drm/msm: Don't use a worker to capture fault devcoredump

Now that we use a threaded IRQ, it should be safe to do this in the
fault handler.

We can also remove fault_info from struct msm_gpu and just pass it
directly.

Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654889/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>

Author: cwabbott0

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -270,14 +270,6 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 	const char *type = "UNKNOWN";
 	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
 
-	/*
-	 * If we aren't going to be resuming later from fault_worker, then do
-	 * it now.
-	 */
-	if (!do_devcoredump) {
-		gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-	}
-
 	/*
 	 * Print a default message if we couldn't get the data from the
 	 * adreno-smmu-priv
@@ -304,16 +296,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			scratch[0], scratch[1], scratch[2], scratch[3]);
 
 	if (do_devcoredump) {
+		struct msm_gpu_fault_info fault_info = {};
+
 		/* Turn off the hangcheck timer to keep it from bothering us */
 		timer_delete(&gpu->hangcheck_timer);
 
-		gpu->fault_info.ttbr0 = info->ttbr0;
-		gpu->fault_info.iova  = iova;
-		gpu->fault_info.flags = flags;
-		gpu->fault_info.type  = type;
-		gpu->fault_info.block = block;
+		fault_info.ttbr0 = info->ttbr0;
+		fault_info.iova  = iova;
+		fault_info.flags = flags;
+		fault_info.type  = type;
+		fault_info.block = block;
 
-		kthread_queue_work(gpu->worker, &gpu->fault_work);
+		msm_gpu_fault_crashstate_capture(gpu, &fault_info);
 	}
 
 	return 0;

drivers/gpu/drm/msm/msm_gpu.c

@@ -257,7 +257,8 @@ static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
 }
 
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 	struct msm_gpu_state *state;
 
@@ -276,7 +277,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	/* Fill in the additional crash state information */
 	state->comm = kstrdup(comm, GFP_KERNEL);
 	state->cmd = kstrdup(cmd, GFP_KERNEL);
-	state->fault_info = gpu->fault_info;
+	if (fault_info)
+		state->fault_info = *fault_info;
 
 	if (submit) {
 		int i;
@@ -308,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 }
 #else
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 }
 #endif
@@ -405,7 +408,7 @@ static void recover_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd);
 
 	kfree(cmd);
 	kfree(comm);
@@ -459,9 +462,8 @@ static void recover_worker(struct kthread_work *work)
 	msm_gpu_retire(gpu);
 }
 
-static void fault_worker(struct kthread_work *work)
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info)
 {
-	struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work);
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
 	char *comm = NULL, *cmd = NULL;
@@ -484,16 +486,13 @@ static void fault_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
 	kfree(cmd);
 	kfree(comm);
 
 resume_smmu:
-	memset(&gpu->fault_info, 0, sizeof(gpu->fault_info));
-	gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-
 	mutex_unlock(&gpu->lock);
 }
 
@@ -882,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	init_waitqueue_head(&gpu->retire_event);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
-	kthread_init_work(&gpu->fault_work, fault_worker);
 
 	priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD;
 

drivers/gpu/drm/msm/msm_gpu.h

@@ -253,12 +253,6 @@ struct msm_gpu {
 #define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3
 	struct timer_list hangcheck_timer;
 
-	/* Fault info for most recent iova fault: */
-	struct msm_gpu_fault_info fault_info;
-
-	/* work for handling GPU ioval faults: */
-	struct kthread_work fault_work;
-
 	/* work for handling GPU recovery: */
 	struct kthread_work recover_work;
 
@@ -705,6 +699,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->lock);
 }
 
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info);
+
 /*
  * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
  * support expanded privileges