1 files changed, 36 insertions, 2 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 0d39e8fdb16f..9c5e4618aa0a 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1193,6 +1193,16 @@ static int a6xx_fault_handler(void *arg, unsigned long iova, int flags, void *da
 	struct msm_gpu *gpu = arg;
 	struct adreno_smmu_fault_info *info = data;
 	const char *type = "UNKNOWN";
+	const char *block;
+	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
@@ -1216,15 +1226,30 @@ static int a6xx_fault_handler(void *arg, unsigned long iova, int flags, void *da
 	else if (info->fsr & ARM_SMMU_FSR_EF)
 		type = "EXTERNAL";
 
+	block = a6xx_fault_block(gpu, info->fsynr1 & 0xff);
+
 	pr_warn_ratelimited("*** gpu fault: ttbr0=%.16llx iova=%.16lx dir=%s type=%s source=%s (%u,%u,%u,%u)\n",
 			info->ttbr0, iova,
-			flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ", type,
-			a6xx_fault_block(gpu, info->fsynr1 & 0xff),
+			flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ",
+			type, block,
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)),
 			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)));
 
+	if (do_devcoredump) {
+		/* Turn off the hangcheck timer to keep it from bothering us */
+		del_timer(&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;
+
+		kthread_queue_work(gpu->worker, &gpu->fault_work);
+	}
+
 	return 0;
 }
 
@@ -1277,6 +1302,15 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 
 	/*
+	 * If stalled on SMMU fault, we could trip the GPU's hang detection,
+	 * but the fault handler will trigger the devcore dump, and we want
+	 * to otherwise resume normally rather than killing the submit, so
+	 * just bail.
+	 */
+	if (gpu_read(gpu, REG_A6XX_RBBM_STATUS3) & A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT)
+		return;
+
+	/*
 	 * Force the GPU to stay on until after we finish
 	 * collecting information
 	 */