2005-04-16 16:20:36 -06:00
|
|
|
/*
|
2009-09-18 11:28:19 -06:00
|
|
|
* Read-Copy Update mechanism for mutual exclusion
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* 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
|
2013-12-03 11:02:52 -07:00
|
|
|
* along with this program; if not, you can access it online at
|
|
|
|
* http://www.gnu.org/licenses/gpl-2.0.html.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
2008-01-25 13:08:24 -07:00
|
|
|
* Copyright IBM Corporation, 2001
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.com>
|
2009-09-18 11:28:19 -06:00
|
|
|
*
|
2006-10-04 03:17:21 -06:00
|
|
|
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
|
2005-04-16 16:20:36 -06:00
|
|
|
* 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 -
|
2009-09-18 11:28:19 -06:00
|
|
|
* http://lse.sourceforge.net/locking/rcupdate.html
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __LINUX_RCUPDATE_H
|
|
|
|
#define __LINUX_RCUPDATE_H
|
|
|
|
|
2011-05-31 22:03:55 -06:00
|
|
|
#include <linux/types.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/cache.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/threads.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/seqlock.h>
|
2007-10-11 14:11:12 -06:00
|
|
|
#include <linux/lockdep.h>
|
rcu: add call_rcu_sched()
Fourth cut of patch to provide the call_rcu_sched(). This is again to
synchronize_sched() as call_rcu() is to synchronize_rcu().
Should be fine for experimental and -rt use, but not ready for inclusion.
With some luck, I will be able to tell Andrew to come out of hiding on
the next round.
Passes multi-day rcutorture sessions with concurrent CPU hotplugging.
Fixes since the first version include a bug that could result in
indefinite blocking (spotted by Gautham Shenoy), better resiliency
against CPU-hotplug operations, and other minor fixes.
Fixes since the second version include reworking grace-period detection
to avoid deadlocks that could happen when running concurrently with
CPU hotplug, adding Mathieu's fix to avoid the softlockup messages,
as well as Mathieu's fix to allow use earlier in boot.
Fixes since the third version include a wrong-CPU bug spotted by
Andrew, getting rid of the obsolete synchronize_kernel API that somehow
snuck back in, merging spin_unlock() and local_irq_restore() in a
few places, commenting the code that checks for quiescent states based
on interrupting from user-mode execution or the idle loop, removing
some inline attributes, and some code-style changes.
Known/suspected shortcomings:
o I still do not entirely trust the sleep/wakeup logic. Next step
will be to use a private snapshot of the CPU online mask in
rcu_sched_grace_period() -- if the CPU wasn't there at the start
of the grace period, we don't need to hear from it. And the
bit about accounting for changes in online CPUs inside of
rcu_sched_grace_period() is ugly anyway.
o It might be good for rcu_sched_grace_period() to invoke
resched_cpu() when a given CPU wasn't responding quickly,
but resched_cpu() is declared static...
This patch also fixes a long-standing bug in the earlier preemptable-RCU
implementation of synchronize_rcu() that could result in loss of
concurrent external changes to a task's CPU affinity mask. I still cannot
remember who reported this...
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 13:21:05 -06:00
|
|
|
#include <linux/completion.h>
|
2010-04-17 06:48:42 -06:00
|
|
|
#include <linux/debugobjects.h>
|
2011-11-23 18:12:59 -07:00
|
|
|
#include <linux/bug.h>
|
2010-04-28 15:39:09 -06:00
|
|
|
#include <linux/compiler.h>
|
2013-12-16 14:24:32 -07:00
|
|
|
#include <asm/barrier.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2014-02-11 14:10:12 -07:00
|
|
|
extern int rcu_expedited; /* for sysctl */
|
2010-03-10 16:24:05 -07:00
|
|
|
#ifdef CONFIG_RCU_TORTURE_TEST
|
|
|
|
extern int rcutorture_runnable; /* for sysctl */
|
|
|
|
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
|
|
|
|
|
2011-04-03 22:33:51 -06:00
|
|
|
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
|
2013-11-11 08:11:23 -07:00
|
|
|
void rcutorture_record_test_transition(void);
|
|
|
|
void rcutorture_record_progress(unsigned long vernum);
|
|
|
|
void do_trace_rcu_torture_read(const char *rcutorturename,
|
|
|
|
struct rcu_head *rhp,
|
|
|
|
unsigned long secs,
|
|
|
|
unsigned long c_old,
|
|
|
|
unsigned long c);
|
2011-04-03 22:33:51 -06:00
|
|
|
#else
|
|
|
|
static inline void rcutorture_record_test_transition(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
static inline void rcutorture_record_progress(unsigned long vernum)
|
|
|
|
{
|
|
|
|
}
|
2011-10-02 08:44:32 -06:00
|
|
|
#ifdef CONFIG_RCU_TRACE
|
2013-11-11 08:11:23 -07:00
|
|
|
void do_trace_rcu_torture_read(const char *rcutorturename,
|
|
|
|
struct rcu_head *rhp,
|
|
|
|
unsigned long secs,
|
|
|
|
unsigned long c_old,
|
|
|
|
unsigned long c);
|
2011-10-02 08:44:32 -06:00
|
|
|
#else
|
2012-11-14 17:26:40 -07:00
|
|
|
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
|
|
|
|
do { } while (0)
|
2011-10-02 08:44:32 -06:00
|
|
|
#endif
|
2011-04-03 22:33:51 -06:00
|
|
|
#endif
|
|
|
|
|
2010-11-22 22:36:11 -07:00
|
|
|
#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b))
|
|
|
|
#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b))
|
2010-08-13 17:16:25 -06:00
|
|
|
#define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b))
|
|
|
|
#define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b))
|
2012-12-28 12:30:36 -07:00
|
|
|
#define ulong2long(a) (*(long *)(&(a)))
|
2010-08-13 17:16:25 -06:00
|
|
|
|
2009-06-25 10:08:16 -06:00
|
|
|
/* Exported common interfaces */
|
2011-05-26 23:14:36 -06:00
|
|
|
|
|
|
|
#ifdef CONFIG_PREEMPT_RCU
|
|
|
|
|
|
|
|
/**
|
|
|
|
* call_rcu() - Queue an RCU callback for invocation after a grace period.
|
|
|
|
* @head: structure to be used for queueing the RCU updates.
|
|
|
|
* @func: actual callback function to be invoked after the grace period
|
|
|
|
*
|
|
|
|
* The callback function will be invoked some time after a full grace
|
|
|
|
* period elapses, in other words after all pre-existing RCU read-side
|
|
|
|
* critical sections have completed. However, the callback function
|
|
|
|
* might well execute concurrently with RCU read-side critical sections
|
|
|
|
* that started after call_rcu() was invoked. RCU read-side critical
|
|
|
|
* sections are delimited by rcu_read_lock() and rcu_read_unlock(),
|
|
|
|
* and may be nested.
|
2012-10-23 14:47:01 -06:00
|
|
|
*
|
|
|
|
* Note that all CPUs must agree that the grace period extended beyond
|
|
|
|
* all pre-existing RCU read-side critical section. On systems with more
|
|
|
|
* than one CPU, this means that when "func()" is invoked, each CPU is
|
|
|
|
* guaranteed to have executed a full memory barrier since the end of its
|
|
|
|
* last RCU read-side critical section whose beginning preceded the call
|
|
|
|
* to call_rcu(). It also means that each CPU executing an RCU read-side
|
|
|
|
* critical section that continues beyond the start of "func()" must have
|
|
|
|
* executed a memory barrier after the call_rcu() but 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 call_rcu() and CPU B invoked the
|
|
|
|
* resulting RCU callback function "func()", then both CPU A and CPU B are
|
|
|
|
* guaranteed to execute a full memory barrier during the time interval
|
|
|
|
* between the call to call_rcu() and the invocation of "func()" -- even
|
|
|
|
* if CPU A and CPU B are the same CPU (but again only if the system has
|
|
|
|
* more than one CPU).
|
2011-05-26 23:14:36 -06:00
|
|
|
*/
|
2013-11-11 08:11:23 -07:00
|
|
|
void call_rcu(struct rcu_head *head,
|
|
|
|
void (*func)(struct rcu_head *head));
|
2011-05-26 23:14:36 -06:00
|
|
|
|
|
|
|
#else /* #ifdef CONFIG_PREEMPT_RCU */
|
|
|
|
|
|
|
|
/* In classic RCU, call_rcu() is just call_rcu_sched(). */
|
|
|
|
#define call_rcu call_rcu_sched
|
|
|
|
|
|
|
|
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
|
|
|
|
|
|
|
|
/**
|
|
|
|
* 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 callback function to be invoked after the grace period
|
|
|
|
*
|
|
|
|
* The callback 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.
|
2012-10-23 14:47:01 -06:00
|
|
|
*
|
|
|
|
* See the description of call_rcu() for more detailed information on
|
|
|
|
* memory ordering guarantees.
|
2011-05-26 23:14:36 -06:00
|
|
|
*/
|
2013-11-11 08:11:23 -07:00
|
|
|
void call_rcu_bh(struct rcu_head *head,
|
|
|
|
void (*func)(struct rcu_head *head));
|
2011-05-26 23:14:36 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* call_rcu_sched() - Queue an RCU for invocation after sched grace period.
|
|
|
|
* @head: structure to be used for queueing the RCU updates.
|
|
|
|
* @func: actual callback function to be invoked after the grace period
|
|
|
|
*
|
|
|
|
* The callback 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_sched() assumes
|
|
|
|
* that the read-side critical sections end on enabling of preemption
|
|
|
|
* or on voluntary preemption.
|
|
|
|
* RCU read-side critical sections are delimited by :
|
|
|
|
* - rcu_read_lock_sched() and rcu_read_unlock_sched(),
|
|
|
|
* OR
|
|
|
|
* anything that disables preemption.
|
|
|
|
* These may be nested.
|
2012-10-23 14:47:01 -06:00
|
|
|
*
|
|
|
|
* See the description of call_rcu() for more detailed information on
|
|
|
|
* memory ordering guarantees.
