On 04/12/2018 04:44 AM, Erik Skultety wrote: > On Thu, Apr 12, 2018 at 09:14:50AM +0200, Michal Privoznik wrote: >> In 2ada9ef1465f we've tried to turn virDomainChrSourceDef into >> virObject. Well, this requires 'virObject' member to be stored on >> the first position of the struct. This adjustment is missing in >> the original commit leading to all sorts of funny memleaks and >> data corruptions. >> >> Signed-off-by: Michal Privoznik <mprivozn@xxxxxxxxxx> >> --- >> src/conf/domain_conf.h | 2 ++ >> 1 file changed, 2 insertions(+) >> Doh! Thanks.... I guess not only do we need a way to detect that we're using VIR_ALLOC on an object (as Eric pointed out in my original patches), but we really should detect when we use virObjectNew without the virObject parent. For some reason, I have a recollection of altering changes during my meanderings through virObject code in order to point out more directly some misuses, but it was rejected. Although I cannot recall if this particular instance of not having virObject parent was addressed... Tks - John >> diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h >> index 89a7131fdb..1426f115ed 100644 >> --- a/src/conf/domain_conf.h >> +++ b/src/conf/domain_conf.h >> @@ -57,6 +57,7 @@ >> # include "virtypedparam.h" >> # include "virsavecookie.h" >> # include "virresctrl.h" >> +# include "virobject.h" > > syntax-check fails ^here because the header is already included on line 49 > > With that fixed: > Reviewed-by: Erik Skultety <eskultet@xxxxxxxxxx> > > -- > libvir-list mailing list > libvir-list@xxxxxxxxxx > https://www.redhat.com/mailman/listinfo/libvir-list > -- libvir-list mailing list libvir-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/libvir-list
