diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 2 | ||||
| -rw-r--r-- | kernel/irq/chip.c | 63 | ||||
| -rw-r--r-- | kernel/irq/migration.c | 34 | ||||
| -rw-r--r-- | kernel/rcupdate.c | 11 | ||||
| -rw-r--r-- | kernel/rcutorture.c | 317 | ||||
| -rw-r--r-- | kernel/srcu.c | 258 | ||||
| -rw-r--r-- | kernel/sys.c | 125 |
7 files changed, 773 insertions, 37 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index d948ca1..5e3f3b7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -8,7 +8,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o latency.o nsproxy.o + hrtimer.o rwsem.o latency.o nsproxy.o srcu.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 736cb0b..4cf65f5 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -18,6 +18,69 @@ #include "internals.h" /** + * dynamic_irq_init - initialize a dynamically allocated irq + * @irq: irq number to initialize + */ +void dynamic_irq_init(unsigned int irq) +{ + struct irq_desc *desc; + unsigned long flags; + + if (irq >= NR_IRQS) { + printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq); + WARN_ON(1); + return; + } + + /* Ensure we don't have left over values from a previous use of this irq */ + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock, flags); + desc->status = IRQ_DISABLED; + desc->chip = &no_irq_chip; + desc->handle_irq = handle_bad_irq; + desc->depth = 1; + desc->handler_data = NULL; + desc->chip_data = NULL; + desc->action = NULL; + desc->irq_count = 0; + desc->irqs_unhandled = 0; +#ifdef CONFIG_SMP + desc->affinity = CPU_MASK_ALL; +#endif + spin_unlock_irqrestore(&desc->lock, flags); +} + +/** + * dynamic_irq_cleanup - cleanup a dynamically allocated irq + * @irq: irq number to initialize + */ +void dynamic_irq_cleanup(unsigned int irq) +{ + struct irq_desc *desc; + unsigned long flags; + + if (irq >= NR_IRQS) { + printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq); + WARN_ON(1); + return; + } + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock, flags); + if (desc->action) { + spin_unlock_irqrestore(&desc->lock, flags); + printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n", + irq); + WARN_ON(1); + return; + } + desc->handle_irq = handle_bad_irq; + desc->chip = &no_irq_chip; + spin_unlock_irqrestore(&desc->lock, flags); +} + + +/** * set_irq_chip - set the irq chip for an irq * @irq: irq number * @chip: pointer to irq chip description structure diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index a57ebe9..4baa3bb 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -7,17 +7,17 @@ void set_pending_irq(unsigned int irq, cpumask_t mask) unsigned long flags; spin_lock_irqsave(&desc->lock, flags); - desc->move_irq = 1; + desc->status |= IRQ_MOVE_PENDING; irq_desc[irq].pending_mask = mask; spin_unlock_irqrestore(&desc->lock, flags); } -void move_native_irq(int irq) +void move_masked_irq(int irq) { struct irq_desc *desc = irq_desc + irq; cpumask_t tmp; - if (likely(!desc->move_irq)) + if (likely(!(desc->status & IRQ_MOVE_PENDING))) return; /* @@ -28,7 +28,7 @@ void move_native_irq(int irq) return; } - desc->move_irq = 0; + desc->status &= ~IRQ_MOVE_PENDING; if (unlikely(cpus_empty(irq_desc[irq].pending_mask))) return; @@ -48,15 +48,29 @@ void move_native_irq(int irq) * when an active trigger is comming in. This could * cause some ioapics to mal-function. * Being paranoid i guess! + * + * For correct operation this depends on the caller + * masking the irqs. */ if (likely(!cpus_empty(tmp))) { - if (likely(!(desc->status & IRQ_DISABLED))) - desc->chip->disable(irq); - desc->chip->set_affinity(irq,tmp); - - if (likely(!(desc->status & IRQ_DISABLED))) - desc->chip->enable(irq); } cpus_clear(irq_desc[irq].pending_mask); } + +void move_native_irq(int irq) +{ + struct irq_desc *desc = irq_desc + irq; + + if (likely(!(desc->status & IRQ_MOVE_PENDING))) + return; + + if (likely(!(desc->status & IRQ_DISABLED))) + desc->chip->disable(irq); + + move_masked_irq(irq); + + if (likely(!(desc->status & IRQ_DISABLED))) + desc->chip->enable(irq); +} + diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 523e464..26bb5ff 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -71,9 +71,6 @@ static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL}; static int blimit = 10; static int qhimark = 10000; static int qlowmark = 100; -#ifdef CONFIG_SMP -static int rsinterval = 1000; -#endif static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); @@ -86,8 +83,8 @@ static void force_quiescent_state(struct rcu_data *rdp, int cpu; cpumask_t cpumask; set_need_resched(); - if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) { - rdp->last_rs_qlen = rdp->qlen; + if (unlikely(!rcp->signaled)) { + rcp->signaled = 1; /* * Don't send IPI to itself. With irqs disabled, * rdp->cpu is the current cpu. @@ -301,6 +298,7 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp) smp_mb(); cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask); + rcp->signaled = 0; } } @@ -628,9 +626,6 @@ void synchronize_rcu(void) module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); -#ifdef CONFIG_SMP -module_param(rsinterval, int, 0); -#endif EXPORT_SYMBOL_GPL(rcu_batches_completed); EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); EXPORT_SYMBOL_GPL(call_rcu); diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 23446e9..e2bda18 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -15,9 +15,10 @@ * 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, 2005 + * Copyright (C) IBM Corporation, 2005, 2006 * * Authors: Paul E. McKenney <paulmck@us.ibm.com> + * Josh Triplett <josh@freedesktop.org> * * See also: Documentation/RCU/torture.txt */ @@ -44,19 +45,25 @@ #include <linux/delay.h> #include <linux/byteorder/swabb.h> #include <linux/stat.h> +#include <linux/srcu.h> MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and " + "Josh Triplett <josh@freedesktop.org>"); static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ +static int nfakewriters = 4; /* # fake writer threads */ static int stat_interval; /* Interval between stats, in seconds. */ /* Defaults to "only at end of test". */ static int verbose; /* Print more debug info. */ static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/ -static char *torture_type = "rcu"; /* What to torture. */ +static char *torture_type = "rcu"; /* What RCU implementation to torture. */ module_param(nreaders, int, 0); MODULE_PARM_DESC(nreaders, "Number of RCU reader threads"); +module_param(nfakewriters, int, 0); +MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads"); module_param(stat_interval, int, 0); MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s"); module_param(verbose, bool, 0); @@ -66,7 +73,7 @@ MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs"); module_param(shuffle_interval, int, 0); MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles"); module_param(torture_type, charp, 0); -MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh)"); +MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)"); #define TORTURE_FLAG "-torture:" #define PRINTK_STRING(s) \ @@ -80,6 +87,7 @@ static char printk_buf[4096]; static int nrealreaders; static struct task_struct *writer_task; +static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; static struct task_struct *shuffler_task; @@ -104,11 +112,12 @@ static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = { 0 }; static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1]; -atomic_t n_rcu_torture_alloc; -atomic_t n_rcu_torture_alloc_fail; -atomic_t n_rcu_torture_free; -atomic_t n_rcu_torture_mberror; -atomic_t n_rcu_torture_error; +static atomic_t n_rcu_torture_alloc; +static atomic_t n_rcu_torture_alloc_fail; +static atomic_t n_rcu_torture_free; +static atomic_t n_rcu_torture_mberror; +static atomic_t n_rcu_torture_error; +static struct list_head rcu_torture_removed; /* * Allocate an element from the rcu_tortures pool. @@ -145,7 +154,7 @@ rcu_torture_free(struct rcu_torture *p) struct rcu_random_state { unsigned long rrs_state; - unsigned long rrs_count; + long rrs_count; }; #define RCU_RANDOM_MULT 39916801 /* prime */ @@ -158,7 +167,7 @@ struct rcu_random_state { * Crude but fast random-number generator. Uses a linear congruential * generator, with occasional help from get_random_bytes(). */ -static long +static unsigned long rcu_random(struct rcu_random_state *rrsp) { long refresh; @@ -180,9 +189,11 @@ struct rcu_torture_ops { void (*init)(void); void (*cleanup)(void); int (*readlock)(void); + void (*readdelay)(struct rcu_random_state *rrsp); void (*readunlock)(int idx); int (*completed)(void); void (*deferredfree)(struct rcu_torture *p); + void (*sync)(void); int (*stats)(char *page); char *name; }; @@ -198,6 +209,18 @@ static int rcu_torture_read_lock(void) __acquires(RCU) return 0; } +static void rcu_read_delay(struct rcu_random_state *rrsp) +{ + long delay; + const long longdelay = 200; + + /* We want there to be long-running readers, but not all the time. */ + + delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay); + if (!delay) + udelay(longdelay); +} + static void rcu_torture_read_unlock(int idx) __releases(RCU) { rcu_read_unlock(); @@ -239,13 +262,54 @@ static struct rcu_torture_ops rcu_ops = { .init = NULL, .cleanup = NULL, .readlock = rcu_torture_read_lock, + .readdelay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, .completed = rcu_torture_completed, .deferredfree = rcu_torture_deferred_free, + .sync = synchronize_rcu, .stats = NULL, .name = "rcu" }; +static void rcu_sync_torture_deferred_free(struct rcu_torture *p) +{ + int i; + struct rcu_torture *rp; + struct rcu_torture *rp1; + + cur_ops->sync(); + list_add(&p->rtort_free, &rcu_torture_removed); + list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) { + i = rp->rtort_pipe_count; + if (i > RCU_TORTURE_PIPE_LEN) + i = RCU_TORTURE_PIPE_LEN; + atomic_inc(&rcu_torture_wcount[i]); + if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { + rp->rtort_mbtest = 0; + list_del(&rp->rtort_free); + rcu_torture_free(rp); + } + } +} + +static void rcu_sync_torture_init(void) +{ + INIT_LIST_HEAD(&rcu_torture_removed); +} + +static struct rcu_torture_ops rcu_sync_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = rcu_torture_read_lock, + .readdelay = rcu_read_delay, + .readunlock = rcu_torture_read_unlock, + .completed = rcu_torture_completed, + .deferredfree = rcu_sync_torture_deferred_free, + .sync = synchronize_rcu, + .stats = NULL, + .name = "rcu_sync" +}; + /* * Definitions for rcu_bh torture testing. */ @@ -271,19 +335,176 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p) call_rcu_bh(&p->rtort_rcu, rcu_torture_cb); } +struct rcu_bh_torture_synchronize { + struct rcu_head head; + struct completion completion; +}; + +static void rcu_bh_torture_wakeme_after_cb(struct rcu_head *head) +{ + struct rcu_bh_torture_synchronize *rcu; + + rcu = container_of(head, struct rcu_bh_torture_synchronize, head); + complete(&rcu->completion); +} + +static void rcu_bh_torture_synchronize(void) +{ + struct rcu_bh_torture_synchronize rcu; + + init_completion(&rcu.completion); + call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb); + wait_for_completion(&rcu.completion); +} + static struct rcu_torture_ops rcu_bh_ops = { .init = NULL, .cleanup = NULL, .readlock = rcu_bh_torture_read_lock, + .readdelay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, .completed = rcu_bh_torture_completed, .deferredfree = rcu_bh_torture_deferred_free, + .sync = rcu_bh_torture_synchronize, .stats = NULL, .name = "rcu_bh" }; +static struct rcu_torture_ops rcu_bh_sync_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = rcu_bh_torture_read_lock, + .readdelay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_bh_torture_read_unlock, + .completed = rcu_bh_torture_completed, + .deferredfree = rcu_sync_torture_deferred_free, + .sync = rcu_bh_torture_synchronize, + .stats = NULL, + .name = "rcu_bh_sync" +}; + +/* + * Definitions for srcu torture testing. + */ + +static struct srcu_struct srcu_ctl; + +static void srcu_torture_init(void) +{ + init_srcu_struct(&srcu_ctl); + rcu_sync_torture_init(); +} + +static void srcu_torture_cleanup(void) +{ + synchronize_srcu(&srcu_ctl); + cleanup_srcu_struct(&srcu_ctl); +} + +static int srcu_torture_read_lock(void) +{ + return srcu_read_lock(&srcu_ctl); +} + +static void srcu_read_delay(struct rcu_random_state *rrsp) +{ + long delay; + const long uspertick = 1000000 / HZ; + const long longdelay = 10; + + /* We want there to be long-running readers, but not all the time. */ + + delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick); + if (!delay) + schedule_timeout_interruptible(longdelay); +} + +static void srcu_torture_read_unlock(int idx) +{ + srcu_read_unlock(&srcu_ctl, idx); +} + +static int srcu_torture_completed(void) +{ + return srcu_batches_completed(&srcu_ctl); +} + +static void srcu_torture_synchronize(void) +{ + synchronize_srcu(&srcu_ctl); +} + +static int srcu_torture_stats(char *page) +{ + int cnt = 0; + int cpu; + int idx = srcu_ctl.completed & 0x1; + + cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):", + torture_type, TORTURE_FLAG, idx); + for_each_possible_cpu(cpu) { + cnt += sprintf(&page[cnt], " %d(%d,%d)", cpu, + per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx], + per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]); + } + cnt += sprintf(&page[cnt], "\n"); + return cnt; +} + +static struct rcu_torture_ops srcu_ops = { + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .readdelay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .completed = srcu_torture_completed, + .deferredfree = rcu_sync_torture_deferred_free, + .sync = srcu_torture_synchronize, + .stats = srcu_torture_stats, + .name = "srcu" +}; + +/* + * Definitions for sched torture testing. + */ + +static int sched_torture_read_lock(void) +{ + preempt_disable(); + return 0; +} + +static void sched_torture_read_unlock(int idx) +{ + preempt_enable(); +} + +static int sched_torture_completed(void) +{ + return 0; +} + +static void sched_torture_synchronize(void) +{ + synchronize_sched(); +} + +static struct rcu_torture_ops sched_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = sched_torture_read_lock, + .readdelay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = sched_torture_read_unlock, + .completed = sched_torture_completed, + .deferredfree = rcu_sync_torture_deferred_free, + .sync = sched_torture_synchronize, + .stats = NULL, + .name = "sched" +}; + static struct rcu_torture_ops *torture_ops[] = - { &rcu_ops, &rcu_bh_ops, NULL }; + { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &srcu_ops, + &sched_ops, NULL }; /* * RCU torture writer kthread. Repeatedly substitutes a new structure @@ -330,6 +551,30 @@ rcu_torture_writer(void *arg) } /* + * RCU torture fake writer kthread. Repeatedly calls sync, with a random + * delay between calls. + */ +static int +rcu_torture_fakewriter(void *arg) +{ + DEFINE_RCU_RANDOM(rand); + + VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task started"); + set_user_nice(current, 19); + + do { + schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); + udelay(rcu_random(&rand) & 0x3ff); + cur_ops->sync(); + } while (!kthread_should_stop() && !fullstop); + + VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping"); + while (!kthread_should_stop()) + schedule_timeout_uninterruptible(1); + return 0; +} + +/* * RCU torture reader kthread. Repeatedly dereferences rcu_torture_current, * incrementing the corresponding element of the pipeline array. The * counter in the element should never be greater than 1, otherwise, the @@ -359,7 +604,7 @@ rcu_torture_reader(void *arg) } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - udelay(rcu_random(&rand) & 0x7f); + cur_ops->readdelay(&rand); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { @@ -483,7 +728,7 @@ static int rcu_idle_cpu; /* Force all torture tasks off this CPU */ /* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs. */ -void rcu_torture_shuffle_tasks(void) +static void rcu_torture_shuffle_tasks(void) { cpumask_t tmp_mask = CPU_MASK_ALL; int i; @@ -507,6 +752,12 @@ void rcu_torture_shuffle_tasks(void) set_cpus_allowed(reader_tasks[i], tmp_mask); } + if (fakewriter_tasks != NULL) { + for (i = 0; i < nfakewriters; i++) + if (fakewriter_tasks[i]) + set_cpus_allowed(fakewriter_tasks[i], tmp_mask); + } + if (writer_task) set_cpus_allowed(writer_task, tmp_mask); @@ -540,11 +791,12 @@ rcu_torture_shuffle(void *arg) static inline void rcu_torture_print_module_parms(char *tag) { - printk(KERN_ALERT "%s" TORTURE_FLAG "--- %s: nreaders=%d " + printk(KERN_ALERT "%s" TORTURE_FLAG + "--- %s: nreaders=%d nfakewriters=%d " "stat_interval=%d verbose=%d test_no_idle_hz=%d " "shuffle_interval = %d\n", - torture_type, tag, nrealreaders, stat_interval, verbose, - test_no_idle_hz, shuffle_interval); + torture_type, tag, nrealreaders, nfakewriters, + stat_interval, verbose, test_no_idle_hz, shuffle_interval); } static void @@ -579,6 +831,19 @@ rcu_torture_cleanup(void) } rcu_torture_current = NULL; + if (fakewriter_tasks != NULL) { + for (i = 0; i < nfakewriters; i++) { + if (fakewriter_tasks[i] != NULL) { + VERBOSE_PRINTK_STRING( + "Stopping