[PATCH v2] coresight: Check runtime PM resume result

[PATCH v2] coresight: Check runtime PM resume result

[Yuho Choi]

coresight_get_ref() ignores the return value of pm_runtime_get_sync()
and reports success even when runtime resume fails. A path is then built
and the CoreSight device may be accessed while it remains powered off.

Use pm_runtime_resume_and_get() so a failed resume is reported and its
runtime PM usage reference is rolled back. Drop the module and device
references acquired before the resume attempt when it fails.

Fixes: 32b0707a4182 ("coresight: Add try_get_module() in coresight_grab_device()")
Signed-off-by: Yuho Choi <oss.patchbox@gmail.com>
---
Changes in v2:
- Point Fixes: at commit 32b0707a4182, which introduced coresight_get_ref()
  with the unchecked pm_runtime_get_sync() (Anshuman Khandual)
- Switch to my oss.patchbox address

v1: https://lore.kernel.org/all/20260802232552.593435-1-dbgh9129@gmail.com/

 drivers/hwtracing/coresight/coresight-core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 928488a216d4..c492f9082c46 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -843,7 +843,11 @@ static bool coresight_get_ref(struct coresight_device *csdev)
 		goto err_module;
 
 	/* Make sure the device is powered on */
-	pm_runtime_get_sync(parent);
+	if (pm_runtime_resume_and_get(parent) < 0) {
+		module_put(drv->owner);
+		goto err_module;
+	}
+
 	return true;
 
 err_module:

base-commit: f0100363d8c374bd8e9ea7c9ba02744f0b802ca4
-- 
2.43.0

Re: [PATCH v2] coresight: Check runtime PM resume result

[Leo Yan]

On Wed, Sep 23, 2026 at 08:18:56PM -0400, Yuho Choi wrote:

> @@ -843,7 +843,11 @@ static bool coresight_get_ref(struct coresight_device *csdev)
>  		goto err_module;
>  
>  	/* Make sure the device is powered on */
> -	pm_runtime_get_sync(parent);
> +	if (pm_runtime_resume_and_get(parent) < 0) {
> +		module_put(drv->owner);
> +		goto err_module;
> +	}
> +

There is already a patch that does something similar and fixes the same
errors across the CoreSight folder. See:

https://lore.kernel.org/linux-arm-kernel/20260911-b4-coresight-runtime-pm-failures-v1-1-acdf49756e11@qti.qualcomm.com/