ret; - - user_ext = u64_to_user_ptr(ext_handles); - while (user_ext) { - struct drm_v3d_extension ext; - - if (copy_from_user(&ext, user_ext, sizeof(ext))) { - DRM_DEBUG("Failed to copy submit extension\n"); - return -EFAULT; - } - - switch (ext.id) { - case DRM_V3D_EXT_ID_MULTI_SYNC: - ret = v3d_get_multisync_submit_deps(file_priv, user_ext, se); - break; - case DRM_V3D_EXT_ID_CPU_INDIRECT_CSD: - ret = v3d_get_cpu_indirect_csd_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY: - ret = v3d_get_cpu_timestamp_query_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY: - ret = v3d_get_cpu_reset_timestamp_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY: - ret = v3d_get_cpu_copy_query_results_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY: - ret = v3d_get_cpu_reset_performance_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY: - ret = v3d_get_cpu_copy_performance_query_params(file_priv, user_ext, job); - break; - default: - DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); - return -EINVAL; - } - - if (ret) - return ret; - - user_ext = u64_to_user_ptr(ext.next); - } - - return 0; -} - -/** - * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * This is the main entrypoint for userspace to submit a 3D frame to - * the GPU. Userspace provides the binner command list (if - * applicable), and the kernel sets up the render command list to draw - * to the framebuffer described in the ioctl, using the command lists - * that the 3D engine's binner will produce. - */ -int -v3d_submit_cl_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct drm_v3d_submit_cl *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_bin_job *bin = NULL; - struct v3d_render_job *render = NULL; - struct v3d_job *clean_job = NULL; - struct v3d_job *last_job; - struct ww_acquire_ctx acquire_ctx; - int ret = 0; - - trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end); - - if (args->pad) - return -EINVAL; - - if (args->flags && - args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE | - DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_job_allocate((void *)&render, sizeof(*render)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &render->base, - v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER); - if (ret) { - v3d_job_deallocate((void *)&render); - goto fail; - } - - render->start = args->rcl_start; - render->end = args->rcl_end; - INIT_LIST_HEAD(&render->unref_list); - - if (args->bcl_start != args->bcl_end) { - ret = v3d_job_allocate((void *)&bin, sizeof(*bin)); - if (ret) - goto fail; - - ret = v3d_job_init(v3d, file_priv, &bin->base, - v3d_job_free, args->in_sync_bcl, &se, V3D_BIN); - if (ret) { - v3d_job_deallocate((void *)&bin); - goto fail; - } - - bin->start = args->bcl_start; - bin->end = args->bcl_end; - bin->qma = args->qma; - bin->qms = args->qms; - bin->qts = args->qts; - bin->render = render; - } - - if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { - ret = v3d_job_allocate((void *)&clean_job, sizeof(*clean_job)); - if (ret) - goto fail; - - ret = v3d_job_init(v3d, file_priv, clean_job, - v3d_job_free, 0, NULL, V3D_CACHE_CLEAN); - if (ret) { - v3d_job_deallocate((void *)&clean_job); - goto fail; - } - - last_job = clean_job; - } else { - last_job = &render->base; - } - - ret = v3d_lookup_bos(dev, file_priv, last_job, - args->bo_handles, args->bo_handle_count); - if (ret) - goto fail; - - ret = v3d_lock_bo_reservations(last_job, &acquire_ctx); - if (ret) - goto fail; - - if (args->perfmon_id) { - render->base.perfmon = v3d_perfmon_find(v3d_priv, - args->perfmon_id); - - if (!render->base.perfmon) { - ret = -ENOENT; - goto fail_perfmon; - } - } - - mutex_lock(&v3d->sched_lock); - if (bin) { - bin->base.perfmon = render->base.perfmon; - v3d_perfmon_get(bin->base.perfmon); - v3d_push_job(&bin->base); - - ret = drm_sched_job_add_dependency(&render->base.base, - dma_fence_get(bin->base.done_fence)); - if (ret) - goto fail_unreserve; - } - - v3d_push_job(&render->base); - - if (clean_job) { - struct dma_fence *render_fence = - dma_fence_get(render->base.done_fence); - ret = drm_sched_job_add_dependency(&clean_job->base, - render_fence); - if (ret) - goto fail_unreserve; - clean_job->perfmon = render->base.perfmon; - v3d_perfmon_get(clean_job->perfmon); - v3d_push_job(clean_job); - } - - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - last_job, - &acquire_ctx, - args->out_sync, - &se, - last_job->done_fence); - - v3d_job_put(&bin->base); - v3d_job_put(&render->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); -fail_perfmon: - drm_gem_unlock_reservations(last_job->bo, - last_job->bo_count, &acquire_ctx); -fail: - v3d_job_cleanup((void *)bin); - v3d_job_cleanup((void *)render); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -/** - * v3d_submit_tfu_ioctl() - Submits a TFU (texture formatting) job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace provides the register setup for the TFU, which we don't - * need to validate since the TFU is behind the MMU. - */ -int -v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_v3d_submit_tfu *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_tfu_job *job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret = 0; - - trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia); - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_DEBUG("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_job_allocate((void *)&job, sizeof(*job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &job->base, - v3d_job_free, args->in_sync, &se, V3D_TFU); - if (ret) { - v3d_job_deallocate((void *)&job); - goto fail; - } - - job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles), - sizeof(*job->base.bo), GFP_KERNEL); - if (!job->base.bo) { - ret = -ENOMEM; - goto fail; - } - - job->args = *args; - - for (job->base.bo_count = 0; - job->base.bo_count < ARRAY_SIZE(args->bo_handles); - job->base.bo_count++) { - struct drm_gem_object *bo; - - if (!args->bo_handles[job->base.bo_count]) - break; - - bo = drm_gem_object_lookup(file_priv, args->bo_handles[job->base.bo_count]); - if (!bo) { - DRM_DEBUG("Failed to look up GEM BO %d: %d\n", - job->base.bo_count, - args->bo_handles[job->base.bo_count]); - ret = -ENOENT; - goto fail; - } - job->base.bo[job->base.bo_count] = bo; - } - - ret = v3d_lock_bo_reservations(&job->base, &acquire_ctx); - if (ret) - goto fail; - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&job->base); - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - &job->base, &acquire_ctx, - args->out_sync, - &se, - job->base.done_fence); - - v3d_job_put(&job->base); - - return 0; - -fail: - v3d_job_cleanup((void *)job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -/** - * v3d_submit_csd_ioctl() - Submits a CSD (compute shader) job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace provides the register setup for the CSD, which we don't - * need to validate since the CSD is behind the MMU. - */ -int -v3d_submit_csd_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct drm_v3d_submit_csd *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_csd_job *job = NULL; - struct v3d_job *clean_job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret; - - trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]); - - if (args->pad) - return -EINVAL; - - if (!v3d_has_csd(v3d)) { - DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n"); - return -EINVAL; - } - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_setup_csd_jobs_and_bos(file_priv, v3d, args, - &job, &clean_job, &se, - &acquire_ctx); - if (ret) - goto fail; - - if (args->perfmon_id) { - job->base.perfmon = v3d_perfmon_find(v3d_priv, - args->perfmon_id); - if (!job->base.perfmon) { - ret = -ENOENT; - goto fail_perfmon; - } - } - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&job->base); - - ret = drm_sched_job_add_dependency(&clean_job->base, - dma_fence_get(job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(clean_job); - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - clean_job, - &acquire_ctx, - args->out_sync, - &se, - clean_job->done_fence); - - v3d_job_put(&job->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); -fail_perfmon: - drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count, - &acquire_ctx); -fail: - v3d_job_cleanup((void *)job); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -static const unsigned int cpu_job_bo_handle_count[] = { - [V3D_CPU_JOB_TYPE_INDIRECT_CSD] = 1, - [V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY] = 1, - [V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY] = 1, - [V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY] = 2, - [V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY] = 0, - [V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY] = 1, -}; - -/** - * v3d_submit_cpu_ioctl() - Submits a CPU job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace specifies the CPU job type and data required to perform its - * operations through the drm_v3d_extension struct. - */ -int -v3d_submit_cpu_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_v3d_submit_cpu *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_submit_ext *out_se = NULL; - struct v3d_cpu_job *cpu_job = NULL; - struct v3d_csd_job *csd_job = NULL; - struct v3d_job *clean_job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret; - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("Invalid flags: %d\n", args->flags); - return -EINVAL; - } - - ret = v3d_job_allocate((void *)&cpu_job, sizeof(*cpu_job)); - if (ret) - return ret; - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, cpu_job); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - goto fail; - } - } - - /* Every CPU job must have a CPU job user extension */ - if (!cpu_job->job_type) { - DRM_DEBUG("CPU job must have a CPU job user extension.\n"); - ret = -EINVAL; - goto fail; - } - - if (args->bo_handle_count != cpu_job_bo_handle_count[cpu_job->job_type]) { - DRM_DEBUG("This CPU job was not submitted with the proper number of BOs.