rcu_torture_fakewriter task"); + kthread_stop(fakewriter_tasks[i]); + } + fakewriter_tasks[i] = NULL; + } + kfree(fakewriter_tasks); + fakewriter_tasks = NULL; + } + if (stats_task != NULL) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task"); kthread_stop(stats_task); @@ -666,7 +931,25 @@ rcu_torture_init(void) writer_task = NULL; goto unwind; } - reader_tasks = kmalloc(nrealreaders * sizeof(reader_tasks[0]), + fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]), + GFP_KERNEL); + if (fakewriter_tasks == NULL) { + VERBOSE_PRINTK_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < nfakewriters; i++) { + VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task"); + fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL, + "rcu_torture_fakewriter"); + if (IS_ERR(fakewriter_tasks[i])) { + firsterr = PTR_ERR(fakewriter_tasks[i]); + VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter"); + fakewriter_tasks[i] = NULL; + goto unwind; + } + } + reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { VERBOSE_PRINTK_ERRSTRING("out of memory"); diff --git a/kernel/srcu.c b/kernel/srcu.c new file mode 100644 index 0000000..3507cab --- /dev/null +++ b/kernel/srcu.c @@ -0,0 +1,258 @@ +/* + * Sleepable 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, 2006 + * + * Author: Paul McKenney <paulmck@us.ibm.com> + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU/ *.txt + * + */ + +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/preempt.h> +#include <linux/rcupdate.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/srcu.h> + +/** + * init_srcu_struct - initialize a sleep-RCU structure + * @sp: structure to initialize. + * + * Must invoke this on a given srcu_struct before passing that srcu_struct + * to any other function. Each srcu_struct represents a separate domain + * of SRCU protection. + */ +int init_srcu_struct(struct srcu_struct *sp) +{ + sp->completed = 0; + mutex_init(&sp->mutex); + sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); + return (sp->per_cpu_ref ? 0 : -ENOMEM); +} + +/* + * srcu_readers_active_idx -- returns approximate number of readers + * active on the specified rank of per-CPU counters. + */ + +static int srcu_readers_active_idx(struct srcu_struct *sp, int idx) +{ + int cpu; + int sum; + + sum = 0; + for_each_possible_cpu(cpu) + sum += per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]; + return sum; +} + +/** + * srcu_readers_active - returns approximate number of readers. + * @sp: which srcu_struct to count active readers (holding srcu_read_lock). + * + * Note that this is not an atomic primitive, and can therefore suffer + * severe errors when invoked on an active srcu_struct. That said, it + * can be useful as an error check at cleanup time. + */ +int srcu_readers_active(struct srcu_struct *sp) +{ + return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1); +} + +/** + * cleanup_srcu_struct - deconstruct a sleep-RCU structure + * @sp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. + */ +void cleanup_srcu_struct(struct srcu_struct *sp) +{ + int sum; + + sum = srcu_readers_active(sp); + WARN_ON(sum); /* Leakage unless caller handles error. */ + if (sum != 0) + return; + free_percpu(sp->per_cpu_ref); + sp->per_cpu_ref = NULL; +} + +/** + * srcu_read_lock - register a new reader for an SRCU-protected structure. + * @sp: srcu_struct in which to register the new reader. + * + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Must be called from process context. + * Returns an index that must be passed to the matching srcu_read_unlock(). + */ +int srcu_read_lock(struct srcu_struct *sp) +{ + int idx; + + preempt_disable(); + idx = sp->completed & 0x1; + barrier(); /* ensure compiler looks -once- at sp->completed. */ + per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]++; + srcu_barrier(); /* ensure compiler won't misorder critical section. */ + preempt_enable(); + return idx; +} + +/** + * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. + * @sp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Removes the count for the old reader from the appropriate per-CPU + * element of the srcu_struct. Note that this may well be a different + * CPU than that which was incremented by the corresponding srcu_read_lock(). + * Must be called from