From caa8e29da59926bef099b46ab6280333d583e944 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Mon, 10 Aug 2020 12:48:30 +0530
Subject: [PATCH] powerpc/smp: Optimize start_secondary

References: jsc#SLE-13617 bsc#1176912 ltc#186322
Patch-mainline: v5.10-rc1
Git-commit: caa8e29da59926bef099b46ab6280333d583e944

In start_secondary, even if shared_cache was already set, system does a
redundant match for cpumask. This redundant check can be removed by
checking if shared_cache is already set.

While here, localize the sibling_mask variable to within the if
condition.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200810071834.92514-7-srikar@linux.vnet.ibm.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/kernel/smp.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 168532e37305..016a822eb8c4 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -852,7 +852,7 @@ static int powerpc_shared_cache_flags(void)
  */
 static const struct cpumask *shared_cache_mask(int cpu)
 {
-	return cpu_l2_cache_mask(cpu);
+	return per_cpu(cpu_l2_cache_map, cpu);
 }
 
 #ifdef CONFIG_SCHED_SMT
@@ -1319,7 +1319,6 @@ static void add_cpu_to_masks(int cpu)
 void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
-	struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
 
 	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
@@ -1345,14 +1344,20 @@ void start_secondary(void *unused)
 	/* Update topology CPU masks */
 	add_cpu_to_masks(cpu);
 
-	if (has_big_cores)
-		sibling_mask = cpu_smallcore_mask;
 	/*
 	 * Check for any shared caches. Note that this must be done on a
 	 * per-core basis because one core in the pair might be disabled.
 	 */
-	if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
-		shared_caches = true;
+	if (!shared_caches) {
+		struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+		struct cpumask *mask = cpu_l2_cache_mask(cpu);
+
+		if (has_big_cores)
+			sibling_mask = cpu_smallcore_mask;
+
+		if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+			shared_caches = true;
+	}
 
 	set_numa_node(numa_cpu_lookup_table[cpu]);
 	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
-- 
2.28.0