|
2011-05-26 23:14:36 -06:00
|
|
|
*/
|
2013-11-11 08:11:23 -07:00
|
|
|
void call_rcu_sched(struct rcu_head *head,
|
|
|
|
void (*func)(struct rcu_head *rcu));
|
2011-05-26 23:14:36 -06:00
|
|
|
|
2013-11-11 08:11:23 -07:00
|
|
|
void synchronize_sched(void);
|
2009-06-25 10:08:16 -06:00
|
|
|
|
2010-08-13 17:16:25 -06:00
|
|
|
#ifdef CONFIG_PREEMPT_RCU
|
|
|
|
|
2013-11-11 08:11:23 -07:00
|
|
|
void __rcu_read_lock(void);
|
|
|
|
void __rcu_read_unlock(void);
|
|
|
|
void rcu_read_unlock_special(struct task_struct *t);
|
2010-08-17 15:18:46 -06:00
|
|
|
void synchronize_rcu(void);
|
|
|
|
|
2010-08-13 17:16:25 -06:00
|
|
|
/*
|
|
|
|
* Defined as a macro as it is a very low level header included from
|
|
|
|
* areas that don't even know about current. This gives the rcu_read_lock()
|
|
|
|
* nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
|
|
|
|
* types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
|
|
|
|
*/
|
|
|
|
#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
|
|
|
|
|
2010-08-17 15:18:46 -06:00
|
|
|
#else /* #ifdef CONFIG_PREEMPT_RCU */
|
|
|
|
|
|
|
|
static inline void __rcu_read_lock(void)
|
|
|
|
{
|
|
|
|
preempt_disable();
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __rcu_read_unlock(void)
|
|
|
|
{
|
|
|
|
preempt_enable();
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void synchronize_rcu(void)
|
|
|
|
{
|
|
|
|
synchronize_sched();
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int rcu_preempt_depth(void)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
|
|
|
|
|
|
|
|
/* Internal to kernel */
|
2013-11-11 08:11:23 -07:00
|
|
|
void rcu_init(void);
|
|
|
|
void rcu_sched_qs(int cpu);
|
|
|
|
void rcu_bh_qs(int cpu);
|
|
|
|
void rcu_check_callbacks(int cpu, int user);
|
2010-08-17 15:18:46 -06:00
|
|
|
struct notifier_block;
|
2013-11-11 08:11:23 -07:00
|
|
|
void rcu_idle_enter(void);
|
|
|
|
void rcu_idle_exit(void);
|
|
|
|
void rcu_irq_enter(void);
|
|
|
|
void rcu_irq_exit(void);
|
2012-07-11 12:26:30 -06:00
|
|
|
|
|
|
|
#ifdef CONFIG_RCU_USER_QS
|
2013-11-11 08:11:23 -07:00
|
|
|
void rcu_user_enter(void);
|
|
|
|
void rcu_user_exit(void);
|
2012-07-11 12:26:30 -06:00
|
|
|
#else
|
|
|
|
static inline void rcu_user_enter(void) { }
|
|
|
|
static inline void rcu_user_exit(void) { }
|
2012-10-10 17:47:16 -06:00
|
|
|
static inline void rcu_user_hooks_switch(struct task_struct *prev,
|
|
|
|
struct task_struct *next) { }
|
2012-07-11 12:26:30 -06:00
|
|
|
#endif /* CONFIG_RCU_USER_QS */
|
|
|
|
|
2012-02-02 16:42:04 -07:00
|
|
|
/**
|
|
|
|
* RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
|
|
|
|
* @a: Code that RCU needs to pay attention to.
|
|
|
|
*
|
|
|
|
* RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden
|
|
|
|
* in the inner idle loop, that is, between the rcu_idle_enter() and
|
|
|
|
* the rcu_idle_exit() -- RCU will happily ignore any such read-side
|
|
|
|
* critical sections. However, things like powertop need tracepoints
|
|
|
|
* in the inner idle loop.
|
|
|
|
*
|
|
|
|
* This macro provides the way out: RCU_NONIDLE(do_something_with_RCU())
|
|
|
|
* will tell RCU that it needs to pay attending, invoke its argument
|
|
|
|
* (in this example, a call to the do_something_with_RCU() function),
|
|
|
|
* and then tell RCU to go back to ignoring this CPU. It is permissible
|
|
|
|
* to nest RCU_NONIDLE() wrappers, but the nesting level is currently
|
|
|
|
* quite limited. If deeper nesting is required, it will be necessary
|
|
|
|
* to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
|
|
|
|
*/
|
|
|
|
#define RCU_NONIDLE(a) \
|
|
|
|
do { \
|
2012-07-31 11:12:48 -06:00
|
|
|
rcu_irq_enter(); \
|
2012-02-02 16:42:04 -07:00
|
|
|
do { a; } while (0); \
|
2012-07-31 11:12:48 -06:00
|
|
|
rcu_irq_exit(); \
|
2012-02-02 16:42:04 -07:00
|
|
|
} while (0)
|
|
|
|
|
2013-09-06 18:39:49 -06:00
|
|
|
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
|
2013-11-11 08:11:23 -07:00
|
|
|
bool __rcu_is_watching(void);
|
2013-09-06 18:39:49 -06:00
|
|
|
#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
|
|
|
|
|
2011-05-26 23:14:36 -06:00
|
|
|
/*
|
|
|
|
* Infrastructure to implement the synchronize_() primitives in
|
|
|
|
* TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
|
|
|
|
*/
|
|
|
|
|
|
|
|
typedef void call_rcu_func_t(struct rcu_head *head,
|
|
|
|
void (*func)(struct rcu_head *head));
|
|
|
|
void wait_rcu_gp(call_rcu_func_t crf);
|
|
|
|
|
rcu: Merge preemptable-RCU functionality into hierarchical RCU
Create a kernel/rcutree_plugin.h file that contains definitions
for preemptable RCU (or, under the #else branch of the #ifdef,
empty definitions for the classic non-preemptable semantics).
These definitions fit into plugins defined in kernel/rcutree.c
for this purpose.
This variant of preemptable RCU uses a new algorithm whose
read-side expense is roughly that of classic hierarchical RCU
under CONFIG_PREEMPT. This new algorithm's update-side expense
is similar to that of classic hierarchical RCU, and, in absence
of read-side preemption or blocking, is exactly that of classic
hierarchical RCU. Perhaps more important, this new algorithm
has a much simpler implementation, saving well over 1,000 lines
of code compared to mainline's implementation of preemptable
RCU, which will hopefully be retired in favor of this new
algorithm.
The simplifications are obtained by maintaining per-task
nesting state for running tasks, and using a simple
lock-protected algorithm to handle accounting when tasks block
within RCU read-side critical sections, making use of lessons
learned while creating numerous user-level RCU implementations
over the past 18 months.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josht@linux.vnet.ibm.com
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
LKML-Reference: <12509746134003-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-22 14:56:52 -06:00
|
|
|
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
|
"Tree RCU": scalable classic RCU implementation
This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs. Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.
This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion. This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.
Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.
Updates from v9 (http://lkml.org/lkml/2008/12/2/334):
o Fixes from remainder of line-by-line code walkthrough,
including comment spelling, initialization, undesirable
narrowing due to type conversion, removing redundant memory
barriers, removing redundant local-variable initialization,
and removing redundant local variables.
I do not believe that any of these fixes address the CPU-hotplug
issues that Andi Kleen was seeing, but please do give it a whirl
in case the machine is smarter than I am.
A writeup from the walkthrough may be found at the following
URL, in case you are suffering from terminal insomnia or
masochism:
http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf
o Made rcutree tracing use seq_file, as suggested some time
ago by Lai Jiangshan.
o Added a .csv variant of the rcudata debugfs trace file, to allow
people having thousands of CPUs to drop the data into
a spreadsheet. Tested with oocalc and gnumeric. Updated
documentation to suit.
Updates from v8 (http://lkml.org/lkml/2008/11/15/139):
o Fix a theoretical race between grace-period initialization and
force_quiescent_state() that could occur if more than three
jiffies were required to carry out the grace-period
initialization. Which it might, if you had enough CPUs.
o Apply Ingo's printk-standardization patch.
o Substitute local variables for repeated accesses to global
variables.
o Fix comment misspellings and redundant (but harmless) increments
of ->n_rcu_pending (this latter after having explicitly added it).
o Apply checkpatch fixes.
Updates from v7 (http://lkml.org/lkml/2008/10/10/291):
o Fixed a number of problems noted by Gautham Shenoy, including
the cpu-stall-detection bug that he was having difficulty
convincing me was real. ;-)
o Changed cpu-stall detection to wait for ten seconds rather than
three in order to reduce false positive, as suggested by Ingo
Molnar.
o Produced a design document (http://lwn.net/Articles/305782/).
The act of writing this document uncovered a number of both
theoretical and "here and now" bugs as noted below.
o Fix dynticks_nesting accounting confusion, simplify WARN_ON()
condition, fix kerneldoc comments, and add memory barriers
in dynticks interface functions.
o Add more data to tracing.
o Remove unused "rcu_barrier" field from rcu_data structure.
o Count calls to rcu_pending() from scheduling-clock interrupt
to use as a surrogate timebase should jiffies stop counting.
o Fix a theoretical race between force_quiescent_state() and
grace-period initialization. Yes, initialization does have to
go on for some jiffies for this race to occur, but given enough
CPUs...
Updates from v6 (http://lkml.org/lkml/2008/9/23/448):
o Fix a number of checkpatch.pl complaints.
o Apply review comments from Ingo Molnar and Lai Jiangshan
on the stall-detection code.
o Fix several bugs in !CONFIG_SMP builds.
o Fix a misspelled config-parameter name so that RCU now announces
at boot time if stall detection is configured.
o Run tests on numerous combinations of configurations parameters,
which after the fixes above, now build and run correctly.
Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):
o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
changeset some time ago, and finally got around to retesting
this option).
o Fix some tracing bugs in rcupreempt that caused incorrect
totals to be printed.
o I now test with a more brutal random-selection online/offline
script (attached). Probably more brutal than it needs to be
on the people reading it as well, but so it goes.
o A number of optimizations and usability improvements:
o Make rcu_pending() ignore the grace-period timeout when
there is no grace period in progress.
o Make force_quiescent_state() avoid going for a global
lock in the case where there is no grace period in
progress.
o Rearrange struct fields to improve struct layout.
o Make call_rcu() initiate a grace period if RCU was
idle, rather than waiting for the next scheduling
clock interrupt.
o Invoke rcu_irq_enter() and rcu_irq_exit() only when
idle, as suggested by Andi Kleen. I still don't
completely trust this change, and might back it out.
o Make CONFIG_RCU_TRACE be the single config variable
manipulated for all forms of RCU, instead of the prior
confusion.
o Document tracing files and formats for both rcupreempt
and rcutree.
Updates from v4 for those missing v5 given its bad subject line:
o Separated dynticks interface so that NMIs and irqs call separate
functions, greatly simplifying it. In particular, this code
no longer requires a proof of correctness. ;-)
o Separated dynticks state out into its own per-CPU structure,
avoiding the duplicated accounting.
o The case where a dynticks-idle CPU runs an irq handler that
invokes call_rcu() is now correctly handled, forcing that CPU
out of dynticks-idle mode.
o Review comments have been applied (thank you all!!!).
For but one example, fixed the dynticks-ordering issue that
Manfred pointed out, saving me much debugging. ;-)
o Adjusted rcuclassic and rcupreempt to handle dynticks changes.
Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel. It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space. That said,
I have already gratefully stolen quite a few of Manfred's ideas.
This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on
64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy. By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware. Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems. I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future. (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)
In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors. This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.
Some shortcomings:
o More bugs will probably surface as a result of an ongoing
line-by-line code inspection.
Patches will be provided as required.
o There are probably hangs, rcutorture failures, &c. Seems
quite stable on a 128-CPU machine, but that is kind of small
compared to 4096 CPUs. However, seems to do better than
mainline.
Patches will be provided as required.
o The memory footprint of this version is several KB larger
than rcuclassic.
A separate UP-only rcutiny patch will be provided, which will
reduce the memory footprint significantly, even compared
to the old rcuclassic. One such patch passes light testing,
and has a memory footprint smaller even than rcuclassic.
Initial reaction from various embedded guys was "it is not
worth it", so am putting it aside.
Credits:
o Manfred Spraul for ideas, review comments, and bugs spotted,
as well as some good friendly competition. ;-)
o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
for reviews and comments.
o Thomas Gleixner for much-needed help with some timer issues
(see patches below).
o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
alive despite my heavy abuse^Wtesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 13:55:32 -07:00
|
|
|
#include <linux/rcutree.h>
|
2013-03-27 09:44:00 -06:00
|
|
|
#elif defined(CONFIG_TINY_RCU)
|
rcu: "Tiny RCU", The Bloatwatch Edition
This patch is a version of RCU designed for !SMP provided for a
small-footprint RCU implementation. In particular, the
implementation of synchronize_rcu() is extremely lightweight and
high performance. It passes rcutorture testing in each of the
four relevant configurations (combinations of NO_HZ and PREEMPT)
on x86. This saves about 1K bytes compared to old Classic RCU
(which is no longer in mainline), and more than three kilobytes
compared to Hierarchical RCU (updated to 2.6.30):
CONFIG_TREE_RCU:
text data bss dec filename
183 4 0 187 kernel/rcupdate.o
2783 520 36 3339 kernel/rcutree.o
3526 Total (vs 4565 for v7)
CONFIG_TREE_PREEMPT_RCU:
text data bss dec filename
263 4 0 267 kernel/rcupdate.o
4594 776 52 5422 kernel/rcutree.o
5689 Total (6155 for v7)
CONFIG_TINY_RCU:
text data bss dec filename
96 4 0 100 kernel/rcupdate.o
734 24 0 758 kernel/rcutiny.o
858 Total (vs 848 for v7)
The above is for x86. Your mileage may vary on other platforms.
Further compression is possible, but is being procrastinated.
Changes from v7 (http://lkml.org/lkml/2009/10/9/388)
o Apply Lai Jiangshan's review comments (aside from
might_sleep() in synchronize_sched(), which is covered by SMP builds).
o Fix up expedited primitives.
Changes from v6 (http://lkml.org/lkml/2009/9/23/293).
o Forward ported to put it into the 2.6.33 stream.
o Added lockdep support.
o Make lightweight rcu_barrier.
Changes from v5 (http://lkml.org/lkml/2009/6/23/12).
o Ported to latest pre-2.6.32 merge window kernel.
- Renamed rcu_qsctr_inc() to rcu_sched_qs().
- Renamed rcu_bh_qsctr_inc() to rcu_bh_qs().
- Provided trivial rcu_cpu_notify().
- Provided trivial exit_rcu().
- Provided trivial rcu_needs_cpu().
- Fixed up the rcu_*_enter/exit() functions in linux/hardirq.h.
o Removed the dependence on EMBEDDED, with a view to making
TINY_RCU default for !SMP at some time in the future.
o Added (trivial) support for expedited grace periods.
Changes from v4 (http://lkml.org/lkml/2009/5/2/91) include:
o Squeeze the size down a bit further by removing the
->completed field from struct rcu_ctrlblk.
o This permits synchronize_rcu() to become the empty function.
Previous concerns about rcutorture were unfounded, as
rcutorture correctly handles a constant value from
rcu_batches_completed() and rcu_batches_completed_bh().
Changes from v3 (http://lkml.org/lkml/2009/3/29/221) include:
o Changed rcu_batches_completed(), rcu_batches_completed_bh()
rcu_enter_nohz(), rcu_exit_nohz(), rcu_nmi_enter(), and
rcu_nmi_exit(), to be static inlines, as suggested by David
Howells. Doing this saves about 100 bytes from rcutiny.o.
(The numbers between v3 and this v4 of the patch are not directly
comparable, since they are against different versions of Linux.)
Changes from v2 (http://lkml.org/lkml/2009/2/3/333) include:
o Fix whitespace issues.
o Change short-circuit "||" operator to instead be "+" in order
to fix performance bug noted by "kraai" on LWN.
(http://lwn.net/Articles/324348/)
Changes from v1 (http://lkml.org/lkml/2009/1/13/440) include:
o This version depends on EMBEDDED as well as !SMP, as suggested
by Ingo.
o Updated rcu_needs_cpu() to unconditionally return zero,
permitting the CPU to enter dynticks-idle mode at any time.
This works because callbacks can be invoked upon entry to
dynticks-idle mode.
o Paul is now OK with this being included, based on a poll at
the Kernel Miniconf at linux.conf.au, where about ten people said
that they cared about saving 900 bytes on single-CPU systems.
o Applies to both mainline and tip/core/rcu.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: David Howells <dhowells@redhat.com>
Acked-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: avi@redhat.com
Cc: mtosatti@redhat.com
LKML-Reference: <12565226351355-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-25 20:03:50 -06:00
|
|
|
#include <linux/rcutiny.h>
|
"Tree RCU": scalable classic RCU implementation
This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs. Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.
This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion. This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.
Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.
Updates from v9 (http://lkml.org/lkml/2008/12/2/334):
o Fixes from remainder of line-by-line code walkthrough,
including comment spelling, initialization, undesirable
narrowing due to type conversion, removing redundant memory
barriers, removing redundant local-variable initialization,
and removing redundant local variables.
I do not believe that any of these fixes address the CPU-hotplug
issues that Andi Kleen was seeing, but please do give it a whirl
in case the machine is smarter than I am.
A writeup from the walkthrough may be found at the following
URL, in case you are suffering from terminal insomnia or
masochism:
http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf
o Made rcutree tracing use seq_file, as suggested some time
ago by Lai Jiangshan.
o Added a .csv variant of the rcudata debugfs trace file, to allow
people having thousands of CPUs to drop the data into
a spreadsheet. Tested with oocalc and gnumeric. Updated
documentation to suit.
Updates from v8 (http://lkml.org/lkml/2008/11/15/139):
o Fix a theoretical race between grace-period initialization and
force_quiescent_state() that could occur if more than three
jiffies were required to carry out the grace-period
initialization. Which it might, if you had enough CPUs.
o Apply Ingo's printk-standardization patch.
o Substitute local variables for repeated accesses to global
variables.
o Fix comment misspellings and redundant (but harmless) increments
of ->n_rcu_pending (this latter after having explicitly added it).
o Apply checkpatch fixes.
Updates from v7 (http://lkml.org/lkml/2008/10/10/291):
o Fixed a number of problems noted by Gautham Shenoy, including
the cpu-stall-detection bug that he was having difficulty
convincing me was real. ;-)
o Changed cpu-stall detection to wait for ten seconds rather than
three in order to reduce false positive, as suggested by Ingo
Molnar.
o Produced a design document (http://lwn.net/Articles/305782/).
The act of writing this document uncovered a number of both
theoretical and "here and now" bugs as noted below.
o Fix dynticks_nesting accounting confusion, simplify WARN_ON()
condition, fix kerneldoc comments, and add memory barriers
in dynticks interface functions.
o Add more data to tracing.
o Remove unused "rcu_barrier" field from rcu_data structure.
o Count calls to rcu_pending() from scheduling-clock interrupt
to use as a surrogate timebase should jiffies stop counting.
o Fix a theoretical race between force_quiescent_state() and
grace-period initialization. Yes, initialization does have to
go on for some jiffies for this race to occur, but given enough
CPUs...
Updates from v6 (http://lkml.org/lkml/2008/9/23/448):
o Fix a number of checkpatch.pl complaints.
o Apply review comments from Ingo Molnar and Lai Jiangshan
on the stall-detection code.
o Fix several bugs in !CONFIG_SMP builds.
o Fix a misspelled config-parameter name so that RCU now announces
at boot time if stall detection is configured.
o Run tests on numerous combinations of configurations parameters,
which after the fixes above, now build and run correctly.
Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):
o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
changeset some time ago, and finally got around to retesting
this option).
o Fix some tracing bugs in rcupreempt that caused incorrect
totals to be printed.
o I now test with a more brutal random-selection online/offline
script (attached). Probably more brutal than it needs to be
on the people reading it as well, but so it goes.
o A number of optimizations and usability improvements:
o Make rcu_pending() ignore the grace-period timeout when
there is no grace period in progress.
o Make force_quiescent_state() avoid going for a global
lock in the case where there is no grace period in
progress.
o Rearrange struct fields to improve struct layout.
o Make call_rcu() initiate a grace period if RCU was
idle, rather than waiting for the next scheduling
clock interrupt.
o Invoke rcu_irq_enter() and rcu_irq_exit() only when
idle, as suggested by Andi Kleen. I still don't
completely trust this change, and might back it out.
o Make CONFIG_RCU_TRACE be the single config variable
manipulated for all forms of RCU, instead of the prior
confusion.
o Document tracing files and formats for both rcupreempt
and rcutree.
Updates from v4 for those missing v5 given its bad subject line:
o Separated dynticks interface so that NMIs and irqs call separate
functions, greatly simplifying it. In particular, this code
no longer requires a proof of correctness. ;-)
o Separated dynticks state out into its own per-CPU structure,
avoiding the duplicated accounting.
o The case where a dynticks-idle CPU runs an irq handler that
invokes call_rcu() is now correctly handled, forcing that CPU
out of dynticks-idle mode.
o Review comments have been applied (thank you all!!!).
For but one example, fixed the dynticks-ordering issue that
Manfred pointed out, saving me much debugging. ;-)
o Adjusted rcuclassic and rcupreempt to handle dynticks changes.
Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel. It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space. That said,
I have already gratefully stolen quite a few of Manfred's ideas.
This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on
64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy. By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware. Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems. I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future. (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)
In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors. This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.
Some shortcomings:
o More bugs will probably surface as a result of an ongoing
line-by-line code inspection.
Patches will be provided as required.
o There are probably hangs, rcutorture failures, &c. Seems
quite stable on a 128-CPU machine, but that is kind of small
compared to 4096 CPUs. However, seems to do better than
mainline.
Patches will be provided as required.
o The memory footprint of this version is several KB larger
than rcuclassic.
A separate UP-only rcutiny patch will be provided, which will
reduce the memory footprint significantly, even compared
to the old rcuclassic. One such patch passes light testing,
and has a memory footprint smaller even than rcuclassic.
Initial reaction from various embedded guys was "it is not
worth it", so am putting it aside.
Credits:
o Manfred Spraul for ideas, review comments, and bugs spotted,
as well as some good friendly competition. ;-)
o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
for reviews and comments.
o Thomas Gleixner for much-needed help with some timer issues
(see patches below).
o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
alive despite my heavy abuse^Wtesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-18 13:55:32 -07:00
|
|
|
#else
|
|
|
|
#error "Unknown RCU implementation specified to kernel configuration"
|
2009-08-22 14:56:53 -06:00
|
|
|
#endif
|
2008-01-25 13:08:24 -07:00
|
|
|
|
2010-04-17 06:48:42 -06:00
|
|
|
/*
|
|
|
|
* init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
|
|
|
|
* initialization and destruction of rcu_head on the stack. rcu_head structures
|
|
|
|
* allocated dynamically in the heap or defined statically don't need any
|
|
|
|
* initialization.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
|
2013-11-11 08:11:23 -07:00
|
|
|
void init_rcu_head_on_stack(struct rcu_head *head);
|
|
|
|
void destroy_rcu_head_on_stack(struct rcu_head *head);
|
2010-04-17 06:48:42 -06:00
|
|
|
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
|
2010-04-17 06:48:39 -06:00
|
|
|
static inline void init_rcu_head_on_stack(struct rcu_head *head)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
|
|
|
|
{
|
|
|
|
}
|
2010-04-17 06:48:42 -06:00
|
|
|
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
|
2010-04-17 06:48:39 -06:00
|
|
|
|
2012-01-23 13:41:26 -07:00
|
|
|
#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
|
|
|
|
bool rcu_lockdep_current_cpu_online(void);
|
|
|
|
#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
|
|
|
|
static inline bool rcu_lockdep_current_cpu_online(void)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
|
|
|
|
|
2009-08-22 14:56:47 -06:00
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
2011-10-07 10:22:02 -06:00
|
|
|
static inline void rcu_lock_acquire(struct lockdep_map *map)
|
|
|
|
{
|
2014-01-20 11:20:06 -07:00
|
|
|
lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
|
2011-10-07 10:22:02 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline void rcu_lock_release(struct lockdep_map *map)
|
|
|
|
{
|
|
|
|
lock_release(map, 1, _THIS_IP_);
|
|
|
|
}
|
|
|
|
|
2009-08-22 14:56:47 -06:00
|
|
|
extern struct lockdep_map rcu_lock_map;
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
extern struct lockdep_map rcu_bh_lock_map;
|
|
|
|
extern struct lockdep_map rcu_sched_lock_map;
|
2013-10-28 10:22:24 -06:00
|
|
|
extern struct lockdep_map rcu_callback_map;
|
2010-04-15 13:50:39 -06:00
|
|
|
extern int debug_lockdep_rcu_enabled(void);
|
2010-03-03 08:46:57 -07:00
|
|
|
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_read_lock_held() - might we be in RCU read-side critical section?
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*
|
2010-03-30 11:52:21 -06:00
|
|
|
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
|
|
|
|
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
* this assumes we are in an RCU read-side critical section unless it can
|
2010-04-28 15:39:09 -06:00
|
|
|
* prove otherwise. This is useful for debug checks in functions that
|
|
|
|
* require that they be called within an RCU read-side critical section.
|
2010-03-03 08:46:57 -07:00
|
|
|
*
|
2010-04-28 15:39:09 -06:00
|
|
|
* Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
|
2010-03-30 11:59:28 -06:00
|
|
|
* and while lockdep is disabled.
|
2011-11-28 11:42:42 -07:00
|
|
|
*
|
|
|
|
* Note that rcu_read_lock() and the matching rcu_read_unlock() must
|
|
|
|
* occur in the same context, for example, it is illegal to invoke
|
|
|
|
* rcu_read_unlock() in process context if the matching rcu_read_lock()
|
|
|
|
* was invoked from within an irq handler.
|
2012-01-23 13:41:26 -07:00
|
|
|
*
|
|
|
|
* Note that rcu_read_lock() is disallowed if the CPU is either idle or
|
|
|
|
* offline from an RCU perspective, so check for those as well.
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*/
|
|
|
|
static inline int rcu_read_lock_held(void)
|
|
|
|
{
|
2010-03-03 08:46:57 -07:00
|
|
|
if (!debug_lockdep_rcu_enabled())
|
|
|
|
return 1;
|
2013-09-13 18:20:11 -06:00
|
|
|
if (!rcu_is_watching())
|
2011-10-07 17:25:18 -06:00
|
|
|
return 0;
|
2012-01-23 13:41:26 -07:00
|
|
|
if (!rcu_lockdep_current_cpu_online())
|
|
|
|
return 0;
|
2010-03-03 08:46:57 -07:00
|
|
|
return lock_is_held(&rcu_lock_map);
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
}
|
|
|
|
|
2010-03-15 18:03:43 -06:00
|
|
|
/*
|
|
|
|
* rcu_read_lock_bh_held() is defined out of line to avoid #include-file
|
|
|
|
* hell.
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*/
|
2013-11-11 08:11:23 -07:00
|
|
|
int rcu_read_lock_bh_held(void);
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*
|
2010-03-30 11:52:21 -06:00
|
|
|
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
|
|
|
|
* RCU-sched read-side critical section. In absence of
|
|
|
|
* CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
|
|
|
|
* critical section unless it can prove otherwise. Note that disabling
|
|
|
|
* of preemption (including disabling irqs) counts as an RCU-sched
|
2010-04-28 15:39:09 -06:00
|
|
|
* read-side critical section. This is useful for debug checks in functions
|
|
|
|
* that required that they be called within an RCU-sched read-side
|
|
|
|
* critical section.
|
2010-03-03 08:46:57 -07:00
|
|
|
*
|
2010-03-30 11:59:28 -06:00
|
|
|
* Check debug_lockdep_rcu_enabled() to prevent false positives during boot
|
|
|
|
* and while lockdep is disabled.
|
2011-10-07 17:25:18 -06:00
|
|
|
*
|
|
|
|
* Note that if the CPU is in the idle loop from an RCU point of
|
|
|
|
* view (ie: that we are in the section between rcu_idle_enter() and
|
|
|
|
* rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
|
|
|
|
* did an rcu_read_lock(). The reason for this is that RCU ignores CPUs
|
|
|
|
* that are in such a section, considering these as in extended quiescent
|
|
|
|
* state, so such a CPU is effectively never in an RCU read-side critical
|
|
|
|
* section regardless of what RCU primitives it invokes. This state of
|
|
|
|
* affairs is required --- we need to keep an RCU-free window in idle
|
|
|
|
* where the CPU may possibly enter into low power mode. This way we can
|
|
|
|
* notice an extended quiescent state to other CPUs that started a grace
|
|
|
|
* period. Otherwise we would delay any grace period as long as we run in
|
|
|
|
* the idle task.
|
2012-01-23 13:41:26 -07:00
|
|
|
*
|
|
|
|
* Similarly, we avoid claiming an SRCU read lock held if the current
|
|
|
|
* CPU is offline.
