linux/kernel/rcupdate.c
Paul E. McKenney 1423cc033d rcu: Delay rcu_barrier() wait until beginning of next CPU-hotunplug operation.
Ingo Molnar reported this lockup:

 [  200.380003] Hangcheck: hangcheck value past margin!
 [  248.192003] INFO: task S99local:2974 blocked for more than 120 seconds.
 [  248.194532] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 [  248.202330] S99local      D 0000000c  6256  2974   2687 0x00000000
 [  248.208929]  9c7ebe90 00000086 6b67ef8b 0000000c 9f25a610 81a69869 00000001 820b6990
 [  248.216123]  820b6990 820b6990 9c6e4c20 9c6e4eb4 82c78990 00000000 6b993559 0000000c
 [  248.220616]  9c7ebe90 8105f22a 9c6e4eb4 9c6e4c20 00000001 9c7ebe98 9c7ebeb4 81a65cb3
 [  248.229990] Call Trace:
 [  248.234049]  [<81a69869>] ? _spin_unlock_irqrestore+0x22/0x37
 [  248.239769]  [<8105f22a>] ? prepare_to_wait+0x48/0x4e
 [  248.244796]  [<81a65cb3>] rcu_barrier_cpu_hotplug+0xaa/0xc9
 [  248.250343]  [<8105f029>] ? autoremove_wake_function+0x0/0x38
 [  248.256063]  [<81062cf2>] notifier_call_chain+0x49/0x71
 [  248.261263]  [<81062da0>] raw_notifier_call_chain+0x11/0x13
 [  248.266809]  [<81a0b475>] _cpu_down+0x272/0x288
 [  248.271316]  [<81a0b4d5>] cpu_down+0x4a/0xa2
 [  248.275563]  [<81a0c48a>] store_online+0x2a/0x5e
 [  248.280156]  [<81a0c460>] ? store_online+0x0/0x5e
 [  248.284836]  [<814ddc35>] sysdev_store+0x20/0x28
 [  248.289429]  [<8112e403>] sysfs_write_file+0xb8/0xe3
 [  248.294369]  [<8112e34b>] ? sysfs_write_file+0x0/0xe3
 [  248.299396]  [<810e4c8f>] vfs_write+0x91/0x120
 [  248.303817]  [<810e4dc1>] sys_write+0x40/0x65
 [  248.308150]  [<81002d73>] sysenter_do_call+0x12/0x28

This change moves an RCU grace period delay off of the
critical path for CPU-hotunplug operations.

Since RCU callback migration is only performed on
CPU-hotunplug operations, and since the rcu_barrier() race is
provoked only by consecutive CPU-hotunplug operations, it is
not necessary to delay the end of a given CPU-hotunplug
operation.

We can instead choose to delay the beginning of the next
CPU-hotunplug operation.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josht@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: hugh.dickins@tiscali.co.uk
Cc: benh@kernel.crashing.org
LKML-Reference: <20090819060614.GA14383@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-19 13:58:54 +02:00

