diff options
Diffstat (limited to 'drivers/gpu/drm/xe/xe_guc_submit.c')
| -rw-r--r-- | drivers/gpu/drm/xe/xe_guc_submit.c | 67 |
1 files changed, 36 insertions, 31 deletions
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index e5a644b47e10..bbcd47737a59 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -23,6 +23,7 @@ #include "xe_force_wake.h" #include "xe_gpu_scheduler.h" #include "xe_gt.h" +#include "xe_gt_printk.h" #include "xe_guc.h" #include "xe_guc_ct.h" #include "xe_guc_exec_queue_types.h" @@ -929,13 +930,15 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) int i = 0; if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) { - xe_assert(xe, !(q->flags & EXEC_QUEUE_FLAG_KERNEL)); - xe_assert(xe, !(q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q))); - drm_notice(&xe->drm, "Timedout job: seqno=%u, guc_id=%d, flags=0x%lx", xe_sched_job_seqno(job), q->guc->id, q->flags); + xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL, + "Kernel-submitted job timed out\n"); + xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q), + "VM job timed out on non-killed execqueue\n"); + simple_error_capture(q); - xe_devcoredump(q); + xe_devcoredump(job); } else { drm_dbg(&xe->drm, "Timedout signaled job: seqno=%u, guc_id=%d, flags=0x%lx", xe_sched_job_seqno(job), q->guc->id, q->flags); @@ -1029,8 +1032,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) if (xe_exec_queue_is_lr(q)) cancel_work_sync(&ge->lr_tdr); - if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT) - xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q); release_guc_id(guc, q); xe_sched_entity_fini(&ge->entity); xe_sched_fini(&ge->sched); @@ -1219,7 +1220,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) init_waitqueue_head(&ge->suspend_wait); timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT : - q->hwe->eclass->sched_props.job_timeout_ms; + q->sched_props.job_timeout_ms; err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops, get_submit_wq(guc), q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES, 64, @@ -1351,21 +1352,6 @@ static int guc_exec_queue_set_preempt_timeout(struct xe_exec_queue *q, return 0; } -static int guc_exec_queue_set_job_timeout(struct xe_exec_queue *q, u32 job_timeout_ms) -{ - struct xe_gpu_scheduler *sched = &q->guc->sched; - struct xe_guc *guc = exec_queue_to_guc(q); - struct xe_device *xe = guc_to_xe(guc); - - xe_assert(xe, !exec_queue_registered(q)); - xe_assert(xe, !exec_queue_banned(q)); - xe_assert(xe, !exec_queue_killed(q)); - - sched->base.timeout = job_timeout_ms; - - return 0; -} - static int guc_exec_queue_suspend(struct xe_exec_queue *q) { struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_SUSPEND; @@ -1416,7 +1402,6 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = { .set_priority = guc_exec_queue_set_priority, .set_timeslice = guc_exec_queue_set_timeslice, .set_preempt_timeout = guc_exec_queue_set_preempt_timeout, - .set_job_timeout = guc_exec_queue_set_job_timeout, .suspend = guc_exec_queue_suspend, .suspend_wait = guc_exec_queue_suspend_wait, .resume = guc_exec_queue_resume, @@ -1797,7 +1782,7 @@ guc_exec_queue_wq_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps /** * xe_guc_exec_queue_snapshot_capture - Take a quick snapshot of the GuC Engine. - * @q: Xe exec queue. + * @job: faulty Xe scheduled job. * * This can be printed out in a later stage like during dev_coredump * analysis. @@ -1806,12 +1791,12 @@ guc_exec_queue_wq_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps * caller, using `xe_guc_exec_queue_snapshot_free`. */ struct xe_guc_submit_exec_queue_snapshot * -xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q) +xe_guc_exec_queue_snapshot_capture(struct xe_sched_job *job) { + struct xe_exec_queue *q = job->q; struct xe_guc *guc = exec_queue_to_guc(q); struct xe_device *xe = guc_to_xe(guc); struct xe_gpu_scheduler *sched = &q->guc->sched; - struct xe_sched_job *job; struct xe_guc_submit_exec_queue_snapshot *snapshot; int i; @@ -1869,14 +1854,16 @@ xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q) if (!snapshot->pending_list) { drm_err(&xe->drm, "Skipping GuC Engine pending_list snapshot.\n"); } else { + struct xe_sched_job *job_iter; + i = 0; - list_for_each_entry(job, &sched->base.pending_list, drm.list) { + list_for_each_entry(job_iter, &sched->base.pending_list, drm.list) { snapshot->pending_list[i].seqno = - xe_sched_job_seqno(job); + xe_sched_job_seqno(job_iter); snapshot->pending_list[i].fence = - dma_fence_is_signaled(job->fence) ? 1 : 0; + dma_fence_is_signaled(job_iter->fence) ? 1 : 0; snapshot->pending_list[i].finished = - dma_fence_is_signaled(&job->drm.s_fence->finished) + dma_fence_is_signaled(&job_iter->drm.s_fence->finished) ? 1 : 0; i++; } @@ -1962,10 +1949,28 @@ void xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *s static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p) { struct xe_guc_submit_exec_queue_snapshot *snapshot; + struct xe_gpu_scheduler *sched = &q->guc->sched; + struct xe_sched_job *job; + bool found = false; - snapshot = xe_guc_exec_queue_snapshot_capture(q); + spin_lock(&sched->base.job_list_lock); + list_for_each_entry(job, &sched->base.pending_list, drm.list) { + if (job->q == q) { + xe_sched_job_get(job); + found = true; + break; + } + } + spin_unlock(&sched->base.job_list_lock); + + if (!found) + return; + + snapshot = xe_guc_exec_queue_snapshot_capture(job); xe_guc_exec_queue_snapshot_print(snapshot, p); xe_guc_exec_queue_snapshot_free(snapshot); + + xe_sched_job_put(job); } /** |