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, 27 insertions, 1 deletions

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 5263746b63e8..a3a24e115d44 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -30,11 +30,19 @@ struct sd_flag_debug {
 };
 extern const struct sd_flag_debug sd_flag_debug[];
 
+struct sched_domain_topology_level;
+
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {
 	return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
 }
+
+static inline const
+struct cpumask *tl_smt_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_smt_mask(cpu);
+}
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
@@ -42,6 +50,12 @@ static inline int cpu_cluster_flags(void)
 {
 	return SD_CLUSTER | SD_SHARE_LLC;
 }
+
+static inline const
+struct cpumask *tl_cls_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_clustergroup_mask(cpu);
+}
 #endif
 
 #ifdef CONFIG_SCHED_MC
@@ -49,8 +63,20 @@ static inline int cpu_core_flags(void)
 {
 	return SD_SHARE_LLC;
 }
+
+static inline const
+struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_coregroup_mask(cpu);
+}
 #endif
 
+static inline const
+struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu)
+{
+	return cpu_node_mask(cpu);
+}
+
 #ifdef CONFIG_NUMA
 static inline int cpu_numa_flags(void)
 {
@@ -172,7 +198,7 @@ bool cpus_equal_capacity(int this_cpu, int that_cpu);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 bool cpus_share_resources(int this_cpu, int that_cpu);
 
-typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef const struct cpumask *(*sched_domain_mask_f)(struct sched_domain_topology_level *tl, int cpu);
 typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {