![Paul E. McKenney](/assets/img/avatar_default.png)
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>
191 lines
5.7 KiB
C
191 lines
5.7 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion (classic 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, 2001
|
|
*
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.com>
|
|
*
|
|
* Based on the original work by Paul McKenney <paulmck@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_RCUCLASSIC_H
|
|
#define __LINUX_RCUCLASSIC_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>
|
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
|
#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rcp->jiffies_stall */
|
|
#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rcp->jiffies_stall */
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
|
|
|
/* Global control variables for rcupdate callback mechanism. */
|
|
struct rcu_ctrlblk {
|
|
long cur; /* Current batch number. */
|
|
long completed; /* Number of the last completed batch */
|
|
long pending; /* Number of the last pending batch */
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
|
unsigned long gp_start; /* Time at which GP started in jiffies. */
|
|
unsigned long jiffies_stall;
|
|
/* Time at which to check for CPU stalls. */
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
|
|
|
int signaled;
|
|
|
|
spinlock_t lock ____cacheline_internodealigned_in_smp;
|
|
DECLARE_BITMAP(cpumask, NR_CPUS); /* CPUs that need to switch for */
|
|
/* current batch to proceed. */
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
/* Is batch a before batch b ? */
|
|
static inline int rcu_batch_before(long a, long b)
|
|
{
|
|
return (a - b) < 0;
|
|
}
|
|
|
|
/* Is batch a after batch b ? */
|
|
static inline int rcu_batch_after(long a, long b)
|
|
{
|
|
return (a - b) > 0;
|
|
}
|
|
|
|
/* Per-CPU data for Read-Copy UPdate. */
|
|
struct rcu_data {
|
|
/* 1) quiescent state handling : */
|
|
long quiescbatch; /* Batch # for grace period */
|
|
int passed_quiesc; /* User-mode/idle loop etc. */
|
|
int qs_pending; /* core waits for quiesc state */
|
|
|
|
/* 2) batch handling */
|
|
/*
|
|
* if nxtlist is not NULL, then:
|
|
* batch:
|
|
* The batch # for the last entry of nxtlist
|
|
* [*nxttail[1], NULL = *nxttail[2]):
|
|
* Entries that batch # <= batch
|
|
* [*nxttail[0], *nxttail[1]):
|
|
* Entries that batch # <= batch - 1
|
|
* [nxtlist, *nxttail[0]):
|
|
* Entries that batch # <= batch - 2
|
|
* The grace period for these entries has completed, and
|
|
* the other grace-period-completed entries may be moved
|
|
* here temporarily in rcu_process_callbacks().
|
|
*/
|
|
long batch;
|
|
struct rcu_head *nxtlist;
|
|
struct rcu_head **nxttail[3];
|
|
long qlen; /* # of queued callbacks */
|
|
struct rcu_head *donelist;
|
|
struct rcu_head **donetail;
|
|
long blimit; /* Upper limit on a processed batch */
|
|
int cpu;
|
|
struct rcu_head barrier;
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_data);
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
|
|
|
|
/*
|
|
* Increment the quiescent state counter.
|
|
* The counter is a bit degenerated: We do not need to know
|
|
* how many quiescent states passed, just if there was at least
|
|
* one since the start of the grace period. Thus just a flag.
|
|
*/
|
|
static inline void rcu_qsctr_inc(int cpu)
|
|
{
|
|
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
|
|
rdp->passed_quiesc = 1;
|
|
}
|
|
static inline void rcu_bh_qsctr_inc(int cpu)
|
|
{
|
|
struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
|
|
rdp->passed_quiesc = 1;
|
|
}
|
|
|
|
extern int rcu_pending(int cpu);
|
|
extern int rcu_needs_cpu(int cpu);
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
extern struct lockdep_map rcu_lock_map;
|
|
# define rcu_read_acquire() \
|
|
lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
|
|
# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
|
|
#else
|
|
# define rcu_read_acquire() do { } while (0)
|
|
# define rcu_read_release() do { } while (0)
|
|
#endif
|
|
|
|
#define __rcu_read_lock() \
|
|
do { \
|
|
preempt_disable(); \
|
|
__acquire(RCU); \
|
|
rcu_read_acquire(); \
|
|
} while (0)
|
|
#define __rcu_read_unlock() \
|
|
do { \
|
|
rcu_read_release(); \
|
|
__release(RCU); \
|
|
preempt_enable(); \
|
|
} while (0)
|
|
#define __rcu_read_lock_bh() \
|
|
do { \
|
|
local_bh_disable(); \
|
|
__acquire(RCU_BH); \
|
|
rcu_read_acquire(); \
|
|
} while (0)
|
|
#define __rcu_read_unlock_bh() \
|
|
do { \
|
|
rcu_read_release(); \
|
|
__release(RCU_BH); \
|
|
local_bh_enable(); \
|
|
} while (0)
|
|
|
|
#define __synchronize_sched() synchronize_rcu()
|
|
|
|
#define call_rcu_sched(head, func) call_rcu(head, func)
|
|
|
|
extern void __rcu_init(void);
|
|
#define rcu_init_sched() do { } while (0)
|
|
extern void rcu_check_callbacks(int cpu, int user);
|
|
extern void rcu_restart_cpu(int cpu);
|
|
|
|
extern long rcu_batches_completed(void);
|
|
extern long rcu_batches_completed_bh(void);
|
|
|
|
#define rcu_enter_nohz() do { } while (0)
|
|
#define rcu_exit_nohz() do { } while (0)
|
|
|
|
/* A context switch is a grace period for rcuclassic. */
|
|
static inline int rcu_blocking_is_gp(void)
|
|
{
|
|
return num_online_cpus() == 1;
|
|
}
|
|
|
|
#endif /* __LINUX_RCUCLASSIC_H */
|