process context. + */ +void srcu_read_unlock(struct srcu_struct *sp, int idx) +{ + preempt_disable(); + srcu_barrier(); /* ensure compiler won't misorder critical section. */ + per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--; + preempt_enable(); +} + +/** + * synchronize_srcu - wait for prior SRCU read-side critical-section completion + * @sp: srcu_struct with which to synchronize. + * + * Flip the completed counter, and wait for the old count to drain to zero. + * As with classic RCU, the updater must use some separate means of + * synchronizing concurrent updates. Can block; must be called from + * process context. + * + * Note that it is illegal to call synchornize_srcu() from the corresponding + * SRCU read-side critical section; doing so will result in deadlock. + * However, it is perfectly legal to call synchronize_srcu() on one + * srcu_struct from some other srcu_struct's read-side critical section. + */ +void synchronize_srcu(struct srcu_struct *sp) +{ + int idx; + + idx = sp->completed; + mutex_lock(&sp->mutex); + + /* + * Check to see if someone else did the work for us while we were + * waiting to acquire the lock. We need -two- advances of + * the counter, not just one. If there was but one, we might have + * shown up -after- our helper's first synchronize_sched(), thus + * having failed to prevent CPU-reordering races with concurrent + * srcu_read_unlock()s on other CPUs (see comment below). So we + * either (1) wait for two or (2) supply the second ourselves. + */ + + if ((sp->completed - idx) >= 2) { + mutex_unlock(&sp->mutex); + return; + } + + synchronize_sched(); /* Force memory barrier on all CPUs. */ + + /* + * The preceding synchronize_sched() ensures that any CPU that + * sees the new value of sp->completed will also see any preceding + * changes to data structures made by this CPU. This prevents + * some other CPU from reordering the accesses in its SRCU + * read-side critical section to precede the corresponding + * srcu_read_lock() -- ensuring that such references will in + * fact be protected. + * + * So it is now safe to do the flip. + */ + + idx = sp->completed & 0x1; + sp->completed++; + + synchronize_sched(); /* Force memory barrier on all CPUs. */ + + /* + * At this point, because of the preceding synchronize_sched(), + * all srcu_read_lock() calls using the old counters have completed. + * Their corresponding critical sections might well be still + * executing, but the srcu_read_lock() primitives themselves + * will have finished executing. + */ + + while (srcu_readers_active_idx(sp, idx)) + schedule_timeout_interruptible(1); + + synchronize_sched(); /* Force memory barrier on all CPUs. */ + + /* + * The preceding synchronize_sched() forces all srcu_read_unlock() + * primitives that were executing concurrently with the preceding + * for_each_possible_cpu() loop to have completed by this point. + * More importantly, it also forces the corresponding SRCU read-side + * critical sections to have also completed, and the corresponding + * references to SRCU-protected data items to be dropped. + * + * Note: + * + * Despite what you might think at first glance, the + * preceding synchronize_sched() -must- be within the + * critical section ended by the following mutex_unlock(). + * Otherwise, a task taking the early exit can race + * with a srcu_read_unlock(), which might have executed + * just before the preceding srcu_readers_active() check, + * and whose CPU might have reordered the srcu_read_unlock() + * with the preceding critical section. In this case, there + * is nothing preventing the synchronize_sched() task that is + * taking the early exit from freeing a data structure that + * is still being referenced (out of order) by the task + * doing the srcu_read_unlock(). + * + * Alternatively, the comparison with "2" on the early exit + * could be changed to "3", but this increases synchronize_srcu() + * latency for bulk loads. So the current code is preferred. + */ + + mutex_unlock(&sp->mutex); +} + +/** + * srcu_batches_completed - return batches completed. + * @sp: srcu_struct on which to report batch completion. + * + * Report the number of batches, correlated with, but not necessarily + * precisely the same as, the number of grace periods that have elapsed. + */ + +long