From 70a94089d7f7fa91bc1795622426b3ed017ec71a Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Mon, 21 Sep 2020 15:26:53 +0530
Subject: [PATCH] powerpc/smp: Optimize update_coregroup_mask

References: jsc#SLE-13615 bsc#1180100 ltc#190257
Patch-mainline: v5.10-rc1
Git-commit: 70a94089d7f7fa91bc1795622426b3ed017ec71a

All threads of a SMT4/SMT8 core can either be part of CPU's coregroup
mask or outside the coregroup. Use this relation to reduce the
number of iterations needed to find all the CPUs that share the same
coregroup

Use a temporary mask to iterate through the CPUs that may share
coregroup mask. Also instead of setting one CPU at a time into
cpu_coregroup_mask, copy the SMT4/SMT8/submask at one shot.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200921095653.9701-12-srikar@linux.vnet.ibm.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/kernel/smp.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 45619433c43a..0dc1b8591cc8 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1339,19 +1339,33 @@ static inline void add_cpu_to_smallcore_masks(int cpu)
 
 static void update_coregroup_mask(int cpu)
 {
-	int first_thread = cpu_first_thread_sibling(cpu);
+	struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
+	cpumask_var_t mask;
 	int coregroup_id = cpu_to_coregroup_id(cpu);
 	int i;
 
-	cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu));
-	for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) {
-		int fcpu = cpu_first_thread_sibling(i);
+	alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu));
+	cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu));
+
+	if (shared_caches)
+		submask_fn = cpu_l2_cache_mask;
+
+	/* Update coregroup mask with all the CPUs that are part of submask */
+	or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask);
+
+	/* Skip all CPUs already part of coregroup mask */
+	cpumask_andnot(mask, mask, cpu_coregroup_mask(cpu));
 
-		if (fcpu == first_thread)
-			set_cpus_related(cpu, i, cpu_coregroup_mask);
-		else if (coregroup_id == cpu_to_coregroup_id(i))
-			set_cpus_related(cpu, i, cpu_coregroup_mask);
+	for_each_cpu(i, mask) {
+		/* Skip all CPUs not part of this coregroup */
+		if (coregroup_id == cpu_to_coregroup_id(i)) {
+			or_cpumasks_related(cpu, i, submask_fn, cpu_coregroup_mask);
+			cpumask_andnot(mask, mask, submask_fn(i));
+		} else {
+			cpumask_andnot(mask, mask, cpu_coregroup_mask(i));
+		}
 	}
+	free_cpumask_var(mask);
 }
 
 static void add_cpu_to_masks(int cpu)
-- 
2.26.2