drm/xe: Add dependency scheduler for GT TLB invalidations to bind queues

Add a generic dependency scheduler for GT TLB invalidations, used to
schedule jobs that issue GT TLB invalidations to bind queues.

v2:
 - Use shared GT TLB invalidation queue for dep scheduler
 - Break allocation of dep scheduler into its own function
 - Add define for max number tlb invalidations
 - Skip media if not present

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-5-matthew.brost@intel.com

2 files changed, 61 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 8991b4aed440..d5958518ef00 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -12,6 +12,7 @@
 #include <drm/drm_file.h>
 #include <uapi/drm/xe_drm.h>
 
+#include "xe_dep_scheduler.h"
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_hw_engine_class_sysfs.h"
@@ -39,6 +40,12 @@ static int exec_queue_user_extensions(struct xe_device *xe, struct xe_exec_queue
 
 static void __xe_exec_queue_free(struct xe_exec_queue *q)
 {
+	int i;
+
+	for (i = 0; i < XE_EXEC_QUEUE_TLB_INVAL_COUNT; ++i)
+		if (q->tlb_inval[i].dep_scheduler)
+			xe_dep_scheduler_fini(q->tlb_inval[i].dep_scheduler);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 	if (q->vm)
@@ -50,6 +57,39 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q)
 	kfree(q);
 }
 
+static int alloc_dep_schedulers(struct xe_device *xe, struct xe_exec_queue *q)
+{
+	struct xe_tile *tile = gt_to_tile(q->gt);
+	int i;
+
+	for (i = 0; i < XE_EXEC_QUEUE_TLB_INVAL_COUNT; ++i) {
+		struct xe_dep_scheduler *dep_scheduler;
+		struct xe_gt *gt;
+		struct workqueue_struct *wq;
+
+		if (i == XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT)
+			gt = tile->primary_gt;
+		else
+			gt = tile->media_gt;
+
+		if (!gt)
+			continue;
+
+		wq = gt->tlb_invalidation.job_wq;
+
+#define MAX_TLB_INVAL_JOBS	16	/* Picking a reasonable value */
+		dep_scheduler = xe_dep_scheduler_create(xe, wq, q->name,
+							MAX_TLB_INVAL_JOBS);
+		if (IS_ERR(dep_scheduler))
+			return PTR_ERR(dep_scheduler);
+
+		q->tlb_inval[i].dep_scheduler = dep_scheduler;
+	}
+#undef MAX_TLB_INVAL_JOBS
+
+	return 0;
+}
+
 static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 						   struct xe_vm *vm,
 						   u32 logical_mask,
@@ -94,6 +134,14 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 	else
 		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
+	if (q->flags & (EXEC_QUEUE_FLAG_MIGRATE | EXEC_QUEUE_FLAG_VM)) {
+		err = alloc_dep_schedulers(xe, q);
+		if (err) {
+			__xe_exec_queue_free(q);
+			return ERR_PTR(err);
+		}
+	}
+
 	if (vm)
 		q->vm = xe_vm_get(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index abdf4a57e6e2..ba443a497b38 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -134,6 +134,19 @@ struct xe_exec_queue {
 		struct list_head link;
 	} lr;
 
+#define XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT	0
+#define XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT	1
+#define XE_EXEC_QUEUE_TLB_INVAL_COUNT		(XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT  + 1)
+
+	/** @tlb_inval: TLB invalidations exec queue state */
+	struct {
+		/**
+		 * @tlb_inval.dep_scheduler: The TLB invalidation
+		 * dependency scheduler
+		 */
+		struct xe_dep_scheduler *dep_scheduler;
+	} tlb_inval[XE_EXEC_QUEUE_TLB_INVAL_COUNT];
+
 	/** @pxp: PXP info tracking */
 	struct {
 		/** @pxp.type: PXP session type used by this queue */