HSI: core: fix resource leaks in hsi_add_client_from_dt()
Subsystems (2)
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().
---
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
@@ -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
Quoted 11 lines · Dan Carpenter
If some of the allocations fail between the
dev_set_name()and thedevice_register()then the name will not be freed. Fix this by movingdev_set_name()directly in front of the call todevice_register().Fixes a2aa24734d9d ("HSI: Add common DT binding for HSI client devices")Signed-off-by Dan Carpenter <[email protected]>---
Jason, this is the most common type of error I see withdevice_register(). Is there a downside to callingdev_set_name()later? Presumably it's printed out somewhere, but I feel like just moving thedev_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