kernel-ark/include/linux/rcupreempt.h
Paul E. McKenney a682604838 rcu: Teach RCU that idle task is not quiscent state at boot
This patch fixes a bug located by Vegard Nossum with the aid of
kmemcheck, updated based on review comments from Nick Piggin,
Ingo Molnar, and Andrew Morton.  And cleans up the variable-name
and function-name language.  ;-)

The boot CPU runs in the context of its idle thread during boot-up.
During this time, idle_cpu(0) will always return nonzero, which will
fool Classic and Hierarchical RCU into deciding that a large chunk of
the boot-up sequence is a big long quiescent state.  This in turn causes
RCU to prematurely end grace periods during this time.

This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks()
function to ignore the idle task as a quiescent state until the
system has started up the scheduler in rest_init(), introducing a
new non-API function rcu_idle_now_means_idle() to inform RCU of this
transition.  RCU maintains an internal rcu_idle_cpu_truthful variable
to track this state, which is then used by rcu_check_callback() to
determine if it should believe idle_cpu().

Because this patch has the effect of disallowing RCU grace periods
during long stretches of the boot-up sequence, this patch also introduces
Josh Triplett's UP-only optimization that makes synchronize_rcu() be a
no-op if num_online_cpus() returns 1.  This allows boot-time code that
calls synchronize_rcu() to proceed normally.  Note, however, that RCU
callbacks registered by call_rcu() will likely queue up until later in
the boot sequence.  Although rcuclassic and rcutree can also use this
same optimization after boot completes, rcupreempt must restrict its
use of this optimization to the portion of the boot sequence before the
scheduler starts up, given that an rcupreempt RCU read-side critical
section may be preeempted.

In addition, this patch takes Nick Piggin's suggestion to make the
system_state global variable be __read_mostly.

Changes since v4:

o	Changes the name of the introduced function and variable to
	be less emotional.  ;-)

Changes since v3:

o	WARN_ON(nr_context_switches() > 0) to verify that RCU
	switches out of boot-time mode before the first context
	switch, as suggested by Nick Piggin.

Changes since v2:

o	Created rcu_blocking_is_gp() internal-to-RCU API that
	determines whether a call to synchronize_rcu() is itself
	a grace period.

o	The definition of rcu_blocking_is_gp() for rcuclassic and
	rcutree checks to see if but a single CPU is online.

o	The definition of rcu_blocking_is_gp() for rcupreempt
	checks to see both if but a single CPU is online and if
	the system is still in early boot.

	This allows rcupreempt to again work correctly if running
	on a single CPU after booting is complete.

o	Added check to rcupreempt's synchronize_sched() for there
	being but one online CPU.

Tested all three variants both SMP and !SMP, booted fine, passed a short
rcutorture test on both x86 and Power.

Located-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-26 04:08:14 +01:00

161 lines
5.0 KiB
C

/*
* Read-Copy Update mechanism for mutual exclusion (RT implementation)
*
* 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 (C) IBM Corporation, 2006
*
* Author: Paul McKenney <paulmck@us.ibm.com>
*
* Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
* Papers:
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*
*/
#ifndef __LINUX_RCUPREEMPT_H
#define __LINUX_RCUPREEMPT_H
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/threads.h>
#include <linux/percpu.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
struct rcu_dyntick_sched {
int dynticks;
int dynticks_snap;
int sched_qs;
int sched_qs_snap;
int sched_dynticks_snap;
};
DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
static inline void rcu_qsctr_inc(int cpu)
{
struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
rdssp->sched_qs++;
}
#define rcu_bh_qsctr_inc(cpu)
/*
* Someone might want to pass call_rcu_bh as a function pointer.
* So this needs to just be a rename and not a macro function.
* (no parentheses)
*/
#define call_rcu_bh call_rcu
/**
* call_rcu_sched - Queue RCU callback for invocation after sched grace period.
* @head: structure to be used for queueing the RCU updates.
* @func: actual update function to be invoked after the grace period
*
* The update function will be invoked some time after a full
* synchronize_sched()-style grace period elapses, in other words after
* all currently executing preempt-disabled sections of code (including
* hardirq handlers, NMI handlers, and local_irq_save() blocks) have
* completed.
*/
extern void call_rcu_sched(struct rcu_head *head,
void (*func)(struct rcu_head *head));
extern void __rcu_read_lock(void) __acquires(RCU);
extern void __rcu_read_unlock(void) __releases(RCU);
extern int rcu_pending(int cpu);
extern int rcu_needs_cpu(int cpu);
#define __rcu_read_lock_bh() { rcu_read_lock(); local_bh_disable(); }
#define __rcu_read_unlock_bh() { local_bh_enable(); rcu_read_unlock(); }
extern void __synchronize_sched(void);
extern void __rcu_init(void);
extern void rcu_init_sched(void);
extern void rcu_check_callbacks(int cpu, int user);
extern void rcu_restart_cpu(int cpu);
extern long rcu_batches_completed(void);
/*
* Return the number of RCU batches processed thus far. Useful for debug
* and statistic. The _bh variant is identifcal to straight RCU
*/
static inline long rcu_batches_completed_bh(void)
{
return rcu_batches_completed();
}
#ifdef CONFIG_RCU_TRACE
struct rcupreempt_trace;
extern long *rcupreempt_flipctr(int cpu);
extern long rcupreempt_data_completed(void);
extern int rcupreempt_flip_flag(int cpu);
extern int rcupreempt_mb_flag(int cpu);
extern char *rcupreempt_try_flip_state_name(void);
extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
#endif
struct softirq_action;
#ifdef CONFIG_NO_HZ
static inline void rcu_enter_nohz(void)
{
static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
__get_cpu_var(rcu_dyntick_sched).dynticks++;
WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs);
}
static inline void rcu_exit_nohz(void)
{
static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
__get_cpu_var(rcu_dyntick_sched).dynticks++;
smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1),
&rs);
}
#else /* CONFIG_NO_HZ */
#define rcu_enter_nohz() do { } while (0)
#define rcu_exit_nohz() do { } while (0)
#endif /* CONFIG_NO_HZ */
/*
* A context switch is a grace period for rcupreempt synchronize_rcu()
* only during early boot, before the scheduler has been initialized.
* So, how the heck do we get a context switch? Well, if the caller
* invokes synchronize_rcu(), they are willing to accept a context
* switch, so we simply pretend that one happened.
*
* After boot, there might be a blocked or preempted task in an RCU
* read-side critical section, so we cannot then take the fastpath.
*/
static inline int rcu_blocking_is_gp(void)
{
return num_online_cpus() == 1 && !rcu_scheduler_active;
}
#endif /* __LINUX_RCUPREEMPT_H */