\n"); - ret = -EINVAL; - goto fail; - } - - trace_v3d_submit_cpu_ioctl(&v3d->drm, cpu_job->job_type); - - ret = v3d_job_init(v3d, file_priv, &cpu_job->base, - v3d_job_free, 0, &se, V3D_CPU); - if (ret) { - v3d_job_deallocate((void *)&cpu_job); - goto fail; - } - - clean_job = cpu_job->indirect_csd.clean_job; - csd_job = cpu_job->indirect_csd.job; - - if (args->bo_handle_count) { - ret = v3d_lookup_bos(dev, file_priv, &cpu_job->base, - args->bo_handles, args->bo_handle_count); - if (ret) - goto fail; - - ret = v3d_lock_bo_reservations(&cpu_job->base, &acquire_ctx); - if (ret) - goto fail; - } - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&cpu_job->base); - - switch (cpu_job->job_type) { - case V3D_CPU_JOB_TYPE_INDIRECT_CSD: - ret = drm_sched_job_add_dependency(&csd_job->base.base, - dma_fence_get(cpu_job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(&csd_job->base); - - ret = drm_sched_job_add_dependency(&clean_job->base, - dma_fence_get(csd_job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(clean_job); - - break; - default: - break; - } - mutex_unlock(&v3d->sched_lock); - - out_se = (cpu_job->job_type == V3D_CPU_JOB_TYPE_INDIRECT_CSD) ? NULL : &se; - - v3d_attach_fences_and_unlock_reservation(file_priv, - &cpu_job->base, - &acquire_ctx, 0, - out_se, cpu_job->base.done_fence); - - switch (cpu_job->job_type) { - case V3D_CPU_JOB_TYPE_INDIRECT_CSD: - v3d_attach_fences_and_unlock_reservation(file_priv, - clean_job, - &cpu_job->indirect_csd.acquire_ctx, - 0, &se, clean_job->done_fence); - break; - default: - break; - } - - v3d_job_put(&cpu_job->base); - v3d_job_put(&csd_job->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); - - drm_gem_unlock_reservations(cpu_job->base.bo, cpu_job->base.bo_count, - &acquire_ctx); - - drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count, - &cpu_job->indirect_csd.acquire_ctx); - -fail: - v3d_job_cleanup((void *)cpu_job); - v3d_job_cleanup((void *)csd_job); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - kvfree(cpu_job->timestamp_query.queries); - kvfree(cpu_job->performance_query.queries); - - return ret; -} diff --git a/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/preimage b/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/preimage deleted file mode 100644 index 17370d99956c..000000000000 --- a/rr-cache/9e63314e5ad6c77e0963bc61cc788b8f74a9860b/preimage +++ /dev/null @@ -1,1547 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2014-2018 Broadcom - * Copyright (C) 2023 Raspberry Pi - */ - -#include <drm/drm_syncobj.h> - -#include "v3d_drv.h" -#include "v3d_regs.h" -#include "v3d_trace.h" - -/* Takes the reservation lock on all the BOs being referenced, so that - * at queue submit time we can update the reservations. - * - * We don't lock the RCL the tile alloc/state BOs, or overflow memory - * (all of which are on exec->unref_list). They're entirely private - * to v3d, so we don't attach dma-buf fences to them. - */ -static int -v3d_lock_bo_reservations(struct v3d_job *job, - struct ww_acquire_ctx *acquire_ctx) -{ - int i, ret; - - ret = drm_gem_lock_reservations(job->bo, job->bo_count, acquire_ctx); - if (ret) - return ret; - - for (i = 0; i < job->bo_count; i++) { - ret = dma_resv_reserve_fences(job->bo[i]->resv, 1); - if (ret) - goto fail; - - ret = drm_sched_job_add_implicit_dependencies(&job->base, - job->bo[i], true); - if (ret) - goto fail; - } - - return 0; - -fail: - drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); - return ret; -} - -/** - * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects - * referenced by the job. - * @dev: DRM device - * @file_priv: DRM file for this fd - * @job: V3D job being set up - * @bo_handles: GEM handles - * @bo_count: Number of GEM handles passed in - * - * The command validator needs to reference BOs by their index within - * the submitted job's BO list. This does the validation of the job's - * BO list and reference counting for the lifetime of the job. - * - * Note that this function doesn't need to unreference the BOs on - * failure, because that will happen at v3d_exec_cleanup() time. - */ -static int -v3d_lookup_bos(struct drm_device *dev, - struct drm_file *file_priv, - struct v3d_job *job, - u64 bo_handles, - u32 bo_count) -{ - job->bo_count = bo_count; - - if (!job->bo_count) { - /* See comment on bo_index for why we have to check - * this. - */ - DRM_DEBUG("Rendering requires BOs\n"); - return -EINVAL; - } - - return drm_gem_objects_lookup(file_priv, - (void __user *)(uintptr_t)bo_handles, - job->bo_count, &job->bo); -} - -static void -v3d_job_free(struct kref *ref) -{ - struct v3d_job *job = container_of(ref, struct v3d_job, refcount); - int i; - - if (job->bo) { - for (i = 0; i < job->bo_count; i++) - drm_gem_object_put(job->bo[i]); - kvfree(job->bo); - } - - dma_fence_put(job->irq_fence); - dma_fence_put(job->done_fence); - - if (job->perfmon) - v3d_perfmon_put(job->perfmon); - - kfree(job); -} - -static void -v3d_render_job_free(struct kref *ref) -{ - struct v3d_render_job *job = container_of(ref, struct v3d_render_job, - base.refcount); - struct v3d_bo *bo, *save; - - list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) { - drm_gem_object_put(&bo->base.base); - } - - v3d_job_free(ref); -} - -void v3d_job_cleanup(struct v3d_job *job) -{ - if (!job) - return; - - drm_sched_job_cleanup(&job->base); - v3d_job_put(job); -} - -void v3d_job_put(struct v3d_job *job) -{ - if (!job) - return; - - kref_put(&job->refcount, job->free); -} - -static int -v3d_job_allocate(void **container, size_t size) -{ - *container = kcalloc(1, size, GFP_KERNEL); - if (!*container) { - DRM_ERROR("Cannot allocate memory for V3D job.\n"); - return -ENOMEM; - } - - return 0; -} - -static void -v3d_job_deallocate(void **container) -{ - kfree(*container); - *container = NULL; -} - -static int -v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, - struct v3d_job *job, void (*free)(struct kref *ref), - u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue) -{ - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); - int ret, i; - - job->v3d = v3d; - job->free = free; - job->file = file_priv; - - ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue], - 1, v3d_priv); - if (ret) - return ret; - - if (has_multisync) { - if (se->in_sync_count && se->wait_stage == queue) { - struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs); - - for (i = 0; i < se->in_sync_count; i++) { - struct drm_v3d_sem in; - - if (copy_from_user(&in, handle++, sizeof(in))) { - ret = -EFAULT; - DRM_DEBUG("Failed to copy wait dep handle.\n"); - goto fail_deps; - } - ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in.handle, 0); - - // TODO: Investigate why this was filtered out for the IOCTL. - if (ret && ret != -ENOENT) - goto fail_deps; - } - } - } else { - ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in_sync, 0); - - // TODO: Investigate why this was filtered out for the IOCTL. - if (ret && ret != -ENOENT) - goto fail_deps; - } - - kref_init(&job->refcount); - - return 0; - -fail_deps: - drm_sched_job_cleanup(&job->base); - return ret; -} - -static void -v3d_push_job(struct v3d_job *job) -{ - drm_sched_job_arm(&job->base); - - job->done_fence = dma_fence_get(&job->base.s_fence->finished); - - /* put by scheduler job completion */ - kref_get(&job->refcount); - - drm_sched_entity_push_job(&job->base); -} - -static void -v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, - struct v3d_job *job, - struct ww_acquire_ctx *acquire_ctx, - u32 out_sync, - struct v3d_submit_ext *se, - struct dma_fence *done_fence) -{ - struct drm_syncobj *sync_out; - bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); - int i; - - for (i = 0; i < job->bo_count; i++) { - /* XXX: Use shared fences for read-only objects. */ - dma_resv_add_fence(job->bo[i]->resv, job->done_fence, - DMA_RESV_USAGE_WRITE); - } - - drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); - - /* Update the return sync object for the job */ - /* If it only supports a single signal semaphore*/ - if (!has_multisync) { - sync_out = drm_syncobj_find(file_priv, out_sync); - if (sync_out) { - drm_syncobj_replace_fence(sync_out, done_fence); - drm_syncobj_put(sync_out); - } - return; - } - - /* If multiple semaphores extension is supported */ - if (se->out_sync_count) { - for (i = 0; i < se->out_sync_count; i++) { - drm_syncobj_replace_fence(se->out_syncs[i].syncobj, - done_fence); - drm_syncobj_put(se->out_syncs[i].syncobj); - } - kvfree(se->out_syncs); - } -} - -static int -v3d_setup_csd_jobs_and_bos(struct drm_file *file_priv, - struct v3d_dev *v3d, - struct drm_v3d_submit_csd *args, - struct v3d_csd_job **job, - struct v3d_job **clean_job, - struct v3d_submit_ext *se, - struct ww_acquire_ctx *acquire_ctx) -{ - int ret; - - ret = v3d_job_allocate((void *)job, sizeof(**job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &(*job)->base, - v3d_job_free, args->in_sync, se, V3D_CSD); - if (ret) { - v3d_job_deallocate((void *)job); - return ret; - } - - ret = v3d_job_allocate((void *)clean_job, sizeof(**clean_job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, *clean_job, - v3d_job_free, 0, NULL, V3D_CACHE_CLEAN); - if (ret) { - v3d_job_deallocate((void *)clean_job); - return ret; - } - - (*job)->args = *args; - - ret = v3d_lookup_bos(&v3d->drm, file_priv, *clean_job, - args->bo_handles, args->bo_handle_count); - if (ret) - return ret; - - return v3d_lock_bo_reservations(*clean_job, acquire_ctx); -} - -static void -v3d_put_multisync_post_deps(struct v3d_submit_ext *se) -{ - unsigned int i; - - if (!(se && se->out_sync_count)) - return; - - for (i = 0; i < se->out_sync_count; i++) - drm_syncobj_put(se->out_syncs[i].syncobj); - kvfree(se->out_syncs); -} - -static int -v3d_get_multisync_post_deps(struct drm_file *file_priv, - struct v3d_submit_ext *se, - u32 count, u64 handles) -{ - struct drm_v3d_sem __user *post_deps; - int i, ret; - - if (!count) - return 0; - - se->out_syncs = (struct v3d_submit_outsync *) - kvmalloc_array(count, - sizeof(struct v3d_submit_outsync), - GFP_KERNEL); - if (!se->out_syncs) - return -ENOMEM; - - post_deps = u64_to_user_ptr(handles); - - for (i = 0; i < count; i++) { - struct drm_v3d_sem out; - - if (copy_from_user(&out, post_deps++, sizeof(out))) { - ret = -EFAULT; - DRM_DEBUG("Failed to copy post dep handles\n"); - goto fail; - } - - se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, - out.handle); - if (!se->out_syncs[i].syncobj) { - ret = -EINVAL; - goto fail; - } - } - se->out_sync_count = count; - - return 0; - -fail: - for (i--; i >= 0; i--) - drm_syncobj_put(se->out_syncs[i].syncobj); - kvfree(se->out_syncs); - - return ret; -} - -/* Get data for multiple binary semaphores synchronization. Parse syncobj - * to be signaled when job completes (out_sync). - */ -static int -v3d_get_multisync_submit_deps(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_submit_ext *se) -{ - struct drm_v3d_multi_sync multisync; - int ret; - - if (se->in_sync_count || se->out_sync_count) { - DRM_DEBUG("Two multisync extensions were added to the same job."); - return -EINVAL; - } - - if (copy_from_user(&multisync, ext, sizeof(multisync))) - return -EFAULT; - - if (multisync.pad) - return -EINVAL; - - ret = v3d_get_multisync_post_deps(file_priv, se, multisync.out_sync_count, - multisync.out_syncs); - if (ret) - return ret; - - se->in_sync_count = multisync.in_sync_count; - se->in_syncs = multisync.in_syncs; - se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC; - se->wait_stage = multisync.wait_stage; - - return 0; -} - -/* Get data for the indirect CSD job submission. */ -static int -v3d_get_cpu_indirect_csd_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct v3d_dev *v3d = v3d_priv->v3d; - struct drm_v3d_indirect_csd indirect_csd; - struct v3d_indirect_csd_info *info = &job->indirect_csd; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&indirect_csd, ext, sizeof(indirect_csd))) - return -EFAULT; - - if (!v3d_has_csd(v3d)) { - DRM_DEBUG("Attempting CSD submit on non-CSD hardware.\n"); - return -EINVAL; - } - - job->job_type = V3D_CPU_JOB_TYPE_INDIRECT_CSD; - info->offset = indirect_csd.offset; - info->wg_size = indirect_csd.wg_size; - memcpy(&info->wg_uniform_offsets, &indirect_csd.wg_uniform_offsets, - sizeof(indirect_csd.wg_uniform_offsets)); - - info->indirect = drm_gem_object_lookup(file_priv, indirect_csd.indirect); - - return v3d_setup_csd_jobs_and_bos(file_priv, v3d, &indirect_csd.submit, - &info->job, &info->clean_job, - NULL, &info->acquire_ctx); -} - -/* Get data for the query timestamp job submission. */ -static int -v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *offsets, *syncs; - struct drm_v3d_timestamp_query timestamp; -<<<<<<< -======= - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; ->>>>>>> - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(×tamp, ext, sizeof(timestamp))) - return -EFAULT; - - if (timestamp.pad) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(timestamp.