/*
* Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
{
struct rcu_synchronize rcu;
struct rcu_head *head = &rcu.head;
bool done = false;
rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
!lock_is_held(&rcu_bh_lock_map) &&
!lock_is_held(&rcu_lock_map) &&
!lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
might_sleep();
init_completion(&rcu.completion);
head->next = NULL;
head->func = wakeme_after_rcu;
spin_lock_irq(&sp->queue_lock);
if (!sp->running) {
/* steal the processing owner */
sp->running = true;
rcu_batch_queue(&sp->batch_check0, head);
spin_unlock_irq(&sp->queue_lock);
srcu_advance_batches(sp, trycount);
if (!rcu_batch_empty(&sp->batch_done)) {
BUG_ON(sp->batch_done.head != head);
rcu_batch_dequeue(&sp->batch_done);
done = true;
}
/* give the processing owner to work_struct */
srcu_reschedule(sp);
} else {
rcu_batch_queue(&sp->batch_queue, head);
spin_unlock_irq(&sp->queue_lock);
}
if (!done)
wait_for_completion(&rcu.completion);
}
/**
* synchronize_srcu - wait for prior SRCU read-side critical-section completion
* @sp: srcu_struct with which to synchronize.
*
* Wait for the count to drain to zero of both indexes. To avoid the
* possible starvation of synchronize_srcu(), it waits for the count of
* the index=((->completed & 1) ^ 1) to drain to zero at first,
* and then flip the completed and wait for the count of the other index.
*
* Can block; must be called from process context.
*
* Note that it is illegal to call synchronize_srcu() from the corresponding
* SRCU read-side critical section; doing so will result in deadlock.
* However, it is perfectly legal to call synchronize_srcu() on one
* srcu_struct from some other srcu_struct's read-side critical section,
* as long as the resulting graph of srcu_structs is acyclic.
*
* There are memory-ordering constraints implied by synchronize_srcu().
* On systems with more than one CPU, when synchronize_srcu() returns,
* each CPU is guaranteed to have executed a full memory barrier since
* the end of its last corresponding SRCU-sched read-side critical section
* whose beginning preceded the call to synchronize_srcu(). In addition,
* each CPU having an SRCU read-side critical section that extends beyond
* the return from synchronize_srcu() is guaranteed to have executed a
* full memory barrier after the beginning of synchronize_srcu() and before
* the beginning of that SRCU read-side critical section. Note that these
* guarantees include CPUs that are offline, idle, or executing in user mode,
* as well as CPUs that are executing in the kernel.
*
* Furthermore, if CPU A invoked synchronize_srcu(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
* synchronize_srcu(). This guarantee applies even if CPU A and CPU B
* are the same CPU, but again only if the system has more than one CPU.
*
* Of course, these memory-ordering guarantees apply only when
* synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
* passed the same srcu_struct structure.
*/
void synchronize_srcu(struct srcu_struct *sp)
{
__synchronize_srcu(sp, rcu_gp_is_expedited()
? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
: SYNCHRONIZE_SRCU_TRYCOUNT);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
/**
* synchronize_srcu_expedited - Brute-force SRCU grace period
* @sp: srcu_struct with which to synchronize.
*
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
*
* Note that synchronize_srcu_expedited() has the same deadlock and
* memory-ordering properties as does synchronize_srcu().
*/
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
__synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT);
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
* @sp: srcu_struct on which to wait for in-flight callbacks.
*/
void srcu_barrier(struct srcu_struct *sp)
{
synchronize_srcu(sp);
}
EXPORT_SYMBOL_GPL(srcu_barrier);
/**
* srcu_batches_completed - return batches completed.
* @sp: srcu_struct on which to report batch completion.
*
* Report the number of batches, correlated with, but not necessarily
* precisely the same as, the number of grace periods that have elapsed.
*/
unsigned long srcu_batches_completed(struct srcu_struct *sp)
{
return sp->completed;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
#define SRCU_CALLBACK_BATCH 10
#define SRCU_INTERVAL 1
/*
* Move any new SRCU callbacks to the first stage of the SRCU grace
* period pipeline.
*/
static void srcu_collect_new(struct srcu_struct *sp)
{
if (!rcu_batch_empty(&sp->batch_queue)) {
spin_lock_irq(&sp->queue_lock);
rcu_batch_move(&sp->batch_check0, &sp->batch_queue);
spin_unlock_irq(&sp->queue_lock);
}
}
/*
* Core SRCU state machine. Advance callbacks from ->batch_check0 to
* ->batch_check1 and then to ->batch_done as readers drain.
*/
static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
{
int idx = 1 ^ (sp->completed & 1);
/*
* Because readers might be delayed for an extended period after
* fetching ->completed for their index, at any point in time there
* might well be readers using both idx=0 and idx=1. We therefore
* need to wait for readers to clear from both index values before
* invoking a callback.
*/
if (rcu_batch_empty(&sp->batch_check0) &&
rcu_batch_empty(&sp->batch_check1))
return; /* no callbacks need to be advanced */
if (!try_check_zero(sp, idx, trycount))
return; /* failed to advance, will try after SRCU_INTERVAL */
/*
* The callbacks in ->batch_check1 have already done with their
* first zero check and flip back when they were enqueued on
* ->batch_check0 in a previous invocation of srcu_advance_batches().
* (Presumably try_check_zero() returned false during that
* invocation, leaving the callbacks stranded on ->batch_check1.)
* They are therefore ready to invoke, so move them to ->batch_done.
*/
rcu_batch_move(&sp->batch_done, &sp->batch_check1);
if (rcu_batch_empty(&sp->batch_check0))
return; /* no callbacks need to be advanced */
srcu_flip(sp);
/*
* The callbacks in ->batch_check0 just finished their
* first check zero and flip, so move them to ->batch_check1
* for future checking on the other idx.
*/
rcu_batch_move(&sp->batch_check1, &sp->batch_check0);
/*
* SRCU read-side critical sections are normally short, so check
* at least twice in quick succession after a flip.
*/
trycount = trycount < 2 ? 2 : trycount;
if (!try_check_zero(sp, idx^1, trycount))
return; /* failed to advance, will try after SRCU_INTERVAL */
/*
* The callbacks in ->batch_check1 have now waited for all
* pre-existing readers using both idx values. They are therefore
* ready to invoke, so move them to ->batch_done.
*/
rcu_batch_move(&sp->batch_done, &sp->batch_check1);
}
/*
* Invoke a limited number of SRCU callbacks that have passed through
* their grace period. If there are more to do, SRCU will reschedule
* the workqueue.
*/
static void srcu_invoke_callbacks(struct srcu_struct *sp)
{
int i;
struct rcu_head *head;
for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
head = rcu_batch_dequeue(&sp->batch_done);
if (!head)
break;
local_bh_disable();
head->func(head);
local_bh_enable();
}
}
/*
* Finished one round of SRCU grace period. Start another if there are
* more SRCU callbacks queued, otherwise put SRCU into not-running state.
*/
static void srcu_reschedule(struct srcu_struct *sp)
{
bool pending = true;
if (rcu_batch_empty(&sp->batch_done) &&
rcu_batch_empty(&sp->batch_check1) &&
rcu_batch_empty(&sp->batch_check0) &&
rcu_batch_empty(&sp->batch_queue)) {
spin_lock_irq(&sp->queue_lock);
if (rcu_batch_empty(&sp->batch_done) &&
rcu_batch_empty(&sp->batch_check1) &&
rcu_batch_empty(&sp->batch_check0) &&
rcu_batch_empty(&sp->batch_queue)) {
sp->running = false;
pending = false;
}
spin_unlock_irq(&sp->queue_lock);
}
if (pending)
queue_delayed_work(system_power_efficient_wq,
&sp->work, SRCU_INTERVAL);
}
/*
* This is the work-queue function that handles SRCU grace periods.
*/
void process_srcu(struct work_struct *work)
{
struct srcu_struct *sp;
sp = container_of(work, struct srcu_struct, work.work);
srcu_collect_new(sp);
srcu_advance_batches(sp, 1);
srcu_invoke_callbacks(sp);
srcu_reschedule(sp);
}
EXPORT_SYMBOL_GPL(process_srcu);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/rcu/tiny.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.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/trace_events.h>
#include "rcu.h"
/* Forward declarations for tiny_plugin.h. */
struct rcu_ctrlblk;
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
static void rcu_process_callbacks(struct softirq_action *unused);
static void __call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu),
struct rcu_ctrlblk *rcp);
#include "tiny_plugin.h"
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
/*
* Test whether RCU thinks that the current CPU is idle.
*/
bool notrace __rcu_is_watching(void)
{
return true;
}
EXPORT_SYMBOL(__rcu_is_watching);
#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
/*
* 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)
{
RCU_TRACE(reset_cpu_stall_ticks(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)
{
RCU_TRACE(check_cpu_stalls());
if (user)
rcu_sched_qs();
else if (!in_softirq())
rcu_bh_qs();
if (user)
rcu_note_voluntary_context_switch(current);
}
/*
* Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
* whose grace period has elapsed.
*/
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
RCU_TRACE(int cb_count = 0);
/* 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;
}
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
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. */
RCU_TRACE(rn = rcp->name);
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
__rcu_reclaim(rn, list);
local_bh_enable();
list = next;
RCU_TRACE(cb_count++);
}
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
RCU_TRACE(trace_rcu_batch_end(rcp->name,
cb_count, 0, need_resched(),
is_idle_task(current),
false));
}
static 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.)
*
* But we want to make this a static inline later. The cond_resched()
* currently makes this problematic.
*/
void synchronize_sched(void)
{
rcu_lockdep_assert(!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");
cond_resched();
}
EXPORT_SYMBOL_GPL(synchronize_sched);
/*
* Helper function for call_rcu() and call_rcu_bh().
*/
static void __call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu),
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;
RCU_TRACE(rcp->qlen++);
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, void (*func)(struct rcu_head *rcu))
{
__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, void (*func)(struct rcu_head *rcu))
{
__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_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
rcu_early_boot_tests();
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/rcu/tiny_plugin.h
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition
* Internal non-public definitions that provide either classic
* or preemptible semantics.
*
* 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 (c) 2010 Linaro
*
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/seq_file.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. */
RCU_TRACE(long qlen); /* Number of pending CBs. */
RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */
RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */
RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */
RCU_TRACE(const char *name); /* Name of RCU type. */
};
/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_sched_ctrlblk = {
.donetail = &rcu_sched_ctrlblk.rcucblist,
.curtail = &rcu_sched_ctrlblk.rcucblist,
RCU_TRACE(.name = "rcu_sched")
};
static struct rcu_ctrlblk rcu_bh_ctrlblk = {
.donetail = &rcu_bh_ctrlblk.rcucblist,
.curtail = &rcu_bh_ctrlblk.rcucblist,
RCU_TRACE(.name = "rcu_bh")
};
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#include <linux/kernel_stat.h>
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
/*
* During boot, we forgive RCU lockdep issues. After this function is
* invoked, we start taking RCU lockdep issues seriously.
*/
void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#ifdef CONFIG_RCU_TRACE
static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
{
unsigned long flags;
local_irq_save(flags);
rcp->qlen -= n;
local_irq_restore(flags);
}
/*
* Dump statistics for TINY_RCU, such as they are.
*/
static int show_tiny_stats(struct seq_file *m, void *unused)
{
seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
return 0;
}
static int show_tiny_stats_open(struct inode *inode, struct file *file)
{
return single_open(file, show_tiny_stats, NULL);
}
static const struct file_operations show_tiny_stats_fops = {
.owner = THIS_MODULE,
.open = show_tiny_stats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static struct dentry *rcudir;
static int __init rcutiny_trace_init(void)
{
struct dentry *retval;
rcudir = debugfs_create_dir("rcu", NULL);
if (!rcudir)
goto free_out;
retval = debugfs_create_file("rcudata", 0444, rcudir,
NULL, &show_tiny_stats_fops);
if (!retval)
goto free_out;
return 0;
free_out:
debugfs_remove_recursive(rcudir);
return 1;
}
static void __exit rcutiny_trace_cleanup(void)
{
debugfs_remove_recursive(rcudir);
}
module_init(rcutiny_trace_init);
module_exit(rcutiny_trace_cleanup);
MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
MODULE_LICENSE("GPL");
static void check_cpu_stall(struct rcu_ctrlblk *rcp)
{
unsigned long j;
unsigned long js;
if (rcu_cpu_stall_suppress)
return;
rcp->ticks_this_gp++;
j = jiffies;
js = READ_ONCE(rcp->jiffies_stall);
if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
jiffies - rcp->gp_start, rcp->qlen);
dump_stack();
WRITE_ONCE(rcp->jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
} else if (ULONG_CMP_GE(j, js)) {
WRITE_ONCE(rcp->jiffies_stall,
jiffies + rcu_jiffies_till_stall_check());
}
}
static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
{
rcp->ticks_this_gp = 0;
rcp->gp_start = jiffies;
WRITE_ONCE(rcp->jiffies_stall,
jiffies + rcu_jiffies_till_stall_check());
}
static void check_cpu_stalls(void)
{
RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
}
#endif /* #ifdef CONFIG_RCU_TRACE */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/rcu/tree.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, you can access it online at
* http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
*
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/nmi.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
#include <linux/kernel_stat.h>
#include <linux/wait.h>
#include <linux/kthread.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
#include <linux/stop_machine.h>
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
#include "tree.h"
#include "rcu.h"
MODULE_ALIAS("rcutree");
#ifdef MODULE_PARAM_PREFIX
#undef MODULE_PARAM_PREFIX
#endif
#define MODULE_PARAM_PREFIX "rcutree."
/* Data structures. */
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
/*
* In order to export the rcu_state name to the tracing tools, it
* needs to be added in the __tracepoint_string section.
* This requires defining a separate variable tp_<sname>_varname
* that points to the string being used, and this will allow
* the tracing userspace tools to be able to decipher the string
* address to the matching string.
*/
#ifdef CONFIG_TRACING
# define DEFINE_RCU_TPS(sname) \
static char sname##_varname[] = #sname; \
static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname;
# define RCU_STATE_NAME(sname) sname##_varname
#else
# define DEFINE_RCU_TPS(sname)
# define RCU_STATE_NAME(sname) __stringify(sname)
#endif
#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
DEFINE_RCU_TPS(sname) \
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
struct rcu_state sname##_state = { \
.level = { &sname##_state.node[0] }, \
.rda = &sname##_data, \
.call = cr, \
.fqs_state = RCU_GP_IDLE, \
.gpnum = 0UL - 300UL, \
.completed = 0UL - 300UL, \
.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
.orphan_nxttail = &sname##_state.orphan_nxtlist, \
.orphan_donetail = &sname##_state.orphan_donelist, \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
}
RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
static struct rcu_state *const rcu_state_p;
static struct rcu_data __percpu *const rcu_data_p;
LIST_HEAD(rcu_struct_flavors);
/* Dump rcu_node combining tree at boot to verify correct setup. */
static bool dump_tree;
module_param(dump_tree, bool, 0444);
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
module_param(rcu_fanout_exact, bool, 0444);
/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */
NUM_RCU_LVL_0,
NUM_RCU_LVL_1,
NUM_RCU_LVL_2,
NUM_RCU_LVL_3,
NUM_RCU_LVL_4,
};
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/*
* The rcu_scheduler_active variable transitions from zero to one just
* before the first task is spawned. So when this variable is zero, RCU
* can assume that there is but one task, allowing RCU to (for example)
* optimize synchronize_sched() to a simple barrier(). When this variable
* is one, RCU must actually do all the hard work required to detect real
* grace periods. This variable is also used to suppress boot-time false
* positives from lockdep-RCU error checking.
*/
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
/*
* The rcu_scheduler_fully_active variable transitions from zero to one
* during the early_initcall() processing, which is after the scheduler
* is capable of creating new tasks. So RCU processing (for example,
* creating tasks for RCU priority boosting) must be delayed until after
* rcu_scheduler_fully_active transitions from zero to one. We also
* currently delay invocation of any RCU callbacks until after this point.
*
* It might later prove better for people registering RCU callbacks during
* early boot to take responsibility for these callbacks, but one step at
* a time.
*/
static int rcu_scheduler_fully_active __read_mostly;
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
/* rcuc/rcub kthread realtime priority */
#ifdef CONFIG_RCU_KTHREAD_PRIO
static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
module_param(kthread_prio, int, 0644);
/* Delay in jiffies for grace-period initialization delays, debug only. */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
module_param(gp_preinit_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
static const int gp_preinit_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
module_param(gp_init_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
static const int gp_init_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
module_param(gp_cleanup_delay, int, 0644);
#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
static const int gp_cleanup_delay;
#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
* the need for long delays to increase some race probabilities with the
* need for fast grace periods to increase other race probabilities.
*/
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */
/*
* Track the rcutorture test sequence number and the update version
* number within a given test. The rcutorture_testseq is incremented
* on every rcutorture module load and unload, so has an odd value
* when a test is running. The rcutorture_vernum is set to zero
* when rcutorture starts and is incremented on each rcutorture update.
* These variables enable correlating rcutorture output with the
* RCU tracing information.
*/
unsigned long rcutorture_testseq;
unsigned long rcutorture_vernum;
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
* held, but the bit corresponding to the current CPU will be stable
* in most contexts.
*/
unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
return READ_ONCE(rnp->qsmaskinitnext);
}
/*
* Return true if an RCU grace period is in progress. The READ_ONCE()s
* permit this function to be invoked without holding the root rcu_node
* structure's ->lock, but of course results can be subject to change.
*/
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
}
/*
* Note a quiescent state. Because 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, this just sets a flag.
* The caller must have disabled preemption.
*/
void rcu_sched_qs(void)
{
if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_sched"),
__this_cpu_read(rcu_sched_data.gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
}
}
void rcu_bh_qs(void)
{
if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_bh"),
__this_cpu_read(rcu_bh_data.gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
}
}
static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
.dynticks = ATOMIC_INIT(1),
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
.dynticks_idle = ATOMIC_INIT(1),
#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
};
DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
/*
* Let the RCU core know that this CPU has gone through the scheduler,
* which is a quiescent state. This is called when the need for a
* quiescent state is urgent, so we burn an atomic operation and full
* memory barriers to let the RCU core know about it, regardless of what
* this CPU might (or might not) do in the near future.