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*/
|
2011-06-07 17:13:27 -06:00
|
|
|
#ifdef CONFIG_PREEMPT_COUNT
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
static inline int rcu_read_lock_sched_held(void)
|
|
|
|
{
|
|
|
|
int lockdep_opinion = 0;
|
|
|
|
|
2010-03-03 08:46:57 -07:00
|
|
|
if (!debug_lockdep_rcu_enabled())
|
|
|
|
return 1;
|
2013-09-13 18:20:11 -06:00
|
|
|
if (!rcu_is_watching())
|
2011-10-07 17:25:18 -06:00
|
|
|
return 0;
|
2012-01-23 13:41:26 -07:00
|
|
|
if (!rcu_lockdep_current_cpu_online())
|
|
|
|
return 0;
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
if (debug_locks)
|
|
|
|
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
|
2010-03-18 13:25:33 -06:00
|
|
|
return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
}
|
2011-06-07 17:13:27 -06:00
|
|
|
#else /* #ifdef CONFIG_PREEMPT_COUNT */
|
2010-03-03 18:50:16 -07:00
|
|
|
static inline int rcu_read_lock_sched_held(void)
|
|
|
|
{
|
|
|
|
return 1;
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
}
|
2011-06-07 17:13:27 -06:00
|
|
|
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
|
|
|
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
|
|
|
|
|
2011-10-07 10:22:03 -06:00
|
|
|
# define rcu_lock_acquire(a) do { } while (0)
|
|
|
|
# define rcu_lock_release(a) do { } while (0)
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
|
|
|
static inline int rcu_read_lock_held(void)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int rcu_read_lock_bh_held(void)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2011-06-07 17:13:27 -06:00
|
|
|
#ifdef CONFIG_PREEMPT_COUNT
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
static inline int rcu_read_lock_sched_held(void)
|
|
|
|
{
|
2010-04-02 17:17:17 -06:00
|
|
|
return preempt_count() != 0 || irqs_disabled();
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
}
|
2011-06-07 17:13:27 -06:00
|
|
|
#else /* #ifdef CONFIG_PREEMPT_COUNT */
|
2010-03-03 18:50:16 -07:00
|
|
|
static inline int rcu_read_lock_sched_held(void)
|
|
|
|
{
|
|
|
|
return 1;
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
}
|
2011-06-07 17:13:27 -06:00
|
|
|
#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
|
|
|
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
|
|
|
|
|
|
|
|
#ifdef CONFIG_PROVE_RCU
|
|
|
|
|
2010-06-25 10:08:19 -06:00
|
|
|
/**
|
|
|
|
* rcu_lockdep_assert - emit lockdep splat if specified condition not met
|
|
|
|
* @c: condition to check
|
2011-05-24 09:31:09 -06:00
|
|
|
* @s: informative message
|
2010-06-25 10:08:19 -06:00
|
|
|
*/
|
2011-05-24 09:31:09 -06:00
|
|
|
#define rcu_lockdep_assert(c, s) \
|
2010-04-20 02:23:07 -06:00
|
|
|
do { \
|
2012-03-23 16:01:52 -06:00
|
|
|
static bool __section(.data.unlikely) __warned; \
|
2010-04-20 02:23:07 -06:00
|
|
|
if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \
|
|
|
|
__warned = true; \
|
2011-05-24 09:31:09 -06:00
|
|
|
lockdep_rcu_suspicious(__FILE__, __LINE__, s); \
|
2010-04-20 02:23:07 -06:00
|
|
|
} \
|
|
|
|
} while (0)
|
|
|
|
|
2012-01-12 14:49:19 -07:00
|
|
|
#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU)
|
|
|
|
static inline void rcu_preempt_sleep_check(void)
|
|
|
|
{
|
|
|
|
rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
|
2012-05-17 16:12:45 -06:00
|
|
|
"Illegal context switch in RCU read-side critical section");
|
2012-01-12 14:49:19 -07:00
|
|
|
}
|
|
|
|
#else /* #ifdef CONFIG_PROVE_RCU */
|
|
|
|
static inline void rcu_preempt_sleep_check(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* #else #ifdef CONFIG_PROVE_RCU */
|
|
|
|
|
2011-05-24 09:31:09 -06:00
|
|
|
#define rcu_sleep_check() \
|
|
|
|
do { \
|
2012-01-12 14:49:19 -07:00
|
|
|
rcu_preempt_sleep_check(); \
|
2011-05-24 09:31:09 -06:00
|
|
|
rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \
|
2013-12-05 16:10:23 -07:00
|
|
|
"Illegal context switch in RCU-bh read-side critical section"); \
|
2011-05-24 09:31:09 -06:00
|
|
|
rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \
|
2013-12-05 16:10:23 -07:00
|
|
|
"Illegal context switch in RCU-sched read-side critical section"); \
|
2011-05-24 09:31:09 -06:00
|
|
|
} while (0)
|
|
|
|
|
2010-04-28 15:39:09 -06:00
|
|
|
#else /* #ifdef CONFIG_PROVE_RCU */
|
|
|
|
|
2011-05-24 09:31:09 -06:00
|
|
|
#define rcu_lockdep_assert(c, s) do { } while (0)
|
|
|
|
#define rcu_sleep_check() do { } while (0)
|
2010-04-28 15:39:09 -06:00
|
|
|
|
|
|
|
#endif /* #else #ifdef CONFIG_PROVE_RCU */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper functions for rcu_dereference_check(), rcu_dereference_protected()
|
|
|
|
* and rcu_assign_pointer(). Some of these could be folded into their
|
|
|
|
* callers, but they are left separate in order to ease introduction of
|
|
|
|
* multiple flavors of pointers to match the multiple flavors of RCU
|
|
|
|
* (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in
|
|
|
|
* the future.
|
|
|
|
*/
|
2010-09-13 18:24:21 -06:00
|
|
|
|
|
|
|
#ifdef __CHECKER__
|
|
|
|
#define rcu_dereference_sparse(p, space) \
|
|
|
|
((void)(((typeof(*p) space *)p) == p))
|
|
|
|
#else /* #ifdef __CHECKER__ */
|
|
|
|
#define rcu_dereference_sparse(p, space)
|
|
|
|
#endif /* #else #ifdef __CHECKER__ */
|
|
|
|
|
2010-04-28 15:39:09 -06:00
|
|
|
#define __rcu_access_pointer(p, space) \
|
2013-12-05 17:19:15 -07:00
|
|
|
({ \
|
|
|
|
typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
|
|
|
|
rcu_dereference_sparse(p, space); \
|
|
|
|
((typeof(*p) __force __kernel *)(_________p1)); \
|
|
|
|
})
|
2010-04-28 15:39:09 -06:00
|
|
|
#define __rcu_dereference_check(p, c, space) \
|
2013-12-05 17:19:15 -07:00
|
|
|
({ \
|
|
|
|
typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
|
|
|
|
rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
|
|
|
|
rcu_dereference_sparse(p, space); \
|
|
|
|
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
|
|
|
|
((typeof(*p) __force __kernel *)(_________p1)); \
|
|
|
|
})
|
2010-04-28 15:39:09 -06:00
|
|
|
#define __rcu_dereference_protected(p, c, space) \
|
2013-12-05 17:19:15 -07:00
|
|
|
({ \
|
|
|
|
rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \
|
|
|
|
rcu_dereference_sparse(p, space); \
|
|
|
|
((typeof(*p) __force __kernel *)(p)); \
|
|
|
|
})
|
2010-04-28 15:39:09 -06:00
|
|
|
|
2011-04-01 08:15:14 -06:00
|
|
|
#define __rcu_access_index(p, space) \
|
2013-12-05 17:19:15 -07:00
|
|
|
({ \
|
|
|
|
typeof(p) _________p1 = ACCESS_ONCE(p); \
|
|
|
|
rcu_dereference_sparse(p, space); \
|
|
|
|
(_________p1); \
|
|
|
|
})
|
2010-04-28 15:39:09 -06:00
|
|
|
#define __rcu_dereference_index_check(p, c) \
|
2013-12-05 17:19:15 -07:00
|
|
|
({ \
|
|
|
|
typeof(p) _________p1 = ACCESS_ONCE(p); \
|
|
|
|
rcu_lockdep_assert(c, \
|
|
|
|
"suspicious rcu_dereference_index_check() usage"); \
|
|
|
|
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
|
|
|
|
(_________p1); \
|
|
|
|
})
|
2013-11-11 10:59:34 -07:00
|
|
|
|
|
|
|
/**
|
|
|
|
* RCU_INITIALIZER() - statically initialize an RCU-protected global variable
|
|
|
|
* @v: The value to statically initialize with.
|
|
|
|
*/
|
|
|
|
#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_assign_pointer() - assign to RCU-protected pointer
|
|
|
|
* @p: pointer to assign to
|
|
|
|
* @v: value to assign (publish)
|
|
|
|
*
|
|
|
|
* Assigns the specified value to the specified RCU-protected
|
|
|
|
* pointer, ensuring that any concurrent RCU readers will see
|
|
|
|
* any prior initialization.
|
|
|
|
*
|
|
|
|
* Inserts memory barriers on architectures that require them
|
|
|
|
* (which is most of them), 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.
|
|
|
|
*
|
|
|
|
* In some special cases, you may use RCU_INIT_POINTER() instead
|
|
|
|
* of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due
|
|
|
|
* to the fact that it does not constrain either the CPU or the compiler.
|
|
|
|
* That said, using RCU_INIT_POINTER() when you should have used
|
|
|
|
* rcu_assign_pointer() is a very bad thing that results in
|
|
|
|
* impossible-to-diagnose memory corruption. So please be careful.
|
|
|
|
* See the RCU_INIT_POINTER() comment header for details.
|
|
|
|
*
|
|
|
|
* Note that rcu_assign_pointer() evaluates each of its arguments only
|
|
|
|
* once, appearances notwithstanding. One of the "extra" evaluations
|
|
|
|
* is in typeof() and the other visible only to sparse (__CHECKER__),
|
|
|
|
* neither of which actually execute the argument. As with most cpp
|
|
|
|
* macros, this execute-arguments-only-once property is important, so
|
|
|
|
* please be careful when making changes to rcu_assign_pointer() and the
|
|
|
|
* other macros that it invokes.
|
|
|
|
*/
|
2013-12-16 14:24:32 -07:00
|
|
|
#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v))
|
2010-04-28 15:39:09 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_access_pointer() - fetch RCU pointer with no dereferencing
|
|
|
|
* @p: The pointer to read
|
|
|
|
*
|
|
|
|
* Return the value of the specified RCU-protected pointer, but omit the
|
|
|
|
* smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
|
|
|
|
* when the value of this pointer is accessed, but the pointer is not
|
|
|
|
* dereferenced, for example, when testing an RCU-protected pointer against
|
|
|
|
* NULL. Although rcu_access_pointer() may also be used in cases where
|
|
|
|
* update-side locks prevent the value of the pointer from changing, you
|
|
|
|
* should instead use rcu_dereference_protected() for this use case.