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - offsets = u64_to_user_ptr(timestamp.offsets); - syncs = u64_to_user_ptr(timestamp.syncs); - - for (i = 0; i < timestamp.count; i++) { - u32 offset, sync; - -<<<<<<< - if (copy_from_user(&offset, offsets++, sizeof(offset))) { -======= - if (get_user(offset, offsets++)) { ->>>>>>> - err = -EFAULT; - goto error; - } - - query_info->queries[i].offset = offset; - -<<<<<<< - if (copy_from_user(&sync, syncs++, sizeof(sync))) { -======= - if (get_user(sync, syncs++)) { ->>>>>>> - err = -EFAULT; - goto error; - } - -<<<<<<< - job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (!job->timestamp_query.queries[i].syncobj) { -======= - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { ->>>>>>> - err = -ENOENT; - goto error; - } - } - query_info->count = timestamp.count; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -} - -static int -v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *syncs; - struct drm_v3d_reset_timestamp_query reset; -<<<<<<< -======= - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; ->>>>>>> - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&reset, ext, sizeof(reset))) - return -EFAULT; - - job->job_type = V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(reset.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - syncs = u64_to_user_ptr(reset.syncs); - - for (i = 0; i < reset.count; i++) { - u32 sync; - - query_info->queries[i].offset = reset.offset + 8 * i; - -<<<<<<< - if (copy_from_user(&sync, syncs++, sizeof(sync))) { -======= - if (get_user(sync, syncs++)) { ->>>>>>> - err = -EFAULT; - goto error; - } - -<<<<<<< - job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (!job->timestamp_query.queries[i].syncobj) { -======= - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { ->>>>>>> - err = -ENOENT; - goto error; - } - } - query_info->count = reset.count; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -} - -/* Get data for the copy timestamp query results job submission. */ -static int -v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - u32 __user *offsets, *syncs; - struct drm_v3d_copy_timestamp_query copy; -<<<<<<< -======= - struct v3d_timestamp_query_info *query_info = &job->timestamp_query; ->>>>>>> - unsigned int i; - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(©, ext, sizeof(copy))) - return -EFAULT; - - if (copy.pad) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY; - - query_info->queries = kvmalloc_array(copy.count, - sizeof(struct v3d_timestamp_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - - offsets = u64_to_user_ptr(copy.offsets); - syncs = u64_to_user_ptr(copy.syncs); - - for (i = 0; i < copy.count; i++) { - u32 offset, sync; - -<<<<<<< - if (copy_from_user(&offset, offsets++, sizeof(offset))) { -======= - if (get_user(offset, offsets++)) { ->>>>>>> - err = -EFAULT; - goto error; - } - - query_info->queries[i].offset = offset; - -<<<<<<< - if (copy_from_user(&sync, syncs++, sizeof(sync))) { -======= - if (get_user(sync, syncs++)) { ->>>>>>> - err = -EFAULT; - goto error; - } - -<<<<<<< - job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (!job->timestamp_query.queries[i].syncobj) { -======= - query_info->queries[i].syncobj = drm_syncobj_find(file_priv, - sync); - if (!query_info->queries[i].syncobj) { ->>>>>>> - err = -ENOENT; - goto error; - } - } - query_info->count = copy.count; - - job->copy.do_64bit = copy.do_64bit; - job->copy.do_partial = copy.do_partial; - job->copy.availability_bit = copy.availability_bit; - job->copy.offset = copy.offset; - job->copy.stride = copy.stride; - - return 0; - -error: - v3d_timestamp_query_info_free(&job->timestamp_query, i); - return err; -<<<<<<< -======= -} - -static int -v3d_copy_query_info(struct v3d_performance_query_info *query_info, - unsigned int count, - unsigned int nperfmons, - u32 __user *syncs, - u64 __user *kperfmon_ids, - struct drm_file *file_priv) -{ - unsigned int i, j; - int err; - - for (i = 0; i < count; i++) { - struct v3d_performance_query *query = &query_info->queries[i]; - u32 __user *ids_pointer; - u32 sync, id; - u64 ids; - - if (get_user(sync, syncs++)) { - err = -EFAULT; - goto error; - } - - if (get_user(ids, kperfmon_ids++)) { - err = -EFAULT; - goto error; - } - - query->kperfmon_ids = - kvmalloc_array(nperfmons, - sizeof(struct v3d_performance_query *), - GFP_KERNEL); - if (!query->kperfmon_ids) { - err = -ENOMEM; - goto error; - } - - ids_pointer = u64_to_user_ptr(ids); - - for (j = 0; j < nperfmons; j++) { - if (get_user(id, ids_pointer++)) { - kvfree(query->kperfmon_ids); - err = -EFAULT; - goto error; - } - - query->kperfmon_ids[j] = id; - } - - query->syncobj = drm_syncobj_find(file_priv, sync); - if (!query->syncobj) { - kvfree(query->kperfmon_ids); - err = -ENOENT; - goto error; - } - } - - return 0; - -error: - v3d_performance_query_info_free(query_info, i); - return err; ->>>>>>> -} - -static int -v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_performance_query_info *query_info = &job->performance_query; - struct drm_v3d_reset_performance_query reset; -<<<<<<< -======= - unsigned int i, j; ->>>>>>> - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(&reset, ext, sizeof(reset))) - return -EFAULT; - - if (reset.nperfmons > V3D_MAX_PERFMONS) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY; - - query_info->queries = - kvmalloc_array(reset.count, - sizeof(struct v3d_performance_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - -<<<<<<< - err = v3d_copy_query_info(query_info, - reset.count, - reset.nperfmons, - u64_to_user_ptr(reset.syncs), - u64_to_user_ptr(reset.kperfmon_ids), - file_priv); - if (err) - return err; - - query_info->count = reset.count; - query_info->nperfmons = reset.nperfmons; -======= - syncs = u64_to_user_ptr(reset.syncs); - kperfmon_ids = u64_to_user_ptr(reset.kperfmon_ids); - - for (i = 0; i < reset.count; i++) { - u32 sync; - u64 ids; - u32 __user *ids_pointer; - u32 id; - - if (copy_from_user(&sync, syncs++, sizeof(sync))) { - err = -EFAULT; - goto error; - } - - if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) { - err = -EFAULT; - goto error; - } - - ids_pointer = u64_to_user_ptr(ids); - - for (j = 0; j < reset.nperfmons; j++) { - if (copy_from_user(&id, ids_pointer++, sizeof(id))) { - err = -EFAULT; - goto error; - } - - job->performance_query.queries[i].kperfmon_ids[j] = id; - } - - job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (!job->performance_query.queries[i].syncobj) { - err = -ENOENT; - goto error; - } - } - job->performance_query.count = reset.count; - job->performance_query.nperfmons = reset.nperfmons; ->>>>>>> - - return 0; - -error: - v3d_performance_query_info_free(&job->performance_query, i); - return err; -} - -static int -v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, - struct drm_v3d_extension __user *ext, - struct v3d_cpu_job *job) -{ - struct v3d_performance_query_info *query_info = &job->performance_query; - struct drm_v3d_copy_performance_query copy; -<<<<<<< -======= - unsigned int i, j; ->>>>>>> - int err; - - if (!job) { - DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); - return -EINVAL; - } - - if (job->job_type) { - DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n"); - return -EINVAL; - } - - if (copy_from_user(©, ext, sizeof(copy))) - return -EFAULT; - - if (copy.pad) - return -EINVAL; - - if (copy.nperfmons > V3D_MAX_PERFMONS) - return -EINVAL; - - job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY; - - query_info->queries = - kvmalloc_array(copy.count, - sizeof(struct v3d_performance_query), - GFP_KERNEL); - if (!query_info->queries) - return -ENOMEM; - -<<<<<<< - err = v3d_copy_query_info(query_info, - copy.count, - copy.nperfmons, - u64_to_user_ptr(copy.syncs), - u64_to_user_ptr(copy.kperfmon_ids), - file_priv); - if (err) - return err; - - query_info->count = copy.count; - query_info->nperfmons = copy.nperfmons; - query_info->ncounters = copy.ncounters; -======= - syncs = u64_to_user_ptr(copy.syncs); - kperfmon_ids = u64_to_user_ptr(copy.kperfmon_ids); - - for (i = 0; i < copy.count; i++) { - u32 sync; - u64 ids; - u32 __user *ids_pointer; - u32 id; - - if (copy_from_user(&sync, syncs++, sizeof(sync))) { - err = -EFAULT; - goto error; - } - - if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) { - err = -EFAULT; - goto error; - } - - ids_pointer = u64_to_user_ptr(ids); - - for (j = 0; j < copy.nperfmons; j++) { - if (copy_from_user(&id, ids_pointer++, sizeof(id))) { - err = -EFAULT; - goto error; - } - - job->performance_query.queries[i].kperfmon_ids[j] = id; - } - - job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (!job->performance_query.queries[i].syncobj) { - err = -ENOENT; - goto error; - } - } - job->performance_query.count = copy.count; - job->performance_query.nperfmons = copy.nperfmons; - job->performance_query.ncounters = copy.ncounters; ->>>>>>> - - job->copy.do_64bit = copy.do_64bit; - job->copy.do_partial = copy.do_partial; - job->copy.availability_bit = copy.availability_bit; - job->copy.offset = copy.offset; - job->copy.stride = copy.stride; - - return 0; - -error: - v3d_performance_query_info_free(&job->performance_query, i); - return err; -} - -/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data - * according to the extension id (name). - */ -static int -v3d_get_extensions(struct drm_file *file_priv, - u64 ext_handles, - struct v3d_submit_ext *se, - struct v3d_cpu_job *job) -{ - struct drm_v3d_extension __user *user_ext; - int ret; - - user_ext = u64_to_user_ptr(ext_handles); - while (user_ext) { - struct drm_v3d_extension ext; - - if (copy_from_user(&ext, user_ext, sizeof(ext))) { - DRM_DEBUG("Failed to copy submit extension\n"); - return -EFAULT; - } - - switch (ext.id) { - case DRM_V3D_EXT_ID_MULTI_SYNC: - ret = v3d_get_multisync_submit_deps(file_priv, user_ext, se); - break; - case DRM_V3D_EXT_ID_CPU_INDIRECT_CSD: - ret = v3d_get_cpu_indirect_csd_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY: - ret = v3d_get_cpu_timestamp_query_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY: - ret = v3d_get_cpu_reset_timestamp_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY: - ret = v3d_get_cpu_copy_query_results_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY: - ret = v3d_get_cpu_reset_performance_params(file_priv, user_ext, job); - break; - case DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY: - ret = v3d_get_cpu_copy_performance_query_params(file_priv, user_ext, job); - break; - default: - DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); - return -EINVAL; - } - - if (ret) - return ret; - - user_ext = u64_to_user_ptr(ext.next); - } - - return 0; -} - -/** - * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * This is the main entrypoint for userspace to submit a 3D frame to - * the GPU. Userspace provides the binner command list (if - * applicable), and the kernel sets up the render command list to draw - * to the framebuffer described in the ioctl, using the command lists - * that the 3D engine's binner will produce. - */ -int -v3d_submit_cl_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct drm_v3d_submit_cl *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_bin_job *bin = NULL; - struct v3d_render_job *render = NULL; - struct v3d_job *clean_job = NULL; - struct v3d_job *last_job; - struct ww_acquire_ctx acquire_ctx; - int ret = 0; - - trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end); - - if (args->pad) - return -EINVAL; - - if (args->flags && - args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE | - DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_job_allocate((void *)&render, sizeof(*render)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &render->base, - v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER); - if (ret) { - v3d_job_deallocate((void *)&render); - goto fail; - } - - render->start = args->rcl_start; - render->end = args->rcl_end; - INIT_LIST_HEAD(&render->unref_list); - - if (args->bcl_start != args->bcl_end) { - ret = v3d_job_allocate((void *)&bin, sizeof(*bin)); - if (ret) - goto fail; - - ret = v3d_job_init(v3d, file_priv, &bin->base, - v3d_job_free, args->in_sync_bcl, &se, V3D_BIN); - if (ret) { - v3d_job_deallocate((void *)&bin); - goto fail; - } - - bin->start = args->bcl_start; - bin->end = args->bcl_end; - bin->qma = args->qma; - bin->qms = args->qms; - bin->qts = args->qts; - bin->render = render; - } - - if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { - ret = v3d_job_allocate((void *)&clean_job, sizeof(*clean_job)); - if (ret) - goto fail; - - ret = v3d_job_init(v3d, file_priv, clean_job, - v3d_job_free, 0, NULL, V3D_CACHE_CLEAN); - if (ret) { - v3d_job_deallocate((void *)&clean_job); - goto fail; - } - - last_job = clean_job; - } else { - last_job = &render->base; - } - - ret = v3d_lookup_bos(dev, file_priv, last_job, - args->bo_handles, args->bo_handle_count); - if (ret) - goto fail; - - ret = v3d_lock_bo_reservations(last_job, &acquire_ctx); - if (ret) - goto fail; - - if (args->perfmon_id) { - render->base.perfmon = v3d_perfmon_find(v3d_priv, - args->perfmon_id); - - if (!render->base.perfmon) { - ret = -ENOENT; - goto fail_perfmon; - } - } - - mutex_lock(&v3d->sched_lock); - if (bin) { - bin->base.perfmon = render->base.perfmon; - v3d_perfmon_get(bin->base.perfmon); - v3d_push_job(&bin->base); - - ret = drm_sched_job_add_dependency(&render->base.base, - dma_fence_get(bin->base.done_fence)); - if (ret) - goto fail_unreserve; - } - - v3d_push_job(&render->base); - - if (clean_job) { - struct dma_fence *render_fence = - dma_fence_get(render->base.done_fence); - ret = drm_sched_job_add_dependency(&clean_job->base, - render_fence); - if (ret) - goto fail_unreserve; - clean_job->perfmon = render->base.perfmon; - v3d_perfmon_get(clean_job->perfmon); - v3d_push_job(clean_job); - } - - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - last_job, - &acquire_ctx, - args->out_sync, - &se, - last_job->done_fence); - - v3d_job_put(&bin->base); - v3d_job_put(&render->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); -fail_perfmon: - drm_gem_unlock_reservations(last_job->bo, - last_job->bo_count, &acquire_ctx); -fail: - v3d_job_cleanup((void *)bin); - v3d_job_cleanup((void *)render); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -/** - * v3d_submit_tfu_ioctl() - Submits a TFU (texture formatting) job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace provides the register setup for the TFU, which we don't - * need to validate since the TFU is behind the MMU. - */ -int -v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_v3d_submit_tfu *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_tfu_job *job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret = 0; - - trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia); - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_DEBUG("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_job_allocate((void *)&job, sizeof(*job)); - if (ret) - return ret; - - ret = v3d_job_init(v3d, file_priv, &job->base, - v3d_job_free, args->in_sync, &se, V3D_TFU); - if (ret) { - v3d_job_deallocate((void *)&job); - goto fail; - } - - job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles), - sizeof(*job->base.bo), GFP_KERNEL); - if (!job->base.bo) { - ret = -ENOMEM; - goto fail; - } - - job->args = *args; - - for (job->base.bo_count = 0; - job->base.bo_count < ARRAY_SIZE(args->bo_handles); - job->base.bo_count++) { - struct drm_gem_object *bo; - - if (!args->bo_handles[job->base.bo_count]) - break; - - bo = drm_gem_object_lookup(file_priv, args->bo_handles[job->base.bo_count]); - if (!bo) { - DRM_DEBUG("Failed to look up GEM BO %d: %d\n", - job->base.bo_count, - args->bo_handles[job->base.bo_count]); - ret = -ENOENT; - goto fail; - } - job->base.bo[job->base.bo_count] = bo; - } - - ret = v3d_lock_bo_reservations(&job->base, &acquire_ctx); - if (ret) - goto fail; - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&job->base); - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - &job->base, &acquire_ctx, - args->out_sync, - &se, - job->base.done_fence); - - v3d_job_put(&job->base); - - return 0; - -fail: - v3d_job_cleanup((void *)job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -/** - * v3d_submit_csd_ioctl() - Submits a CSD (compute shader) job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace provides the register setup for the CSD, which we don't - * need to validate since the CSD is behind the MMU. - */ -int -v3d_submit_csd_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; - struct drm_v3d_submit_csd *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_csd_job *job = NULL; - struct v3d_job *clean_job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret; - - trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]); - - if (args->pad) - return -EINVAL; - - if (!v3d_has_csd(v3d)) { - DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n"); - return -EINVAL; - } - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("invalid flags: %d\n", args->flags); - return -EINVAL; - } - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, NULL); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - return ret; - } - } - - ret = v3d_setup_csd_jobs_and_bos(file_priv, v3d, args, - &job, &clean_job, &se, - &acquire_ctx); - if (ret) - goto fail; - - if (args->perfmon_id) { - job->base.perfmon = v3d_perfmon_find(v3d_priv, - args->perfmon_id); - if (!job->base.perfmon) { - ret = -ENOENT; - goto fail_perfmon; - } - } - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&job->base); - - ret = drm_sched_job_add_dependency(&clean_job->base, - dma_fence_get(job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(clean_job); - mutex_unlock(&v3d->sched_lock); - - v3d_attach_fences_and_unlock_reservation(file_priv, - clean_job, - &acquire_ctx, - args->out_sync, - &se, - clean_job->done_fence); - - v3d_job_put(&job->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); -fail_perfmon: - drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count, - &acquire_ctx); -fail: - v3d_job_cleanup((void *)job); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - - return ret; -} - -static const unsigned int cpu_job_bo_handle_count[] = { - [V3D_CPU_JOB_TYPE_INDIRECT_CSD] = 1, - [V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY] = 1, - [V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY] = 1, - [V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY] = 2, - [V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY] = 0, - [V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY] = 1, -}; - -/** - * v3d_submit_cpu_ioctl() - Submits a CPU job to the V3D. - * @dev: DRM device - * @data: ioctl argument - * @file_priv: DRM file for this fd - * - * Userspace specifies the CPU job type and data required to perform its - * operations through the drm_v3d_extension struct. - */ -int -v3d_submit_cpu_ioctl(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - struct v3d_dev *v3d = to_v3d_dev(dev); - struct drm_v3d_submit_cpu *args = data; - struct v3d_submit_ext se = {0}; - struct v3d_submit_ext *out_se = NULL; - struct v3d_cpu_job *cpu_job = NULL; - struct v3d_csd_job *csd_job = NULL; - struct v3d_job *clean_job = NULL; - struct ww_acquire_ctx acquire_ctx; - int ret; - - if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { - DRM_INFO("Invalid flags: %d\n", args->flags); - return -EINVAL; - } - - ret = v3d_job_allocate((void *)&cpu_job, sizeof(*cpu_job)); - if (ret) - return ret; - - if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, args->extensions, &se, cpu_job); - if (ret) { - DRM_DEBUG("Failed to get extensions.\n"); - goto fail; - } - } - - /* Every CPU job must have a CPU job user extension */ - if (!cpu_job->job_type) { - DRM_DEBUG("CPU job must have a CPU job user extension.\n"); - ret = -EINVAL; - goto fail; - } - - if (args->bo_handle_count != cpu_job_bo_handle_count[cpu_job->job_type]) { - DRM_DEBUG("This CPU job was not submitted with the proper number of BOs.\n"); - ret = -EINVAL; - goto fail; - } - - trace_v3d_submit_cpu_ioctl(&v3d->drm, cpu_job->job_type); - - ret = v3d_job_init(v3d, file_priv, &cpu_job->base, - v3d_job_free, 0, &se, V3D_CPU); - if (ret) { - v3d_job_deallocate((void *)&cpu_job); - goto fail; - } - - clean_job = cpu_job->indirect_csd.clean_job; - csd_job = cpu_job->indirect_csd.job; - - if (args->bo_handle_count) { - ret = v3d_lookup_bos(dev, file_priv, &cpu_job->base, - args->bo_handles, args->bo_handle_count); - if (ret) - goto fail; - - ret = v3d_lock_bo_reservations(&cpu_job->base, &acquire_ctx); - if (ret) - goto fail; - } - - mutex_lock(&v3d->sched_lock); - v3d_push_job(&cpu_job->base); - - switch (cpu_job->job_type) { - case V3D_CPU_JOB_TYPE_INDIRECT_CSD: - ret = drm_sched_job_add_dependency(&csd_job->base.base, - dma_fence_get(cpu_job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(&csd_job->base); - - ret = drm_sched_job_add_dependency(&clean_job->base, - dma_fence_get(csd_job->base.done_fence)); - if (ret) - goto fail_unreserve; - - v3d_push_job(clean_job); - - break; - default: - break; - } - mutex_unlock(&v3d->sched_lock); - - out_se = (cpu_job->job_type == V3D_CPU_JOB_TYPE_INDIRECT_CSD) ? NULL : &se; - - v3d_attach_fences_and_unlock_reservation(file_priv, - &cpu_job->base, - &acquire_ctx, 0, - out_se, cpu_job->base.done_fence); - - switch (cpu_job->job_type) { - case V3D_CPU_JOB_TYPE_INDIRECT_CSD: - v3d_attach_fences_and_unlock_reservation(file_priv, - clean_job, - &cpu_job->indirect_csd.acquire_ctx, - 0, &se, clean_job->done_fence); - break; - default: - break; - } - - v3d_job_put(&cpu_job->base); - v3d_job_put(&csd_job->base); - v3d_job_put(clean_job); - - return 0; - -fail_unreserve: - mutex_unlock(&v3d->sched_lock); - - drm_gem_unlock_reservations(cpu_job->base.bo, cpu_job->base.bo_count, - &acquire_ctx); - - drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count, - &cpu_job->indirect_csd.acquire_ctx); - -fail: - v3d_job_cleanup((void *)cpu_job); - v3d_job_cleanup((void *)csd_job); - v3d_job_cleanup(clean_job); - v3d_put_multisync_post_deps(&se); - kvfree(cpu_job->timestamp_query.queries); - kvfree(cpu_job->performance_query.queries); - - return ret; -} diff --git a/rr-cache/c3af3f3a26e05878b3dc9cf670c390ed4180ae9f/preimage b/rr-cache/c3af3f3a26e05878b3dc9cf670c390ed4180ae9f/preimage new file mode 100644 index 000000000000..cc2cfd343e11 --- /dev/null +++ b/rr-cache/c3af3f3a26e05878b3dc9cf670c390ed4180ae9f/preimage @@ -0,0 +1,1766 @@ +/* i915_drv.c -- i830,i845,i855,i865,i915 driver -*- linux-c -*- + */ +/* + * + * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. + * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR + * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include <linux/acpi.