From: Daniel Vetter daniel.vetter@ffwll.ch
mainline inclusion from mainline-v5.16-rc1 commit ebd5f74255b9f5f8a154ba5535f83387ae599d46 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IB3ULB
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
Instead of just a callback we can just glue in the gem helpers that panfrost, v3d and lima currently use. There's really not that many ways to skin this cat.
v2/3: Rebased.
v4: Repaint this shed. The functions are now called _add_dependency() and _add_implicit_dependency()
Reviewed-by: Christian König christian.koenig@amd.com Reviewed-by: Boris Brezillon boris.brezillon@collabora.com (v3) Reviewed-by: Steven Price steven.price@arm.com (v1) Acked-by: Melissa Wen mwen@igalia.com Signed-off-by: Daniel Vetter daniel.vetter@intel.com Cc: David Airlie airlied@linux.ie Cc: Daniel Vetter daniel@ffwll.ch Cc: Sumit Semwal sumit.semwal@linaro.org Cc: "Christian König" christian.koenig@amd.com Cc: Andrey Grodzovsky andrey.grodzovsky@amd.com Cc: Lee Jones lee.jones@linaro.org Cc: Nirmoy Das nirmoy.aiemd@gmail.com Cc: Boris Brezillon boris.brezillon@collabora.com Cc: Luben Tuikov luben.tuikov@amd.com Cc: Alex Deucher alexander.deucher@amd.com Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-5-daniel...
Conflicts: context conflicts in below files: include/drm/gpu_scheduler.h drivers/gpu/drm/scheduler/sched_main.c rename dma_resv_get_excl_unlocked to dma_resv_get_excl_rcu rename dma_resv_get_fences to dma_resv_get_fences_rcu #include <linux/dma-resv.h> & <drm/drm_gem.h>
Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/gpu/drm/scheduler/sched_entity.c | 18 +++- drivers/gpu/drm/scheduler/sched_main.c | 104 +++++++++++++++++++++++ include/drm/gpu_scheduler.h | 33 ++++++- 3 files changed, 149 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 3f7f761df4cd..1b1b770dc949 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -208,6 +208,19 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, job->sched->ops->free_job(job); }
+static struct dma_fence * +drm_sched_job_dependency(struct drm_sched_job *job, + struct drm_sched_entity *entity) +{ + if (!xa_empty(&job->dependencies)) + return xa_erase(&job->dependencies, job->last_dependency++); + + if (job->sched->ops->dependency) + return job->sched->ops->dependency(job, entity); + + return NULL; +} + /** * drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed * @@ -226,7 +239,7 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) struct drm_sched_fence *s_fence = job->s_fence;
/* Wait for all dependencies to avoid data corruptions */ - while ((f = job->sched->ops->dependency(job, entity))) + while ((f = drm_sched_job_dependency(job, entity))) dma_fence_wait(f, false);
drm_sched_fence_scheduled(s_fence); @@ -416,7 +429,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) */ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) { - struct drm_gpu_scheduler *sched = entity->rq->sched; struct drm_sched_job *sched_job;
sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); @@ -424,7 +436,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) return NULL;
while ((entity->dependency = - sched->ops->dependency(sched_job, entity))) { + drm_sched_job_dependency(sched_job, entity))) { trace_drm_sched_job_wait_dep(sched_job, entity->dependency);
if (drm_sched_entity_add_dependency_cb(entity)) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index b6c2757c3d83..3780433e93d9 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -48,9 +48,11 @@ #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/gpu_scheduler.h> #include <drm/spsc_queue.h>
@@ -567,10 +569,104 @@ int drm_sched_job_init(struct drm_sched_job *job,
INIT_LIST_HEAD(&job->node);
+ xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC); + return 0; } EXPORT_SYMBOL(drm_sched_job_init);
+/** + * 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) +{ + struct dma_fence *entry; + unsigned long index; + u32 id = 0; + int ret; + + if (!fence) + return 0; + + /* Deduplicate if we already depend on a fence from the same context. + * This lets the size of the array of deps scale with the number of + * engines involved, rather than the number of BOs. + */ + xa_for_each(&job->dependencies, index, entry) { + if (entry->context != fence->context) + continue; + + if (dma_fence_is_later(fence, entry)) { + dma_fence_put(entry); + xa_store(&job->dependencies, index, fence, GFP_KERNEL); + } else { + dma_fence_put(fence); + } + return 0; + } + + ret = xa_alloc(&job->dependencies, &id, fence, xa_limit_32b, GFP_KERNEL); + if (ret != 0) + dma_fence_put(fence); + + return ret; +} +EXPORT_SYMBOL(drm_sched_job_add_dependency); + +/** + * 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) +{ + int ret; + struct dma_fence **fences; + unsigned int i, fence_count; + + if (!write) { + struct dma_fence *fence = dma_resv_get_excl_rcu(obj->resv); + + return drm_sched_job_add_dependency(job, fence); + } + + ret = dma_resv_get_fences_rcu(obj->resv, NULL, &fence_count, &fences); + if (ret || !fence_count) + return ret; + + for (i = 0; i < fence_count; i++) { + ret = drm_sched_job_add_dependency(job, fences[i]); + if (ret) + break; + } + + for (; i < fence_count; i++) + dma_fence_put(fences[i]); + kfree(fences); + return ret; +} +EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies); + /** * drm_sched_job_cleanup - clean up scheduler job resources * @@ -578,8 +674,16 @@ EXPORT_SYMBOL(drm_sched_job_init); */ void drm_sched_job_cleanup(struct drm_sched_job *job) { + struct dma_fence *fence; + unsigned long index; + dma_fence_put(&job->s_fence->finished); job->s_fence = NULL; + + xa_for_each(&job->dependencies, index, fence) { + dma_fence_put(fence); + } + xa_destroy(&job->dependencies); } EXPORT_SYMBOL(drm_sched_job_cleanup);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 92436553fd6a..842df37f43be 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -27,9 +27,12 @@ #include <drm/spsc_queue.h> #include <linux/dma-fence.h> #include <linux/completion.h> +#include <linux/xarray.h>
#define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
+struct drm_gem_object; + struct drm_gpu_scheduler; struct drm_sched_rq;
@@ -198,6 +201,17 @@ struct drm_sched_job { enum drm_sched_priority s_priority; struct drm_sched_entity *entity; 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; + + /** @last_dependency: tracks @dependencies as they signal */ + unsigned long last_dependency; };
static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, @@ -214,9 +228,15 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, */ struct drm_sched_backend_ops { /** - * @dependency: 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. + * @dependency: + * + * 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. + * + * If a driver exclusively uses drm_sched_job_add_dependency() and + * drm_sched_job_add_implicit_dependencies() this can be ommitted and + * left as NULL. */ struct dma_fence *(*dependency)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); @@ -299,6 +319,13 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner); +int drm_sched_job_add_dependency(struct drm_sched_job *job, + struct dma_fence *fence); +int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, + struct drm_gem_object *obj, + bool write); + + void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, struct drm_gpu_scheduler **sched_list, unsigned int num_sched_list);