On 26/08/25 12:13, Peter Zijlstra wrote:

Subject: sched/fair: Get rid of sched_domains_curr_level hack for tl->cpumask()
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 25 Aug 2025 12:02:44 +0000

Leon [1] and Vinicius [2] noted a topology_span_sane() warning during
their testing starting from v6.16-rc1. Debug that followed pointed to
the tl->mask() for the NODE domain being incorrectly resolved to that of
the highest NUMA domain.

tl->mask() for NODE is set to the sd_numa_mask() which depends on the
global "sched_domains_curr_level" hack. "sched_domains_curr_level" is
set to the "tl->numa_level" during tl traversal in build_sched_domains()
calling sd_init() but was not reset before topology_span_sane().

Since "tl->numa_level" still reflected the old value from
build_sched_domains(), topology_span_sane() for the NODE domain trips
when the span of the last NUMA domain overlaps.

Instead of replicating the "sched_domains_curr_level" hack, get rid of
it entirely and instead, pass the entire "sched_domain_topology_level"
object to tl->cpumask() function to prevent such mishap in the future.

sd_numa_mask() now directly references "tl->numa_level" instead of
relying on the global "sched_domains_curr_level" hack to index into
sched_domains_numa_masks[].

Eh, of course I see this *after* looking at the v6 patch.

I tested this again for good measure, but given I only test this under
x86 and the changes with v6 are in s390/ppc, I didn't expect to see much
change :-)

Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>