2008-01-25 13:08:24 -07:00
|
|
|
/*
|
|
|
|
* Read-Copy Update mechanism for mutual exclusion (classic version)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
* (at your option) any later version.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
|
|
*
|
|
|
|
* Copyright IBM Corporation, 2001
|
|
|
|
*
|
|
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.com>
|
|
|
|
*
|
|
|
|
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
|
|
|
|
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
|
|
|
|
* Papers:
|
|
|
|
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
|
|
|
|
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
|
|
|
|
*
|
|
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
|
|
* Documentation/RCU
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __LINUX_RCUCLASSIC_H
|
|
|
|
#define __LINUX_RCUCLASSIC_H
|
|
|
|
|
|
|
|
#include <linux/cache.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/threads.h>
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
#include <linux/seqlock.h>
|
|
|
|
|
2008-10-02 17:06:39 -06:00
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
2008-11-03 10:16:39 -07:00
|
|
|
#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rcp->jiffies_stall */
|
2008-10-02 17:06:39 -06:00
|
|
|
#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rcp->jiffies_stall */
|
|
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
2008-01-25 13:08:24 -07:00
|
|
|
|
|
|
|
/* Global control variables for rcupdate callback mechanism. */
|
|
|
|
struct rcu_ctrlblk {
|
|
|
|
long cur; /* Current batch number. */
|
|
|
|
long completed; /* Number of the last completed batch */
|
2008-07-06 03:23:55 -06:00
|
|
|
long pending; /* Number of the last pending batch */
|
2008-10-02 17:06:39 -06:00
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
|
|
|
unsigned long gp_start; /* Time at which GP started in jiffies. */
|
|
|
|
unsigned long jiffies_stall;
|
|
|
|
/* Time at which to check for CPU stalls. */
|
|
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
2008-01-25 13:08:24 -07:00
|
|
|
|
|
|
|
int signaled;
|
|
|
|
|
|
|
|
spinlock_t lock ____cacheline_internodealigned_in_smp;
|
|
|
|
cpumask_t cpumask; /* CPUs that need to switch in order */
|
|
|
|
/* for current batch to proceed. */
|
|
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
|
|
|
|
/* Is batch a before batch b ? */
|
|
|
|
static inline int rcu_batch_before(long a, long b)
|
|
|
|
{
|
|
|
|
return (a - b) < 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Is batch a after batch b ? */
|
|
|
|
static inline int rcu_batch_after(long a, long b)
|
|
|
|
{
|
|
|
|
return (a - b) > 0;
|
|
|
|
}
|
|
|
|
|
rcu classic: new algorithm for callbacks-processing(v2)
This is v2, it's a little deference from v1 that I
had send to lkml.
use ACCESS_ONCE
use rcu_batch_after/rcu_batch_before for batch # comparison.
rcutorture test result:
(hotplugs: do cpu-online/offline once per second)
No CONFIG_NO_HZ: OK, 12hours
No CONFIG_NO_HZ, hotplugs: OK, 12hours
CONFIG_NO_HZ=y: OK, 24hours
CONFIG_NO_HZ=y, hotplugs: Failed.
(Failed also without my patch applied, exactly the same bug occurred,
http://lkml.org/lkml/2008/7/3/24)
v1's email thread:
http://lkml.org/lkml/2008/6/2/539
v1's description:
The code/algorithm of the implement of current callbacks-processing
is very efficient and technical. But when I studied it and I found
a disadvantage:
In multi-CPU systems, when a new RCU callback is being
queued(call_rcu[_bh]), this callback will be invoked after the grace
period for the batch with batch number = rcp->cur+2 has completed
very very likely in current implement. Actually, this callback can be
invoked after the grace period for the batch with
batch number = rcp->cur+1 has completed. The delay of invocation means
that latency of synchronize_rcu() is extended. But more important thing
is that the callbacks usually free memory, and these works are delayed
too! it's necessary for reclaimer to free memory as soon as
possible when left memory is few.
