Merge tag 'drm-msm-next-2021-06-23b' of https://gitlab.freedesktop.org/drm/msm into drm-next

* devcoredump support for display errors
* dpu: irq cleanup/refactor
* dpu: dt bindings conversion to yaml
* dsi: dt bindings conversion to yaml
* mdp5: alpha/blend_mode/zpos support
* a6xx: cached coherent buffer support
* a660 support
* gpu iova fault improvements:
   - info about which block triggered the fault, etc
   - generation of gpu devcoredump on fault
* assortment of other cleanups and fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGs4=qsGBBbyn-4JWqW4-YUSTKh67X3DsPQ=T2D9aXKqNA@mail.gmail.com

1 files changed, 50 insertions, 1 deletions

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 9dd1c58430ab..0ebf7bc6ad09 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -387,6 +387,7 @@ 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 (submit) {
 		int i, nr = 0;
@@ -559,10 +560,57 @@ static void recover_worker(struct kthread_work *work)
 	msm_gpu_retire(gpu);
 }
 
+static void fault_worker(struct kthread_work *work)
+{
+	struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work);
+	struct drm_device *dev = gpu->dev;
+	struct msm_gem_submit *submit;
+	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
+	char *comm = NULL, *cmd = NULL;
+
+	mutex_lock(&dev->struct_mutex);
+
+	submit = find_submit(cur_ring, cur_ring->memptrs->fence + 1);
+	if (submit && submit->fault_dumped)
+		goto resume_smmu;
+
+	if (submit) {
+		struct task_struct *task;
+
+		task = get_pid_task(submit->pid, PIDTYPE_PID);
+		if (task) {
+			comm = kstrdup(task->comm, GFP_KERNEL);
+			cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL);
+			put_task_struct(task);
+		}
+
+		/*
+		 * When we get GPU iova faults, we can get 1000s of them,
+		 * but we really only want to log the first one.
+		 */
+		submit->fault_dumped = true;
+	}
+
+	/* Record the crash state */
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_crashstate_capture(gpu, submit, 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(&dev->struct_mutex);
+}
+
 static void hangcheck_timer_reset(struct msm_gpu *gpu)
 {
+	struct msm_drm_private *priv = gpu->dev->dev_private;
 	mod_timer(&gpu->hangcheck_timer,
-			round_jiffies_up(jiffies + DRM_MSM_HANGCHECK_JIFFIES));
+			round_jiffies_up(jiffies + msecs_to_jiffies(priv->hangcheck_period)));
 }
 
 static void hangcheck_handler(struct timer_list *t)
@@ -922,6 +970,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	INIT_LIST_HEAD(&gpu->active_list);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
+	kthread_init_work(&gpu->fault_work, fault_worker);
 
 	timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0);