/* * 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. * */ #ifndef _DRM_GPU_SCHEDULER_H_#define _DRM_GPU_SCHEDULER_H_ #include <drm/spsc_queue.h>#include <linux/average.h>#include <linux/dma-fence.h>#include <linux/completion.h>#include <linux/xarray.h>#include <linux/workqueue.h> DECLARE_EWMA(drm_sched_avgtime, 6, 4); #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) /** * DRM_SCHED_FENCE_DONT_PIPELINE - Prevent dependency pipelining * * Setting this flag on a scheduler fence prevents pipelining of jobs depending * on this fence. In other words we always insert a full CPU round trip before * dependent jobs are pushed to the hw queue. */#define DRM_SCHED_FENCE_DONT_PIPELINE DMA_FENCE_FLAG_USER_BITS /** * DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT - A fence deadline hint has been set * * Because we could have a deadline hint can be set before the backing hw * fence is created, we need to keep track of whether a deadline has already * been set. */#define DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT (DMA_FENCE_FLAG_USER_BITS + 1) enum dma_resv_usage;struct dma_resv;struct drm_gem_object; struct drm_gpu_scheduler;struct drm_sched_rq; struct drm_file; /* These are often used as an (initial) index * to an array, and as such should start at 0. */enum drm_sched_priority { DRM_SCHED_PRIORITY_INVALID = -1, /* Internal marker - do not use. */ DRM_SCHED_PRIORITY_KERNEL, DRM_SCHED_PRIORITY_HIGH, DRM_SCHED_PRIORITY_NORMAL, DRM_SCHED_PRIORITY_LOW, DRM_SCHED_PRIORITY_COUNT}; struct drm_sched_entity_stats; /** * struct drm_sched_entity - A wrapper around a job queue (typically * attached to the DRM file_priv). * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on * scheduling policy. */struct drm_sched_entity { /** * @list: * * Used to append this struct to the list of entities in the runqueue * @rq under &drm_sched_rq.entities. * * Protected by &drm_sched_rq.lock of @rq. */ struct list_head list; /** * @lock: * * Lock protecting the run-queue (@rq) to which this entity belongs, * @priority, the list of schedulers (@sched_list, @num_sched_list) and * the @rr_ts field. */ spinlock_t lock; /** * @rq: * * Runqueue on which this entity is currently scheduled. * * FIXME: Locking is very unclear for this. Writers are protected by * @lock, but readers are generally lockless and seem to just race with * not even a READ_ONCE. */ struct drm_sched_rq *rq; /** * @stats: Stats object reference held by the entity and jobs. */ struct drm_sched_entity_stats *stats; /** * @sched_list: * * A list of schedulers (struct drm_gpu_scheduler). Jobs from this entity can * be scheduled on any scheduler on this list. * * This can be modified by calling drm_sched_entity_modify_sched(). * Locking is entirely up to the driver, see the above function for more * details. * * This will be set to NULL if &num_sched_list equals 1 and @rq has been * set already. * * FIXME: This means priority changes through * drm_sched_entity_set_priority() will be lost henceforth in this case. */ struct drm_gpu_scheduler **sched_list; /** * @num_sched_list: * * Number of drm_gpu_schedulers in the @sched_list. */ unsigned int num_sched_list; /** * @priority: * * Priority of the entity. This can be modified by calling * drm_sched_entity_set_priority(). Protected by @lock. */ enum drm_sched_priority priority; /** * @rq_priority: Run-queue priority */ enum drm_sched_priority rq_priority; /** * @rr_ts: * * Fake timestamp of the last popped job from the entity. */ ktime_t rr_ts; /** * @job_queue: the list of jobs of this entity. */ struct spsc_queue job_queue; /** * @fence_seq: * * A linearly increasing seqno incremented with each new * &drm_sched_fence which is part of the entity. * * FIXME: Callers of drm_sched_job_arm() need to ensure correct locking, * this doesn't need to be atomic. */ atomic_t fence_seq; /** * @fence_context: * * A unique context for all the fences which belong to this entity. The * &drm_sched_fence.scheduled uses the fence_context but * &drm_sched_fence.finished uses fence_context + 1. */ uint64_t