diff options
| -rw-r--r-- | arch/powerpc/kernel/smp.c | 50 |
1 files changed, 49 insertions, 1 deletions
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index b42c868e1ac1..e0a4c1f82e25 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -957,6 +957,8 @@ static void add_cpu_to_masks(int cpu) set_cpus_related(cpu, i, cpu_core_mask); } +static bool shared_caches; + /* Activate a secondary processor. */ void start_secondary(void *unused) { @@ -986,6 +988,13 @@ void start_secondary(void *unused) /* Update topology CPU masks */ add_cpu_to_masks(cpu); + /* + * 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), cpu_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])); @@ -1027,6 +1036,35 @@ static struct sched_domain_topology_level powerpc_topology[] = { { NULL, }, }; +/* + * 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 + * at the scheduler level so an extra topology level is required. + */ +static int powerpc_shared_cache_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} + +/* + * We can't just pass cpu_l2_cache_mask() directly because + * returns a non-const pointer and the compiler barfs on that. + */ +static const struct cpumask *shared_cache_mask(int cpu) +{ + return cpu_l2_cache_mask(cpu); +} + +static struct sched_domain_topology_level power9_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_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + void __init smp_cpus_done(unsigned int max_cpus) { /* @@ -1040,7 +1078,17 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); - set_sched_topology(powerpc_topology); + /* + * If any CPU detects that it's sharing a cache with another CPU then + * use the deeper topology that is aware of this sharing. + */ + if (shared_caches) { + pr_info("Using shared cache scheduler topology\n"); + set_sched_topology(power9_topology); + } else { + pr_info("Using standard scheduler topology\n"); + set_sched_topology(powerpc_topology); + } } #ifdef CONFIG_HOTPLUG_CPU |