drm/i915/gvt: Fix GPU hang after reusing vGPU instance across different guest OS

We have implemented delayed ring mmio switch mechanism to reduce
unnecessary mmio switch. While the vGPU is being destroyed or
detached from VM, we need to force the ring switch to host context.

The later deadline is missed. Then it got a chance that word load
from VM2 might execute under the ring context of VM1 which was
attached to a same vGPU instance. Finally, the GPU is hang.

This patch guarantee the two deadline are performed.

v2: Remove unused variable 'scheduler'

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 436377da41baced8e81352587cc3e035d0dc1ba3..03532dfc0cd51b8342e50da61524024dafc8ac34 100644 (file)
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -308,20 +308,8 @@ static int tbs_sched_init_vgpu(struct intel_vgpu *vgpu)
 
 static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu)
 {
-       struct intel_gvt_workload_scheduler *scheduler = &vgpu->gvt->scheduler;
-       int ring_id;
-
        kfree(vgpu->sched_data);
        vgpu->sched_data = NULL;
-
-       spin_lock_bh(&scheduler->mmio_context_lock);
-       for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
-               if (scheduler->engine_owner[ring_id] == vgpu) {
-                       intel_gvt_switch_mmio(vgpu, NULL, ring_id);
-                       scheduler->engine_owner[ring_id] = NULL;
-               }
-       }
-       spin_unlock_bh(&scheduler->mmio_context_lock);
 }
 
 static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
@@ -388,6 +376,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 {
        struct intel_gvt_workload_scheduler *scheduler =
                &vgpu->gvt->scheduler;
+       int ring_id;
 
        gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
 
@@ -401,4 +390,13 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
                scheduler->need_reschedule = true;
                scheduler->current_vgpu = NULL;
        }
+
+       spin_lock_bh(&scheduler->mmio_context_lock);
+       for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
+               if (scheduler->engine_owner[ring_id] == vgpu) {
+                       intel_gvt_switch_mmio(vgpu, NULL, ring_id);
+                       scheduler->engine_owner[ring_id] = NULL;
+               }
+       }
+       spin_unlock_bh(&scheduler->mmio_context_lock);
 }