A very simple way can solve this problem:
a field(struct rcu_head::batch) is added to record the batch number for
the RCU callback. And when a new RCU callback is being queued, we
determine the batch number for this callback(head->batch = rcp->cur+1)
and we move this callback to rdp->donelist if we find
that head->batch <= rcp->completed when we process callbacks.
This simple way reduces the wait time for invocation a lot. (about
2.5Grace Period -> 1.5Grace Period in average in multi-CPU systems)
This is my algorithm. But I do not add any field for struct rcu_head
in my implement. We just need to memorize the last 2 batches and
their batch number, because these 2 batches include all entries that
for whom the grace period hasn't completed. So we use a special
linked-list rather than add a field.
Please see the comment of struct rcu_data.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Gautham Shenoy <ego@in.ibm.com>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-06 03:23:59 -06:00
|
|
|
/* Per-CPU data for Read-Copy UPdate. */
|
2008-01-25 13:08:24 -07:00
|
|
|
struct rcu_data {
|
|
|
|
/* 1) quiescent state handling : */
|
|
|
|
long quiescbatch; /* Batch # for grace period */
|
|
|
|
int passed_quiesc; /* User-mode/idle loop etc. */
|
|
|
|
int qs_pending; /* core waits for quiesc state */
|
|
|
|
|
|
|
|
/* 2) batch handling */
|
rcu classic: new algorithm for callbacks-processing(v2)
This is v2, it's a little deference from v1 that I
had send to lkml.
use ACCESS_ONCE
use rcu_batch_after/rcu_batch_before for batch # comparison.
rcutorture test result:
(hotplugs: do cpu-online/offline once per second)
No CONFIG_NO_HZ: OK, 12hours
No CONFIG_NO_HZ, hotplugs: OK, 12hours
CONFIG_NO_HZ=y: OK, 24hours
CONFIG_NO_HZ=y, hotplugs: Failed.
(Failed also without my patch applied, exactly the same bug occurred,
http://lkml.org/lkml/2008/7/3/24)
v1's email thread:
http://lkml.org/lkml/2008/6/2/539
v1's description:
The code/algorithm of the implement of current callbacks-processing
is very efficient and technical. But when I studied it and I found
a disadvantage:
In multi-CPU systems, when a new RCU callback is being
queued(call_rcu[_bh]), this callback will be invoked after the grace
period for the batch with batch number = rcp->cur+2 has completed
very very likely in current implement. Actually, this callback can be
invoked after the grace period for the batch with
batch number = rcp->cur+1 has completed. The delay of invocation means
that latency of synchronize_rcu() is extended. But more important thing
is that the callbacks usually free memory, and these works are delayed
too! it's necessary for reclaimer to free memory as soon as
possible when left memory is few.
A very simple way can solve this problem:
a field(struct rcu_head::batch) is added to record the batch number for
the RCU callback. And when a new RCU callback is being queued, we
determine the batch number for this callback(head->batch = rcp->cur+1)
and we move this callback to rdp->donelist if we find
that head->batch <= rcp->completed when we process callbacks.
This simple way reduces the wait time for invocation a lot. (about
2.5Grace Period -> 1.5Grace Period in average in multi-CPU systems)
This is my algorithm. But I do not add any field for struct rcu_head
in my implement. We just need to memorize the last 2 batches and
their batch number, because these 2 batches include all entries that
for whom the grace period hasn't completed. So we use a special
linked-list rather than add a field.
