Event tracing is moving to SRCU in order to take advantage of the fact that SRCU may be safely used from idle and even offline CPUs. However, event tracing can invoke call_srcu() very early in the boot process, even before workqueue_init_early() is invoked (let alone rcu_init()). Therefore, call_srcu()'s attempts to queue work fail miserably. This commit therefore detects this situation, and refrains from attempting to queue work before rcu_init() time, but does everything else that it would have done, and in addition, adds the srcu_struct to a global list. The rcu_init() function now invokes a new srcu_init() function, which is empty if CONFIG_SRCU=n. Otherwise, srcu_init() queues work for each srcu_struct on the list. This all happens early enough in boot that there is but a single CPU with interrupts disabled, which allows synchronization to be dispensed with. Of course, the queued work won't actually be invoked until after workqueue_init() is invoked, which happens shortly after the scheduler is up and running. This means that although call_srcu() may be invoked any time after per-CPU variables have been set up, there is still a very narrow window when synchronize_srcu() won't work, and this window extends from the time that the scheduler starts until the time that workqueue_init() returns. This can be fixed in a manner similar to the fix for synchronize_rcu_expedited() and friends, but until someone actually needs to use synchronize_srcu() during this window, this fix is added churn for no benefit. Finally, note that Tree SRCU's new srcu_init() function invokes queue_work() rather than the queue_delayed_work() function that is invoked post-boot. The reason is that queue_delayed_work() will (as you would expect) post a timer, and timers have not yet been initialized. So use of queue_work() avoids the complaints about use of uninitialized spinlocks that would otherwise result. Besides, some delay is already provide by the aforementioned fact that the queued work won't actually be invoked until after the scheduler is up and running. Requested-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
241 lines
6.2 KiB
C
241 lines
6.2 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
|
|
*
|
|
* 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, you can access it online at
|
|
* http://www.gnu.org/licenses/gpl-2.0.html.
|
|
*
|
|
* Copyright IBM Corporation, 2008
|
|
*
|
|
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
*
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
* Documentation/RCU
|
|
*/
|
|
#include <linux/completion.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/rcupdate_wait.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/export.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/types.h>
|
|
#include <linux/init.h>
|
|
#include <linux/time.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/prefetch.h>
|
|
|
|
#include "rcu.h"
|
|
|
|
/* Global control variables for rcupdate callback mechanism. */
|
|
struct rcu_ctrlblk {
|
|
struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
|
|
struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
|
|
struct rcu_head **curtail; /* ->next pointer of last CB. */
|
|
};
|
|
|
|
/* Definition for rcupdate control block. */
|
|
static struct rcu_ctrlblk rcu_sched_ctrlblk = {
|
|
.donetail = &rcu_sched_ctrlblk.rcucblist,
|
|
.curtail = &rcu_sched_ctrlblk.rcucblist,
|
|
};
|
|
|
|
static struct rcu_ctrlblk rcu_bh_ctrlblk = {
|
|
.donetail = &rcu_bh_ctrlblk.rcucblist,
|
|
.curtail = &rcu_bh_ctrlblk.rcucblist,
|
|
};
|
|
|
|
void rcu_barrier_bh(void)
|
|
{
|
|
wait_rcu_gp(call_rcu_bh);
|
|
}
|
|
EXPORT_SYMBOL(rcu_barrier_bh);
|
|
|
|
void rcu_barrier_sched(void)
|
|
{
|
|
wait_rcu_gp(call_rcu_sched);
|
|
}
|
|
EXPORT_SYMBOL(rcu_barrier_sched);
|
|
|
|
/*
|
|
* Helper function for rcu_sched_qs() and rcu_bh_qs().
|
|
* Also irqs are disabled to avoid confusion due to interrupt handlers
|
|
* invoking call_rcu().
|
|
*/
|
|
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
|
|
{
|
|
if (rcp->donetail != rcp->curtail) {
|
|
rcp->donetail = rcp->curtail;
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Record an rcu quiescent state. And an rcu_bh quiescent state while we
|
|
* are at it, given that any rcu quiescent state is also an rcu_bh
|
|
* quiescent state. Use "+" instead of "||" to defeat short circuiting.
|
|
*/
|
|
void rcu_sched_qs(void)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
|
|
rcu_qsctr_help(&rcu_bh_ctrlblk))
|
|
raise_softirq(RCU_SOFTIRQ);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
/*
|
|
* Record an rcu_bh quiescent state.
