6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tvrtko Ursulin tvrtko.ursulin@igalia.com
[ Upstream commit f93126f5d55920d1447ef00a3fbe6706f40f53de ]
When writing to a drm_sched_entity's run-queue, writers are protected through the lock drm_sched_entity.rq_lock. This naming, however, frequently collides with the separate internal lock of struct drm_sched_rq, resulting in uses like this:
spin_lock(&entity->rq_lock); spin_lock(&entity->rq->lock);
Rename drm_sched_entity.rq_lock to improve readability. While at it, re-order that struct's members to make it more obvious what the lock protects.
v2: * Rename some rq_lock straddlers in kerneldoc, improve commit text. (Philipp)
Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@igalia.com Suggested-by: Christian König christian.koenig@amd.com Cc: Alex Deucher alexander.deucher@amd.com Cc: Luben Tuikov ltuikov89@gmail.com Cc: Matthew Brost matthew.brost@intel.com Cc: Philipp Stanner pstanner@redhat.com Reviewed-by: Christian König christian.koenig@amd.com [pstanner: Fix typo in docstring] Signed-off-by: Philipp Stanner pstanner@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20241016122013.7857-5-tursulin... Stable-dep-of: d25e3a610bae ("drm/sched: Fix race in drm_sched_entity_select_rq()") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/scheduler/sched_entity.c | 28 ++++++++++++++-------------- drivers/gpu/drm/scheduler/sched_main.c | 2 +- include/drm/gpu_scheduler.h | 21 +++++++++++---------- 3 files changed, 26 insertions(+), 25 deletions(-)
--- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -106,7 +106,7 @@ int drm_sched_entity_init(struct drm_sch /* We start in an idle state. */ complete_all(&entity->entity_idle);
- spin_lock_init(&entity->rq_lock); + spin_lock_init(&entity->lock); spsc_queue_init(&entity->job_queue);
atomic_set(&entity->fence_seq, 0); @@ -134,10 +134,10 @@ void drm_sched_entity_modify_sched(struc { WARN_ON(!num_sched_list || !sched_list);
- spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); entity->sched_list = sched_list; entity->num_sched_list = num_sched_list; - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock); } EXPORT_SYMBOL(drm_sched_entity_modify_sched);
@@ -246,10 +246,10 @@ static void drm_sched_entity_kill(struct if (!entity->rq) return;
- spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); entity->stopped = true; drm_sched_rq_remove_entity(entity->rq, entity); - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock);
/* Make sure this entity is not used by the scheduler at the moment */ wait_for_completion(&entity->entity_idle); @@ -395,9 +395,9 @@ static void drm_sched_entity_wakeup(stru void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority) { - spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); entity->priority = priority; - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock); } EXPORT_SYMBOL(drm_sched_entity_set_priority);
@@ -507,10 +507,10 @@ struct drm_sched_job *drm_sched_entity_p
next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); if (next) { - spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); drm_sched_rq_update_fifo_locked(entity, next->submit_ts); - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock); } }
@@ -551,14 +551,14 @@ void drm_sched_entity_select_rq(struct d if (fence && !dma_fence_is_signaled(fence)) return;
- spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list); rq = sched ? sched->sched_rq[entity->priority] : NULL; if (rq != entity->rq) { drm_sched_rq_remove_entity(entity->rq, entity); entity->rq = rq; } - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock);
if (entity->num_sched_list == 1) entity->sched_list = NULL; @@ -599,9 +599,9 @@ void drm_sched_entity_push_job(struct dr struct drm_sched_rq *rq;
/* Add the entity to the run queue */ - spin_lock(&entity->rq_lock); + spin_lock(&entity->lock); if (entity->stopped) { - spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock);
DRM_ERROR("Trying to push to a killed entity\n"); return; @@ -615,7 +615,7 @@ void drm_sched_entity_push_job(struct dr if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) drm_sched_rq_update_fifo_locked(entity, submit_ts);
- spin_unlock(&entity->rq_lock); + spin_unlock(&entity->lock);
drm_sched_wakeup(sched); } --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -176,7 +176,7 @@ void drm_sched_rq_update_fifo_locked(str * for entity from within concurrent drm_sched_entity_select_rq and the * other to update the rb tree structure. */ - lockdep_assert_held(&entity->rq_lock); + lockdep_assert_held(&entity->lock);
spin_lock(&entity->rq->lock);
--- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -97,13 +97,21 @@ struct drm_sched_entity { struct list_head list;
/** + * @lock: + * + * Lock protecting the run-queue (@rq) to which this entity belongs, + * @priority and the list of schedulers (@sched_list, @num_sched_list). + */ + spinlock_t lock; + + /** * @rq: * * Runqueue on which this entity is currently scheduled. * * FIXME: Locking is very unclear for this. Writers are protected by - * @rq_lock, but readers are generally lockless and seem to just race - * with not even a READ_ONCE. + * @lock, but readers are generally lockless and seem to just race with + * not even a READ_ONCE. */ struct drm_sched_rq *rq;
@@ -136,18 +144,11 @@ struct drm_sched_entity { * @priority: * * Priority of the entity. This can be modified by calling - * drm_sched_entity_set_priority(). Protected by &rq_lock. + * drm_sched_entity_set_priority(). Protected by @lock. */ enum drm_sched_priority priority;
/** - * @rq_lock: - * - * Lock to modify the runqueue to which this entity belongs. - */ - spinlock_t rq_lock; - - /** * @job_queue: the list of jobs of this entity. */ struct spsc_queue job_queue;