[PATCH v6 1/8] drm/xe: Track exec queue priority band counts for user VMs

Add a per-priority-band count (LOW/NORMAL/HIGH) of exec queues
attached to a user VM in xe_vm_add_exec_queue()/xe_vm_remove_exec_queue(),
protected by vm->exec_queues.lock in write mode. KERNEL priority is
not counted since it is not possible for user exec queues.

This count is needed so a VM's private buffer objects can later be
prioritized for eviction based on the priority userspace has assigned
to the exec queues using that VM (i.e. work submitted at a higher
priority band implies its buffers are more important to keep
resident), rather than treating every VM the same.

Also move the has_ctx_tlb_inval check inside the lock in
xe_vm_add_exec_queue() so the list add/count update is properly
gated under the same critical section, and make
xe_vm_remove_exec_queue() bail out early if q->xef is not set,
rather than relying on callers to check this.

Cc: Carlos Santa <[email protected]>
Cc: Ryan Neph <[email protected]>
Assisted-by: GitHub_Copilot:claude-sonnet-5
Signed-off-by: Matthew Brost <[email protected]>
---
 drivers/gpu/drm/xe/xe_vm.c       | 31 ++++++++++++++++++++-----------
 drivers/gpu/drm/xe/xe_vm_types.h |  7 +++++++
 2 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 9e0176861cb6..f2636fea4dec 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4946,8 +4946,9 @@ int xe_vm_alloc_cpu_addr_mirror_vma(struct xe_vm *vm, uint64_t start, uint64_t r
  * @vm: The VM.
  * @q: The exec_queue
  *
- * Add exec queue to VM, skipped if the device does not have context based TLB
- * invalidations.
+ * Track exec queue's priority band count for the VM. Also links the exec
+ * queue onto the per-GT list, skipped if the device does not have context
+ * based TLB invalidations.
  */
 void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 {
@@ -4961,12 +4962,14 @@ void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 	xe_assert(xe, vm->xef);
 	xe_assert(xe, vm == q->vm);
 
-	if (!xe->info.has_ctx_tlb_inval)
-		return;
-
 	down_write(&vm->exec_queues.lock);
-	list_add(&q->vm_exec_queue_link, &vm->exec_queues.list[q->gt->info.id]);
-	++vm->exec_queues.count[q->gt->info.id];
+	if (xe->info.has_ctx_tlb_inval) {
+		list_add(&q->vm_exec_queue_link, &vm->exec_queues.list[q->gt->info.id]);
+		++vm->exec_queues.count[q->gt->info.id];
+	}
+	if (q->sched_props.priority >= XE_EXEC_QUEUE_PRIORITY_LOW &&
+	    q->sched_props.priority <= XE_EXEC_QUEUE_PRIORITY_HIGH)
+		++vm->exec_queues.priority_count[q->sched_props.priority];
 	up_write(&vm->exec_queues.lock);
 }
 
@@ -4975,18 +4978,24 @@ void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
  * @vm: The VM.
  * @q: The exec_queue
  *
- * Remove exec queue from VM, skipped if the device does not have context based
- * TLB invalidations.
+ * Untrack exec queue's priority band count for the VM. Also unlinks the
+ * exec queue from the per-GT list, skipped if the device does not have
+ * context based TLB invalidations. No-op if @q is not a user exec queue,
+ * or is a VM exec queue (VM exec queues are never tracked by
+ * xe_vm_add_exec_queue()).
  */
 void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 {
-	if (!vm->xe->info.has_ctx_tlb_inval)
+	if (!q->xef || (q->flags & EXEC_QUEUE_FLAG_VM))
 		return;
 
 	down_write(&vm->exec_queues.lock);
-	if (!list_empty(&q->vm_exec_queue_link)) {
+	if (vm->xe->info.has_ctx_tlb_inval && !list_empty(&q->vm_exec_queue_link)) {
 		list_del(&q->vm_exec_queue_link);
 		--vm->exec_queues.count[q->gt->info.id];
 	}
+	if (q->sched_props.priority >= XE_EXEC_QUEUE_PRIORITY_LOW &&
+	    q->sched_props.priority <= XE_EXEC_QUEUE_PRIORITY_HIGH)
+		--vm->exec_queues.priority_count[q->sched_props.priority];
 	up_write(&vm->exec_queues.lock);
 }
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 635ed29b9a69..d75546c4eb66 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -16,6 +16,7 @@
 #include <linux/scatterlist.h>
 
 #include "xe_device_types.h"
+#include "xe_exec_queue_types.h"
 #include "xe_pt_types.h"
 #include "xe_range_fence.h"
 #include "xe_tlb_inval_types.h"
@@ -342,6 +343,12 @@ struct xe_vm {
 		 * per GT
 		 */
 		int count[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
+		/**
+		 * @exec_queues.priority_count: count of exec queues attached
+		 * to this VM, per priority band (LOW / NORMAL / HIGH only,
+		 * KERNEL priority is not possible for user exec queues)
+		 */
+		int priority_count[XE_EXEC_QUEUE_PRIORITY_HIGH + 1];
 		/** @exec_queues.lock: lock to protect exec_queues list */
 		struct rw_semaphore lock;
 	} exec_queues;
-- 
2.34.1