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/oom.h> +#include <linux/pci.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> +#include <linux/string_helpers.h> +#include <linux/vga_switcheroo.h> +#include <linux/vt.h> + +#include <drm/drm_aperture.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_ioctl.h> +#include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> + +#include "display/i9xx_display_sr.h" +#include "display/intel_acpi.h" +#include "display/intel_bw.h" +#include "display/intel_cdclk.h" +#include "display/intel_display_driver.h" +#include "display/intel_display.h" +#include "display/intel_dmc.h" +#include "display/intel_dp.h" +#include "display/intel_dpt.h" +#include "display/intel_encoder.h" +#include "display/intel_fbdev.h" +#include "display/intel_hotplug.h" +#include "display/intel_overlay.h" +#include "display/intel_pch_refclk.h" +#include "display/intel_pps.h" +#include "display/intel_sprite.h" +#include "display/intel_vga.h" +#include "display/skl_watermark.h" + +#include "gem/i915_gem_context.h" +#include "gem/i915_gem_create.h" +#include "gem/i915_gem_dmabuf.h" +#include "gem/i915_gem_ioctls.h" +#include "gem/i915_gem_mman.h" +#include "gem/i915_gem_pm.h" +#include "gt/intel_gt.h" +#include "gt/intel_gt_pm.h" +#include "gt/intel_gt_print.h" +#include "gt/intel_rc6.h" + +#include "pxp/intel_pxp.h" +#include "pxp/intel_pxp_debugfs.h" +#include "pxp/intel_pxp_pm.h" + +#include "soc/intel_dram.h" +#include "soc/intel_gmch.h" + +#include "i915_debugfs.h" +#include "i915_driver.h" +#include "i915_drm_client.h" +#include "i915_drv.h" +#include "i915_file_private.h" +#include "i915_getparam.h" +#include "i915_hwmon.h" +#include "i915_ioc32.h" +#include "i915_ioctl.h" +#include "i915_irq.h" +#include "i915_memcpy.h" +#include "i915_perf.h" +#include "i915_query.h" +#include "i915_switcheroo.h" +#include "i915_sysfs.h" +#include "i915_utils.h" +#include "i915_vgpu.h" +#include "intel_clock_gating.h" +#include "intel_gvt.h" +#include "intel_memory_region.h" +#include "intel_pci_config.h" +#include "intel_pcode.h" +#include "intel_region_ttm.h" +#include "vlv_suspend.h" + +static const struct drm_driver i915_drm_driver; + +static int i915_workqueues_init(struct drm_i915_private *dev_priv) +{ + /* + * The i915 workqueue is primarily used for batched retirement of + * requests (and thus managing bo) once the task has been completed + * by the GPU. i915_retire_requests() is called directly when we + * need high-priority retirement, such as waiting for an explicit + * bo. + * + * It is also used for periodic low-priority events, such as + * idle-timers and recording error state. + * + * All tasks on the workqueue are expected to acquire the dev mutex + * so there is no point in running more than one instance of the + * workqueue at any time. Use an ordered one. + */ + dev_priv->wq = alloc_ordered_workqueue("i915", 0); + if (dev_priv->wq == NULL) + goto out_err; + + dev_priv->display.hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0); + if (dev_priv->display.hotplug.dp_wq == NULL) + goto out_free_wq; + + /* + * The unordered i915 workqueue should be used for all work + * scheduling that do not require running in order, which used + * to be scheduled on the system_wq before moving to a driver + * instance due deprecation of flush_scheduled_work(). + */ + dev_priv->unordered_wq = alloc_workqueue("i915-unordered", 0, 0); + if (dev_priv->unordered_wq == NULL) + goto out_free_dp_wq; + + return 0; + +out_free_dp_wq: + destroy_workqueue(dev_priv->display.hotplug.dp_wq); +out_free_wq: + destroy_workqueue(dev_priv->wq); +out_err: + drm_err(&dev_priv->drm, "Failed to allocate workqueues.\n"); + + return -ENOMEM; +} + +static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv) +{ + destroy_workqueue(dev_priv->unordered_wq); + destroy_workqueue(dev_priv->display.hotplug.dp_wq); + destroy_workqueue(dev_priv->wq); +} + +/* + * We don't keep the workarounds for pre-production hardware, so we expect our + * driver to fail on these machines in one way or another. A little warning on + * dmesg may help both the user and the bug triagers. + * + * Our policy for removing pre-production workarounds is to keep the + * current gen workarounds as a guide to the bring-up of the next gen + * (workarounds have a habit of persisting!). Anything older than that + * should be removed along with the complications they introduce. + */ +static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) +{ + bool pre = false; + + pre |= IS_HASWELL_EARLY_SDV(dev_priv); + pre |= IS_SKYLAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x6; + pre |= IS_BROXTON(dev_priv) && INTEL_REVID(dev_priv) < 0xA; + pre |= IS_KABYLAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x1; + pre |= IS_GEMINILAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x3; + pre |= IS_ICELAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x7; + pre |= IS_TIGERLAKE(dev_priv) && INTEL_REVID(dev_priv) < 0x1; + pre |= IS_DG1(dev_priv) && INTEL_REVID(dev_priv) < 0x1; + pre |= IS_DG2_G10(dev_priv) && INTEL_REVID(dev_priv) < 0x8; + pre |= IS_DG2_G11(dev_priv) && INTEL_REVID(dev_priv) < 0x5; + pre |= IS_DG2_G12(dev_priv) && INTEL_REVID(dev_priv) < 0x1; + + if (pre) { + drm_err(&dev_priv->drm, "This is a pre-production stepping. " + "It may not be fully functional.\n"); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); + } +} + +static void sanitize_gpu(struct drm_i915_private *i915) +{ + if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) { + struct intel_gt *gt; + unsigned int i; + + for_each_gt(gt, i915, i) + intel_gt_reset_all_engines(gt); + } +} + +/** + * i915_driver_early_probe - setup state not requiring device access + * @dev_priv: device private + * + * Initialize everything that is a "SW-only" state, that is state not + * requiring accessing the device or exposing the driver via kernel internal + * or userspace interfaces. Example steps belonging here: lock initialization, + * system memory allocation, setting up device specific attributes and + * function hooks not requiring accessing the device. + */ +static int i915_driver_early_probe(struct drm_i915_private *dev_priv) +{ + int ret = 0; + + if (i915_inject_probe_failure(dev_priv)) + return -ENODEV; + + intel_device_info_runtime_init_early(dev_priv); + + intel_step_init(dev_priv); + + intel_uncore_mmio_debug_init_early(dev_priv); + + spin_lock_init(&dev_priv->irq_lock); + spin_lock_init(&dev_priv->gpu_error.lock); + + mutex_init(&dev_priv->sb_lock); + cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE); + + i915_memcpy_init_early(dev_priv); + intel_runtime_pm_init_early(&dev_priv->runtime_pm); + + ret = i915_workqueues_init(dev_priv); + if (ret < 0) + return ret; + + ret = vlv_suspend_init(dev_priv); + if (ret < 0) + goto err_workqueues; + + ret = intel_region_ttm_device_init(dev_priv); + if (ret) + goto err_ttm; + + ret = intel_root_gt_init_early(dev_priv); + if (ret < 0) + goto err_rootgt; + + i915_gem_init_early(dev_priv); + + /* This must be called before any calls to HAS_PCH_* */ + intel_detect_pch(dev_priv); + + intel_irq_init(dev_priv); + intel_display_driver_early_probe(dev_priv); + intel_clock_gating_hooks_init(dev_priv); + + intel_detect_preproduction_hw(dev_priv); + + return 0; + +err_rootgt: + intel_region_ttm_device_fini(dev_priv); +err_ttm: + vlv_suspend_cleanup(dev_priv); +err_workqueues: + i915_workqueues_cleanup(dev_priv); + return ret; +} + +/** + * i915_driver_late_release - cleanup the setup done in + * i915_driver_early_probe() + * @dev_priv: device private + */ +static void i915_driver_late_release(struct drm_i915_private *dev_priv) +{ + intel_irq_fini(dev_priv); + intel_power_domains_cleanup(dev_priv); + i915_gem_cleanup_early(dev_priv); + intel_gt_driver_late_release_all(dev_priv); + intel_region_ttm_device_fini(dev_priv); + vlv_suspend_cleanup(dev_priv); + i915_workqueues_cleanup(dev_priv); + + cpu_latency_qos_remove_request(&dev_priv->sb_qos); + mutex_destroy(&dev_priv->sb_lock); + + i915_params_free(&dev_priv->params); +} + +/** + * i915_driver_mmio_probe - setup device MMIO + * @dev_priv: device private + * + * Setup minimal device state necessary for MMIO accesses later in the + * initialization sequence. The setup here should avoid any other device-wide + * side effects or exposing the driver via kernel internal or user space + * interfaces. + */ +static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) +{ + struct intel_gt *gt; + int ret, i; + + if (i915_inject_probe_failure(dev_priv)) + return -ENODEV; + + ret = intel_gmch_bridge_setup(dev_priv); + if (ret < 0) + return ret; + + for_each_gt(gt, dev_priv, i) { + ret = intel_uncore_init_mmio(gt->uncore); + if (ret) + return ret; + + ret = drmm_add_action_or_reset(&dev_priv->drm, + intel_uncore_fini_mmio, + gt->uncore); + if (ret) + return ret; + } + + /* Try to make sure MCHBAR is enabled before poking at it */ + intel_gmch_bar_setup(dev_priv); + intel_device_info_runtime_init(dev_priv); + intel_display_device_info_runtime_init(dev_priv); + + for_each_gt(gt, dev_priv, i) { + ret = intel_gt_init_mmio(gt); + if (ret) + goto err_uncore; + } + + /* As early as possible, scrub existing GPU state before clobbering */ + sanitize_gpu(dev_priv); + + return 0; + +err_uncore: + intel_gmch_bar_teardown(dev_priv); + + return ret; +} + +/** + * i915_driver_mmio_release - cleanup the setup done in i915_driver_mmio_probe() + * @dev_priv: device private + */ +static void i915_driver_mmio_release(struct drm_i915_private *dev_priv) +{ + intel_gmch_bar_teardown(dev_priv); +} + +/** + * i915_set_dma_info - set all relevant PCI dma info as configured for the + * platform + * @i915: valid i915 instance + * + * Set the dma max segment size, device and coherent masks. The dma mask set + * needs to occur before i915_ggtt_probe_hw. + * + * A couple of platforms have special needs. Address them as well. + * + */ +static int i915_set_dma_info(struct drm_i915_private *i915) +{ + unsigned int mask_size = INTEL_INFO(i915)->dma_mask_size; + int ret; + + GEM_BUG_ON(!mask_size); + + /* + * We don't have a max segment size, so set it to the max so sg's + * debugging layer doesn't complain + */ + dma_set_max_seg_size(i915->drm.dev, UINT_MAX); + + ret = dma_set_mask(i915->drm.dev, DMA_BIT_MASK(mask_size)); + if (ret) + goto mask_err; + + /* overlay on gen2 is broken and can't address above 1G */ + if (GRAPHICS_VER(i915) == 2) + mask_size = 30; + + /* + * 965GM sometimes incorrectly writes to hardware status page (HWS) + * using 32bit addressing, overwriting memory if HWS is located + * above 4GB. + * + * The documentation also mentions an issue with undefined + * behaviour if any general state is accessed within a page above 4GB, + * which also needs to be handled carefully. + */ + if (IS_I965G(i915) || IS_I965GM(i915)) + mask_size = 32; + + ret = dma_set_coherent_mask(i915->drm.dev, DMA_BIT_MASK(mask_size)); + if (ret) + goto mask_err; + + return 0; + +mask_err: + drm_err(&i915->drm, "Can't set DMA mask/consistent mask (%d)\n", ret); + return ret; +} + +static int i915_pcode_init(struct drm_i915_private *i915) +{ + struct intel_gt *gt; + int id, ret; + + for_each_gt(gt, i915, id) { + ret = intel_pcode_init(gt->uncore); + if (ret) { + gt_err(gt, "intel_pcode_init failed %d\n", ret); + return ret; + } + } + + return 0; +} + +/** + * i915_driver_hw_probe - setup state requiring device access + * @dev_priv: device private + * + * Setup state that requires accessing the device, but doesn't require + * exposing the driver via kernel internal or userspace interfaces. + */ +static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) +{ + struct intel_display *display = &dev_priv->display; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + int ret; + + if (i915_inject_probe_failure(dev_priv)) + return -ENODEV; + + if (HAS_PPGTT(dev_priv)) { + if (intel_vgpu_active(dev_priv) && + !intel_vgpu_has_full_ppgtt(dev_priv)) { + drm_err(&dev_priv->drm, + "incompatible vGPU found, support for isolated ppGTT required\n"); + return -ENXIO; + } + } + + if (HAS_EXECLISTS(dev_priv)) { + /* + * Older GVT emulation depends upon intercepting CSB mmio, + * which we no longer use, preferring to use the HWSP cache + * instead. + */ + if (intel_vgpu_active(dev_priv) && + !intel_vgpu_has_hwsp_emulation(dev_priv)) { + drm_err(&dev_priv->drm, + "old vGPU host found, support for HWSP emulation required\n"); + return -ENXIO; + } + } + + /* needs to be done before ggtt probe */ + intel_dram_edram_detect(dev_priv); + + ret = i915_set_dma_info(dev_priv); + if (ret) + return ret; + + ret = i915_perf_init(dev_priv); + if (ret) + return ret; + + ret = i915_ggtt_probe_hw(dev_priv); + if (ret) + goto err_perf; + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, dev_priv->drm.driver); + if (ret) + goto err_ggtt; + + ret = i915_ggtt_init_hw(dev_priv); + if (ret) + goto err_ggtt; + + /* + * Make sure we probe lmem before we probe stolen-lmem. The BAR size + * might be different due to bar resizing. + */ + ret = intel_gt_tiles_init(dev_priv); + if (ret) + goto err_ggtt; + + ret = intel_memory_regions_hw_probe(dev_priv); + if (ret) + goto err_ggtt; + + ret = i915_ggtt_enable_hw(dev_priv); + if (ret) { + drm_err(&dev_priv->drm, "failed to enable GGTT\n"); + goto err_mem_regions; + } + + pci_set_master(pdev); + + /* On the 945G/GM, the chipset reports the MSI capability on the + * integrated graphics even though the support isn't actually there + * according to the published specs. It doesn't appear to function + * correctly in testing on 945G. + * This may be a side effect of MSI having been made available for PEG + * and the registers being closely associated. + * + * According to chipset errata, on the 965GM, MSI interrupts may + * be lost or delayed, and was defeatured. MSI interrupts seem to + * get lost on g4x as well, and interrupt delivery seems to stay + * properly dead afterwards. So we'll just disable them for all + * pre-gen5 chipsets. + * + * dp aux and gmbus irq on gen4 seems to be able to generate legacy + * interrupts even when in MSI mode. This results in spurious + * interrupt warnings if the legacy irq no. is shared with another + * device. The kernel then disables that interrupt source and so + * prevents the other device from working properly. + */ + if (GRAPHICS_VER(dev_priv) >= 5) { + if (pci_enable_msi(pdev) < 0) + drm_dbg(&dev_priv->drm, "can't enable MSI"); + } + + ret = intel_gvt_init(dev_priv); + if (ret) + goto err_msi; + + intel_opregion_setup(display); + + ret = i915_pcode_init(dev_priv); + if (ret) + goto err_opregion; + + /* + * Fill the dram structure to get the system dram info. This will be + * used for memory latency calculation. + */ + intel_dram_detect(dev_priv); + + intel_bw_init_hw(dev_priv); + + return 0; + +err_opregion: + intel_opregion_cleanup(display); +err_msi: + if (pdev->msi_enabled) + pci_disable_msi(pdev); +err_mem_regions: + intel_memory_regions_driver_release(dev_priv); +err_ggtt: + i915_ggtt_driver_release(dev_priv); + i915_gem_drain_freed_objects(dev_priv); + i915_ggtt_driver_late_release(dev_priv); +err_perf: + i915_perf_fini(dev_priv); + return ret; +} + +/** + * i915_driver_hw_remove - cleanup the setup done in i915_driver_hw_probe() + * @dev_priv: device private + */ +static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) +{ + struct intel_display *display = &dev_priv->display; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + + i915_perf_fini(dev_priv); + + intel_opregion_cleanup(display); + + if (pdev->msi_enabled) + pci_disable_msi(pdev); +} + +/** + * i915_driver_register - register the driver with the rest of the system + * @dev_priv: device private + * + * Perform any steps necessary to make the driver available via kernel + * internal or userspace interfaces. + */ +static void i915_driver_register(struct drm_i915_private *dev_priv) +{ + struct intel_gt *gt; + unsigned int i; + + i915_gem_driver_register(dev_priv); + i915_pmu_register(dev_priv); + + intel_vgpu_register(dev_priv); + + /* Reveal our presence to userspace */ + if (drm_dev_register(&dev_priv->drm, 0)) { + drm_err(&dev_priv->drm, + "Failed to register driver for userspace access!\n"); + return; + } + + i915_debugfs_register(dev_priv); + i915_setup_sysfs(dev_priv); + + /* Depends on sysfs having been initialized */ + i915_perf_register(dev_priv); + + for_each_gt(gt, dev_priv, i) + intel_gt_driver_register(gt); + + intel_pxp_debugfs_register(dev_priv->pxp); + + i915_hwmon_register(dev_priv); + + intel_display_driver_register(dev_priv); + + intel_power_domains_enable(dev_priv); + intel_runtime_pm_enable(&dev_priv->runtime_pm); + + intel_register_dsm_handler(); + + if (i915_switcheroo_register(dev_priv)) + drm_err(&dev_priv->drm, "Failed to register vga switcheroo!\n"); +} + +/** + * i915_driver_unregister - cleanup the registration done in i915_driver_regiser() + * @dev_priv: device private + */ +static void i915_driver_unregister(struct drm_i915_private *dev_priv) +{ + struct intel_gt *gt; + unsigned int i; + + i915_switcheroo_unregister(dev_priv); + + intel_unregister_dsm_handler(); + + intel_runtime_pm_disable(&dev_priv->runtime_pm); + intel_power_domains_disable(dev_priv); + + intel_display_driver_unregister(dev_priv); + + intel_pxp_fini(dev_priv); + + for_each_gt(gt, dev_priv, i) + intel_gt_driver_unregister(gt); + + i915_hwmon_unregister(dev_priv); + + i915_perf_unregister(dev_priv); + i915_pmu_unregister(dev_priv); + + i915_teardown_sysfs(dev_priv); + drm_dev_unplug(&dev_priv->drm); + + i915_gem_driver_unregister(dev_priv); +} + +void +i915_print_iommu_status(struct drm_i915_private *i915, struct drm_printer *p) +{ + drm_printf(p, "iommu: %s\n", + str_enabled_disabled(i915_vtd_active(i915))); +} + +static void i915_welcome_messages(struct drm_i915_private *dev_priv) +{ + if (drm_debug_enabled(DRM_UT_DRIVER)) { + struct drm_printer p = drm_dbg_printer(&dev_priv->drm, DRM_UT_DRIVER, + "device info:"); + struct intel_gt *gt; + unsigned int i; + + drm_printf(&p, "pciid=0x%04x rev=0x%02x platform=%s (subplatform=0x%x) gen=%i\n", + INTEL_DEVID(dev_priv), + INTEL_REVID(dev_priv), + intel_platform_name(INTEL_INFO(dev_priv)->platform), + intel_subplatform(RUNTIME_INFO(dev_priv), + INTEL_INFO(dev_priv)->platform), + GRAPHICS_VER(dev_priv)); + + intel_device_info_print(INTEL_INFO(dev_priv), + RUNTIME_INFO(dev_priv), &p); + i915_print_iommu_status(dev_priv, &p); + for_each_gt(gt, dev_priv, i) + intel_gt_info_print(>->info, &p); + } + + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG)) + drm_info(&dev_priv->drm, "DRM_I915_DEBUG enabled\n"); + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) + drm_info(&dev_priv->drm, "DRM_I915_DEBUG_GEM enabled\n"); + if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)) + drm_info(&dev_priv->drm, + "DRM_I915_DEBUG_RUNTIME_PM enabled\n"); +} + +static struct drm_i915_private * +i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + const struct intel_device_info *match_info = + (struct intel_device_info *)ent->driver_data; + struct drm_i915_private *i915; + + i915 = devm_drm_dev_alloc(&pdev->dev, &i915_drm_driver, + struct drm_i915_private, drm); + if (IS_ERR(i915)) + return i915; + + pci_set_drvdata(pdev, &i915->drm); + + /* Device parameters start as a copy of module parameters. */ + i915_params_copy(&i915->params, &i915_modparams); + + /* Set up device info and initial runtime info. */ + intel_device_info_driver_create(i915, pdev->device, match_info); + + intel_display_device_probe(i915); + + return i915; +} + +/** + * i915_driver_probe - setup chip and create an initial config + * @pdev: PCI device + * @ent: matching PCI ID entry + * + * The driver probe routine has to do several things: + * - drive output discovery via intel_display_driver_probe() + * - initialize the memory manager + * - allocate initial config memory + * - setup the DRM framebuffer with the allocated memory + */ +int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct drm_i915_private *i915; + int ret; + + ret = pci_enable_device(pdev); + if (ret) { + pr_err("Failed to enable graphics device: %pe\n", ERR_PTR(ret)); + return ret; + } + + i915 = i915_driver_create(pdev, ent); + if (IS_ERR(i915)) { + pci_disable_device(pdev); + return PTR_ERR(i915); + } + + ret = i915_driver_early_probe(i915); + if (ret < 0) + goto out_pci_disable; + + disable_rpm_wakeref_asserts(&i915->runtime_pm); + + intel_vgpu_detect(i915); + + ret = intel_gt_probe_all(i915); + if (ret < 0) + goto out_runtime_pm_put; + + ret = i915_driver_mmio_probe(i915); + if (ret < 0) + goto out_runtime_pm_put; + + ret = i915_driver_hw_probe(i915); + if (ret < 0) + goto out_cleanup_mmio; + + ret = intel_display_driver_probe_noirq(i915); + if (ret < 0) + goto out_cleanup_hw; + + ret = intel_irq_install(i915); + if (ret) + goto out_cleanup_modeset; + + ret = intel_display_driver_probe_nogem(i915); + if (ret) + goto out_cleanup_irq; + + ret = i915_gem_init(i915); + if (ret) + goto out_cleanup_modeset2; + + ret = intel_pxp_init(i915); + if (ret && ret != -ENODEV) + drm_dbg(&i915->drm, "pxp init failed with %d\n", ret); + + ret = intel_display_driver_probe(i915); + if (ret) + goto out_cleanup_gem; + + i915_driver_register(i915); + + enable_rpm_wakeref_asserts(&i915->runtime_pm); + + i915_welcome_messages(i915); + + i915->do_release = true; + + return 0; + +out_cleanup_gem: + i915_gem_suspend(i915); + i915_gem_driver_remove(i915); + i915_gem_driver_release(i915); +out_cleanup_modeset2: + /* FIXME clean up the error path */ + intel_display_driver_remove(i915); + intel_irq_uninstall(i915); + intel_display_driver_remove_noirq(i915); + goto out_cleanup_modeset; +out_cleanup_irq: + intel_irq_uninstall(i915); +out_cleanup_modeset: + intel_display_driver_remove_nogem(i915); +out_cleanup_hw: + i915_driver_hw_remove(i915); + intel_memory_regions_driver_release(i915); + i915_ggtt_driver_release(i915); + i915_gem_drain_freed_objects(i915); + i915_ggtt_driver_late_release(i915); +out_cleanup_mmio: + i915_driver_mmio_release(i915); +out_runtime_pm_put: + enable_rpm_wakeref_asserts(&i915->runtime_pm); + i915_driver_late_release(i915); +out_pci_disable: + pci_disable_device(pdev); + i915_probe_error(i915, "Device initialization failed (%d)\n", ret); + return ret; +} + +void i915_driver_remove(struct drm_i915_private *i915) +{ + intel_wakeref_t wakeref; + + wakeref = intel_runtime_pm_get(&i915->runtime_pm); + + i915_driver_unregister(i915); + + /* Flush any external code that still may be under the RCU lock */ + synchronize_rcu(); + + i915_gem_suspend(i915); + + intel_gvt_driver_remove(i915); + + intel_display_driver_remove(i915); + + intel_irq_uninstall(i915); + + intel_display_driver_remove_noirq(i915); + + i915_reset_error_state(i915); + i915_gem_driver_remove(i915); + + intel_display_driver_remove_nogem(i915); + + i915_driver_hw_remove(i915); + + intel_runtime_pm_put(&i915->runtime_pm, wakeref); +} + +static