8b6490e5fa
First of a number of files_lock scaability patches. Here are the x86 numbers - tiobench on a 4(8)-way (HT) P4 system on ramdisk : (lockfree) Test 2.6.10-vanilla Stdev 2.6.10-fd Stdev ------------------------------------------------------------- Seqread 1400.8 11.52 1465.4 34.27 Randread 1594 8.86 2397.2 29.21 Seqwrite 242.72 3.47 238.46 6.53 Randwrite 445.74 9.15 446.4 9.75 The performance improvement is very significant. We are getting killed by the cacheline bouncing of the files_struct lock here. Writes on ramdisk (ext2) seems to vary just too much to get any meaningful number. Also, With Tridge's thread_perf test on a 4(8)-way (HT) P4 xeon system : 2.6.12-rc5-vanilla : Running test 'readwrite' with 8 tasks Threads 0.34 +/- 0.01 seconds Processes 0.16 +/- 0.00 seconds 2.6.12-rc5-fd : Running test 'readwrite' with 8 tasks Threads 0.17 +/- 0.02 seconds Processes 0.17 +/- 0.02 seconds I repeated the measurements on ramfs (as opposed to ext2 on ramdisk in the earlier measurement) and I got more consistent results from tiobench : 4(8) way xeon P4 ----------------- (lock-free) Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev ------------------------------------------------------------- Seqread 1282 18.59 1343.6 26.37 Randread 1517 7 2415 34.27 Seqwrite 702.2 5.27 709.46 5.9 Randwrite 846.86 15.15 919.68 21.4 4-way ppc64 ------------ (lock-free) Test 2.6.12-rc5 Stdev 2.6.12-rc5-fd Stdev ------------------------------------------------------------- Seqread 1549 91.16 1569.6 47.2 Randread 1473.6 25.11 1585.4 69.99 Seqwrite 1096.8 20.03 1136 29.61 Randwrite 1189.6 4.04 1275.2 32.96 Also running Tridge's thread_perf test on ppc64 : 2.6.12-rc5-vanilla -------------------- Running test 'readwrite' with 4 tasks Threads 0.20 +/- 0.02 seconds Processes 0.16 +/- 0.01 seconds 2.6.12-rc5-fd -------------------- Running test 'readwrite' with 4 tasks Threads 0.18 +/- 0.04 seconds Processes 0.16 +/- 0.01 seconds The benefits are huge (upto ~60%) in some cases on x86 primarily due to the atomic operations during acquisition of ->file_lock and cache line bouncing in fast path. ppc64 benefits are modest due to LL/SC based locking, but still statistically significant. This patch: RCU head initilizer no longer needs the head varible name since we don't use list.h lists anymore. Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
288 lines
9.6 KiB
C
288 lines
9.6 KiB
C
/*
|
|
* Read-Copy Update mechanism for mutual exclusion
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
*
|
|
* Copyright (C) IBM Corporation, 2001
|
|
*
|
|
* Author: Dipankar Sarma <dipankar@in.ibm.com>
|
|
*
|
|
* Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
|
|
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
|
|
* Papers:
|
|
* http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
|
|
* http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
|
|
*
|
|
* For detailed explanation of Read-Copy Update mechanism see -
|
|
* http://lse.sourceforge.net/locking/rcupdate.html
|
|
*
|
|
*/
|
|
|
|
#ifndef __LINUX_RCUPDATE_H
|
|
#define __LINUX_RCUPDATE_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/cache.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/seqlock.h>
|
|
|
|
/**
|
|
* struct rcu_head - callback structure for use with RCU
|
|
* @next: next update requests in a list
|
|
* @func: actual update function to call after the grace period.
|
|
*/
|
|
struct rcu_head {
|
|
struct rcu_head *next;
|
|
void (*func)(struct rcu_head *head);
|
|
};
|
|
|
|
#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
|
|
#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
|
|
#define INIT_RCU_HEAD(ptr) do { \
|
|
(ptr)->next = NULL; (ptr)->func = NULL; \
|
|
} while (0)
|
|
|
|
|
|
|
|
/* Global control variables for rcupdate callback mechanism. */
|
|
struct rcu_ctrlblk {
|
|
long cur; /* Current batch number. */
|
|
long completed; /* Number of the last completed batch */
|
|
int next_pending; /* Is the next batch already waiting? */
|
|
} ____cacheline_maxaligned_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;
|
|
}
|
|
|
|
/*
|
|
* Per-CPU data for Read-Copy UPdate.
|
|
* nxtlist - new callbacks are added here
|
|
* curlist - current batch for which quiescent cycle started if any
|
|
*/
|
|
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 */
|
|
long batch; /* Batch # for current RCU batch */
|
|
struct rcu_head *nxtlist;
|
|
struct rcu_head **nxttail;
|
|
struct rcu_head *curlist;
|
|
struct rcu_head **curtail;
|
|
struct rcu_head *donelist;
|
|
struct rcu_head **donetail;
|
|
int cpu;
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_data);
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
|
|
extern struct rcu_ctrlblk rcu_ctrlblk;
|
|
extern struct rcu_ctrlblk rcu_bh_ctrlblk;
|
|
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
static inline int __rcu_pending(struct rcu_ctrlblk *rcp,
|
|
struct rcu_data *rdp)
|
|
{
|
|
/* This cpu has pending rcu entries and the grace period
|
|
* for them has completed.