Please see the comment of struct rcu_data.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Gautham Shenoy <ego@in.ibm.com>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-06 03:23:59 -06:00
|
|
|
/*
|
|
|
|
* if nxtlist is not NULL, then:
|
|
|
|
* batch:
|
|
|
|
* The batch # for the last entry of nxtlist
|
|
|
|
* [*nxttail[1], NULL = *nxttail[2]):
|
|
|
|
* Entries that batch # <= batch
|
|
|
|
* [*nxttail[0], *nxttail[1]):
|
|
|
|
* Entries that batch # <= batch - 1
|
|
|
|
* [nxtlist, *nxttail[0]):
|
|
|
|
* Entries that batch # <= batch - 2
|
|
|
|
* The grace period for these entries has completed, and
|
|
|
|
* the other grace-period-completed entries may be moved
|
|
|
|
* here temporarily in rcu_process_callbacks().
|
|
|
|
*/
|
|
|
|
long batch;
|
2008-01-25 13:08:24 -07:00
|
|
|
struct rcu_head *nxtlist;
|
rcu classic: new algorithm for callbacks-processing(v2)
This is v2, it's a little deference from v1 that I
had send to lkml.
use ACCESS_ONCE
use rcu_batch_after/rcu_batch_before for batch # comparison.
rcutorture test result:
(hotplugs: do cpu-online/offline once per second)
No CONFIG_NO_HZ: OK, 12hours
No CONFIG_NO_HZ, hotplugs: OK, 12hours
CONFIG_NO_HZ=y: OK, 24hours
CONFIG_NO_HZ=y, hotplugs: Failed.
(Failed also without my patch applied, exactly the same bug occurred,
http://lkml.org/lkml/2008/7/3/24)
v1's email thread:
http://lkml.org/lkml/2008/6/2/539
v1's description:
The code/algorithm of the implement of current callbacks-processing
is very efficient and technical. But when I studied it and I found
a disadvantage:
In multi-CPU systems, when a new RCU callback is being
queued(call_rcu[_bh]), this callback will be invoked after the grace
period for the batch with batch number = rcp->cur+2 has completed
very very likely in current implement. Actually, this callback can be
invoked after the grace period for the batch with
batch number = rcp->cur+1 has completed. The delay of invocation means
that latency of synchronize_rcu() is extended. But more important thing
is that the callbacks usually free memory, and these works are delayed
too! it's necessary for reclaimer to free memory as soon as
possible when left memory is few.
A very simple way can solve this problem:
a field(struct rcu_head::batch) is added to record the batch number for
the RCU callback. And when a new RCU callback is being queued, we
determine the batch number for this callback(head->batch = rcp->cur+1)
and we move this callback to rdp->donelist if we find
that head->batch <= rcp->completed when we process callbacks.
This simple way reduces the wait time for invocation a lot. (about
2.5Grace Period -> 1.5Grace Period in average in multi-CPU systems)
This is my algorithm. But I do not add any field for struct rcu_head
in my implement. We just need to memorize the last 2 batches and
their batch number, because these 2 batches include all entries that
for whom the grace period hasn't completed. So we use a special
linked-list rather than add a field.
Please see the comment of struct rcu_data.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Gautham Shenoy <ego@in.ibm.com>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-06 03:23:59 -06:00
|
|
|
struct rcu_head **nxttail[3];
|
2008-01-25 13:08:24 -07:00
|
|
|
long qlen; /* # of queued callbacks */
|
|
|
|
struct rcu_head *donelist;
|
|
|
|
struct rcu_head **donetail;
|
|
|
|
long blimit; /* Upper limit on a processed batch */
|
|
|
|
int cpu;
|
|
|
|
struct rcu_head barrier;
|
|
|
|
};
|
|
|
|
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_data);
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Increment the quiescent state counter.
|
|
|
|
* The counter is a bit degenerated: We do not need to know
|
|
|
|
* how many quiescent states passed, just if there was at least
|
|
|
|
* one since the start of the grace period. Thus just a flag.
|
|
|
|
*/
|
|
|
|
static inline void rcu_qsctr_inc(int cpu)
|
|
|
|
{
|
|
|
|
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
|
|
|
|
rdp->passed_quiesc = 1;
|
|
|
|
}
|
|
|
|
static inline void rcu_bh_qsctr_inc(int cpu)
|
|
|
|
{
|
|
|
|
struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
|
|
|
|
rdp->passed_quiesc = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern int rcu_pending(int cpu);
|
|
|
|
extern int rcu_needs_cpu(int cpu);
|
|
|
|
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
|
|
extern struct lockdep_map rcu_lock_map;
|
|
|
|
# define rcu_read_acquire() \
|
lockdep: lock protection locks
On Fri, 2008-08-01 at 16:26 -0700, Linus Torvalds wrote:
> On Fri, 1 Aug 2008, David Miller wrote:
> >
> > Taking more than a few locks of the same class at once is bad
> > news and it's better to find an alternative method.
>
> It's not always wrong.
>
> If you can guarantee that anybody that takes more than one lock of a
> particular class will always take a single top-level lock _first_, then
> that's all good. You can obviously screw up and take the same lock _twice_
> (which will deadlock), but at least you cannot get into ABBA situations.
>
> So maybe the right thing to do is to just teach lockdep about "lock
> protection locks". That would have solved the multi-queue issues for
> networking too - all the actual network drivers would still have taken
> just their single queue lock, but the one case that needs to take all of
> them would have taken a separate top-level lock first.
>
> Never mind that the multi-queue locks were always taken in the same order:
> it's never wrong to just have some top-level serialization, and anybody
> who needs to take <n> locks might as well do <n+1>, because they sure as
> hell aren't going to be on _any_ fastpaths.
>
> So the simplest solution really sounds like just teaching lockdep about
> that one special case. It's not "nesting" exactly, although it's obviously
> related to it.
Do as Linus suggested. The lock protection lock is called nest_lock.
Note that we still have the MAX_LOCK_DEPTH (48) limit to consider, so anything
that spills that it still up shit creek.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 01:30:24 -06:00
|
|
|
lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
|
2008-01-25 13:08:24 -07:00
|
|
|
# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
|
|
|
|
#else
|
|
|
|
# define rcu_read_acquire() do { } while (0)
|
|
|
|
# define rcu_read_release() do { } while (0)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define __rcu_read_lock() \
|
|
|
|
do { \
|
|
|
|
preempt_disable(); \
|
|
|
|
__acquire(RCU); \
|
|
|
|
rcu_read_acquire(); \
|
|
|
|
} while (0)
|
|
|
|
#define __rcu_read_unlock() \
|
|
|
|
do { \
|
|
|
|
rcu_read_release(); \
|
|
|
|
__release(RCU); \
|
|
|
|
preempt_enable(); \
|
|
|
|
} while (0)
|
|
|
|
#define __rcu_read_lock_bh() \
|
|
|
|
do { \
|
|
|
|
local_bh_disable(); \
|
|
|
|
__acquire(RCU_BH); \
|
|
|
|
rcu_read_acquire(); \
|
|
|
|
} while (0)
|
|
|
|
#define __rcu_read_unlock_bh() \
|
|
|
|
do { \
|
|
|
|
rcu_read_release(); \
|
|
|
|
__release(RCU_BH); \
|
|
|
|
local_bh_enable(); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define __synchronize_sched() synchronize_rcu()
|
|
|
|
|
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
|
|
|
#define call_rcu_sched(head, func) call_rcu(head, func)
|
|
|
|
|
2008-01-25 13:08:24 -07:00
|
|
|
extern void __rcu_init(void);
|
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
|
|
|
#define rcu_init_sched() do { } while (0)
|
2008-01-25 13:08:24 -07:00
|
|
|
extern void rcu_check_callbacks(int cpu, int user);
|
|
|
|
extern void rcu_restart_cpu(int cpu);
|
|
|
|
|
2008-01-25 13:08:24 -07:00
|
|
|
extern long rcu_batches_completed(void);
|
|
|
|
extern long rcu_batches_completed_bh(void);
|
|
|
|
|
2008-02-29 10:46:50 -07:00
|
|
|
#define rcu_enter_nohz() do { } while (0)
|
|
|
|
#define rcu_exit_nohz() do { } while (0)
|
|
|
|
|
2008-01-25 13:08:24 -07:00
|
|
|
#endif /* __LINUX_RCUCLASSIC_H */
|