void i915_driver_release(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + intel_wakeref_t wakeref; + + if (!dev_priv->do_release) + return; + + wakeref = intel_runtime_pm_get(rpm); + + i915_gem_driver_release(dev_priv); + + intel_memory_regions_driver_release(dev_priv); + i915_ggtt_driver_release(dev_priv); + i915_gem_drain_freed_objects(dev_priv); + i915_ggtt_driver_late_release(dev_priv); + + i915_driver_mmio_release(dev_priv); + + intel_runtime_pm_put(rpm, wakeref); + + intel_runtime_pm_driver_release(rpm); + + i915_driver_late_release(dev_priv); + + intel_display_device_remove(dev_priv); +} + +static int i915_driver_open(struct drm_device *dev, struct drm_file *file) +{ + struct drm_i915_private *i915 = to_i915(dev); + int ret; + + ret = i915_gem_open(i915, file); + if (ret) + return ret; + + return 0; +} + +static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) +{ + struct drm_i915_file_private *file_priv = file->driver_priv; + + i915_gem_context_close(file); + i915_drm_client_put(file_priv->client); + + kfree_rcu(file_priv, rcu); + + /* Catch up with all the deferred frees from "this" client */ + i915_gem_flush_free_objects(to_i915(dev)); +} + +void i915_driver_shutdown(struct drm_i915_private *i915) +{ + disable_rpm_wakeref_asserts(&i915->runtime_pm); + intel_runtime_pm_disable(&i915->runtime_pm); + + intel_display_driver_shutdown(i915); + + intel_irq_suspend(i915); + + intel_display_driver_shutdown_noirq(i915); + + i915_gem_suspend(i915); + + /* TODO: + * - unify the pci_driver::shutdown sequence here with the + * pci_driver.driver.pm.poweroff,poweroff_late sequence. + * - unify the driver remove and system/runtime suspend sequences with + * the above unified shutdown/poweroff sequence. + */ + + enable_rpm_wakeref_asserts(&i915->runtime_pm); + + intel_runtime_pm_driver_last_release(&i915->runtime_pm); +} + +static bool suspend_to_idle(struct drm_i915_private *dev_priv) +{ +#if IS_ENABLED(CONFIG_ACPI_SLEEP) + if (acpi_target_system_state() < ACPI_STATE_S3) + return true; +#endif + return false; +} + +static void i915_drm_complete(struct drm_device *dev) +{ + struct drm_i915_private *i915 = to_i915(dev); + + intel_pxp_resume_complete(i915->pxp); +} + +static int i915_drm_prepare(struct drm_device *dev) +{ + struct drm_i915_private *i915 = to_i915(dev); + + intel_pxp_suspend_prepare(i915->pxp); + + /* + * NB intel_display_driver_suspend() may issue new requests after we've + * ostensibly marked the GPU as ready-to-sleep here. We need to + * split out that work and pull it forward so that after point, + * the GPU is not woken again. + */ + return i915_gem_backup_suspend(i915); +} + +static int i915_drm_suspend(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = &dev_priv->display; +<<<<<<< +======= + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + pci_power_t opregion_target_state; +>>>>>>> + + disable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + /* We do a lot of poking in a lot of registers, make sure they work + * properly. */ + intel_power_domains_disable(dev_priv); + intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true); + if (HAS_DISPLAY(dev_priv)) { + drm_kms_helper_poll_disable(dev); + intel_display_driver_disable_user_access(dev_priv); + } + + pci_save_state(pdev); + + intel_display_driver_suspend(dev_priv); + + intel_irq_suspend(dev_priv); + + intel_display_driver_suspend_noirq(dev_priv); + + i915_ggtt_suspend(to_gt(dev_priv)->ggtt); + + i9xx_display_sr_save(dev_priv); + + intel_display_driver_suspend_noggtt(display, suspend_to_idle(dev_priv)); + + dev_priv->suspend_count++; + + enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + i915_gem_drain_freed_objects(dev_priv); + + return 0; +} + +static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct intel_gt *gt; + int ret, i; + bool s2idle = !hibernation && suspend_to_idle(dev_priv); + + disable_rpm_wakeref_asserts(rpm); + + intel_pxp_suspend(dev_priv->pxp); + + i915_gem_suspend_late(dev_priv); + + for_each_gt(gt, dev_priv, i) + intel_uncore_suspend(gt->uncore); + + intel_power_domains_suspend(dev_priv, s2idle); + + intel_display_power_suspend_late(dev_priv); + + ret = vlv_suspend_complete(dev_priv); + if (ret) { + drm_err(&dev_priv->drm, "Suspend complete failed: %d\n", ret); + intel_power_domains_resume(dev_priv); + + goto out; + } + + pci_disable_device(pdev); + /* + * During hibernation on some platforms the BIOS may try to access + * the device even though it's already in D3 and hang the machine. So + * leave the device in D0 on those platforms and hope the BIOS will + * power down the device properly. The issue was seen on multiple old + * GENs with different BIOS vendors, so having an explicit blacklist + * is inpractical; apply the workaround on everything pre GEN6. The + * platforms where the issue was seen: + * Lenovo Thinkpad X301, X61s, X60, T60, X41 + * Fujitsu FSC S7110 + * Acer Aspire 1830T + */ + if (!(hibernation && GRAPHICS_VER(dev_priv) < 6)) + pci_set_power_state(pdev, PCI_D3hot); + +out: + enable_rpm_wakeref_asserts(rpm); + if (!dev_priv->uncore.user_forcewake_count) + intel_runtime_pm_driver_release(rpm); + + return ret; +} + +int i915_driver_suspend_switcheroo(struct drm_i915_private *i915, + pm_message_t state) +{ + int error; + + if (drm_WARN_ON_ONCE(&i915->drm, state.event != PM_EVENT_SUSPEND && + state.event != PM_EVENT_FREEZE)) + return -EINVAL; + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + error = i915_drm_suspend(&i915->drm); + if (error) + return error; + + return i915_drm_suspend_late(&i915->drm, false); +} + +static int i915_drm_resume(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_display *display = &dev_priv->display; + struct intel_gt *gt; + int ret, i; + + disable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + ret = i915_pcode_init(dev_priv); + if (ret) + return ret; + + sanitize_gpu(dev_priv); + + ret = i915_ggtt_enable_hw(dev_priv); + if (ret) + drm_err(&dev_priv->drm, "failed to re-enable GGTT\n"); + + i915_ggtt_resume(to_gt(dev_priv)->ggtt); + + for_each_gt(gt, dev_priv, i) + if (GRAPHICS_VER(gt->i915) >= 8) + setup_private_pat(gt); + + /* Must be called after GGTT is resumed. */ + intel_dpt_resume(dev_priv); + + intel_dmc_resume(display); + + i9xx_display_sr_restore(dev_priv); + + intel_vga_redisable(display); + + intel_gmbus_reset(dev_priv); + + intel_pps_unlock_regs_wa(display); + + intel_init_pch_refclk(dev_priv); + + /* + * Interrupts have to be enabled before any batches are run. If not the + * GPU will hang. i915_gem_init_hw() will initiate batches to + * update/restore the context. + * + * drm_mode_config_reset() needs AUX interrupts. + * + * Modeset enabling in intel_display_driver_init_hw() also needs working + * interrupts. + */ + intel_irq_resume(dev_priv); + + if (HAS_DISPLAY(dev_priv)) + drm_mode_config_reset(dev); + + i915_gem_resume(dev_priv); + + intel_display_driver_init_hw(dev_priv); + + intel_clock_gating_init(dev_priv); + + if (HAS_DISPLAY(dev_priv)) + intel_display_driver_resume_access(dev_priv); + + intel_hpd_init(dev_priv); + + intel_display_driver_resume(dev_priv); + + if (HAS_DISPLAY(dev_priv)) { + intel_display_driver_enable_user_access(dev_priv); + drm_kms_helper_poll_enable(dev); + } + intel_hpd_poll_disable(dev_priv); + + intel_opregion_resume(display); + + intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false); + + intel_power_domains_enable(dev_priv); + + intel_gvt_resume(dev_priv); + + enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + return 0; +} + +static int i915_drm_resume_early(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct intel_gt *gt; + int ret, i; + + /* + * We have a resume ordering issue with the snd-hda driver also + * requiring our device to be power up. Due to the lack of a + * parent/child relationship we currently solve this with an early + * resume hook. + * + * FIXME: This should be solved with a special hdmi sink device or + * similar so that power domains can be employed. + */ + + /* + * Note that we need to set the power state explicitly, since we + * powered off the device during freeze and the PCI core won't power + * it back up for us during thaw. Powering off the device during + * freeze is not a hard requirement though, and during the + * suspend/resume phases the PCI core makes sure we get here with the + * device powered on. So in case we change our freeze logic and keep + * the device powered we can also remove the following set power state + * call. + */ + ret = pci_set_power_state(pdev, PCI_D0); + if (ret) { + drm_err(&dev_priv->drm, + "failed to set PCI D0 power state (%d)\n", ret); + return ret; + } + + /* + * Note that pci_enable_device() first enables any parent bridge + * device and only then sets the power state for this device. The + * bridge enabling is a nop though, since bridge devices are resumed + * first. The order of enabling power and enabling the device is + * imposed by the PCI core as described above, so here we preserve the + * same order for the freeze/thaw phases. + * + * TODO: eventually we should remove pci_disable_device() / + * pci_enable_enable_device() from suspend/resume. Due to how they + * depend on the device enable refcount we can't anyway depend on them + * disabling/enabling the device. + */ + if (pci_enable_device(pdev)) + return -EIO; + + pci_set_master(pdev); + + disable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + ret = vlv_resume_prepare(dev_priv, false); + if (ret) + drm_err(&dev_priv->drm, + "Resume prepare failed: %d, continuing anyway\n", ret); + + for_each_gt(gt, dev_priv, i) + intel_gt_resume_early(gt); + + intel_display_power_resume_early(dev_priv); + + intel_power_domains_resume(dev_priv); + + enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); + + return ret; +} + +int i915_driver_resume_switcheroo(struct drm_i915_private *i915) +{ + int ret; + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + ret = i915_drm_resume_early(&i915->drm); + if (ret) + return ret; + + return i915_drm_resume(&i915->drm); +} + +static int i915_pm_prepare(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (!i915) { + dev_err(kdev, "DRM not initialized, aborting suspend.\n"); + return -ENODEV; + } + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_prepare(&i915->drm); +} + +static int i915_pm_suspend(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (!i915) { + dev_err(kdev, "DRM not initialized, aborting suspend.