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: 4760a896be88e ("remoteproc: q6v5-mss: Vote for rpmh power domains")
Signed-off-by: Zhang Qilong <zhangqilong3@xxxxxxxxxx>
---
drivers/remoteproc/qcom_q6v5_mss.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index eb3457a6c3b7..ba6f7551242d 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -349,8 +349,11 @@ 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;
--
2.17.1
