Commit a2472305 authored Nov 02, 2020 by Zhang Qilong Committed by Bjorn Andersson Dec 10, 2020

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.com


Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>

parent e59aef4e

drivers/remoteproc/qcom_q6v5_mss.c

+4 −1

Original line number	Diff line number	Diff line
		@@ -351,9 +351,12 @@ 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;

Admin message