mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-27 04:20:51 +07:00
a682604838
This patch fixes a bug located by Vegard Nossum with the aid of kmemcheck, updated based on review comments from Nick Piggin, Ingo Molnar, and Andrew Morton. And cleans up the variable-name and function-name language. ;-) The boot CPU runs in the context of its idle thread during boot-up. During this time, idle_cpu(0) will always return nonzero, which will fool Classic and Hierarchical RCU into deciding that a large chunk of the boot-up sequence is a big long quiescent state. This in turn causes RCU to prematurely end grace periods during this time. This patch changes the rcutree.c and rcuclassic.c rcu_check_callbacks() function to ignore the idle task as a quiescent state until the system has started up the scheduler in rest_init(), introducing a new non-API function rcu_idle_now_means_idle() to inform RCU of this transition. RCU maintains an internal rcu_idle_cpu_truthful variable to track this state, which is then used by rcu_check_callback() to determine if it should believe idle_cpu(). Because this patch has the effect of disallowing RCU grace periods during long stretches of the boot-up sequence, this patch also introduces Josh Triplett's UP-only optimization that makes synchronize_rcu() be a no-op if num_online_cpus() returns 1. This allows boot-time code that calls synchronize_rcu() to proceed normally. Note, however, that RCU callbacks registered by call_rcu() will likely queue up until later in the boot sequence. Although rcuclassic and rcutree can also use this same optimization after boot completes, rcupreempt must restrict its use of this optimization to the portion of the boot sequence before the scheduler starts up, given that an rcupreempt RCU read-side critical section may be preeempted. In addition, this patch takes Nick Piggin's suggestion to make the system_state global variable be __read_mostly. Changes since v4: o Changes the name of the introduced function and variable to be less emotional. ;-) Changes since v3: o WARN_ON(nr_context_switches() > 0) to verify that RCU switches out of boot-time mode before the first context switch, as suggested by Nick Piggin. Changes since v2: o Created rcu_blocking_is_gp() internal-to-RCU API that determines whether a call to synchronize_rcu() is itself a grace period. o The definition of rcu_blocking_is_gp() for rcuclassic and rcutree checks to see if but a single CPU is online. o The definition of rcu_blocking_is_gp() for rcupreempt checks to see both if but a single CPU is online and if the system is still in early boot. This allows rcupreempt to again work correctly if running on a single CPU after booting is complete. o Added check to rcupreempt's synchronize_sched() for there being but one online CPU. Tested all three variants both SMP and !SMP, booted fine, passed a short rcutorture test on both x86 and Power. Located-by: Vegard Nossum <vegard.nossum@gmail.com> Tested-by: Vegard Nossum <vegard.nossum@gmail.com> Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
190 lines
5.2 KiB
C
190 lines
5.2 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
*
|
|
* Copyright IBM Corporation, 2001
|
|
*
|
|
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
|
|
* Manfred Spraul <manfred@colorfullife.com>
|
|
*
|
|
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
|
|
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
|
|
* Papers:
|
|
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
|
|
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
|
|
*
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
* http://lse.sourceforge.net/locking/rcupdate.html
|
|
*
|
|
*/
|
|
#include <linux/types.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/init.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/sched.h>
|
|
#include <asm/atomic.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/module.h>
|
|
#include <linux/kernel_stat.h>
|
|
|
|
enum rcu_barrier {
|
|
RCU_BARRIER_STD,
|
|
RCU_BARRIER_BH,
|
|
RCU_BARRIER_SCHED,
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
|
|
static atomic_t rcu_barrier_cpu_count;
|
|
static DEFINE_MUTEX(rcu_barrier_mutex);
|
|
static struct completion rcu_barrier_completion;
|
|
int rcu_scheduler_active __read_mostly;
|
|
|
|
/*
|
|
* Awaken the corresponding synchronize_rcu() instance now that a
|
|
* grace period has elapsed.
|
|
*/
|
|
void wakeme_after_rcu(struct rcu_head *head)
|
|
{
|
|
struct rcu_synchronize *rcu;
|
|
|
|
rcu = container_of(head, struct rcu_synchronize, head);
|
|
complete(&rcu->completion);
|
|
}
|
|
|
|
/**
|
|
* synchronize_rcu - wait until a grace period has elapsed.
