On 2/16/26 5:49 PM, Vishal Chourasia wrote:
Expedite synchronize_rcu during the SMT mode switch operation when
initiated via /sys/devices/system/cpu/smt/control interface
SMT mode switch operation i.e. between SMT 8 to SMT 1 or vice versa and
others, are user driven operations and therefore should complete as soon
as possible. Switching SMT states involves iterating over a list of CPUs
and performing hotplug operations. It was found these transitions took
significantly large amount of time to complete particularly on
high-core-count systems because system was blocked on synchronize_rcu
calls.
Below is one of the call-stacks that accounted for most of the blocking
time overhead as reported by offcputime bcc script for CPU offline
operation,
finish_task_switch
__schedule
schedule
schedule_timeout
wait_for_completion
__wait_rcu_gp
synchronize_rcu
cpuidle_uninstall_idle_handler
powernv_cpuidle_cpu_dead
cpuhp_invoke_callback
__cpuhp_invoke_callback_range
_cpu_down
cpu_device_down
cpu_subsys_offline
device_offline
online_store
dev_attr_store
sysfs_kf_write
kernfs_fop_write_iter
vfs_write
ksys_write
system_call_exception
system_call_common
- bash (29705)
5771569 ------------------------> Duration (us)
Signed-off-by: Vishal Chourasia <[email protected]>
---
include/linux/rcupdate.h | 3 +++
kernel/cpu.c | 4 ++++
2 files changed, 7 insertions(+)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7729fef249e1..f12d0d0f008d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1190,6 +1190,9 @@ rcu_head_after_call_rcu(struct rcu_head *rhp,
rcu_callback_t f)
extern int rcu_expedited;
extern int rcu_normal;
+extern void rcu_expedite_gp(void);
+extern void rcu_unexpedite_gp(void);
+
DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock())
DECLARE_LOCK_GUARD_0_ATTRS(rcu, __acquires_shared(RCU),
__releases_shared(RCU))
IMHO, below maybe better.
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f12d0d0f008d..61b80c29d53b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1190,8 +1190,13 @@ rcu_head_after_call_rcu(struct rcu_head *rhp,
rcu_callback_t f)
extern int rcu_expedited;
extern int rcu_normal;
-extern void rcu_expedite_gp(void);
-extern void rcu_unexpedite_gp(void);
+#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/rcu/rcu.h b/kernel/rcu/rcu.h
index dc5d614b372c..41a0d262e964 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -512,8 +512,6 @@ 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; }
@@ -521,8 +519,6 @@ 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);
