[PATCH v2 11/11] powerpc/smp: Optimize update_coregroup_mask

[Srikar Dronamraju]

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.

Cc: linuxppc-dev <linuxppc-dev at lists.ozlabs.org>
Cc: LKML <linux-kernel at vger.kernel.org>
Cc: Michael Ellerman <mpe at ellerman.id.au>
Cc: Nicholas Piggin <npiggin at gmail.com>
Cc: Anton Blanchard <anton at ozlabs.org>
Cc: Oliver O'Halloran <oohall at gmail.com>
Cc: Nathan Lynch <nathanl at linux.ibm.com>
Cc: Michael Neuling <mikey at neuling.org>
Cc: Gautham R Shenoy <ego at linux.vnet.ibm.com>
Cc: Satheesh Rajendran <sathnaga at linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo at kernel.org>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Valentin Schneider <valentin.schneider at arm.com>
Signed-off-by: Srikar Dronamraju <srikar at linux.vnet.ibm.com>
---
 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 b48ae4e306d3..bbaea93dc558 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)
-- 
2.17.1