*
* We inform the RCU core by emulating a zero-duration dyntick-idle
* period, which we in turn do by incrementing the ->dynticks counter
* by two.
*/
static void rcu_momentary_dyntick_idle(void)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_dynticks *rdtp;
int resched_mask;
struct rcu_state *rsp;
local_irq_save(flags);
/*
* Yes, we can lose flag-setting operations. This is OK, because
* the flag will be set again after some delay.
*/
resched_mask = raw_cpu_read(rcu_sched_qs_mask);
raw_cpu_write(rcu_sched_qs_mask, 0);
/* Find the flavor that needs a quiescent state. */
for_each_rcu_flavor(rsp) {
rdp = raw_cpu_ptr(rsp->rda);
if (!(resched_mask & rsp->flavor_mask))
continue;
smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
if (READ_ONCE(rdp->mynode->completed) !=
READ_ONCE(rdp->cond_resched_completed))
continue;
/*
* Pretend to be momentarily idle for the quiescent state.
* This allows the grace-period kthread to record the
* quiescent state, with no need for this CPU to do anything
* further.
*/
rdtp = this_cpu_ptr(&rcu_dynticks);
smp_mb__before_atomic(); /* Earlier stuff before QS. */
atomic_add(2, &rdtp->dynticks); /* QS. */
smp_mb__after_atomic(); /* Later stuff after QS. */
break;
}
local_irq_restore(flags);
}
/*
* Note a context switch. This is a quiescent state for RCU-sched,
* and requires special handling for preemptible RCU.
* The caller must have disabled preemption.
*/
void rcu_note_context_switch(void)
{
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs();
rcu_preempt_note_context_switch();
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
trace_rcu_utilization(TPS("End context switch"));
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
/*
* Register a quiescent state for all RCU flavors. If there is an
* emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
* dyntick-idle quiescent state visible to other CPUs (but only for those
* RCU flavors in desperate need of a quiescent state, which will normally
* be none of them). Either way, do a lightweight quiescent state for
* all RCU flavors.
*/
void rcu_all_qs(void)
{
if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
rcu_momentary_dyntick_idle();
this_cpu_inc(rcu_qs_ctr);
}
EXPORT_SYMBOL_GPL(rcu_all_qs);
static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */
static long qhimark = 10000; /* If this many pending, ignore blimit. */
static long qlowmark = 100; /* Once only this many pending, use blimit. */
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);
/*
* How long the grace period must be before we start recruiting
* quiescent-state help from rcu_note_context_switch().
*/
static ulong jiffies_till_sched_qs = HZ / 20;
module_param(jiffies_till_sched_qs, ulong, 0644);
static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp);
static void force_qs_rnp(struct rcu_state *rsp,
int (*f)(struct rcu_data *rsp, bool *isidle,
unsigned long *maxj),
bool *isidle, unsigned long *maxj);
static void force_quiescent_state(struct rcu_state *rsp);
static int rcu_pending(void);
/*
* Return the number of RCU batches started thus far for debug & stats.
*/
unsigned long rcu_batches_started(void)
{
return rcu_state_p->gpnum;
}
EXPORT_SYMBOL_GPL(rcu_batches_started);
/*
* Return the number of RCU-sched batches started thus far for debug & stats.
*/
unsigned long rcu_batches_started_sched(void)
{
return rcu_sched_state.gpnum;
}
EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
/*
* Return the number of RCU BH batches started thus far for debug & stats.
*/
unsigned long rcu_batches_started_bh(void)
{
return rcu_bh_state.gpnum;
}
EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
/*
* Return the number of RCU batches completed thus far for debug & stats.
*/
unsigned long rcu_batches_completed(void)
{
return rcu_state_p->completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed);
/*
* Return the number of RCU-sched batches completed thus far for debug & stats.
*/
unsigned long rcu_batches_completed_sched(void)
{
return rcu_sched_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
/*
* Return the number of RCU BH batches completed thus far for debug & stats.
*/
unsigned long rcu_batches_completed_bh(void)
{
return rcu_bh_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
/*
* Force a quiescent state.
*/
void rcu_force_quiescent_state(void)
{
force_quiescent_state(rcu_state_p);
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
* Force a quiescent state for RCU BH.
*/
void rcu_bh_force_quiescent_state(void)
{
force_quiescent_state(&rcu_bh_state);
}
EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
/*
* Force a quiescent state for RCU-sched.
*/
void rcu_sched_force_quiescent_state(void)
{
force_quiescent_state(&rcu_sched_state);
}
EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
pr_info("%s: wait state: %d ->state: %#lx\n",
rsp->name, rsp->gp_state, rsp->gp_kthread->state);
/* sched_show_task(rsp->gp_kthread); */
}
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
/*
* Record the number of times rcutorture tests have been initiated and
* terminated. This information allows the debugfs tracing stats to be
* correlated to the rcutorture messages, even when the rcutorture module
* is being repeatedly loaded and unloaded. In other words, we cannot
* store this state in rcutorture itself.
*/
void rcutorture_record_test_transition(void)
{
rcutorture_testseq++;
rcutorture_vernum = 0;
}
EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gpnum, unsigned long *completed)
{
struct rcu_state *rsp = NULL;
switch (test_type) {
case RCU_FLAVOR:
rsp = rcu_state_p;
break;
case RCU_BH_FLAVOR:
rsp = &rcu_bh_state;
break;
case RCU_SCHED_FLAVOR:
rsp = &rcu_sched_state;
break;
default:
break;
}
if (rsp != NULL) {
*flags = READ_ONCE(rsp->gp_flags);
*gpnum = READ_ONCE(rsp->gpnum);
*completed = READ_ONCE(rsp->completed);
return;
}
*flags = 0;
*gpnum = 0;
*completed = 0;
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
* Record the number of writer passes through the current rcutorture test.
* This is also used to correlate debugfs tracing stats with the rcutorture
* messages.
*/
void rcutorture_record_progress(unsigned long vernum)
{
rcutorture_vernum++;
}
EXPORT_SYMBOL_GPL(rcutorture_record_progress);
/*
* Does the CPU have callbacks ready to be invoked?
*/
static int
cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
{
return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
rdp->nxttail[RCU_DONE_TAIL] != NULL;
}
/*
* Return the root node of the specified rcu_state structure.
*/
static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
{
return &rsp->node[0];
}
/*
* Is there any need for future grace periods?
* Interrupts must be disabled. If the caller does not hold the root
* rnp_node structure's ->lock, the results are advisory only.
*/
static int rcu_future_needs_gp(struct rcu_state *rsp)
{
struct rcu_node *rnp = rcu_get_root(rsp);
int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
int *fp = &rnp->need_future_gp[idx];
return READ_ONCE(*fp);
}
/*
* Does the current CPU require a not-yet-started grace period?
* The caller must have disabled interrupts to prevent races with
* normal callback registry.
*/
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
int i;
if (rcu_gp_in_progress(rsp))
return 0; /* No, a grace period is already in progress. */
if (rcu_future_needs_gp(rsp))
return 1; /* Yes, a no-CBs CPU needs one. */
if (!rdp->nxttail[RCU_NEXT_TAIL])
return 0; /* No, this is a no-CBs (or offline) CPU. */
if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
return 1; /* Yes, this CPU has newly registered callbacks. */
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
ULONG_CMP_LT(READ_ONCE(rsp->completed),
rdp->nxtcompleted[i]))
return 1; /* Yes, CBs for future grace period. */
return 0; /* No grace period needed. */
}
/*
* rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
*
* If the new value of the ->dynticks_nesting counter now is zero,
* we really have entered idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
static void rcu_eqs_enter_common(long long oldval, bool user)
{
struct rcu_state *rsp;
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
ftrace_dump(DUMP_ORIG);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
do_nocb_deferred_wakeup(rdp);
}
rcu_prepare_for_idle();
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic(); /* Force ordering with next sojourn. */
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
atomic_read(&rdtp->dynticks) & 0x1);
rcu_dynticks_task_enter();
/*
* It is illegal to enter an extended quiescent state while
* in an RCU read-side critical section.
*/
rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
"Illegal idle entry in RCU read-side critical section.");
rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
"Illegal idle entry in RCU-bh read-side critical section.");
rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
"Illegal idle entry in RCU-sched read-side critical section.");
}
/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*/
static void rcu_eqs_enter(bool user)
{
long long oldval;
struct rcu_dynticks *rdtp;
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(oldval & DYNTICK_TASK_NEST_MASK) == 0);
if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
rcu_eqs_enter_common(oldval, user);
} else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
}
}
/**
* rcu_idle_enter - inform RCU that current CPU is entering idle
*
* Enter idle mode, in other words, -leave- the mode in which RCU
* read-side critical sections can occur. (Though RCU read-side
* critical sections can occur in irq handlers in idle, a possibility
* handled by irq_enter() and irq_exit().)
*
* We crowbar the ->dynticks_nesting field to zero to allow for
* the possibility of usermode upcalls having messed up our count
* of interrupt nesting level during the prior busy period.
*/
void rcu_idle_enter(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_eqs_enter(false);
rcu_sysidle_enter(0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_RCU_USER_QS
/**
* rcu_user_enter - inform RCU that we are resuming userspace.
*
* Enter RCU idle mode right before resuming userspace. No use of RCU
* is permitted between this call and rcu_user_exit(). This way the
* CPU doesn't need to maintain the tick for RCU maintenance purposes
* when the CPU runs in userspace.
*/
void rcu_user_enter(void)
{
rcu_eqs_enter(1);
}
#endif /* CONFIG_RCU_USER_QS */
/**
* rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
*
* Exit from an interrupt handler, which might possibly result in entering
* idle mode, in other words, leaving the mode in which read-side critical
* sections can occur.
*
* This code assumes that the idle loop never does anything that might
* result in unbalanced calls to irq_enter() and irq_exit(). If your
* architecture violates this assumption, RCU will give you what you
* deserve, good and hard. But very infrequently and irreproducibly.
*
* Use things like work queues to work around this limitation.
*
* You have been warned.
*/
void rcu_irq_exit(void)
{
unsigned long flags;
long long oldval;
struct rcu_dynticks *rdtp;
local_irq_save(flags);
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting--;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting < 0);
if (rdtp->dynticks_nesting)
trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
else
rcu_eqs_enter_common(oldval, true);
rcu_sysidle_enter(1);
local_irq_restore(flags);
}
/*
* rcu_eqs_exit_common - current CPU moving away from extended quiescent state
*
* If the new value of the ->dynticks_nesting counter was previously zero,
* we really have exited idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
static void rcu_eqs_exit_common(long long oldval, int user)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
rcu_dynticks_task_exit();
smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!(atomic_read(&rdtp->dynticks) & 0x1));
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
idle_task(smp_processor_id());
trace_rcu_dyntick(TPS("Error on exit: not idle task"),
oldval, rdtp->dynticks_nesting);
ftrace_dump(DUMP_ORIG);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
}
/*
* Exit an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*/
static void rcu_eqs_exit(bool user)
{
struct rcu_dynticks *rdtp;
long long oldval;
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
} else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
rcu_eqs_exit_common(oldval, user);
}
}
/**
* rcu_idle_exit - inform RCU that current CPU is leaving idle
*
* Exit idle mode, in other words, -enter- the mode in which RCU
* read-side critical sections can occur.
*
* We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to
* allow for the possibility of usermode upcalls messing up our count
* of interrupt nesting level during the busy period that is just
* now starting.
*/
void rcu_idle_exit(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_eqs_exit(false);
rcu_sysidle_exit(0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
#ifdef CONFIG_RCU_USER_QS
/**
* rcu_user_exit - inform RCU that we are exiting userspace.
*
* Exit RCU idle mode while entering the kernel because it can
* run a RCU read side critical section anytime.
*/
void rcu_user_exit(void)
{
rcu_eqs_exit(1);
}
#endif /* CONFIG_RCU_USER_QS */
/**
* rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
*
* Enter an interrupt handler, which might possibly result in exiting
* idle mode, in other words, entering the mode in which read-side critical
* sections can occur.
*
* Note that the Linux kernel is fully capable of entering an interrupt
* handler that it never exits, for example when doing upcalls to
* user mode! This code assumes that the idle loop never does upcalls to
* user mode. If your architecture does do upcalls from the idle loop (or
* does anything else that results in unbalanced calls to the irq_enter()
* and irq_exit() functions), RCU will give you what you deserve, good
* and hard. But very infrequently and irreproducibly.
*
* Use things like work queues to work around this limitation.
*
* You have been warned.
*/
void rcu_irq_enter(void)
{
unsigned long flags;
struct rcu_dynticks *rdtp;
long long oldval;
local_irq_save(flags);
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting == 0);
if (oldval)
trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
else
rcu_eqs_exit_common(oldval, true);
rcu_sysidle_exit(1);
local_irq_restore(flags);
}
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*
* If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
* rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
* that the CPU is active. This implementation permits nested NMIs, as
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
*/
void rcu_nmi_enter(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
int incby = 2;
/* Complain about underflow. */
WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0);
/*
* If idle from RCU viewpoint, atomically increment ->dynticks
* to mark non-idle and increment ->dynticks_nmi_nesting by one.
* Otherwise, increment ->dynticks_nmi_nesting by two. This means
* if ->dynticks_nmi_nesting is equal to one, we are guaranteed
* to be in the outermost NMI handler that interrupted an RCU-idle
* period (observation due to Andy Lutomirski).
*/
if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
smp_mb__before_atomic(); /* Force delay from prior write. */
atomic_inc(&rdtp->dynticks);
/* atomic_inc() before later RCU read-side crit sects */
smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
incby = 1;
}
rdtp->dynticks_nmi_nesting += incby;
barrier();
}
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
*
* If we are returning from the outermost NMI handler that interrupted an
* RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
*/
void rcu_nmi_exit(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
/*
* Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
* (We are exiting an NMI handler, so RCU better be paying attention
* to us!)
*/
WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
/*
* If the nesting level is not 1, the CPU wasn't RCU-idle, so
* leave it in non-RCU-idle state.
*/
if (rdtp->dynticks_nmi_nesting != 1) {
rdtp->dynticks_nmi_nesting -= 2;
return;
}
/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
rdtp->dynticks_nmi_nesting = 0;
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
smp_mb__after_atomic(); /* Force delay to next write. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
}
/**
* __rcu_is_watching - are RCU read-side critical sections safe?
*
* Return true if RCU is watching the running CPU, which means that
* this CPU can safely enter RCU read-side critical sections. Unlike
* rcu_is_watching(), the caller of __rcu_is_watching() must have at
* least disabled preemption.
*/
bool notrace __rcu_is_watching(void)
{
return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
}
/**
* rcu_is_watching - see if RCU thinks that the current CPU is idle
*
* If the current CPU is in its idle loop and is neither in an interrupt
* or NMI handler, return true.
*/
bool notrace rcu_is_watching(void)
{
bool ret;
preempt_disable();
ret = __rcu_is_watching();
preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
* Is the current CPU online? Disable preemption to avoid false positives
* that could otherwise happen due to the current CPU number being sampled,
* this task being preempted, its old CPU being taken offline, resuming
* on some other CPU, then determining that its old CPU is now offline.
* It is OK to use RCU on an offline processor during initial boot, hence
* the check for rcu_scheduler_fully_active. Note also that it is OK
* for a CPU coming online to use RCU for one jiffy prior to marking itself
* online in the cpu_online_mask. Similarly, it is OK for a CPU going
* offline to continue to use RCU for one jiffy after marking itself
* offline in the cpu_online_mask. This leniency is necessary given the
* non-atomic nature of the online and offline processing, for example,
* the fact that a CPU enters the scheduler after completing the CPU_DYING
* notifiers.
*
* This is also why RCU internally marks CPUs online during the
* CPU_UP_PREPARE phase and offline during the CPU_DEAD phase.
*
* Disable checking if in an NMI handler because we cannot safely report
* errors from NMI handlers anyway.
*/
bool rcu_lockdep_current_cpu_online(void)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
bool ret;
if (in_nmi())
return true;
preempt_disable();
rdp = this_cpu_ptr(&rcu_sched_data);
rnp = rdp->mynode;
ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
!rcu_scheduler_fully_active;
preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */
/**
* rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
*
* If the current CPU is idle or running at a first-level (not nested)
* interrupt from idle, return true. The caller must have at least
* disabled preemption.
*/
static int rcu_is_cpu_rrupt_from_idle(void)
{
return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1;
}
/*
* Snapshot the specified CPU's dynticks counter so that we can later
* credit them with an implicit quiescent state. Return 1 if this CPU
* is in dynticks idle mode, which is an extended quiescent state.
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
rcu_sysidle_check_cpu(rdp, isidle, maxj);
if ((rdp->dynticks_snap & 0x1) == 0) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
return 1;
} else {
if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
rdp->mynode->gpnum))
WRITE_ONCE(rdp->gpwrap, true);
return 0;
}
}
/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
* for this same CPU, or by virtue of having been offline.
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
bool *isidle, unsigned long *maxj)
{
unsigned int curr;
int *rcrmp;
unsigned int snap;
curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
snap = (unsigned int)rdp->dynticks_snap;
/*
* If the CPU passed through or entered a dynticks idle phase with
* no active irq/NMI handlers, then we can safely pretend that the CPU
* already acknowledged the request to pass through a quiescent
* state. Either way, that CPU cannot possibly be in an RCU
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
rdp->dynticks_fqs++;
return 1;
}
/*
* Check for the CPU being offline, but only if the grace period
* is old enough. We don't need to worry about the CPU changing
* state: If we see it offline even once, it has been through a
* quiescent state.
*
* The reason for insisting that the grace period be at least
* one jiffy old is that CPUs that are not quite online and that
* have just gone offline can still execute RCU read-side critical
* sections.
*/
if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
return 0; /* Grace period is not old enough. */
barrier();
if (cpu_is_offline(rdp->cpu)) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
rdp->offline_fqs++;
return 1;
}
/*
* A CPU running for an extended time within the kernel can
* delay RCU grace periods. When the CPU is in NO_HZ_FULL mode,
* even context-switching back and forth between a pair of
* in-kernel CPU-bound tasks cannot advance grace periods.
