1 files changed, 21 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/common/linux/channel.c b/drivers/gpu/nvgpu/common/linux/channel.c
index a725cd6b..35fb3023 100644
--- a/drivers/gpu/nvgpu/common/linux/channel.c
+++ b/drivers/gpu/nvgpu/common/linux/channel.c
@@ -720,7 +720,8 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
                 return -EINVAL;
 
         if ((flags & (NVGPU_SUBMIT_GPFIFO_FLAGS_FENCE_WAIT |
-                      NVGPU_SUBMIT_GPFIFO_FLAGS_FENCE_GET)) &&
+                      NVGPU_SUBMIT_GPFIFO_FLAGS_FENCE_GET |
+                      NVGPU_SUBMIT_GPFIFO_FLAGS_USER_FENCE_UPDATE)) &&
             !fence)
                 return -EINVAL;
 
@@ -757,6 +758,16 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
                         (g->can_railgate && !c->deterministic) ||
                         !skip_buffer_refcounting;
 
+        /*
+         * If User is adding increments to the pushbuffer and doing all job
+         * tracking, then no need for kernel tracking here
+         * User should ensure that all pre-requisites for fast submit are met
+         * Fail the submit if that's not the case
+         */
+        if (need_job_tracking &&
+            (flags & NVGPU_SUBMIT_GPFIFO_FLAGS_USER_FENCE_UPDATE))
+                return -EINVAL;
+
         if (need_job_tracking) {
                 bool need_sync_framework = false;
 
@@ -868,6 +879,15 @@ int gk20a_submit_channel_gpfifo(struct channel_gk20a *c,
                 goto clean_up;
         }
 
+        if (flags & NVGPU_SUBMIT_GPFIFO_FLAGS_USER_FENCE_UPDATE) {
+                /*
+                 * User space adds increments in the pushbuffer, so just
+                 * handle the threshold book keeping in kernel by adding
+                 * number of syncpoint increments to threshold
+                 */
+                c->sync->add_user_incrs(c->sync, fence->value);
+        }
+
         if (need_job_tracking) {
                 err = channel_gk20a_alloc_job(c, &job);
                 if (err)