On Mon, Jun 15, 2026 at 09:55:16AM +0530, Vishal Chourasia wrote: > On large idle systems, changing system-wide SMT level using the sysfs > control interface still takes approximately 40-55 minutes. Changing SMT > levels is an user triggered operation generally done when systems are > fairly idle. This causes users to be blocked from doing other subsequent > work. > > Analyzing the collected profile data during SMT level switch, showed > that CPU hotplug machinery was blocked on synchronize_rcu() calls. > > Expedite RCU grace periods for the entire duration of triggered SMT > switch operation via the sysfs control interface. Individual CPU hotplug > operations via the online/offline interface are not affected. > > On a PPC64 system with 400 CPUs: > > SMT8 to SMT1: > before: 1m14s > after: 3.2s (~23x faster) > > SMT1 to SMT8: > before: 2m27s > after: 2.5s (~58x faster) > > On a large config system with 1920 CPUs, completion time improves from > ~1 hour to 5-6 minutes. > > Tested-by: Samir <[email protected]> > Reviewed-by: Shrikanth Hegde <[email protected]> > Signed-off-by: Vishal Chourasia <[email protected]>
>From an RCU viewpoint: Reviewed-by: Paul E. McKenney <[email protected]> I am guessing that you will be taking this up some other path, but if you would like it to to via RCU, please let me know. Thanx, Paul > --- > include/linux/rcupdate.h | 8 ++++++++ > kernel/cpu.c | 4 ++++ > kernel/rcu/rcu.h | 4 ---- > 3 files changed, 12 insertions(+), 4 deletions(-) > > diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h > index bfa765132de8..b6bccf131f1c 100644 > --- a/include/linux/rcupdate.h > +++ b/include/linux/rcupdate.h > @@ -1178,6 +1178,14 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, > rcu_callback_t f) > extern int rcu_expedited; > extern int rcu_normal; > > +#ifdef CONFIG_TINY_RCU > +static inline void rcu_expedite_gp(void) { } > +static inline void rcu_unexpedite_gp(void) { } > +#else > +void rcu_expedite_gp(void); > +void rcu_unexpedite_gp(void); > +#endif > + > DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) > DECLARE_LOCK_GUARD_0_ATTRS(rcu, __acquires_shared(RCU), > __releases_shared(RCU)) > > diff --git a/kernel/cpu.c b/kernel/cpu.c > index bc4f7a9ba64e..6351da9dffdc 100644 > --- a/kernel/cpu.c > +++ b/kernel/cpu.c > @@ -2658,6 +2658,7 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) > int cpu, ret = 0; > > cpu_maps_update_begin(); > + rcu_expedite_gp(); > for_each_online_cpu(cpu) { > if (topology_is_primary_thread(cpu)) > continue; > @@ -2687,6 +2688,7 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) > } > if (!ret) > cpu_smt_control = ctrlval; > + rcu_unexpedite_gp(); > cpu_maps_update_done(); > return ret; > } > @@ -2704,6 +2706,7 @@ int cpuhp_smt_enable(void) > int cpu, ret = 0; > > cpu_maps_update_begin(); > + rcu_expedite_gp(); > cpu_smt_control = CPU_SMT_ENABLED; > for_each_present_cpu(cpu) { > /* Skip online CPUs and CPUs on offline nodes */ > @@ -2717,6 +2720,7 @@ int cpuhp_smt_enable(void) > /* See comment in cpuhp_smt_disable() */ > cpuhp_online_cpu_device(cpu); > } > + rcu_unexpedite_gp(); > cpu_maps_update_done(); > return ret; > } > diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h > index fa6d30ce73d1..d6a63ee60bc0 100644 > --- a/kernel/rcu/rcu.h > +++ b/kernel/rcu/rcu.h > @@ -521,8 +521,6 @@ do { > \ > static inline bool rcu_gp_is_normal(void) { return true; } > static inline bool rcu_gp_is_expedited(void) { return false; } > static inline bool rcu_async_should_hurry(void) { return false; } > -static inline void rcu_expedite_gp(void) { } > -static inline void rcu_unexpedite_gp(void) { } > static inline void rcu_async_hurry(void) { } > static inline void rcu_async_relax(void) { } > static inline bool rcu_cpu_online(int cpu) { return true; } > @@ -530,8 +528,6 @@ static inline bool rcu_cpu_online(int cpu) { return true; > } > bool rcu_gp_is_normal(void); /* Internal RCU use. */ > bool rcu_gp_is_expedited(void); /* Internal RCU use. */ > bool rcu_async_should_hurry(void); /* Internal RCU use. */ > -void rcu_expedite_gp(void); > -void rcu_unexpedite_gp(void); > void rcu_async_hurry(void); > void rcu_async_relax(void); > void rcupdate_announce_bootup_oddness(void); > -- > 2.54.0 >
