[PATCH 1/2] drm/msm/a3xx: Add hangcheck progress detection

[Dmitry Baryshkov]

A3xx has no progress callback, so the hangcheck declares a lockup as soon
as a submit is still running when the timer expires, no matter whether
the CP is advancing. On A306 a piglit tex-miplevel-selection run is a
single submit of about 58k draws that takes 1.2-1.3 s to complete, and it
gets reset partway through on every run. With the hangcheck period raised
to 10 s the same runs pass without a hang.

Compare the CP IB1/IB2 base and remaining size between timer expirations,
like a6xx does. On A306 these move on every 20 ms sample while such a
submit executes and read zero when idle. The prefetch queues are small
(32 and 64 for IB1 and IB2), so buffered data does not hide progress for
long.

Assisted-by: LLM
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxxxxxxxx>
---
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 0259e60b8011..c95bbb4bcf47 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -536,6 +536,23 @@ static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return ring->memptrs->rptr;
 }
 
+static bool a3xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+{
+	struct msm_cp_state cp_state = {
+		.ib1_base = gpu_read(gpu, REG_AXXX_CP_IB1_BASE),
+		.ib2_base = gpu_read(gpu, REG_AXXX_CP_IB2_BASE),
+		.ib1_rem  = gpu_read(gpu, REG_AXXX_CP_IB1_BUFSZ),
+		.ib2_rem  = gpu_read(gpu, REG_AXXX_CP_IB2_BUFSZ),
+	};
+	bool progress;
+
+	progress = !!memcmp(&cp_state, &ring->last_cp_state, sizeof(cp_state));
+
+	ring->last_cp_state = cp_state;
+
+	return progress;
+}
+
 static struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 {
 	struct a3xx_gpu *a3xx_gpu = NULL;
@@ -630,6 +647,7 @@ const struct adreno_gpu_funcs a3xx_gpu_funcs = {
 		.gpu_state_put = adreno_gpu_state_put,
 		.create_vm = adreno_create_vm,
 		.get_rptr = a3xx_get_rptr,
+		.progress = a3xx_progress,
 	},
 	.init = a3xx_gpu_init,
 };

-- 
2.47.3