powerpc/smp: Optimize start_secondary

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

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 168532e37305dcbcb021f7d163dfb2ccfb472885..016a822eb8c44197f4537800f37833967dc258f3 100644 (file)
--- 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]));