[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201228124949.879848158@linuxfoundation.org>
Date: Mon, 28 Dec 2020 13:48:19 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Zhang Qilong <zhangqilong3@...wei.com>,
Bjorn Andersson <bjorn.andersson@...aro.org>,
Sasha Levin <sashal@...nel.org>
Subject: [PATCH 5.4 263/453] remoteproc: q6v5-mss: fix error handling in q6v5_pds_enable
From: Zhang Qilong <zhangqilong3@...wei.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@...wei.com>
Link: https://lore.kernel.org/r/20201102143433.143996-1-zhangqilong3@huawei.com
Signed-off-by: Bjorn Andersson <bjorn.andersson@...aro.org>
Signed-off-by: Sasha Levin <sashal@...nel.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 a67c55785b4de..5e54e6f5edb1a 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -331,8 +331,11 @@ 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;
--
2.27.0
Powered by blists - more mailing lists