[PATCH v4 3/4] media: wave5: handle encoder runtime resume failures

[Jiale Yao]

The encoder callbacks ignore failures from pm_runtime_resume_and_get()
and continue issuing firmware commands. Runtime resume can fail while
enabling the VPU clocks, leaving the registers inaccessible. The
callbacks can then drop a runtime PM reference that was not acquired.

Runtime PM retains a resume error, so simply finishing the current job
leaves PIC_RUN runnable and causes the mem2mem scheduler to retry the
same failing job. On a resume failure, stop the instance, mark both
queues in error, return their queued buffers as errors, and finish the
job. Also stop the instance in stop_streaming() before attempting the
runtime resume, since the state transition only touches software state.
Propagate the error from start_streaming() and preserve buffer cleanup
without accessing the hardware or issuing an unmatched put.

Fixes: 2092b3833487 ("media: chips-media: wave5: Support runtime suspend/resume")
Cc: stable@xxxxxxxxxxxxxxx
Reviewed-by: Jackson Lee <jackson.lee@xxxxxxxxxxxxxxx>
Signed-off-by: Jiale Yao <yaojiale02@xxxxxxx>
---
 .../chips-media/wave5/wave5-vpu-enc.c         | 35 ++++++++++++++++---
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
index f9fcdf4c22..3463b7d7fb 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
@@ -1351,7 +1351,12 @@ static int wave5_vpu_enc_start_streaming(struct vb2_queue *q, unsigned int count
 	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
 	int ret = 0;
 
-	pm_runtime_resume_and_get(inst->dev->dev);
+	ret = pm_runtime_resume_and_get(inst->dev->dev);
+	if (ret < 0) {
+		wave5_return_bufs(q, VB2_BUF_STATE_QUEUED);
+		return ret;
+	}
+
 	v4l2_m2m_update_start_streaming_state(m2m_ctx, q);
 
 	if (inst->state == VPU_INST_STATE_NONE && q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
@@ -1451,6 +1456,7 @@ static void wave5_vpu_enc_stop_streaming(struct vb2_queue *q)
 {
 	struct vpu_instance *inst = vb2_get_drv_priv(q);
 	bool check_cmd = true;
+	int ret;
 
 	/*
 	 * Note that we don't need m2m_ctx->next_buf_last for this driver, so we
@@ -1458,11 +1464,18 @@ static void wave5_vpu_enc_stop_streaming(struct vb2_queue *q)
 	 */
 
 	dev_dbg(inst->dev->dev, "%s: type: %u\n", __func__, q->type);
-	pm_runtime_resume_and_get(inst->dev->dev);
-
 	if (wave5_vpu_both_queues_are_streaming(inst))
 		switch_state(inst, VPU_INST_STATE_STOP);
 
+	ret = pm_runtime_resume_and_get(inst->dev->dev);
+	if (ret < 0) {
+		if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+			streamoff_output(inst, q);
+		else
+			streamoff_capture(inst, q);
+		return;
+	}
+
 	while (check_cmd) {
 		struct queue_status_info q_status;
 		struct enc_output_info enc_output_info;
@@ -1526,7 +1539,21 @@ static void wave5_vpu_enc_device_run(void *priv)
 	u32 fail_res = 0;
 	int ret = 0;
 
-	pm_runtime_resume_and_get(inst->dev->dev);
+	ret = pm_runtime_resume_and_get(inst->dev->dev);
+	if (ret < 0) {
+		struct vb2_queue *src_vq = v4l2_m2m_get_src_vq(m2m_ctx);
+		struct vb2_queue *dst_vq = v4l2_m2m_get_dst_vq(m2m_ctx);
+
+		dev_err(inst->dev->dev, "Failed to resume VPU: %d\n", ret);
+		switch_state(inst, VPU_INST_STATE_STOP);
+		vb2_queue_error(src_vq);
+		vb2_queue_error(dst_vq);
+		wave5_return_bufs(src_vq, VB2_BUF_STATE_ERROR);
+		wave5_return_bufs(dst_vq, VB2_BUF_STATE_ERROR);
+		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
+		return;
+	}
+
 	switch (inst->state) {
 	case VPU_INST_STATE_PIC_RUN:
 		ret = start_encode(inst, &fail_res);
-- 
2.34.1