fence_context; /** * @dependency: * * The dependency fence of the job which is on the top of the job queue. */ struct dma_fence *dependency; /** * @cb: * * Callback for the dependency fence above. */ struct dma_fence_cb cb; /** * @guilty: * * Points to entities' guilty. */ atomic_t *guilty; /** * @last_scheduled: * * Points to the finished fence of the last scheduled job. Only written * by drm_sched_entity_pop_job(). Can be accessed locklessly from * drm_sched_job_arm() if the queue is empty. */ struct dma_fence __rcu *last_scheduled; /** * @last_user: last group leader pushing a job into the entity. */ struct task_struct *last_user; /** * @stopped: * * Marks the enity as removed from rq and destined for * termination. This is set by calling drm_sched_entity_flush(). */ bool stopped; /** * @entity_idle: * * Signals when entity is not in use, used to sequence entity cleanup in * drm_sched_entity_fini(). */ struct completion entity_idle; /** * @oldest_job_waiting: * * Marks earliest job waiting in SW queue */ ktime_t oldest_job_waiting; /** * @rb_tree_node: * * The node used to insert this entity into time based priority queue */ struct rb_node rb_tree_node; }; /** * struct drm_sched_rq - queue of entities to be scheduled. * * @sched: the scheduler to which this rq belongs to. * @lock: protects @entities, @rb_tree_root, @rr_ts and @head_prio. * @rr_ts: monotonically incrementing fake timestamp for RR mode. * @entities: list of the entities to be scheduled. * @rb_tree_root: root of time based priority queue of entities for FIFO scheduling * @head_prio: priority of the top tree element. * * Run queue is a set of entities scheduling command submissions for * one specific ring. It implements the scheduling policy that selects * the next entity to emit commands from. */struct drm_sched_rq { struct drm_gpu_scheduler *sched; spinlock_t lock; /* Following members are protected by the @lock: */ ktime_t rr_ts; struct list_head entities; struct rb_root_cached rb_tree_root; enum drm_sched_priority head_prio;}; /** * struct drm_sched_fence - fences corresponding to the scheduling of a job. */struct drm_sched_fence { /** * @scheduled: this fence is what will be signaled by the scheduler * when the job is scheduled. */ struct dma_fence scheduled; /** * @finished: this fence is what will be signaled by the scheduler * when the job is completed. * * When setting up an out fence for the job, you should use * this, since it's available immediately upon * drm_sched_job_init(), and the fence returned by the driver * from run_job() won't be created until the dependencies have * resolved. */ struct dma_fence finished; /** * @deadline: deadline set on &drm_sched_fence.finished which * potentially needs to be propagated to &drm_sched_fence.parent */ ktime_t deadline; /** * @parent: the fence returned by &drm_sched_backend_ops.run_job * when scheduling the job on hardware. We signal the * &drm_sched_fence.finished fence once parent is signalled. */ struct dma_fence *parent; /** * @sched: the scheduler instance to which the job having this struct * belongs to. */ struct drm_gpu_scheduler *sched; /** * @lock: the lock used by the scheduled and the finished fences. */ spinlock_t lock; /** * @owner: job owner for debugging */ void *owner; /** * @drm_client_id: * * The client_id of the drm_file which owns the job. */ uint64_t drm_client_id;}; struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); /** * struct drm_sched_job - A job to be run by an entity. * * @queue_node: used to append this struct to the queue of jobs in an entity. * @list: a job participates in a "pending" and "done" lists. * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. * @credits: the number of credits this job contributes to the scheduler * @work: Helper to reschedule job kill to different context. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not * be scheduled further. * @s_priority: the priority of the job. * @entity: the entity to which this job belongs. * @cb: the callback for the parent fence in s_fence. * * A job is created by the driver using drm_sched_job_init(), and * should call drm_sched_entity_push_job() once it wants the scheduler * to schedule the job. */struct drm_sched_job { /** * @submit_ts: * * When the job was pushed into the entity queue. */ ktime_t submit_ts; /** * @sched: * * The scheduler this job is or will be scheduled on. Gets set by * drm_sched_job_arm(). Valid until drm_sched_backend_ops.free_job() * has finished. */ struct drm_gpu_scheduler *sched; struct drm_sched_fence *s_fence; struct drm_sched_entity *entity; /** * @entity_stats: Stats object reference held by the job and entity. */ struct drm_sched_entity_stats *entity_stats; enum drm_sched_priority s_priority; u32 credits; /** @last_dependency: tracks @dependencies as they signal */ unsigned int last_dependency; atomic_t karma; struct spsc_node queue_node; struct list_head list; /* * work is used only after finish_cb has been used and will not be * accessed anymore. */ union { struct dma_fence_cb finish_cb; struct work_struct work; }; struct dma_fence_cb cb; /** * @dependencies: * * Contains the dependencies as struct dma_fence for this job, see * drm_sched_job_add_dependency() and * drm_sched_job_add_implicit_dependencies(). */ struct xarray dependencies;}; /** * enum drm_gpu_sched_stat - the scheduler's status * * @DRM_GPU_SCHED_STAT_NONE: Reserved. Do not use. * @DRM_GPU_SCHED_STAT_RESET: The GPU hung and successfully reset. * @DRM_GPU_SCHED_STAT_ENODEV: Error: Device is not available anymore. * @DRM_GPU_SCHED_STAT_NO_HANG: Contrary to scheduler's assumption, the GPU * did not hang and is still running. */enum drm_gpu_sched_stat { DRM_GPU_SCHED_STAT_NONE, DRM_GPU_SCHED_STAT_RESET, DRM_GPU_SCHED_STAT_ENODEV, DRM_GPU_SCHED_STAT_NO_HANG,}; /** * struct drm_sched_backend_ops - Define the backend operations * called by the scheduler * * These functions should be implemented in the driver side. */struct drm_sched_backend_ops { /** * @prepare_job: * * Called when the scheduler is considering scheduling this job next, to * get another struct dma_fence for this job to block on. Once it * returns NULL, run_job() may be called. * * Can be NULL if no additional preparation to the dependencies are * necessary. Skipped when jobs are killed instead of run. */ struct dma_fence *(*prepare_job)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); /** * @run_job: Called to execute the job once all of the dependencies * have been resolved. * * @sched_job: the job to run * * The deprecated drm_sched_resubmit_jobs() (called by &struct * drm_sched_backend_ops.timedout_job) can invoke this again with the * same parameters. Using this is discouraged because it violates * dma_fence rules, notably dma_fence_init() has to be called on * already initialized fences for a second time. Moreover, this is * dangerous because attempts to allocate memory might deadlock with * memory management code waiting for the reset to complete. * * TODO: Document what drivers should do / use instead. * * This method is called in a workqueue context - either from the * submit_wq the driver passed through drm_sched_init(), or, if the * driver passed NULL, a separate, ordered workqueue the scheduler * allocated. * * Note that the scheduler expects to 'inherit' its own reference to * this fence from the callback. It does not invoke an extra * dma_fence_get() on it. Consequently, this callback must take a * reference for the scheduler, and additional ones for the driver's * respective needs. * * Return: * * On success: dma_fence the driver must signal once the hardware has * completed the job ("hardware fence"). * * On failure: NULL or an ERR_PTR. */ struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); /** * @timedout_job: Called when a job has taken too long to execute, * to trigger GPU recovery. * * @sched_job: The job that has timed out * * Drivers typically issue a reset to recover from GPU hangs. * This procedure looks very different depending on whether a firmware * or a hardware scheduler is being used. * * For a FIRMWARE SCHEDULER, each ring has one scheduler, and eachLines 1–500 of 789. Load more
