/* * Copyright 2015 Advanced Micro Devices, Inc. * * 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, sublicense, * 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 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 NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. * */ /** * DOC: Overview * * The GPU scheduler provides entities which allow userspace to push jobs * into software queues which are then scheduled on a hardware run queue. * The software queues have a priority among them. The scheduler selects the entities * from the run queue using a FIFO. The scheduler provides dependency handling * features among jobs. The driver is supposed to provide callback functions for * backend operations to the scheduler like submitting a job to hardware run queue, * returning the dependencies of a job etc. * * The organisation of the scheduler is the following: * * 1. Each hw run queue has one scheduler * 2. Each scheduler has multiple run queues with different priorities * (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL) * 3. Each scheduler run queue has a queue of entities to schedule * 4. Entities themselves maintain a queue of jobs that will be scheduled on * the hardware. * * The jobs in a entity are always scheduled in the order that they were pushed. * * Note that once a job was taken from the entities queue and pushed to the * hardware, i.e. the pending queue, the entity must not be referenced anymore * through the jobs entity pointer. */ /** * DOC: Flow Control * * The DRM GPU scheduler provides a flow control mechanism to regulate the rate * in which the jobs fetched from scheduler entities are executed. * * In this context the &drm_gpu_scheduler keeps track of a driver specified * credit limit representing the capacity of this scheduler and a credit count; * every &drm_sched_job carries a driver specified number of credits. * * Once a job is executed (but not yet finished), the job's credits contribute * to the scheduler's credit count until the job is finished. If by executing * one more job the scheduler's credit count would exceed the scheduler's * credit limit, the job won't be executed. Instead, the scheduler will wait * until the credit count has decreased enough to not overflow its credit limit. * This implies waiting for previously executed jobs. * * Optionally, drivers may register a callback (update_job_credits) provided by * struct drm_sched_backend_ops to update the job's credits dynamically. The * scheduler executes this callback every time the scheduler considers a job for * execution and subsequently checks whether the job fits the scheduler's credit * limit. */ #include <linux/wait.h> #include <linux/sched.h> #include <linux/completion.h> #include <linux/dma-resv.h> #include <uapi/linux/sched/types.h> #include <drm/drm_print.h> #include <drm/drm_gem.h> #include <drm/drm_syncobj.h> #include <drm/gpu_scheduler.h> #include <drm/spsc_queue.h> #define CREATE_TRACE_POINTS #include "gpu_scheduler_trace.h" #define to_drm_sched_job(sched_job) … int drm_sched_policy = …; /** * DOC: sched_policy (int) * Used to override default entities scheduling policy in a run queue. */ MODULE_PARM_DESC(…) …; module_param_named(sched_policy, drm_sched_policy, int, 0444); static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_can_queue -- Can we queue more to the hardware? * @sched: scheduler instance * @entity: the scheduler entity * * Return true if we can push at least one more job from @entity, false * otherwise. */ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { … } static __always_inline bool drm_sched_entity_compare_before(struct rb_node *a, const struct rb_node *b) { … } static inline void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *entity) { … } void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts) { … } /** * drm_sched_rq_init - initialize a given run queue struct * * @sched: scheduler instance to associate with this run queue * @rq: scheduler run queue * * Initializes a scheduler runqueue. */ static void drm_sched_rq_init(struct drm_gpu_scheduler *sched, struct drm_sched_rq *rq) { … } /** * drm_sched_rq_add_entity - add an entity * * @rq: scheduler run queue * @entity: scheduler entity * * Adds a scheduler entity to the run queue. */ void drm_sched_rq_add_entity(struct drm_sched_rq *rq, struct drm_sched_entity *entity) { … } /** * drm_sched_rq_remove_entity - remove an entity * * @rq: scheduler run queue * @entity: scheduler entity * * Removes a scheduler entity from the run queue. */ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, struct drm_sched_entity *entity) { … } /** * drm_sched_rq_select_entity_rr - Select an entity which could provide a job to run * * @sched: the gpu scheduler * @rq: scheduler run queue to check. * * Try to find the next ready entity. * * Return an entity if one is found; return an error-pointer (!NULL) if an * entity was ready, but the scheduler had insufficient credits to accommodate * its job; return NULL, if no ready entity was found. */ static struct drm_sched_entity * drm_sched_rq_select_entity_rr(struct drm_gpu_scheduler *sched, struct drm_sched_rq *rq) { … } /** * drm_sched_rq_select_entity_fifo - Select an entity which provides a job to run * * @sched: the gpu scheduler * @rq: scheduler run queue to check. * * Find oldest waiting ready entity. * * Return an entity if one is found; return an error-pointer (!NULL) if an * entity was ready, but the scheduler had insufficient credits to accommodate * its job; return NULL, if no ready entity was found. */ static struct drm_sched_entity * drm_sched_rq_select_entity_fifo(struct drm_gpu_scheduler *sched, struct drm_sched_rq *rq) { … } /** * drm_sched_run_job_queue - enqueue run-job work * @sched: scheduler instance */ static void drm_sched_run_job_queue(struct drm_gpu_scheduler *sched) { … } /** * __drm_sched_run_free_queue - enqueue free-job work * @sched: scheduler instance */ static void __drm_sched_run_free_queue(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_run_free_queue - enqueue free-job work if ready * @sched: scheduler instance */ static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_job_done - complete a job * @s_job: pointer to the job which is done * * Finish the job's fence and wake up the worker thread. */ static void drm_sched_job_done(struct drm_sched_job *s_job, int result) { … } /** * drm_sched_job_done_cb - the callback for a done job * @f: fence * @cb: fence callbacks */ static void drm_sched_job_done_cb(struct dma_fence *f, struct dma_fence_cb *cb) { … } /** * drm_sched_start_timeout - start timeout for reset worker * * @sched: scheduler instance to start the worker for * * Start the timeout for the given scheduler. */ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) { … } static void drm_sched_start_timeout_unlocked(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_tdr_queue_imm: - immediately start job timeout handler * * @sched: scheduler for which the timeout handling should be started. * * Start timeout handling immediately for the named scheduler. */ void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_fault - immediately start timeout handler * * @sched: scheduler where the timeout handling should be started. * * Start timeout handling immediately when the driver detects a hardware fault. */ void drm_sched_fault(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_suspend_timeout - Suspend scheduler job timeout * * @sched: scheduler instance for which to suspend the timeout * * Suspend the delayed work timeout for the scheduler. This is done by * modifying the delayed work timeout to an arbitrary large value, * MAX_SCHEDULE_TIMEOUT in this case. * * Returns the timeout remaining * */ unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_resume_timeout - Resume scheduler job timeout * * @sched: scheduler instance for which to resume the timeout * @remaining: remaining timeout * * Resume the delayed work timeout for the scheduler. */ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched, unsigned long remaining) { … } EXPORT_SYMBOL(…); static void drm_sched_job_begin(struct drm_sched_job *s_job) { … } static void drm_sched_job_timedout(struct work_struct *work) { … } /** * drm_sched_stop - stop the scheduler * * @sched: scheduler instance * @bad: job which caused the time out * * Stop the scheduler and also removes and frees all completed jobs. * Note: bad job will not be freed as it might be used later and so it's * callers responsibility to release it manually if it's not part of the * pending list any more. * */ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) { … } EXPORT_SYMBOL(…); /** * drm_sched_start - recover jobs after a reset * * @sched: scheduler instance * @full_recovery: proceed with complete sched restart * */ void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery) { … } EXPORT_SYMBOL(…); /** * drm_sched_resubmit_jobs - Deprecated, don't use in new code! * * @sched: scheduler instance * * Re-submitting jobs was a concept AMD came up as cheap way to implement * recovery after a job timeout. * * This turned out to be not working very well. First of all there are many * problem with the dma_fence implementation and requirements. Either the * implementation is risking deadlocks with core memory management or violating * documented implementation details of the dma_fence object. * * Drivers can still save and restore their state for recovery operations, but * we shouldn't make this a general scheduler feature around the dma_fence * interface. */ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_init - init a scheduler job * @job: scheduler job to init * @entity: scheduler entity to use * @credits: the number of credits this job contributes to the schedulers * credit limit * @owner: job owner for debugging * * Refer to drm_sched_entity_push_job() documentation * for locking considerations. * * Drivers must make sure drm_sched_job_cleanup() if this function returns * successfully, even when @job is aborted before drm_sched_job_arm() is called. * * WARNING: amdgpu abuses &drm_sched.ready to signal when the hardware * has died, which can mean that there's no valid runqueue for a @entity. * This function returns -ENOENT in this case (which probably should be -EIO as * a more meanigful return value). * * Returns 0 for success, negative error code otherwise. */ int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, u32 credits, void *owner) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_arm - arm a scheduler job for execution * @job: scheduler job to arm * * This arms a scheduler job for execution. Specifically it initializes the * &drm_sched_job.s_fence of @job, so that it can be attached to struct dma_resv * or other places that need to track the completion of this job. * * Refer to drm_sched_entity_push_job() documentation for locking * considerations. * * This can only be called if drm_sched_job_init() succeeded. */ void drm_sched_job_arm(struct drm_sched_job *job) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_add_dependency - adds the fence as a job dependency * @job: scheduler job to add the dependencies to * @fence: the dma_fence to add to the list of dependencies. * * Note that @fence is consumed in both the success and error cases. * * Returns: * 0 on success, or an error on failing to expand the array. */ int drm_sched_job_add_dependency(struct drm_sched_job *job, struct dma_fence *fence) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_add_syncobj_dependency - adds a syncobj's fence as a job dependency * @job: scheduler job to add the dependencies to * @file: drm file private pointer * @handle: syncobj handle to lookup * @point: timeline point * * This adds the fence matching the given syncobj to @job. * * Returns: * 0 on success, or an error on failing to expand the array. */ int drm_sched_job_add_syncobj_dependency(struct drm_sched_job *job, struct drm_file *file, u32 handle, u32 point) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_add_resv_dependencies - add all fences from the resv to the job * @job: scheduler job to add the dependencies to * @resv: the dma_resv object to get the fences from * @usage: the dma_resv_usage to use to filter the fences * * This adds all fences matching the given usage from @resv to @job. * Must be called with the @resv lock held. * * Returns: * 0 on success, or an error on failing to expand the array. */ int drm_sched_job_add_resv_dependencies(struct drm_sched_job *job, struct dma_resv *resv, enum dma_resv_usage usage) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job * dependencies * @job: scheduler job to add the dependencies to * @obj: the gem object to add new dependencies from. * @write: whether the job might write the object (so we need to depend on * shared fences in the reservation object). * * This should be called after drm_gem_lock_reservations() on your array of * GEM objects used in the job but before updating the reservations with your * own fences. * * Returns: * 0 on success, or an error on failing to expand the array. */ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, struct drm_gem_object *obj, bool write) { … } EXPORT_SYMBOL(…); /** * drm_sched_job_cleanup - clean up scheduler job resources * @job: scheduler job to clean up * * Cleans up the resources allocated with drm_sched_job_init(). * * Drivers should call this from their error unwind code if @job is aborted * before drm_sched_job_arm() is called. * * After that point of no return @job is committed to be executed by the * scheduler, and this function should be called from the * &drm_sched_backend_ops.free_job callback. */ void drm_sched_job_cleanup(struct drm_sched_job *job) { … } EXPORT_SYMBOL(…); /** * drm_sched_wakeup - Wake up the scheduler if it is ready to queue * @sched: scheduler instance * @entity: the scheduler entity * * Wake up the scheduler if we can queue jobs. */ void drm_sched_wakeup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity) { … } /** * drm_sched_select_entity - Select next entity to process * * @sched: scheduler instance * * Return an entity to process or NULL if none are found. * * Note, that we break out of the for-loop when "entity" is non-null, which can * also be an error-pointer--this assures we don't process lower priority * run-queues. See comments in the respectively called functions. */ static struct drm_sched_entity * drm_sched_select_entity(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_get_finished_job - fetch the next finished job to be destroyed * * @sched: scheduler instance * * Returns the next finished job from the pending list (if there is one) * ready for it to be destroyed. */ static struct drm_sched_job * drm_sched_get_finished_job(struct drm_gpu_scheduler *sched) { … } /** * drm_sched_pick_best - Get a drm sched from a sched_list with the least load * @sched_list: list of drm_gpu_schedulers * @num_sched_list: number of drm_gpu_schedulers in the sched_list * * Returns pointer of the sched with the least load or NULL if none of the * drm_gpu_schedulers are ready */ struct drm_gpu_scheduler * drm_sched_pick_best(struct drm_gpu_scheduler **sched_list, unsigned int num_sched_list) { … } EXPORT_SYMBOL(…); /** * drm_sched_free_job_work - worker to call free_job * * @w: free job work */ static void drm_sched_free_job_work(struct work_struct *w) { … } /** * drm_sched_run_job_work - worker to call run_job * * @w: run job work */ static void drm_sched_run_job_work(struct work_struct *w) { … } /** * drm_sched_init - Init a gpu scheduler instance * * @sched: scheduler instance * @ops: backend operations for this scheduler * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is * allocated and used * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT * @credit_limit: the number of credits this scheduler can hold from all jobs * @hang_limit: number of times to allow a job to hang before dropping it * @timeout: timeout value in jiffies for the scheduler * @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is * used * @score: optional score atomic shared with other schedulers * @name: name used for debugging * @dev: target &struct device * * Return 0 on success, otherwise error code. */ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, struct workqueue_struct *submit_wq, u32 num_rqs, u32 credit_limit, unsigned int hang_limit, long timeout, struct workqueue_struct *timeout_wq, atomic_t *score, const char *name, struct device *dev) { … } EXPORT_SYMBOL(…); /** * drm_sched_fini - Destroy a gpu scheduler * * @sched: scheduler instance * * Tears down and cleans up the scheduler. */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_increase_karma - Update sched_entity guilty flag * * @bad: The job guilty of time out * * Increment on every hang caused by the 'bad' job. If this exceeds the hang * limit of the scheduler then the respective sched entity is marked guilty and * jobs from it will not be scheduled further */ void drm_sched_increase_karma(struct drm_sched_job *bad) { … } EXPORT_SYMBOL(…); /** * drm_sched_wqueue_ready - Is the scheduler ready for submission * * @sched: scheduler instance * * Returns true if submission is ready */ bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_wqueue_stop - stop scheduler submission * * @sched: scheduler instance */ void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…); /** * drm_sched_wqueue_start - start scheduler submission * * @sched: scheduler instance */ void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux