drm/nouveau: wait for the exclusive fence after the shared ones v2

commit 67f7430 upstream.

Always waiting for the exclusive fence resulted on some performance
regressions. So try to wait for the shared fences first, then the
exclusive fence should always be signaled already.

v2: fix incorrectly placed "(", add some comment why we do this.

Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Stefan Fritsch <sf@sfritsch.de>
Tested-by: Dan Moulding <dmoulding@me.com>
Acked-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: <stable@vger.kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20211209102335.18321-1-christian.koenig@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/gpu/drm/nouveau/nouveau_fence.c

@@ -353,15 +353,22 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e
 
 		if (ret)
 			return ret;
-	}
 
-	fobj = dma_resv_shared_list(resv);
-	fence = dma_resv_excl_fence(resv);
+		fobj = NULL;
+	} else {
+		fobj = dma_resv_shared_list(resv);
+	}
 
-	if (fence) {
+	/* Waiting for the exclusive fence first causes performance regressions
+	 * under some circumstances. So manually wait for the shared ones first.
+	 */
+	for (i = 0; i < (fobj ? fobj->shared_count : 0) && !ret; ++i) {
 		struct nouveau_channel *prev = NULL;
 		bool must_wait = true;
 
+		fence = rcu_dereference_protected(fobj->shared[i],
+						dma_resv_held(resv));
+
 		f = nouveau_local_fence(fence, chan->drm);
 		if (f) {
 			rcu_read_lock();
@@ -373,20 +380,13 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e
 
 		if (must_wait)
 			ret = dma_fence_wait(fence, intr);
-
-		return ret;
 	}
 
-	if (!exclusive || !fobj)
-		return ret;
-
-	for (i = 0; i < fobj->shared_count && !ret; ++i) {
+	fence = dma_resv_excl_fence(resv);
+	if (fence) {
 		struct nouveau_channel *prev = NULL;
 		bool must_wait = true;
 
-		fence = rcu_dereference_protected(fobj->shared[i],
-						dma_resv_held(resv));
-
 		f = nouveau_local_fence(fence, chan->drm);
 		if (f) {
 			rcu_read_lock();
@@ -398,6 +398,8 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e
 
 		if (must_wait)
 			ret = dma_fence_wait(fence, intr);
+
+		return ret;
 	}
 
 	return ret;