drm/i915/gvt: Use fence error from GVT request for workload status

The req->fence.error will be set if this request caused GPU hang so
we can use this value to workload->status to indicate whether this
GVT request caused any problem. If it caused GPU hang, we shouldn't
trigger any context switch back to the guest.

v2:
- only take -EIO from fence->error. (Zhenyu)

Fixes: 8f1117abb408 (drm/i915/gvt: handle workload lifecycle properly)
Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 5aeba13a5de4d48860727f061db40fde491160eb..4f7057d62d88b393ce77670f9100bc2d3b246014 100644 (file)
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -174,15 +174,6 @@ static int shadow_context_status_change(struct notifier_block *nb,
                atomic_set(&workload->shadow_ctx_active, 1);
                break;
        case INTEL_CONTEXT_SCHEDULE_OUT:
-               /* If the status is -EINPROGRESS means this workload
-                * doesn't meet any issue during dispatching so when
-                * get the SCHEDULE_OUT set the status to be zero for
-                * good. If the status is NOT -EINPROGRESS means there
-                * is something wrong happened during dispatching and
-                * the status should not be set to zero
-                */
-               if (workload->status == -EINPROGRESS)
-                       workload->status = 0;
                atomic_set(&workload->shadow_ctx_active, 0);
                break;
        default:
@@ -427,6 +418,18 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
                wait_event(workload->shadow_ctx_status_wq,
                           !atomic_read(&workload->shadow_ctx_active));
 
+               /* If this request caused GPU hang, req->fence.error will
+                * be set to -EIO. Use -EIO to set workload status so
+                * that when this request caused GPU hang, didn't trigger
+                * context switch interrupt to guest.
+                */
+               if (likely(workload->status == -EINPROGRESS)) {
+                       if (workload->req->fence.error == -EIO)
+                               workload->status = -EIO;
+                       else
+                               workload->status = 0;
+               }
+
                i915_gem_request_put(fetch_and_zero(&workload->req));
 
                if (!workload->status && !vgpu->resetting) {