srcu_batches_completed(struct srcu_struct *sp) +{ + return sp->completed; +} + +EXPORT_SYMBOL_GPL(init_srcu_struct); +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(srcu_read_lock); +EXPORT_SYMBOL_GPL(srcu_read_unlock); +EXPORT_SYMBOL_GPL(synchronize_srcu); +EXPORT_SYMBOL_GPL(srcu_batches_completed); +EXPORT_SYMBOL_GPL(srcu_readers_active); diff --git a/kernel/sys.c b/kernel/sys.c index 2314867..98489d8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -153,7 +153,7 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl, /* * Atomic notifier chain routines. Registration and unregistration - * use a mutex, and call_chain is synchronized by RCU (no locks). + * use a spinlock, and call_chain is synchronized by RCU (no locks). */ /** @@ -401,6 +401,129 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh, EXPORT_SYMBOL_GPL(raw_notifier_call_chain); +/* + * SRCU notifier chain routines. Registration and unregistration + * use a mutex, and call_chain is synchronized by SRCU (no locks). + */ + +/** + * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to an SRCU notifier chain. + * Must be called in process context. + * + * Currently always returns zero. + */ + +int srcu_notifier_chain_register(struct srcu_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call mutex_lock(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_register(&nh->head, n); + + mutex_lock(&nh->mutex); + ret = notifier_chain_register(&nh->head, n); + mutex_unlock(&nh->mutex); + return ret; +} + +EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); + +/** + * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @n: Entry to remove from notifier chain + * + * Removes a notifier from an SRCU notifier chain. + * Must be called from process context. + * + * Returns zero on success or %-ENOENT on failure. + */ +int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, + struct notifier_block *n) +{ + int ret; + + /* + * This code gets used during boot-up, when task switching is + * not yet working and interrupts must remain disabled. At + * such times we must not call mutex_lock(). + */ + if (unlikely(system_state == SYSTEM_BOOTING)) + return notifier_chain_unregister(&nh->head, n); + + mutex_lock(&nh->mutex); + ret = notifier_chain_unregister(&nh->head, n); + mutex_unlock(&nh->mutex); + synchronize_srcu(&nh->srcu); + return ret; +} + +EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); + +/** + * srcu_notifier_call_chain - Call functions in an SRCU notifier chain + * @nh: Pointer to head of the SRCU notifier chain + * @val: Value passed unmodified to notifier function + * @v: Pointer passed unmodified to notifier function + * + * Calls each function in a notifier chain in turn. The functions + * run in a process context, so they are allowed to block. + * + * If the return value of the notifier can be and'ed + * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain + * will return immediately, with the return value of + * the notifier function which halted execution. + * Otherwise the return value is the return value + * of the last notifier function called. + */ + +int srcu_notifier_call_chain(struct srcu_notifier_head *nh, + unsigned long val, void *v) +{ + int ret; + int idx; + + idx = srcu_read_lock(&nh->srcu); + ret = notifier_call_chain(&nh->head, val, v); + srcu_read_unlock(&nh->srcu, idx); + return ret; +} + +EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); + +/** + * srcu_init_notifier_head - Initialize an SRCU notifier head + * @nh: Pointer to head of the srcu notifier chain + * + * Unlike other sorts of notifier heads, SRCU notifier heads require + * dynamic initialization. Be sure to call this routine before + * calling any of the other SRCU notifier routines for this head. + * + * If an SRCU notifier head is deallocated, it must first be cleaned + * up by calling srcu_cleanup_notifier_head(). Otherwise the head's + * per-cpu data (used by the SRCU mechanism) will leak. + */ + +void srcu_init_notifier_head(struct srcu_notifier_head *nh) +{ + mutex_init(&nh->mutex); + if (init_srcu_struct(&nh->srcu) < 0) + BUG(); + nh->head = NULL; +} + +EXPORT_SYMBOL_GPL(srcu_init_notifier_head); + /** * register_reboot_notifier - Register function to be called at reboot time * @nb: Info about notifier function to be called |