|
|
*/
|
|
if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
|
|
return 1;
|
|
|
|
/* This cpu has no pending entries, but there are new entries */
|
|
if (!rdp->curlist && rdp->nxtlist)
|
|
return 1;
|
|
|
|
/* This cpu has finished callbacks to invoke */
|
|
if (rdp->donelist)
|
|
return 1;
|
|
|
|
/* The rcu core waits for a quiescent state from the cpu */
|
|
if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
|
|
return 1;
|
|
|
|
/* nothing to do */
|
|
return 0;
|
|
}
|
|
|
|
static inline int rcu_pending(int cpu)
|
|
{
|
|
return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
|
|
__rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
|
|
}
|
|
|
|
/**
|
|
* rcu_read_lock - mark the beginning of an RCU read-side critical section.
|
|
*
|
|
* When synchronize_rcu() is invoked on one CPU while other CPUs
|
|
* are within RCU read-side critical sections, then the
|
|
* synchronize_rcu() is guaranteed to block until after all the other
|
|
* CPUs exit their critical sections. Similarly, if call_rcu() is invoked
|
|
* on one CPU while other CPUs are within RCU read-side critical
|
|
* sections, invocation of the corresponding RCU callback is deferred
|
|
* until after the all the other CPUs exit their critical sections.
|
|
*
|
|
* Note, however, that RCU callbacks are permitted to run concurrently
|
|
* with RCU read-side critical sections. One way that this can happen
|
|
* is via the following sequence of events: (1) CPU 0 enters an RCU
|
|
* read-side critical section, (2) CPU 1 invokes call_rcu() to register
|
|
* an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
|
|
* (4) CPU 2 enters a RCU read-side critical section, (5) the RCU
|
|
* callback is invoked. This is legal, because the RCU read-side critical
|
|
* section that was running concurrently with the call_rcu() (and which
|
|
* therefore might be referencing something that the corresponding RCU
|
|
* callback would free up) has completed before the corresponding
|
|
* RCU callback is invoked.
|
|
*
|
|
* RCU read-side critical sections may be nested. Any deferred actions
|
|
* will be deferred until the outermost RCU read-side critical section
|
|
* completes.
|
|
*
|
|
* It is illegal to block while in an RCU read-side critical section.
|
|
*/
|
|
#define rcu_read_lock() preempt_disable()
|
|
|
|
/**
|
|
* rcu_read_unlock - marks the end of an RCU read-side critical section.
|
|
*
|
|
* See rcu_read_lock() for more information.
|
|
*/
|
|
#define rcu_read_unlock() preempt_enable()
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
/**
|
|
* rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
|
|
*
|
|
* This is equivalent of rcu_read_lock(), but to be used when updates
|
|
* are being done using call_rcu_bh(). Since call_rcu_bh() callbacks
|
|
* consider completion of a softirq handler to be a quiescent state,
|
|
* a process in RCU read-side critical section must be protected by
|
|
* disabling softirqs. Read-side critical sections in interrupt context
|
|
* can use just rcu_read_lock().
|
|
*
|
|
*/
|
|
#define rcu_read_lock_bh() local_bh_disable()
|
|
|
|
/*
|
|
* rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
|
|
*
|
|
* See rcu_read_lock_bh() for more information.
|
|
*/
|
|
#define rcu_read_unlock_bh() local_bh_enable()
|
|
|
|
/**
|
|
* rcu_dereference - fetch an RCU-protected pointer in an
|
|
* RCU read-side critical section. This pointer may later
|
|
* be safely dereferenced.
|
|
*
|
|
* Inserts memory barriers on architectures that require them
|
|
* (currently only the Alpha), and, more importantly, documents
|
|
* exactly which pointers are protected by RCU.
|
|
*/
|
|
|
|
#define rcu_dereference(p) ({ \
|
|
typeof(p) _________p1 = p; \
|
|
smp_read_barrier_depends(); \
|
|
(_________p1); \
|
|
})
|
|
|
|
/**
|
|
* rcu_assign_pointer - assign (publicize) a pointer to a newly
|
|
* initialized structure that will be dereferenced by RCU read-side
|
|
* critical sections. Returns the value assigned.
|
|
*
|
|
* Inserts memory barriers on architectures that require them
|
|
* (pretty much all of them other than x86), and also prevents
|
|
* the compiler from reordering the code that initializes the
|
|
* structure after the pointer assignment. More importantly, this
|
|
* call documents which pointers will be dereferenced by RCU read-side
|
|
* code.
|
|
*/
|
|
|
|
#define rcu_assign_pointer(p, v) ({ \
|
|
smp_wmb(); \
|
|
(p) = (v); \
|
|
})
|
|
|
|
/**
|
|
* synchronize_sched - block until all CPUs have exited any non-preemptive
|
|
* kernel code sequences.
|
|
*
|
|
* This means that all preempt_disable code sequences, including NMI and
|
|
* hardware-interrupt handlers, in progress on entry will have completed
|
|
* before this primitive returns. However, this does not guarantee that
|
|
* softirq handlers will have completed, since in some kernels
|
|
*
|
|
* This primitive provides the guarantees made by the (deprecated)
|
|
* synchronize_kernel() API. In contrast, synchronize_rcu() only
|
|
* guarantees that rcu_read_lock() sections will have completed.
|
|
*/
|
|
#define synchronize_sched() synchronize_rcu()
|
|
|
|
extern void rcu_init(void);
|
|
extern void rcu_check_callbacks(int cpu, int user);
|
|
extern void rcu_restart_cpu(int cpu);
|
|
|
|
/* Exported interfaces */
|
|
extern void FASTCALL(call_rcu(struct rcu_head *head,
|
|
void (*func)(struct rcu_head *head)));
|
|
extern void FASTCALL(call_rcu_bh(struct rcu_head *head,
|
|
void (*func)(struct rcu_head *head)));
|
|
extern __deprecated_for_modules void synchronize_kernel(void);
|
|
extern void synchronize_rcu(void);
|
|
void synchronize_idle(void);
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* __LINUX_RCUPDATE_H */
|