SH> At checkpoint, you only need the uts_sem right around the reading SH> (and length-checking) of uts_ns->name. You're keeping it around SH> writing into the checkpoint image (and cr_hbuf_get). Right, okay. SH> At restart, you shouldn't actually need uts_sem - the nsproxy is SH> not yet available to anyone else, so there is no chance of a race, SH> right? Hmm, well maybe I'm being overly optimistic, since restart SH> is coordinated by userspace which could mess up and somehow run SH> sethostname(2) while it's supposed to be running sys_restart(). SH> But then sys_restart() wouldn't yet have hooked up the task to the SH> new nsproxy. Good, you passed the test. Yeah, that's it... :) -- Dan Smith IBM Linux Technology Center email: danms@xxxxxxxxxx _______________________________________________ Containers mailing list Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/containers
