remoteproc: q6v5-mss: fix error handling in q6v5_pds_enable

If the pm_runtime_get_sync failed in q6v5_pds_enable when
loop (i), The unroll_pd_votes will start from (i - 1), and
it will resulted in following problems:

  1) pm_runtime_get_sync will increment pm usage counter even it
     failed. Forgetting to pm_runtime_put_noidle will result in
     reference leak.

  2) Have not reset pds[i] performance state.

Then we fix it.

Fixes: 4760a896 ("remoteproc: q6v5-mss: Vote for rpmh power domains")
Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
Link: https://lore.kernel.org/r/20201102143433.143996-1-zhangqilong3@huawei.comSigned-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>

drivers/remoteproc/qcom_q6v5_mss.c

@@ -351,8 +351,11 @@ static int q6v5_pds_enable(struct q6v5 *qproc, struct device **pds,
 	for (i = 0; i < pd_count; i++) {
 		dev_pm_genpd_set_performance_state(pds[i], INT_MAX);
 		ret = pm_runtime_get_sync(pds[i]);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_noidle(pds[i]);
+			dev_pm_genpd_set_performance_state(pds[i], 0);
 			goto unroll_pd_votes;
+		}
 	}
 
 	return 0;