Skip to contentSkip to conversation

HSI: core: fix resource leaks in hsi_add_client_from_dt()

PATCH In review Dan Carpenter 2 participants 2 messages Apr 9, 2021

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 HSI: core: fix resource leaks in hsi_add_client_from_dt()

If some of the allocations fail between the dev_set_name() and the device_register() then the name will not be freed. Fix this by moving dev_set_name() directly in front of the call to device_register().

Fixes a2aa24734d9d ("HSI: Add common DT binding for HSI client devices")

---
Jason, this is the most common type of error I see with device_register(). Is there a downside to calling dev_set_name() later? Presumably it's printed out somewhere, but I feel like just moving the dev_set_name() is almost always the best and simplest fix.

 drivers/hsi/hsi_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/hsi/hsi_core.c +1 -2
index c3fb5beb846e..ec90713564e3 100644
@@ -210,8 +210,6 @@ static void hsi_add_client_from_dt(struct hsi_port *port,
 	if (err)
 		goto err;
 
-	dev_set_name(&cl->device, "%s", name);
-
 	err = hsi_of_property_parse_mode(client, "hsi-mode", &mode);
 	if (err) {
 		err = hsi_of_property_parse_mode(client, "hsi-rx-mode",
@@ -293,6 +291,7 @@ static void hsi_add_client_from_dt(struct hsi_port *port,
 	cl->device.release = hsi_client_release;
 	cl->device.of_node = client;
 
+	dev_set_name(&cl->device, "%s", name);
 	if (device_register(&cl->device) < 0) {
 		pr_err("hsi: failed to register client: %s\n", name);
 		put_device(&cl->device);
Signature · 1 line
2.30.2
Reviewed-by on v1 1/1
#1 lore raw
Quoted 11 lines · Dan Carpenter

If some of the allocations fail between the dev_set_name() and the device_register() then the name will not be freed. Fix this by moving dev_set_name() directly in front of the call to device_register().

Fixes a2aa24734d9d ("HSI: Add common DT binding for HSI client devices")

---
Jason, this is the most common type of error I see with device_register(). Is there a downside to calling dev_set_name() later? Presumably it's printed out somewhere, but I feel like just moving the dev_set_name() is almost always the best and simplest fix.

It is hard to tell without detailed analysis.. ie a dev_err()/etc call will use the name. It is why I don't like this design pattern of avoiding device_initialize() and using device_registrR()

This movement looks OK though

Jason