* So if the grace period is old enough, make the CPU pay attention.
* Note that the unsynchronized assignments to the per-CPU
* rcu_sched_qs_mask variable are safe. Yes, setting of
* bits can be lost, but they will be set again on the next
* force-quiescent-state pass. So lost bit sets do not result
* in incorrect behavior, merely in a grace period lasting
* a few jiffies longer than it might otherwise. Because
* there are at most four threads involved, and because the
* updates are only once every few jiffies, the probability of
* lossage (and thus of slight grace-period extension) is
* quite low.
*
* Note that if the jiffies_till_sched_qs boot/sysfs parameter
* is set too high, we override with half of the RCU CPU stall
* warning delay.
*/
rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
if (ULONG_CMP_GE(jiffies,
rdp->rsp->gp_start + jiffies_till_sched_qs) ||
ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
WRITE_ONCE(rdp->cond_resched_completed,
READ_ONCE(rdp->mynode->completed));
smp_mb(); /* ->cond_resched_completed before *rcrmp. */
WRITE_ONCE(*rcrmp,
READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
rdp->rsp->jiffies_resched += 5; /* Enable beating. */
} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
/* Time to beat on that CPU again! */
resched_cpu(rdp->cpu); /* Force CPU into scheduler. */
rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
}
}
return 0;
}
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
unsigned long j = jiffies;
unsigned long j1;
rsp->gp_start = j;
smp_wmb(); /* Record start time before stall time. */
j1 = rcu_jiffies_till_stall_check();
WRITE_ONCE(rsp->jiffies_stall, j + j1);
rsp->jiffies_resched = j + j1 / 2;
rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
}
/*
* Complain about starvation of grace-period kthread.
*/
static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
{
unsigned long gpa;
unsigned long j;
j = jiffies;
gpa = READ_ONCE(rsp->gp_activity);
if (j - gpa > 2 * HZ)
pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
rsp->name, j - gpa,
rsp->gpnum, rsp->completed, rsp->gp_flags);
}
/*
* Dump stacks of all tasks running on stalled CPUs.
*/
static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
{
int cpu;
unsigned long flags;
struct rcu_node *rnp;
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
if (rnp->qsmask != 0) {
for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
if (rnp->qsmask & (1UL << cpu))
dump_cpu_task(rnp->grplo + cpu);
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
}
static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
{
int cpu;
long delta;
unsigned long flags;
unsigned long gpa;
unsigned long j;
int ndetected = 0;
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
/* Only let one CPU complain about others per time interval. */
raw_spin_lock_irqsave(&rnp->lock, flags);
delta = jiffies - READ_ONCE(rsp->jiffies_stall);
if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
WRITE_ONCE(rsp->jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
* OK, time to rat on our buddy...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s detected stalls on CPUs/tasks:",
rsp->name);
print_cpu_stall_info_begin();
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
if (rnp->qsmask & (1UL << cpu)) {
print_cpu_stall_info(rsp,
rnp->grplo + cpu);
ndetected++;
}
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
(long)rsp->gpnum, (long)rsp->completed, totqlen);
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
} else {
if (READ_ONCE(rsp->gpnum) != gpnum ||
READ_ONCE(rsp->completed) == gpnum) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
gpa = READ_ONCE(rsp->gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rsp->name, j - gpa, j, gpa,
jiffies_till_next_fqs,
rcu_get_root(rsp)->qsmask);
/* In this case, the current CPU might be at fault. */
sched_show_task(current);
}
}
/* Complain about tasks blocking the grace period. */
rcu_print_detail_task_stall(rsp);
rcu_check_gp_kthread_starvation(rsp);
force_quiescent_state(rsp); /* Kick them all. */
}
static void print_cpu_stall(struct rcu_state *rsp)
{
int cpu;
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
/*
* OK, time to rat on ourselves...
* See Documentation/RCU/stallwarn.txt for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s self-detected stall on CPU", rsp->name);
print_cpu_stall_info_begin();
print_cpu_stall_info(rsp, smp_processor_id());
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
jiffies - rsp->gp_start,
(long)rsp->gpnum, (long)rsp->completed, totqlen);
rcu_check_gp_kthread_starvation(rsp);
rcu_dump_cpu_stacks(rsp);
raw_spin_lock_irqsave(&rnp->lock, flags);
if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
WRITE_ONCE(rsp->jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
* Attempt to revive the RCU machinery by forcing a context switch.
*
* A context switch would normally allow the RCU state machine to make
* progress and it could be we're stuck in kernel space without context
* switches for an entirely unreasonable amount of time.
*/
resched_cpu(smp_processor_id());
}
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long completed;
unsigned long gpnum;
unsigned long gps;
unsigned long j;
unsigned long js;
struct rcu_node *rnp;
if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
return;
j = jiffies;
/*
* Lots of memory barriers to reject false positives.
*
* The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
* then rsp->gp_start, and finally rsp->completed. These values
* are updated in the opposite order with memory barriers (or
* equivalent) during grace-period initialization and cleanup.
* Now, a false positive can occur if we get an new value of
* rsp->gp_start and a old value of rsp->jiffies_stall. But given
* the memory barriers, the only way that this can happen is if one
* grace period ends and another starts between these two fetches.
* Detect this by comparing rsp->completed with the previous fetch
* from rsp->gpnum.
*
* Given this check, comparisons of jiffies, rsp->jiffies_stall,
* and rsp->gp_start suffice to forestall false positives.
*/
gpnum = READ_ONCE(rsp->gpnum);
smp_rmb(); /* Pick up ->gpnum first... */
js = READ_ONCE(rsp->jiffies_stall);
smp_rmb(); /* ...then ->jiffies_stall before the rest... */
gps = READ_ONCE(rsp->gp_start);
smp_rmb(); /* ...and finally ->gp_start before ->completed. */
completed = READ_ONCE(rsp->completed);
if (ULONG_CMP_GE(completed, gpnum) ||
ULONG_CMP_LT(j, js) ||
ULONG_CMP_GE(gps, js))
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
if (rcu_gp_in_progress(rsp) &&
(READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
} else if (rcu_gp_in_progress(rsp) &&
ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
/* They had a few time units to dump stack, so complain. */
print_other_cpu_stall(rsp, gpnum);
}
}
/**
* rcu_cpu_stall_reset - prevent further stall warnings in current grace period
*
* Set the stall-warning timeout way off into the future, thus preventing
* any RCU CPU stall-warning messages from appearing in the current set of
* RCU grace periods.
*
* The caller must disable hard irqs.
*/
void rcu_cpu_stall_reset(void)
{
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
/*
* Initialize the specified rcu_data structure's default callback list
* to empty. The default callback list is the one that is not used by
* no-callbacks CPUs.
*/
static void init_default_callback_list(struct rcu_data *rdp)
{
int i;
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
}
/*
* Initialize the specified rcu_data structure's callback list to empty.
*/
static void init_callback_list(struct rcu_data *rdp)
{
if (init_nocb_callback_list(rdp))
return;
init_default_callback_list(rdp);
}
/*
* Determine the value that ->completed will have at the end of the
* next subsequent grace period. This is used to tag callbacks so that
* a CPU can invoke callbacks in a timely fashion even if that CPU has
* been dyntick-idle for an extended period with callbacks under the
* influence of RCU_FAST_NO_HZ.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
struct rcu_node *rnp)
{
/*
* If RCU is idle, we just wait for the next grace period.
* But we can only be sure that RCU is idle if we are looking
* at the root rcu_node structure -- otherwise, a new grace
* period might have started, but just not yet gotten around
* to initializing the current non-root rcu_node structure.
*/
if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
return rnp->completed + 1;
/*
* Otherwise, wait for a possible partial grace period and
* then the subsequent full grace period.
*/
return rnp->completed + 2;
}
/*
* Trace-event helper function for rcu_start_future_gp() and
* rcu_nocb_wait_gp().
*/
static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long c, const char *s)
{
trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
rnp->completed, c, rnp->level,
rnp->grplo, rnp->grphi, s);
}
/*
* Start some future grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
* rcu_node structure's ->need_future_gp field. Returns true if there
* is reason to awaken the grace-period kthread.
*
* The caller must hold the specified rcu_node structure's ->lock.
*/
static bool __maybe_unused
rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long *c_out)
{
unsigned long c;
int i;
bool ret = false;
struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
/*
* Pick up grace-period number for new callbacks. If this
* grace period is already marked as needed, return to the caller.
*/
c = rcu_cbs_completed(rdp->rsp, rnp);
trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf"));
if (rnp->need_future_gp[c & 0x1]) {
trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf"));
goto out;
}
/*
* If either this rcu_node structure or the root rcu_node structure
* believe that a grace period is in progress, then we must wait
* for the one following, which is in "c". Because our request
* will be noticed at the end of the current grace period, we don't
* need to explicitly start one. We only do the lockless check
* of rnp_root's fields if the current rcu_node structure thinks
* there is no grace period in flight, and because we hold rnp->lock,
* the only possible change is when rnp_root's two fields are
* equal, in which case rnp_root->gpnum might be concurrently
* incremented. But that is OK, as it will just result in our
* doing some extra useless work.
*/
if (rnp->gpnum != rnp->completed ||
READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
rnp->need_future_gp[c & 0x1]++;
trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
goto out;
}
/*
* There might be no grace period in progress. If we don't already
* hold it, acquire the root rcu_node structure's lock in order to
* start one (if needed).
*/
if (rnp != rnp_root) {
raw_spin_lock(&rnp_root->lock);
smp_mb__after_unlock_lock();
}
/*
* Get a new grace-period number. If there really is no grace
* period in progress, it will be smaller than the one we obtained
* earlier. Adjust callbacks as needed. Note that even no-CBs
* CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
*/
c = rcu_cbs_completed(rdp->rsp, rnp_root);
for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
rdp->nxtcompleted[i] = c;
/*
* If the needed for the required grace period is already
* recorded, trace and leave.
*/
if (rnp_root->need_future_gp[c & 0x1]) {
trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot"));
goto unlock_out;
}
/* Record the need for the future grace period. */
rnp_root->need_future_gp[c & 0x1]++;
/* If a grace period is not already in progress, start one. */
if (rnp_root->gpnum != rnp_root->completed) {
trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot"));
} else {
trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot"));
ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
}
unlock_out:
if (rnp != rnp_root)
raw_spin_unlock(&rnp_root->lock);
out:
if (c_out != NULL)
*c_out = c;
return ret;
}
/*
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested. Also invoke
* rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
* waiting for this grace period to complete.
*/
static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
int c = rnp->completed;
int needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
rcu_nocb_gp_cleanup(rsp, rnp);
rnp->need_future_gp[c & 0x1] = 0;
needmore = rnp->need_future_gp[(c + 1) & 0x1];
trace_rcu_future_gp(rnp, rdp, c,
needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
/*
* Awaken the grace-period kthread for the specified flavor of RCU.
* Don't do a self-awaken, and don't bother awakening when there is
* nothing for the grace-period kthread to do (as in several CPUs
* raced to awaken, and we lost), and finally don't try to awaken
* a kthread that has not yet been created.
*/
static void rcu_gp_kthread_wake(struct rcu_state *rsp)
{
if (current == rsp->gp_kthread ||
!READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
wake_up(&rsp->gp_wq);
}
/*
* If there is room, assign a ->completed number to any callbacks on
* this CPU that have not already been assigned. Also accelerate any
* callbacks that were previously assigned a ->completed number that has
* since proven to be too conservative, which can happen if callbacks get
* assigned a ->completed number while RCU is idle, but with reference to
* a non-root rcu_node structure. This function is idempotent, so it does
* not hurt to call it repeatedly. Returns an flag saying that we should
* awaken the RCU grace-period kthread.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
unsigned long c;
int i;
bool ret;
/* If the CPU has no callbacks, nothing to do. */
if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
return false;
/*
* Starting from the sublist containing the callbacks most
* recently assigned a ->completed number and working down, find the
* first sublist that is not assignable to an upcoming grace period.
* Such a sublist has something in it (first two tests) and has
* a ->completed number assigned that will complete sooner than
* the ->completed number for newly arrived callbacks (last test).
*
* The key point is that any later sublist can be assigned the
* same ->completed number as the newly arrived callbacks, which
* means that the callbacks in any of these later sublist can be
* grouped into a single sublist, whether or not they have already
* been assigned a ->completed number.
*/
c = rcu_cbs_completed(rsp, rnp);
for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
!ULONG_CMP_GE(rdp->nxtcompleted[i], c))
break;
/*
* If there are no sublist for unassigned callbacks, leave.
* At the same time, advance "i" one sublist, so that "i" will
* index into the sublist where all the remaining callbacks should
* be grouped into.
*/
if (++i >= RCU_NEXT_TAIL)
return false;
/*
* Assign all subsequent callbacks' ->completed number to the next
* full grace period and group them all in the sublist initially
* indexed by "i".
*/
for (; i <= RCU_NEXT_TAIL; i++) {
rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
rdp->nxtcompleted[i] = c;
}
/* Record any needed additional grace periods. */
ret = rcu_start_future_gp(rnp, rdp, NULL);
/* Trace depending on how much we were able to accelerate. */
if (!*rdp->nxttail[RCU_WAIT_TAIL])
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
else
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
return ret;
}
/*
* Move any callbacks whose grace period has completed to the
* RCU_DONE_TAIL sublist, then compact the remaining sublists and
* assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
* sublist. This function is idempotent, so it does not hurt to
* invoke it repeatedly. As long as it is not invoked -too- often...
* Returns true if the RCU grace-period kthread needs to be awakened.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
int i, j;
/* If the CPU has no callbacks, nothing to do. */
if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
return false;
/*
* Find all callbacks whose ->completed numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
break;
rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
}
/* Clean up any sublist tail pointers that were misordered above. */
for (j = RCU_WAIT_TAIL; j < i; j++)
rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];
/* Copy down callbacks to fill in empty sublists. */
for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
break;
rdp->nxttail[j] = rdp->nxttail[i];
rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
}
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rsp, rnp, rdp);
}
/*
* Update CPU-local rcu_data state to record the beginnings and ends of
* grace periods. The caller must hold the ->lock of the leaf rcu_node
* structure corresponding to the current CPU, and must have irqs disabled.
* Returns true if the grace-period kthread needs to be awakened.
*/
static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
bool ret;
/* Handle the ends of any preceding grace periods first. */
if (rdp->completed == rnp->completed &&
!unlikely(READ_ONCE(rdp->gpwrap))) {
/* No grace period end, so just accelerate recent callbacks. */
ret = rcu_accelerate_cbs(rsp, rnp, rdp);
} else {
/* Advance callbacks. */
ret = rcu_advance_cbs(rsp, rnp, rdp);
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
}
if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
rdp->gpnum = rnp->gpnum;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
rdp->passed_quiesce = 0;
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
zero_cpu_stall_ticks(rdp);
WRITE_ONCE(rdp->gpwrap, false);
}
return ret;
}
static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
bool needwake;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
rdp->completed == READ_ONCE(rnp->completed) &&
!unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
}
smp_mb__after_unlock_lock();
needwake = __note_gp_changes(rsp, rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (needwake)
rcu_gp_kthread_wake(rsp);
}
static void rcu_gp_slow(struct rcu_state *rsp, int delay)
{
if (delay > 0 &&
!(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_uninterruptible(delay);
}
/*
* Initialize a new grace period. Return 0 if no grace period required.
*/
static int rcu_gp_init(struct rcu_state *rsp)
{
unsigned long oldmask;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
if (!READ_ONCE(rsp->gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq(&rnp->lock);
return 0;
}
WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
/*
* Grace period already in progress, don't start another.
* Not supposed to be able to happen.
*/
raw_spin_unlock_irq(&rnp->lock);
return 0;
}
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time(rsp);
/* Record GP times before starting GP, hence smp_store_release(). */
smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
raw_spin_unlock_irq(&rnp->lock);
/*
* Apply per-leaf buffered online and offline operations to the
* rcu_node tree. Note that this new grace period need not wait
* for subsequent online CPUs, and that quiescent-state forcing
* will handle subsequent offline CPUs.
*/
rcu_for_each_leaf_node(rsp, rnp) {
rcu_gp_slow(rsp, gp_preinit_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq(&rnp->lock);
continue;
}
/* Record old state, apply changes to ->qsmaskinit field. */
oldmask = rnp->qsmaskinit;
rnp->qsmaskinit = rnp->qsmaskinitnext;
/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
if (!oldmask != !rnp->qsmaskinit) {
if (!oldmask) /* First online CPU for this rcu_node. */
rcu_init_new_rnp(rnp);
else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
rnp->wait_blkd_tasks = true;
else /* Last offline CPU and can propagate. */
rcu_cleanup_dead_rnp(rnp);
}
/*
* If all waited-on tasks from prior grace period are
* done, and if all this rcu_node structure's CPUs are
* still offline, propagate up the rcu_node tree and
* clear ->wait_blkd_tasks. Otherwise, if one of this
* rcu_node structure's CPUs has since come back online,
* simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
* checks for this, so just call it unconditionally).
*/
if (rnp->wait_blkd_tasks &&
(!rcu_preempt_has_tasks(rnp) ||
rnp->qsmaskinit)) {
rnp->wait_blkd_tasks = false;
rcu_cleanup_dead_rnp(rnp);
}
raw_spin_unlock_irq(&rnp->lock);
}
/*
* Set the quiescent-state-needed bits in all the rcu_node
* structures for all currently online CPUs in breadth-first order,
* starting from the root rcu_node structure, relying on the layout
* of the tree within the rsp->node[] array. Note that other CPUs
* will access only the leaves of the hierarchy, thus seeing that no
* grace period is in progress, at least until the corresponding
* leaf node has been initialized. In addition, we have excluded
* CPU-hotplug operations.
*
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
rcu_gp_slow(rsp, gp_init_delay);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
WRITE_ONCE(rnp->gpnum, rsp->gpnum);
if (WARN_ON_ONCE(rnp->completed != rsp->completed))
WRITE_ONCE(rnp->completed, rsp->completed);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
}
return 1;
}
/*
* Do one round of quiescent-state forcing.
*/
static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
{
int fqs_state = fqs_state_in;
bool isidle = false;
unsigned long maxj;
struct rcu_node *rnp = rcu_get_root(rsp);
WRITE_ONCE(rsp->gp_activity, jiffies);
rsp->n_force_qs++;
if (fqs_state == RCU_SAVE_DYNTICK) {
/* Collect dyntick-idle snapshots. */
if (is_sysidle_rcu_state(rsp)) {
isidle = true;
maxj = jiffies - ULONG_MAX / 4;
}
force_qs_rnp(rsp, dyntick_save_progress_counter,
&isidle, &maxj);
rcu_sysidle_report_gp(rsp, isidle, maxj);
fqs_state = RCU_FORCE_QS;
} else {
/* Handle dyntick-idle and offline CPUs. */
isidle = true;
force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
}
/* Clear flag to prevent immediate re-entry. */
if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
WRITE_ONCE(rsp->gp_flags,
READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq(&rnp->lock);
}
return fqs_state;
}
/*
* Clean up after the old grace period.
*/
static void rcu_gp_cleanup(struct rcu_state *rsp)
{
unsigned long gp_duration;
bool needgp = false;
int nocb = 0;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
WRITE_ONCE(rsp->gp_activity, jiffies);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
if (gp_duration > rsp->gp_max)
rsp->gp_max = gp_duration;
/*
* We know the grace period is complete, but to everyone else
* it appears to still be ongoing. But it is also the case
* that to everyone else it looks like there is nothing that
* they can do to advance the grace period. It is therefore
* safe for us to drop the lock in order to mark the grace
* period as completed in all of the rcu_node structures.
*/
raw_spin_unlock_irq(&rnp->lock);
/*
* Propagate new ->completed value to rcu_node structures so
* that other CPUs don't have to wait until the start of the next
* grace period to process their callbacks. This also avoids
* some nasty RCU grace-period initialization races by forcing
* the end of the current grace period to be completely recorded in
* all of the rcu_node structures before the beginning of the next
* grace period is recorded in any of the rcu_node structures.
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
WARN_ON_ONCE(rnp->qsmask);
WRITE_ONCE(rnp->completed, rsp->gpnum);
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
rcu_nocb_gp_set(rnp, nocb);
/* Declare grace period done. */
WRITE_ONCE(rsp->completed, rsp->gpnum);
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
rsp->fqs_state = RCU_GP_IDLE;
rdp = this_cpu_ptr(rsp->rda);
/* Advance CBs to reduce false positives below. */
needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
if (needgp || cpu_needs_another_gp(rsp, rdp)) {
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("newreq"));
}
raw_spin_unlock_irq(&rnp->lock);
}
/*
* Body of kthread that handles grace periods.
*/
static int __noreturn rcu_gp_kthread(void *arg)
{
int fqs_state;
int gf;
unsigned long j;
int ret;
struct rcu_state *rsp = arg;
struct rcu_node *rnp = rcu_get_root(rsp);
rcu_bind_gp_kthread();
for (;;) {
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("reqwait"));
rsp->gp_state = RCU_GP_WAIT_GPS;
wait_event_interruptible(rsp->gp_wq,
READ_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
fqs_state = RCU_SAVE_DYNTICK;
j = jiffies_till_first_fqs;
if (j > HZ) {
j = HZ;
jiffies_till_first_fqs = HZ;
}
ret = 0;
for (;;) {
if (!ret)
rsp->jiffies_force_qs = jiffies + j;
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqswait"));
rsp->gp_state = RCU_GP_WAIT_FQS;
ret = wait_event_interruptible_timeout(rsp->gp_wq,
((gf = READ_ONCE(rsp->gp_flags)) &
RCU_GP_FLAG_FQS) ||
(!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp)),
j);
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
(gf & RCU_GP_FLAG_FQS)) {
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqsstart"));
fqs_state = rcu_gp_fqs(rsp, fqs_state);
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqsend"));
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
} else {
/* Deal with stray signal. */
cond_resched_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqswaitsig"));
}
j = jiffies_till_next_fqs;
if (j > HZ) {
j = HZ;
jiffies_till_next_fqs = HZ;
} else if (j < 1) {
j = 1;
jiffies_till_next_fqs = 1;
}
}
/* Handle grace-period end. */
rcu_gp_cleanup(rsp);
}
}
/*
* Start a new RCU grace period if warranted, re-initializing the hierarchy
* in preparation for detecting the next grace period. The caller must hold
* the root node's ->lock and hard irqs must be disabled.
*
* Note that it is legal for a dying CPU (which is marked as offline) to
* invoke this function. This can happen when the dying CPU reports its
* quiescent state.
*
* Returns true if the grace-period kthread must be awakened.
*/
static bool
rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
/*
* Either we have not yet spawned the grace-period
* task, this CPU does not need another grace period,
* or a grace period is already in progress.
* Either way, don't start a new grace period.
*/
return false;
}
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
TPS("newreq"));
/*
* We can't do wakeups while holding the rnp->lock, as that
* could cause possible deadlocks with the rq->lock. Defer
* the wakeup to our caller.
*/
return true;
}
/*
* Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
* callbacks. Note that rcu_start_gp_advanced() cannot do this because it
* is invoked indirectly from rcu_advance_cbs(), which would result in
* endless recursion -- or would do so if it wasn't for the self-deadlock
* that is encountered beforehand.
*
* Returns true if the grace-period kthread needs to be awakened.
*/
static bool rcu_start_gp(struct rcu_state *rsp)
{
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
struct rcu_node *rnp = rcu_get_root(rsp);
bool ret = false;
/*
* If there is no grace period in progress right now, any
* callbacks we have up to this point will be satisfied by the
* next grace period. Also, advancing the callbacks reduces the
* probability of false positives from cpu_needs_another_gp()
* resulting in pointless grace periods. So, advance callbacks
* then start the grace period!
*/
ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
return ret;
}
/*
* Report a full set of quiescent states to the specified rcu_state
* data structure. This involves cleaning up after the prior grace
* period and letting rcu_start_gp() start up the next grace period
* if one is needed. Note that the caller must hold rnp->lock, which
* is released before return.
*/
static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
__releases(rcu_get_root(rsp)->lock)
{
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
rcu_gp_kthread_wake(rsp);
}
/*
* Similar to rcu_report_qs_rdp(), for which it is a helper function.
* Allows quiescent states for a group of CPUs to be reported at one go
* to the specified rcu_node structure, though all the CPUs in the group
* must be represented by the same rcu_node structure (which need not be a
* leaf rcu_node structure, though it often will be). The gps parameter
* is the grace-period snapshot, which means that the quiescent states
* are valid only if rnp->gpnum is equal to gps. That structure's lock
* must be held upon entry, and it is released before return.
*/
static void
rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
struct rcu_node *rnp, unsigned long gps, unsigned long flags)
__releases(rnp->lock)
{
unsigned long oldmask = 0;
struct rcu_node *rnp_c;
/* Walk up the rcu_node hierarchy. */
for (;;) {
if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
/*
* Our bit has already been cleared, or the
* relevant grace period is already over, so done.
*/
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
rnp->qsmask &= ~mask;
trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
!!rnp->gp_tasks);
if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
/* Other bits still set at this level, so done. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
mask = rnp->grpmask;
if (rnp->parent == NULL) {
/* No more levels. Exit loop holding root lock. */
break;
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
oldmask = rnp_c->qsmask;
}
/*
* Get here if we are the last CPU to pass through a quiescent
* state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
}
/*
* Record a quiescent state for all tasks that were previously queued
* on the specified rcu_node structure and that were blocking the current
* RCU grace period. The caller must hold the specified rnp->lock with
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
unsigned long mask;
struct rcu_node *rnp_p;
if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return; /* Still need more quiescent states! */
}
rnp_p = rnp->parent;
if (rnp_p == NULL) {
/*
* Only one rcu_node structure in the tree, so don't
* try to report up to its nonexistent parent!
*/
rcu_report_qs_rsp(rsp, flags);
return;
}
/* Report up the rest of the hierarchy, tracking current ->gpnum. */
gps = rnp->gpnum;
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */
smp_mb__after_unlock_lock();
rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
}
/*
* Record a quiescent state for the specified CPU to that CPU's rcu_data
* structure. This must be either called from the specified CPU, or
* called when the specified CPU is known to be offline (and when it is
* also known that no other CPU is concurrently trying to help the offline
* CPU). The lastcomp argument is used to make sure we are still in the
* grace period of interest. We don't want to end the current grace period
* based on quiescent states detected in an earlier grace period!
*/
static void
rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
bool needwake;
struct rcu_node *rnp;
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if ((rdp->passed_quiesce == 0 &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
rdp->gpwrap) {
/*
* The grace period in which this quiescent state was
* recorded has ended, so don't report it upwards.
* We will instead need a new quiescent state that lies
* within the current grace period.
*/
rdp->passed_quiesce = 0; /* need qs for new gp. */
rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
mask = rdp->grpmask;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else {
rdp->qs_pending = 0;
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
*/
needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
/* ^^^ Released rnp->lock */
if (needwake)
rcu_gp_kthread_wake(rsp);
}
}
/*
* Check to see if there is a new grace period of which this CPU
* is not yet aware, and if so, set up local rcu_data state for it.
* Otherwise, see if this CPU has just passed through its first
* quiescent state for this grace period, and record that fact if so.
*/
static void
rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
{
/* Check for grace-period ends and beginnings. */
note_gp_changes(rsp, rdp);
/*
* Does this CPU still need to do its part for current grace period?
* If no, return and let the other CPUs do their part as well.
*/
if (!rdp->qs_pending)
return;
/*
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
if (!rdp->passed_quiesce &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
return;
/*
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
}
/*
* Send the specified CPU's RCU callbacks to the orphanage. The
* specified CPU must be offline, and the caller must hold the
* ->orphan_lock.
*/
static void
rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
struct rcu_node *rnp, struct rcu_data *rdp)
{
/* No-CBs CPUs do not have orphanable callbacks. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
return;
/*
* Orphan the callbacks. First adjust the counts. This is safe
* because _rcu_barrier() excludes CPU-hotplug operations, so it
* cannot be running now. Thus no memory barrier is required.
*/
if (rdp->nxtlist != NULL) {
rsp->qlen_lazy += rdp->qlen_lazy;
rsp->qlen += rdp->qlen;
rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen_lazy = 0;
WRITE_ONCE(rdp->qlen, 0);
}
/*
* Next, move those callbacks still needing a grace period to
* the orphanage, where some other CPU will pick them up.
* Some of the callbacks might have gone partway through a grace
* period, but that is too bad. They get to start over because we
* cannot assume that grace periods are synchronized across CPUs.
* We don't bother updating the ->nxttail[] array yet, instead
* we just reset the whole thing later on.
*/
if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
*rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
*rdp->nxttail[RCU_DONE_TAIL] = NULL;
}
/*
* Then move the ready-to-invoke callbacks to the orphanage,
* where some other CPU will pick them up. These will not be
* required to pass though another grace period: They are done.
*/
if (rdp->nxtlist != NULL) {
*rsp->orphan_donetail = rdp->nxtlist;
rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
}
/*
* Finally, initialize the rcu_data structure's list to empty and
* disallow further callbacks on this CPU.
*/
init_callback_list(rdp);
rdp->nxttail[RCU_NEXT_TAIL] = NULL;
}
/*
* Adopt the RCU callbacks from the specified rcu_state structure's
* orphanage. The caller must hold the ->orphan_lock.
*/
static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
int i;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
rdp->qlen_lazy += rsp->qlen_lazy;
rdp->qlen += rsp->qlen;
rdp->n_cbs_adopted += rsp->qlen;
if (rsp->qlen_lazy != rsp->qlen)
rcu_idle_count_callbacks_posted();
rsp->qlen_lazy = 0;
rsp->qlen = 0;
/*
* We do not need a memory barrier here because the only way we
* can get here if there is an rcu_barrier() in flight is if
* we are the task doing the rcu_barrier().
*/
/* First adopt the ready-to-invoke callbacks. */
if (rsp->orphan_donelist != NULL) {
*rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
*rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
rdp->nxttail[i] = rsp->orphan_donetail;
rsp->orphan_donelist = NULL;
rsp->orphan_donetail = &rsp->orphan_donelist;
}
/* And then adopt the callbacks that still need a grace period. */
if (rsp->orphan_nxtlist != NULL) {
*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
}
}
/*
* Trace the fact that this CPU is going offline.
*/
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
RCU_TRACE(unsigned long mask);
RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
RCU_TRACE(mask = rdp->grpmask);
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
TPS("cpuofl"));
}
/*
* All CPUs for the specified rcu_node structure have gone offline,
* and all tasks that were preempted within an RCU read-side critical
* section while running on one of those CPUs have since exited their RCU
* read-side critical section. Some other CPU is reporting this fact with
* the specified rcu_node structure's ->lock held and interrupts disabled.
* This function therefore goes up the tree of rcu_node structures,
* clearing the corresponding bits in the ->qsmaskinit fields. Note that
* the leaf rcu_node structure's ->qsmaskinit field has already been
* updated
*
* This function does check that the specified rcu_node structure has
* all CPUs offline and no blocked tasks, so it is OK to invoke it
* prematurely. That said, invoking it after the fact will cost you
* a needless lock acquisition. So once it has done its work, don't
* invoke it again.
*/
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
long mask;
struct rcu_node *rnp = rnp_leaf;
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
return;
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (!rnp)
break;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
smp_mb__after_unlock_lock(); /* GP memory ordering. */
rnp->qsmaskinit &= ~mask;
rnp->qsmask &= ~mask;
if (rnp->qsmaskinit) {
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
return;
}
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
}
/*
* The CPU is exiting the idle loop into the arch_cpu_idle_dead()
* function. We now remove it from the rcu_node tree's ->qsmaskinit
* bit masks.
*/
static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */
rnp->qsmaskinitnext &= ~mask;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* The CPU has been completely removed, and some other CPU is reporting
* this fact from process context. Do the remainder of the cleanup,
* including orphaning the outgoing CPU's RCU callbacks, and also
* adopting them. There can only be one CPU hotplug operation at a time,
* so no other CPU can be attempting to update rcu_cpu_kthread_task.
*/
static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
rcu_adopt_orphan_cbs(rsp, flags);
raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
cpu, rdp->qlen, rdp->nxtlist);
}
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
long bl, count, count_lazy;
int i;
/* If no callbacks are ready, just return. */
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
}
/*
* Extract the list of ready callbacks, disabling to prevent
* races with call_rcu() from interrupt handlers.
*/
local_irq_save(flags);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
bl = rdp->blimit;
trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);
list = rdp->nxtlist;
rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
*rdp->nxttail[RCU_DONE_TAIL] = NULL;
tail = rdp->nxttail[RCU_DONE_TAIL];
for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
rdp->nxttail[i] = &rdp->nxtlist;
local_irq_restore(flags);
/* Invoke callbacks. */
count = count_lazy = 0;
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
if (__rcu_reclaim(rsp->name, list))
count_lazy++;
list = next;
/* Stop only if limit reached and CPU has something to do. */
if (++count >= bl &&
(need_resched() ||
(!is_idle_task(current) && !rcu_is_callbacks_kthread())))
break;
}
local_irq_save(flags);
trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
is_idle_task(current),
rcu_is_callbacks_kthread());
/* Update count, and requeue any remaining callbacks. */
if (list != NULL) {
*tail = rdp->nxtlist;
rdp->nxtlist = list;
for (i = 0; i < RCU_NEXT_SIZE; i++)
if (&rdp->nxtlist == rdp->nxttail[i])
rdp->nxttail[i] = tail;
else
break;
}
smp_mb(); /* List handling before counting for rcu_barrier(). */
rdp->qlen_lazy -= count_lazy;
WRITE_ONCE(rdp->qlen, rdp->qlen - count);
rdp->n_cbs_invoked += count;
/* Reinstate batch limit if we have worked down the excess. */
if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
} else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
rdp->qlen_last_fqs_check = rdp->qlen;
WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0));
local_irq_restore(flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
if (cpu_has_callbacks_ready_to_invoke(rdp))
invoke_rcu_core();
}
/*
* Check to see if this CPU is in a non-context-switch quiescent state
* (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
* Also schedule RCU core processing.
*
* This function must be called from hardirq context. It is normally
* invoked from the scheduling-clock interrupt. If rcu_pending returns
* false, there is no point in invoking rcu_check_callbacks().
*/
void rcu_check_callbacks(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
increment_cpu_stall_ticks();
if (user || rcu_is_cpu_rrupt_from_idle()) {
/*
* Get here if this CPU took its interrupt from user
* mode or from the idle loop, and if this is not a
* nested interrupt. In this case, the CPU is in
* a quiescent state, so note it.
*
* No memory barrier is required here because both
* rcu_sched_qs() and rcu_bh_qs() reference only CPU-local
* variables that other CPUs neither access nor modify,
* at least not while the corresponding CPU is online.
*/
rcu_sched_qs();
rcu_bh_qs();
} else if (!in_softirq()) {
/*
* Get here if this CPU did not take its interrupt from
* softirq, in other words, if it is not interrupting
* a rcu_bh read-side critical section. This is an _bh
* critical section, so note it.
*/
rcu_bh_qs();
}
rcu_preempt_check_callbacks();
if (rcu_pending())
invoke_rcu_core();
if (user)
rcu_note_voluntary_context_switch(current);
trace_rcu_utilization(TPS("End scheduler-tick"));
}
/*
* Scan the leaf rcu_node structures, processing dyntick state for any that
* have not yet encountered a quiescent state, using the function specified.
* Also initiate boosting for any threads blocked on the root rcu_node.
*
* The caller must have suppressed start of new grace periods.
*/
static void force_qs_rnp(struct rcu_state *rsp,
int (*f)(struct rcu_data *rsp, bool *isidle,
unsigned long *maxj),
bool *isidle, unsigned long *maxj)
{
unsigned long bit;
int cpu;
unsigned long flags;
unsigned long mask;
struct rcu_node *rnp;
rcu_for_each_leaf_node(rsp, rnp) {
cond_resched_rcu_qs();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if (rnp->qsmask == 0) {
if (rcu_state_p == &rcu_sched_state ||
rsp != rcu_state_p ||
rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
* priority-boost blocked readers.
*/
rcu_initiate_boost(rnp, flags);
/* rcu_initiate_boost() releases rnp->lock */
continue;
}
if (rnp->parent &&
(rnp->parent->qsmask & rnp->grpmask)) {
/*
* Race between grace-period
* initialization and task exiting RCU
* read-side critical section: Report.
*/
rcu_report_unblock_qs_rnp(rsp, rnp, flags);
/* rcu_report_unblock_qs_rnp() rlses ->lock */
continue;
}
}
cpu = rnp->grplo;
bit = 1;
for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
if ((rnp->qsmask & bit) != 0) {
if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
mask |= bit;
}
}
if (mask != 0) {
/* Idle/offline CPUs, report (releases rnp->lock. */
rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
}
}
/*
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
static void force_quiescent_state(struct rcu_state *rsp)
{
unsigned long flags;
bool ret;
struct rcu_node *rnp;
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
rnp = __this_cpu_read(rsp->rda->mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret) {
rsp->n_force_qs_lh++;
return;
}
rnp_old = rnp;
}
/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave(&rnp_old->lock, flags);
smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
rsp->n_force_qs_lh++;
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
return; /* Someone beat us to it. */
}
WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
rcu_gp_kthread_wake(rsp);
}
/*
* This does the RCU core processing work for the specified rcu_state
* and rcu_data structures. This may be called only from the CPU to
* whom the rdp belongs.
*/
static void
__rcu_process_callbacks(struct rcu_state *rsp)
{
unsigned long flags;
bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
WARN_ON_ONCE(rdp->beenonline == 0);
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
/* Does this CPU require a not-yet-started grace period? */
local_irq_save(flags);
if (cpu_needs_another_gp(rsp, rdp)) {
raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
needwake = rcu_start_gp(rsp);
raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
if (needwake)
rcu_gp_kthread_wake(rsp);
} else {
local_irq_restore(flags);
}
/* If there are callbacks ready, invoke them. */
if (cpu_has_callbacks_ready_to_invoke(rdp))
invoke_rcu_callbacks(rsp, rdp);
/* Do any needed deferred wakeups of rcuo kthreads. */
do_nocb_deferred_wakeup(rdp);
}
/*
* Do RCU core processing for the current CPU.
*/
static void rcu_process_callbacks(struct softirq_action *unused)
{
struct rcu_state *rsp;
if (cpu_is_offline(smp_processor_id()))
return;
trace_rcu_utilization(TPS("Start RCU core"));
for_each_rcu_flavor(rsp)
__rcu_process_callbacks(rsp);
trace_rcu_utilization(TPS("End RCU core"));
}
/*
* Schedule RCU callback invocation. If the specified type of RCU
* does not support RCU priority boosting, just do a direct call,
* otherwise wake up the per-CPU kernel kthread. Note that because we
* are running on the current CPU with softirqs disabled, the
* rcu_cpu_kthread_task cannot disappear out from under us.
*/
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
{
if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
return;
if (likely(!rsp->boost)) {
rcu_do_batch(rsp, rdp);
return;
}
invoke_rcu_callbacks_kthread();
}
static void invoke_rcu_core(void)
{
if (cpu_online(smp_processor_id()))
raise_softirq(RCU_SOFTIRQ);
}
/*
* Handle any core-RCU processing required by a call_rcu() invocation.
*/
static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_head *head, unsigned long flags)
{
bool needwake;
/*
* If called from an extended quiescent state, invoke the RCU
* core in order to force a re-evaluation of RCU's idleness.
*/
if (!rcu_is_watching())
invoke_rcu_core();
/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id()))
return;
/*
* Force the grace period if too many callbacks or too long waiting.
* Enforce hysteresis, and don't invoke force_quiescent_state()
* if some other CPU has recently done so. Also, don't bother
* invoking force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
note_gp_changes(rsp, rdp);
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
struct rcu_node *rnp_root = rcu_get_root(rsp);
raw_spin_lock(&rnp_root->lock);
smp_mb__after_unlock_lock();
needwake = rcu_start_gp(rsp);
raw_spin_unlock(&rnp_root->lock);
if (needwake)
rcu_gp_kthread_wake(rsp);
} else {
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
if (rsp->n_force_qs == rdp->n_force_qs_snap &&
*rdp->nxttail[RCU_DONE_TAIL] != head)
force_quiescent_state(rsp);
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->qlen_last_fqs_check = rdp->qlen;
}
}
}
/*
* RCU callback function to leak a callback.
*/
static void rcu_leak_callback(struct rcu_head *rhp)
{
}
/*
* Helper function for call_rcu() and friends. The cpu argument will
* normally be -1, indicating "currently running CPU". It may specify
* a CPU only if that CPU is a no-CBs CPU. Currently, only _rcu_barrier()
* is expected to specify a CPU.
*/
static void
__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
struct rcu_state *rsp, int cpu, bool lazy)
{
unsigned long flags;
struct rcu_data *rdp;
WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
if (debug_rcu_head_queue(head)) {
/* Probable double call_rcu(), so leak the callback. */
WRITE_ONCE(head->func, rcu_leak_callback);
WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
return;
}
head->func = func;
head->next = NULL;
/*
* Opportunistically note grace-period endings and beginnings.
* Note that we might see a beginning right after we see an
* end, but never vice versa, since this CPU has to pass through
* a quiescent state betweentimes.
*/
local_irq_save(flags);
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
int offline;
if (cpu != -1)
rdp = per_cpu_ptr(rsp->rda, cpu);
if (likely(rdp->mynode)) {
/* Post-boot, so this should be for a no-CBs CPU. */
offline = !__call_rcu_nocb(rdp, head, lazy, flags);
WARN_ON_ONCE(offline);
/* Offline CPU, _call_rcu() illegal, leak callback. */
local_irq_restore(flags);
return;
}
/*
* Very early boot, before rcu_init(). Initialize if needed
* and then drop through to queue the callback.
*/
BUG_ON(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
if (!likely(rdp->nxtlist))
init_default_callback_list(rdp);
}
WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
if (lazy)
rdp->qlen_lazy++;
else
rcu_idle_count_callbacks_posted();
smp_mb(); /* Count before adding callback for rcu_barrier(). */
*rdp->nxttail[RCU_NEXT_TAIL] = head;
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
rdp->qlen_lazy, rdp->qlen);
else
trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen);
/* Go handle any RCU core processing required. */
__call_rcu_core(rsp, rdp, head, flags);
local_irq_restore(flags);
}
/*
* Queue an RCU-sched callback for invocation after a grace period.
*/
void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
__call_rcu(head, func, &rcu_sched_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);
/*
* Queue an RCU callback for invocation after a quicker grace period.
*/
void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
__call_rcu(head, func, &rcu_bh_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
/*
* Queue an RCU callback for lazy invocation after a grace period.
* This will likely be later named something like "call_rcu_lazy()",
* but this change will require some way of tagging the lazy RCU
* callbacks in the list of pending callbacks. Until then, this
* function may only be called from __kfree_rcu().
*/
void kfree_call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu))
{
__call_rcu(head, func, rcu_state_p, -1, 1);
}
EXPORT_SYMBOL_GPL(kfree_call_rcu);
/*
* Because a context switch is a grace period for RCU-sched and RCU-bh,
* any blocking grace-period wait automatically implies a grace period
* if there is only one CPU online at any point time during execution
* of either synchronize_sched() or synchronize_rcu_bh(). It is OK to
* occasionally incorrectly indicate that there are multiple CPUs online
* when there was in fact only one the whole time, as this just adds
* some overhead: RCU still operates correctly.
*/
static inline int rcu_blocking_is_gp(void)
{
int ret;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
ret = num_online_cpus() <= 1;
preempt_enable();
return ret;
}
/**
* synchronize_sched - wait until an rcu-sched grace period has elapsed.
*
* Control will return to the caller some time after a full rcu-sched
* grace period has elapsed, in other words after all currently executing
* rcu-sched read-side critical sections have completed. These read-side
* critical sections are delimited by rcu_read_lock_sched() and
* rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
* local_irq_disable(), and so on may be used in place of
* rcu_read_lock_sched().
*
* This means that all preempt_disable code sequences, including NMI and
* non-threaded hardware-interrupt handlers, in progress on entry will
* have completed before this primitive returns. However, this does not
* guarantee that softirq handlers will have completed, since in some
* kernels, these handlers can run in process context, and can block.
*
* Note that this guarantee implies further memory-ordering guarantees.
* On systems with more than one CPU, when synchronize_sched() returns,
* each CPU is guaranteed to have executed a full memory barrier since the
* end of its last RCU-sched read-side critical section whose beginning
* preceded the call to synchronize_sched(). In addition, each CPU having
* an RCU read-side critical section that extends beyond the return from
* synchronize_sched() is guaranteed to have executed a full memory barrier
* after the beginning of synchronize_sched() and before the beginning of
* that RCU read-side critical section. Note that these guarantees include
* CPUs that are offline, idle, or executing in user mode, as well as CPUs
* that are executing in the kernel.
*
* Furthermore, if CPU A invoked synchronize_sched(), which returned
* to its caller on CPU B, then both CPU A and CPU B are guaranteed
* to have executed a full memory barrier during the execution of
* synchronize_sched() -- even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*
* This primitive provides the guarantees made by the (now removed)
* synchronize_kernel() API. In contrast, synchronize_rcu() only
* guarantees that rcu_read_lock() sections will have completed.
* In "classic RCU", these two guarantees happen to be one and
* the same, but can differ in realtime RCU implementations.
*/
void synchronize_sched(void)
{
rcu_lockdep_assert(!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-sched read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
synchronize_sched_expedited();
else
wait_rcu_gp(call_rcu_sched);
}
EXPORT_SYMBOL_GPL(synchronize_sched);
/**
* 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.
*
* See the description of synchronize_sched() for more detailed information
* on memory ordering guarantees.
*/
void synchronize_rcu_bh(void)
{
rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
!lock_is_held(&rcu_lock_map) &&
!lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
if (rcu_blocking_is_gp())
return;
if (rcu_gp_is_expedited())
synchronize_rcu_bh_expedited();
else
wait_rcu_gp(call_rcu_bh);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
/**
* get_state_synchronize_rcu - Snapshot current RCU state
*
* Returns a cookie that is used by a later call to cond_synchronize_rcu()
* to determine whether or not a full grace period has elapsed in the
* meantime.
*/
unsigned long get_state_synchronize_rcu(void)
{
/*
* Any prior manipulation of RCU-protected data must happen
* before the load from ->gpnum.
*/
smp_mb(); /* ^^^ */
/*
* Make sure this load happens before the purportedly
* time-consuming work between get_state_synchronize_rcu()
* and cond_synchronize_rcu().
*/
return smp_load_acquire(&rcu_state_p->gpnum);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/**
* cond_synchronize_rcu - Conditionally wait for an RCU grace period
*
* @oldstate: return value from earlier call to get_state_synchronize_rcu()
*
* If a full RCU grace period has elapsed since the earlier call to
* get_state_synchronize_rcu(), just return. Otherwise, invoke
* synchronize_rcu() to wait for a full grace period.
*
* Yes, this function does not take counter wrap into account. But
* counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
* so waiting for one additional grace period should be just fine.
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
unsigned long newstate;
/*
* Ensure that this load happens before any RCU-destructive
* actions the caller might carry out after we return.
*/
newstate = smp_load_acquire(&rcu_state_p->completed);
if (ULONG_CMP_GE(oldstate, newstate))
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
static int synchronize_sched_expedited_cpu_stop(void *data)
{
/*
* There must be a full memory barrier on each affected CPU
* between the time that try_stop_cpus() is called and the
* time that it returns.
*
* In the current initial implementation of cpu_stop, the
* above condition is already met when the control reaches
* this point and the following smp_mb() is not strictly
* necessary. Do smp_mb() anyway for documentation and
* robustness against future implementation changes.
*/
smp_mb(); /* See above comment block. */
return 0;
}
/**
* synchronize_sched_expedited - Brute-force RCU-sched grace period
*
* Wait for an RCU-sched grace period to elapse, but use a "big hammer"
* approach to force the grace period to end quickly. This consumes
* significant time on all CPUs and is unfriendly to real-time workloads,
* so is thus not recommended for any sort of common-case code. In fact,
* if you are using synchronize_sched_expedited() in a loop, please
* restructure your code to batch your updates, and then use a single
* synchronize_sched() instead.
*
* This implementation can be thought of as an application of ticket
* locking to RCU, with sync_sched_expedited_started and
* sync_sched_expedited_done taking on the roles of the halves
* of the ticket-lock word. Each task atomically increments
* sync_sched_expedited_started upon entry, snapshotting the old value,
* then attempts to stop all the CPUs. If this succeeds, then each
* CPU will have executed a context switch, resulting in an RCU-sched
* grace period. We are then done, so we use atomic_cmpxchg() to
* update sync_sched_expedited_done to match our snapshot -- but
* only if someone else has not already advanced past our snapshot.
*
* On the other hand, if try_stop_cpus() fails, we check the value
* of sync_sched_expedited_done. If it has advanced past our
* initial snapshot, then someone else must have forced a grace period
* some time after we took our snapshot. In this case, our work is
* done for us, and we can simply return. Otherwise, we try again,
* but keep our initial snapshot for purposes of checking for someone
* doing our work for us.
*
* If we fail too many times in a row, we fall back to synchronize_sched().
*/
void synchronize_sched_expedited(void)
{
cpumask_var_t cm;
bool cma = false;
int cpu;
long firstsnap, s, snap;
int trycount = 0;
struct rcu_state *rsp = &rcu_sched_state;
/*
* If we are in danger of counter wrap, just do synchronize_sched().
* By allowing sync_sched_expedited_started to advance no more than
* ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring
* that more than 3.5 billion CPUs would be required to force a
* counter wrap on a 32-bit system. Quite a few more CPUs would of
* course be required on a 64-bit system.
*/
if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
(ulong)atomic_long_read(&rsp->expedited_done) +
ULONG_MAX / 8)) {
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_wrap);
return;
}
/*
* Take a ticket. Note that atomic_inc_return() implies a
* full memory barrier.
*/
snap = atomic_long_inc_return(&rsp->expedited_start);
firstsnap = snap;
if (!try_get_online_cpus()) {
/* CPU hotplug operation in flight, fall back to normal GP. */
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
return;
}
WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
/* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
if (cma) {
cpumask_copy(cm, cpu_online_mask);
cpumask_clear_cpu(raw_smp_processor_id(), cm);
for_each_cpu(cpu, cm) {
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
cpumask_clear_cpu(cpu, cm);
}
if (cpumask_weight(cm) == 0)
goto all_cpus_idle;
}
/*
* Each pass through the following loop attempts to force a
* context switch on each CPU.
*/
while (try_stop_cpus(cma ? cm : cpu_online_mask,
synchronize_sched_expedited_cpu_stop,
NULL) == -EAGAIN) {
put_online_cpus();
atomic_long_inc(&rsp->expedited_tryfail);
/* Check to see if someone else did our work for us. */
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
/* ensure test happens before caller kfree */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone1);
free_cpumask_var(cm);
return;
}
/* No joy, try again later. Or just synchronize_sched(). */
if (trycount++ < 10) {
udelay(trycount * num_online_cpus());
} else {
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
free_cpumask_var(cm);
return;
}
/* Recheck to see if someone else did our work for us. */
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
/* ensure test happens before caller kfree */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone2);
free_cpumask_var(cm);
return;
}
/*
* Refetching sync_sched_expedited_started allows later
* callers to piggyback on our grace period. We retry
* after they started, so our grace period works for them,
* and they started after our first try, so their grace
* period works for us.
*/
if (!try_get_online_cpus()) {
/* CPU hotplug operation in flight, use normal GP. */
wait_rcu_gp(call_rcu_sched);
atomic_long_inc(&rsp->expedited_normal);
free_cpumask_var(cm);
return;
}
snap = atomic_long_read(&rsp->expedited_start);
smp_mb(); /* ensure read is before try_stop_cpus(). */
}
atomic_long_inc(&rsp->expedited_stoppedcpus);
all_cpus_idle:
free_cpumask_var(cm);
/*
* Everyone up to our most recent fetch is covered by our grace
* period. Update the counter, but only if our work is still
* relevant -- which it won't be if someone who started later
* than we did already did their update.
*/
do {
atomic_long_inc(&rsp->expedited_done_tries);
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
/* ensure test happens before caller kfree */
smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_done_lost);
break;
}
} while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s);
atomic_long_inc(&rsp->expedited_done_exit);
put_online_cpus();
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, for the specified type of RCU, returning 1 if so.
* The checks are in order of increasing expense: checks that can be
* carried out against CPU-local state are performed first. However,
* we must check for CPU stalls first, else we might not get a chance.
*/
static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
{
struct rcu_node *rnp = rdp->mynode;
rdp->n_rcu_pending++;
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rsp, rdp);
/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
if (rcu_nohz_full_cpu(rsp))
return 0;
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->qs_pending && !rdp->passed_quiesce &&
rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
rdp->n_rp_qs_pending++;
} else if (rdp->qs_pending &&
(rdp->passed_quiesce ||
rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
rdp->n_rp_report_qs++;
return 1;
}
/* Does this CPU have callbacks ready to invoke? */
if (cpu_has_callbacks_ready_to_invoke(rdp)) {
rdp->n_rp_cb_ready++;
return 1;
}
/* Has RCU gone idle with this CPU needing another grace period? */
if (cpu_needs_another_gp(rsp, rdp)) {
rdp->n_rp_cpu_needs_gp++;
return 1;
}
/* Has another RCU grace period completed? */
if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
rdp->n_rp_gp_completed++;
return 1;
}
/* Has a new RCU grace period started? */
if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
rdp->n_rp_gp_started++;
return 1;
}
/* Does this CPU need a deferred NOCB wakeup? */
if (rcu_nocb_need_deferred_wakeup(rdp)) {
rdp->n_rp_nocb_defer_wakeup++;
return 1;
}
/* nothing to do */
rdp->n_rp_need_nothing++;
return 0;
}
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, returning 1 if so. This function is part of the
* RCU implementation; it is -not- an exported member of the RCU API.
