[PATCH v2] drm/i915/gvt: add a spin_lock to protect the current_workload

[Chuanxiao Dong]

There is a corner case which can cause kernel panic after a GPU reset.
The reason for this kernel panic is that, sometimes there is still a
context switch comes from HW to notify SW for a failed workload. But
as it is a failed workload, GVT has already freed this workload and
the current_workload in scheduler is NULL. Accessing NULL caused kernel
panic. So this issue is caused by unsynchronized between the workload
free and unexpected notification handling.

To protect the current_workload, add a spin_lock. So it can provide a
chance for SW to synchronize with each other to avoid such kind of
conflict.

v2: update the commit message;
    add EINPROGRESS check for workload->status

Signed-off-by: Chuanxiao Dong <chuanxiao.dong at intel.com>
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 30 ++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/gvt/scheduler.h |  2 ++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 7ea68a7..c300197 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -136,8 +136,30 @@ static int shadow_context_status_change(struct notifier_block *nb,
 		(struct drm_i915_gem_request *)data;
 	struct intel_gvt_workload_scheduler *scheduler =
 		&vgpu->gvt->scheduler;
-	struct intel_vgpu_workload *workload =
-		scheduler->current_workload[req->engine->id];
+	struct intel_vgpu_workload *workload;
+	unsigned long flags;
+
+	spin_lock_irqsave(&scheduler->cur_workload_lock, flags);
+	workload = scheduler->current_workload[req->engine->id];
+	/* Sometimes a failed workload still has this notification
+	 * from HW side.
+	 * So at this point, the failed workload may
+	 * already been freed. In this case, do nothing. Even the
+	 * failed workload is not freed yet, still do nothing.
+	 *
+	 * Another case, when we goes here, this workload is actually
+	 * a new workload already and we cannot do the context schedule
+	 * out based on the last failed one.
+	 */
+	if (unlikely(!workload ||
+		((workload->status != -EINPROGRESS && workload->status) ||
+		 vgpu->resetting) ||
+		(action == INTEL_CONTEXT_SCHEDULE_OUT &&
+		!atomic_read(&workload->shadow_ctx_active)))) {
+		spin_unlock_irqrestore(&scheduler->cur_workload_lock, flags);
+		return NOTIFY_OK;
+	}
+	spin_unlock_irqrestore(&scheduler->cur_workload_lock, flags);
 
 	switch (action) {
 	case INTEL_CONTEXT_SCHEDULE_IN:
@@ -352,6 +374,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	struct intel_vgpu_workload *workload;
 	struct intel_vgpu *vgpu;
 	int event;
+	unsigned long flags;
 
 	mutex_lock(&gvt->lock);
 
@@ -372,7 +395,9 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
 			ring_id, workload, workload->status);
 
+	spin_lock_irqsave(&scheduler->cur_workload_lock, flags);
 	scheduler->current_workload[ring_id] = NULL;
+	spin_unlock_irqrestore(&scheduler->cur_workload_lock, flags);
 
 	list_del_init(&workload->list);
 	workload->complete(workload);
@@ -513,6 +538,7 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
 
 	gvt_dbg_core("init workload scheduler\n");
 
+	spin_lock_init(&scheduler->cur_workload_lock);
 	init_waitqueue_head(&scheduler->workload_complete_wq);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 2833dfa..b446ea9 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -40,6 +40,8 @@ struct intel_gvt_workload_scheduler {
 	struct intel_vgpu *current_vgpu;
 	struct intel_vgpu *next_vgpu;
 	struct intel_vgpu_workload *current_workload[I915_NUM_ENGINES];
+	/* For current_workload handling sync */
+	spinlock_t cur_workload_lock;
 	bool need_reschedule;
 
 	wait_queue_head_t workload_complete_wq;
-- 
2.7.4