drm/msm: Add wait-boost support

Add a way for various userspace waits to signal urgency.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/525817/
Link: https://lore.kernel.org/r/20230308155322.344664-14-robdclark@gmail.com

drivers/gpu/drm/msm/msm_drv.c

@@ -46,6 +46,7 @@
  * - 1.8.0 - Add MSM_BO_CACHED_COHERENT for supported GPUs (a6xx)
  * - 1.9.0 - Add MSM_SUBMIT_FENCE_SN_IN
  * - 1.10.0 - Add MSM_SUBMIT_BO_NO_IMPLICIT
+ * - 1.11.0 - Add wait boost (MSM_WAIT_FENCE_BOOST, MSM_PREP_BOOST)
  */
 #define MSM_VERSION_MAJOR	1
 #define MSM_VERSION_MINOR	10
@@ -899,7 +900,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 }
 
 static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
-		      ktime_t timeout)
+		      ktime_t timeout, uint32_t flags)
 {
 	struct dma_fence *fence;
 	int ret;
@@ -927,6 +928,9 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
 	if (!fence)
 		return 0;
 
+	if (flags & MSM_WAIT_FENCE_BOOST)
+		dma_fence_set_deadline(fence, ktime_get());
+
 	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
 	if (ret == 0) {
 		ret = -ETIMEDOUT;
@@ -947,8 +951,8 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	struct msm_gpu_submitqueue *queue;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (args->flags & ~MSM_WAIT_FENCE_FLAGS) {
+		DRM_ERROR("invalid flags: %08x\n", args->flags);
 		return -EINVAL;
 	}
 
@@ -959,7 +963,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout), args->flags);
 
 	msm_submitqueue_put(queue);
 

drivers/gpu/drm/msm/msm_gem.c

@@ -895,6 +895,11 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
 		op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout);
 	long ret;
 
+	if (op & MSM_PREP_BOOST) {
+		dma_resv_set_deadline(obj->resv, dma_resv_usage_rw(write),
+				      ktime_get());
+	}
+
 	ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write),
 				    true,  remain);
 	if (ret == 0)

include/uapi/drm/msm_drm.h

@@ -151,8 +151,13 @@ struct drm_msm_gem_info {
 #define MSM_PREP_READ        0x01
 #define MSM_PREP_WRITE       0x02
 #define MSM_PREP_NOSYNC      0x04
+#define MSM_PREP_BOOST       0x08
 
-#define MSM_PREP_FLAGS       (MSM_PREP_READ | MSM_PREP_WRITE | MSM_PREP_NOSYNC)
+#define MSM_PREP_FLAGS       (MSM_PREP_READ | \
+			      MSM_PREP_WRITE | \
+			      MSM_PREP_NOSYNC | \
+			      MSM_PREP_BOOST | \
+			      0)
 
 struct drm_msm_gem_cpu_prep {
 	__u32 handle;         /* in */
@@ -286,6 +291,11 @@ struct drm_msm_gem_submit {
 
 };
 
+#define MSM_WAIT_FENCE_BOOST	0x00000001
+#define MSM_WAIT_FENCE_FLAGS	( \
+		MSM_WAIT_FENCE_BOOST | \
+		0)
+
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
  * a buffer if you need to access it from the CPU (other cmdstream
  * submission from same or other contexts, PAGE_FLIP ioctl, etc, all
@@ -295,7 +305,7 @@ struct drm_msm_gem_submit {
  */
 struct drm_msm_wait_fence {
 	__u32 fence;          /* in */
-	__u32 pad;
+	__u32 flags;          /* in, bitmask of MSM_WAIT_FENCE_x */
 	struct drm_msm_timespec timeout;   /* in */
 	__u32 queueid;         /* in, submitqueue id */
 };