drm/msm: Hangcheck progress detection

If the hangcheck timer expires, check if the fw's position in the
cmdstream has advanced (changed) since last timer expiration, and
allow it up to three additional "extensions" to it's alotted time.
The intention is to continue to catch "shader stuck in a loop" type
hangs quickly, but allow more time for things that are actually
making forward progress.

Because we need to sample the CP state twice to detect if there has
not been progress, this also cuts the the timer's duration in half.

v2: Fix typo (REG_A6XX_CP_CSQ_IB2_STAT), add comment
v3: Only halve hangcheck timer duration for generations which
    support progress detection (hdanton); removed unused a5xx
    progress (without knowing how to adjust for data buffered
    in ROQ it is too likely to report a false negative)
v4: Comment updates to better describe the total hangcheck
    duration when progress detection is applied

Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Tested-by: Chia-I Wu <olvaffe@gmail.com> # dEQP-GLES2.functional.flush_finish.wait
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/511584/
Link: https://lore.kernel.org/r/20221114193049.1533391-3-robdclark@gmail.com

1 files changed, 30 insertions, 1 deletions

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0098ee8438aa..f7195b43cc6c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -492,6 +492,21 @@ static void hangcheck_timer_reset(struct msm_gpu *gpu)
 			round_jiffies_up(jiffies + msecs_to_jiffies(priv->hangcheck_period)));
 }
 
+static bool made_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	if (ring->hangcheck_progress_retries >= DRM_MSM_HANGCHECK_PROGRESS_RETRIES)
+		return false;
+
+	if (!gpu->funcs->progress)
+		return false;
+
+	if (!gpu->funcs->progress(gpu, ring))
+		return false;
+
+	ring->hangcheck_progress_retries++;
+	return true;
+}
+
 static void hangcheck_handler(struct timer_list *t)
 {
 	struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer);
@@ -502,9 +517,12 @@ static void hangcheck_handler(struct timer_list *t)
 	if (fence != ring->hangcheck_fence) {
 		/* some progress has been made.. ya! */
 		ring->hangcheck_fence = fence;
-	} else if (fence_before(fence, ring->fctx->last_fence)) {
+		ring->hangcheck_progress_retries = 0;
+	} else if (fence_before(fence, ring->fctx->last_fence) &&
+			!made_progress(gpu, ring)) {
 		/* no progress and not done.. hung! */
 		ring->hangcheck_fence = fence;
+		ring->hangcheck_progress_retries = 0;
 		DRM_DEV_ERROR(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n",
 				gpu->name, ring->id);
 		DRM_DEV_ERROR(dev->dev, "%s:     completed fence: %u\n",
@@ -830,6 +848,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
 		const char *name, struct msm_gpu_config *config)
 {
+	struct msm_drm_private *priv = drm->dev_private;
 	int i, ret, nr_rings = config->nr_rings;
 	void *memptrs;
 	uint64_t memptrs_iova;
@@ -857,6 +876,16 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	kthread_init_work(&gpu->recover_work, recover_worker);
 	kthread_init_work(&gpu->fault_work, fault_worker);
 
+	priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD;
+
+	/*
+	 * If progress detection is supported, halve the hangcheck timer
+	 * duration, as it takes two iterations of the hangcheck handler
+	 * to detect a hang.
+	 */
+	if (funcs->progress)
+		priv->hangcheck_period /= 2;
+
 	timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0);
 
 	spin_lock_init(&gpu->perf_lock);