| Message ID | c3b5546444a33840c569e9b7b968f5f81db96ac0.1620207353.git.mchehab+huawei@kernel.org |
|---|---|
| State | Accepted |
| Commit | 220955ec3c84505ec6a75bea494ec61f5295ef7a |
| Headers | show |
| Series | [01/25] staging: media: rkvdec: fix pm_runtime_get_sync() usage count | expand |
diff --git a/drivers/media/platform/renesas-ceu.c b/drivers/media/platform/renesas-ceu.c index cd137101d41e..17f01b6e3fe0 100644 --- a/drivers/media/platform/renesas-ceu.c +++ b/drivers/media/platform/renesas-ceu.c @@ -1099,10 +1099,10 @@ static int ceu_open(struct file *file) mutex_lock(&ceudev->mlock); /* Causes soft-reset and sensor power on on first open */ - pm_runtime_get_sync(ceudev->dev); + ret = pm_runtime_resume_and_get(ceudev->dev); mutex_unlock(&ceudev->mlock); - return 0; + return ret; } static int ceu_release(struct file *file)
Right now, the driver just assumes that PM runtime resume worked, but it may fail. Well, the pm_runtime_get_sync() internally increments the dev->power.usage_count without decrementing it, even on errors. So, using it is tricky. Let's replace it by the new pm_runtime_resume_and_get(), introduced by: commit dd8088d5a896 ("PM: runtime: Add pm_runtime_resume_and_get to deal with usage counter") and return an error if something bad happens. This should ensure that the PM runtime usage_count will be properly decremented if an error happens at open time. Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> --- drivers/media/platform/renesas-ceu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)