powerpc/smp: Check for duplicate topologies and consolidate

CACHE and COREGROUP domains are now part of default topology. However on
systems that don't support CACHE or COREGROUP, these domains will
eventually be degenerated. The degeneration happens per CPU. Do note the
current fixup_topology() logic ensures that mask of a domain that is not
supported on the current platform is set to the previous domain.

Instead of waiting for the scheduler to degenerated try to consolidate
based on their masks and sd_flags. This is done just before setting
the scheduler topology.
Signed-off-by: NSrikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200921095653.9701-9-srikar@linux.vnet.ibm.com

arch/powerpc/kernel/smp.c

@@ -1401,6 +1401,8 @@ int setup_profiling_timer(unsigned int multiplier)
 
 static void fixup_topology(void)
 {
+	int i;
+
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
@@ -1410,6 +1412,30 @@ static void fixup_topology(void)
 
 	if (!has_coregroup_support())
 		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
+
+	/*
+	 * Try to consolidate topology levels here instead of
+	 * allowing scheduler to degenerate.
+	 * - Dont consolidate if masks are different.
+	 * - Dont consolidate if sd_flags exists and are different.
+	 */
+	for (i = 1; i <= die_idx; i++) {
+		if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
+			continue;
+
+		if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
+				powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
+			continue;
+
+		if (!powerpc_topology[i - 1].sd_flags)
+			powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+
+		powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
+		powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
+#ifdef CONFIG_SCHED_DEBUG
+		powerpc_topology[i].name = powerpc_topology[i + 1].name;
+#endif
+	}
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)