*/
static int rcu_pending(void)
{
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda)))
return 1;
return 0;
}
/*
* Return true if the specified CPU has any callback. If all_lazy is
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
{
bool al = true;
bool hc = false;
struct rcu_data *rdp;
struct rcu_state *rsp;
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
if (!rdp->nxtlist)
continue;
hc = true;
if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
al = false;
break;
}
}
if (all_lazy)
*all_lazy = al;
return hc;
}
/*
* Helper function for _rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
*/
static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s,
int cpu, unsigned long done)
{
trace_rcu_barrier(rsp->name, s, cpu,
atomic_read(&rsp->barrier_cpu_count), done);
}
/*
* RCU callback function for _rcu_barrier(). If we are last, wake
* up the task executing _rcu_barrier().
*/
static void rcu_barrier_callback(struct rcu_head *rhp)
{
struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head);
struct rcu_state *rsp = rdp->rsp;
if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
_rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done);
complete(&rsp->barrier_completion);
} else {
_rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done);
}
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
static void rcu_barrier_func(void *type)
{
struct rcu_state *rsp = type;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
_rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
atomic_inc(&rsp->barrier_cpu_count);
rsp->call(&rdp->barrier_head, rcu_barrier_callback);
}
/*
* Orchestrate the specified type of RCU barrier, waiting for all
* RCU callbacks of the specified type to complete.
*/
static void _rcu_barrier(struct rcu_state *rsp)
{
int cpu;
struct rcu_data *rdp;
unsigned long snap = READ_ONCE(rsp->n_barrier_done);
unsigned long snap_done;
_rcu_barrier_trace(rsp, "Begin", -1, snap);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
mutex_lock(&rsp->barrier_mutex);
/*
* Ensure that all prior references, including to ->n_barrier_done,
* are ordered before the _rcu_barrier() machinery.
*/
smp_mb(); /* See above block comment. */
/*
* Recheck ->n_barrier_done to see if others did our work for us.
* This means checking ->n_barrier_done for an even-to-odd-to-even
* transition. The "if" expression below therefore rounds the old
* value up to the next even number and adds two before comparing.
*/
snap_done = rsp->n_barrier_done;
_rcu_barrier_trace(rsp, "Check", -1, snap_done);
/*
* If the value in snap is odd, we needed to wait for the current
* rcu_barrier() to complete, then wait for the next one, in other
* words, we need the value of snap_done to be three larger than
* the value of snap. On the other hand, if the value in snap is
* even, we only had to wait for the next rcu_barrier() to complete,
* in other words, we need the value of snap_done to be only two
* greater than the value of snap. The "(snap + 3) & ~0x1" computes
* this for us (thank you, Linus!).
*/
if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
smp_mb(); /* caller's subsequent code after above check. */
mutex_unlock(&rsp->barrier_mutex);
return;
}
/*
* Increment ->n_barrier_done to avoid duplicate work. Use
* WRITE_ONCE() to prevent the compiler from speculating
* the increment to precede the early-exit check.
*/
WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
/*
* Initialize the count to one rather than to zero in order to
* avoid a too-soon return to zero in case of a short grace period
* (or preemption of this task). Exclude CPU-hotplug operations
* to ensure that no offline CPU has callbacks queued.
*/
init_completion(&rsp->barrier_completion);
atomic_set(&rsp->barrier_cpu_count, 1);
get_online_cpus();
/*
* Force each CPU with callbacks to register a new callback.
* When that callback is invoked, we will know that all of the
* corresponding CPU's preceding callbacks have been invoked.
*/
for_each_possible_cpu(cpu) {
if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
continue;
rdp = per_cpu_ptr(rsp->rda, cpu);
if (rcu_is_nocb_cpu(cpu)) {
if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
rsp->n_barrier_done);
} else {
_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
rsp->n_barrier_done);
smp_mb__before_atomic();
atomic_inc(&rsp->barrier_cpu_count);
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
} else if (READ_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
} else {
_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
rsp->n_barrier_done);
}
}
put_online_cpus();
/*
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
if (atomic_dec_and_test(&rsp->barrier_cpu_count))
complete(&rsp->barrier_completion);
/* Increment ->n_barrier_done to prevent duplicate work. */
smp_mb(); /* Keep increment after above mechanism. */
WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
smp_mb(); /* Keep increment before caller's subsequent code. */
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
wait_for_completion(&rsp->barrier_completion);
/* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rsp->barrier_mutex);
}
/**
* rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
*/
void rcu_barrier_bh(void)
{
_rcu_barrier(&rcu_bh_state);
}
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_sched_state);
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
* first CPU in a given leaf rcu_node structure coming online. The caller
* must hold the corresponding leaf rcu_node ->lock with interrrupts
* disabled.
*/
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
{
long mask;
struct rcu_node *rnp = rnp_leaf;
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (rnp == NULL)
return;
raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */
rnp->qsmaskinit |= mask;
raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
}
}
/*
* Do boot-time initialization of a CPU's per-CPU RCU data.
*/
static void __init
rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
rdp->cpu = cpu;
rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* Initialize a CPU's per-CPU RCU data. Note that only one online or
* offline event can be happening at a given time. Note also that we
* can accept some slop in the rsp->completed access due to the fact
* that this CPU cannot possibly have any RCU callbacks in flight yet.
*/
static void
rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
{
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
rdp->beenonline = 1; /* We have now been online. */
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
if (!rdp->nxtlist)
init_callback_list(rdp); /* Re-enable callbacks on this CPU. */
rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
rcu_sysidle_init_percpu_data(rdp->dynticks);
atomic_set(&rdp->dynticks->dynticks,
(atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
/*
* Add CPU to leaf rcu_node pending-online bitmask. Any needed
* propagation up the rcu_node tree will happen at the beginning
* of the next grace period.
*/
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
smp_mb__after_unlock_lock();
rnp->qsmaskinitnext |= mask;
rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
rdp->completed = rnp->completed;
rdp->passed_quiesce = false;
rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
rdp->qs_pending = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
static void rcu_prepare_cpu(int cpu)
{
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
rcu_init_percpu_data(cpu, rsp);
}
/*
* Handle CPU online/offline notification events.
*/
int rcu_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
struct rcu_node *rnp = rdp->mynode;
struct rcu_state *rsp;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
rcu_prepare_cpu(cpu);
rcu_prepare_kthreads(cpu);
rcu_spawn_all_nocb_kthreads(cpu);
break;
case CPU_ONLINE:
case CPU_DOWN_FAILED:
rcu_boost_kthread_setaffinity(rnp, -1);
break;
case CPU_DOWN_PREPARE:
rcu_boost_kthread_setaffinity(rnp, cpu);
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
for_each_rcu_flavor(rsp)
rcu_cleanup_dying_cpu(rsp);
break;
case CPU_DYING_IDLE:
for_each_rcu_flavor(rsp) {
rcu_cleanup_dying_idle_cpu(cpu, rsp);
}
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
for_each_rcu_flavor(rsp) {
rcu_cleanup_dead_cpu(cpu, rsp);
do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu));
}
break;
default:
break;
}
return NOTIFY_OK;
}
static int rcu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
rcu_unexpedite_gp();
break;
default:
break;
}
return NOTIFY_OK;
}
/*
* Spawn the kthreads that handle each RCU flavor's grace periods.
*/
static int __init rcu_spawn_gp_kthread(void)
{
unsigned long flags;
int kthread_prio_in = kthread_prio;
struct rcu_node *rnp;
struct rcu_state *rsp;
struct sched_param sp;
struct task_struct *t;
/* Force priority into range. */
if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
kthread_prio = 1;
else if (kthread_prio < 0)
kthread_prio = 0;
else if (kthread_prio > 99)
kthread_prio = 99;
if (kthread_prio != kthread_prio_in)
pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
kthread_prio, kthread_prio_in);
rcu_scheduler_fully_active = 1;
for_each_rcu_flavor(rsp) {
t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name);
BUG_ON(IS_ERR(t));
rnp = rcu_get_root(rsp);
raw_spin_lock_irqsave(&rnp->lock, flags);
rsp->gp_kthread = t;
if (kthread_prio) {
sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
}
wake_up_process(t);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
rcu_spawn_nocb_kthreads();
rcu_spawn_boost_kthreads();
return 0;
}
early_initcall(rcu_spawn_gp_kthread);
/*
* This function is invoked towards the end of the scheduler's initialization
* process. Before this is called, the idle task might contain
* RCU read-side critical sections (during which time, this idle
* task is booting the system). After this function is called, the
* idle tasks are prohibited from containing RCU read-side critical
* sections. This function also enables RCU lockdep checking.
*/
void rcu_scheduler_starting(void)
{
WARN_ON(num_online_cpus() != 1);
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}
/*
* Compute the per-level fanout, either using the exact fanout specified
* or balancing the tree, depending on the rcu_fanout_exact boot parameter.
*/
static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
if (rcu_fanout_exact) {
rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
rsp->levelspread[i] = RCU_FANOUT;
} else {
int ccur;
int cprv;
cprv = nr_cpu_ids;
for (i = rcu_num_lvls - 1; i >= 0; i--) {
ccur = rsp->levelcnt[i];
rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
cprv = ccur;
}
}
}
/*
* Helper function for rcu_init() that initializes one rcu_state structure.
*/
static void __init rcu_init_one(struct rcu_state *rsp,
struct rcu_data __percpu *rda)
{
static const char * const buf[] = {
"rcu_node_0",
"rcu_node_1",
"rcu_node_2",
"rcu_node_3" }; /* Match MAX_RCU_LVLS */
static const char * const fqs[] = {
"rcu_node_fqs_0",
"rcu_node_fqs_1",
"rcu_node_fqs_2",
"rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */
static u8 fl_mask = 0x1;
int cpustride = 1;
int i;
int j;
struct rcu_node *rnp;
BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
/* Silence gcc 4.8 false positive about array index out of range. */
if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
panic("rcu_init_one: rcu_num_lvls out of range");
/* Initialize the level-tracking arrays. */
for (i = 0; i < rcu_num_lvls; i++)
rsp->levelcnt[i] = num_rcu_lvl[i];
for (i = 1; i < rcu_num_lvls; i++)
rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
rcu_init_levelspread(rsp);
rsp->flavor_mask = fl_mask;
fl_mask <<= 1;
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= rsp->levelspread[i];
rnp = rsp->level[i];
for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
raw_spin_lock_init(&rnp->lock);
lockdep_set_class_and_name(&rnp->lock,
&rcu_node_class[i], buf[i]);
raw_spin_lock_init(&rnp->fqslock);
lockdep_set_class_and_name(&rnp->fqslock,
&rcu_fqs_class[i], fqs[i]);
rnp->gpnum = rsp->gpnum;
rnp->completed = rsp->completed;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
rnp->grphi = (j + 1) * cpustride - 1;
if (rnp->grphi >= nr_cpu_ids)
rnp->grphi = nr_cpu_ids - 1;
if (i == 0) {
rnp->grpnum = 0;
rnp->grpmask = 0;
rnp->parent = NULL;
} else {
rnp->grpnum = j % rsp->levelspread[i - 1];
rnp->grpmask = 1UL << rnp->grpnum;
rnp->parent = rsp->level[i - 1] +
j / rsp->levelspread[i - 1];
}
rnp->level = i;
INIT_LIST_HEAD(&rnp->blkd_tasks);
rcu_init_one_nocb(rnp);
}
}
init_waitqueue_head(&rsp->gp_wq);
rnp = rsp->level[rcu_num_lvls - 1];
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
per_cpu_ptr(rsp->rda, i)->mynode = rnp;
rcu_boot_init_percpu_data(i, rsp);
}
list_add(&rsp->flavors, &rcu_struct_flavors);
}
/*
* Compute the rcu_node tree geometry from kernel parameters. This cannot
* replace the definitions in tree.h because those are needed to size
* the ->node array in the rcu_state structure.
*/
static void __init rcu_init_geometry(void)
{
ulong d;
int i;
int j;
int n = nr_cpu_ids;
int rcu_capacity[MAX_RCU_LVLS + 1];
/*
* Initialize any unspecified boot parameters.
* The default values of jiffies_till_first_fqs and
* jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
* value, which is a function of HZ, then adding one for each
* RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
*/
d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
if (jiffies_till_first_fqs == ULONG_MAX)
jiffies_till_first_fqs = d;
if (jiffies_till_next_fqs == ULONG_MAX)
jiffies_till_next_fqs = d;
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
rcu_fanout_leaf, nr_cpu_ids);
/*
* Compute number of nodes that can be handled an rcu_node tree
* with the given number of levels. Setting rcu_capacity[0] makes
* some of the arithmetic easier.
*/
rcu_capacity[0] = 1;
rcu_capacity[1] = rcu_fanout_leaf;
for (i = 2; i <= MAX_RCU_LVLS; i++)
rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
* The boot-time rcu_fanout_leaf parameter is only permitted
* to increase the leaf-level fanout, not decrease it. Of course,
* the leaf-level fanout cannot exceed the number of bits in
* the rcu_node masks. Finally, the tree must be able to accommodate
* the configured number of CPUs. Complain and fall back to the
* compile-time values if these limits are exceeded.
*/
if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
n > rcu_capacity[MAX_RCU_LVLS]) {
WARN_ON(1);
return;
}
/* Calculate the number of rcu_nodes at each level of the tree. */
for (i = 1; i <= MAX_RCU_LVLS; i++)
if (n <= rcu_capacity[i]) {
for (j = 0; j <= i; j++)
num_rcu_lvl[j] =
DIV_ROUND_UP(n, rcu_capacity[i - j]);
rcu_num_lvls = i;
for (j = i + 1; j <= MAX_RCU_LVLS; j++)
num_rcu_lvl[j] = 0;
break;
}
/* Calculate the total number of rcu_node structures. */
rcu_num_nodes = 0;
for (i = 0; i <= MAX_RCU_LVLS; i++)
rcu_num_nodes += num_rcu_lvl[i];
rcu_num_nodes -= n;
}
/*
* Dump out the structure of the rcu_node combining tree associated
* with the rcu_state structure referenced by rsp.
*/
static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
{
int level = 0;
struct rcu_node *rnp;
pr_info("rcu_node tree layout dump\n");
pr_info(" ");
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp->level != level) {
pr_cont("\n");
pr_info(" ");
level = rnp->level;
}
pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum);
}
pr_cont("\n");
}
void __init rcu_init(void)
{
int cpu;
rcu_early_boot_tests();
rcu_bootup_announce();
rcu_init_geometry();
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
rcu_init_one(&rcu_sched_state, &rcu_sched_data);
if (dump_tree)
rcu_dump_rcu_node_tree(&rcu_sched_state);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
/*
* We don't need protection against CPU-hotplug here because
* this is called early in boot, before either interrupts
* or the scheduler are operational.
*/
cpu_notifier(rcu_cpu_notify, 0);
pm_notifier(rcu_pm_notify, 0);
for_each_online_cpu(cpu)
rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
}
#include "tree_plugin.h"
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/rcu/tree.h
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions.
*
* 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: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
/*
* Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
* CONFIG_RCU_FANOUT_LEAF.
* In theory, it should be possible to add more levels straightforwardly.
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
#ifdef CONFIG_RCU_FANOUT
#define RCU_FANOUT CONFIG_RCU_FANOUT
#else /* #ifdef CONFIG_RCU_FANOUT */
# ifdef CONFIG_64BIT
# define RCU_FANOUT 64
# else
# define RCU_FANOUT 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
#ifdef CONFIG_RCU_FANOUT_LEAF
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
# ifdef CONFIG_64BIT
# define RCU_FANOUT_LEAF 64
# else
# define RCU_FANOUT_LEAF 32
# endif
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT_1
# define RCU_NUM_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_2
# define RCU_NUM_LVLS 2
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_3
# define RCU_NUM_LVLS 3
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_3 (NR_CPUS)
# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_4
# define RCU_NUM_LVLS 4
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_4 (NR_CPUS)
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
extern int rcu_num_lvls;
extern int rcu_num_nodes;
/*
* Dynticks per-CPU state.
*/
struct rcu_dynticks {
long long dynticks_nesting; /* Track irq/process nesting level. */
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
long long dynticks_idle_nesting;
/* irq/process nesting level from idle. */
atomic_t dynticks_idle; /* Even value for idle, else odd. */
/* "Idle" excludes userspace execution. */
unsigned long dynticks_idle_jiffies;
/* End of last non-NMI non-idle period. */
#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
#ifdef CONFIG_RCU_FAST_NO_HZ
bool all_lazy; /* Are all CPU's CBs lazy? */
unsigned long nonlazy_posted;
/* # times non-lazy CBs posted to CPU. */
unsigned long nonlazy_posted_snap;
/* idle-period nonlazy_posted snapshot. */
unsigned long last_accelerate;
/* Last jiffy CBs were accelerated. */
unsigned long last_advance_all;
/* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED 0
#define RCU_KTHREAD_RUNNING 1
#define RCU_KTHREAD_WAITING 2
#define RCU_KTHREAD_OFFCPU 3
#define RCU_KTHREAD_YIELDING 4
#define RCU_KTHREAD_MAX 4
/*
* Definition for node within the RCU grace-period-detection hierarchy.
