[PATCH v3 6/7] x86/smpboot: introduce per-cpu variable for HT siblings

[subhra mazumdar]

Introduce a per-cpu variable to keep the number of HT siblings of a cpu.
This will be used for quick lookup in select_idle_cpu to determine the
limits of search. This patch does it only for x86.

Signed-off-by: subhra mazumdar <subhra.mazumdar@xxxxxxxxxx>
---
 arch/x86/include/asm/smp.h      |  1 +
 arch/x86/include/asm/topology.h |  1 +
 arch/x86/kernel/smpboot.c       | 17 ++++++++++++++++-
 include/linux/topology.h        |  4 ++++
 4 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index da545df..1e90cbd 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -22,6 +22,7 @@ extern int smp_num_siblings;
 extern unsigned int num_processors;
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned int, cpumask_weight_sibling);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 /* cpus sharing the last level cache: */
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 453cf38..dd19c71 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -111,6 +111,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #ifdef CONFIG_SMP
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_weight(cpu)	(per_cpu(cpumask_weight_sibling, cpu))
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 362dd89..20bf676 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -85,6 +85,10 @@
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
+/* representing number of HT siblings of each CPU */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned int, cpumask_weight_sibling);
+EXPORT_PER_CPU_SYMBOL(cpumask_weight_sibling);
+
 /* representing HT and core siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
@@ -520,6 +524,8 @@ void set_cpu_sibling_map(int cpu)
 
 	if (!has_mp) {
 		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
+		per_cpu(cpumask_weight_sibling, cpu) =
+		    cpumask_weight(topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
 		c->booted_cores = 1;
@@ -529,8 +535,12 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_smt && match_smt(c, o)))
+		if ((i == cpu) || (has_smt && match_smt(c, o))) {
 			link_mask(topology_sibling_cpumask, cpu, i);
+			threads = cpumask_weight(topology_sibling_cpumask(cpu));
+			per_cpu(cpumask_weight_sibling, cpu) = threads;
+			per_cpu(cpumask_weight_sibling, i) = threads;
+		}
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(cpu_llc_shared_mask, cpu, i);
@@ -1173,6 +1183,8 @@ static __init void disable_smp(void)
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
+	per_cpu(cpumask_weight_sibling, 0) =
+	    cpumask_weight(topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
 }
 
@@ -1482,6 +1494,8 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
 		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
+		per_cpu(cpumask_weight_sibling, sibling) =
+		    cpumask_weight(topology_sibling_cpumask(sibling));
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
@@ -1495,6 +1509,7 @@ static void remove_siblinginfo(int cpu)
 		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
+	per_cpu(cpumask_weight_sibling, cpu) = 0;
 	cpumask_clear(topology_core_cpumask(cpu));
 	c->cpu_core_id = 0;
 	c->booted_cores = 0;
diff --git a/include/linux/topology.h b/include/linux/topology.h
index cb0775e..a85aea1 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -190,6 +190,10 @@ static inline int cpu_to_mem(int cpu)
 #ifndef topology_sibling_cpumask
 #define topology_sibling_cpumask(cpu)		cpumask_of(cpu)
 #endif
+#ifndef topology_sibling_weight
+#define topology_sibling_weight(cpu)	\
+		cpumask_weight(topology_sibling_cpumask(cpu))
+#endif
 #ifndef topology_core_cpumask
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
 #endif
-- 
2.9.3