![Paul E. McKenney](/assets/img/avatar_default.png)
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>
275 lines
9.9 KiB
C
275 lines
9.9 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
|
|
*
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.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
|
|
*
|
|
*/
|
|
|
|
#ifndef __LINUX_RCUPDATE_H
|
|
#define __LINUX_RCUPDATE_H
|
|
|
|
#include <linux/cache.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/seqlock.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/completion.h>
|
|
|
|
/**
|
|
* struct rcu_head - callback structure for use with RCU
|
|
* @next: next update requests in a list
|
|
* @func: actual update function to call after the grace period.
|
|
*/
|
|
struct rcu_head {
|
|
struct rcu_head *next;
|
|
void (*func)(struct rcu_head *head);
|
|
};
|
|
|
|
/* Internal to kernel, but needed by rcupreempt.h. */
|
|
extern int rcu_scheduler_active;
|
|
|
|
#if defined(CONFIG_CLASSIC_RCU)
|
|
#include <linux/rcuclassic.h>
|
|
#elif defined(CONFIG_TREE_RCU)
|
|
#include <linux/rcutree.h>
|
|
#elif defined(CONFIG_PREEMPT_RCU)
|
|
#include <linux/rcupreempt.h>
|
|
#else
|
|
#error "Unknown RCU implementation specified to kernel configuration"
|
|
#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */
|
|
|
|
#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
|
|
#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
|
|
#define INIT_RCU_HEAD(ptr) do { \
|
|
(ptr)->next = NULL; (ptr)->func = NULL; \
|
|
} while (0)
|
|
|
|
/**
|
|
* rcu_read_lock - mark the beginning of an RCU read-side critical section.
|
|
*
|
|
* When synchronize_rcu() is invoked on one CPU while other CPUs
|
|
* are within RCU read-side critical sections, then the
|
|
* synchronize_rcu() is guaranteed to block until after all the other
|
|
* CPUs exit their critical sections. Similarly, if call_rcu() is invoked
|
|
* on one CPU while other CPUs are within RCU read-side critical
|
|
* sections, invocation of the corresponding RCU callback is deferred
|
|
* until after the all the other CPUs exit their critical sections.
|
|
*
|
|
* Note, however, that RCU callbacks are permitted to run concurrently
|
|
* with RCU read-side critical sections. One way that this can happen
|
|
* is via the following sequence of events: (1) CPU 0 enters an RCU
|
|
* read-side critical section, (2) CPU 1 invokes call_rcu() to register
|
|
* an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
|
|
* (4) CPU 2 enters a RCU read-side critical section, (5) the RCU
|
|
* callback is invoked. This is legal, because the RCU read-side critical
|
|
* section that was running concurrently with the call_rcu() (and which
|
|
* therefore might be referencing something that the corresponding RCU
|
|
* callback would free up) has completed before the corresponding
|
|
* RCU callback is invoked.
|
|
*
|
|
* RCU read-side critical sections may be nested. Any deferred actions
|
|
* will be deferred until the outermost RCU read-side critical section
|
|
* completes.
|
|
*
|
|
* It is illegal to block while in an RCU read-side critical section.
|
|
*/
|
|
#define rcu_read_lock() __rcu_read_lock()
|
|
|
|
/**
|
|
* rcu_read_unlock - marks the end of an RCU read-side critical section.
|
|
*
|
|
* See rcu_read_lock() for more information.
|
|
*/
|
|
|
|
/*
|
|
* So where is rcu_write_lock()? It does not exist, as there is no
|
|
* way for writers to lock out RCU readers. This is a feature, not
|
|
* a bug -- this property is what provides RCU's performance benefits.
|
|
* Of course, writers must coordinate with each other. The normal
|
|
* spinlock primitives work well for this, but any other technique may be
|
|
* used as well. RCU does not care how the writers keep out of each
|
|
* others' way, as long as they do so.
|
|
*/
|
|
#define rcu_read_unlock() __rcu_read_unlock()
|
|
|
|
/**
|
|
* rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
|
|
*
|
|
* This is equivalent of rcu_read_lock(), but to be used when updates
|
|
* are being done using call_rcu_bh(). Since call_rcu_bh() callbacks
|
|
* consider completion of a softirq handler to be a quiescent state,
|
|
* a process in RCU read-side critical section must be protected by
|
|
* disabling softirqs. Read-side critical sections in interrupt context
|
|
* can use just rcu_read_lock().
|
|
*
|
|
*/
|
|
#define rcu_read_lock_bh() __rcu_read_lock_bh()
|
|
|
|
/*
|
|
* rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
|
|
*
|
|
* See rcu_read_lock_bh() for more information.
|
|
*/
|
|
#define rcu_read_unlock_bh() __rcu_read_unlock_bh()
|
|
|
|
/**
|
|
* rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
|
|
*
|
|
* Should be used with either
|
|
* - synchronize_sched()
|
|
* or
|
|
* - call_rcu_sched() and rcu_barrier_sched()
|
|
* on the write-side to insure proper synchronization.
|
|
*/
|
|
#define rcu_read_lock_sched() preempt_disable()
|
|
#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
|
|
|
|
/*
|
|
* rcu_read_unlock_sched - marks the end of a RCU-classic critical section
|
|
*
|
|
* See rcu_read_lock_sched for more information.
|
|
*/
|
|
#define rcu_read_unlock_sched() preempt_enable()
|
|
#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
|
|
|
|
|
|
|
|
/**
|
|
* rcu_dereference - fetch an RCU-protected pointer in an
|
|
* RCU read-side critical section. This pointer may later
|
|
* be safely dereferenced.
|
|
*
|
|
* Inserts memory barriers on architectures that require them
|
|
* (currently only the Alpha), and, more importantly, documents
|
|
* exactly which pointers are protected by RCU.
|
|
*/
|
|
|
|
#define rcu_dereference(p) ({ \
|
|
typeof(p) _________p1 = ACCESS_ONCE(p); \
|
|
smp_read_barrier_depends(); \
|
|
(_________p1); \
|
|
})
|
|
|
|
/**
|
|
* rcu_assign_pointer - assign (publicize) a pointer to a newly
|
|
* initialized structure that will be dereferenced by RCU read-side
|
|
* critical sections. Returns the value assigned.
|
|
*
|
|
* Inserts memory barriers on architectures that require them
|
|
* (pretty much all of them other than x86), and also prevents
|
|
* the compiler from reordering the code that initializes the
|
|
* structure after the pointer assignment. More importantly, this
|
|
* call documents which pointers will be dereferenced by RCU read-side
|
|
* code.
|
|
*/
|
|
|
|
#define rcu_assign_pointer(p, v) \
|
|
({ \
|
|
if (!__builtin_constant_p(v) || \
|
|
((v) != NULL)) \
|
|
smp_wmb(); \
|
|
(p) = (v); \
|
|
})
|
|
|
|
/* Infrastructure to implement the synchronize_() primitives. */
|
|
|
|
struct rcu_synchronize {
|
|
struct rcu_head head;
|
|
struct completion completion;
|
|
};
|
|
|
|
extern void wakeme_after_rcu(struct rcu_head *head);
|
|
|
|
/**
|
|
* synchronize_sched - block until all CPUs have exited any non-preemptive
|
|
* kernel code sequences.
|
|
*
|
|
* This means that all preempt_disable code sequences, including NMI and
|
|
* 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.
|
|
*
|
|
* 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.
|
|
*/
|
|
#define synchronize_sched() __synchronize_sched()
|
|
|
|
/**
|
|
* call_rcu - Queue an RCU callback for invocation after a grace period.
|
|
* @head: structure to be used for queueing the RCU updates.
|
|
* @func: actual update function to be invoked after the grace period
|
|
*
|
|
* The update function will be invoked some time after a full grace
|
|
* period elapses, 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.
|
|
*/
|
|
extern void call_rcu(struct rcu_head *head,
|
|
void (*func)(struct rcu_head *head));
|
|
|
|
/**
|
|
* call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
|
|
* @head: structure to be used for queueing the RCU updates.
|
|
* @func: actual update function to be invoked after the grace period
|
|
*
|
|
* The update function will be invoked some time after a full grace
|
|
* period elapses, in other words after all currently executing RCU
|
|
* read-side critical sections have completed. call_rcu_bh() assumes
|
|
* that the read-side critical sections end on completion of a softirq
|
|
* handler. This means that read-side critical sections in process
|
|
* context must not be interrupted by softirqs. This interface is to be
|
|
* used when most of the read-side critical sections are in softirq context.
|
|
* RCU read-side critical sections are delimited by :
|
|
* - rcu_read_lock() and rcu_read_unlock(), if in interrupt context.
|
|
* OR
|
|
* - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
|
|
* These may be nested.
|
|
*/
|
|
extern void call_rcu_bh(struct rcu_head *head,
|
|
void (*func)(struct rcu_head *head));
|
|
|
|
/* Exported common interfaces */
|
|
extern void synchronize_rcu(void);
|
|
extern void rcu_barrier(void);
|
|
extern void rcu_barrier_bh(void);
|
|
extern void rcu_barrier_sched(void);
|
|
|
|
/* Internal to kernel */
|
|
extern void rcu_init(void);
|
|
extern void rcu_scheduler_starting(void);
|
|
extern int rcu_needs_cpu(int cpu);
|
|
|
|
#endif /* __LINUX_RCUPDATE_H */
|