drm/xe/exec_queue: Prepare last fence for hw engine group resume context

Ensure we can safely take a ref of the exec queue's last fence from the
context of resuming jobs from the hw engine group. The locking requirements
differ from the general case, hence the introduction of this new function.

v2: Add kernel doc, rework the code to prevent code duplication

v3: Fix kernel doc, remove now unnecessary lockdep variants (Matt Brost)

v4: Remove new put function (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/20240809155156.1955925-7-francois.dugast@intel.com

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 3ce4582..6d3b44c 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -837,10 +837,12 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 static void xe_exec_queue_last_fence_lockdep_assert(struct xe_exec_queue *q,
                                                    struct xe_vm *vm)
 {
-       if (q->flags & EXEC_QUEUE_FLAG_VM)
+       if (q->flags & EXEC_QUEUE_FLAG_VM) {
                lockdep_assert_held(&vm->lock);
-       else
+       } else {
                xe_vm_assert_held(vm);
+               lockdep_assert_held(&q->hwe->hw_engine_group->mode_sem);
+       }
 }
 
 /**
@@ -894,6 +896,33 @@ struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
        return fence;
 }
 
+/**
+ * xe_exec_queue_last_fence_get_for_resume() - Get last fence
+ * @q: The exec queue
+ * @vm: The VM the engine does a bind or exec for
+ *
+ * Get last fence, takes a ref. Only safe to be called in the context of
+ * resuming the hw engine group's long-running exec queue, when the group
+ * semaphore is held.
+ *
+ * Returns: last fence if not signaled, dma fence stub if signaled
+ */
+struct dma_fence *xe_exec_queue_last_fence_get_for_resume(struct xe_exec_queue *q,
+                                                         struct xe_vm *vm)
+{
+       struct dma_fence *fence;
+
+       lockdep_assert_held_write(&q->hwe->hw_engine_group->mode_sem);
+
+       if (q->last_fence &&
+           test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
+               xe_exec_queue_last_fence_put_unlocked(q);
+
+       fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+       dma_fence_get(fence);
+       return fence;
+}
+
 /**
  * xe_exec_queue_last_fence_set() - Set last fence
  * @q: The exec queue

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index 9913936..90c7f73 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -77,6 +77,8 @@ void xe_exec_queue_last_fence_put(struct xe_exec_queue *e, struct xe_vm *vm);
 void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *e);
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *e,
                                               struct xe_vm *vm);
+struct dma_fence *xe_exec_queue_last_fence_get_for_resume(struct xe_exec_queue *e,
+                                                         struct xe_vm *vm);
 void xe_exec_queue_last_fence_set(struct xe_exec_queue *e, struct xe_vm *vm,
                                  struct dma_fence *fence);
 int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,