On Mon, Sep 29, 2014 at 11:45:23AM +0200, Philipp Zabel wrote: > Am Montag, den 29.09.2014, 12:13 +0300 schrieb Dan Carpenter: > > On Mon, Sep 29, 2014 at 10:15:44AM +0200, Philipp Zabel wrote: > > > In preparation for a following patch, stop decrementing the endpoint node > > > refcount in the loop. This temporarily leaks a reference to the endpoint node, > > > which will be fixed by having of_graph_get_next_endpoint decrement the refcount > > > of its prev argument instead. > > > > Don't do this... > > > > My understanding (and I haven't invested much time into trying to > > understand this beyond glancing at the change) is that patch 1 and 2, > > introduce small bugs that are fixed in patch 3? > > > > Just fold all three patches into one patch. We need an Ack from Mauro > > and Greg and then send the patch through Grant's tree. > > Yes. Patches 1 and 2 leak a reference on of_nodes touched by the loop. > As far as I am aware, all users of this code don't use the reference > counting (CONFIG_OF_DYNAMIC is disabled), so this bug should be > theoretical. > > I'd be happy do as you suggest if Mauro and Greg agree. Let's see the correct patch, don't break things and then later on fix them... thanks, greg k-h -- To unsubscribe from this list: send the line "unsubscribe linux-media" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
