Messages in this thread | | | Date | Thu, 3 Nov 2016 18:47:53 +0100 | From | Sebastian Andrzej Siewior <> | Subject | Re: [RFC PATCH] perf/x86/intel/rapl: avoid access unallocate memory |
| |
On 2016-11-02 18:47:49 [-0400], Charles (Chas) Williams wrote: > I don't this this is a race. Here is some debugging from the two CPU VM > (2 sockets, 1 core per socket). In identify_cpu() we have: > > /* The boot/hotplug time assigment got cleared, restore it */ > c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id); > > The values just after this: > > [ 0.228306] identify_cpu: c ffff88023fd0a040 logical_proc_id 65535 c->phys_proc_id 2 > > So what's interesting here, is the phys_proc_id of 2 for CPU1: > > int topology_phys_to_logical_pkg(unsigned int phys_pkg) > { > if (phys_pkg >= max_physical_pkg_id) > return -1; > return physical_to_logical_pkg[phys_pkg]; > } > > And we happen to know the max_physical_pkg_id is 2 in this case. > So apparently, topology_phys_to_logical_pkg() returns -1 and it gets > assigned to the logical_proc_id. > > I don't know why the CPU's phys_proc_id is 2.
This is the physical ID. You have two logical IDs (on your two sockets machine). What is max_physical_pkg_id? In order to get that -1 you would have to max_physical_pkg_id of 1 but code does max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
and I would be a little surprised if this is 1.
Sebastian
| |