aa9b16306e
When a CPU is entering dyntick-idle mode, tick_nohz_stop_sched_tick() calls rcu_needs_cpu() see if RCU needs that CPU, and, if not, computes the next wakeup time based on the timer wheels. Only later, when actually entering the idle loop, rcu_prepare_for_idle() will be invoked. In some cases, rcu_prepare_for_idle() will post timers to wake the CPU back up. But all for naught: The next wakeup time for the CPU has already been computed, and posting a timer afterwards does not force that wakeup time to be recomputed. This means that rcu_prepare_for_idle()'s have no effect. This is not a problem on a busy system because something else will wake up the CPU soon enough. However, on lightly loaded systems, the CPU might stay asleep for a considerable length of time. If that CPU has a callback that the rest of the system is waiting on, the system might run very slowly or (in theory) even hang. This commit avoids this problem by having rcu_needs_cpu() give tick_nohz_stop_sched_tick() an estimate of when RCU will need the CPU to wake back up, which tick_nohz_stop_sched_tick() takes into account when programming the CPU's wakeup time. An alternative approach is for rcu_prepare_for_idle() to use hrtimers instead of normal timers, but timers are much more efficient than are hrtimers for frequently and repeatedly posting and cancelling a given timer, which is exactly what RCU_FAST_NO_HZ does. Reported-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr> Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr>
93 lines
3.3 KiB
C
93 lines
3.3 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
*
|
|
* Copyright IBM Corporation, 2008
|
|
*
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.com>
|
|
* Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical algorithm
|
|
*
|
|
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
|
|
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
|
|
*
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
* Documentation/RCU
|
|
*/
|
|
|
|
#ifndef __LINUX_RCUTREE_H
|
|
#define __LINUX_RCUTREE_H
|
|
|
|
extern void rcu_init(void);
|
|
extern void rcu_note_context_switch(int cpu);
|
|
extern int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
|
|
extern void rcu_cpu_stall_reset(void);
|
|
|
|
/*
|
|
* Note a virtualization-based context switch. This is simply a
|
|
* wrapper around rcu_note_context_switch(), which allows TINY_RCU
|
|
* to save a few bytes.
|
|
*/
|
|
static inline void rcu_virt_note_context_switch(int cpu)
|
|
{
|
|
rcu_note_context_switch(cpu);
|
|
}
|
|
|
|
extern void synchronize_rcu_bh(void);
|
|
extern void synchronize_sched_expedited(void);
|
|
extern void synchronize_rcu_expedited(void);
|
|
|
|
void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
|
|
|
|
/**
|
|
* synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period
|
|
*
|
|
* Wait for an RCU-bh grace period to elapse, but use a "big hammer"
|
|
* approach to force the grace period to end quickly. This consumes
|
|
* significant time on all CPUs and is unfriendly to real-time workloads,
|
|
* so is thus not recommended for any sort of common-case code. In fact,
|
|
* if you are using synchronize_rcu_bh_expedited() in a loop, please
|
|
* restructure your code to batch your updates, and then use a single
|
|
* synchronize_rcu_bh() instead.
|
|
*
|
|
* Note that it is illegal to call this function while holding any lock
|
|
* that is acquired by a CPU-hotplug notifier. And yes, it is also illegal
|
|
* to call this function from a CPU-hotplug notifier. Failing to observe
|
|
* these restriction will result in deadlock.
|
|
*/
|
|
static inline void synchronize_rcu_bh_expedited(void)
|
|
{
|
|
synchronize_sched_expedited();
|
|
}
|
|
|
|
extern void rcu_barrier(void);
|
|
extern void rcu_barrier_bh(void);
|
|
extern void rcu_barrier_sched(void);
|
|
|
|
extern unsigned long rcutorture_testseq;
|
|
extern unsigned long rcutorture_vernum;
|
|
extern long rcu_batches_completed(void);
|
|
extern long rcu_batches_completed_bh(void);
|
|
extern long rcu_batches_completed_sched(void);
|
|
|
|
extern void rcu_force_quiescent_state(void);
|
|
extern void rcu_bh_force_quiescent_state(void);
|
|
extern void rcu_sched_force_quiescent_state(void);
|
|
|
|
extern void rcu_scheduler_starting(void);
|
|
extern int rcu_scheduler_active __read_mostly;
|
|
|
|
#endif /* __LINUX_RCUTREE_H */
|