summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/smp.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kernel/smp.c')
-rw-r--r--arch/powerpc/kernel/smp.c124
1 files changed, 70 insertions, 54 deletions
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ab691c89d787..693334c20d07 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -77,10 +77,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -93,15 +93,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
EXPORT_SYMBOL_GPL(has_big_cores);
-enum {
-#ifdef CONFIG_SCHED_SMT
- smt_idx,
-#endif
- cache_idx,
- mc_idx,
- die_idx,
-};
-
#define MAX_THREAD_LIST_SIZE 8
#define THREAD_GROUP_SHARE_L1 1
#define THREAD_GROUP_SHARE_L2_L3 2
@@ -987,7 +978,7 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
return 0;
}
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
#ifdef CONFIG_SCHED_SMT
/* cpumask of CPUs with asymmetric SMT dependency */
@@ -1004,6 +995,13 @@ static int powerpc_smt_flags(void)
#endif
/*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
* P9 has a slightly odd architecture where pairs of cores share an L2 cache.
* This topology makes it *much* cheaper to migrate tasks between adjacent cores
* since the migrated task remains cache hot. We want to take advantage of this
@@ -1011,9 +1009,20 @@ static int powerpc_smt_flags(void)
*/
static int powerpc_shared_cache_flags(void)
{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+
return SD_SHARE_PKG_RESOURCES;
}
+static int powerpc_shared_proc_flags(void)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return SD_ASYM_PACKING;
+
+ return 0;
+}
+
/*
* We can't just pass cpu_l2_cache_mask() directly because
* returns a non-const pointer and the compiler barfs on that.
@@ -1037,6 +1046,10 @@ static struct cpumask *cpu_coregroup_mask(int cpu)
static bool has_coregroup_support(void)
{
+ /* Coregroup identification not available on shared systems */
+ if (is_shared_processor())
+ return 0;
+
return coregroup_enabled;
}
@@ -1045,16 +1058,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
return cpu_coregroup_mask(cpu);
}
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_mc_mask, SD_INIT_NAME(MC) },
- { cpu_cpu_mask, SD_INIT_NAME(PKG) },
- { NULL, },
-};
-
static int __init init_big_cores(void)
{
int cpu;
@@ -1682,43 +1685,45 @@ void start_secondary(void *unused)
BUG();
}
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
{
- int i;
+ int i = 0;
+
+ if (is_shared_processor() && has_big_cores)
+ static_branch_enable(&splpar_asym_pack);
#ifdef CONFIG_SCHED_SMT
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
- powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+ };
+ } else {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+ };
}
#endif
+ if (shared_caches) {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
+ };
+ }
+ if (has_coregroup_support()) {
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
+ };
+ }
+ powerpc_topology[i++] = (struct sched_domain_topology_level){
+ cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
+ };
- if (!has_coregroup_support())
- powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
- /*
- * Try to consolidate topology levels here instead of
- * allowing scheduler to degenerate.
- * - Dont consolidate if masks are different.
- * - Dont consolidate if sd_flags exists and are different.
- */
- for (i = 1; i <= die_idx; i++) {
- if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
- continue;
-
- if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
- powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
- continue;
-
- if (!powerpc_topology[i - 1].sd_flags)
- powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+ /* There must be one trailing NULL entry left. */
+ BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
- powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
- powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
- powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
- }
+ set_sched_topology(powerpc_topology);
}
void __init smp_cpus_done(unsigned int max_cpus)
@@ -1733,9 +1738,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
smp_ops->bringup_done();
dump_numa_cpu_topology();
+ build_sched_topology();
+}
- fixup_topology();
- set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+ if (static_branch_unlikely(&splpar_asym_pack))
+ return -cpu / threads_per_core;
+
+ return -cpu;
}
#ifdef CONFIG_HOTPLUG_CPU