diff options
| -rw-r--r-- | arch/powerpc/kernel/smp.c | 25 |
1 files changed, 23 insertions, 2 deletions
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ab691c89d787..3fc8ad9646a4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1004,6 +1004,13 @@ 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 +1018,20 @@ 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. @@ -1050,8 +1068,8 @@ static struct sched_domain_topology_level powerpc_topology[] = { { 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) }, + { cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) }, + { cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG) }, { NULL, }, }; @@ -1686,6 +1704,9 @@ static void __init fixup_topology(void) { int i; + 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"); |