Messages in this thread | | | Date | Thu, 29 Jun 2023 21:27:10 +0800 | From | Feng Tang <> | Subject | Re: [Patch v2 2/2] x86/tsc: use logical_packages as a better estimation of socket numbers |
| |
On Tue, Jun 27, 2023 at 01:14:34PM +0200, Thomas Gleixner wrote: > On Sun, Jun 25 2023 at 22:51, Feng Tang wrote: > > From debug, the reason of the hung/stall is detect_extended_topology_early() > > is called by cpu hotplug after boot, where there is "maxcpus=XXX" setting, > > (#echo 1 > /sys/devices/system/cpu/cpuX/online). > > > > It could be fixed with below patch: > > ---------------------------------------------------------------- > > diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c > > index 828c1f7edac1..1ff73c8c4972 100644 > > --- a/arch/x86/kernel/cpu/topology.c > > +++ b/arch/x86/kernel/cpu/topology.c > > @@ -29,7 +29,7 @@ unsigned int __max_die_per_package __read_mostly = 1; > > EXPORT_SYMBOL(__max_die_per_package); > > > > #ifdef CONFIG_SMP > > -unsigned int apic_to_pkg_shift __ro_after_init; > > +unsigned int apic_to_pkg_shift; > > Bah, yes. I missed the early_init() call from init_intel(). I hate that > code with a passion.
I tested the patch on a 2S Icelake with Sub-NUMA-Cluster enabled, which shows 4 NUMA nodes, and this patch gave the right package number: 2
On a hybrid system Alderlake with 8 P-core and 8 E-core, '__max_logical_packages' is 1.
I also tried 'acpi=off' parameter. On a 2S Cascade Lake box, it only brought up one CPU due to no MP table, while on another single socket 18C/36T Cascade Lake box which has MP table, it brought up 18 CPUs. The '__max_logical_packages' is 1 for both of them.
The patch covers most of cases we have listed, so feel free to add:
Tested-by: Feng Tang <feng.tang@intel.com>
Thanks, Feng
| |