linux/kernel/rcu/tiny.c
Frederic Weisbecker 8e9c01c717 srcu: Initialize SRCU after timers
Once srcu_init() is called, the SRCU core will make use of delayed
workqueues, which rely on timers.  However init_timers() is called
several steps after rcu_init().  This means that a call_srcu() after
rcu_init() but before init_timers() would find itself within a dangerously
uninitialized timer core.

This commit therefore creates a separate call to srcu_init() after
init_timer() completes, which ensures that we stay in early SRCU mode
until timers are safe(r).

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Neeraj Upadhyay <neeraju@codeaurora.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2021-05-10 16:03:35 -07:00

225 lines
5.9 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
* Copyright IBM Corporation, 2008
*
* Author: Paul E. McKenney <paulmck@linux.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 <linux/slab.h>
#include <linux/mm.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. */
unsigned long gp_seq; /* Grace-period counter. */
};
/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_ctrlblk = {
.donetail = &rcu_ctrlblk.rcucblist,
.curtail = &rcu_ctrlblk.rcucblist,
.gp_seq = 0 - 300UL,
};
void rcu_barrier(void)
{
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL(rcu_barrier);
/* Record an rcu quiescent state. */
void rcu_qs(void)
{
unsigned long flags;
local_irq_save(flags);
if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
raise_softirq_irqoff(RCU_SOFTIRQ);
}
WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 1);
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_sched_clock_irq(int user)
{
if (user) {
rcu_qs();
} else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
}
/*
* Reclaim the specified callback, either by invoking it for non-kfree cases or
* freeing it directly (for kfree). Return true if kfreeing, false otherwise.
*/
static inline bool rcu_reclaim_tiny(struct rcu_head *head)
{
rcu_callback_t f;
unsigned long offset = (unsigned long)head->func;
rcu_lock_acquire(&rcu_callback_map);
if (__is_kvfree_rcu_offset(offset)) {
trace_rcu_invoke_kvfree_callback("", head, offset);
kvfree((void *)head - offset);
rcu_lock_release(&rcu_callback_map);
return true;
}
trace_rcu_invoke_callback("", head);
f = head->func;
WRITE_ONCE(head->func, (rcu_callback_t)0L);
f(head);
rcu_lock_release(&rcu_callback_map);
return false;
}
/* Invoke the RCU callbacks whose grace period has elapsed. */
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
struct rcu_head *next, *list;
unsigned long flags;
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
if (rcu_ctrlblk.donetail == &rcu_ctrlblk.rcucblist) {
/* No callbacks ready, so just leave. */
local_irq_restore(flags);
return;
}
list = rcu_ctrlblk.rcucblist;
rcu_ctrlblk.rcucblist = *rcu_ctrlblk.donetail;
*rcu_ctrlblk.donetail = NULL;
if (rcu_ctrlblk.curtail == rcu_ctrlblk.donetail)
rcu_ctrlblk.curtail = &rcu_ctrlblk.rcucblist;
rcu_ctrlblk.donetail = &rcu_ctrlblk.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_tiny(list);
local_bh_enable();
list = next;
}
}
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_rcu() from within an RCU read-side critical section.
* Therefore, any legal call to synchronize_rcu() is a quiescent
* state, and so on a UP system, synchronize_rcu() need do nothing.
* (But Lai Jiangshan points out the benefits of doing might_sleep()
* to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
*/
void synchronize_rcu(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_rcu() in RCU read-side critical section");
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/*
* Post an RCU callback to be invoked after the end of an RCU grace
* period. But since we have but one CPU, that would be after any
* quiescent state.
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
unsigned long flags;
debug_rcu_head_queue(head);
head->func = func;
head->next = NULL;
local_irq_save(flags);
*rcu_ctrlblk.curtail = head;
rcu_ctrlblk.curtail = &head->next;
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
}
EXPORT_SYMBOL_GPL(call_rcu);
/*
* Return a grace-period-counter "cookie". For more information,
* see the Tree RCU header comment.
*/
unsigned long get_state_synchronize_rcu(void)
{
return READ_ONCE(rcu_ctrlblk.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/*
* Return a grace-period-counter "cookie" and ensure that a future grace
* period completes. For more information, see the Tree RCU header comment.
*/
unsigned long start_poll_synchronize_rcu(void)
{
unsigned long gp_seq = get_state_synchronize_rcu();
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
return gp_seq;
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
/*
* Return true if the grace period corresponding to oldstate has completed
* and false otherwise. For more information, see the Tree RCU header
* comment.
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
return READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
rcu_early_boot_tests();
}