|
2012-01-12 18:21:20 -07:00
|
|
|
*
|
|
|
|
* It is also permissible to use rcu_access_pointer() when read-side
|
|
|
|
* access to the pointer was removed at least one grace period ago, as
|
|
|
|
* is the case in the context of the RCU callback that is freeing up
|
|
|
|
* the data, or after a synchronize_rcu() returns. This can be useful
|
|
|
|
* when tearing down multi-linked structures after a grace period
|
|
|
|
* has elapsed.
|
2010-04-28 15:39:09 -06:00
|
|
|
*/
|
|
|
|
#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
|
|
|
|
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_dereference_check() - rcu_dereference with debug checking
|
2010-04-09 16:39:11 -06:00
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
* @c: The conditions under which the dereference will take place
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*
|
2010-04-09 16:39:11 -06:00
|
|
|
* Do an rcu_dereference(), but check that the conditions under which the
|
2010-04-28 15:39:09 -06:00
|
|
|
* dereference will take place are correct. Typically the conditions
|
|
|
|
* indicate the various locking conditions that should be held at that
|
|
|
|
* point. The check should return true if the conditions are satisfied.
|
|
|
|
* An implicit check for being in an RCU read-side critical section
|
|
|
|
* (rcu_read_lock()) is included.
|
2010-04-09 16:39:11 -06:00
|
|
|
*
|
|
|
|
* For example:
|
|
|
|
*
|
2010-04-28 15:39:09 -06:00
|
|
|
* bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
|
2010-04-09 16:39:11 -06:00
|
|
|
*
|
|
|
|
* could be used to indicate to lockdep that foo->bar may only be dereferenced
|
2010-04-28 15:39:09 -06:00
|
|
|
* if either rcu_read_lock() is held, or that the lock required to replace
|
2010-04-09 16:39:11 -06:00
|
|
|
* the bar struct at foo->bar is held.
|
|
|
|
*
|
|
|
|
* Note that the list of conditions may also include indications of when a lock
|
|
|
|
* need not be held, for example during initialisation or destruction of the
|
|
|
|
* target struct:
|
|
|
|
*
|
2010-04-28 15:39:09 -06:00
|
|
|
* bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
|
2010-04-09 16:39:11 -06:00
|
|
|
* atomic_read(&foo->usage) == 0);
|
2010-04-28 15:39:09 -06:00
|
|
|
*
|
|
|
|
* Inserts memory barriers on architectures that require them
|
|
|
|
* (currently only the Alpha), prevents the compiler from refetching
|
|
|
|
* (and from merging fetches), and, more importantly, documents exactly
|
|
|
|
* which pointers are protected by RCU and checks that the pointer is
|
|
|
|
* annotated as __rcu.
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
*/
|
|
|
|
#define rcu_dereference_check(p, c) \
|
2010-04-28 15:39:09 -06:00
|
|
|
__rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu)
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
* @c: The conditions under which the dereference will take place
|
|
|
|
*
|
|
|
|
* This is the RCU-bh counterpart to rcu_dereference_check().
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_bh_check(p, c) \
|
|
|
|
__rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
|
rcu: Introduce lockdep-based checking to RCU read-side primitives
Inspection is proving insufficient to catch all RCU misuses,
which is understandable given that rcu_dereference() might be
protected by any of four different flavors of RCU (RCU, RCU-bh,
RCU-sched, and SRCU), and might also/instead be protected by any
of a number of locking primitives. It is therefore time to
enlist the aid of lockdep.
This set of patches is inspired by earlier work by Peter
Zijlstra and Thomas Gleixner, and takes the following approach:
o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched.
o Set up separate lockdep classes for each instance of SRCU.
o Create primitives that check for being in an RCU read-side
critical section. These return exact answers if lockdep is
fully enabled, but if unsure, report being in an RCU read-side
critical section. (We want to avoid false positives!)
The primitives are:
For RCU: rcu_read_lock_held(void)
For RCU-bh: rcu_read_lock_bh_held(void)
For RCU-sched: rcu_read_lock_sched_held(void)
For SRCU: srcu_read_lock_held(struct srcu_struct *sp)
o Add rcu_dereference_check(), which takes a second argument
in which one places a boolean expression based on the above
primitives and/or lockdep_is_held().
o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables
rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING,
and should be quite helpful during the transition period while
CONFIG_PROVE_RCU-unaware patches are in flight.
The existing rcu_dereference() primitive does no checking, but
upcoming patches will change that.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-22 18:04:45 -07:00
|
|
|
|
2010-04-09 16:39:10 -06:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
* @c: The conditions under which the dereference will take place
|
|
|
|
*
|
|
|
|
* This is the RCU-sched counterpart to rcu_dereference_check().
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_sched_check(p, c) \
|
|
|
|
__rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \
|
|
|
|
__rcu)
|
|
|
|
|
|
|
|
#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/
|
|
|
|
|
2013-05-28 12:38:42 -06:00
|
|
|
/*
|
|
|
|
* The tracing infrastructure traces RCU (we want that), but unfortunately
|
|
|
|
* some of the RCU checks causes tracing to lock up the system.
|
|
|
|
*
|
|
|
|
* The tracing version of rcu_dereference_raw() must not call
|
|
|
|
* rcu_read_lock_held().
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
|
|
|
|
|
2011-04-01 08:15:14 -06:00
|
|
|
/**
|
|
|
|
* rcu_access_index() - fetch RCU index with no dereferencing
|
|
|
|
* @p: The index to read
|
|
|
|
*
|
|
|
|
* Return the value of the specified RCU-protected index, but omit the
|
|
|
|
* smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful
|
|
|
|
* when the value of this index is accessed, but the index is not
|
|
|
|
* dereferenced, for example, when testing an RCU-protected index against
|
|
|
|
* -1. Although rcu_access_index() may also be used in cases where
|
|
|
|
* update-side locks prevent the value of the index from changing, you
|
|
|
|
* should instead use rcu_dereference_index_protected() for this use case.
|
|
|
|
*/
|
|
|
|
#define rcu_access_index(p) __rcu_access_index((p), __rcu)
|
|
|
|
|
2010-04-28 15:39:09 -06:00
|
|
|
/**
|
|
|
|
* rcu_dereference_index_check() - rcu_dereference for indices with debug checking
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
* @c: The conditions under which the dereference will take place
|
|
|
|
*
|
|
|
|
* Similar to rcu_dereference_check(), but omits the sparse checking.
|
|
|
|
* This allows rcu_dereference_index_check() to be used on integers,
|
|
|
|
* which can then be used as array indices. Attempting to use
|
|
|
|
* rcu_dereference_check() on an integer will give compiler warnings
|
|
|
|
* because the sparse address-space mechanism relies on dereferencing
|
|
|
|
* the RCU-protected pointer. Dereferencing integers is not something
|
|
|
|
* that even gcc will put up with.
|
|
|
|
*
|
|
|
|
* Note that this function does not implicitly check for RCU read-side
|
|
|
|
* critical sections. If this function gains lots of uses, it might
|
|
|
|
* make sense to provide versions for each flavor of RCU, but it does
|
|
|
|
* not make sense as of early 2010.
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_index_check(p, c) \
|
|
|
|
__rcu_dereference_index_check((p), (c))
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_dereference_protected() - fetch RCU pointer when updates prevented
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
* @c: The conditions under which the dereference will take place
|
2010-04-09 16:39:10 -06:00
|
|
|
*
|
|
|
|
* Return the value of the specified RCU-protected pointer, but omit
|
|
|
|
* both the smp_read_barrier_depends() and the ACCESS_ONCE(). This
|
|
|
|
* is useful in cases where update-side locks prevent the value of the
|
|
|
|
* pointer from changing. Please note that this primitive does -not-
|
|
|
|
* prevent the compiler from repeating this reference or combining it
|
|
|
|
* with other references, so it should not be used without protection
|
|
|
|
* of appropriate locks.
|
2010-04-28 15:39:09 -06:00
|
|
|
*
|
|
|
|
* This function is only for update-side use. Using this function
|
|
|
|
* when protected only by rcu_read_lock() will result in infrequent
|
|
|
|
* but very ugly failures.
|
2010-04-09 16:39:10 -06:00
|
|
|
*/
|
|
|
|
#define rcu_dereference_protected(p, c) \
|
2010-04-28 15:39:09 -06:00
|
|
|
__rcu_dereference_protected((p), (c), __rcu)
|
2010-04-09 16:39:10 -06:00
|
|
|
|
2009-08-22 14:56:47 -06:00
|
|
|
|
2010-04-09 16:39:10 -06:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_dereference() - fetch RCU-protected pointer for dereferencing
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
2010-04-09 16:39:10 -06:00
|
|
|
*
|
2010-04-28 15:39:09 -06:00
|
|
|
* This is a simple wrapper around rcu_dereference_check().
|
2010-04-09 16:39:10 -06:00
|
|
|
*/
|
2010-04-28 15:39:09 -06:00
|
|
|
#define rcu_dereference(p) rcu_dereference_check(p, 0)
|
2010-04-09 16:39:10 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
*
|
|
|
|
* Makes rcu_dereference_check() do the dirty work.