/* * 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. * */ #ifndef _DRM_GPU_SCHEDULER_H_ #define _DRM_GPU_SCHEDULER_H_ #include <drm/spsc_queue.h> #include <linux/average.h> #include <linux/dma-fence.h> #include <linux/completion.h> #include <linux/xarray.h> #include <linux/workqueue.h> DECLARE_EWMA(drm_sched_avgtime, 6, 4); #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) /** * DRM_SCHED_FENCE_DONT_PIPELINE - Prevent dependency pipelining * * Setting this flag on a scheduler fence prevents pipelining of jobs depending * on this fence. In other words we always insert a full CPU round trip before * dependent jobs are pushed to the hw queue. */ #define DRM_SCHED_FENCE_DONT_PIPELINE DMA_FENCE_FLAG_USER_BITS /** * DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT - A fence deadline hint has been set * * Because we could have a deadline hint can be set before the backing hw * fence is created, we need to keep track of whether a deadline has already * been set. */ #define DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT (DMA_FENCE_FLAG_USER_BITS + 1) enum dma_resv_usage; struct dma_resv; struct drm_gem_object; struct drm_gpu_scheduler; struct drm_sched_rq; struct drm_file; /* These are often used as an (initial) index * to an array, and as such should start at 0. */ enum drm_sched_priority { DRM_SCHED_PRIORITY_INVALID = -1, /* Internal marker - do not use. */ DRM_SCHED_PRIORITY_KERNEL, DRM_SCHED_PRIORITY_HIGH, DRM_SCHED_PRIORITY_NORMAL, DRM_SCHED_PRIORITY_LOW, DRM_SCHED_PRIORITY_COUNT }; struct drm_sched_entity_stats; /** * struct drm_sched_entity - A wrapper around a job queue (typically * attached to the DRM file_priv). * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on * scheduling policy. */ struct drm_sched_entity { /** * @list: * * Used to append this struct to the list of entities in the runqueue * @rq under &drm_sched_rq.entities. * * Protected by &drm_sched_rq.lock of @rq. */ struct list_head list; /** * @lock: * * Lock protecting the run-queue (@rq) to which this entity belongs, * @priority, the list of schedulers (@sched_list, @num_sched_list) and * the @rr_ts field. */ spinlock_t lock; /** * @rq: * * Runqueue on which this entity is currently scheduled. * * FIXME: Locking is very unclear for this. Writers are protected by * @lock, but readers are generally lockless and seem to just race with * not even a READ_ONCE. */ struct drm_sched_rq *rq; /** * @stats: Stats object reference held by the entity and jobs. */ struct drm_sched_entity_stats *stats; /** * @sched_list: * * A list of schedulers (struct drm_gpu_scheduler). Jobs from this entity can * be scheduled on any scheduler on this list. * * This can be modified by calling drm_sched_entity_modify_sched(). * Locking is entirely up to the driver, see the above function for more * details. * * This will be set to NULL if &num_sched_list equals 1 and @rq has been * set already. * * FIXME: This means priority changes through * drm_sched_entity_set_priority() will be lost henceforth in this case. */ struct drm_gpu_scheduler **sched_list; /** * @num_sched_list: * * Number of drm_gpu_schedulers in the @sched_list. */ unsigned int num_sched_list; /** * @priority: * * Priority of the entity. This can be modified by calling * drm_sched_entity_set_priority(). Protected by @lock. */ enum drm_sched_priority priority; /** * @rq_priority: Run-queue priority */ enum drm_sched_priority rq_priority; /** * @rr_ts: * * Fake timestamp of the last popped job from the entity. */ ktime_t rr_ts; /** * @job_queue: the list of jobs of this entity. */ struct spsc_queue job_queue; /** * @fence_seq: * * A linearly increasing seqno incremented with each new * &drm_sched_fence which is part of the entity. * * FIXME: Callers of drm_sched_job_arm() need to ensure correct locking, * this doesn't need to be atomic. */ atomic_t fence_seq; /** * @fence_context: * * A unique context for all the fences which belong to this entity. The * &drm_sched_fence.scheduled uses the fence_context but * &drm_sched_fence.finished uses fence_context + 1. */ uint64_t fence_context; /** * @dependency: * * The dependency fence of the job which is on the top of the job queue. */ struct dma_fence *dependency; /** * @cb: * * Callback for the dependency fence above. */ struct dma_fence_cb cb; /** * @guilty: * * Points to entities' guilty. */ atomic_t *guilty; /** * @last_scheduled: * * Points to the finished fence of the last scheduled job. Only written * by drm_sched_entity_pop_job(). Can be accessed locklessly from * drm_sched_job_arm() if the queue is empty. */ struct dma_fence __rcu *last_scheduled; /** * @last_user: last group leader pushing a job into the entity. */ struct task_struct *last_user; /** * @stopped: * * Marks the enity as removed from rq and destined for * termination. This is set by calling drm_sched_entity_flush(). */ bool stopped; /** * @entity_idle: * * Signals when entity is not in use, used to sequence entity cleanup in * drm_sched_entity_fini(). */ struct completion entity_idle; /** * @oldest_job_waiting: * * Marks earliest job waiting in SW queue */ ktime_t oldest_job_waiting; /** * @rb_tree_node: * * The node used to insert this entity into time based priority queue */ struct rb_node rb_tree_node; }; /** * struct drm_sched_rq - queue of entities to be scheduled. * * @sched: the scheduler to which this rq belongs to. * @lock: protects @entities, @rb_tree_root, @rr_ts and @head_prio. * @rr_ts: monotonically incrementing fake timestamp for RR mode. * @entities: list of the entities to be scheduled. * @rb_tree_root: root of time based priority queue of entities for FIFO scheduling * @head_prio: priority of the top tree element. * * Run queue is a set of entities scheduling command submissions for * one specific ring. It implements the scheduling policy that selects * the next entity to emit commands from. */ struct drm_sched_rq { struct drm_gpu_scheduler *sched; spinlock_t lock; /* Following members are protected by the @lock: */ ktime_t rr_ts; struct list_head entities; struct rb_root_cached rb_tree_root; enum drm_sched_priority head_prio; }; /** * struct drm_sched_fence - fences corresponding to the scheduling of a job. */ struct drm_sched_fence { /** * @scheduled: this fence is what will be signaled by the scheduler * when the job is scheduled. */ struct dma_fence scheduled; /** * @finished: this fence is what will be signaled by the scheduler * when the job is completed. * * When setting up an out fence for the job, you should use * this, since it's available immediately upon * drm_sched_job_init(), and the fence returned by the driver * from run_job() won't be created until the dependencies have * resolved. */ struct dma_fence finished; /** * @deadline: deadline set on &drm_sched_fence.finished which * potentially needs to be propagated to &drm_sched_fence.parent */ ktime_t deadline; /** * @parent: the fence returned by &drm_sched_backend_ops.run_job * when scheduling the job on hardware. We signal the * &drm_sched_fence.finished fence once parent is signalled. */ struct dma_fence *parent; /** * @sched: the scheduler instance to which the job having this struct * belongs to. */ struct drm_gpu_scheduler *sched; /** * @lock: the lock used by the scheduled and the finished fences. */ spinlock_t lock; /** * @owner: job owner for debugging */ void *owner; /** * @drm_client_id: * * The client_id of the drm_file which owns the job. */ uint64_t drm_client_id; }; struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); /** * struct drm_sched_job - A job to be run by an entity. * * @queue_node: used to append this struct to the queue of jobs in an entity. * @list: a job participates in a "pending" and "done" lists. * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. * @credits: the number of credits this job contributes to the scheduler * @work: Helper to reschedule job kill to different context. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not * be scheduled further. * @s_priority: the priority of the job. * @entity: the entity to which this job belongs. * @cb: the callback for the parent fence in s_fence. * * A job is created by the driver using drm_sched_job_init(), and * should call drm_sched_entity_push_job() once it wants the scheduler * to schedule the job. */ struct drm_sched_job { /** * @submit_ts: * * When the job was pushed into the entity queue. */ ktime_t submit_ts; /** * @sched: * * The scheduler this job is or will be scheduled on. Gets set by * drm_sched_job_arm(). Valid until drm_sched_backend_ops.free_job() * has finished. */ struct drm_gpu_scheduler *sched; struct drm_sched_fence *s_fence; struct drm_sched_entity *entity; /** * @entity_stats: Stats object reference held by the job and entity. */ struct drm_sched_entity_stats *entity_stats; enum drm_sched_priority s_priority; u32 credits; /** @last_dependency: tracks @dependencies as they signal */ unsigned int last_dependency; atomic_t karma; struct spsc_node queue_node; struct list_head list; /* * work is used only after finish_cb has been used and will not be * accessed anymore. */ union { struct dma_fence_cb finish_cb; struct work_struct work; }; struct dma_fence_cb cb; /** * @dependencies: * * Contains the dependencies as struct dma_fence for this job, see * drm_sched_job_add_dependency() and * drm_sched_job_add_implicit_dependencies(). */ struct xarray dependencies; }; /** * enum drm_gpu_sched_stat - the scheduler's status * * @DRM_GPU_SCHED_STAT_NONE: Reserved. Do not use. * @DRM_GPU_SCHED_STAT_RESET: The GPU hung and successfully reset. * @DRM_GPU_SCHED_STAT_ENODEV: Error: Device is not available anymore. * @DRM_GPU_SCHED_STAT_NO_HANG: Contrary to scheduler's assumption, the GPU * did not hang and is still running. */ enum drm_gpu_sched_stat { DRM_GPU_SCHED_STAT_NONE, DRM_GPU_SCHED_STAT_RESET, DRM_GPU_SCHED_STAT_ENODEV, DRM_GPU_SCHED_STAT_NO_HANG, }; /** * struct drm_sched_backend_ops - Define the backend operations * called by the scheduler * * These functions should be implemented in the driver side. */ struct drm_sched_backend_ops { /** * @prepare_job: * * Called when the scheduler is considering scheduling this job next, to * get another struct dma_fence for this job to block on. Once it * returns NULL, run_job() may be called. * * Can be NULL if no additional preparation to the dependencies are * necessary. Skipped when jobs are killed instead of run. */ struct dma_fence *(*prepare_job)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); /** * @run_job: Called to execute the job once all of the dependencies * have been resolved. * * @sched_job: the job to run * * The deprecated drm_sched_resubmit_jobs() (called by &struct * drm_sched_backend_ops.timedout_job) can invoke this again with the * same parameters. Using this is discouraged because it violates * dma_fence rules, notably dma_fence_init() has to be called on * already initialized fences for a second time. Moreover, this is * dangerous because attempts to allocate memory might deadlock with * memory management code waiting for the reset to complete. * * TODO: Document what drivers should do / use instead. * * This method is called in a workqueue context - either from the * submit_wq the driver passed through drm_sched_init(), or, if the * driver passed NULL, a separate, ordered workqueue the scheduler * allocated. * * Note that the scheduler expects to 'inherit' its own reference to * this fence from the callback. It does not invoke an extra * dma_fence_get() on it. Consequently, this callback must take a * reference for the scheduler, and additional ones for the driver's * respective needs. * * Return: * * On success: dma_fence the driver must signal once the hardware has * completed the job ("hardware fence"). * * On failure: NULL or an ERR_PTR. */ struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); /** * @timedout_job: Called when a job has taken too long to execute, * to trigger GPU recovery. * * @sched_job: The job that has timed out * * Drivers typically issue a reset to recover from GPU hangs. * This procedure looks very different depending on whether a firmware * or a hardware scheduler is being used. * * For a FIRMWARE SCHEDULER, each ring has one scheduler, and each