sched/fair: Get rid of sched_domains_curr_level hack for tl->cpumask()

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[].

The original warning was reproducible on the following NUMA topology
reported by Leon:

    $ sudo numactl -H
    available: 5 nodes (0-4)
    node 0 cpus: 0 1
    node 0 size: 2927 MB
    node 0 free: 1603 MB
    node 1 cpus: 2 3
    node 1 size: 3023 MB
    node 1 free: 3008 MB
    node 2 cpus: 4 5
    node 2 size: 3023 MB
    node 2 free: 3007 MB
    node 3 cpus: 6 7
    node 3 size: 3023 MB
    node 3 free: 3002 MB
    node 4 cpus: 8 9
    node 4 size: 3022 MB
    node 4 free: 2718 MB
    node distances:
    node   0   1   2   3   4
      0:  10  39  38  37  36
      1:  39  10  38  37  36
      2:  38  38  10  37  36
      3:  37  37  37  10  36
      4:  36  36  36  36  10

The above topology can be mimicked using the following QEMU cmd that was
used to reproduce the warning and test the fix:

     sudo qemu-system-x86_64 -enable-kvm -cpu host \
     -m 20G -smp cpus=10,sockets=10 -machine q35 \
     -object memory-backend-ram,size=4G,id=m0 \
     -object memory-backend-ram,size=4G,id=m1 \
     -object memory-backend-ram,size=4G,id=m2 \
     -object memory-backend-ram,size=4G,id=m3 \
     -object memory-backend-ram,size=4G,id=m4 \
     -numa node,cpus=0-1,memdev=m0,nodeid=0 \
     -numa node,cpus=2-3,memdev=m1,nodeid=1 \
     -numa node,cpus=4-5,memdev=m2,nodeid=2 \
     -numa node,cpus=6-7,memdev=m3,nodeid=3 \
     -numa node,cpus=8-9,memdev=m4,nodeid=4 \
     -numa dist,src=0,dst=1,val=39 \
     -numa dist,src=0,dst=2,val=38 \
     -numa dist,src=0,dst=3,val=37 \
     -numa dist,src=0,dst=4,val=36 \
     -numa dist,src=1,dst=0,val=39 \
     -numa dist,src=1,dst=2,val=38 \
     -numa dist,src=1,dst=3,val=37 \
     -numa dist,src=1,dst=4,val=36 \
     -numa dist,src=2,dst=0,val=38 \
     -numa dist,src=2,dst=1,val=38 \
     -numa dist,src=2,dst=3,val=37 \
     -numa dist,src=2,dst=4,val=36 \
     -numa dist,src=3,dst=0,val=37 \
     -numa dist,src=3,dst=1,val=37 \
     -numa dist,src=3,dst=2,val=37 \
     -numa dist,src=3,dst=4,val=36 \
     -numa dist,src=4,dst=0,val=36 \
     -numa dist,src=4,dst=1,val=36 \
     -numa dist,src=4,dst=2,val=36 \
     -numa dist,src=4,dst=3,val=36 \
     ...

  [ prateek: Moved common functions to include/linux/sched/topology.h,
    reuse the common bits for s390 and ppc, commit message ]

Closes: https://lore.kernel.org/lkml/20250610110701.GA256154@unreal/ [1]
Fixes: ccf74128d66c ("sched/topology: Assert non-NUMA topology masks don't (partially) overlap") # ce29a7da84cd, f55dac1dafb3
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Tested-by: Valentin Schneider <vschneid@redhat.com> # x86
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com> # powerpc
Link: https://lore.kernel.org/lkml/a3de98387abad28592e6ab591f3ff6107fe01dc1.1755893468.git.tim.c.chen@linux.intel.com/ [2]

1 files changed, 10 insertions, 18 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 977e133bb8a4..18889bd97e22 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1591,7 +1591,6 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 enum numa_topology_type sched_numa_topology_type;
 
 static int			sched_domains_numa_levels;
-static int			sched_domains_curr_level;
 
 int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
@@ -1632,14 +1631,7 @@ sd_init(struct sched_domain_topology_level *tl,
 	int sd_id, sd_weight, sd_flags = 0;
 	struct cpumask *sd_span;
 
-#ifdef CONFIG_NUMA
-	/*
-	 * Ugly hack to pass state to sd_numa_mask()...
-	 */
-	sched_domains_curr_level = tl->numa_level;
-#endif
-
-	sd_weight = cpumask_weight(tl->mask(cpu));
+	sd_weight = cpumask_weight(tl->mask(tl, cpu));
 
 	if (tl->sd_flags)
 		sd_flags = (*tl->sd_flags)();
@@ -1677,7 +1669,7 @@ sd_init(struct sched_domain_topology_level *tl,
 	};
 
 	sd_span = sched_domain_span(sd);
-	cpumask_and(sd_span, cpu_map, tl->mask(cpu));
+	cpumask_and(sd_span, cpu_map, tl->mask(tl, cpu));
 	sd_id = cpumask_first(sd_span);
 
 	sd->flags |= asym_cpu_capacity_classify(sd_span, cpu_map);
@@ -1737,17 +1729,17 @@ sd_init(struct sched_domain_topology_level *tl,
  */
 static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT),
+	SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT),
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
-	SDTL_INIT(cpu_clustergroup_mask, cpu_cluster_flags, CLS),
+	SDTL_INIT(tl_cls_mask, cpu_cluster_flags, CLS),
 #endif
 
 #ifdef CONFIG_SCHED_MC
-	SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC),
+	SDTL_INIT(tl_mc_mask, cpu_core_flags, MC),
 #endif
-	SDTL_INIT(cpu_cpu_mask, NULL, PKG),
+	SDTL_INIT(tl_pkg_mask, NULL, PKG),
 	{ NULL, },
 };
 
@@ -1769,9 +1761,9 @@ void __init set_sched_topology(struct sched_domain_topology_level *tl)
 
 #ifdef CONFIG_NUMA
 
-static const struct cpumask *sd_numa_mask(int cpu)
+static const struct cpumask *sd_numa_mask(struct sched_domain_topology_level *tl, int cpu)
 {
-	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+	return sched_domains_numa_masks[tl->numa_level][cpu_to_node(cpu)];
 }
 
 static void sched_numa_warn(const char *str)
@@ -2411,7 +2403,7 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
 		 * breaks the linking done for an earlier span.
 		 */
 		for_each_cpu(cpu, cpu_map) {
-			const struct cpumask *tl_cpu_mask = tl->mask(cpu);
+			const struct cpumask *tl_cpu_mask = tl->mask(tl, cpu);
 			int id;
 
 			/* lowest bit set in this mask is used as a unique id */
@@ -2419,7 +2411,7 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
 
 			if (cpumask_test_cpu(id, id_seen)) {
 				/* First CPU has already been seen, ensure identical spans */
-				if (!cpumask_equal(tl->mask(id), tl_cpu_mask))
+				if (!cpumask_equal(tl->mask(tl, id), tl_cpu_mask))
 					return false;
 			} else {
 				/* First CPU hasn't been seen before, ensure it's a completely new span */