|
|
*
|
|
* Control will return to the caller some time after a full grace
|
|
* period has elapsed, in other words after all currently executing RCU
|
|
* read-side critical sections have completed. RCU read-side critical
|
|
* sections are delimited by rcu_read_lock() and rcu_read_unlock(),
|
|
* and may be nested.
|
|
*/
|
|
void synchronize_rcu(void)
|
|
{
|
|
struct rcu_synchronize rcu;
|
|
|
|
if (rcu_blocking_is_gp())
|
|
return;
|
|
|
|
init_completion(&rcu.completion);
|
|
/* Will wake me after RCU finished. */
|
|
call_rcu(&rcu.head, wakeme_after_rcu);
|
|
/* Wait for it. */
|
|
wait_for_completion(&rcu.completion);
|
|
}
|
|
EXPORT_SYMBOL_GPL(synchronize_rcu);
|
|
|
|
static void rcu_barrier_callback(struct rcu_head *notused)
|
|
{
|
|
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
|
|
complete(&rcu_barrier_completion);
|
|
}
|
|
|
|
/*
|
|
* Called with preemption disabled, and from cross-cpu IRQ context.
|
|
*/
|
|
static void rcu_barrier_func(void *type)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
|
|
|
|
atomic_inc(&rcu_barrier_cpu_count);
|
|
switch ((enum rcu_barrier)type) {
|
|
case RCU_BARRIER_STD:
|
|
call_rcu(head, rcu_barrier_callback);
|
|
break;
|
|
case RCU_BARRIER_BH:
|
|
call_rcu_bh(head, rcu_barrier_callback);
|
|
break;
|
|
case RCU_BARRIER_SCHED:
|
|
call_rcu_sched(head, rcu_barrier_callback);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Orchestrate the specified type of RCU barrier, waiting for all
|
|
* RCU callbacks of the specified type to complete.
|
|
*/
|
|
static void _rcu_barrier(enum rcu_barrier type)
|
|
{
|
|
BUG_ON(in_interrupt());
|
|
/* Take cpucontrol mutex to protect against CPU hotplug */
|
|
mutex_lock(&rcu_barrier_mutex);
|
|
init_completion(&rcu_barrier_completion);
|
|
/*
|
|
* Initialize rcu_barrier_cpu_count to 1, then invoke
|
|
* rcu_barrier_func() on each CPU, so that each CPU also has
|
|
* incremented rcu_barrier_cpu_count. Only then is it safe to
|
|
* decrement rcu_barrier_cpu_count -- otherwise the first CPU
|
|
* might complete its grace period before all of the other CPUs
|
|
* did their increment, causing this function to return too
|
|
* early.
|
|
*/
|
|
atomic_set(&rcu_barrier_cpu_count, 1);
|
|
on_each_cpu(rcu_barrier_func, (void *)type, 1);
|
|
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
|
|
complete(&rcu_barrier_completion);
|
|
wait_for_completion(&rcu_barrier_completion);
|
|
mutex_unlock(&rcu_barrier_mutex);
|
|
}
|
|
|
|
/**
|
|
* rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
|
|
*/
|
|
void rcu_barrier(void)
|
|
{
|
|
_rcu_barrier(RCU_BARRIER_STD);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rcu_barrier);
|
|
|
|
/**
|
|
* rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
|
|
*/
|
|
void rcu_barrier_bh(void)
|
|
{
|
|
_rcu_barrier(RCU_BARRIER_BH);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rcu_barrier_bh);
|
|
|
|
/**
|
|
* rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
|
|
*/
|
|
void rcu_barrier_sched(void)
|
|
{
|
|
_rcu_barrier(RCU_BARRIER_SCHED);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
|
|
|
|
void __init rcu_init(void)
|
|
{
|
|
__rcu_init();
|
|
}
|
|
|
|
void rcu_scheduler_starting(void)
|
|
{
|
|
WARN_ON(num_online_cpus() != 1);
|
|
WARN_ON(nr_context_switches() > 0);
|
|
rcu_scheduler_active = 1;
|
|
}
|