272 lines
7.8 KiB
C

/*
* Read-Copy Update mechanism for mutual exclusion
*
* 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
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.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 -
* http://lse.sourceforge.net/locking/rcupdate.html
*
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
#include <linux/kernel_stat.h>
enum rcu_barrier {
RCU_BARRIER_STD,
RCU_BARRIER_BH,
RCU_BARRIER_SCHED,
};
static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
static atomic_t rcu_barrier_cpu_count;
static DEFINE_MUTEX(rcu_barrier_mutex);
static struct completion rcu_barrier_completion;
int rcu_scheduler_active __read_mostly;
static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
static struct rcu_head rcu_migrate_head[3];
static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
/*
* Awaken the corresponding synchronize_rcu() instance now that a
* grace period has elapsed.
*/
void wakeme_after_rcu(struct rcu_head *head)
{
struct rcu_synchronize *rcu;
rcu = container_of(head, struct rcu_synchronize, head);
complete(&rcu->completion);
}
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
* Control will return to the caller some time after a full grace
* period has elapsed, in other words after all currently executing RCU
* read-side critical sections have completed. RCU read-side critical
* sections are delimited by rcu_read_lock() and rcu_read_unlock(),
* and may be nested.
*/
void synchronize_rcu(void)
{
struct rcu_synchronize rcu;
if (rcu_blocking_is_gp())
return;
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/**
* synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
*
* Control will return to the caller some time after a full rcu_bh grace
* period has elapsed, in other words after all currently executing rcu_bh
* read-side critical sections have completed. RCU read-side critical
* sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
* and may be nested.
*/
void synchronize_rcu_bh(void)
{
struct rcu_synchronize rcu;
if (rcu_blocking_is_gp())
return;
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_bh(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
static void rcu_barrier_callback(struct rcu_head *notused)
{
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
static void rcu_barrier_func(void *type)
{
int cpu = smp_processor_id();
struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
atomic_inc(&rcu_barrier_cpu_count);
switch ((enum rcu_barrier)type) {
case RCU_BARRIER_STD:
call_rcu(head, rcu_barrier_callback);
break;
case RCU_BARRIER_BH:
call_rcu_bh(head, rcu_barrier_callback);
break;
case RCU_BARRIER_SCHED:
call_rcu_sched(head, rcu_barrier_callback);
break;
}
}
static inline void wait_migrated_callbacks(void)
{
wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
smp_mb(); /* In case we didn't sleep. */
}
/*
* Orchestrate the specified type of RCU barrier, waiting for all
* RCU callbacks of the specified type to complete.
*/
static void _rcu_barrier(enum rcu_barrier type)
{
BUG_ON(in_interrupt());
/* Take cpucontrol mutex to protect against CPU hotplug */
mutex_lock(&rcu_barrier_mutex);
init_completion(&rcu_barrier_completion);
/*
* Initialize rcu_barrier_cpu_count to 1, then invoke
* rcu_barrier_func() on each CPU, so that each CPU also has
* incremented rcu_barrier_cpu_count. Only then is it safe to
* decrement rcu_barrier_cpu_count -- otherwise the first CPU
* might complete its grace period before all of the other CPUs
* did their increment, causing this function to return too
* early.
*/
atomic_set(&rcu_barrier_cpu_count, 1);
on_each_cpu(rcu_barrier_func, (void *)type, 1);
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
wait_for_completion(&rcu_barrier_completion);
mutex_unlock(&rcu_barrier_mutex);
wait_migrated_callbacks();
}
/**
* rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
*/
void rcu_barrier(void)
{
_rcu_barrier(RCU_BARRIER_STD);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
/**
* rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
*/
void rcu_barrier_bh(void)
{
_rcu_barrier(RCU_BARRIER_BH);
}
EXPORT_SYMBOL_GPL(rcu_barrier_bh);
/**
* rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
*/
void rcu_barrier_sched(void)
{
_rcu_barrier(RCU_BARRIER_SCHED);
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
static void rcu_migrate_callback(struct rcu_head *notused)
{
if (atomic_dec_and_test(&rcu_migrate_type_count))
wake_up(&rcu_migrate_wq);
}
extern int rcu_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu);
static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
unsigned long action, void *hcpu)
{
rcu_cpu_notify(self, action, hcpu);
if (action == CPU_DYING) {
/*
* preempt_disable() in on_each_cpu() prevents stop_machine(),
* so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
* returns, all online cpus have queued rcu_barrier_func(),
* and the dead cpu(if it exist) queues rcu_migrate_callback()s.
*
* These callbacks ensure _rcu_barrier() waits for all
* RCU callbacks of the specified type to complete.
*/
atomic_set(&rcu_migrate_type_count, 3);
call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
} else if (action == CPU_DOWN_PREPARE) {
/* Don't need to wait until next removal operation. */
/* rcu_migrate_head is protected by cpu_add_remove_lock */
wait_migrated_callbacks();
}
return NOTIFY_OK;
}
void __init rcu_init(void)
{
int i;
__rcu_init();
cpu_notifier(rcu_barrier_cpu_hotplug, 0);
/*
* We don't need protection against CPU-hotplug here because
* this is called early in boot, before either interrupts
* or the scheduler are operational.
*/
for_each_online_cpu(i)
rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
}
void rcu_scheduler_starting(void)
{
WARN_ON(num_online_cpus() != 1);
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}