*/
struct rcu_node {
raw_spinlock_t lock; /* Root rcu_node's lock protects some */
/* rcu_state fields as well as following. */
unsigned long gpnum; /* Current grace period for this node. */
/* This will either be equal to or one */
/* behind the root rcu_node's gpnum. */
unsigned long completed; /* Last GP completed for this node. */
/* This will either be equal to or one */
/* behind the root rcu_node's gpnum. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
/* In leaf rcu_node, each bit corresponds to */
/* an rcu_data structure, otherwise, each */
/* bit corresponds to a child rcu_node */
/* structure. */
unsigned long expmask; /* Groups that have ->blkd_tasks */
/* elements that need to drain to allow the */
/* current expedited grace period to */
/* complete (only for PREEMPT_RCU). */
unsigned long qsmaskinit;
/* Per-GP initial value for qsmask & expmask. */
/* Initialized from ->qsmaskinitnext at the */
/* beginning of each grace period. */
unsigned long qsmaskinitnext;
/* Online CPUs for next grace period. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
/* Only one bit will be set in this mask. */
int grplo; /* lowest-numbered CPU or group here. */
int grphi; /* highest-numbered CPU or group here. */
u8 grpnum; /* CPU/group number for next level up. */
u8 level; /* root is at level 0. */
bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
/* exit RCU read-side critical sections */
/* before propagating offline up the */
/* rcu_node tree? */
struct rcu_node *parent;
struct list_head blkd_tasks;
/* Tasks blocked in RCU read-side critical */
/* section. Tasks are placed at the head */
/* of this list and age towards the tail. */
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
/* is no such task. */
struct list_head *exp_tasks;
/* Pointer to the first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there can cannot be any such task. */
struct list_head *boost_tasks;
/* Pointer to first task that needs to be */
/* priority boosted, or NULL if no priority */
/* boosting is needed for this rcu_node */
/* structure. If there are no tasks */
/* queued on this rcu_node structure that */
/* are blocking the current grace period, */
/* there can be no such task. */
struct rt_mutex boost_mtx;
/* Used only for the priority-boosting */
/* side effect, not as a lock. */
unsigned long boost_time;
/* When to start boosting (jiffies). */
struct task_struct *boost_kthread_task;
/* kthread that takes care of priority */
/* boosting for this rcu_node structure. */
unsigned int boost_kthread_status;
/* State of boost_kthread_task for tracing. */
unsigned long n_tasks_boosted;
/* Total number of tasks boosted. */
unsigned long n_exp_boosts;
/* Number of tasks boosted for expedited GP. */
unsigned long n_normal_boosts;
/* Number of tasks boosted for normal GP. */
unsigned long n_balk_blkd_tasks;
/* Refused to boost: no blocked tasks. */
unsigned long n_balk_exp_gp_tasks;
/* Refused to boost: nothing blocking GP. */
unsigned long n_balk_boost_tasks;
/* Refused to boost: already boosting. */
unsigned long n_balk_notblocked;
/* Refused to boost: RCU RS CS still running. */
unsigned long n_balk_notyet;
/* Refused to boost: not yet time. */
unsigned long n_balk_nos;
/* Refused to boost: not sure why, though. */
/* This can happen due to race conditions. */
#ifdef CONFIG_RCU_NOCB_CPU
wait_queue_head_t nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
int need_future_gp[2];
/* Counts of upcoming no-CB GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
} ____cacheline_internodealigned_in_smp;
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
*/
#define rcu_for_each_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
* Do a breadth-first scan of the non-leaf rcu_node structures for the
* specified rcu_state structure. Note that if there is a singleton
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
for ((rnp) = &(rsp)->node[0]; \
(rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
* structure. Note that if there is a singleton rcu_node tree with but
* one rcu_node structure, this loop -will- visit the rcu_node structure.
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/* Index values for nxttail array in struct rcu_data. */
#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
#define RCU_NEXT_TAIL 3
#define RCU_NEXT_SIZE 4
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
unsigned long completed; /* Track rsp->completed gp number */
/* in order to detect GP end. */
unsigned long gpnum; /* Highest gp number that this CPU */
/* is aware of having started. */
unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
/* for rcu_all_qs() invocations. */
bool passed_quiesce; /* User-mode/idle loop etc. */
bool qs_pending; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
bool gpwrap; /* Possible gpnum/completed wrap. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
#ifdef CONFIG_RCU_CPU_STALL_INFO
unsigned long ticks_this_gp; /* The number of scheduling-clock */
/* ticks this CPU has handled */
/* during and after the last grace */
/* period it is aware of. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
/* 2) batch handling */
/*
* If nxtlist is not NULL, it is partitioned as follows.
* Any of the partitions might be empty, in which case the
* pointer to that partition will be equal to the pointer for
* the following partition. When the list is empty, all of
* the nxttail elements point to the ->nxtlist pointer itself,
* which in that case is NULL.
*
* [nxtlist, *nxttail[RCU_DONE_TAIL]):
* Entries that batch # <= ->completed
* The grace period for these entries has completed, and
* the other grace-period-completed entries may be moved
* here temporarily in rcu_process_callbacks().
* [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
* Entries that batch # <= ->completed - 1: waiting for current GP
* [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
* Entries known to have arrived before current GP ended
* [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
* Entries that might have arrived after current GP ended
* Note that the value of *nxttail[RCU_NEXT_TAIL] will
* always be NULL, as this is the end of the list.
*/
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
unsigned long nxtcompleted[RCU_NEXT_SIZE];
/* grace periods for sublists. */
long qlen_lazy; /* # of lazy queued callbacks */
long qlen; /* # of queued callbacks, incl lazy */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
unsigned long n_nocbs_invoked; /* count of no-CBs RCU cbs invoked. */
unsigned long n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
unsigned long n_cbs_adopted; /* RCU cbs adopted from dying CPU */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
/* 3) dynticks interface. */
struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long cond_resched_completed;
/* Grace period that needs help */
/* from cond_resched(). */
/* 5) __rcu_pending() statistics. */
unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */
unsigned long n_rp_qs_pending;
unsigned long n_rp_report_qs;
unsigned long n_rp_cb_ready;
unsigned long n_rp_cpu_needs_gp;
unsigned long n_rp_gp_completed;
unsigned long n_rp_gp_started;
unsigned long n_rp_nocb_defer_wakeup;
unsigned long n_rp_need_nothing;
/* 6) _rcu_barrier() and OOM callbacks. */
struct rcu_head barrier_head;
#ifdef CONFIG_RCU_FAST_NO_HZ
struct rcu_head oom_head;
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
/* 7) Callback offloading. */
#ifdef CONFIG_RCU_NOCB_CPU
struct rcu_head *nocb_head; /* CBs waiting for kthread. */
struct rcu_head **nocb_tail;
atomic_long_t nocb_q_count; /* # CBs waiting for nocb */
atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */
struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
struct rcu_head **nocb_follower_tail;
wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
/* The following fields are used by the leader, hence own cacheline. */
struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
/* CBs waiting for GP. */
struct rcu_head **nocb_gp_tail;
bool nocb_leader_sleep; /* Is the nocb leader thread asleep? */
struct rcu_data *nocb_next_follower;
/* Next follower in wakeup chain. */
/* The following fields are used by the follower, hence new cachline. */
struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp;
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 8) RCU CPU stall data. */
#ifdef CONFIG_RCU_CPU_STALL_INFO
unsigned int softirq_snap; /* Snapshot of softirq activity. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
int cpu;
struct rcu_state *rsp;
};
/* Values for fqs_state field in struct rcu_state. */
#define RCU_GP_IDLE 0 /* No grace period in progress. */
#define RCU_GP_INIT 1 /* Grace period being initialized. */
#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
/* Values for nocb_defer_wakeup field in struct rcu_data. */
#define RCU_NOGP_WAKE_NOT 0
#define RCU_NOGP_WAKE 1
#define RCU_NOGP_WAKE_FORCE 2
#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
/* For jiffies_till_first_fqs and */
/* and jiffies_till_next_fqs. */
#define RCU_JIFFIES_FQS_DIV 256 /* Very large systems need more */
/* delay between bouts of */
/* quiescent-state forcing. */
#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time to take */
/* at least one scheduling clock */
/* irq before ratting on them. */
#define rcu_wait(cond) \
do { \
for (;;) { \
set_current_state(TASK_INTERRUPTIBLE); \
if (cond) \
break; \
schedule(); \
} \
__set_current_state(TASK_RUNNING); \
} while (0)
/*
* RCU global state, including node hierarchy. This hierarchy is
* represented in "heap" form in a dense array. The root (first level)
* of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
* level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
* and the third level in ->node[m+1] and following (->node[m+1] referenced
* by ->level[2]). The number of levels is determined by the number of
* CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
* consisting of a single rcu_node.
*/
struct rcu_state {
struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */
u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */
u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
u8 flavor_mask; /* bit in flavor mask. */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
void (*call)(struct rcu_head *head, /* call_rcu() flavor. */
void (*func)(struct rcu_head *head));
/* The following fields are guarded by the root rcu_node's lock. */
u8 fqs_state ____cacheline_internodealigned_in_smp;
/* Force QS state. */
u8 boost; /* Subject to priority boost. */
unsigned long gpnum; /* Current gp number. */
unsigned long completed; /* # of last completed gp. */
struct task_struct *gp_kthread; /* Task for grace periods. */
wait_queue_head_t gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
short gp_state; /* GP kthread sleep state. */
/* End of fields guarded by root rcu_node's lock. */
raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
/* Protect following fields. */
struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */
/* need a grace period. */
struct rcu_head **orphan_nxttail; /* Tail of above. */
struct rcu_head *orphan_donelist; /* Orphaned callbacks that */
/* are ready to invoke. */
struct rcu_head **orphan_donetail; /* Tail of above. */
long qlen_lazy; /* Number of lazy callbacks. */
long qlen; /* Total number of callbacks. */
/* End of fields guarded by orphan_lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
atomic_t barrier_cpu_count; /* # CPUs waiting on. */
struct completion barrier_completion; /* Wake at barrier end. */
unsigned long n_barrier_done; /* ++ at start and end of */
/* _rcu_barrier(). */
/* End of fields guarded by barrier_mutex. */
atomic_long_t expedited_start; /* Starting ticket. */
atomic_long_t expedited_done; /* Done ticket. */
atomic_long_t expedited_wrap; /* # near-wrap incidents. */
atomic_long_t expedited_tryfail; /* # acquisition failures. */
atomic_long_t expedited_workdone1; /* # done by others #1. */
atomic_long_t expedited_workdone2; /* # done by others #2. */
atomic_long_t expedited_normal; /* # fallbacks to normal. */
atomic_long_t expedited_stoppedcpus; /* # successful stop_cpus. */
atomic_long_t expedited_done_tries; /* # tries to update _done. */
atomic_long_t expedited_done_lost; /* # times beaten to _done. */
atomic_long_t expedited_done_exit; /* # times exited _done loop. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long n_force_qs; /* Number of calls to */
/* force_quiescent_state(). */
unsigned long n_force_qs_lh; /* ~Number of calls leaving */
/* due to lock unavailable. */
unsigned long n_force_qs_ngp; /* Number of calls leaving */
/* due to no GP active. */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
/* GP start. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
struct list_head flavors; /* List of RCU flavors. */
};
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */
#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_WAIT_INIT 0 /* Initial state. */
#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */
#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */
extern struct list_head rcu_struct_flavors;
/* Sequence through rcu_state structures for each RCU flavor. */
#define for_each_rcu_flavor(rsp) \
list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
/*
* RCU implementation internal declarations:
*/
extern struct rcu_state rcu_sched_state;
extern struct rcu_state rcu_bh_state;
#ifdef CONFIG_PREEMPT_RCU
extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DECLARE_PER_CPU(char, rcu_cpu_has_work);
#endif /* #ifdef CONFIG_RCU_BOOST */
#ifndef RCU_TREE_NONCORE
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_preempt_note_context_switch(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
static void __init __rcu_init_preempt(void);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
static bool rcu_is_callbacks_kthread(void);
#ifdef CONFIG_RCU_BOOST
static void rcu_preempt_do_callbacks(void);
static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
static void __init rcu_spawn_boost_kthreads(void);
static void rcu_prepare_kthreads(int cpu);
static void rcu_cleanup_after_idle(void);
static void rcu_prepare_for_idle(void);
static void rcu_idle_count_callbacks_posted(void);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static void print_cpu_stall_info_begin(void);
static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void);
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
bool lazy, unsigned long flags);
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
struct rcu_data *rdp,
unsigned long flags);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_all_nocb_kthreads(int cpu);
static void __init rcu_spawn_nocb_kthreads(void);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_sysidle_enter(int irq);
static void rcu_sysidle_exit(int irq);
static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
unsigned long *maxj);
static bool is_sysidle_rcu_state(struct rcu_state *rsp);
static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj);
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
#endif /* #ifndef RCU_TREE_NONCORE */
#ifdef CONFIG_RCU_TRACE
/* Read out queue lengths for tracing. */
static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
{
#ifdef CONFIG_RCU_NOCB_CPU
*ql = atomic_long_read(&rdp->nocb_q_count);
*qll = atomic_long_read(&rdp->nocb_q_count_lazy);
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
*ql = 0;
*qll = 0;
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
}
#endif /* #ifdef CONFIG_RCU_TRACE */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/rcu/tree_plugin.h
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
* Internal non-public definitions that provide either classic
* or preemptible semantics.
*
* 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 Red Hat, 2009
* Copyright IBM Corporation, 2009
*
* Author: Ingo Molnar <mingo@elte.hu>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
#include <linux/delay.h>
#include <linux/gfp.h>
#include <linux/oom.h>
#include <linux/smpboot.h>
#include "../time/tick-internal.h"
#ifdef CONFIG_RCU_BOOST
#include "../locking/rtmutex_common.h"
/*
* Control variables for per-CPU and per-rcu_node kthreads. These
* handle all flavors of RCU.
*/
static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
#else /* #ifdef CONFIG_RCU_BOOST */
/*
* Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
* all uses are in dead code. Provide a definition to keep the compiler
* happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
* This probably needs to be excluded from -rt builds.
*/
#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
#endif /* #else #ifdef CONFIG_RCU_BOOST */
#ifdef CONFIG_RCU_NOCB_CPU
static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */
static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/*
* Check the RCU kernel configuration parameters and print informative
* messages about anything out of the ordinary. If you like #ifdef, you
* will love this function.
*/
static void __init rcu_bootup_announce_oddness(void)
{
if (IS_ENABLED(CONFIG_RCU_TRACE))
pr_info("\tRCU debugfs-based tracing is enabled.\n");
if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
(!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
RCU_FANOUT);
if (rcu_fanout_exact)
pr_info("\tHierarchical RCU autobalancing is disabled.\n");
if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
if (IS_ENABLED(CONFIG_PROVE_RCU))
pr_info("\tRCU lockdep checking is enabled.\n");
if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE))
pr_info("\tRCU torture testing starts during boot.\n");
if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO))
pr_info("\tAdditional per-CPU info printed with stalls.\n");
if (NUM_RCU_LVL_4 != 0)
pr_info("\tFour-level hierarchy is enabled.\n");
if (RCU_FANOUT_LEAF != 16)
pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
RCU_FANOUT_LEAF);
if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
if (IS_ENABLED(CONFIG_RCU_BOOST))
pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
}
#ifdef CONFIG_PREEMPT_RCU
RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
static int rcu_preempted_readers_exp(struct rcu_node *rnp);
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake);
/*
* Tell them what RCU they are running.
*/
static void __init rcu_bootup_announce(void)
{
pr_info("Preemptible hierarchical RCU implementation.\n");
rcu_bootup_announce_oddness();
}
/*
* Record a preemptible-RCU quiescent state for the specified CPU. Note
* that this just means that the task currently running on the CPU is
* not in a quiescent state. There might be any number of tasks blocked
* while in an RCU read-side critical section.
*
* As with the other rcu_*_qs() functions, callers to this function
* must disable preemption.
*/
static void rcu_preempt_qs(void)
{
if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
trace_rcu_grace_period(TPS("rcu_preempt"),
__this_cpu_read(rcu_data_p->gpnum),
TPS("cpuqs"));
__this_cpu_write(rcu_data_p->passed_quiesce, 1);
barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
current->rcu_read_unlock_special.b.need_qs = false;
}
}
/*
* We have entered the scheduler, and the current task might soon be
* context-switched away from. If this task is in an RCU read-side
* critical section, we will no longer be able to rely on the CPU to
* record that fact, so we enqueue the task on the blkd_tasks list.
* The task will dequeue itself when it exits the outermost enclosing
* RCU read-side critical section. Therefore, the current grace period
* cannot be permitted to complete until the blkd_tasks list entries
* predating the current grace period drain, in other words, until
* rnp->gp_tasks becomes NULL.
*
* Caller must disable preemption.
*/
static void rcu_preempt_note_context_switch(void)
{
struct task_struct *t = current;
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
if (t->rcu_read_lock_nesting > 0 &&
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
rdp = this_cpu_ptr(rcu_state_p->rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
t->rcu_read_unlock_special.b.blocked = true;
t->rcu_blocked_node = rnp;
/*
* If this CPU has already checked in, then this task
* will hold up the next grace period rather than the
* current grace period. Queue the task accordingly.
* If the task is queued for the current grace period
* (i.e., this CPU has not yet passed through a quiescent
* state for the current grace period), then as long
* as that task remains queued, the current grace period
* cannot end. Note that there is some uncertainty as
* to exactly when the current grace period started.
* We take a conservative approach, which can result
* in unnecessarily waiting on tasks that started very
* slightly after the current grace period began. C'est
* la vie!!!
*
* But first, note that the current CPU must still be
* on line!
*/
WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0);
WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
rnp->gp_tasks = &t->rcu_node_entry;
if (IS_ENABLED(CONFIG_RCU_BOOST) &&
rnp->boost_tasks != NULL)
rnp->boost_tasks = rnp->gp_tasks;
} else {
list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
if (rnp->qsmask & rdp->grpmask)
rnp->gp_tasks = &t->rcu_node_entry;
}
trace_rcu_preempt_task(rdp->rsp->name,
t->pid,
(rnp->qsmask & rdp->grpmask)
? rnp->gpnum
: rnp->gpnum + 1);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else if (t->rcu_read_lock_nesting < 0 &&
t->rcu_read_unlock_special.s) {
/*
* Complete exit from RCU read-side critical section on
* behalf of preempted instance of __rcu_read_unlock().
*/
rcu_read_unlock_special(t);
}
/*
* Either we were not in an RCU read-side critical section to
* begin with, or we have now recorded that critical section
* globally. Either way, we can now note a quiescent state
* for this CPU. Again, if we were in an RCU read-side critical
* section, and if that critical section was blocking the current
* grace period, then the fact that the task has been enqueued
* means that we continue to block the current grace period.