|
|
*/
|
|
void rcu_bh_qs(void)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
|
|
raise_softirq(RCU_SOFTIRQ);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
/*
|
|
* Check to see if the scheduling-clock interrupt came from an extended
|
|
* quiescent state, and, if so, tell RCU about it. This function must
|
|
* be called from hardirq context. It is normally called from the
|
|
* scheduling-clock interrupt.
|
|
*/
|
|
void rcu_check_callbacks(int user)
|
|
{
|
|
if (user)
|
|
rcu_sched_qs();
|
|
if (user || !in_softirq())
|
|
rcu_bh_qs();
|
|
}
|
|
|
|
/*
|
|
* Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
|
|
* whose grace period has elapsed.
|
|
*/
|
|
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
|
|
{
|
|
struct rcu_head *next, *list;
|
|
unsigned long flags;
|
|
|
|
/* Move the ready-to-invoke callbacks to a local list. */
|
|
local_irq_save(flags);
|
|
if (rcp->donetail == &rcp->rcucblist) {
|
|
/* No callbacks ready, so just leave. */
|
|
local_irq_restore(flags);
|
|
return;
|
|
}
|
|
list = rcp->rcucblist;
|
|
rcp->rcucblist = *rcp->donetail;
|
|
*rcp->donetail = NULL;
|
|
if (rcp->curtail == rcp->donetail)
|
|
rcp->curtail = &rcp->rcucblist;
|
|
rcp->donetail = &rcp->rcucblist;
|
|
local_irq_restore(flags);
|
|
|
|
/* Invoke the callbacks on the local list. */
|
|
while (list) {
|
|
next = list->next;
|
|
prefetch(next);
|
|
debug_rcu_head_unqueue(list);
|
|
local_bh_disable();
|
|
__rcu_reclaim("", list);
|
|
local_bh_enable();
|
|
list = next;
|
|
}
|
|
}
|
|
|
|
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
|
|
{
|
|
__rcu_process_callbacks(&rcu_sched_ctrlblk);
|
|
__rcu_process_callbacks(&rcu_bh_ctrlblk);
|
|
}
|
|
|
|
/*
|
|
* Wait for a grace period to elapse. But it is illegal to invoke
|
|
* synchronize_sched() from within an RCU read-side critical section.
|
|
* Therefore, any legal call to synchronize_sched() is a quiescent
|
|
* state, and so on a UP system, synchronize_sched() need do nothing.
|
|
* Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the
|
|
* benefits of doing might_sleep() to reduce latency.)
|
|
*
|
|
* Cool, huh? (Due to Josh Triplett.)
|
|
*/
|
|
void synchronize_sched(void)
|
|
{
|
|
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
|
|
lock_is_held(&rcu_lock_map) ||
|
|
lock_is_held(&rcu_sched_lock_map),
|
|
"Illegal synchronize_sched() in RCU read-side critical section");
|
|
}
|
|
EXPORT_SYMBOL_GPL(synchronize_sched);
|
|
|
|
/*
|
|
* Helper function for call_rcu() and call_rcu_bh().
|
|
*/
|
|
static void __call_rcu(struct rcu_head *head,
|
|
rcu_callback_t func,
|
|
struct rcu_ctrlblk *rcp)
|
|
{
|
|
unsigned long flags;
|
|
|
|
debug_rcu_head_queue(head);
|
|
head->func = func;
|
|
head->next = NULL;
|
|
|
|
local_irq_save(flags);
|
|
*rcp->curtail = head;
|
|
rcp->curtail = &head->next;
|
|
local_irq_restore(flags);
|
|
|
|
if (unlikely(is_idle_task(current))) {
|
|
/* force scheduling for rcu_sched_qs() */
|
|
resched_cpu(0);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Post an RCU callback to be invoked after the end of an RCU-sched grace
|
|
* period. But since we have but one CPU, that would be after any
|
|
* quiescent state.
|
|
*/
|
|
void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
|
|
{
|
|
__call_rcu(head, func, &rcu_sched_ctrlblk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(call_rcu_sched);
|
|
|
|
/*
|
|
* Post an RCU bottom-half callback to be invoked after any subsequent
|
|
* quiescent state.
|
|
*/
|
|
void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
|
|
{
|
|
__call_rcu(head, func, &rcu_bh_ctrlblk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(call_rcu_bh);
|
|
|
|
void __init rcu_init(void)
|
|
{
|
|
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
|
|
rcu_early_boot_tests();
|
|
srcu_init();
|
|
}
|