[PATCH] drm/xe: Bump LRU for external objects on exec and rebind

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

The VM's private BOs get their LRU position refreshed in bulk via
ttm_lru_bulk_move_tail() on vm->lru_bulk_move, both after a successful
non-LR exec and after the LR preempt-fence rebind worker runs. External
objects (BOs potentially shared across VMs) are never added to that
per-VM bulk move list, so their LRU position is never refreshed by
either path. This makes external objects in active use look more
evictable than they are.

Add xe_vm_bump_lru(), which, under a single lru_lock critical section,
performs the bulk move of the VM's private BOs and bumps each external
object locked by the drm_exec transaction. Use it from both the non-LR
exec path and the LR rebind worker, replacing the open-coded bulk move.

Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Assisted-by: LLM
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c |  7 ++-----
 drivers/gpu/drm/xe/xe_vm.c   | 31 ++++++++++++++++++++++++++++---
 drivers/gpu/drm/xe/xe_vm.h   |  2 ++
 3 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index d5293bc33a67..7dc9a0a1f569 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -346,11 +346,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	xe_sched_job_push(job);
 	xe_vm_reactivate_rebind(vm);
 
-	if (!err && !xe_vm_in_lr_mode(vm)) {
-		spin_lock(&xe->ttm.lru_lock);
-		ttm_lru_bulk_move_tail(&vm->lru_bulk_move);
-		spin_unlock(&xe->ttm.lru_lock);
-	}
+	if (!err && !xe_vm_in_lr_mode(vm))
+		xe_vm_bump_lru(vm, exec);
 
 	if (mode == EXEC_MODE_LR)
 		xe_hw_engine_group_resume_faulting_lr_jobs(group);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ef369df4aa26..095f762bbb6f 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -413,6 +413,33 @@ int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
 	return 0;
 }
 
+/**
+ * xe_vm_bump_lru() - Bump the LRU position of BOs used by a submission
+ * @vm: The vm for which we are bumping LRUs.
+ * @exec: The struct drm_exec with the locked GEM objects.
+ *
+ * Move the VM's private BOs, and all external objects locked by @exec,
+ * to the LRU tail. Private BOs are moved in bulk using @vm's
+ * &xe_vm.lru_bulk_move. External objects, which may be shared with other
+ * VMs, are not part of that bulk move and are bumped individually.
+ */
+void xe_vm_bump_lru(struct xe_vm *vm, struct drm_exec *exec)
+{
+	spinlock_t *lru_lock = &vm->xe->ttm.lru_lock;
+	struct drm_gem_object *obj;
+
+	spin_lock(lru_lock);
+	ttm_lru_bulk_move_tail(&vm->lru_bulk_move);
+	drm_exec_for_each_locked_object(exec, obj) {
+		if (!drm_gpuvm_is_extobj(&vm->gpuvm, obj))
+			continue;
+
+		ttm_bo_move_to_lru_tail(&gem_to_xe_bo(obj)->ttm);
+		cond_resched_lock(lru_lock);
+	}
+	spin_unlock(lru_lock);
+}
+
 static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 				 bool *done)
 {
@@ -563,9 +590,7 @@ static void preempt_rebind_work_func(struct work_struct *w)
 
 #undef retry_required
 
-	spin_lock(&vm->xe->ttm.lru_lock);
-	ttm_lru_bulk_move_tail(&vm->lru_bulk_move);
-	spin_unlock(&vm->xe->ttm.lru_lock);
+	xe_vm_bump_lru(vm, &exec);
 
 	/* Point of no return. */
 	arm_preempt_fences(vm, &preempt_fences);
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 89c4f95984a2..06138c3c4315 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -284,6 +284,8 @@ int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma);
 int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
 			  unsigned int num_fences);
 
+void xe_vm_bump_lru(struct xe_vm *vm, struct drm_exec *exec);
+
 struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo,
 				       struct xe_exec_queue *q, u64 addr,
 				       enum xe_cache_level cache_lvl);
-- 
2.56.0