*/
rcu_preempt_qs();
}
/*
* Check for preempted RCU readers blocking the current grace period
* for the specified rcu_node structure. If the caller needs a reliable
* answer, it must hold the rcu_node's ->lock.
*/
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
{
return rnp->gp_tasks != NULL;
}
/*
* Advance a ->blkd_tasks-list pointer to the next entry, instead
* returning NULL if at the end of the list.
*/
static struct list_head *rcu_next_node_entry(struct task_struct *t,
struct rcu_node *rnp)
{
struct list_head *np;
np = t->rcu_node_entry.next;
if (np == &rnp->blkd_tasks)
np = NULL;
return np;
}
/*
* Return true if the specified rcu_node structure has tasks that were
* preempted within an RCU read-side critical section.
*/
static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
{
return !list_empty(&rnp->blkd_tasks);
}
/*
* Handle special cases during rcu_read_unlock(), such as needing to
* notify RCU core processing or task having blocked during the RCU
* read-side critical section.
*/
void rcu_read_unlock_special(struct task_struct *t)
{
bool empty_exp;
bool empty_norm;
bool empty_exp_now;
unsigned long flags;
struct list_head *np;
bool drop_boost_mutex = false;
struct rcu_node *rnp;
union rcu_special special;
/* NMI handlers cannot block and cannot safely manipulate state. */
if (in_nmi())
return;
local_irq_save(flags);
/*
* If RCU core is waiting for this CPU to exit critical section,
* let it know that we have done so. Because irqs are disabled,
* t->rcu_read_unlock_special cannot change.
*/
special = t->rcu_read_unlock_special;
if (special.b.need_qs) {
rcu_preempt_qs();
t->rcu_read_unlock_special.b.need_qs = false;
if (!t->rcu_read_unlock_special.s) {
local_irq_restore(flags);
return;
}
}
/* Hardware IRQ handlers cannot block, complain if they get here. */
if (in_irq() || in_serving_softirq()) {
lockdep_rcu_suspicious(__FILE__, __LINE__,
"rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n",
t->rcu_read_unlock_special.s,
t->rcu_read_unlock_special.b.blocked,
t->rcu_read_unlock_special.b.need_qs);
local_irq_restore(flags);
return;
}
/* Clean up if blocked during RCU read-side critical section. */
if (special.b.blocked) {
t->rcu_read_unlock_special.b.blocked = false;
/*
* Remove this task from the list it blocked on. The task
* now remains queued on the rcu_node corresponding to
* the CPU it first blocked on, so the first attempt to
* acquire the task's rcu_node's ->lock will succeed.
* Keep the loop and add a WARN_ON() out of sheer paranoia.
*/
for (;;) {
rnp = t->rcu_blocked_node;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
WARN_ON_ONCE(1);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
empty_exp = !rcu_preempted_readers_exp(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
np = rcu_next_node_entry(t, rnp);
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
rnp->gpnum, t->pid);
if (&t->rcu_node_entry == rnp->gp_tasks)
rnp->gp_tasks = np;
if (&t->rcu_node_entry == rnp->exp_tasks)
rnp->exp_tasks = np;
if (IS_ENABLED(CONFIG_RCU_BOOST)) {
if (&t->rcu_node_entry == rnp->boost_tasks)
rnp->boost_tasks = np;
/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
}
/*
* If this was the last task on the current list, and if
* we aren't waiting on any CPUs, report the quiescent state.
* Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
* so we must take a snapshot of the expedited state.
*/
empty_exp_now = !rcu_preempted_readers_exp(rnp);
if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
rnp->gpnum,
0, rnp->qsmask,
rnp->level,
rnp->grplo,
rnp->grphi,
!!rnp->gp_tasks);
rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
} else {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/* Unboost if we were boosted. */
if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
rt_mutex_unlock(&rnp->boost_mtx);
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
if (!empty_exp && empty_exp_now)
rcu_report_exp_rnp(rcu_state_p, rnp, true);
} else {
local_irq_restore(flags);
}
}
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period on the specified rcu_node structure.
*/
static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
{
unsigned long flags;
struct task_struct *t;
raw_spin_lock_irqsave(&rnp->lock, flags);
if (!rcu_preempt_blocked_readers_cgp(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
sched_show_task(t);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* Dump detailed information for all tasks blocking the current RCU
* grace period.
*/
static void rcu_print_detail_task_stall(struct rcu_state *rsp)
{
struct rcu_node *rnp = rcu_get_root(rsp);
rcu_print_detail_task_stall_rnp(rnp);
rcu_for_each_leaf_node(rsp, rnp)
rcu_print_detail_task_stall_rnp(rnp);
}
#ifdef CONFIG_RCU_CPU_STALL_INFO
static void rcu_print_task_stall_begin(struct rcu_node *rnp)
{
pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
rnp->level, rnp->grplo, rnp->grphi);
}
static void rcu_print_task_stall_end(void)
{
pr_cont("\n");
}
#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
static void rcu_print_task_stall_begin(struct rcu_node *rnp)
{
}
static void rcu_print_task_stall_end(void)
{
}
#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
struct task_struct *t;
int ndetected = 0;
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
rcu_print_task_stall_begin(rnp);
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
rcu_print_task_stall_end();
return ndetected;
}
/*
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
* period that still has RCU readers blocked! This function must be
* invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
* must be held by the caller.
*
* Also, if there are blocked tasks on the list, they automatically
* block the newly created grace period, so set up ->gp_tasks accordingly.
*/
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
if (rcu_preempt_has_tasks(rnp))
rnp->gp_tasks = rnp->blkd_tasks.next;
WARN_ON_ONCE(rnp->qsmask);
}
/*
* Check for a quiescent state from the current CPU. When a task blocks,
* the task is recorded in the corresponding CPU's rcu_node structure,
* which is checked elsewhere.
*
* Caller must disable hard irqs.
*/
static void rcu_preempt_check_callbacks(void)
{
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
rcu_preempt_qs();
return;
}
if (t->rcu_read_lock_nesting > 0 &&
__this_cpu_read(rcu_data_p->qs_pending) &&
!__this_cpu_read(rcu_data_p->passed_quiesce))
t->rcu_read_unlock_special.b.need_qs = true;
}
#ifdef CONFIG_RCU_BOOST
static void rcu_preempt_do_callbacks(void)
{
rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
}
#endif /* #ifdef CONFIG_RCU_BOOST */
/*
* Queue a preemptible-RCU callback for invocation after a grace period.
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
__call_rcu(head, func, rcu_state_p, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu);
/**
* 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. Note, however, that
* upon return from synchronize_rcu(), the caller might well be executing
* concurrently with new RCU read-side critical sections that began while
* synchronize_rcu() was waiting. RCU read-side critical sections are
* delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
*
* See the description of synchronize_sched() for more detailed information
* on memory ordering guarantees.
*/
void synchronize_rcu(void)
{
rcu_lockdep_assert(!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");
if (!rcu_scheduler_active)
return;
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
static unsigned long sync_rcu_preempt_exp_count;
static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
/*
* Return non-zero if there are any tasks in RCU read-side critical
* sections blocking the current preemptible-RCU expedited grace period.
* If there is no preemptible-RCU expedited grace period currently in
* progress, returns zero unconditionally.
*/
static int rcu_preempted_readers_exp(struct rcu_node *rnp)
{
return rnp->exp_tasks != NULL;
}
/*
* return non-zero if there is no RCU expedited grace period in progress
* for the specified rcu_node structure, in other words, if all CPUs and
* tasks covered by the specified rcu_node structure have done their bit
* for the current expedited grace period. Works only for preemptible
* RCU -- other RCU implementation use other means.
*
* Caller must hold sync_rcu_preempt_exp_mutex.
*/
static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
return !rcu_preempted_readers_exp(rnp) &&
READ_ONCE(rnp->expmask) == 0;
}
/*
* Report the exit from RCU read-side critical section for the last task
* that queued itself during or before the current expedited preemptible-RCU
* grace period. This event is reported either to the rcu_node structure on
* which the task was queued or to one of that rcu_node structure's ancestors,
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
* Caller must hold sync_rcu_preempt_exp_mutex.
*/
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake)
{
unsigned long flags;
unsigned long mask;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
break;
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (wake) {
smp_mb(); /* EGP done before wake_up(). */
wake_up(&sync_rcu_preempt_exp_wq);
}
break;
}
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock(&rnp->lock); /* irqs already disabled */
smp_mb__after_unlock_lock();
rnp->expmask &= ~mask;
}
}
/*
* Snapshot the tasks blocking the newly started preemptible-RCU expedited
* grace period for the specified rcu_node structure, phase 1. If there
* are such tasks, set the ->expmask bits up the rcu_node tree and also
* set the ->expmask bits on the leaf rcu_node structures to tell phase 2
* that work is needed here.
*
* Caller must hold sync_rcu_preempt_exp_mutex.
*/
static void
sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
{
unsigned long flags;
unsigned long mask;
struct rcu_node *rnp_up;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
WARN_ON_ONCE(rnp->expmask);
WARN_ON_ONCE(rnp->exp_tasks);
if (!rcu_preempt_has_tasks(rnp)) {
/* No blocked tasks, nothing to do. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
/* Call for Phase 2 and propagate ->expmask bits up the tree. */
rnp->expmask = 1;
rnp_up = rnp;
while (rnp_up->parent) {
mask = rnp_up->grpmask;
rnp_up = rnp_up->parent;
if (rnp_up->expmask & mask)
break;
raw_spin_lock(&rnp_up->lock); /* irqs already off */
smp_mb__after_unlock_lock();
rnp_up->expmask |= mask;
raw_spin_unlock(&rnp_up->lock); /* irqs still off */
}
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
* Snapshot the tasks blocking the newly started preemptible-RCU expedited
* grace period for the specified rcu_node structure, phase 2. If the
* leaf rcu_node structure has its ->expmask field set, check for tasks.
* If there are some, clear ->expmask and set ->exp_tasks accordingly,
* then initiate RCU priority boosting. Otherwise, clear ->expmask and
* invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits,
* enabling rcu_read_unlock_special() to do the bit-clearing.
*
* Caller must hold sync_rcu_preempt_exp_mutex.
*/
static void
sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
{
unsigned long flags;
raw_spin_lock_irqsave(&rnp->lock, flags);
smp_mb__after_unlock_lock();
if (!rnp->expmask) {
/* Phase 1 didn't do anything, so Phase 2 doesn't either. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
/* Phase 1 is over. */
rnp->expmask = 0;
/*
* If there are still blocked tasks, set up ->exp_tasks so that
* rcu_read_unlock_special() will wake us and then boost them.
*/
if (rcu_preempt_has_tasks(rnp)) {
rnp->exp_tasks = rnp->blkd_tasks.next;
rcu_initiate_boost(rnp, flags); /* releases rnp->lock */
return;
}
/* No longer any blocked tasks, so undo bit setting. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
rcu_report_exp_rnp(rsp, rnp, false);
}
/**
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU-preempt grace period, but expedite it. The basic
* idea is to invoke synchronize_sched_expedited() to push all the tasks to
* the ->blkd_tasks lists and wait for this list to drain. This consumes
* significant time on all CPUs and is unfriendly to real-time workloads,
* so is thus not recommended for any sort of common-case code.
* In fact, if you are using synchronize_rcu_expedited() in a loop,
* please restructure your code to batch your updates, and then Use a
* single synchronize_rcu() instead.
*/
void synchronize_rcu_expedited(void)
{
struct rcu_node *rnp;
struct rcu_state *rsp = rcu_state_p;
unsigned long snap;
int trycount = 0;
smp_mb(); /* Caller's modifications seen first by other CPUs. */
snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
smp_mb(); /* Above access cannot bleed into critical section. */
/*
* Block CPU-hotplug operations. This means that any CPU-hotplug
* operation that finds an rcu_node structure with tasks in the
* process of being boosted will know that all tasks blocking
* this expedited grace period will already be in the process of
* being boosted. This simplifies the process of moving tasks
* from leaf to root rcu_node structures.
*/
if (!try_get_online_cpus()) {
/* CPU-hotplug operation in flight, fall back to normal GP. */
wait_rcu_gp(call_rcu);
return;
}
/*
* Acquire lock, falling back to synchronize_rcu() if too many
* lock-acquisition failures. Of course, if someone does the
* expedited grace period for us, just leave.
*/
while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
if (ULONG_CMP_LT(snap,
READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto mb_ret; /* Others did our work for us. */
}
if (trycount++ < 10) {
udelay(trycount * num_online_cpus());
} else {
put_online_cpus();
wait_rcu_gp(call_rcu);
return;
}
}
if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) {
put_online_cpus();
goto unlock_mb_ret; /* Others did our work for us. */
}
/* force all RCU readers onto ->blkd_tasks lists. */
synchronize_sched_expedited();
/*
* Snapshot current state of ->blkd_tasks lists into ->expmask.
* Phase 1 sets bits and phase 2 permits rcu_read_unlock_special()
* to start clearing them. Doing this in one phase leads to
* strange races between setting and clearing bits, so just say "no"!
*/
rcu_for_each_leaf_node(rsp, rnp)
sync_rcu_preempt_exp_init1(rsp, rnp);
rcu_for_each_leaf_node(rsp, rnp)
sync_rcu_preempt_exp_init2(rsp, rnp);
put_online_cpus();
/* Wait for snapshotted ->blkd_tasks lists to drain. */
rnp = rcu_get_root(rsp);
wait_event(sync_rcu_preempt_exp_wq,
sync_rcu_preempt_exp_done(rnp));
/* Clean up and exit. */
smp_mb(); /* ensure expedited GP seen before counter increment. */
WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1);
unlock_mb_ret:
mutex_unlock(&sync_rcu_preempt_exp_mutex);
mb_ret:
smp_mb(); /* ensure subsequent action seen after grace period. */
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
/**
* rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
*
* Note that this primitive does not necessarily wait for an RCU grace period
* to complete. For example, if there are no RCU callbacks queued anywhere
* in the system, then rcu_barrier() is within its rights to return
* immediately, without waiting for anything, much less an RCU grace period.
*/
void rcu_barrier(void)
{
_rcu_barrier(rcu_state_p);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
/*
* Initialize preemptible RCU's state structures.
*/
static void __init __rcu_init_preempt(void)
{
rcu_init_one(rcu_state_p, rcu_data_p);
}
/*
* Check for a task exiting while in a preemptible-RCU read-side
* critical section, clean up if so. No need to issue warnings,
* as debug_check_no_locks_held() already does this if lockdep
* is enabled.
*/
void exit_rcu(void)
{
struct task_struct *t = current;
if (likely(list_empty(¤t->rcu_node_entry)))
return;
t->rcu_read_lock_nesting = 1;
barrier();
t->rcu_read_unlock_special.b.blocked = true;
__rcu_read_unlock();
}
#else /* #ifdef CONFIG_PREEMPT_RCU */
static struct rcu_state *const rcu_state_p = &rcu_sched_state;
static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
/*
* Tell them what RCU they are running.
*/
static void __init rcu_bootup_announce(void)
{
pr_info("Hierarchical RCU implementation.\n");
rcu_bootup_announce_oddness();
}
/*
* Because preemptible RCU does not exist, we never have to check for
* CPUs being in quiescent states.
*/
static void rcu_preempt_note_context_switch(void)
{
}
/*
* Because preemptible RCU does not exist, there are never any preempted
* RCU readers.
*/
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
{
return 0;
}
/*
* Because there is no preemptible RCU, there can be no readers blocked.
*/
static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
{
return false;
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static void rcu_print_detail_task_stall(struct rcu_state *rsp)
{
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
static int rcu_print_task_stall(struct rcu_node *rnp)
{
return 0;
}
/*
* Because there is no preemptible RCU, there can be no readers blocked,
* so there is no need to check for blocked tasks. So check only for
* bogus qsmask values.
*/
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
WARN_ON_ONCE(rnp->qsmask);
}
/*
* Because preemptible RCU does not exist, it never has any callbacks
* to check.
*/
static void rcu_preempt_check_callbacks(void)
{
}
/*
* Wait for an rcu-preempt grace period, but make it happen quickly.
* But because preemptible RCU does not exist, map to rcu-sched.
*/
void synchronize_rcu_expedited(void)
{
synchronize_sched_expedited();
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
/*
* Because preemptible RCU does not exist, rcu_barrier() is just
* another name for rcu_barrier_sched().
*/
void rcu_barrier(void)
{
rcu_barrier_sched();
}
EXPORT_SYMBOL_GPL(rcu_barrier);
/*
* Because preemptible RCU does not exist, it need not be initialized.
*/
static void __init __rcu_init_preempt(void)
{
}
/*
* Because preemptible RCU does not exist, tasks cannot possibly exit
* while in preemptible RCU read-side critical sections.
*/
void exit_rcu(void)
{
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
#include "../locking/rtmutex_common.h"
#ifdef CONFIG_RCU_TRACE
static void rcu_initiate_boost_trace(struct rcu_node *rnp)
{
if (!rcu_preempt_has_tasks(rnp))
rnp->n_balk_blkd_tasks++;
else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL)
rnp->n_balk_exp_gp_tasks++;
else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL)
rnp->n_balk_boost_tasks++;
else if (rnp->gp_tasks != NULL && rnp->qsmask != 0)
rnp->n_balk_notblocked++;
else if (rnp->gp_tasks != NULL &&
ULONG_CMP_LT(jiffies, rnp->boost_time))
rnp->n_balk_notyet++;
else
rnp->n_balk_nos++;
}
#else /* #ifdef CONFIG_RCU_TRACE */
static void rcu_initiate_boost_trace(struct rcu_node *rnp)
{
}
#endif /* #else #ifdef CONFIG_RCU_TRACE */
static void rcu_wake_cond(struct task_struct *t, int status)
{
/*
* If the thread is yielding, only wake it when this
* is invoked from idle
*/
if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
wake_up_process(t);
}
11-12
906
906
10-09
07-23
1023
1023
07-23
1009
1009
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