\n"); + return -ENODEV; + } + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_suspend(&i915->drm); +} + +static int i915_pm_suspend_late(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + /* + * We have a suspend ordering issue with the snd-hda driver also + * requiring our device to be power up. Due to the lack of a + * parent/child relationship we currently solve this with an late + * suspend hook. + * + * FIXME: This should be solved with a special hdmi sink device or + * similar so that power domains can be employed. + */ + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_suspend_late(&i915->drm, false); +} + +static int i915_pm_poweroff_late(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_suspend_late(&i915->drm, true); +} + +static int i915_pm_resume_early(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_resume_early(&i915->drm); +} + +static int i915_pm_resume(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_resume(&i915->drm); +} + +static void i915_pm_complete(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + + if (i915->drm.switch_power_state == DRM_SWITCH_POWER_OFF) + return; + + i915_drm_complete(&i915->drm); +} + +/* freeze: before creating the hibernation_image */ +static int i915_pm_freeze(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + int ret; + + if (i915->drm.switch_power_state != DRM_SWITCH_POWER_OFF) { + ret = i915_drm_suspend(&i915->drm); + if (ret) + return ret; + } + + ret = i915_gem_freeze(i915); + if (ret) + return ret; + + return 0; +} + +static int i915_pm_freeze_late(struct device *kdev) +{ + struct drm_i915_private *i915 = kdev_to_i915(kdev); + int ret; + + if (i915->drm.switch_power_state != DRM_SWITCH_POWER_OFF) { + ret = i915_drm_suspend_late(&i915->drm, true); + if (ret) + return ret; + } + + ret = i915_gem_freeze_late(i915); + if (ret) + return ret; + + return 0; +} + +/* thaw: called after creating the hibernation image, but before turning off. */ +static int i915_pm_thaw_early(struct device *kdev) +{ + return i915_pm_resume_early(kdev); +} + +static int i915_pm_thaw(struct device *kdev) +{ + return i915_pm_resume(kdev); +} + +/* restore: called after loading the hibernation image. */ +static int i915_pm_restore_early(struct device *kdev) +{ + return i915_pm_resume_early(kdev); +} + +static int i915_pm_restore(struct device *kdev) +{ + return i915_pm_resume(kdev); +} + +static int intel_runtime_suspend(struct device *kdev) +{ + struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct intel_display *display = &dev_priv->display; + struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; + struct intel_gt *gt; + int ret, i; + + if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) + return -ENODEV; + + drm_dbg(&dev_priv->drm, "Suspending device\n"); + + disable_rpm_wakeref_asserts(rpm); + + /* + * We are safe here against re-faults, since the fault handler takes + * an RPM reference. + */ + i915_gem_runtime_suspend(dev_priv); + + intel_pxp_runtime_suspend(dev_priv->pxp); + + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_suspend(gt); + + intel_irq_suspend(dev_priv); + + for_each_gt(gt, dev_priv, i) + intel_uncore_suspend(gt->uncore); + + intel_display_power_suspend(dev_priv); + + ret = vlv_suspend_complete(dev_priv); + if (ret) { + drm_err(&dev_priv->drm, + "Runtime suspend failed, disabling it (%d)\n", ret); + intel_uncore_runtime_resume(&dev_priv->uncore); + + intel_irq_resume(dev_priv); + + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_resume(gt); + + enable_rpm_wakeref_asserts(rpm); + + return ret; + } + + enable_rpm_wakeref_asserts(rpm); + intel_runtime_pm_driver_release(rpm); + + if (intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore)) + drm_err(&dev_priv->drm, + "Unclaimed access detected prior to suspending\n"); + + /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM. + */ + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_disable(root_pdev); + + /* + * FIXME: We really should find a document that references the arguments + * used below! + */ + if (IS_BROADWELL(dev_priv)) { + /* + * On Broadwell, if we use PCI_D1 the PCH DDI ports will stop + * being detected, and the call we do at intel_runtime_resume() + * won't be able to restore them. Since PCI_D3hot matches the + * actual specification and appears to be working, use it. + */ + intel_opregion_notify_adapter(display, PCI_D3hot); + } else { + /* + * current versions of firmware which depend on this opregion + * notification have repurposed the D1 definition to mean + * "runtime suspended" vs. what you would normally expect (D3) + * to distinguish it from notifications that might be sent via + * the suspend path. + */ + intel_opregion_notify_adapter(display, PCI_D1); + } + + assert_forcewakes_inactive(&dev_priv->uncore); + + if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) + intel_hpd_poll_enable(dev_priv); + + drm_dbg(&dev_priv->drm, "Device suspended\n"); + return 0; +} + +static int intel_runtime_resume(struct device *kdev) +{ + struct drm_i915_private *dev_priv = kdev_to_i915(kdev); + struct intel_display *display = &dev_priv->display; + struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; + struct intel_gt *gt; + int ret, i; + + if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) + return -ENODEV; + + drm_dbg(&dev_priv->drm, "Resuming device\n"); + + drm_WARN_ON_ONCE(&dev_priv->drm, atomic_read(&rpm->wakeref_count)); + disable_rpm_wakeref_asserts(rpm); + + intel_opregion_notify_adapter(display, PCI_D0); + + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_enable(root_pdev); + + if (intel_uncore_unclaimed_mmio(&dev_priv->uncore)) + drm_dbg(&dev_priv->drm, + "Unclaimed access during suspend, bios?\n"); + + intel_display_power_resume(dev_priv); + + ret = vlv_resume_prepare(dev_priv, true); + + for_each_gt(gt, dev_priv, i) + intel_uncore_runtime_resume(gt->uncore); + + intel_irq_resume(dev_priv); + + /* + * No point of rolling back things in case of an error, as the best + * we can do is to hope that things will still work (and disable RPM). + */ + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_resume(gt); + + intel_pxp_runtime_resume(dev_priv->pxp); + + /* + * On VLV/CHV display interrupts are part of the display + * power well, so hpd is reinitialized from there. For + * everyone else do it here. + */ + if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) { + intel_hpd_init(dev_priv); + intel_hpd_poll_disable(dev_priv); + } + + skl_watermark_ipc_update(dev_priv); + + enable_rpm_wakeref_asserts(rpm); + + if (ret) + drm_err(&dev_priv->drm, + "Runtime resume failed, disabling it (%d)\n", ret); + else + drm_dbg(&dev_priv->drm, "Device resumed\n"); + + return ret; +} + +const struct dev_pm_ops i915_pm_ops = { + /* + * S0ix (via system suspend) and S3 event handlers [PMSG_SUSPEND, + * PMSG_RESUME] + */ + .prepare = i915_pm_prepare, + .suspend = i915_pm_suspend, + .suspend_late = i915_pm_suspend_late, + .resume_early = i915_pm_resume_early, + .resume = i915_pm_resume, + .complete = i915_pm_complete, + + /* + * S4 event handlers + * @freeze, @freeze_late : called (1) before creating the + * hibernation image [PMSG_FREEZE] and + * (2) after rebooting, before restoring + * the image [PMSG_QUIESCE] + * @thaw, @thaw_early : called (1) after creating the hibernation + * image, before writing it [PMSG_THAW] + * and (2) after failing to create or + * restore the image [PMSG_RECOVER] + * @poweroff, @poweroff_late: called after writing the hibernation + * image, before rebooting [PMSG_HIBERNATE] + * @restore, @restore_early : called after rebooting and restoring the + * hibernation image [PMSG_RESTORE] + */ + .freeze = i915_pm_freeze, + .freeze_late = i915_pm_freeze_late, + .thaw_early = i915_pm_thaw_early, + .thaw = i915_pm_thaw, + .poweroff = i915_pm_suspend, + .poweroff_late = i915_pm_poweroff_late, + .restore_early = i915_pm_restore_early, + .restore = i915_pm_restore, + + /* S0ix (via runtime suspend) event handlers */ + .runtime_suspend = intel_runtime_suspend, + .runtime_resume = intel_runtime_resume, +}; + +static const struct file_operations i915_driver_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .release = drm_release_noglobal, + .unlocked_ioctl = drm_ioctl, + .mmap = i915_gem_mmap, + .poll = drm_poll, + .read = drm_read, + .compat_ioctl = i915_ioc32_compat_ioctl, + .llseek = noop_llseek, +#ifdef CONFIG_PROC_FS + .show_fdinfo = drm_show_fdinfo, +#endif +}; + +static int +i915_gem_reject_pin_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + return -ENODEV; +} + +static const struct drm_ioctl_desc i915_ioctls[] = { + DRM_IOCTL_DEF_DRV(I915_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_FLUSH, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_FLIP, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_BATCHBUFFER, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_IRQ_EMIT, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_IRQ_WAIT, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_SETPARAM, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_ALLOC, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_FREE, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_INIT_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_CMDBUFFER, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_DESTROY_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_SET_VBLANK_PIPE, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GET_VBLANK_PIPE, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_VBLANK_SWAP, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_HWS_ADDR, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER, drm_invalid_op, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2_WR, i915_gem_execbuffer2_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHING, i915_gem_set_caching_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHING, i915_gem_get_caching_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CREATE_EXT, i915_gem_create_ext_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_OFFSET, i915_gem_mmap_offset_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_GET_TILING, i915_gem_get_tiling_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id_ioctl, 0), + DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image_ioctl, DRM_MASTER), + DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs_ioctl, DRM_MASTER), + DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey_ioctl, DRM_MASTER), + DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER), + DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE_EXT, i915_gem_context_create_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_gem_context_reset_stats_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_PERF_OPEN, i915_perf_open_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_PERF_ADD_CONFIG, i915_perf_add_config_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_PERF_REMOVE_CONFIG, i915_perf_remove_config_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_QUERY, i915_query_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_VM_CREATE, i915_gem_vm_create_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_VM_DESTROY, i915_gem_vm_destroy_ioctl, DRM_RENDER_ALLOW), +}; + +/* + * Interface history: + * + * 1.1: Original. + * 1.2: Add Power Management + * 1.3: Add vblank support + * 1.4: Fix cmdbuffer path, add heap destroy + * 1.5: Add vblank pipe configuration + * 1.6: - New ioctl for scheduling buffer swaps on vertical blank + * - Support vertical blank on secondary display pipe + */ +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 6 +#define DRIVER_PATCHLEVEL 0 + +static const struct drm_driver i915_drm_driver = { + /* Don't use MTRRs here; the Xserver or userspace app should + * deal with them for Intel hardware. + */ + .driver_features = + DRIVER_GEM | + DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ | + DRIVER_SYNCOBJ_TIMELINE, + .release = i915_driver_release, + .open = i915_driver_open, + .postclose = i915_driver_postclose, + .show_fdinfo = PTR_IF(IS_ENABLED(CONFIG_PROC_FS), i915_drm_client_fdinfo), + + .gem_prime_import = i915_gem_prime_import, + + .dumb_create = i915_gem_dumb_create, + .dumb_map_offset = i915_gem_dumb_mmap_offset, + + .ioctls = i915_ioctls, + .num_ioctls = ARRAY_SIZE(i915_ioctls), + .fops = &i915_driver_fops, + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + .patchlevel = DRIVER_PATCHLEVEL, +}; |