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0)
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing
|
|
|
|
* @p: The pointer to read, prior to dereferencing
|
|
|
|
*
|
|
|
|
* Makes rcu_dereference_check() do the dirty work.
|
|
|
|
*/
|
|
|
|
#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0)
|
|
|
|
|
|
|
|
/**
|
|
|
|
* rcu_read_lock() - mark the beginning of an RCU read-side critical section
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
2005-05-01 09:59:04 -06:00
|
|
|
* When synchronize_rcu() is invoked on one CPU while other CPUs
|
2005-04-16 16:20:36 -06:00
|
|
|
* are within RCU read-side critical sections, then the
|
2005-05-01 09:59:04 -06:00
|
|
|
* synchronize_rcu() is guaranteed to block until after all the other
|
2005-04-16 16:20:36 -06:00
|
|
|
* 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
|
2010-07-08 18:38:59 -06:00
|
|
|
* with new RCU read-side critical sections. One way that this can happen
|
2005-04-16 16:20:36 -06:00
|
|
|
* 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.
|
|
|
|
*
|
2010-08-07 22:59:54 -06:00
|
|
|
* You can avoid reading and understanding the next paragraph by
|
|
|
|
* following this rule: don't put anything in an rcu_read_lock() RCU
|
|
|
|
* read-side critical section that would block in a !PREEMPT kernel.
|
|
|
|
* But if you want the full story, read on!
|
|
|
|
*
|
|
|
|
* In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
|
|
|
|
* is illegal to block while in an RCU read-side critical section. In
|
|
|
|
* preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
|
|
|
|
* in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
|
|
|
|
* be preempted, but explicit blocking is illegal. Finally, in preemptible
|
2013-01-10 06:24:49 -07:00
|
|
|
* RCU implementations in real-time (with -rt patchset) kernel builds,
|
2010-08-07 22:59:54 -06:00
|
|
|
* RCU read-side critical sections may be preempted and they may also
|
|
|
|
* block, but only when acquiring spinlocks that are subject to priority
|
|
|
|
* inheritance.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2009-08-22 14:56:47 -06:00
|
|
|
static inline void rcu_read_lock(void)
|
|
|
|
{
|
|
|
|
__rcu_read_lock();
|
|
|
|
__acquire(RCU);
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_acquire(&rcu_lock_map);
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_lock() used illegally while idle");
|
2009-08-22 14:56:47 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2009-09-28 08:46:32 -06:00
|
|
|
|
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_read_unlock() - marks the end of an RCU read-side critical section.
|
2009-09-28 08:46:32 -06:00
|
|
|
*
|
|
|
|
* See rcu_read_lock() for more information.
|
|
|
|
*/
|
2009-08-22 14:56:47 -06:00
|
|
|
static inline void rcu_read_unlock(void)
|
|
|
|
{
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_unlock() used illegally while idle");
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_release(&rcu_lock_map);
|
2009-08-22 14:56:47 -06:00
|
|
|
__release(RCU);
|
|
|
|
__rcu_read_unlock();
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* This is equivalent of rcu_read_lock(), but to be used when updates
|
2010-04-28 15:39:09 -06:00
|
|
|
* are being done using call_rcu_bh() or synchronize_rcu_bh(). Since
|
|
|
|
* both call_rcu_bh() and synchronize_rcu_bh() 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(),
|
|
|
|
* though this should at least be commented to avoid confusing people
|
|
|
|
* reading the code.
|
2011-11-28 11:42:42 -07:00
|
|
|
*
|
|
|
|
* Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh()
|
|
|
|
* must occur in the same context, for example, it is illegal to invoke
|
|
|
|
* rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh()
|
|
|
|
* was invoked from some other task.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2009-08-22 14:56:47 -06:00
|
|
|
static inline void rcu_read_lock_bh(void)
|
|
|
|
{
|
2011-08-01 07:22:11 -06:00
|
|
|
local_bh_disable();
|
2009-08-22 14:56:47 -06:00
|
|
|
__acquire(RCU_BH);
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_acquire(&rcu_bh_lock_map);
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_lock_bh() used illegally while idle");
|
2009-08-22 14:56:47 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
|
|
|
|
*
|
|
|
|
* See rcu_read_lock_bh() for more information.
|
|
|
|
*/
|
2009-08-22 14:56:47 -06:00
|
|
|
static inline void rcu_read_unlock_bh(void)
|
|
|
|
{
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_unlock_bh() used illegally while idle");
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_release(&rcu_bh_lock_map);
|
2009-08-22 14:56:47 -06:00
|
|
|
__release(RCU_BH);
|
2011-08-01 07:22:11 -06:00
|
|
|
local_bh_enable();
|
2009-08-22 14:56:47 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-09-29 09:06:46 -06:00
|
|
|
/**
|
2010-04-28 15:39:09 -06:00
|
|
|
* rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
|
2008-09-29 09:06:46 -06:00
|
|
|
*
|
2010-04-28 15:39:09 -06:00
|
|
|
* This is equivalent of rcu_read_lock(), but to be used when updates
|
|
|
|
* are being done using call_rcu_sched() or synchronize_rcu_sched().
|
|
|
|
* Read-side critical sections can also be introduced by anything that
|
|
|
|
* disables preemption, including local_irq_disable() and friends.
|
2011-11-28 11:42:42 -07:00
|
|
|
*
|
|
|
|
* Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched()
|
|
|
|
* must occur in the same context, for example, it is illegal to invoke
|
|
|
|
* rcu_read_unlock_sched() from process context if the matching
|
|
|
|
* rcu_read_lock_sched() was invoked from an NMI handler.
|
2008-09-29 09:06:46 -06:00
|
|
|
*/
|
2009-08-22 14:56:46 -06:00
|
|
|
static inline void rcu_read_lock_sched(void)
|
|
|
|
{
|
|
|
|
preempt_disable();
|
2009-08-22 14:56:47 -06:00
|
|
|
__acquire(RCU_SCHED);
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_acquire(&rcu_sched_lock_map);
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_lock_sched() used illegally while idle");
|
2009-08-22 14:56:46 -06:00
|
|
|
}
|
2009-09-23 10:50:42 -06:00
|
|
|
|
|
|
|
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
|
2009-08-24 10:42:00 -06:00
|
|
|
static inline notrace void rcu_read_lock_sched_notrace(void)
|
2009-08-22 14:56:46 -06:00
|
|
|
{
|
|
|
|
preempt_disable_notrace();
|
2009-08-22 14:56:47 -06:00
|
|
|
__acquire(RCU_SCHED);
|
2009-08-22 14:56:46 -06:00
|
|
|
}
|
2008-09-29 09:06:46 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* rcu_read_unlock_sched - marks the end of a RCU-classic critical section
|
|
|
|
*
|
|
|
|
* See rcu_read_lock_sched for more information.
|
|
|
|
*/
|
2009-08-22 14:56:46 -06:00
|
|
|
static inline void rcu_read_unlock_sched(void)
|
|
|
|
{
|
2013-09-13 18:20:11 -06:00
|
|
|
rcu_lockdep_assert(rcu_is_watching(),
|
2012-02-01 11:30:46 -07:00
|
|
|
"rcu_read_unlock_sched() used illegally while idle");
|
2011-10-07 10:22:03 -06:00
|
|
|
rcu_lock_release(&rcu_sched_lock_map);
|
2009-08-22 14:56:47 -06:00
|
|
|
__release(RCU_SCHED);
|
2009-08-22 14:56:46 -06:00
|
|
|
preempt_enable();
|
|
|
|
}
|
2009-09-23 10:50:42 -06:00
|
|
|
|
|
|
|
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
|
2009-08-24 10:42:00 -06:00
|
|
|
static inline notrace void rcu_read_unlock_sched_notrace(void)
|
2009-08-22 14:56:46 -06:00
|
|
|
{
|
2009-08-22 14:56:47 -06:00
|
|
|
__release(RCU_SCHED);
|
2009-08-22 14:56:46 -06:00
|
|
|
preempt_enable_notrace();
|
|
|
|
}
|
2008-09-29 09:06:46 -06:00
|
|
|
|
2010-04-28 15:39:09 -06:00
|
|
|
/**
|
|
|
|
* RCU_INIT_POINTER() - initialize an RCU protected pointer
|
|
|
|
*
|
2011-07-31 23:33:02 -06:00
|
|
|
* Initialize an RCU-protected pointer in special cases where readers
|
|
|
|
* do not need ordering constraints on the CPU or the compiler. These
|
|
|
|
* special cases are:
|
|
|
|
*
|
|
|
|
* 1. This use of RCU_INIT_POINTER() is NULLing out the pointer -or-
|
|
|
|
* 2. The caller has taken whatever steps are required to prevent
|
|
|
|
* RCU readers from concurrently accessing this pointer -or-
|
|
|
|
* 3. The referenced data structure has already been exposed to
|
|
|
|
* readers either at compile time or via rcu_assign_pointer() -and-
|
|
|
|
* a. You have not made -any- reader-visible changes to
|
|
|
|
* this structure since then -or-
|
|
|
|
* b. It is OK for readers accessing this structure from its
|
|
|
|
* new location to see the old state of the structure. (For
|
|
|
|
* example, the changes were to statistical counters or to
|
|
|
|
* other state where exact synchronization is not required.)
|
|
|
|
*
|
|
|
|
* Failure to follow these rules governing use of RCU_INIT_POINTER() will
|
|
|
|
* result in impossible-to-diagnose memory corruption. As in the structures
|
|
|
|
* will look OK in crash dumps, but any concurrent RCU readers might
|
|
|
|
* see pre-initialized values of the referenced data structure. So
|
|
|
|
* please be very careful how you use RCU_INIT_POINTER()!!!
|
|
|
|
*
|
|
|
|
* If you are creating an RCU-protected linked structure that is accessed
|
|
|
|
* by a single external-to-structure RCU-protected pointer, then you may
|
|
|
|
* use RCU_INIT_POINTER() to initialize the internal RCU-protected
|
|
|
|
* pointers, but you must use rcu_assign_pointer() to initialize the
|
|
|
|
* external-to-structure pointer -after- you have completely initialized
|
|
|
|
* the reader-accessible portions of the linked structure.
|
2010-04-28 15:39:09 -06:00
|
|
|
*/
|
|
|
|
#define RCU_INIT_POINTER(p, v) \
|
2012-05-16 16:42:30 -06:00
|
|
|
do { \
|
2013-11-11 10:59:34 -07:00
|
|
|
p = RCU_INITIALIZER(v); \
|
2012-05-16 16:42:30 -06:00
|
|
|
} while (0)
|
rcu: introduce kfree_rcu()
Many rcu callbacks functions just call kfree() on the base structure.
These functions are trivial, but their size adds up, and furthermore
when they are used in a kernel module, that module must invoke the
high-latency rcu_barrier() function at module-unload time.
The kfree_rcu() function introduced by this commit addresses this issue.
Rather than encoding a function address in the embedded rcu_head
structure, kfree_rcu() instead encodes the offset of the rcu_head
structure within the base structure. Because the functions are not
allowed in the low-order 4096 bytes of kernel virtual memory, offsets
up to 4095 bytes can be accommodated. If the offset is larger than
4095 bytes, a compile-time error will be generated in __kfree_rcu().
If this error is triggered, you can either fall back to use of call_rcu()
or rearrange the structure to position the rcu_head structure into the
first 4096 bytes.
