drm/xe/exec: Switch hw engine group execution mode upon job submission

If the job about to be submitted is a dma-fence job, update the current
execution mode of the hw engine group. This triggers an immediate suspend
of the exec queues running faulting long-running jobs.

If the job about to be submitted is a long-running job, kick a new worker
used to resume the exec queues running faulting long-running jobs once
the dma-fence jobs have completed.

v2: Kick the resume worker from exec IOCTL, switch to unordered workqueue,
    destroy it after use (Matt Brost)

v3: Do not resume if no exec queue was suspended (Matt Brost)

v4: Squash commits (Matt Brost)

v5: Do not kick the worker when xe_vm_in_preempt_fence_mode (Matt Brost)

Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-10-francois.dugast@intel.com

1 files changed, 19 insertions, 1 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index f36980aa26e6..484acfbe0e61 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -14,6 +14,7 @@
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_exec_queue.h"
+#include "xe_hw_engine_group.h"
 #include "xe_macros.h"
 #include "xe_ring_ops_types.h"
 #include "xe_sched_job.h"
@@ -124,6 +125,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	bool write_locked, skip_retry = false;
 	ktime_t end = 0;
 	int err = 0;
+	struct xe_hw_engine_group *group;
+	enum xe_hw_engine_group_execution_mode mode, previous_mode;
 
 	if (XE_IOCTL_DBG(xe, args->extensions) ||
 	    XE_IOCTL_DBG(xe, args->pad[0] || args->pad[1] || args->pad[2]) ||
@@ -182,6 +185,15 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		}
 	}
 
+	group = q->hwe->hw_engine_group;
+	mode = xe_hw_engine_group_find_exec_mode(q);
+
+	if (mode == EXEC_MODE_DMA_FENCE) {
+		err = xe_hw_engine_group_get_mode(group, mode, &previous_mode);
+		if (err)
+			goto err_syncs;
+	}
+
 retry:
 	if (!xe_vm_in_lr_mode(vm) && xe_vm_userptr_check_repin(vm)) {
 		err = down_write_killable(&vm->lock);
@@ -199,7 +211,7 @@ retry:
 		downgrade_write(&vm->lock);
 		write_locked = false;
 		if (err)
-			goto err_unlock_list;
+			goto err_hw_exec_mode;
 	}
 
 	if (!args->num_batch_buffer) {
@@ -312,6 +324,9 @@ retry:
 		spin_unlock(&xe->ttm.lru_lock);
 	}
 
+	if (mode == EXEC_MODE_LR)
+		xe_hw_engine_group_resume_faulting_lr_jobs(group);
+
 err_repin:
 	if (!xe_vm_in_lr_mode(vm))
 		up_read(&vm->userptr.notifier_lock);
@@ -324,6 +339,9 @@ err_unlock_list:
 	up_read(&vm->lock);
 	if (err == -EAGAIN && !skip_retry)
 		goto retry;
+err_hw_exec_mode:
+	if (mode == EXEC_MODE_DMA_FENCE)
+		xe_hw_engine_group_put(group);
 err_syncs:
 	while (num_syncs--)
 		xe_sync_entry_cleanup(&syncs[num_syncs]);