From: Zhang Qilong zhangqilong3@huawei.com
[ Upstream commit a24723050037303e4008b37f1f8dcc99c58901aa ]
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@huawei.com Link: https://lore.kernel.org/r/20201102143433.143996-1-zhangqilong3@huawei.com Signed-off-by: Bjorn Andersson bjorn.andersson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- 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 eb3457a6c3b73..ba6f7551242de 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;