Note that the allowable offset might decrease in the future, for example,
to allow something like kmem_cache_free_rcu().
The new kfree_rcu() function can replace code as follows:
call_rcu(&p->rcu, simple_kfree_callback);
where "simple_kfree_callback()" might be defined as follows:
void simple_kfree_callback(struct rcu_head *p)
{
struct foo *q = container_of(p, struct foo, rcu);
kfree(q);
}
with the following:
kfree_rcu(&p->rcu, rcu);
Note that the "rcu" is the name of a field in the structure being
freed. The reason for using this rather than passing in a pointer
to the base structure is that the above approach allows better type
checking.
This commit is based on earlier work by Lai Jiangshan and Manfred Spraul:
Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1
Manfred's patch: http://lkml.org/lkml/2009/1/2/115
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-03-17 21:15:47 -06:00
|
|
|
|
2012-05-16 16:23:45 -06:00
|
|
|
/**
|
|
|
|
* RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer
|
|
|
|
*
|
|
|
|
* GCC-style initialization for an RCU-protected pointer in a structure field.
|
|
|
|
*/
|
|
|
|
#define RCU_POINTER_INITIALIZER(p, v) \
|
2013-11-11 10:59:34 -07:00
|
|
|
.p = RCU_INITIALIZER(v)
|
rcu: introduce kfree_rcu()
Many rcu callbacks functions just call kfree() on the base structure.
These functions are trivial, but their size adds up, and furthermore
when they are used in a kernel module, that module must invoke the
high-latency rcu_barrier() function at module-unload time.
The kfree_rcu() function introduced by this commit addresses this issue.
Rather than encoding a function address in the embedded rcu_head
structure, kfree_rcu() instead encodes the offset of the rcu_head
structure within the base structure. Because the functions are not
allowed in the low-order 4096 bytes of kernel virtual memory, offsets
up to 4095 bytes can be accommodated. If the offset is larger than
4095 bytes, a compile-time error will be generated in __kfree_rcu().
If this error is triggered, you can either fall back to use of call_rcu()
or rearrange the structure to position the rcu_head structure into the
first 4096 bytes.
Note that the allowable offset might decrease in the future, for example,
to allow something like kmem_cache_free_rcu().
The new kfree_rcu() function can replace code as follows:
call_rcu(&p->rcu, simple_kfree_callback);
where "simple_kfree_callback()" might be defined as follows:
void simple_kfree_callback(struct rcu_head *p)
{
struct foo *q = container_of(p, struct foo, rcu);
kfree(q);
}
with the following:
kfree_rcu(&p->rcu, rcu);
Note that the "rcu" is the name of a field in the structure being
freed. The reason for using this rather than passing in a pointer
to the base structure is that the above approach allows better type
checking.
This commit is based on earlier work by Lai Jiangshan and Manfred Spraul:
Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1
Manfred's patch: http://lkml.org/lkml/2009/1/2/115
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-03-17 21:15:47 -06:00
|
|
|
|
2012-04-19 12:44:39 -06:00
|
|
|
/*
|
|
|
|
* Does the specified offset indicate that the corresponding rcu_head
|
|
|
|
* structure can be handled by kfree_rcu()?
|
|
|
|
*/
|
|
|
|
#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
|
|
|
|
*/
|
|
|
|
#define __kfree_rcu(head, offset) \
|
|
|
|
do { \
|
|
|
|
BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
|
2012-06-05 16:53:53 -06:00
|
|
|
kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
|
2012-04-19 12:44:39 -06:00
|
|
|
} while (0)
|
|
|
|
|
rcu: introduce kfree_rcu()
Many rcu callbacks functions just call kfree() on the base structure.
These functions are trivial, but their size adds up, and furthermore
when they are used in a kernel module, that module must invoke the
high-latency rcu_barrier() function at module-unload time.
The kfree_rcu() function introduced by this commit addresses this issue.
Rather than encoding a function address in the embedded rcu_head
structure, kfree_rcu() instead encodes the offset of the rcu_head
structure within the base structure. Because the functions are not
allowed in the low-order 4096 bytes of kernel virtual memory, offsets
up to 4095 bytes can be accommodated. If the offset is larger than
4095 bytes, a compile-time error will be generated in __kfree_rcu().
If this error is triggered, you can either fall back to use of call_rcu()
or rearrange the structure to position the rcu_head structure into the
first 4096 bytes.
Note that the allowable offset might decrease in the future, for example,
to allow something like kmem_cache_free_rcu().
The new kfree_rcu() function can replace code as follows:
call_rcu(&p->rcu, simple_kfree_callback);
where "simple_kfree_callback()" might be defined as follows:
void simple_kfree_callback(struct rcu_head *p)
{
struct foo *q = container_of(p, struct foo, rcu);
kfree(q);
}
with the following:
kfree_rcu(&p->rcu, rcu);
Note that the "rcu" is the name of a field in the structure being
freed. The reason for using this rather than passing in a pointer
to the base structure is that the above approach allows better type
checking.
This commit is based on earlier work by Lai Jiangshan and Manfred Spraul:
Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1
Manfred's patch: http://lkml.org/lkml/2009/1/2/115
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-03-17 21:15:47 -06:00
|
|
|
/**
|
|
|
|
* kfree_rcu() - kfree an object after a grace period.
|
|
|
|
* @ptr: pointer to kfree
|
|
|
|
* @rcu_head: the name of the struct rcu_head within the type of @ptr.
|
|
|
|
*
|
|
|
|
* Many rcu callbacks functions just call kfree() on the base structure.
|
|
|
|
* These functions are trivial, but their size adds up, and furthermore
|
|
|
|
* when they are used in a kernel module, that module must invoke the
|
|
|
|
* high-latency rcu_barrier() function at module-unload time.
|
|
|
|
*
|
|
|
|
* The kfree_rcu() function handles this issue. Rather than encoding a
|
|
|
|
* function address in the embedded rcu_head structure, kfree_rcu() instead
|
|
|
|
* encodes the offset of the rcu_head structure within the base structure.
|
|
|
|
* Because the functions are not allowed in the low-order 4096 bytes of
|
|
|
|
* kernel virtual memory, offsets up to 4095 bytes can be accommodated.
|
|
|
|
* If the offset is larger than 4095 bytes, a compile-time error will
|
|
|
|
* be generated in __kfree_rcu(). If this error is triggered, you can
|
|
|
|
* either fall back to use of call_rcu() or rearrange the structure to
|
|
|
|
* position the rcu_head structure into the first 4096 bytes.
|
|
|
|
*
|
|
|
|
* Note that the allowable offset might decrease in the future, for example,
|
|
|
|
* to allow something like kmem_cache_free_rcu().
|
2012-04-19 12:44:39 -06:00
|
|
|
*
|
|
|
|
* The BUILD_BUG_ON check must not involve any function calls, hence the
|
|
|
|
* checks are done in macros here.
|
rcu: introduce kfree_rcu()
Many rcu callbacks functions just call kfree() on the base structure.
These functions are trivial, but their size adds up, and furthermore
when they are used in a kernel module, that module must invoke the
high-latency rcu_barrier() function at module-unload time.
The kfree_rcu() function introduced by this commit addresses this issue.
Rather than encoding a function address in the embedded rcu_head
structure, kfree_rcu() instead encodes the offset of the rcu_head
structure within the base structure. Because the functions are not
allowed in the low-order 4096 bytes of kernel virtual memory, offsets
up to 4095 bytes can be accommodated. If the offset is larger than
4095 bytes, a compile-time error will be generated in __kfree_rcu().
If this error is triggered, you can either fall back to use of call_rcu()
or rearrange the structure to position the rcu_head structure into the
first 4096 bytes.
Note that the allowable offset might decrease in the future, for example,
to allow something like kmem_cache_free_rcu().
The new kfree_rcu() function can replace code as follows:
call_rcu(&p->rcu, simple_kfree_callback);
where "simple_kfree_callback()" might be defined as follows:
void simple_kfree_callback(struct rcu_head *p)
{
struct foo *q = container_of(p, struct foo, rcu);
kfree(q);
}
with the following:
kfree_rcu(&p->rcu, rcu);
Note that the "rcu" is the name of a field in the structure being
freed. The reason for using this rather than passing in a pointer
to the base structure is that the above approach allows better type
checking.
This commit is based on earlier work by Lai Jiangshan and Manfred Spraul:
Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1
Manfred's patch: http://lkml.org/lkml/2009/1/2/115
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-03-17 21:15:47 -06:00
|
|
|
*/
|
|
|
|
#define kfree_rcu(ptr, rcu_head) \
|
|
|
|
__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
|
|
|
|
|
2013-11-17 20:27:16 -07:00
|
|
|
#if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL)
|
|
|
|
static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
|
|
|
|
{
|
|
|
|
*delta_jiffies = ULONG_MAX;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* #if defined(CONFIG_TINY_RCU) || defined(CONFIG_RCU_NOCB_CPU_ALL) */
|
|
|
|
|
2013-11-17 19:25:48 -07:00
|
|
|
#if defined(CONFIG_RCU_NOCB_CPU_ALL)
|
|
|
|
static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
|
|
|
|
#elif defined(CONFIG_RCU_NOCB_CPU)
|
2013-11-11 08:11:23 -07:00
|
|
|
bool rcu_is_nocb_cpu(int cpu);
|
2013-03-26 16:47:24 -06:00
|
|
|
#else
|
|
|
|
static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
|
2013-11-17 19:25:48 -07:00
|
|
|
#endif
|
2013-03-26 16:47:24 -06:00
|
|
|
|
|
|
|
|
2013-06-21 17:37:22 -06:00
|
|
|
/* Only for use by adaptive-ticks code. */
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
|
2013-11-11 08:11:23 -07:00
|
|
|
bool rcu_sys_is_idle(void);
|
|
|
|
void rcu_sysidle_force_exit(void);
|
2013-06-21 17:37:22 -06:00
|
|
|
#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
|
|
|
|
|
|
|
|
static inline bool rcu_sys_is_idle(void)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void rcu_sysidle_force_exit(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
|
|
|
|
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#endif /* __LINUX_RCUPDATE_H */
|